Repository Public Research preview
1{2 "created_at": "2026-11-10T16:35:40Z",3 "git": {4 "commit": "cc9bca8eddf181414db3d2d4228a5ebd08c91242",5 "branch": "main",6 "dirty": false7 },8 "libraries": {9 "python": "3.14.4",10 "torch": "2.12.0",11 "numpy": "2.5.4",12 "anthropic": "2.3.0",13 "transformers": "5.8.1",14 "sentencepiece": "0.2.2",15 "lxml": "6.1.3",16 "pyarrow": "24.0.0",17 "sacrebleu": "2.6.0",18 "datasketch": "2.0.0",19 "rapidfuzz": "3.14.6"20 },21 "hardware": {22 "platform": "macOS-27.0-arm64-arm-64bit-Mach-O",23 "machine": "arm64",24 "cpu_count": 18,25 "chip": "Apple M5 Max",26 "ram_gb": 48.0,27 "torch_mps": true,28 "torch_cuda": false29 },30 "n_pairs": 15649,31 "systems": {32 "B0_identity": {33 "overall": {34 "n": 15649,35 "chrf": {36 "mean": 68.9129812756793,37 "ci_low": 68.34795520986935,38 "ci_high": 69.47238105866612,39 "n_items": 15649,40 "n_groups": 65241 },42 "edit_sim": {43 "mean": 0.6820733818847613,44 "ci_low": 0.6768981315405241,45 "ci_high": 0.6872363326859595,46 "n_items": 15649,47 "n_groups": 65248 },49 "rougeL": {50 "mean": 0.6888943478429753,51 "ci_low": 0.6830376087423201,52 "ci_high": 0.6948320844236089,53 "n_items": 15649,54 "n_groups": 65255 },56 "exact_match": {57 "mean": 0.0,58 "ci_low": 0.0,59 "ci_high": 0.0,60 "n_items": 15649,61 "n_groups": 65262 },63 "number_recall": {64 "mean": 1.0,65 "ci_low": 1.0,66 "ci_high": 1.0,67 "n_items": 15649,68 "n_groups": 65269 },70 "placeholders_exact": {71 "mean": 1.0,72 "ci_low": 1.0,73 "ci_high": 1.0,74 "n_items": 15649,75 "n_groups": 65276 }77 },78 "by_variant": {79 "A": {80 "n": 2664,81 "chrf": {82 "mean": 67.71928207725095,83 "ci_low": 67.08092807371821,84 "ci_high": 68.38964513770549,85 "n_items": 2664,86 "n_groups": 63087 },88 "edit_sim": {89 "mean": 0.6661221796081508,90 "ci_low": 0.660085551874572,91 "ci_high": 0.6727349072348292,92 "n_items": 2664,93 "n_groups": 63094 },95 "rougeL": {96 "mean": 0.6695247207760138,97 "ci_low": 0.6628594493046654,98 "ci_high": 0.6764635425596528,99 "n_items": 2664,100 "n_groups": 630101 },102 "exact_match": {103 "mean": 0.0,104 "ci_low": 0.0,105 "ci_high": 0.0,106 "n_items": 2664,107 "n_groups": 630108 },109 "number_recall": {110 "mean": 1.0,111 "ci_low": 1.0,112 "ci_high": 1.0,113 "n_items": 2664,114 "n_groups": 630115 },116 "placeholders_exact": {117 "mean": 1.0,118 "ci_low": 1.0,119 "ci_high": 1.0,120 "n_items": 2664,121 "n_groups": 630122 }123 },124 "B": {125 "n": 2539,126 "chrf": {127 "mean": 76.89547506755116,128 "ci_low": 76.27097135629506,129 "ci_high": 77.50878366941032,130 "n_items": 2539,131 "n_groups": 614132 },133 "edit_sim": {134 "mean": 0.771782705413539,135 "ci_low": 0.7657130628335964,136 "ci_high": 0.7779320240915212,137 "n_items": 2539,138 "n_groups": 614139 },140 "rougeL": {141 "mean": 0.7803091660310831,142 "ci_low": 0.7738700652116886,143 "ci_high": 0.7869305162021843,144 "n_items": 2539,145 "n_groups": 614146 },147 "exact_match": {148 "mean": 0.0,149 "ci_low": 0.0,150 "ci_high": 0.0,151 "n_items": 2539,152 "n_groups": 614153 },154 "number_recall": {155 "mean": 1.0,156 "ci_low": 1.0,157 "ci_high": 1.0,158 "n_items": 2539,159 "n_groups": 614160 },161 "placeholders_exact": {162 "mean": 1.0,163 "ci_low": 1.0,164 "ci_high": 1.0,165 "n_items": 2539,166 "n_groups": 614167 }168 },169 "C": {170 "n": 2663,171 "chrf": {172 "mean": 73.00177970610315,173 "ci_low": 72.40914365157718,174 "ci_high": 73.62182449329212,175 "n_items": 2663,176 "n_groups": 638177 },178 "edit_sim": {179 "mean": 0.7425871285765981,180 "ci_low": 0.7370418429933602,181 "ci_high": 0.7484286341658202,182 "n_items": 2663,183 "n_groups": 638184 },185 "rougeL": {186 "mean": 0.764669369162413,187 "ci_low": 0.7586148350919166,188 "ci_high": 0.7709626650446721,189 "n_items": 2663,190 "n_groups": 638191 },192 "exact_match": {193 "mean": 0.0,194 "ci_low": 0.0,195 "ci_high": 0.0,196 "n_items": 2663,197 "n_groups": 638198 },199 "number_recall": {200 "mean": 1.0,201 "ci_low": 1.0,202 "ci_high": 1.0,203 "n_items": 2663,204 "n_groups": 638205 },206 "placeholders_exact": {207 "mean": 1.0,208 "ci_low": 1.0,209 "ci_high": 1.0,210 "n_items": 2663,211 "n_groups": 638212 }213 },214 "D": {215 "n": 2708,216 "chrf": {217 "mean": 68.71882183403973,218 "ci_low": 68.10123807979738,219 "ci_high": 69.34503345032982,220 "n_items": 2708,221 "n_groups": 638222 },223 "edit_sim": {224 "mean": 0.686751331129231,225 "ci_low": 0.6810473096255292,226 "ci_high": 0.6925233810067101,227 "n_items": 2708,228 "n_groups": 638229 },230 "rougeL": {231 "mean": 0.6882622206773306,232 "ci_low": 0.6822084647328402,233 "ci_high": 0.6945202520536766,234 "n_items": 2708,235 "n_groups": 638236 },237 "exact_match": {238 "mean": 0.0,239 "ci_low": 0.0,240 "ci_high": 0.0,241 "n_items": 2708,242 "n_groups": 638243 },244 "number_recall": {245 "mean": 1.0,246 "ci_low": 1.0,247 "ci_high": 1.0,248 "n_items": 2708,249 "n_groups": 638250 },251 "placeholders_exact": {252 "mean": 1.0,253 "ci_low": 1.0,254 "ci_high": 1.0,255 "n_items": 2708,256 "n_groups": 638257 }258 },259 "E": {260 "n": 5075,261 "chrf": {262 "mean": 63.504070236229346,263 "ci_low": 62.886720786482734,264 "ci_high": 64.1286830734911,265 "n_items": 5075,266 "n_groups": 623267 },268 "edit_sim": {269 "mean": 0.6113159506396262,270 "ci_low": 0.6058185595924279,271 "ci_high": 0.6169780313798546,272 "n_items": 5075,273 "n_groups": 623274 },275 "rougeL": {276 "mean": 0.6139034870976909,277 "ci_low": 0.6073302333577092,278 "ci_high": 0.6207091993555574,279 "n_items": 5075,280 "n_groups": 623281 },282 "exact_match": {283 "mean": 0.0,284 "ci_low": 0.0,285 "ci_high": 0.0,286 "n_items": 5075,287 "n_groups": 623288 },289 "number_recall": {290 "mean": 1.0,291 "ci_low": 1.0,292 "ci_high": 1.0,293 "n_items": 5075,294 "n_groups": 623295 },296 "placeholders_exact": {297 "mean": 1.0,298 "ci_low": 1.0,299 "ci_high": 1.0,300 "n_items": 5075,301 "n_groups": 623302 }303 }304 },305 "by_discipline": {306 "biomedicine": {307 "n": 2154,308 "chrf": {309 "mean": 69.16503028449597,310 "ci_low": 68.04521336379203,311 "ci_high": 70.25451665696339,312 "n_items": 2154,313 "n_groups": 244314 },315 "edit_sim": {316 "mean": 0.6786197955434704,317 "ci_low": 0.6700133673330664,318 "ci_high": 0.6875122424837307,319 "n_items": 2154,320 "n_groups": 244321 },322 "rougeL": {323 "mean": 0.6853804516172162,324 "ci_low": 0.675348945098432,325 "ci_high": 0.6957826620415155,326 "n_items": 2154,327 "n_groups": 244328 },329 "exact_match": {330 "mean": 0.0,331 "ci_low": 0.0,332 "ci_high": 0.0,333 "n_items": 2154,334 "n_groups": 244335 },336 "number_recall": {337 "mean": 1.0,338 "ci_low": 1.0,339 "ci_high": 1.0,340 "n_items": 2154,341 "n_groups": 244342 },343 "placeholders_exact": {344 "mean": 1.0,345 "ci_low": 1.0,346 "ci_high": 1.0,347 "n_items": 2154,348 "n_groups": 244349 }350 },351 "chemistry": {352 "n": 837,353 "chrf": {354 "mean": 72.53946094912628,355 "ci_low": 71.03198848687634,356 "ci_high": 74.13928260298343,357 "n_items": 837,358 "n_groups": 13359 },360 "edit_sim": {361 "mean": 0.6996694950165775,362 "ci_low": 0.6830507057675218,363 "ci_high": 0.7196285982473057,364 "n_items": 837,365 "n_groups": 13366 },367 "rougeL": {368 "mean": 0.7175254585138302,369 "ci_low": 0.7018281806971526,370 "ci_high": 0.7365774703788974,371 "n_items": 837,372 "n_groups": 13373 },374 "exact_match": {375 "mean": 0.0,376 "ci_low": 0.0,377 "ci_high": 0.0,378 "n_items": 837,379 "n_groups": 13380 },381 "number_recall": {382 "mean": 1.0,383 "ci_low": 1.0,384 "ci_high": 1.0,385 "n_items": 837,386 "n_groups": 13387 },388 "placeholders_exact": {389 "mean": 1.0,390 "ci_low": 1.0,391 "ci_high": 1.0,392 "n_items": 837,393 "n_groups": 13394 }395 },396 "computer_science": {397 "n": 1375,398 "chrf": {399 "mean": 69.14855096540924,400 "ci_low": 67.40054571413997,401 "ci_high": 70.76681019451198,402 "n_items": 1375,403 "n_groups": 20404 },405 "edit_sim": {406 "mean": 0.687839023367926,407 "ci_low": 0.6695816037959246,408 "ci_high": 0.7040186810697247,409 "n_items": 1375,410 "n_groups": 20411 },412 "rougeL": {413 "mean": 0.6910357646587281,414 "ci_low": 0.6705902537165145,415 "ci_high": 0.7081528470026383,416 "n_items": 1375,417 "n_groups": 20418 },419 "exact_match": {420 "mean": 0.0,421 "ci_low": 0.0,422 "ci_high": 0.0,423 "n_items": 1375,424 "n_groups": 20425 },426 "number_recall": {427 "mean": 1.0,428 "ci_low": 1.0,429 "ci_high": 1.0,430 "n_items": 1375,431 "n_groups": 20432 },433 "placeholders_exact": {434 "mean": 1.0,435 "ci_low": 1.0,436 "ci_high": 1.0,437 "n_items": 1375,438 "n_groups": 20439 }440 },441 "economics": {442 "n": 1944,443 "chrf": {444 "mean": 67.69725202403306,445 "ci_low": 66.77163833809269,446 "ci_high": 68.53327326088065,447 "n_items": 1944,448 "n_groups": 103449 },450 "edit_sim": {451 "mean": 0.6760694125807966,452 "ci_low": 0.666791345165578,453 "ci_high": 0.6851982879429593,454 "n_items": 1944,455 "n_groups": 103456 },457 "rougeL": {458 "mean": 0.6784917131734737,459 "ci_low": 0.6670779808452865,460 "ci_high": 0.6894993927636344,461 "n_items": 1944,462 "n_groups": 103463 },464 "exact_match": {465 "mean": 0.0,466 "ci_low": 0.0,467 "ci_high": 0.0,468 "n_items": 1944,469 "n_groups": 103470 },471 "number_recall": {472 "mean": 1.0,473 "ci_low": 1.0,474 "ci_high": 1.0,475 "n_items": 1944,476 "n_groups": 103477 },478 "placeholders_exact": {479 "mean": 1.0,480 "ci_low": 1.0,481 "ci_high": 1.0,482 "n_items": 1944,483 "n_groups": 103484 }485 },486 "engineering": {487 "n": 1296,488 "chrf": {489 "mean": 66.09623846240457,490 "ci_low": 64.60152384096747,491 "ci_high": 67.81277715777485,492 "n_items": 1296,493 "n_groups": 17494 },495 "edit_sim": {496 "mean": 0.6540141018333105,497 "ci_low": 0.6401051915673123,498 "ci_high": 0.6688682482317372,499 "n_items": 1296,500 "n_groups": 17501 },502 "rougeL": {503 "mean": 0.6605179571596008,504 "ci_low": 0.6466366474444584,505 "ci_high": 0.6763828551658173,506 "n_items": 1296,507 "n_groups": 17508 },509 "exact_match": {510 "mean": 0.0,511 "ci_low": 0.0,512 "ci_high": 0.0,513 "n_items": 1296,514 "n_groups": 17515 },516 "number_recall": {517 "mean": 1.0,518 "ci_low": 1.0,519 "ci_high": 1.0,520 "n_items": 1296,521 "n_groups": 17522 },523 "placeholders_exact": {524 "mean": 1.0,525 "ci_low": 1.0,526 "ci_high": 1.0,527 "n_items": 1296,528 "n_groups": 17529 }530 },531 "finance": {532 "n": 2043,533 "chrf": {534 "mean": 67.7346855785838,535 "ci_low": 66.51969483947565,536 "ci_high": 69.14752599188147,537 "n_items": 2043,538 "n_groups": 51539 },540 "edit_sim": {541 "mean": 0.6728254242223485,542 "ci_low": 0.6603299007855545,543 "ci_high": 0.6871306386530238,544 "n_items": 2043,545 "n_groups": 51546 },547 "rougeL": {548 "mean": 0.6779675010033517,549 "ci_low": 0.6640612577268024,550 "ci_high": 0.6939138338557648,551 "n_items": 2043,552 "n_groups": 51553 },554 "exact_match": {555 "mean": 0.0,556 "ci_low": 0.0,557 "ci_high": 0.0,558 "n_items": 2043,559 "n_groups": 51560 },561 "number_recall": {562 "mean": 1.0,563 "ci_low": 1.0,564 "ci_high": 1.0,565 "n_items": 2043,566 "n_groups": 51567 },568 "placeholders_exact": {569 "mean": 1.0,570 "ci_low": 1.0,571 "ci_high": 1.0,572 "n_items": 2043,573 "n_groups": 51574 }575 },576 "general_reference": {577 "n": 118,578 "chrf": {579 "mean": 76.72096212721462,580 "ci_low": 60.71520977444342,581 "ci_high": 78.36641330366774,582 "n_items": 118,583 "n_groups": 2584 },585 "edit_sim": {586 "mean": 0.7974938099395277,587 "ci_low": 0.6091977626097322,588 "ci_high": 0.816851347515488,589 "n_items": 118,590 "n_groups": 2591 },592 "rougeL": {593 "mean": 0.8231653433964996,594 "ci_low": 0.6186940008227512,595 "ci_high": 0.8441857617919317,596 "n_items": 118,597 "n_groups": 2598 },599 "exact_match": {600 "mean": 0.0,601 "ci_low": 0.0,602 "ci_high": 0.0,603 "n_items": 118,604 "n_groups": 2605 },606 "number_recall": {607 "mean": 1.0,608 "ci_low": 1.0,609 "ci_high": 1.0,610 "n_items": 118,611 "n_groups": 2612 },613 "placeholders_exact": {614 "mean": 1.0,615 "ci_low": 1.0,616 "ci_high": 1.0,617 "n_items": 118,618 "n_groups": 2619 }620 },621 "humanities": {622 "n": 263,623 "chrf": {624 "mean": 64.2525187986508,625 "ci_low": 60.38757940342256,626 "ci_high": 64.77673000145495,627 "n_items": 263,628 "n_groups": 3629 },630 "edit_sim": {631 "mean": 0.662169427286415,632 "ci_low": 0.6231751708140568,633 "ci_high": 0.665415115533,634 "n_items": 263,635 "n_groups": 3636 },637 "rougeL": {638 "mean": 0.6685988194909697,639 "ci_low": 0.6230506022139842,640 "ci_high": 0.6754235269082698,641 "n_items": 263,642 "n_groups": 3643 },644 "exact_match": {645 "mean": 0.0,646 "ci_low": 0.0,647 "ci_high": 0.0,648 "n_items": 263,649 "n_groups": 3650 },651 "number_recall": {652 "mean": 1.0,653 "ci_low": 1.0,654 "ci_high": 1.0,655 "n_items": 263,656 "n_groups": 3657 },658 "placeholders_exact": {659 "mean": 1.0,660 "ci_low": 1.0,661 "ci_high": 1.0,662 "n_items": 263,663 "n_groups": 3664 }665 },666 "life_sciences": {667 "n": 1874,668 "chrf": {669 "mean": 71.84266695395003,670 "ci_low": 70.14174991593757,671 "ci_high": 73.37998126566826,672 "n_items": 1874,673 "n_groups": 143674 },675 "edit_sim": {676 "mean": 0.7062629192375465,677 "ci_low": 0.6937101341466857,678 "ci_high": 0.7192633780532487,679 "n_items": 1874,680 "n_groups": 143681 },682 "rougeL": {683 "mean": 0.7165965439085322,684 "ci_low": 0.7029742961521294,685 "ci_high": 0.7300192507482427,686 "n_items": 1874,687 "n_groups": 143688 },689 "exact_match": {690 "mean": 0.0,691 "ci_low": 0.0,692 "ci_high": 0.0,693 "n_items": 1874,694 "n_groups": 143695 },696 "number_recall": {697 "mean": 1.0,698 "ci_low": 1.0,699 "ci_high": 1.0,700 "n_items": 1874,701 "n_groups": 143702 },703 "placeholders_exact": {704 "mean": 1.0,705 "ci_low": 1.0,706 "ci_high": 1.0,707 "n_items": 1874,708 "n_groups": 143709 }710 },711 "mathematics": {712 "n": 712,713 "chrf": {714 "mean": 67.78527452308505,715 "ci_low": 64.9571857317589,716 "ci_high": 71.09473695721078,717 "n_items": 712,718 "n_groups": 5719 },720 "edit_sim": {721 "mean": 0.6857396829160551,722 "ci_low": 0.664535009727461,723 "ci_high": 0.70632068738845,724 "n_items": 712,725 "n_groups": 5726 },727 "rougeL": {728 "mean": 0.6810397100604912,729 "ci_low": 0.6563514173744496,730 "ci_high": 0.7161614005661232,731 "n_items": 712,732 "n_groups": 5733 },734 "exact_match": {735 "mean": 0.0,736 "ci_low": 0.0,737 "ci_high": 0.0,738 "n_items": 712,739 "n_groups": 5740 },741 "number_recall": {742 "mean": 1.0,743 "ci_low": 1.0,744 "ci_high": 1.0,745 "n_items": 712,746 "n_groups": 5747 },748 "placeholders_exact": {749 "mean": 1.0,750 "ci_low": 1.0,751 "ci_high": 1.0,752 "n_items": 712,753 "n_groups": 5754 }755 },756 "other": {757 "n": 669,758 "chrf": {759 "mean": 68.46409725328678,760 "ci_low": 65.75270014059473,761 "ci_high": 71.91319657778081,762 "n_items": 669,763 "n_groups": 13764 },765 "edit_sim": {766 "mean": 0.670302257664901,767 "ci_low": 0.648439704521576,768 "ci_high": 0.6991288018823857,769 "n_items": 669,770 "n_groups": 13771 },772 "rougeL": {773 "mean": 0.6763987344396003,774 "ci_low": 0.653031200271687,775 "ci_high": 0.7073705744433337,776 "n_items": 669,777 "n_groups": 13778 },779 "exact_match": {780 "mean": 0.0,781 "ci_low": 0.0,782 "ci_high": 0.0,783 "n_items": 669,784 "n_groups": 13785 },786 "number_recall": {787 "mean": 1.0,788 "ci_low": 1.0,789 "ci_high": 1.0,790 "n_items": 669,791 "n_groups": 13792 },793 "placeholders_exact": {794 "mean": 1.0,795 "ci_low": 1.0,796 "ci_high": 1.0,797 "n_items": 669,798 "n_groups": 13799 }800 },801 "social_sciences": {802 "n": 1536,803 "chrf": {804 "mean": 68.51093660035752,805 "ci_low": 66.52374247901957,806 "ci_high": 70.02463640104527,807 "n_items": 1536,808 "n_groups": 29809 },810 "edit_sim": {811 "mean": 0.6812046328899303,812 "ci_low": 0.663552641004157,813 "ci_high": 0.6970478203115381,814 "n_items": 1536,815 "n_groups": 29816 },817 "rougeL": {818 "mean": 0.6864758081862351,819 "ci_low": 0.6663589429469002,820 "ci_high": 0.7037329755597199,821 "n_items": 1536,822 "n_groups": 29823 },824 "exact_match": {825 "mean": 0.0,826 "ci_low": 0.0,827 "ci_high": 0.0,828 "n_items": 1536,829 "n_groups": 29830 },831 "number_recall": {832 "mean": 1.0,833 "ci_low": 1.0,834 "ci_high": 1.0,835 "n_items": 1536,836 "n_groups": 29837 },838 "placeholders_exact": {839 "mean": 1.0,840 "ci_low": 1.0,841 "ci_high": 1.0,842 "n_items": 1536,843 "n_groups": 29844 }845 },846 "statistics": {847 "n": 828,848 "chrf": {849 "mean": 70.18574607682088,850 "ci_low": 67.06751605389542,851 "ci_high": 73.23227138791293,852 "n_items": 828,853 "n_groups": 9854 },855 "edit_sim": {856 "mean": 0.6876244118376665,857 "ci_low": 0.6597887039510572,858 "ci_high": 0.7145837790038773,859 "n_items": 828,860 "n_groups": 9861 },862 "rougeL": {863 "mean": 0.7072869714767691,864 "ci_low": 0.6759491489159473,865 "ci_high": 0.7372880225433048,866 "n_items": 828,867 "n_groups": 9868 },869 "exact_match": {870 "mean": 0.0,871 "ci_low": 0.0,872 "ci_high": 0.0,873 "n_items": 828,874 "n_groups": 9875 },876 "number_recall": {877 "mean": 1.0,878 "ci_low": 1.0,879 "ci_high": 1.0,880 "n_items": 828,881 "n_groups": 9882 },883 "placeholders_exact": {884 "mean": 1.0,885 "ci_low": 1.0,886 "ci_high": 1.0,887 "n_items": 828,888 "n_groups": 9889 }890 }891 },892 "by_era": {893 "1900-1949": {894 "n": 1164,895 "chrf": {896 "mean": 64.93605658192583,897 "ci_low": 62.5252524755676,898 "ci_high": 68.25752704008018,899 "n_items": 1164,900 "n_groups": 18901 },902 "edit_sim": {903 "mean": 0.6637202369019892,904 "ci_low": 0.6386645524723538,905 "ci_high": 0.7035693994849358,906 "n_items": 1164,907 "n_groups": 18908 },909 "rougeL": {910 "mean": 0.6703085262092002,911 "ci_low": 0.6432787500968075,912 "ci_high": 0.7143859978254608,913 "n_items": 1164,914 "n_groups": 18915 },916 "exact_match": {917 "mean": 0.0,918 "ci_low": 0.0,919 "ci_high": 0.0,920 "n_items": 1164,921 "n_groups": 18922 },923 "number_recall": {924 "mean": 1.0,925 "ci_low": 1.0,926 "ci_high": 1.0,927 "n_items": 1164,928 "n_groups": 18929 },930 "placeholders_exact": {931 "mean": 1.0,932 "ci_low": 1.0,933 "ci_high": 1.0,934 "n_items": 1164,935 "n_groups": 18936 }937 },938 "1950-1979": {939 "n": 206,940 "chrf": {941 "mean": 63.63596494753569,942 "ci_low": 61.031733452798335,943 "ci_high": 64.26349060891819,944 "n_items": 206,945 "n_groups": 2946 },947 "edit_sim": {948 "mean": 0.6566791793799391,949 "ci_low": 0.6204250443447361,950 "ci_high": 0.6654151155330001,951 "n_items": 206,952 "n_groups": 2953 },954 "rougeL": {955 "mean": 0.6600656042163887,956 "ci_low": 0.625490798905545,957 "ci_high": 0.6683968826045437,958 "n_items": 206,959 "n_groups": 2960 },961 "exact_match": {962 "mean": 0.0,963 "ci_low": 0.0,964 "ci_high": 0.0,965 "n_items": 206,966 "n_groups": 2967 },968 "number_recall": {969 "mean": 1.0,970 "ci_low": 1.0,971 "ci_high": 1.0,972 "n_items": 206,973 "n_groups": 2974 },975 "placeholders_exact": {976 "mean": 1.0,977 "ci_low": 1.0,978 "ci_high": 1.0,979 "n_items": 206,980 "n_groups": 2981 }982 },983 "1980-1999": {984 "n": 151,985 "chrf": {986 "mean": 64.23427197790915,987 "ci_low": 62.80825994875232,988 "ci_high": 79.3356052855077,989 "n_items": 151,990 "n_groups": 4991 },992 "edit_sim": {993 "mean": 0.6716063119040058,994 "ci_low": 0.6588758265992047,995 "ci_high": 0.806759481208687,996 "n_items": 151,997 "n_groups": 4998 },999 "rougeL": {1000 "mean": 0.6691370817152577,1001 "ci_low": 0.6567162835594913,1002 "ci_high": 0.7967001965349463,1003 "n_items": 151,1004 "n_groups": 41005 },1006 "exact_match": {1007 "mean": 0.0,1008 "ci_low": 0.0,1009 "ci_high": 0.0,1010 "n_items": 151,1011 "n_groups": 41012 },1013 "number_recall": {1014 "mean": 1.0,1015 "ci_low": 1.0,1016 "ci_high": 1.0,1017 "n_items": 151,1018 "n_groups": 41019 },1020 "placeholders_exact": {1021 "mean": 1.0,1022 "ci_low": 1.0,1023 "ci_high": 1.0,1024 "n_items": 151,1025 "n_groups": 41026 }1027 },1028 "2000-2009": {1029 "n": 1545,1030 "chrf": {1031 "mean": 69.8344025489106,1032 "ci_low": 68.2669306268874,1033 "ci_high": 71.43028364985794,1034 "n_items": 1545,1035 "n_groups": 691036 },1037 "edit_sim": {1038 "mean": 0.6929947710793917,1039 "ci_low": 0.6778569961596331,1040 "ci_high": 0.7086765381764918,1041 "n_items": 1545,1042 "n_groups": 691043 },1044 "rougeL": {1045 "mean": 0.7002250682499428,1046 "ci_low": 0.684923981187482,1047 "ci_high": 0.7162556190316847,1048 "n_items": 1545,1049 "n_groups": 691050 },1051 "exact_match": {1052 "mean": 0.0,1053 "ci_low": 0.0,1054 "ci_high": 0.0,1055 "n_items": 1545,1056 "n_groups": 691057 },1058 "number_recall": {1059 "mean": 1.0,1060 "ci_low": 1.0,1061 "ci_high": 1.0,1062 "n_items": 1545,1063 "n_groups": 691064 },1065 "placeholders_exact": {1066 "mean": 1.0,1067 "ci_low": 1.0,1068 "ci_high": 1.0,1069 "n_items": 1545,1070 "n_groups": 691071 }1072 },1073 "2010-2017": {1074 "n": 12583,1075 "chrf": {1076 "mean": 69.31027086830008,1077 "ci_low": 68.75833653575201,1078 "ci_high": 69.86513777915589,1079 "n_items": 12583,1080 "n_groups": 5591081 },1082 "edit_sim": {1083 "mean": 0.6829715180794153,1084 "ci_low": 0.6773858067072651,1085 "ci_high": 0.6880365145997545,1086 "n_items": 12583,1087 "n_groups": 5591088 },1089 "rougeL": {1090 "mean": 0.689931461546012,1091 "ci_low": 0.6838368952818058,1092 "ci_high": 0.6959941708637488,1093 "n_items": 12583,1094 "n_groups": 5591095 },1096 "exact_match": {1097 "mean": 0.0,1098 "ci_low": 0.0,1099 "ci_high": 0.0,1100 "n_items": 12583,1101 "n_groups": 5591102 },1103 "number_recall": {1104 "mean": 1.0,1105 "ci_low": 1.0,1106 "ci_high": 1.0,1107 "n_items": 12583,1108 "n_groups": 5591109 },1110 "placeholders_exact": {1111 "mean": 1.0,1112 "ci_low": 1.0,1113 "ci_high": 1.0,1114 "n_items": 12583,1115 "n_groups": 5591116 }1117 }1118 },1119 "by_role": {1120 "abstract": {1121 "n": 1255,1122 "chrf": {1123 "mean": 69.67685710470836,1124 "ci_low": 68.79618409933362,1125 "ci_high": 70.63505534263449,1126 "n_items": 1255,1127 "n_groups": 1951128 },1129 "edit_sim": {1130 "mean": 0.6794451930099601,1131 "ci_low": 0.6697648300846006,1132 "ci_high": 0.6898289376456963,1133 "n_items": 1255,1134 "n_groups": 1951135 },1136 "rougeL": {1137 "mean": 0.678871157184743,1138 "ci_low": 0.669391040308309,1139 "ci_high": 0.6892747227152723,1140 "n_items": 1255,1141 "n_groups": 1951142 },1143 "exact_match": {1144 "mean": 0.0,1145 "ci_low": 0.0,1146 "ci_high": 0.0,1147 "n_items": 1255,1148 "n_groups": 1951149 },1150 "number_recall": {1151 "mean": 1.0,1152 "ci_low": 1.0,1153 "ci_high": 1.0,1154 "n_items": 1255,1155 "n_groups": 1951156 },1157 "placeholders_exact": {1158 "mean": 1.0,1159 "ci_low": 1.0,1160 "ci_high": 1.0,1161 "n_items": 1255,1162 "n_groups": 1951163 }1164 },1165 "background": {1166 "n": 964,1167 "chrf": {1168 "mean": 69.64637262418452,1169 "ci_low": 68.57637711538662,1170 "ci_high": 70.7842943247679,1171 "n_items": 964,1172 "n_groups": 841173 },1174 "edit_sim": {1175 "mean": 0.6891397594383877,1176 "ci_low": 0.6763321909534497,1177 "ci_high": 0.7015813941867909,1178 "n_items": 964,1179 "n_groups": 841180 },1181 "rougeL": {1182 "mean": 0.6944363996978752,1183 "ci_low": 0.678241338592745,1184 "ci_high": 0.7101668480222706,1185 "n_items": 964,1186 "n_groups": 841187 },1188 "exact_match": {1189 "mean": 0.0,1190 "ci_low": 0.0,1191 "ci_high": 0.0,1192 "n_items": 964,1193 "n_groups": 841194 },1195 "number_recall": {1196 "mean": 1.0,1197 "ci_low": 1.0,1198 "ci_high": 1.0,1199 "n_items": 964,1200 "n_groups": 841201 },1202 "placeholders_exact": {1203 "mean": 1.0,1204 "ci_low": 1.0,1205 "ci_high": 1.0,1206 "n_items": 964,1207 "n_groups": 841208 }1209 },1210 "chapter": {1211 "n": 1287,1212 "chrf": {1213 "mean": 64.69562058211837,1214 "ci_low": 63.44231249581201,1215 "ci_high": 66.5333222247081,1216 "n_items": 1287,1217 "n_groups": 211218 },1219 "edit_sim": {1220 "mean": 0.6604183764203291,1221 "ci_low": 0.6475754544459603,1222 "ci_high": 0.6837633550879065,1223 "n_items": 1287,1224 "n_groups": 211225 },1226 "rougeL": {1227 "mean": 0.6667136028483119,1228 "ci_low": 0.6537192537949066,1229 "ci_high": 0.6893953978498882,1230 "n_items": 1287,1231 "n_groups": 211232 },1233 "exact_match": {1234 "mean": 0.0,1235 "ci_low": 0.0,1236 "ci_high": 0.0,1237 "n_items": 1287,1238 "n_groups": 211239 },1240 "number_recall": {1241 "mean": 1.0,1242 "ci_low": 1.0,1243 "ci_high": 1.0,1244 "n_items": 1287,1245 "n_groups": 211246 },1247 "placeholders_exact": {1248 "mean": 1.0,1249 "ci_low": 1.0,1250 "ci_high": 1.0,1251 "n_items": 1287,1252 "n_groups": 211253 }1254 },1255 "conclusion": {1256 "n": 1168,1257 "chrf": {1258 "mean": 66.48255954086925,1259 "ci_low": 65.48430255822404,1260 "ci_high": 67.51445714109757,1261 "n_items": 1168,1262 "n_groups": 1541263 },1264 "edit_sim": {1265 "mean": 0.6573015834363356,1266 "ci_low": 0.6463580500829366,1267 "ci_high": 0.6688846896168182,1268 "n_items": 1168,1269 "n_groups": 1541270 },1271 "rougeL": {1272 "mean": 0.6533889568975365,1273 "ci_low": 0.6419305399486386,1274 "ci_high": 0.6654320638062552,1275 "n_items": 1168,1276 "n_groups": 1541277 },1278 "exact_match": {1279 "mean": 0.0,1280 "ci_low": 0.0,1281 "ci_high": 0.0,1282 "n_items": 1168,1283 "n_groups": 1541284 },1285 "number_recall": {1286 "mean": 1.0,1287 "ci_low": 1.0,1288 "ci_high": 1.0,1289 "n_items": 1168,1290 "n_groups": 1541291 },1292 "placeholders_exact": {1293 "mean": 1.0,1294 "ci_low": 1.0,1295 "ci_high": 1.0,1296 "n_items": 1168,1297 "n_groups": 1541298 }1299 },1300 "data": {1301 "n": 912,1302 "chrf": {1303 "mean": 70.41412553734712,1304 "ci_low": 69.30321022956544,1305 "ci_high": 71.60288449882061,1306 "n_items": 912,1307 "n_groups": 1041308 },1309 "edit_sim": {1310 "mean": 0.6912310015722472,1311 "ci_low": 0.6796366457080272,1312 "ci_high": 0.7030614153985604,1313 "n_items": 912,1314 "n_groups": 1041315 },1316 "rougeL": {1317 "mean": 0.7090298176048545,1318 "ci_low": 0.6956152265471911,1319 "ci_high": 0.722145400827728,1320 "n_items": 912,1321 "n_groups": 1041322 },1323 "exact_match": {1324 "mean": 0.0,1325 "ci_low": 0.0,1326 "ci_high": 0.0,1327 "n_items": 912,1328 "n_groups": 1041329 },1330 "number_recall": {1331 "mean": 1.0,1332 "ci_low": 1.0,1333 "ci_high": 1.0,1334 "n_items": 912,1335 "n_groups": 1041336 },1337 "placeholders_exact": {1338 "mean": 1.0,1339 "ci_low": 1.0,1340 "ci_high": 1.0,1341 "n_items": 912,1342 "n_groups": 1041343 }1344 },1345 "discussion": {1346 "n": 1601,1347 "chrf": {1348 "mean": 68.60876520640325,1349 "ci_low": 67.61726097645408,1350 "ci_high": 69.56279208592564,1351 "n_items": 1601,1352 "n_groups": 1421353 },1354 "edit_sim": {1355 "mean": 0.6774797318094666,1356 "ci_low": 0.6673034292910918,1357 "ci_high": 0.687335598494636,1358 "n_items": 1601,1359 "n_groups": 1421360 },1361 "rougeL": {1362 "mean": 0.6784616661699024,1363 "ci_low": 0.6674348410018011,1364 "ci_high": 0.6895622288335442,1365 "n_items": 1601,1366 "n_groups": 1421367 },1368 "exact_match": {1369 "mean": 0.0,1370 "ci_low": 0.0,1371 "ci_high": 0.0,1372 "n_items": 1601,1373 "n_groups": 1421374 },1375 "number_recall": {1376 "mean": 1.0,1377 "ci_low": 1.0,1378 "ci_high": 1.0,1379 "n_items": 1601,1380 "n_groups": 1421381 },1382 "placeholders_exact": {1383 "mean": 1.0,1384 "ci_low": 1.0,1385 "ci_high": 1.0,1386 "n_items": 1601,1387 "n_groups": 1421388 }1389 },1390 "introduction": {1391 "n": 1789,1392 "chrf": {1393 "mean": 68.35053900583573,1394 "ci_low": 67.24849261002655,1395 "ci_high": 69.4125164491419,1396 "n_items": 1789,1397 "n_groups": 1761398 },1399 "edit_sim": {1400 "mean": 0.6752351955039635,1401 "ci_low": 0.6647012295816729,1402 "ci_high": 0.6859958929183871,1403 "n_items": 1789,1404 "n_groups": 1761405 },1406 "rougeL": {1407 "mean": 0.674172227705161,1408 "ci_low": 0.6631926735817912,1409 "ci_high": 0.685291892973566,1410 "n_items": 1789,1411 "n_groups": 1761412 },1413 "exact_match": {1414 "mean": 0.0,1415 "ci_low": 0.0,1416 "ci_high": 0.0,1417 "n_items": 1789,1418 "n_groups": 1761419 },1420 "number_recall": {1421 "mean": 1.0,1422 "ci_low": 1.0,1423 "ci_high": 1.0,1424 "n_items": 1789,1425 "n_groups": 1761426 },1427 "placeholders_exact": {1428 "mean": 1.0,1429 "ci_low": 1.0,1430 "ci_high": 1.0,1431 "n_items": 1789,1432 "n_groups": 1761433 }1434 },1435 "limitations": {1436 "n": 425,1437 "chrf": {1438 "mean": 66.39111657511303,1439 "ci_low": 64.38607812235193,1440 "ci_high": 68.52037561796128,1441 "n_items": 425,1442 "n_groups": 411443 },1444 "edit_sim": {1445 "mean": 0.6565833829499282,1446 "ci_low": 0.6371811869383076,1447 "ci_high": 0.6777529922620432,1448 "n_items": 425,1449 "n_groups": 411450 },1451 "rougeL": {1452 "mean": 0.6576907745965377,1453 "ci_low": 0.632568076333673,1454 "ci_high": 0.6849895106717083,1455 "n_items": 425,1456 "n_groups": 411457 },1458 "exact_match": {1459 "mean": 0.0,1460 "ci_low": 0.0,1461 "ci_high": 0.0,1462 "n_items": 425,1463 "n_groups": 411464 },1465 "number_recall": {1466 "mean": 1.0,1467 "ci_low": 1.0,1468 "ci_high": 1.0,1469 "n_items": 425,1470 "n_groups": 411471 },1472 "placeholders_exact": {1473 "mean": 1.0,1474 "ci_low": 1.0,1475 "ci_high": 1.0,1476 "n_items": 425,1477 "n_groups": 411478 }1479 },1480 "methods": {1481 "n": 1528,1482 "chrf": {1483 "mean": 71.10776419795096,1484 "ci_low": 70.18229312273078,1485 "ci_high": 72.08667646814627,1486 "n_items": 1528,1487 "n_groups": 1511488 },1489 "edit_sim": {1490 "mean": 0.7010510498541032,1491 "ci_low": 0.6917337513956535,1492 "ci_high": 0.7102782034302209,1493 "n_items": 1528,1494 "n_groups": 1511495 },1496 "rougeL": {1497 "mean": 0.7167202147822925,1498 "ci_low": 0.7060883542293289,1499 "ci_high": 0.7275349432815003,1500 "n_items": 1528,1501 "n_groups": 1511502 },1503 "exact_match": {1504 "mean": 0.0,1505 "ci_low": 0.0,1506 "ci_high": 0.0,1507 "n_items": 1528,1508 "n_groups": 1511509 },1510 "number_recall": {1511 "mean": 1.0,1512 "ci_low": 1.0,1513 "ci_high": 1.0,1514 "n_items": 1528,1515 "n_groups": 1511516 },1517 "placeholders_exact": {1518 "mean": 1.0,1519 "ci_low": 1.0,1520 "ci_high": 1.0,1521 "n_items": 1528,1522 "n_groups": 1511523 }1524 },1525 "other": {1526 "n": 1387,1527 "chrf": {1528 "mean": 69.89973095743697,1529 "ci_low": 68.75639504619247,1530 "ci_high": 71.06558748257291,1531 "n_items": 1387,1532 "n_groups": 1191533 },1534 "edit_sim": {1535 "mean": 0.6918491009197876,1536 "ci_low": 0.6807789587205183,1537 "ci_high": 0.7032237592707054,1538 "n_items": 1387,1539 "n_groups": 1191540 },1541 "rougeL": {1542 "mean": 0.698980875415242,1543 "ci_low": 0.6868387114544352,1544 "ci_high": 0.7111311372607779,1545 "n_items": 1387,1546 "n_groups": 1191547 },1548 "exact_match": {1549 "mean": 0.0,1550 "ci_low": 0.0,1551 "ci_high": 0.0,1552 "n_items": 1387,1553 "n_groups": 1191554 },1555 "number_recall": {1556 "mean": 1.0,1557 "ci_low": 1.0,1558 "ci_high": 1.0,1559 "n_items": 1387,1560 "n_groups": 1191561 },1562 "placeholders_exact": {1563 "mean": 1.0,1564 "ci_low": 1.0,1565 "ci_high": 1.0,1566 "n_items": 1387,1567 "n_groups": 1191568 }1569 },1570 "preface": {1571 "n": 362,1572 "chrf": {1573 "mean": 64.45950610254158,1574 "ci_low": 59.7051743358362,1575 "ci_high": 69.5074156314821,1576 "n_items": 362,1577 "n_groups": 131578 },1579 "edit_sim": {1580 "mean": 0.6619529763234206,1581 "ci_low": 0.6120868108150262,1582 "ci_high": 0.7157468087234341,1583 "n_items": 362,1584 "n_groups": 131585 },1586 "rougeL": {1587 "mean": 0.666151023478552,1588 "ci_low": 0.6104664782263557,1589 "ci_high": 0.7288506273324655,1590 "n_items": 362,1591 "n_groups": 131592 },1593 "exact_match": {1594 "mean": 0.0,1595 "ci_low": 0.0,1596 "ci_high": 0.0,1597 "n_items": 362,1598 "n_groups": 131599 },1600 "number_recall": {1601 "mean": 1.0,1602 "ci_low": 1.0,1603 "ci_high": 1.0,1604 "n_items": 362,1605 "n_groups": 131606 },1607 "placeholders_exact": {1608 "mean": 1.0,1609 "ci_low": 1.0,1610 "ci_high": 1.0,1611 "n_items": 362,1612 "n_groups": 131613 }1614 },1615 "related_work": {1616 "n": 557,1617 "chrf": {1618 "mean": 70.3492186335612,1619 "ci_low": 68.58164406371951,1620 "ci_high": 72.02933894583181,1621 "n_items": 557,1622 "n_groups": 391623 },1624 "edit_sim": {1625 "mean": 0.6909294863142362,1626 "ci_low": 0.6721396654372904,1627 "ci_high": 0.7111619855651581,1628 "n_items": 557,1629 "n_groups": 391630 },1631 "rougeL": {1632 "mean": 0.6952665869093336,1633 "ci_low": 0.6734411008642771,1634 "ci_high": 0.7161116192942492,1635 "n_items": 557,1636 "n_groups": 391637 },1638 "exact_match": {1639 "mean": 0.0,1640 "ci_low": 0.0,1641 "ci_high": 0.0,1642 "n_items": 557,1643 "n_groups": 391644 },1645 "number_recall": {1646 "mean": 1.0,1647 "ci_low": 1.0,1648 "ci_high": 1.0,1649 "n_items": 557,1650 "n_groups": 391651 },1652 "placeholders_exact": {1653 "mean": 1.0,1654 "ci_low": 1.0,1655 "ci_high": 1.0,1656 "n_items": 557,1657 "n_groups": 391658 }1659 },1660 "results": {1661 "n": 1501,1662 "chrf": {1663 "mean": 70.60706017763856,1664 "ci_low": 69.28963985168325,1665 "ci_high": 71.93555977492257,1666 "n_items": 1501,1667 "n_groups": 1531668 },1669 "edit_sim": {1670 "mean": 0.6946123554221982,1671 "ci_low": 0.6833517410705127,1672 "ci_high": 0.7063998917547067,1673 "n_items": 1501,1674 "n_groups": 1531675 },1676 "rougeL": {1677 "mean": 0.7174445189071659,1678 "ci_low": 0.7047192772723933,1679 "ci_high": 0.730753525665349,1680 "n_items": 1501,1681 "n_groups": 1531682 },1683 "exact_match": {1684 "mean": 0.0,1685 "ci_low": 0.0,1686 "ci_high": 0.0,1687 "n_items": 1501,1688 "n_groups": 1531689 },1690 "number_recall": {1691 "mean": 1.0,1692 "ci_low": 1.0,1693 "ci_high": 1.0,1694 "n_items": 1501,1695 "n_groups": 1531696 },1697 "placeholders_exact": {1698 "mean": 1.0,1699 "ci_low": 1.0,1700 "ci_high": 1.0,1701 "n_items": 1501,1702 "n_groups": 1531703 }1704 },1705 "theory": {1706 "n": 913,1707 "chrf": {1708 "mean": 70.38498753077992,1709 "ci_low": 69.02954042273294,1710 "ci_high": 71.72233276543018,1711 "n_items": 913,1712 "n_groups": 791713 },1714 "edit_sim": {1715 "mean": 0.6999619138697949,1716 "ci_low": 0.6849194279626947,1717 "ci_high": 0.7145781704121333,1718 "n_items": 913,1719 "n_groups": 791720 },1721 "rougeL": {1722 "mean": 0.7113631860456063,1723 "ci_low": 0.6952113350161511,1724 "ci_high": 0.7275307283532821,1725 "n_items": 913,1726 "n_groups": 791727 },1728 "exact_match": {1729 "mean": 0.0,1730 "ci_low": 0.0,1731 "ci_high": 0.0,1732 "n_items": 913,1733 "n_groups": 791734 },1735 "number_recall": {1736 "mean": 1.0,1737 "ci_low": 1.0,1738 "ci_high": 1.0,1739 "n_items": 913,1740 "n_groups": 791741 },1742 "placeholders_exact": {1743 "mean": 1.0,1744 "ci_low": 1.0,1745 "ci_high": 1.0,1746 "n_items": 913,1747 "n_groups": 791748 }1749 }1750 }1751 },1752 "B1_generic_paraphrase": {1753 "overall": {1754 "n": 15649,1755 "chrf": {1756 "mean": 66.22174532253949,1757 "ci_low": 65.67543897539284,1758 "ci_high": 66.76320495262648,1759 "n_items": 15649,1760 "n_groups": 6521761 },1762 "edit_sim": {1763 "mean": 0.5695185236066106,1764 "ci_low": 0.5643543743221083,1765 "ci_high": 0.5748489317893415,1766 "n_items": 15649,1767 "n_groups": 6521768 },1769 "rougeL": {1770 "mean": 0.605616032772102,1771 "ci_low": 0.5996346046839452,1772 "ci_high": 0.6117522028754913,1773 "n_items": 15649,1774 "n_groups": 6521775 },1776 "exact_match": {1777 "mean": 0.0,1778 "ci_low": 0.0,1779 "ci_high": 0.0,1780 "n_items": 15649,1781 "n_groups": 6521782 },1783 "number_recall": {1784 "mean": 0.9998980453241866,1785 "ci_low": 0.9997924439744722,1786 "ci_high": 0.9999759094209152,1787 "n_items": 15649,1788 "n_groups": 6521789 },1790 "placeholders_exact": {1791 "mean": 1.0,1792 "ci_low": 1.0,1793 "ci_high": 1.0,1794 "n_items": 15649,1795 "n_groups": 6521796 }1797 },1798 "by_variant": {1799 "A": {1800 "n": 2664,1801 "chrf": {1802 "mean": 65.35711038182322,1803 "ci_low": 64.73843864813793,1804 "ci_high": 66.01392708808108,1805 "n_items": 2664,1806 "n_groups": 6301807 },1808 "edit_sim": {1809 "mean": 0.560565306554354,1810 "ci_low": 0.5536709596057783,1811 "ci_high": 0.5683195108248917,1812 "n_items": 2664,1813 "n_groups": 6301814 },1815 "rougeL": {1816 "mean": 0.5923120690888656,1817 "ci_low": 0.5847756473914789,1818 "ci_high": 0.6002614159579642,1819 "n_items": 2664,1820 "n_groups": 6301821 },1822 "exact_match": {1823 "mean": 0.0,1824 "ci_low": 0.0,1825 "ci_high": 0.0,1826 "n_items": 2664,1827 "n_groups": 6301828 },1829 "number_recall": {1830 "mean": 0.9998832165498832,1831 "ci_low": 0.9996803819001092,1832 "ci_high": 1.0,1833 "n_items": 2664,1834 "n_groups": 6301835 },1836 "placeholders_exact": {1837 "mean": 1.0,1838 "ci_low": 1.0,1839 "ci_high": 1.0,1840 "n_items": 2664,1841 "n_groups": 6301842 }1843 },1844 "B": {1845 "n": 2539,1846 "chrf": {1847 "mean": 72.8390654359606,1848 "ci_low": 72.25098768725493,1849 "ci_high": 73.42253524731146,1850 "n_items": 2539,1851 "n_groups": 6141852 },1853 "edit_sim": {1854 "mean": 0.6308951405705167,1855 "ci_low": 0.6240765969531724,1856 "ci_high": 0.6374126019976686,1857 "n_items": 2539,1858 "n_groups": 6141859 },1860 "rougeL": {1861 "mean": 0.6771906224338275,1862 "ci_low": 0.6703408787455334,1863 "ci_high": 0.6837435949374128,1864 "n_items": 2539,1865 "n_groups": 6141866 },1867 "exact_match": {1868 "mean": 0.0,1869 "ci_low": 0.0,1870 "ci_high": 0.0,1871 "n_items": 2539,1872 "n_groups": 6141873 },1874 "number_recall": {1875 "mean": 0.9998917472228556,1876 "ci_low": 0.9997445346879699,1877 "ci_high": 1.0,1878 "n_items": 2539,1879 "n_groups": 6141880 },1881 "placeholders_exact": {1882 "mean": 1.0,1883 "ci_low": 1.0,1884 "ci_high": 1.0,1885 "n_items": 2539,1886 "n_groups": 6141887 }1888 },1889 "C": {1890 "n": 2663,1891 "chrf": {1892 "mean": 69.5315702823788,1893 "ci_low": 68.9668530758054,1894 "ci_high": 70.11640770877149,1895 "n_items": 2663,1896 "n_groups": 6381897 },1898 "edit_sim": {1899 "mean": 0.6168223711776557,1900 "ci_low": 0.6113227817171719,1901 "ci_high": 0.6226899880636535,1902 "n_items": 2663,1903 "n_groups": 6381904 },1905 "rougeL": {1906 "mean": 0.6660199892588079,1907 "ci_low": 0.6601840365720554,1908 "ci_high": 0.6723783318832757,1909 "n_items": 2663,1910 "n_groups": 6381911 },1912 "exact_match": {1913 "mean": 0.0,1914 "ci_low": 0.0,1915 "ci_high": 0.0,1916 "n_items": 2663,1917 "n_groups": 6381918 },1919 "number_recall": {1920 "mean": 0.999924896733008,1921 "ci_low": 0.9997450827323028,1922 "ci_high": 1.0,1923 "n_items": 2663,1924 "n_groups": 6381925 },1926 "placeholders_exact": {1927 "mean": 1.0,1928 "ci_low": 1.0,1929 "ci_high": 1.0,1930 "n_items": 2663,1931 "n_groups": 6381932 }1933 },1934 "D": {1935 "n": 2708,1936 "chrf": {1937 "mean": 66.15758174525958,1938 "ci_low": 65.57060891846795,1939 "ci_high": 66.75813095191835,1940 "n_items": 2708,1941 "n_groups": 6381942 },1943 "edit_sim": {1944 "mean": 0.5722345842157557,1945 "ci_low": 0.5658712057738327,1946 "ci_high": 0.5785332581721029,1947 "n_items": 2708,1948 "n_groups": 6381949 },1950 "rougeL": {1951 "mean": 0.6067654696424878,1952 "ci_low": 0.6003330413318962,1953 "ci_high": 0.6134616008587375,1954 "n_items": 2708,1955 "n_groups": 6381956 },1957 "exact_match": {1958 "mean": 0.0,1959 "ci_low": 0.0,1960 "ci_high": 0.0,1961 "n_items": 2708,1962 "n_groups": 6381963 },1964 "number_recall": {1965 "mean": 0.9999261447562777,1966 "ci_low": 0.9997644287396938,1967 "ci_high": 1.0,1968 "n_items": 2708,1969 "n_groups": 6381970 },1971 "placeholders_exact": {1972 "mean": 1.0,1973 "ci_low": 1.0,1974 "ci_high": 1.0,1975 "n_items": 2708,1976 "n_groups": 6381977 }1978 },1979 "E": {1980 "n": 5075,1981 "chrf": {1982 "mean": 61.662474940926444,1983 "ci_low": 61.0740705266234,1984 "ci_high": 62.271240007123865,1985 "n_items": 5075,1986 "n_groups": 6231987 },1988 "edit_sim": {1989 "mean": 0.5172408687385506,1990 "ci_low": 0.5117424969321182,1991 "ci_high": 0.5227910980172388,1992 "n_items": 5075,1993 "n_groups": 6231994 },1995 "rougeL": {1996 "mean": 0.5444821342365188,1997 "ci_low": 0.5380137279249407,1998 "ci_high": 0.5512765510522301,1999 "n_items": 5075,2000 "n_groups": 6232001 },2002 "exact_match": {2003 "mean": 0.0,2004 "ci_low": 0.0,2005 "ci_high": 0.0,2006 "n_items": 5075,2007 "n_groups": 6232008 },2009 "number_recall": {2010 "mean": 0.9998798967863007,2011 "ci_low": 0.9997073596184908,2012 "ci_high": 1.0,2013 "n_items": 5075,2014 "n_groups": 6232015 },2016 "placeholders_exact": {2017 "mean": 1.0,2018 "ci_low": 1.0,2019 "ci_high": 1.0,2020 "n_items": 5075,2021 "n_groups": 6232022 }2023 }2024 },2025 "by_discipline": {2026 "biomedicine": {2027 "n": 2154,2028 "chrf": {2029 "mean": 66.25621186932783,2030 "ci_low": 65.279551711698,2031 "ci_high": 67.24792384516823,2032 "n_items": 2154,2033 "n_groups": 2442034 },2035 "edit_sim": {2036 "mean": 0.5637737064349946,2037 "ci_low": 0.5546203893402987,2038 "ci_high": 0.5732724422840921,2039 "n_items": 2154,2040 "n_groups": 2442041 },2042 "rougeL": {2043 "mean": 0.6001549757903762,2044 "ci_low": 0.590128307705976,2045 "ci_high": 0.6106392185048126,2046 "n_items": 2154,2047 "n_groups": 2442048 },2049 "exact_match": {2050 "mean": 0.0,2051 "ci_low": 0.0,2052 "ci_high": 0.0,2053 "n_items": 2154,2054 "n_groups": 2442055 },2056 "number_recall": {2057 "mean": 1.0,2058 "ci_low": 1.0,2059 "ci_high": 1.0,2060 "n_items": 2154,2061 "n_groups": 2442062 },2063 "placeholders_exact": {2064 "mean": 1.0,2065 "ci_low": 1.0,2066 "ci_high": 1.0,2067 "n_items": 2154,2068 "n_groups": 2442069 }2070 },2071 "chemistry": {2072 "n": 837,2073 "chrf": {2074 "mean": 69.86675231850036,2075 "ci_low": 68.45400798669742,2076 "ci_high": 71.35614054924021,2077 "n_items": 837,2078 "n_groups": 132079 },2080 "edit_sim": {2081 "mean": 0.5927984743094057,2082 "ci_low": 0.578848019117656,2083 "ci_high": 0.6086395646792,2084 "n_items": 837,2085 "n_groups": 132086 },2087 "rougeL": {2088 "mean": 0.640140369921715,2089 "ci_low": 0.6246834483774133,2090 "ci_high": 0.6562312417228843,2091 "n_items": 837,2092 "n_groups": 132093 },2094 "exact_match": {2095 "mean": 0.0,2096 "ci_low": 0.0,2097 "ci_high": 0.0,2098 "n_items": 837,2099 "n_groups": 132100 },2101 "number_recall": {2102 "mean": 1.0,2103 "ci_low": 1.0,2104 "ci_high": 1.0,2105 "n_items": 837,2106 "n_groups": 132107 },2108 "placeholders_exact": {2109 "mean": 1.0,2110 "ci_low": 1.0,2111 "ci_high": 1.0,2112 "n_items": 837,2113 "n_groups": 132114 }2115 },2116 "computer_science": {2117 "n": 1375,2118 "chrf": {2119 "mean": 66.27289796274476,2120 "ci_low": 64.61103933255892,2121 "ci_high": 67.92268723724575,2122 "n_items": 1375,2123 "n_groups": 202124 },2125 "edit_sim": {2126 "mean": 0.5723413272945898,2127 "ci_low": 0.5562321477995938,2128 "ci_high": 0.5857592955946215,2129 "n_items": 1375,2130 "n_groups": 202131 },2132 "rougeL": {2133 "mean": 0.6050015903723286,2134 "ci_low": 0.5861881785140154,2135 "ci_high": 0.6209408541456112,2136 "n_items": 1375,2137 "n_groups": 202138 },2139 "exact_match": {2140 "mean": 0.0,2141 "ci_low": 0.0,2142 "ci_high": 0.0,2143 "n_items": 1375,2144 "n_groups": 202145 },2146 "number_recall": {2147 "mean": 0.9994435786435787,2148 "ci_low": 0.9986742807214629,2149 "ci_high": 1.0,2150 "n_items": 1375,2151 "n_groups": 202152 },2153 "placeholders_exact": {2154 "mean": 1.0,2155 "ci_low": 1.0,2156 "ci_high": 1.0,2157 "n_items": 1375,2158 "n_groups": 202159 }2160 },2161 "economics": {2162 "n": 1944,2163 "chrf": {2164 "mean": 64.90159302084997,2165 "ci_low": 64.01984874967987,2166 "ci_high": 65.73241614919097,2167 "n_items": 1944,2168 "n_groups": 1032169 },2170 "edit_sim": {2171 "mean": 0.5636197902176169,2172 "ci_low": 0.553844642277861,2173 "ci_high": 0.5737747039928323,2174 "n_items": 1944,2175 "n_groups": 1032176 },2177 "rougeL": {2178 "mean": 0.5940649532087621,2179 "ci_low": 0.5824292826882213,2180 "ci_high": 0.606043341962697,2181 "n_items": 1944,2182 "n_groups": 1032183 },2184 "exact_match": {2185 "mean": 0.0,2186 "ci_low": 0.0,2187 "ci_high": 0.0,2188 "n_items": 1944,2189 "n_groups": 1032190 },2191 "number_recall": {2192 "mean": 0.9998971193415638,2193 "ci_low": 0.9996677324888102,2194 "ci_high": 1.0,2195 "n_items": 1944,2196 "n_groups": 1032197 },2198 "placeholders_exact": {2199 "mean": 1.0,2200 "ci_low": 1.0,2201 "ci_high": 1.0,2202 "n_items": 1944,2203 "n_groups": 1032204 }2205 },2206 "engineering": {2207 "n": 1296,2208 "chrf": {2209 "mean": 63.68446393406927,2210 "ci_low": 62.17000693041499,2211 "ci_high": 65.41779103586914,2212 "n_items": 1296,2213 "n_groups": 172214 },2215 "edit_sim": {2216 "mean": 0.5511627659104922,2217 "ci_low": 0.5369034851349525,2218 "ci_high": 0.566668252464184,2219 "n_items": 1296,2220 "n_groups": 172221 },2222 "rougeL": {2223 "mean": 0.5807404885149823,2224 "ci_low": 0.5661461841956003,2225 "ci_high": 0.59682957915803,2226 "n_items": 1296,2227 "n_groups": 172228 },2229 "exact_match": {2230 "mean": 0.0,2231 "ci_low": 0.0,2232 "ci_high": 0.0,2233 "n_items": 1296,2234 "n_groups": 172235 },2236 "number_recall": {2237 "mean": 1.0,2238 "ci_low": 1.0,2239 "ci_high": 1.0,2240 "n_items": 1296,2241 "n_groups": 172242 },2243 "placeholders_exact": {2244 "mean": 1.0,2245 "ci_low": 1.0,2246 "ci_high": 1.0,2247 "n_items": 1296,2248 "n_groups": 172249 }2250 },2251 "finance": {2252 "n": 2043,2253 "chrf": {2254 "mean": 65.24211355387368,2255 "ci_low": 64.08436527660123,2256 "ci_high": 66.61755711823355,2257 "n_items": 2043,2258 "n_groups": 512259 },2260 "edit_sim": {2261 "mean": 0.5619314590338308,2262 "ci_low": 0.5488115393709454,2263 "ci_high": 0.5773732704278333,2264 "n_items": 2043,2265 "n_groups": 512266 },2267 "rougeL": {2268 "mean": 0.5965207344608537,2269 "ci_low": 0.5821113734331229,2270 "ci_high": 0.6129793848893937,2271 "n_items": 2043,2272 "n_groups": 512273 },2274 "exact_match": {2275 "mean": 0.0,2276 "ci_low": 0.0,2277 "ci_high": 0.0,2278 "n_items": 2043,2279 "n_groups": 512280 },2281 "number_recall": {2282 "mean": 0.9997458158367039,2283 "ci_low": 0.9992633280388044,2284 "ci_high": 1.0,2285 "n_items": 2043,2286 "n_groups": 512287 },2288 "placeholders_exact": {2289 "mean": 1.0,2290 "ci_low": 1.0,2291 "ci_high": 1.0,2292 "n_items": 2043,2293 "n_groups": 512294 }2295 },2296 "general_reference": {2297 "n": 118,2298 "chrf": {2299 "mean": 75.2596454414096,2300 "ci_low": 59.71627869208917,2301 "ci_high": 76.85756164928368,2302 "n_items": 118,2303 "n_groups": 22304 },2305 "edit_sim": {2306 "mean": 0.7067889157474608,2307 "ci_low": 0.5177479796705575,2308 "ci_high": 0.7262230306712545,2309 "n_items": 118,2310 "n_groups": 22311 },2312 "rougeL": {2313 "mean": 0.7635524137185197,2314 "ci_low": 0.5440724754363317,2315 "ci_high": 0.7861157718596791,2316 "n_items": 118,2317 "n_groups": 22318 },2319 "exact_match": {2320 "mean": 0.0,2321 "ci_low": 0.0,2322 "ci_high": 0.0,2323 "n_items": 118,2324 "n_groups": 22325 },2326 "number_recall": {2327 "mean": 1.0,2328 "ci_low": 1.0,2329 "ci_high": 1.0,2330 "n_items": 118,2331 "n_groups": 22332 },2333 "placeholders_exact": {2334 "mean": 1.0,2335 "ci_low": 1.0,2336 "ci_high": 1.0,2337 "n_items": 118,2338 "n_groups": 22339 }2340 },2341 "humanities": {2342 "n": 263,2343 "chrf": {2344 "mean": 62.14903286977755,2345 "ci_low": 59.35711544192951,2346 "ci_high": 62.37060728046157,2347 "n_items": 263,2348 "n_groups": 32349 },2350 "edit_sim": {2351 "mean": 0.5545892434018241,2352 "ci_low": 0.538898528900713,2353 "ci_high": 0.5622429979676264,2354 "n_items": 263,2355 "n_groups": 32356 },2357 "rougeL": {2358 "mean": 0.5918999059678813,2359 "ci_low": 0.5796168350285145,2360 "ci_high": 0.5962719748248508,2361 "n_items": 263,2362 "n_groups": 32363 },2364 "exact_match": {2365 "mean": 0.0,2366 "ci_low": 0.0,2367 "ci_high": 0.0,2368 "n_items": 263,2369 "n_groups": 32370 },2371 "number_recall": {2372 "mean": 1.0,2373 "ci_low": 1.0,2374 "ci_high": 1.0,2375 "n_items": 263,2376 "n_groups": 32377 },2378 "placeholders_exact": {2379 "mean": 1.0,2380 "ci_low": 1.0,2381 "ci_high": 1.0,2382 "n_items": 263,2383 "n_groups": 32384 }2385 },2386 "life_sciences": {2387 "n": 1874,2388 "chrf": {2389 "mean": 69.07378021223245,2390 "ci_low": 67.48959673458377,2391 "ci_high": 70.52260314406558,2392 "n_items": 1874,2393 "n_groups": 1432394 },2395 "edit_sim": {2396 "mean": 0.5859630209523973,2397 "ci_low": 0.5736285610808517,2398 "ci_high": 0.598711536364533,2399 "n_items": 1874,2400 "n_groups": 1432401 },2402 "rougeL": {2403 "mean": 0.6294253423587328,2404 "ci_low": 0.6167532014474189,2405 "ci_high": 0.6419938970276923,2406 "n_items": 1874,2407 "n_groups": 1432408 },2409 "exact_match": {2410 "mean": 0.0,2411 "ci_low": 0.0,2412 "ci_high": 0.0,2413 "n_items": 1874,2414 "n_groups": 1432415 },2416 "number_recall": {2417 "mean": 0.9999407091189375,2418 "ci_low": 0.9997956506706744,2419 "ci_high": 1.0,2420 "n_items": 1874,2421 "n_groups": 1432422 },2423 "placeholders_exact": {2424 "mean": 1.0,2425 "ci_low": 1.0,2426 "ci_high": 1.0,2427 "n_items": 1874,2428 "n_groups": 1432429 }2430 },2431 "mathematics": {2432 "n": 712,2433 "chrf": {2434 "mean": 64.87606780717017,2435 "ci_low": 62.237920481192894,2436 "ci_high": 68.33738054619862,2437 "n_items": 712,2438 "n_groups": 52439 },2440 "edit_sim": {2441 "mean": 0.5717937106631926,2442 "ci_low": 0.5502361348574476,2443 "ci_high": 0.5966184664375929,2444 "n_items": 712,2445 "n_groups": 52446 },2447 "rougeL": {2448 "mean": 0.5978225301536132,2449 "ci_low": 0.5737103531935047,2450 "ci_high": 0.6329194695600322,2451 "n_items": 712,2452 "n_groups": 52453 },2454 "exact_match": {2455 "mean": 0.0,2456 "ci_low": 0.0,2457 "ci_high": 0.0,2458 "n_items": 712,2459 "n_groups": 52460 },2461 "number_recall": {2462 "mean": 1.0,2463 "ci_low": 1.0,2464 "ci_high": 1.0,2465 "n_items": 712,2466 "n_groups": 52467 },2468 "placeholders_exact": {2469 "mean": 1.0,2470 "ci_low": 1.0,2471 "ci_high": 1.0,2472 "n_items": 712,2473 "n_groups": 52474 }2475 },2476 "other": {2477 "n": 669,2478 "chrf": {2479 "mean": 66.14764452590862,2480 "ci_low": 63.77824862628497,2481 "ci_high": 69.27722416232626,2482 "n_items": 669,2483 "n_groups": 132484 },2485 "edit_sim": {2486 "mean": 0.5527085107803538,2487 "ci_low": 0.5302872136729124,2488 "ci_high": 0.584975013858039,2489 "n_items": 669,2490 "n_groups": 132491 },2492 "rougeL": {2493 "mean": 0.5866342837136935,2494 "ci_low": 0.5644671452124008,2495 "ci_high": 0.619463361501964,2496 "n_items": 669,2497 "n_groups": 132498 },2499 "exact_match": {2500 "mean": 0.0,2501 "ci_low": 0.0,2502 "ci_high": 0.0,2503 "n_items": 669,2504 "n_groups": 132505 },2506 "number_recall": {2507 "mean": 1.0,2508 "ci_low": 1.0,2509 "ci_high": 1.0,2510 "n_items": 669,2511 "n_groups": 132512 },2513 "placeholders_exact": {2514 "mean": 1.0,2515 "ci_low": 1.0,2516 "ci_high": 1.0,2517 "n_items": 669,2518 "n_groups": 132519 }2520 },2521 "social_sciences": {2522 "n": 1536,2523 "chrf": {2524 "mean": 65.84661565294095,2525 "ci_low": 63.93582512647813,2526 "ci_high": 67.28369407865412,2527 "n_items": 1536,2528 "n_groups": 292529 },2530 "edit_sim": {2531 "mean": 0.5627014658779202,2532 "ci_low": 0.5480750380083351,2533 "ci_high": 0.5758852485276333,2534 "n_items": 1536,2535 "n_groups": 292536 },2537 "rougeL": {2538 "mean": 0.6001233811912391,2539 "ci_low": 0.5808550004766273,2540 "ci_high": 0.616245451954905,2541 "n_items": 1536,2542 "n_groups": 292543 },2544 "exact_match": {2545 "mean": 0.0,2546 "ci_low": 0.0,2547 "ci_high": 0.0,2548 "n_items": 1536,2549 "n_groups": 292550 },2551 "number_recall": {2552 "mean": 1.0,2553 "ci_low": 1.0,2554 "ci_high": 1.0,2555 "n_items": 1536,2556 "n_groups": 292557 },2558 "placeholders_exact": {2559 "mean": 1.0,2560 "ci_low": 1.0,2561 "ci_high": 1.0,2562 "n_items": 1536,2563 "n_groups": 292564 }2565 },2566 "statistics": {2567 "n": 828,2568 "chrf": {2569 "mean": 67.3140962329259,2570 "ci_low": 64.30469015888764,2571 "ci_high": 70.42468729936277,2572 "n_items": 828,2573 "n_groups": 92574 },2575 "edit_sim": {2576 "mean": 0.5897754166573279,2577 "ci_low": 0.5657651644087487,2578 "ci_high": 0.6162752800958786,2579 "n_items": 828,2580 "n_groups": 92581 },2582 "rougeL": {2583 "mean": 0.6346299003656629,2584 "ci_low": 0.6066221742413962,2585 "ci_high": 0.6639698921128518,2586 "n_items": 828,2587 "n_groups": 92588 },2589 "exact_match": {2590 "mean": 0.0,2591 "ci_low": 0.0,2592 "ci_high": 0.0,2593 "n_items": 828,2594 "n_groups": 92595 },2596 "number_recall": {2597 "mean": 1.0,2598 "ci_low": 1.0,2599 "ci_high": 1.0,2600 "n_items": 828,2601 "n_groups": 92602 },2603 "placeholders_exact": {2604 "mean": 1.0,2605 "ci_low": 1.0,2606 "ci_high": 1.0,2607 "n_items": 828,2608 "n_groups": 92609 }2610 }2611 },2612 "by_era": {2613 "1900-1949": {2614 "n": 1164,2615 "chrf": {2616 "mean": 62.94183785134411,2617 "ci_low": 60.50043723280602,2618 "ci_high": 66.29597094420404,2619 "n_items": 1164,2620 "n_groups": 182621 },2622 "edit_sim": {2623 "mean": 0.5503249545050714,2624 "ci_low": 0.5257328717910494,2625 "ci_high": 0.593746890294689,2626 "n_items": 1164,2627 "n_groups": 182628 },2629 "rougeL": {2630 "mean": 0.5900017913091421,2631 "ci_low": 0.5620583668205706,2632 "ci_high": 0.6375358335205975,2633 "n_items": 1164,2634 "n_groups": 182635 },2636 "exact_match": {2637 "mean": 0.0,2638 "ci_low": 0.0,2639 "ci_high": 0.0,2640 "n_items": 1164,2641 "n_groups": 182642 },2643 "number_recall": {2644 "mean": 1.0,2645 "ci_low": 1.0,2646 "ci_high": 1.0,2647 "n_items": 1164,2648 "n_groups": 182649 },2650 "placeholders_exact": {2651 "mean": 1.0,2652 "ci_low": 1.0,2653 "ci_high": 1.0,2654 "n_items": 1164,2655 "n_groups": 182656 }2657 },2658 "1950-1979": {2659 "n": 206,2660 "chrf": {2661 "mean": 61.491520903920915,2662 "ci_low": 57.84331244127718,2663 "ci_high": 62.37060728046157,2664 "n_items": 206,2665 "n_groups": 22666 },2667 "edit_sim": {2668 "mean": 0.5529790378640467,2669 "ci_low": 0.5145336034341911,2670 "ci_high": 0.5622429979676263,2671 "n_items": 206,2672 "n_groups": 22673 },2674 "rougeL": {2675 "mean": 0.5854187655323763,2676 "ci_low": 0.5403779469686075,2677 "ci_high": 0.5962719748248507,2678 "n_items": 206,2679 "n_groups": 22680 },2681 "exact_match": {2682 "mean": 0.0,2683 "ci_low": 0.0,2684 "ci_high": 0.0,2685 "n_items": 206,2686 "n_groups": 22687 },2688 "number_recall": {2689 "mean": 1.0,2690 "ci_low": 1.0,2691 "ci_high": 1.0,2692 "n_items": 206,2693 "n_groups": 22694 },2695 "placeholders_exact": {2696 "mean": 1.0,2697 "ci_low": 1.0,2698 "ci_high": 1.0,2699 "n_items": 206,2700 "n_groups": 22701 }2702 },2703 "1980-1999": {2704 "n": 151,2705 "chrf": {2706 "mean": 61.802308795910704,2707 "ci_low": 60.375350480275515,2708 "ci_high": 76.45663059442045,2709 "n_items": 151,2710 "n_groups": 42711 },2712 "edit_sim": {2713 "mean": 0.5462451199449841,2714 "ci_low": 0.5388229274548831,2715 "ci_high": 0.6184266122914621,2716 "n_items": 151,2717 "n_groups": 42718 },2719 "rougeL": {2720 "mean": 0.5792793740324184,2721 "ci_low": 0.5706075014910068,2722 "ci_high": 0.6734816465547853,2723 "n_items": 151,2724 "n_groups": 42725 },2726 "exact_match": {2727 "mean": 0.0,2728 "ci_low": 0.0,2729 "ci_high": 0.0,2730 "n_items": 151,2731 "n_groups": 42732 },2733 "number_recall": {2734 "mean": 1.0,2735 "ci_low": 1.0,2736 "ci_high": 1.0,2737 "n_items": 151,2738 "n_groups": 42739 },2740 "placeholders_exact": {2741 "mean": 1.0,2742 "ci_low": 1.0,2743 "ci_high": 1.0,2744 "n_items": 151,2745 "n_groups": 42746 }2747 },2748 "2000-2009": {2749 "n": 1545,2750 "chrf": {2751 "mean": 67.08485336042727,2752 "ci_low": 65.64567585979138,2753 "ci_high": 68.55840493894749,2754 "n_items": 1545,2755 "n_groups": 692756 },2757 "edit_sim": {2758 "mean": 0.5740249653812002,2759 "ci_low": 0.5620553512479686,2760 "ci_high": 0.5864152554806888,2761 "n_items": 1545,2762 "n_groups": 692763 },2764 "rougeL": {2765 "mean": 0.614220763155076,2766 "ci_low": 0.6017168696052589,2767 "ci_high": 0.6283145020686234,2768 "n_items": 1545,2769 "n_groups": 692770 },2771 "exact_match": {2772 "mean": 0.0,2773 "ci_low": 0.0,2774 "ci_high": 0.0,2775 "n_items": 1545,2776 "n_groups": 692777 },2778 "number_recall": {2779 "mean": 0.9996145704065991,2780 "ci_low": 0.9989721615657259,2781 "ci_high": 1.0,2782 "n_items": 1545,2783 "n_groups": 692784 },2785 "placeholders_exact": {2786 "mean": 1.0,2787 "ci_low": 1.0,2788 "ci_high": 1.0,2789 "n_items": 1545,2790 "n_groups": 692791 }2792 },2793 "2010-2017": {2794 "n": 12583,2795 "chrf": {2796 "mean": 66.54965373259203,2797 "ci_low": 66.0115336954475,2798 "ci_high": 67.09447100497306,2799 "n_items": 12583,2800 "n_groups": 5592801 },2802 "edit_sim": {2803 "mean": 0.5712907782285865,2804 "ci_low": 0.5659477140875001,2805 "ci_high": 0.5766533512089658,2806 "n_items": 12583,2807 "n_groups": 5592808 },2809 "rougeL": {2810 "mean": 0.6066506144412003,2811 "ci_low": 0.6004752441319331,2812 "ci_high": 0.6130921320024701,2813 "n_items": 12583,2814 "n_groups": 5592815 },2816 "exact_match": {2817 "mean": 0.0,2818 "ci_low": 0.0,2819 "ci_high": 0.0,2820 "n_items": 12583,2821 "n_groups": 5592822 },2823 "number_recall": {2824 "mean": 0.999920527696098,2825 "ci_low": 0.9998331657426881,2826 "ci_high": 0.9999901206392953,2827 "n_items": 12583,2828 "n_groups": 5592829 },2830 "placeholders_exact": {2831 "mean": 1.0,2832 "ci_low": 1.0,2833 "ci_high": 1.0,2834 "n_items": 12583,2835 "n_groups": 5592836 }2837 }2838 },2839 "by_role": {2840 "abstract": {2841 "n": 1255,2842 "chrf": {2843 "mean": 67.02906871347514,2844 "ci_low": 66.21374633890338,2845 "ci_high": 67.93135114789129,2846 "n_items": 1255,2847 "n_groups": 1952848 },2849 "edit_sim": {2850 "mean": 0.5646392325506095,2851 "ci_low": 0.5539230617080412,2852 "ci_high": 0.5756105731358279,2853 "n_items": 1255,2854 "n_groups": 1952855 },2856 "rougeL": {2857 "mean": 0.5933932194113252,2858 "ci_low": 0.582655809180166,2859 "ci_high": 0.6046998337969347,2860 "n_items": 1255,2861 "n_groups": 1952862 },2863 "exact_match": {2864 "mean": 0.0,2865 "ci_low": 0.0,2866 "ci_high": 0.0,2867 "n_items": 1255,2868 "n_groups": 1952869 },2870 "number_recall": {2871 "mean": 1.0,2872 "ci_low": 1.0,2873 "ci_high": 1.0,2874 "n_items": 1255,2875 "n_groups": 1952876 },2877 "placeholders_exact": {2878 "mean": 1.0,2879 "ci_low": 1.0,2880 "ci_high": 1.0,2881 "n_items": 1255,2882 "n_groups": 1952883 }2884 },2885 "background": {2886 "n": 964,2887 "chrf": {2888 "mean": 67.05205092728195,2889 "ci_low": 66.02498931645763,2890 "ci_high": 68.14970698183946,2891 "n_items": 964,2892 "n_groups": 842893 },2894 "edit_sim": {2895 "mean": 0.5750911199918748,2896 "ci_low": 0.5632076918682926,2897 "ci_high": 0.5878376102976275,2898 "n_items": 964,2899 "n_groups": 842900 },2901 "rougeL": {2902 "mean": 0.6098855118463269,2903 "ci_low": 0.5942536655164518,2904 "ci_high": 0.6261210304809224,2905 "n_items": 964,2906 "n_groups": 842907 },2908 "exact_match": {2909 "mean": 0.0,2910 "ci_low": 0.0,2911 "ci_high": 0.0,2912 "n_items": 964,2913 "n_groups": 842914 },2915 "number_recall": {2916 "mean": 1.0,2917 "ci_low": 1.0,2918 "ci_high": 1.0,2919 "n_items": 964,2920 "n_groups": 842921 },2922 "placeholders_exact": {2923 "mean": 1.0,2924 "ci_low": 1.0,2925 "ci_high": 1.0,2926 "n_items": 964,2927 "n_groups": 842928 }2929 },2930 "chapter": {2931 "n": 1287,2932 "chrf": {2933 "mean": 62.70418615118341,2934 "ci_low": 61.35795870578241,2935 "ci_high": 64.56754457365734,2936 "n_items": 1287,2937 "n_groups": 212938 },2939 "edit_sim": {2940 "mean": 0.54668394852737,2941 "ci_low": 0.5323121597427467,2942 "ci_high": 0.5725351449331506,2943 "n_items": 1287,2944 "n_groups": 212945 },2946 "rougeL": {2947 "mean": 0.5845162936168558,2948 "ci_low": 0.5696441990323867,2949 "ci_high": 0.6111398183540012,2950 "n_items": 1287,2951 "n_groups": 212952 },2953 "exact_match": {2954 "mean": 0.0,2955 "ci_low": 0.0,2956 "ci_high": 0.0,2957 "n_items": 1287,2958 "n_groups": 212959 },2960 "number_recall": {2961 "mean": 1.0,2962 "ci_low": 1.0,2963 "ci_high": 1.0,2964 "n_items": 1287,2965 "n_groups": 212966 },2967 "placeholders_exact": {2968 "mean": 1.0,2969 "ci_low": 1.0,2970 "ci_high": 1.0,2971 "n_items": 1287,2972 "n_groups": 212973 }2974 },2975 "conclusion": {2976 "n": 1168,2977 "chrf": {2978 "mean": 63.654778725272365,2979 "ci_low": 62.68770334551986,2980 "ci_high": 64.64559870374701,2981 "n_items": 1168,2982 "n_groups": 1542983 },2984 "edit_sim": {2985 "mean": 0.5454816765201909,2986 "ci_low": 0.5357828715695593,2987 "ci_high": 0.5546850997754329,2988 "n_items": 1168,2989 "n_groups": 1542990 },2991 "rougeL": {2992 "mean": 0.5661118154223387,2993 "ci_low": 0.5559231672117608,2994 "ci_high": 0.5757936046729795,2995 "n_items": 1168,2996 "n_groups": 1542997 },2998 "exact_match": {2999 "mean": 0.0,3000 "ci_low": 0.0,3001 "ci_high": 0.0,3002 "n_items": 1168,3003 "n_groups": 1543004 },3005 "number_recall": {3006 "mean": 0.9998776908023483,3007 "ci_low": 0.9996152599999677,3008 "ci_high": 1.0,3009 "n_items": 1168,3010 "n_groups": 1543011 },3012 "placeholders_exact": {3013 "mean": 1.0,3014 "ci_low": 1.0,3015 "ci_high": 1.0,3016 "n_items": 1168,3017 "n_groups": 1543018 }3019 },3020 "data": {3021 "n": 912,3022 "chrf": {3023 "mean": 67.56131709777137,3024 "ci_low": 66.50521327339486,3025 "ci_high": 68.65598210839258,3026 "n_items": 912,3027 "n_groups": 1043028 },3029 "edit_sim": {3030 "mean": 0.5744527143967597,3031 "ci_low": 0.5617509425918077,3032 "ci_high": 0.5867691699283507,3033 "n_items": 912,3034 "n_groups": 1043035 },3036 "rougeL": {3037 "mean": 0.6236628139961006,3038 "ci_low": 0.6100241697831807,3039 "ci_high": 0.6366937300745946,3040 "n_items": 912,3041 "n_groups": 1043042 },3043 "exact_match": {3044 "mean": 0.0,3045 "ci_low": 0.0,3046 "ci_high": 0.0,3047 "n_items": 912,3048 "n_groups": 1043049 },3050 "number_recall": {3051 "mean": 0.9998781676413255,3052 "ci_low": 0.9996049488700325,3053 "ci_high": 1.0,3054 "n_items": 912,3055 "n_groups": 1043056 },3057 "placeholders_exact": {3058 "mean": 1.0,3059 "ci_low": 1.0,3060 "ci_high": 1.0,3061 "n_items": 912,3062 "n_groups": 1043063 }3064 },3065 "discussion": {3066 "n": 1601,3067 "chrf": {3068 "mean": 65.18068591883014,3069 "ci_low": 64.21332189080266,3070 "ci_high": 66.11295348711273,3071 "n_items": 1601,3072 "n_groups": 1423073 },3074 "edit_sim": {3075 "mean": 0.5583614995914667,3076 "ci_low": 0.5497955335759122,3077 "ci_high": 0.5677640248373044,3078 "n_items": 1601,3079 "n_groups": 1423080 },3081 "rougeL": {3082 "mean": 0.5869640848013351,3083 "ci_low": 0.5762495992016431,3084 "ci_high": 0.5978381169674976,3085 "n_items": 1601,3086 "n_groups": 1423087 },3088 "exact_match": {3089 "mean": 0.0,3090 "ci_low": 0.0,3091 "ci_high": 0.0,3092 "n_items": 1601,3093 "n_groups": 1423094 },3095 "number_recall": {3096 "mean": 1.0,3097 "ci_low": 1.0,3098 "ci_high": 1.0,3099 "n_items": 1601,3100 "n_groups": 1423101 },3102 "placeholders_exact": {3103 "mean": 1.0,3104 "ci_low": 1.0,3105 "ci_high": 1.0,3106 "n_items": 1601,3107 "n_groups": 1423108 }3109 },3110 "introduction": {3111 "n": 1789,3112 "chrf": {3113 "mean": 65.83101632779612,3114 "ci_low": 64.80898129329908,3115 "ci_high": 66.84313908447534,3116 "n_items": 1789,3117 "n_groups": 1763118 },3119 "edit_sim": {3120 "mean": 0.5580427170024725,3121 "ci_low": 0.5468127275186832,3122 "ci_high": 0.5695592618930959,3123 "n_items": 1789,3124 "n_groups": 1763125 },3126 "rougeL": {3127 "mean": 0.5882375601206278,3128 "ci_low": 0.5770969531946842,3129 "ci_high": 0.5994451926319173,3130 "n_items": 1789,3131 "n_groups": 1763132 },3133 "exact_match": {3134 "mean": 0.0,3135 "ci_low": 0.0,3136 "ci_high": 0.0,3137 "n_items": 1789,3138 "n_groups": 1763139 },3140 "number_recall": {3141 "mean": 1.0,3142 "ci_low": 1.0,3143 "ci_high": 1.0,3144 "n_items": 1789,3145 "n_groups": 1763146 },3147 "placeholders_exact": {3148 "mean": 1.0,3149 "ci_low": 1.0,3150 "ci_high": 1.0,3151 "n_items": 1789,3152 "n_groups": 1763153 }3154 },3155 "limitations": {3156 "n": 425,3157 "chrf": {3158 "mean": 62.66239155568727,3159 "ci_low": 60.73548958685929,3160 "ci_high": 64.67585770965914,3161 "n_items": 425,3162 "n_groups": 413163 },3164 "edit_sim": {3165 "mean": 0.5403360613296634,3166 "ci_low": 0.5168308619102939,3167 "ci_high": 0.5660433519242883,3168 "n_items": 425,3169 "n_groups": 413170 },3171 "rougeL": {3172 "mean": 0.5621173589562345,3173 "ci_low": 0.5327411128807266,3174 "ci_high": 0.5928936835568901,3175 "n_items": 425,3176 "n_groups": 413177 },3178 "exact_match": {3179 "mean": 0.0,3180 "ci_low": 0.0,3181 "ci_high": 0.0,3182 "n_items": 425,3183 "n_groups": 413184 },3185 "number_recall": {3186 "mean": 1.0,3187 "ci_low": 1.0,3188 "ci_high": 1.0,3189 "n_items": 425,3190 "n_groups": 413191 },3192 "placeholders_exact": {3193 "mean": 1.0,3194 "ci_low": 1.0,3195 "ci_high": 1.0,3196 "n_items": 425,3197 "n_groups": 413198 }3199 },3200 "methods": {3201 "n": 1528,3202 "chrf": {3203 "mean": 68.65230547843471,3204 "ci_low": 67.64977519702452,3205 "ci_high": 69.66446030622646,3206 "n_items": 1528,3207 "n_groups": 1513208 },3209 "edit_sim": {3210 "mean": 0.5919984055912778,3211 "ci_low": 0.5816055644010211,3212 "ci_high": 0.6020897769353283,3213 "n_items": 1528,3214 "n_groups": 1513215 },3216 "rougeL": {3217 "mean": 0.6374496759230961,3218 "ci_low": 0.625329657989609,3219 "ci_high": 0.6492370650594983,3220 "n_items": 1528,3221 "n_groups": 1513222 },3223 "exact_match": {3224 "mean": 0.0,3225 "ci_low": 0.0,3226 "ci_high": 0.0,3227 "n_items": 1528,3228 "n_groups": 1513229 },3230 "number_recall": {3231 "mean": 0.999869109947644,3232 "ci_low": 0.9995791533671501,3233 "ci_high": 1.0,3234 "n_items": 1528,3235 "n_groups": 1513236 },3237 "placeholders_exact": {3238 "mean": 1.0,3239 "ci_low": 1.0,3240 "ci_high": 1.0,3241 "n_items": 1528,3242 "n_groups": 1513243 }3244 },3245 "other": {3246 "n": 1387,3247 "chrf": {3248 "mean": 67.31319190145183,3249 "ci_low": 66.23914439501807,3250 "ci_high": 68.40522483778634,3251 "n_items": 1387,3252 "n_groups": 1193253 },3254 "edit_sim": {3255 "mean": 0.578033744879101,3256 "ci_low": 0.567565069408051,3257 "ci_high": 0.5903332406594007,3258 "n_items": 1387,3259 "n_groups": 1193260 },3261 "rougeL": {3262 "mean": 0.6160829855957196,3263 "ci_low": 0.6043230726396068,3264 "ci_high": 0.6291808085567466,3265 "n_items": 1387,3266 "n_groups": 1193267 },3268 "exact_match": {3269 "mean": 0.0,3270 "ci_low": 0.0,3271 "ci_high": 0.0,3272 "n_items": 1387,3273 "n_groups": 1193274 },3275 "number_recall": {3276 "mean": 1.0,3277 "ci_low": 1.0,3278 "ci_high": 1.0,3279 "n_items": 1387,3280 "n_groups": 1193281 },3282 "placeholders_exact": {3283 "mean": 1.0,3284 "ci_low": 1.0,3285 "ci_high": 1.0,3286 "n_items": 1387,3287 "n_groups": 1193288 }3289 },3290 "preface": {3291 "n": 362,3292 "chrf": {3293 "mean": 62.34562864292377,3294 "ci_low": 57.49845588640267,3295 "ci_high": 67.58465038581195,3296 "n_items": 362,3297 "n_groups": 133298 },3299 "edit_sim": {3300 "mean": 0.5509275022451771,3301 "ci_low": 0.5024103188687266,3302 "ci_high": 0.608254802491421,3303 "n_items": 362,3304 "n_groups": 133305 },3306 "rougeL": {3307 "mean": 0.5887347847249392,3308 "ci_low": 0.532375346898843,3309 "ci_high": 0.6547645703227547,3310 "n_items": 362,3311 "n_groups": 133312 },3313 "exact_match": {3314 "mean": 0.0,3315 "ci_low": 0.0,3316 "ci_high": 0.0,3317 "n_items": 362,3318 "n_groups": 133319 },3320 "number_recall": {3321 "mean": 1.0,3322 "ci_low": 1.0,3323 "ci_high": 1.0,3324 "n_items": 362,3325 "n_groups": 133326 },3327 "placeholders_exact": {3328 "mean": 1.0,3329 "ci_low": 1.0,3330 "ci_high": 1.0,3331 "n_items": 362,3332 "n_groups": 133333 }3334 },3335 "related_work": {3336 "n": 557,3337 "chrf": {3338 "mean": 68.00442751635427,3339 "ci_low": 66.20509420901006,3340 "ci_high": 69.75399386697093,3341 "n_items": 557,3342 "n_groups": 393343 },3344 "edit_sim": {3345 "mean": 0.5885595484686642,3346 "ci_low": 0.5670599978810992,3347 "ci_high": 0.6124156330075596,3348 "n_items": 557,3349 "n_groups": 393350 },3351 "rougeL": {3352 "mean": 0.6227272016298749,3353 "ci_low": 0.5998262321986533,3354 "ci_high": 0.646214578051263,3355 "n_items": 557,3356 "n_groups": 393357 },3358 "exact_match": {3359 "mean": 0.0,3360 "ci_low": 0.0,3361 "ci_high": 0.0,3362 "n_items": 557,3363 "n_groups": 393364 },3365 "number_recall": {3366 "mean": 0.9999055088349239,3367 "ci_low": 0.9997026042089044,3368 "ci_high": 1.0,3369 "n_items": 557,3370 "n_groups": 393371 },3372 "placeholders_exact": {3373 "mean": 1.0,3374 "ci_low": 1.0,3375 "ci_high": 1.0,3376 "n_items": 557,3377 "n_groups": 393378 }3379 },3380 "results": {3381 "n": 1501,3382 "chrf": {3383 "mean": 67.6233890027053,3384 "ci_low": 66.29696007848663,3385 "ci_high": 68.98580716052744,3386 "n_items": 1501,3387 "n_groups": 1533388 },3389 "edit_sim": {3390 "mean": 0.592775586087034,3391 "ci_low": 0.58092252012877,3392 "ci_high": 0.6053987100470044,3393 "n_items": 1501,3394 "n_groups": 1533395 },3396 "rougeL": {3397 "mean": 0.6425214075186916,3398 "ci_low": 0.6289677865317899,3399 "ci_high": 0.6568834957340861,3400 "n_items": 1501,3401 "n_groups": 1533402 },3403 "exact_match": {3404 "mean": 0.0,3405 "ci_low": 0.0,3406 "ci_high": 0.0,3407 "n_items": 1501,3408 "n_groups": 1533409 },3410 "number_recall": {3411 "mean": 0.9992745577022725,3412 "ci_low": 0.9984126984126983,3413 "ci_high": 0.9999541510472564,3414 "n_items": 1501,3415 "n_groups": 1533416 },3417 "placeholders_exact": {3418 "mean": 1.0,3419 "ci_low": 1.0,3420 "ci_high": 1.0,3421 "n_items": 1501,3422 "n_groups": 1533423 }3424 },3425 "theory": {3426 "n": 913,3427 "chrf": {3428 "mean": 67.80673668985655,3429 "ci_low": 66.52388579981874,3430 "ci_high": 69.11226347247391,3431 "n_items": 913,3432 "n_groups": 793433 },3434 "edit_sim": {3435 "mean": 0.5909481154335386,3436 "ci_low": 0.5732806984583372,3437 "ci_high": 0.6081964709302639,3438 "n_items": 913,3439 "n_groups": 793440 },3441 "rougeL": {3442 "mean": 0.6335743287318747,3443 "ci_low": 0.6158476795498001,3444 "ci_high": 0.6505903282071263,3445 "n_items": 913,3446 "n_groups": 793447 },3448 "exact_match": {3449 "mean": 0.0,3450 "ci_low": 0.0,3451 "ci_high": 0.0,3452 "n_items": 913,3453 "n_groups": 793454 },3455 "number_recall": {3456 "mean": 1.0,3457 "ci_low": 1.0,3458 "ci_high": 1.0,3459 "n_items": 913,3460 "n_groups": 793461 },3462 "placeholders_exact": {3463 "mean": 1.0,3464 "ci_low": 1.0,3465 "ci_high": 1.0,3466 "n_items": 913,3467 "n_groups": 793468 }3469 }3470 }3471 },3472 "B2_t5-small": {3473 "overall": {3474 "n": 15649,3475 "chrf": {3476 "mean": 68.83040420391266,3477 "ci_low": 68.30424603034916,3478 "ci_high": 69.34589365551466,3479 "n_items": 15649,3480 "n_groups": 6523481 },3482 "edit_sim": {3483 "mean": 0.6841118556843337,3484 "ci_low": 0.6792803276935759,3485 "ci_high": 0.6890227929602598,3486 "n_items": 15649,3487 "n_groups": 6523488 },3489 "rougeL": {3490 "mean": 0.6932070505325503,3491 "ci_low": 0.688035079181893,3492 "ci_high": 0.6984879782611016,3493 "n_items": 15649,3494 "n_groups": 6523495 },3496 "exact_match": {3497 "mean": 0.0,3498 "ci_low": 0.0,3499 "ci_high": 0.0,3500 "n_items": 15649,3501 "n_groups": 6523502 },3503 "number_recall": {3504 "mean": 0.9864194430285068,3505 "ci_low": 0.9827438007320243,3506 "ci_high": 0.989689639788037,3507 "n_items": 15649,3508 "n_groups": 6523509 },3510 "placeholders_exact": {3511 "mean": 0.7332736916096875,3512 "ci_low": 0.7051554126465206,3513 "ci_high": 0.7606728719234145,3514 "n_items": 15649,3515 "n_groups": 6523516 }3517 },3518 "by_variant": {3519 "A": {3520 "n": 2664,3521 "chrf": {3522 "mean": 68.3108825424772,3523 "ci_low": 67.72587744068993,3524 "ci_high": 68.90526230066541,3525 "n_items": 2664,3526 "n_groups": 6303527 },3528 "edit_sim": {3529 "mean": 0.6751038881756756,3530 "ci_low": 0.6695759484715175,3531 "ci_high": 0.680998226448832,3532 "n_items": 2664,3533 "n_groups": 6303534 },3535 "rougeL": {3536 "mean": 0.6817450308117767,3537 "ci_low": 0.676065402514391,3538 "ci_high": 0.6878846357257307,3539 "n_items": 2664,3540 "n_groups": 6303541 },3542 "exact_match": {3543 "mean": 0.0,3544 "ci_low": 0.0,3545 "ci_high": 0.0,3546 "n_items": 2664,3547 "n_groups": 6303548 },3549 "number_recall": {3550 "mean": 0.9856988178307633,3551 "ci_low": 0.9815196605462578,3552 "ci_high": 0.989314596203166,3553 "n_items": 2664,3554 "n_groups": 6303555 },3556 "placeholders_exact": {3557 "mean": 0.7331081081081081,3558 "ci_low": 0.7052390366017848,3559 "ci_high": 0.7604804445630272,3560 "n_items": 2664,3561 "n_groups": 6303562 }3563 },3564 "B": {3565 "n": 2539,3566 "chrf": {3567 "mean": 74.82560185774054,3568 "ci_low": 74.24151152729702,3569 "ci_high": 75.42299462653757,3570 "n_items": 2539,3571 "n_groups": 6143572 },3573 "edit_sim": {3574 "mean": 0.7548323584806368,3575 "ci_low": 0.7490630000380238,3576 "ci_high": 0.7606179492111275,3577 "n_items": 2539,3578 "n_groups": 6143579 },3580 "rougeL": {3581 "mean": 0.7625096322162453,3582 "ci_low": 0.7565641763339523,3583 "ci_high": 0.7685061241334112,3584 "n_items": 2539,3585 "n_groups": 6143586 },3587 "exact_match": {3588 "mean": 0.0,3589 "ci_low": 0.0,3590 "ci_high": 0.0,3591 "n_items": 2539,3592 "n_groups": 6143593 },3594 "number_recall": {3595 "mean": 0.9879802341537948,3596 "ci_low": 0.9840654900182226,3597 "ci_high": 0.9914760874680361,3598 "n_items": 2539,3599 "n_groups": 6143600 },3601 "placeholders_exact": {3602 "mean": 0.7325718786923986,3603 "ci_low": 0.7045445555235904,3604 "ci_high": 0.7591053634568581,3605 "n_items": 2539,3606 "n_groups": 6143607 }3608 },3609 "C": {3610 "n": 2663,3611 "chrf": {3612 "mean": 71.1313453474362,3613 "ci_low": 70.57275120547249,3614 "ci_high": 71.71008227065698,3615 "n_items": 2663,3616 "n_groups": 6383617 },3618 "edit_sim": {3619 "mean": 0.7267188255629258,3620 "ci_low": 0.7212684568059985,3621 "ci_high": 0.7322804869118957,3622 "n_items": 2663,3623 "n_groups": 6383624 },3625 "rougeL": {3626 "mean": 0.7461264027908023,3627 "ci_low": 0.7405730878321016,3628 "ci_high": 0.7518893398304686,3629 "n_items": 2663,3630 "n_groups": 6383631 },3632 "exact_match": {3633 "mean": 0.0,3634 "ci_low": 0.0,3635 "ci_high": 0.0,3636 "n_items": 2663,3637 "n_groups": 6383638 },3639 "number_recall": {3640 "mean": 0.9874807210749406,3641 "ci_low": 0.9829722765812918,3642 "ci_high": 0.9913824474215671,3643 "n_items": 2663,3644 "n_groups": 6383645 },3646 "placeholders_exact": {3647 "mean": 0.7375140818625611,3648 "ci_low": 0.7087927660796453,3649 "ci_high": 0.7654194748700343,3650 "n_items": 2663,3651 "n_groups": 6383652 }3653 },3654 "D": {3655 "n": 2708,3656 "chrf": {3657 "mean": 69.4587431093605,3658 "ci_low": 68.88110567185812,3659 "ci_high": 70.04736813145249,3660 "n_items": 2708,3661 "n_groups": 6383662 },3663 "edit_sim": {3664 "mean": 0.696263435703173,3665 "ci_low": 0.6910067841921711,3666 "ci_high": 0.7016707973291082,3667 "n_items": 2708,3668 "n_groups": 6383669 },3670 "rougeL": {3671 "mean": 0.7016029991277004,3672 "ci_low": 0.6963774302895359,3673 "ci_high": 0.7071221742175284,3674 "n_items": 2708,3675 "n_groups": 6383676 },3677 "exact_match": {3678 "mean": 0.0,3679 "ci_low": 0.0,3680 "ci_high": 0.0,3681 "n_items": 2708,3682 "n_groups": 6383683 },3684 "number_recall": {3685 "mean": 0.9859337611045704,3686 "ci_low": 0.9816457098569865,3687 "ci_high": 0.9896389398259832,3688 "n_items": 2708,3689 "n_groups": 6383690 },3691 "placeholders_exact": {3692 "mean": 0.73301329394387,3693 "ci_low": 0.7050152225224917,3694 "ci_high": 0.7612290578975056,3695 "n_items": 2708,3696 "n_groups": 6383697 }3698 },3699 "E": {3700 "n": 5075,3701 "chrf": {3702 "mean": 64.56109402496473,3703 "ci_low": 63.97938040409464,3704 "ci_high": 65.13154789137288,3705 "n_items": 5075,3706 "n_groups": 6233707 },3708 "edit_sim": {3709 "mean": 0.6246180683671996,3710 "ci_low": 0.6194203139510748,3711 "ci_high": 0.6299918526755242,3712 "n_items": 5075,3713 "n_groups": 6233714 },3715 "rougeL": {3716 "mean": 0.6323036223122248,3717 "ci_low": 0.6264680051600654,3718 "ci_high": 0.6385014500507051,3719 "n_items": 5075,3720 "n_groups": 6233721 },3722 "exact_match": {3723 "mean": 0.0,3724 "ci_low": 0.0,3725 "ci_high": 0.0,3726 "n_items": 5075,3727 "n_groups": 6233728 },3729 "number_recall": {3730 "mean": 0.9857191356535413,3731 "ci_low": 0.9819173310578478,3732 "ci_high": 0.9891472228290815,3733 "n_items": 5075,3734 "n_groups": 6233735 },3736 "placeholders_exact": {3737 "mean": 0.7316256157635468,3738 "ci_low": 0.7025063716185563,3739 "ci_high": 0.7602296385086115,3740 "n_items": 5075,3741 "n_groups": 6233742 }3743 }3744 },3745 "by_discipline": {3746 "biomedicine": {3747 "n": 2154,3748 "chrf": {3749 "mean": 69.10095557603023,3750 "ci_low": 68.08083903783157,3751 "ci_high": 70.10889298283232,3752 "n_items": 2154,3753 "n_groups": 2443754 },3755 "edit_sim": {3756 "mean": 0.681936785225258,3757 "ci_low": 0.6734648998600237,3758 "ci_high": 0.6908549630315906,3759 "n_items": 2154,3760 "n_groups": 2443761 },3762 "rougeL": {3763 "mean": 0.6903359445711789,3764 "ci_low": 0.6815602410671006,3765 "ci_high": 0.699395936762714,3766 "n_items": 2154,3767 "n_groups": 2443768 },3769 "exact_match": {3770 "mean": 0.0,3771 "ci_low": 0.0,3772 "ci_high": 0.0,3773 "n_items": 2154,3774 "n_groups": 2443775 },3776 "number_recall": {3777 "mean": 0.9824395128057261,3778 "ci_low": 0.9725749711672319,3779 "ci_high": 0.9899643421905964,3780 "n_items": 2154,3781 "n_groups": 2443782 },3783 "placeholders_exact": {3784 "mean": 0.6977715877437326,3785 "ci_low": 0.6300801216268309,3786 "ci_high": 0.7608198375995023,3787 "n_items": 2154,3788 "n_groups": 2443789 }3790 },3791 "chemistry": {3792 "n": 837,3793 "chrf": {3794 "mean": 72.21520245404442,3795 "ci_low": 70.96696556286753,3796 "ci_high": 73.55588281633959,3797 "n_items": 837,3798 "n_groups": 133799 },3800 "edit_sim": {3801 "mean": 0.7014177500295116,3802 "ci_low": 0.6879533290276583,3803 "ci_high": 0.7173967916091112,3804 "n_items": 837,3805 "n_groups": 133806 },3807 "rougeL": {3808 "mean": 0.717495760318007,3809 "ci_low": 0.7028213716930813,3810 "ci_high": 0.7341965666044061,3811 "n_items": 837,3812 "n_groups": 133813 },3814 "exact_match": {3815 "mean": 0.0,3816 "ci_low": 0.0,3817 "ci_high": 0.0,3818 "n_items": 837,3819 "n_groups": 133820 },3821 "number_recall": {3822 "mean": 0.9817509063565035,3823 "ci_low": 0.969689069411619,3824 "ci_high": 0.9909170526383152,3825 "n_items": 837,3826 "n_groups": 133827 },3828 "placeholders_exact": {3829 "mean": 0.6379928315412187,3830 "ci_low": 0.5487168141592921,3831 "ci_high": 0.7308202957298673,3832 "n_items": 837,3833 "n_groups": 133834 }3835 },3836 "computer_science": {3837 "n": 1375,3838 "chrf": {3839 "mean": 69.13987718767673,3840 "ci_low": 67.6792724505366,3841 "ci_high": 70.45080923144941,3842 "n_items": 1375,3843 "n_groups": 203844 },3845 "edit_sim": {3846 "mean": 0.6921186685978582,3847 "ci_low": 0.6757425623295255,3848 "ci_high": 0.706498523420094,3849 "n_items": 1375,3850 "n_groups": 203851 },3852 "rougeL": {3853 "mean": 0.6973827629667245,3854 "ci_low": 0.6792111715713705,3855 "ci_high": 0.7120057021303623,3856 "n_items": 1375,3857 "n_groups": 203858 },3859 "exact_match": {3860 "mean": 0.0,3861 "ci_low": 0.0,3862 "ci_high": 0.0,3863 "n_items": 1375,3864 "n_groups": 203865 },3866 "number_recall": {3867 "mean": 0.9892121212121211,3868 "ci_low": 0.97529564275014,3869 "ci_high": 0.9974959644213394,3870 "n_items": 1375,3871 "n_groups": 203872 },3873 "placeholders_exact": {3874 "mean": 0.6909090909090909,3875 "ci_low": 0.6163470789459619,3876 "ci_high": 0.7676572749523303,3877 "n_items": 1375,3878 "n_groups": 203879 }3880 },3881 "economics": {3882 "n": 1944,3883 "chrf": {3884 "mean": 68.46504710725964,3885 "ci_low": 67.64624271034008,3886 "ci_high": 69.21961915364051,3887 "n_items": 1944,3888 "n_groups": 1033889 },3890 "edit_sim": {3891 "mean": 0.6844659111357663,3892 "ci_low": 0.6755942545505714,3893 "ci_high": 0.6931853134461663,3894 "n_items": 1944,3895 "n_groups": 1033896 },3897 "rougeL": {3898 "mean": 0.6902913718171733,3899 "ci_low": 0.6801242513575841,3900 "ci_high": 0.7003331305274754,3901 "n_items": 1944,3902 "n_groups": 1033903 },3904 "exact_match": {3905 "mean": 0.0,3906 "ci_low": 0.0,3907 "ci_high": 0.0,3908 "n_items": 1944,3909 "n_groups": 1033910 },3911 "number_recall": {3912 "mean": 0.9946735988634137,3913 "ci_low": 0.9902406821620854,3914 "ci_high": 0.9980375488386175,3915 "n_items": 1944,3916 "n_groups": 1033917 },3918 "placeholders_exact": {3919 "mean": 0.8353909465020576,3920 "ci_low": 0.7826996658243458,3921 "ci_high": 0.8834430628963902,3922 "n_items": 1944,3923 "n_groups": 1033924 }3925 },3926 "engineering": {3927 "n": 1296,3928 "chrf": {3929 "mean": 66.26367377706995,3930 "ci_low": 64.91877441805156,3931 "ci_high": 67.68894109353278,3932 "n_items": 1296,3933 "n_groups": 173934 },3935 "edit_sim": {3936 "mean": 0.6545802711573013,3937 "ci_low": 0.642861458171349,3938 "ci_high": 0.6661809368977101,3939 "n_items": 1296,3940 "n_groups": 173941 },3942 "rougeL": {3943 "mean": 0.6666077393288755,3944 "ci_low": 0.6560241087482158,3945 "ci_high": 0.6778922517466573,3946 "n_items": 1296,3947 "n_groups": 173948 },3949 "exact_match": {3950 "mean": 0.0,3951 "ci_low": 0.0,3952 "ci_high": 0.0,3953 "n_items": 1296,3954 "n_groups": 173955 },3956 "number_recall": {3957 "mean": 0.9879197377644015,3958 "ci_low": 0.979294616021928,3959 "ci_high": 0.9944728030125382,3960 "n_items": 1296,3961 "n_groups": 173962 },3963 "placeholders_exact": {3964 "mean": 0.7021604938271605,3965 "ci_low": 0.6044821321804719,3966 "ci_high": 0.8056712188361652,3967 "n_items": 1296,3968 "n_groups": 173969 }3970 },3971 "finance": {3972 "n": 2043,3973 "chrf": {3974 "mean": 67.66990089570308,3975 "ci_low": 66.41927511555907,3976 "ci_high": 69.08682537519356,3977 "n_items": 2043,3978 "n_groups": 513979 },3980 "edit_sim": {3981 "mean": 0.6749317619422365,3982 "ci_low": 0.6617138697461153,3983 "ci_high": 0.6890181362482515,3984 "n_items": 2043,3985 "n_groups": 513986 },3987 "rougeL": {3988 "mean": 0.6832809073235949,3989 "ci_low": 0.6698383691859345,3990 "ci_high": 0.6983502588714876,3991 "n_items": 2043,3992 "n_groups": 513993 },3994 "exact_match": {3995 "mean": 0.0,3996 "ci_low": 0.0,3997 "ci_high": 0.0,3998 "n_items": 2043,3999 "n_groups": 514000 },4001 "number_recall": {4002 "mean": 0.9837856397694871,4003 "ci_low": 0.9719195010068338,4004 "ci_high": 0.9924653679667562,4005 "n_items": 2043,4006 "n_groups": 514007 },4008 "placeholders_exact": {4009 "mean": 0.8487518355359766,4010 "ci_low": 0.7829160240574153,4011 "ci_high": 0.906865363700339,4012 "n_items": 2043,4013 "n_groups": 514014 }4015 },4016 "general_reference": {4017 "n": 118,4018 "chrf": {4019 "mean": 75.64722844980474,4020 "ci_low": 62.666484837119704,4021 "ci_high": 76.98169741933313,4022 "n_items": 118,4023 "n_groups": 24024 },4025 "edit_sim": {4026 "mean": 0.7898016262663665,4027 "ci_low": 0.6205509693325109,4028 "ci_high": 0.8072012265119034,4029 "n_items": 118,4030 "n_groups": 24031 },4032 "rougeL": {4033 "mean": 0.816441691327601,4034 "ci_low": 0.6278129141877393,4035 "ci_high": 0.8358334347718857,4036 "n_items": 118,4037 "n_groups": 24038 },4039 "exact_match": {4040 "mean": 0.0,4041 "ci_low": 0.0,4042 "ci_high": 0.0,4043 "n_items": 118,4044 "n_groups": 24045 },4046 "number_recall": {4047 "mean": 0.9989406779661016,4048 "ci_low": 0.9988317757009346,4049 "ci_high": 1.0,4050 "n_items": 118,4051 "n_groups": 24052 },4053 "placeholders_exact": {4054 "mean": 1.0,4055 "ci_low": 1.0,4056 "ci_high": 1.0,4057 "n_items": 118,4058 "n_groups": 24059 }4060 },4061 "humanities": {4062 "n": 263,4063 "chrf": {4064 "mean": 63.11868639218365,4065 "ci_low": 60.45648538524554,4066 "ci_high": 64.61044758028054,4067 "n_items": 263,4068 "n_groups": 34069 },4070 "edit_sim": {4071 "mean": 0.6568092591801992,4072 "ci_low": 0.6238533537061939,4073 "ci_high": 0.6587317923216975,4074 "n_items": 263,4075 "n_groups": 34076 },4077 "rougeL": {4078 "mean": 0.6660385661960015,4079 "ci_low": 0.623379708309106,4080 "ci_high": 0.6732826148493815,4081 "n_items": 263,4082 "n_groups": 34083 },4084 "exact_match": {4085 "mean": 0.0,4086 "ci_low": 0.0,4087 "ci_high": 0.0,4088 "n_items": 263,4089 "n_groups": 34090 },4091 "number_recall": {4092 "mean": 1.0,4093 "ci_low": 1.0,4094 "ci_high": 1.0,4095 "n_items": 263,4096 "n_groups": 34097 },4098 "placeholders_exact": {4099 "mean": 1.0,4100 "ci_low": 1.0,4101 "ci_high": 1.0,4102 "n_items": 263,4103 "n_groups": 34104 }4105 },4106 "life_sciences": {4107 "n": 1874,4108 "chrf": {4109 "mean": 71.05713095886539,4110 "ci_low": 69.42286851407651,4111 "ci_high": 72.4876417820326,4112 "n_items": 1874,4113 "n_groups": 1434114 },4115 "edit_sim": {4116 "mean": 0.7038847162607594,4117 "ci_low": 0.6902628052851053,4118 "ci_high": 0.7169139474034223,4119 "n_items": 1874,4120 "n_groups": 1434121 },4122 "rougeL": {4123 "mean": 0.7142803832801932,4124 "ci_low": 0.7004476806495155,4125 "ci_high": 0.7276127846396256,4126 "n_items": 1874,4127 "n_groups": 1434128 },4129 "exact_match": {4130 "mean": 0.0,4131 "ci_low": 0.0,4132 "ci_high": 0.0,4133 "n_items": 1874,4134 "n_groups": 1434135 },4136 "number_recall": {4137 "mean": 0.9874776800786379,4138 "ci_low": 0.979116622101696,4139 "ci_high": 0.9938250900680818,4140 "n_items": 1874,4141 "n_groups": 1434142 },4143 "placeholders_exact": {4144 "mean": 0.6072572038420491,4145 "ci_low": 0.5193133317752427,4146 "ci_high": 0.6984804884584409,4147 "n_items": 1874,4148 "n_groups": 1434149 }4150 },4151 "mathematics": {4152 "n": 712,4153 "chrf": {4154 "mean": 67.04852519367749,4155 "ci_low": 65.00844141092217,4156 "ci_high": 69.4880244836876,4157 "n_items": 712,4158 "n_groups": 54159 },4160 "edit_sim": {4161 "mean": 0.6839741502580056,4162 "ci_low": 0.6635739772892326,4163 "ci_high": 0.6989522702441285,4164 "n_items": 712,4165 "n_groups": 54166 },4167 "rougeL": {4168 "mean": 0.6812092736459491,4169 "ci_low": 0.661247886219021,4170 "ci_high": 0.7031895876317407,4171 "n_items": 712,4172 "n_groups": 54173 },4174 "exact_match": {4175 "mean": 0.0,4176 "ci_low": 0.0,4177 "ci_high": 0.0,4178 "n_items": 712,4179 "n_groups": 54180 },4181 "number_recall": {4182 "mean": 0.9630672230391333,4183 "ci_low": 0.9330014373381721,4184 "ci_high": 0.990521043582268,4185 "n_items": 712,4186 "n_groups": 54187 },4188 "placeholders_exact": {4189 "mean": 0.5617977528089888,4190 "ci_low": 0.44,4191 "ci_high": 0.674863387978142,4192 "n_items": 712,4193 "n_groups": 54194 }4195 },4196 "other": {4197 "n": 669,4198 "chrf": {4199 "mean": 68.85890215442578,4200 "ci_low": 66.50678328141373,4201 "ci_high": 71.78329235146298,4202 "n_items": 669,4203 "n_groups": 134204 },4205 "edit_sim": {4206 "mean": 0.6740459447156049,4207 "ci_low": 0.6526813731561665,4208 "ci_high": 0.7016055851070508,4209 "n_items": 669,4210 "n_groups": 134211 },4212 "rougeL": {4213 "mean": 0.6844607929204329,4214 "ci_low": 0.6638125747190796,4215 "ci_high": 0.7116707899086271,4216 "n_items": 669,4217 "n_groups": 134218 },4219 "exact_match": {4220 "mean": 0.0,4221 "ci_low": 0.0,4222 "ci_high": 0.0,4223 "n_items": 669,4224 "n_groups": 134225 },4226 "number_recall": {4227 "mean": 0.998088238783306,4228 "ci_low": 0.9961498989235656,4229 "ci_high": 0.9996252396471007,4230 "n_items": 669,4231 "n_groups": 134232 },4233 "placeholders_exact": {4234 "mean": 0.828101644245142,4235 "ci_low": 0.6395860389610389,4236 "ci_high": 0.9246791712042184,4237 "n_items": 669,4238 "n_groups": 134239 }4240 },4241 "social_sciences": {4242 "n": 1536,4243 "chrf": {4244 "mean": 68.85949670933084,4245 "ci_low": 66.78974168694253,4246 "ci_high": 70.36867184591298,4247 "n_items": 1536,4248 "n_groups": 294249 },4250 "edit_sim": {4251 "mean": 0.6849839980415631,4252 "ci_low": 0.6670309856810197,4253 "ci_high": 0.699416220046132,4254 "n_items": 1536,4255 "n_groups": 294256 },4257 "rougeL": {4258 "mean": 0.6911333031831789,4259 "ci_low": 0.6714828903542289,4260 "ci_high": 0.7071930030951461,4261 "n_items": 1536,4262 "n_groups": 294263 },4264 "exact_match": {4265 "mean": 0.0,4266 "ci_low": 0.0,4267 "ci_high": 0.0,4268 "n_items": 1536,4269 "n_groups": 294270 },4271 "number_recall": {4272 "mean": 0.9967226675234487,4273 "ci_low": 0.9942343479917426,4274 "ci_high": 0.9987139753180339,4275 "n_items": 1536,4276 "n_groups": 294277 },4278 "placeholders_exact": {4279 "mean": 0.7955729166666666,4280 "ci_low": 0.7266274989611708,4281 "ci_high": 0.860086509273501,4282 "n_items": 1536,4283 "n_groups": 294284 }4285 },4286 "statistics": {4287 "n": 828,4288 "chrf": {4289 "mean": 69.18805295625154,4290 "ci_low": 66.71910256554938,4291 "ci_high": 71.8083430815517,4292 "n_items": 828,4293 "n_groups": 94294 },4295 "edit_sim": {4296 "mean": 0.6825148278860239,4297 "ci_low": 0.6641836543628179,4298 "ci_high": 0.7042211590094394,4299 "n_items": 828,4300 "n_groups": 94301 },4302 "rougeL": {4303 "mean": 0.7067627781701638,4304 "ci_low": 0.684103674391568,4305 "ci_high": 0.7315887589093156,4306 "n_items": 828,4307 "n_groups": 94308 },4309 "exact_match": {4310 "mean": 0.0,4311 "ci_low": 0.0,4312 "ci_high": 0.0,4313 "n_items": 828,4314 "n_groups": 94315 },4316 "number_recall": {4317 "mean": 0.9646719509263605,4318 "ci_low": 0.9298464805845608,4319 "ci_high": 0.9886513081458443,4320 "n_items": 828,4321 "n_groups": 94322 },4323 "placeholders_exact": {4324 "mean": 0.6340579710144928,4325 "ci_low": 0.549113394226005,4326 "ci_high": 0.7174196908573123,4327 "n_items": 828,4328 "n_groups": 94329 }4330 }4331 },4332 "by_era": {4333 "1900-1949": {4334 "n": 1164,4335 "chrf": {4336 "mean": 64.26884428643135,4337 "ci_low": 62.01735983044432,4338 "ci_high": 67.40059322576415,4339 "n_items": 1164,4340 "n_groups": 184341 },4342 "edit_sim": {4343 "mean": 0.6606980825402603,4344 "ci_low": 0.6368919509055597,4345 "ci_high": 0.6993640750575987,4346 "n_items": 1164,4347 "n_groups": 184348 },4349 "rougeL": {4350 "mean": 0.6704871236094939,4351 "ci_low": 0.6451448193219675,4352 "ci_high": 0.7121969635269102,4353 "n_items": 1164,4354 "n_groups": 184355 },4356 "exact_match": {4357 "mean": 0.0,4358 "ci_low": 0.0,4359 "ci_high": 0.0,4360 "n_items": 1164,4361 "n_groups": 184362 },4363 "number_recall": {4364 "mean": 0.9993628293241694,4365 "ci_low": 0.9982832883332631,4366 "ci_high": 1.0,4367 "n_items": 1164,4368 "n_groups": 184369 },4370 "placeholders_exact": {4371 "mean": 0.9948453608247423,4372 "ci_low": 0.9861671469740634,4373 "ci_high": 1.0,4374 "n_items": 1164,4375 "n_groups": 184376 }4377 },4378 "1950-1979": {4379 "n": 206,4380 "chrf": {4381 "mean": 62.23133568710763,4382 "ci_low": 60.92016248366658,4383 "ci_high": 62.547281037334386,4384 "n_items": 206,4385 "n_groups": 24386 },4387 "edit_sim": {4388 "mean": 0.6502446368982611,4389 "ci_low": 0.6172000657116994,4390 "ci_high": 0.6582071841721312,4391 "n_items": 206,4392 "n_groups": 24393 },4394 "rougeL": {4395 "mean": 0.6588327251531616,4396 "ci_low": 0.6315244308477408,4397 "ci_high": 0.6654130370339861,4398 "n_items": 206,4399 "n_groups": 24400 },4401 "exact_match": {4402 "mean": 0.0,4403 "ci_low": 0.0,4404 "ci_high": 0.0,4405 "n_items": 206,4406 "n_groups": 24407 },4408 "number_recall": {4409 "mean": 1.0,4410 "ci_low": 1.0,4411 "ci_high": 1.0,4412 "n_items": 206,4413 "n_groups": 24414 },4415 "placeholders_exact": {4416 "mean": 1.0,4417 "ci_low": 1.0,4418 "ci_high": 1.0,4419 "n_items": 206,4420 "n_groups": 24421 }4422 },4423 "1980-1999": {4424 "n": 151,4425 "chrf": {4426 "mean": 64.37321439821943,4427 "ci_low": 63.04536693917965,4428 "ci_high": 77.78540030006177,4429 "n_items": 151,4430 "n_groups": 44431 },4432 "edit_sim": {4433 "mean": 0.6660122973783752,4434 "ci_low": 0.6532322458729404,4435 "ci_high": 0.7907838515378773,4436 "n_items": 151,4437 "n_groups": 44438 },4439 "rougeL": {4440 "mean": 0.6714777109959055,4441 "ci_low": 0.6588833082089998,4442 "ci_high": 0.8033050510868991,4443 "n_items": 151,4444 "n_groups": 44445 },4446 "exact_match": {4447 "mean": 0.0,4448 "ci_low": 0.0,4449 "ci_high": 0.0,4450 "n_items": 151,4451 "n_groups": 44452 },4453 "number_recall": {4454 "mean": 1.0,4455 "ci_low": 1.0,4456 "ci_high": 1.0,4457 "n_items": 151,4458 "n_groups": 44459 },4460 "placeholders_exact": {4461 "mean": 0.9602649006622517,4462 "ci_low": 0.21739130434782608,4463 "ci_high": 1.0,4464 "n_items": 151,4465 "n_groups": 44466 }4467 },4468 "2000-2009": {4469 "n": 1545,4470 "chrf": {4471 "mean": 69.48228036644537,4472 "ci_low": 68.13380959879326,4473 "ci_high": 70.82373110070122,4474 "n_items": 1545,4475 "n_groups": 694476 },4477 "edit_sim": {4478 "mean": 0.694771603837157,4479 "ci_low": 0.6824087997711572,4480 "ci_high": 0.7075450978118499,4481 "n_items": 1545,4482 "n_groups": 694483 },4484 "rougeL": {4485 "mean": 0.703857321073683,4486 "ci_low": 0.6915276585236718,4487 "ci_high": 0.7164871186765885,4488 "n_items": 1545,4489 "n_groups": 694490 },4491 "exact_match": {4492 "mean": 0.0,4493 "ci_low": 0.0,4494 "ci_high": 0.0,4495 "n_items": 1545,4496 "n_groups": 694497 },4498 "number_recall": {4499 "mean": 0.9900193993454987,4500 "ci_low": 0.9781386606685923,4501 "ci_high": 0.9979193979631521,4502 "n_items": 1545,4503 "n_groups": 694504 },4505 "placeholders_exact": {4506 "mean": 0.7132686084142394,4507 "ci_low": 0.639105781504912,4508 "ci_high": 0.7844955413165579,4509 "n_items": 1545,4510 "n_groups": 694511 }4512 },4513 "2010-2017": {4514 "n": 12583,4515 "chrf": {4516 "mean": 69.33385734290628,4517 "ci_low": 68.87375044269248,4518 "ci_high": 69.82118625505335,4519 "n_items": 12583,4520 "n_groups": 5594521 },4522 "edit_sim": {4523 "mean": 0.6857405611931725,4524 "ci_low": 0.680806622952577,4525 "ci_high": 0.6903913739655649,4526 "n_items": 12583,4527 "n_groups": 5594528 },4529 "rougeL": {4530 "mean": 0.694824595494052,4531 "ci_low": 0.6894801891959597,4532 "ci_high": 0.6999916928677983,4533 "n_items": 12583,4534 "n_groups": 5594535 },4536 "exact_match": {4537 "mean": 0.0,4538 "ci_low": 0.0,4539 "ci_high": 0.0,4540 "n_items": 12583,4541 "n_groups": 5594542 },4543 "number_recall": {4544 "mean": 0.9843947833291722,4545 "ci_low": 0.9800726342243907,4546 "ci_high": 0.9882025031160608,4547 "n_items": 12583,4548 "n_groups": 5594549 },4550 "placeholders_exact": {4551 "mean": 0.7044425017881268,4552 "ci_low": 0.6767512850793217,4553 "ci_high": 0.7309976411437248,4554 "n_items": 12583,4555 "n_groups": 5594556 }4557 }4558 },4559 "by_role": {4560 "abstract": {4561 "n": 1255,4562 "chrf": {4563 "mean": 70.49228580932895,4564 "ci_low": 69.69621368297996,4565 "ci_high": 71.36038096654839,4566 "n_items": 1255,4567 "n_groups": 1954568 },4569 "edit_sim": {4570 "mean": 0.6855801415386156,4571 "ci_low": 0.6758223572597425,4572 "ci_high": 0.6956886862894467,4573 "n_items": 1255,4574 "n_groups": 1954575 },4576 "rougeL": {4577 "mean": 0.6904200247194261,4578 "ci_low": 0.6812986397818308,4579 "ci_high": 0.6999639346167272,4580 "n_items": 1255,4581 "n_groups": 1954582 },4583 "exact_match": {4584 "mean": 0.0,4585 "ci_low": 0.0,4586 "ci_high": 0.0,4587 "n_items": 1255,4588 "n_groups": 1954589 },4590 "number_recall": {4591 "mean": 0.9829190328073416,4592 "ci_low": 0.9702915583244521,4593 "ci_high": 0.9925788076245944,4594 "n_items": 1255,4595 "n_groups": 1954596 },4597 "placeholders_exact": {4598 "mean": 0.9808764940239044,4599 "ci_low": 0.9596072793062322,4600 "ci_high": 0.9954376082814207,4601 "n_items": 1255,4602 "n_groups": 1954603 }4604 },4605 "background": {4606 "n": 964,4607 "chrf": {4608 "mean": 69.07782783682619,4609 "ci_low": 68.23267127121393,4610 "ci_high": 69.93175259940047,4611 "n_items": 964,4612 "n_groups": 844613 },4614 "edit_sim": {4615 "mean": 0.6917633794851059,4616 "ci_low": 0.6801037439653904,4617 "ci_high": 0.7028568315194765,4618 "n_items": 964,4619 "n_groups": 844620 },4621 "rougeL": {4622 "mean": 0.694232993136882,4623 "ci_low": 0.6799677648863661,4624 "ci_high": 0.7078361358169328,4625 "n_items": 964,4626 "n_groups": 844627 },4628 "exact_match": {4629 "mean": 0.0,4630 "ci_low": 0.0,4631 "ci_high": 0.0,4632 "n_items": 964,4633 "n_groups": 844634 },4635 "number_recall": {4636 "mean": 0.9813117466903774,4637 "ci_low": 0.9624918285147931,4638 "ci_high": 0.9950939614406467,4639 "n_items": 964,4640 "n_groups": 844641 },4642 "placeholders_exact": {4643 "mean": 0.5217842323651453,4644 "ci_low": 0.40310813630402215,4645 "ci_high": 0.6203620814859888,4646 "n_items": 964,4647 "n_groups": 844648 }4649 },4650 "chapter": {4651 "n": 1287,4652 "chrf": {4653 "mean": 64.28576599659623,4654 "ci_low": 63.08178260169719,4655 "ci_high": 65.98513421140197,4656 "n_items": 1287,4657 "n_groups": 214658 },4659 "edit_sim": {4660 "mean": 0.6581491943786804,4661 "ci_low": 0.6460517266019355,4662 "ci_high": 0.6799393024851728,4663 "n_items": 1287,4664 "n_groups": 214665 },4666 "rougeL": {4667 "mean": 0.6691806188399442,4668 "ci_low": 0.6569976222465597,4669 "ci_high": 0.6899512745900824,4670 "n_items": 1287,4671 "n_groups": 214672 },4673 "exact_match": {4674 "mean": 0.0,4675 "ci_low": 0.0,4676 "ci_high": 0.0,4677 "n_items": 1287,4678 "n_groups": 214679 },4680 "number_recall": {4681 "mean": 0.9992100492100492,4682 "ci_low": 0.9981540289967304,4683 "ci_high": 1.0,4684 "n_items": 1287,4685 "n_groups": 214686 },4687 "placeholders_exact": {4688 "mean": 0.9953379953379954,4689 "ci_low": 0.986656287508193,4690 "ci_high": 1.0,4691 "n_items": 1287,4692 "n_groups": 214693 }4694 },4695 "conclusion": {4696 "n": 1168,4697 "chrf": {4698 "mean": 67.45208100971183,4699 "ci_low": 66.46706042397415,4700 "ci_high": 68.43166930888927,4701 "n_items": 1168,4702 "n_groups": 1544703 },4704 "edit_sim": {4705 "mean": 0.6674674291859282,4706 "ci_low": 0.6566194190465311,4707 "ci_high": 0.6785765842404619,4708 "n_items": 1168,4709 "n_groups": 1544710 },4711 "rougeL": {4712 "mean": 0.6680135978865991,4713 "ci_low": 0.6571292327777055,4714 "ci_high": 0.6788874300831296,4715 "n_items": 1168,4716 "n_groups": 1544717 },4718 "exact_match": {4719 "mean": 0.0,4720 "ci_low": 0.0,4721 "ci_high": 0.0,4722 "n_items": 1168,4723 "n_groups": 1544724 },4725 "number_recall": {4726 "mean": 0.993830180474016,4727 "ci_low": 0.987216993581594,4728 "ci_high": 0.9987137423480263,4729 "n_items": 1168,4730 "n_groups": 1544731 },4732 "placeholders_exact": {4733 "mean": 0.8792808219178082,4734 "ci_low": 0.8299044925397606,4735 "ci_high": 0.9244478963303582,4736 "n_items": 1168,4737 "n_groups": 1544738 }4739 },4740 "data": {4741 "n": 912,4742 "chrf": {4743 "mean": 70.85148084588721,4744 "ci_low": 69.8048380395964,4745 "ci_high": 71.93255172642021,4746 "n_items": 912,4747 "n_groups": 1044748 },4749 "edit_sim": {4750 "mean": 0.6958177351345811,4751 "ci_low": 0.6854580057334577,4752 "ci_high": 0.7065196136551033,4753 "n_items": 912,4754 "n_groups": 1044755 },4756 "rougeL": {4757 "mean": 0.7164195212254919,4758 "ci_low": 0.704761961938359,4759 "ci_high": 0.7282643336884433,4760 "n_items": 912,4761 "n_groups": 1044762 },4763 "exact_match": {4764 "mean": 0.0,4765 "ci_low": 0.0,4766 "ci_high": 0.0,4767 "n_items": 912,4768 "n_groups": 1044769 },4770 "number_recall": {4771 "mean": 0.9841351291316666,4772 "ci_low": 0.9735037388393907,4773 "ci_high": 0.9918504556735327,4774 "n_items": 912,4775 "n_groups": 1044776 },4777 "placeholders_exact": {4778 "mean": 0.7730263157894737,4779 "ci_low": 0.6958798560065136,4780 "ci_high": 0.836565596436836,4781 "n_items": 912,4782 "n_groups": 1044783 }4784 },4785 "discussion": {4786 "n": 1601,4787 "chrf": {4788 "mean": 68.72716453457515,4789 "ci_low": 67.87806773403096,4790 "ci_high": 69.5568178357021,4791 "n_items": 1601,4792 "n_groups": 1424793 },4794 "edit_sim": {4795 "mean": 0.6821509320543754,4796 "ci_low": 0.6732865528214997,4797 "ci_high": 0.69115710980646,4798 "n_items": 1601,4799 "n_groups": 1424800 },4801 "rougeL": {4802 "mean": 0.6843058435848538,4803 "ci_low": 0.6745933055015766,4804 "ci_high": 0.6939795179153875,4805 "n_items": 1601,4806 "n_groups": 1424807 },4808 "exact_match": {4809 "mean": 0.0,4810 "ci_low": 0.0,4811 "ci_high": 0.0,4812 "n_items": 1601,4813 "n_groups": 1424814 },4815 "number_recall": {4816 "mean": 0.9841882018077044,4817 "ci_low": 0.9685900592061221,4818 "ci_high": 0.9960242176784176,4819 "n_items": 1601,4820 "n_groups": 1424821 },4822 "placeholders_exact": {4823 "mean": 0.5965021861336665,4824 "ci_low": 0.5222928116469517,4825 "ci_high": 0.6672969671120879,4826 "n_items": 1601,4827 "n_groups": 1424828 }4829 },4830 "introduction": {4831 "n": 1789,4832 "chrf": {4833 "mean": 68.13084434624147,4834 "ci_low": 67.2227565487288,4835 "ci_high": 69.04148483126791,4836 "n_items": 1789,4837 "n_groups": 1764838 },4839 "edit_sim": {4840 "mean": 0.6794756090735904,4841 "ci_low": 0.6697591691696614,4842 "ci_high": 0.6893208162029468,4843 "n_items": 1789,4844 "n_groups": 1764845 },4846 "rougeL": {4847 "mean": 0.6752360352706627,4848 "ci_low": 0.6657072351239857,4849 "ci_high": 0.6847006940215702,4850 "n_items": 1789,4851 "n_groups": 1764852 },4853 "exact_match": {4854 "mean": 0.0,4855 "ci_low": 0.0,4856 "ci_high": 0.0,4857 "n_items": 1789,4858 "n_groups": 1764859 },4860 "number_recall": {4861 "mean": 0.996394838625135,4862 "ci_low": 0.9936997757915162,4863 "ci_high": 0.9984840988132176,4864 "n_items": 1789,4865 "n_groups": 1764866 },4867 "placeholders_exact": {4868 "mean": 0.4510899944102851,4869 "ci_low": 0.3762843771859421,4870 "ci_high": 0.5285244903162887,4871 "n_items": 1789,4872 "n_groups": 1764873 }4874 },4875 "limitations": {4876 "n": 425,4877 "chrf": {4878 "mean": 67.60883809839137,4879 "ci_low": 66.1254456596341,4880 "ci_high": 69.25167407708841,4881 "n_items": 425,4882 "n_groups": 414883 },4884 "edit_sim": {4885 "mean": 0.6699086850778384,4886 "ci_low": 0.6542721703879565,4887 "ci_high": 0.6865956480983586,4888 "n_items": 425,4889 "n_groups": 414890 },4891 "rougeL": {4892 "mean": 0.6774596634430418,4893 "ci_low": 0.6566721527255823,4894 "ci_high": 0.6999200026946348,4895 "n_items": 425,4896 "n_groups": 414897 },4898 "exact_match": {4899 "mean": 0.0,4900 "ci_low": 0.0,4901 "ci_high": 0.0,4902 "n_items": 425,4903 "n_groups": 414904 },4905 "number_recall": {4906 "mean": 0.9933155080213903,4907 "ci_low": 0.9818171879141266,4908 "ci_high": 1.0,4909 "n_items": 425,4910 "n_groups": 414911 },4912 "placeholders_exact": {4913 "mean": 0.7741176470588236,4914 "ci_low": 0.6566670933606418,4915 "ci_high": 0.885498818073686,4916 "n_items": 425,4917 "n_groups": 414918 }4919 },4920 "methods": {4921 "n": 1528,4922 "chrf": {4923 "mean": 70.63412890824166,4924 "ci_low": 69.7445414260231,4925 "ci_high": 71.58089196402041,4926 "n_items": 1528,4927 "n_groups": 1514928 },4929 "edit_sim": {4930 "mean": 0.6985914769065037,4931 "ci_low": 0.6894107332136988,4932 "ci_high": 0.7076863945346341,4933 "n_items": 1528,4934 "n_groups": 1514935 },4936 "rougeL": {4937 "mean": 0.720659009204832,4938 "ci_low": 0.7114401831717072,4939 "ci_high": 0.7307148205952384,4940 "n_items": 1528,4941 "n_groups": 1514942 },4943 "exact_match": {4944 "mean": 0.0,4945 "ci_low": 0.0,4946 "ci_high": 0.0,4947 "n_items": 1528,4948 "n_groups": 1514949 },4950 "number_recall": {4951 "mean": 0.9761252149323831,4952 "ci_low": 0.9627381616651517,4953 "ci_high": 0.9874306388029503,4954 "n_items": 1528,4955 "n_groups": 1514956 },4957 "placeholders_exact": {4958 "mean": 0.7545811518324608,4959 "ci_low": 0.6990643550793023,4960 "ci_high": 0.8109008458739142,4961 "n_items": 1528,4962 "n_groups": 1514963 }4964 },4965 "other": {4966 "n": 1387,4967 "chrf": {4968 "mean": 68.917357398491,4969 "ci_low": 67.88175106877284,4970 "ci_high": 70.00893178049373,4971 "n_items": 1387,4972 "n_groups": 1194973 },4974 "edit_sim": {4975 "mean": 0.6850904961288296,4976 "ci_low": 0.6743137569630834,4977 "ci_high": 0.6966460292258342,4978 "n_items": 1387,4979 "n_groups": 1194980 },4981 "rougeL": {4982 "mean": 0.6933627413305364,4983 "ci_low": 0.6834826229483008,4984 "ci_high": 0.7039955791264666,4985 "n_items": 1387,4986 "n_groups": 1194987 },4988 "exact_match": {4989 "mean": 0.0,4990 "ci_low": 0.0,4991 "ci_high": 0.0,4992 "n_items": 1387,4993 "n_groups": 1194994 },4995 "number_recall": {4996 "mean": 0.9901593959993382,4997 "ci_low": 0.983285085476049,4998 "ci_high": 0.99608789973807,4999 "n_items": 1387,5000 "n_groups": 1195001 },5002 "placeholders_exact": {5003 "mean": 0.5940879596250901,5004 "ci_low": 0.5038376577840112,5005 "ci_high": 0.6817838414714484,5006 "n_items": 1387,5007 "n_groups": 1195008 }5009 },5010 "preface": {5011 "n": 362,5012 "chrf": {5013 "mean": 63.7469551824738,5014 "ci_low": 59.1043334857153,5015 "ci_high": 68.60226199399585,5016 "n_items": 362,5017 "n_groups": 135018 },5019 "edit_sim": {5020 "mean": 0.658630354449019,5021 "ci_low": 0.6092678434248737,5022 "ci_high": 0.7108183112871086,5023 "n_items": 362,5024 "n_groups": 135025 },5026 "rougeL": {5027 "mean": 0.6665264201079959,5028 "ci_low": 0.6116118764844634,5029 "ci_high": 0.7267176366950766,5030 "n_items": 362,5031 "n_groups": 135032 },5033 "exact_match": {5034 "mean": 0.0,5035 "ci_low": 0.0,5036 "ci_high": 0.0,5037 "n_items": 362,5038 "n_groups": 135039 },5040 "number_recall": {5041 "mean": 0.9996546961325967,5042 "ci_low": 0.9991118873797278,5043 "ci_high": 1.0,5044 "n_items": 362,5045 "n_groups": 135046 },5047 "placeholders_exact": {5048 "mean": 1.0,5049 "ci_low": 1.0,5050 "ci_high": 1.0,5051 "n_items": 362,5052 "n_groups": 135053 }5054 },5055 "related_work": {5056 "n": 557,5057 "chrf": {5058 "mean": 70.42566538178752,5059 "ci_low": 68.93592673583387,5060 "ci_high": 71.9247079784059,5061 "n_items": 557,5062 "n_groups": 395063 },5064 "edit_sim": {5065 "mean": 0.6941327673330409,5066 "ci_low": 0.677628862408734,5067 "ci_high": 0.713319278864655,5068 "n_items": 557,5069 "n_groups": 395070 },5071 "rougeL": {5072 "mean": 0.699758776687086,5073 "ci_low": 0.6813395566742597,5074 "ci_high": 0.7180380998036836,5075 "n_items": 557,5076 "n_groups": 395077 },5078 "exact_match": {5079 "mean": 0.0,5080 "ci_low": 0.0,5081 "ci_high": 0.0,5082 "n_items": 557,5083 "n_groups": 395084 },5085 "number_recall": {5086 "mean": 0.9960939753737302,5087 "ci_low": 0.992197318842155,5088 "ci_high": 0.9993048097240057,5089 "n_items": 557,5090 "n_groups": 395091 },5092 "placeholders_exact": {5093 "mean": 0.7145421903052065,5094 "ci_low": 0.5720595975713367,5095 "ci_high": 0.8498316744730678,5096 "n_items": 557,5097 "n_groups": 395098 }5099 },5100 "results": {5101 "n": 1501,5102 "chrf": {5103 "mean": 70.78450731017112,5104 "ci_low": 69.66046262074644,5105 "ci_high": 71.9118461387716,5106 "n_items": 1501,5107 "n_groups": 1535108 },5109 "edit_sim": {5110 "mean": 0.6976170100412791,5111 "ci_low": 0.6877240220337129,5112 "ci_high": 0.7078892492465269,5113 "n_items": 1501,5114 "n_groups": 1535115 },5116 "rougeL": {5117 "mean": 0.7213162534916825,5118 "ci_low": 0.7100388430227907,5119 "ci_high": 0.7330376129972721,5120 "n_items": 1501,5121 "n_groups": 1535122 },5123 "exact_match": {5124 "mean": 0.0,5125 "ci_low": 0.0,5126 "ci_high": 0.0,5127 "n_items": 1501,5128 "n_groups": 1535129 },5130 "number_recall": {5131 "mean": 0.9738648219251612,5132 "ci_low": 0.9623276671247724,5133 "ci_high": 0.984206185314922,5134 "n_items": 1501,5135 "n_groups": 1535136 },5137 "placeholders_exact": {5138 "mean": 0.8414390406395736,5139 "ci_low": 0.7889723421172194,5140 "ci_high": 0.8906161865808804,5141 "n_items": 1501,5142 "n_groups": 1535143 }5144 },5145 "theory": {5146 "n": 913,5147 "chrf": {5148 "mean": 69.23482910879916,5149 "ci_low": 67.95981763443187,5150 "ci_high": 70.57252969977246,5151 "n_items": 913,5152 "n_groups": 795153 },5154 "edit_sim": {5155 "mean": 0.695414506694028,5156 "ci_low": 0.6801773202309974,5157 "ci_high": 0.7100786373789296,5158 "n_items": 913,5159 "n_groups": 795160 },5161 "rougeL": {5162 "mean": 0.7112083111979506,5163 "ci_low": 0.6950773944258876,5164 "ci_high": 0.7270667600857829,5165 "n_items": 913,5166 "n_groups": 795167 },5168 "exact_match": {5169 "mean": 0.0,5170 "ci_low": 0.0,5171 "ci_high": 0.0,5172 "n_items": 913,5173 "n_groups": 795174 },5175 "number_recall": {5176 "mean": 0.9735882925641961,5177 "ci_low": 0.954829756748621,5178 "ci_high": 0.9903366882985283,5179 "n_items": 913,5180 "n_groups": 795181 },5182 "placeholders_exact": {5183 "mean": 0.6976998904709748,5184 "ci_low": 0.5980113939264702,5185 "ci_high": 0.7843623071822038,5186 "n_items": 913,5187 "n_groups": 795188 }5189 }5190 }5191 },5192 "htr-m1-small": {5193 "overall": {5194 "n": 15649,5195 "chrf": {5196 "mean": 69.01877397269232,5197 "ci_low": 68.48247498109687,5198 "ci_high": 69.54266649528925,5199 "n_items": 15649,5200 "n_groups": 6525201 },5202 "edit_sim": {5203 "mean": 0.6794887115686464,5204 "ci_low": 0.6745799084421338,5205 "ci_high": 0.6844325128440454,5206 "n_items": 15649,5207 "n_groups": 6525208 },5209 "rougeL": {5210 "mean": 0.6881556536577896,5211 "ci_low": 0.6828443653331948,5212 "ci_high": 0.6934699249372112,5213 "n_items": 15649,5214 "n_groups": 6525215 },5216 "exact_match": {5217 "mean": 0.0,5218 "ci_low": 0.0,5219 "ci_high": 0.0,5220 "n_items": 15649,5221 "n_groups": 6525222 },5223 "number_recall": {5224 "mean": 0.9899920041162837,5225 "ci_low": 0.9879932565204333,5226 "ci_high": 0.9917429898891365,5227 "n_items": 15649,5228 "n_groups": 6525229 },5230 "placeholders_exact": {5231 "mean": 0.9907981340660745,5232 "ci_low": 0.9879549690586584,5233 "ci_high": 0.9932774525794598,5234 "n_items": 15649,5235 "n_groups": 6525236 }5237 },5238 "by_variant": {5239 "A": {5240 "n": 2664,5241 "chrf": {5242 "mean": 68.41424894634778,5243 "ci_low": 67.79994416195348,5244 "ci_high": 69.02922762278058,5245 "n_items": 2664,5246 "n_groups": 6305247 },5248 "edit_sim": {5249 "mean": 0.6700139610402278,5250 "ci_low": 0.6643591254783299,5251 "ci_high": 0.6761895902376605,5252 "n_items": 2664,5253 "n_groups": 6305254 },5255 "rougeL": {5256 "mean": 0.6759256883852605,5257 "ci_low": 0.6698744593132399,5258 "ci_high": 0.6823311425856703,5259 "n_items": 2664,5260 "n_groups": 6305261 },5262 "exact_match": {5263 "mean": 0.0,5264 "ci_low": 0.0,5265 "ci_high": 0.0,5266 "n_items": 2664,5267 "n_groups": 6305268 },5269 "number_recall": {5270 "mean": 0.9890681308069676,5271 "ci_low": 0.9864410722214967,5272 "ci_high": 0.9915459614955767,5273 "n_items": 2664,5274 "n_groups": 6305275 },5276 "placeholders_exact": {5277 "mean": 0.987987987987988,5278 "ci_low": 0.9838759024638524,5279 "ci_high": 0.9917075790555459,5280 "n_items": 2664,5281 "n_groups": 6305282 }5283 },5284 "B": {5285 "n": 2539,5286 "chrf": {5287 "mean": 74.63621127144887,5288 "ci_low": 74.02499894560285,5289 "ci_high": 75.21393280190617,5290 "n_items": 2539,5291 "n_groups": 6145292 },5293 "edit_sim": {5294 "mean": 0.7473832187016465,5295 "ci_low": 0.7417119463969144,5296 "ci_high": 0.7530325090679115,5297 "n_items": 2539,5298 "n_groups": 6145299 },5300 "rougeL": {5301 "mean": 0.754846011933392,5302 "ci_low": 0.7489551338701228,5303 "ci_high": 0.7607473058369771,5304 "n_items": 2539,5305 "n_groups": 6145306 },5307 "exact_match": {5308 "mean": 0.0,5309 "ci_low": 0.0,5310 "ci_high": 0.0,5311 "n_items": 2539,5312 "n_groups": 6145313 },5314 "number_recall": {5315 "mean": 0.9918985977476423,5316 "ci_low": 0.9896777685765074,5317 "ci_high": 0.9938770298648668,5318 "n_items": 2539,5319 "n_groups": 6145320 },5321 "placeholders_exact": {5322 "mean": 0.9917290271760536,5323 "ci_low": 0.9878830849330913,5324 "ci_high": 0.9950293568393377,5325 "n_items": 2539,5326 "n_groups": 6145327 }5328 },5329 "C": {5330 "n": 2663,5331 "chrf": {5332 "mean": 71.51674162090903,5333 "ci_low": 70.9839445057458,5334 "ci_high": 72.07850295127581,5335 "n_items": 2663,5336 "n_groups": 6385337 },5338 "edit_sim": {5339 "mean": 0.722312172148383,5340 "ci_low": 0.7170257621846392,5341 "ci_high": 0.7276445211563063,5342 "n_items": 2663,5343 "n_groups": 6385344 },5345 "rougeL": {5346 "mean": 0.7421802862014091,5347 "ci_low": 0.7366818641673664,5348 "ci_high": 0.7478152869714676,5349 "n_items": 2663,5350 "n_groups": 6385351 },5352 "exact_match": {5353 "mean": 0.0,5354 "ci_low": 0.0,5355 "ci_high": 0.0,5356 "n_items": 2663,5357 "n_groups": 6385358 },5359 "number_recall": {5360 "mean": 0.9912134971309221,5361 "ci_low": 0.988733322655336,5362 "ci_high": 0.9933648302626586,5363 "n_items": 2663,5364 "n_groups": 6385365 },5366 "placeholders_exact": {5367 "mean": 0.9913631242959069,5368 "ci_low": 0.9872535442334524,5369 "ci_high": 0.9951288901841411,5370 "n_items": 2663,5371 "n_groups": 6385372 }5373 },5374 "D": {5375 "n": 2708,5376 "chrf": {5377 "mean": 69.65244762733548,5378 "ci_low": 69.08128283230583,5379 "ci_high": 70.25101602164652,5380 "n_items": 2708,5381 "n_groups": 6385382 },5383 "edit_sim": {5384 "mean": 0.6905744287411734,5385 "ci_low": 0.6852428310179535,5386 "ci_high": 0.6959835120693104,5387 "n_items": 2708,5388 "n_groups": 6385389 },5390 "rougeL": {5391 "mean": 0.6952719443025603,5392 "ci_low": 0.6898139583695353,5393 "ci_high": 0.7008586261869943,5394 "n_items": 2708,5395 "n_groups": 6385396 },5397 "exact_match": {5398 "mean": 0.0,5399 "ci_low": 0.0,5400 "ci_high": 0.0,5401 "n_items": 2708,5402 "n_groups": 6385403 },5404 "number_recall": {5405 "mean": 0.9891157322514448,5406 "ci_low": 0.9864083680651315,5407 "ci_high": 0.991429638590722,5408 "n_items": 2708,5409 "n_groups": 6385410 },5411 "placeholders_exact": {5412 "mean": 0.992245199409158,5413 "ci_low": 0.9888811612460031,5414 "ci_high": 0.9952729417587857,5415 "n_items": 2708,5416 "n_groups": 6385417 }5418 },5419 "E": {5420 "n": 5075,5421 "chrf": {5422 "mean": 64.87684397558182,5423 "ci_low": 64.26960212814515,5424 "ci_high": 65.47903067166457,5425 "n_items": 5075,5426 "n_groups": 6235427 },5428 "edit_sim": {5429 "mean": 0.6221089251981992,5430 "ci_low": 0.6167709760075789,5431 "ci_high": 0.6276922239641035,5432 "n_items": 5075,5433 "n_groups": 6235434 },5435 "rougeL": {5436 "mean": 0.6290650716468664,5437 "ci_low": 0.6230696191627103,5438 "ci_high": 0.6353841301297821,5439 "n_items": 5075,5440 "n_groups": 6235441 },5442 "exact_match": {5443 "mean": 0.0,5444 "ci_low": 0.0,5445 "ci_high": 0.0,5446 "n_items": 5075,5447 "n_groups": 6235448 },5449 "number_recall": {5450 "mean": 0.989349731323772,5451 "ci_low": 0.9871346331312432,5452 "ci_high": 0.9912225720624507,5453 "n_items": 5075,5454 "n_groups": 6235455 },5456 "placeholders_exact": {5457 "mean": 0.9907389162561576,5458 "ci_low": 0.9875521280041273,5459 "ci_high": 0.993497859543922,5460 "n_items": 5075,5461 "n_groups": 6235462 }5463 }5464 },5465 "by_discipline": {5466 "biomedicine": {5467 "n": 2154,5468 "chrf": {5469 "mean": 69.1227246453803,5470 "ci_low": 67.99000096196002,5471 "ci_high": 70.19278777193749,5472 "n_items": 2154,5473 "n_groups": 2445474 },5475 "edit_sim": {5476 "mean": 0.6759898048164359,5477 "ci_low": 0.6675846352195546,5478 "ci_high": 0.6846273404677777,5479 "n_items": 2154,5480 "n_groups": 2445481 },5482 "rougeL": {5483 "mean": 0.6849426814524071,5484 "ci_low": 0.675466121723714,5485 "ci_high": 0.6942971945562473,5486 "n_items": 2154,5487 "n_groups": 2445488 },5489 "exact_match": {5490 "mean": 0.0,5491 "ci_low": 0.0,5492 "ci_high": 0.0,5493 "n_items": 2154,5494 "n_groups": 2445495 },5496 "number_recall": {5497 "mean": 0.987261866996704,5498 "ci_low": 0.9825556990956811,5499 "ci_high": 0.9914907082748663,5500 "n_items": 2154,5501 "n_groups": 2445502 },5503 "placeholders_exact": {5504 "mean": 0.9883936861652739,5505 "ci_low": 0.9808446388133311,5506 "ci_high": 0.9948347243118851,5507 "n_items": 2154,5508 "n_groups": 2445509 }5510 },5511 "chemistry": {5512 "n": 837,5513 "chrf": {5514 "mean": 72.16621484540143,5515 "ci_low": 70.70453588100997,5516 "ci_high": 73.50864348992366,5517 "n_items": 837,5518 "n_groups": 135519 },5520 "edit_sim": {5521 "mean": 0.6926199429068263,5522 "ci_low": 0.6766185347773437,5523 "ci_high": 0.709305816585457,5524 "n_items": 837,5525 "n_groups": 135526 },5527 "rougeL": {5528 "mean": 0.7096506010620621,5529 "ci_low": 0.6947772487190536,5530 "ci_high": 0.7247059926902615,5531 "n_items": 837,5532 "n_groups": 135533 },5534 "exact_match": {5535 "mean": 0.0,5536 "ci_low": 0.0,5537 "ci_high": 0.0,5538 "n_items": 837,5539 "n_groups": 135540 },5541 "number_recall": {5542 "mean": 0.9811295654989052,5543 "ci_low": 0.9764369706882333,5544 "ci_high": 0.9858042506454798,5545 "n_items": 837,5546 "n_groups": 135547 },5548 "placeholders_exact": {5549 "mean": 0.9904420549581839,5550 "ci_low": 0.9837628044412607,5551 "ci_high": 0.9958741572146932,5552 "n_items": 837,5553 "n_groups": 135554 }5555 },5556 "computer_science": {5557 "n": 1375,5558 "chrf": {5559 "mean": 69.18631336278494,5560 "ci_low": 67.8088358230827,5561 "ci_high": 70.4703642105963,5562 "n_items": 1375,5563 "n_groups": 205564 },5565 "edit_sim": {5566 "mean": 0.6862866416470426,5567 "ci_low": 0.6704291205222667,5568 "ci_high": 0.6999800498276184,5569 "n_items": 1375,5570 "n_groups": 205571 },5572 "rougeL": {5573 "mean": 0.6904508054929929,5574 "ci_low": 0.67464391821314,5575 "ci_high": 0.7032673040520505,5576 "n_items": 1375,5577 "n_groups": 205578 },5579 "exact_match": {5580 "mean": 0.0,5581 "ci_low": 0.0,5582 "ci_high": 0.0,5583 "n_items": 1375,5584 "n_groups": 205585 },5586 "number_recall": {5587 "mean": 0.9945359044995408,5588 "ci_low": 0.9902830214442522,5589 "ci_high": 0.9972940493427377,5590 "n_items": 1375,5591 "n_groups": 205592 },5593 "placeholders_exact": {5594 "mean": 0.9934545454545455,5595 "ci_low": 0.9872907065546573,5596 "ci_high": 0.9986064889437972,5597 "n_items": 1375,5598 "n_groups": 205599 }5600 },5601 "economics": {5602 "n": 1944,5603 "chrf": {5604 "mean": 68.43041273629649,5605 "ci_low": 67.60382367916529,5606 "ci_high": 69.19655634023003,5607 "n_items": 1944,5608 "n_groups": 1035609 },5610 "edit_sim": {5611 "mean": 0.6772517340134607,5612 "ci_low": 0.6681031498533739,5613 "ci_high": 0.6859381443477419,5614 "n_items": 1944,5615 "n_groups": 1035616 },5617 "rougeL": {5618 "mean": 0.6815267564523709,5619 "ci_low": 0.6713583366449591,5620 "ci_high": 0.691373542093548,5621 "n_items": 1944,5622 "n_groups": 1035623 },5624 "exact_match": {5625 "mean": 0.0,5626 "ci_low": 0.0,5627 "ci_high": 0.0,5628 "n_items": 1944,5629 "n_groups": 1035630 },5631 "number_recall": {5632 "mean": 0.9884577836429688,5633 "ci_low": 0.9826960381889491,5634 "ci_high": 0.9932385195362327,5635 "n_items": 1944,5636 "n_groups": 1035637 },5638 "placeholders_exact": {5639 "mean": 0.9974279835390947,5640 "ci_low": 0.9916196425331724,5641 "ci_high": 1.0,5642 "n_items": 1944,5643 "n_groups": 1035644 }5645 },5646 "engineering": {5647 "n": 1296,5648 "chrf": {5649 "mean": 66.745508857844,5650 "ci_low": 65.15333754977519,5651 "ci_high": 68.36954644215902,5652 "n_items": 1296,5653 "n_groups": 175654 },5655 "edit_sim": {5656 "mean": 0.6544418378142993,5657 "ci_low": 0.6388361254798762,5658 "ci_high": 0.6693204758996036,5659 "n_items": 1296,5660 "n_groups": 175661 },5662 "rougeL": {5663 "mean": 0.6655698381234172,5664 "ci_low": 0.651288791296085,5665 "ci_high": 0.6797641524406163,5666 "n_items": 1296,5667 "n_groups": 175668 },5669 "exact_match": {5670 "mean": 0.0,5671 "ci_low": 0.0,5672 "ci_high": 0.0,5673 "n_items": 1296,5674 "n_groups": 175675 },5676 "number_recall": {5677 "mean": 0.9941685231372122,5678 "ci_low": 0.990907658916007,5679 "ci_high": 0.9969440294347187,5680 "n_items": 1296,5681 "n_groups": 175682 },5683 "placeholders_exact": {5684 "mean": 0.9845679012345679,5685 "ci_low": 0.9727111976358345,5686 "ci_high": 0.9953325277682391,5687 "n_items": 1296,5688 "n_groups": 175689 }5690 },5691 "finance": {5692 "n": 2043,5693 "chrf": {5694 "mean": 67.83012272277485,5695 "ci_low": 66.50924854075019,5696 "ci_high": 69.27396679186248,5697 "n_items": 2043,5698 "n_groups": 515699 },5700 "edit_sim": {5701 "mean": 0.671411030993103,5702 "ci_low": 0.6583048679072909,5703 "ci_high": 0.6862753314528436,5704 "n_items": 2043,5705 "n_groups": 515706 },5707 "rougeL": {5708 "mean": 0.6784076970978994,5709 "ci_low": 0.6645464303933966,5710 "ci_high": 0.694062873757085,5711 "n_items": 2043,5712 "n_groups": 515713 },5714 "exact_match": {5715 "mean": 0.0,5716 "ci_low": 0.0,5717 "ci_high": 0.0,5718 "n_items": 2043,5719 "n_groups": 515720 },5721 "number_recall": {5722 "mean": 0.9927713667924143,5723 "ci_low": 0.9884215721990681,5724 "ci_high": 0.9961472220523161,5725 "n_items": 2043,5726 "n_groups": 515727 },5728 "placeholders_exact": {5729 "mean": 0.9931473323543808,5730 "ci_low": 0.9863726291289061,5731 "ci_high": 0.9979957792709437,5732 "n_items": 2043,5733 "n_groups": 515734 }5735 },5736 "general_reference": {5737 "n": 118,5738 "chrf": {5739 "mean": 74.2398139141625,5740 "ci_low": 60.73705920409043,5741 "ci_high": 75.62794757594561,5742 "n_items": 118,5743 "n_groups": 25744 },5745 "edit_sim": {5746 "mean": 0.7765934209858709,5747 "ci_low": 0.6062786640577962,5748 "ci_high": 0.794102414688757,5749 "n_items": 118,5750 "n_groups": 25751 },5752 "rougeL": {5753 "mean": 0.8052431979360511,5754 "ci_low": 0.6211317017971457,5755 "ci_high": 0.8241705480064059,5756 "n_items": 118,5757 "n_groups": 25758 },5759 "exact_match": {5760 "mean": 0.0,5761 "ci_low": 0.0,5762 "ci_high": 0.0,5763 "n_items": 118,5764 "n_groups": 25765 },5766 "number_recall": {5767 "mean": 1.0,5768 "ci_low": 1.0,5769 "ci_high": 1.0,5770 "n_items": 118,5771 "n_groups": 25772 },5773 "placeholders_exact": {5774 "mean": 1.0,5775 "ci_low": 1.0,5776 "ci_high": 1.0,5777 "n_items": 118,5778 "n_groups": 25779 }5780 },5781 "humanities": {5782 "n": 263,5783 "chrf": {5784 "mean": 63.456289040879355,5785 "ci_low": 59.85374827775726,5786 "ci_high": 64.2144334120457,5787 "n_items": 263,5788 "n_groups": 35789 },5790 "edit_sim": {5791 "mean": 0.6539965842228366,5792 "ci_low": 0.6173185231539425,5793 "ci_high": 0.6571684577906617,5794 "n_items": 263,5795 "n_groups": 35796 },5797 "rougeL": {5798 "mean": 0.6599733802330574,5799 "ci_low": 0.61735606177273,5800 "ci_high": 0.6649466078128539,5801 "n_items": 263,5802 "n_groups": 35803 },5804 "exact_match": {5805 "mean": 0.0,5806 "ci_low": 0.0,5807 "ci_high": 0.0,5808 "n_items": 263,5809 "n_groups": 35810 },5811 "number_recall": {5812 "mean": 1.0,5813 "ci_low": 1.0,5814 "ci_high": 1.0,5815 "n_items": 263,5816 "n_groups": 35817 },5818 "placeholders_exact": {5819 "mean": 1.0,5820 "ci_low": 1.0,5821 "ci_high": 1.0,5822 "n_items": 263,5823 "n_groups": 35824 }5825 },5826 "life_sciences": {5827 "n": 1874,5828 "chrf": {5829 "mean": 71.5316373324792,5830 "ci_low": 69.7117892176343,5831 "ci_high": 73.07365932381835,5832 "n_items": 1874,5833 "n_groups": 1435834 },5835 "edit_sim": {5836 "mean": 0.7004535228576667,5837 "ci_low": 0.6867566099456126,5838 "ci_high": 0.7138515028824938,5839 "n_items": 1874,5840 "n_groups": 1435841 },5842 "rougeL": {5843 "mean": 0.7105777493741667,5844 "ci_low": 0.6965172199663073,5845 "ci_high": 0.7242933223349468,5846 "n_items": 1874,5847 "n_groups": 1435848 },5849 "exact_match": {5850 "mean": 0.0,5851 "ci_low": 0.0,5852 "ci_high": 0.0,5853 "n_items": 1874,5854 "n_groups": 1435855 },5856 "number_recall": {5857 "mean": 0.984343105446406,5858 "ci_low": 0.9757368826327374,5859 "ci_high": 0.9906427053819883,5860 "n_items": 1874,5861 "n_groups": 1435862 },5863 "placeholders_exact": {5864 "mean": 0.9861259338313767,5865 "ci_low": 0.9748519942046221,5866 "ci_high": 0.9942136402593502,5867 "n_items": 1874,5868 "n_groups": 1435869 }5870 },5871 "mathematics": {5872 "n": 712,5873 "chrf": {5874 "mean": 68.41092100375164,5875 "ci_low": 65.77727292403904,5876 "ci_high": 71.45107264295076,5877 "n_items": 712,5878 "n_groups": 55879 },5880 "edit_sim": {5881 "mean": 0.686648849777525,5882 "ci_low": 0.6640349014163085,5883 "ci_high": 0.7052566098503708,5884 "n_items": 712,5885 "n_groups": 55886 },5887 "rougeL": {5888 "mean": 0.6872408101792112,5889 "ci_low": 0.6642919334217109,5890 "ci_high": 0.718331142128572,5891 "n_items": 712,5892 "n_groups": 55893 },5894 "exact_match": {5895 "mean": 0.0,5896 "ci_low": 0.0,5897 "ci_high": 0.0,5898 "n_items": 712,5899 "n_groups": 55900 },5901 "number_recall": {5902 "mean": 0.9953884832396069,5903 "ci_low": 0.9932700068293289,5904 "ci_high": 0.997670912931649,5905 "n_items": 712,5906 "n_groups": 55907 },5908 "placeholders_exact": {5909 "mean": 0.9803370786516854,5910 "ci_low": 0.9334677419354839,5911 "ci_high": 0.9987745098039216,5912 "n_items": 712,5913 "n_groups": 55914 }5915 },5916 "other": {5917 "n": 669,5918 "chrf": {5919 "mean": 69.05130931422133,5920 "ci_low": 66.421462148901,5921 "ci_high": 72.41853346392784,5922 "n_items": 669,5923 "n_groups": 135924 },5925 "edit_sim": {5926 "mean": 0.6692849775699723,5927 "ci_low": 0.6460824395610518,5928 "ci_high": 0.6995880697207366,5929 "n_items": 669,5930 "n_groups": 135931 },5932 "rougeL": {5933 "mean": 0.6777419512528183,5934 "ci_low": 0.6531800644504066,5935 "ci_high": 0.7097177105780172,5936 "n_items": 669,5937 "n_groups": 135938 },5939 "exact_match": {5940 "mean": 0.0,5941 "ci_low": 0.0,5942 "ci_high": 0.0,5943 "n_items": 669,5944 "n_groups": 135945 },5946 "number_recall": {5947 "mean": 0.9825278192991198,5948 "ci_low": 0.9635541276215974,5949 "ci_high": 0.9954466035717352,5950 "n_items": 669,5951 "n_groups": 135952 },5953 "placeholders_exact": {5954 "mean": 0.9985052316890882,5955 "ci_low": 0.9935758449981753,5956 "ci_high": 1.0,5957 "n_items": 669,5958 "n_groups": 135959 }5960 },5961 "social_sciences": {5962 "n": 1536,5963 "chrf": {5964 "mean": 68.28616102531139,5965 "ci_low": 66.2934967003194,5966 "ci_high": 69.75092833575046,5967 "n_items": 1536,5968 "n_groups": 295969 },5970 "edit_sim": {5971 "mean": 0.6740619434416217,5972 "ci_low": 0.6571583737730775,5973 "ci_high": 0.6895612463467273,5974 "n_items": 1536,5975 "n_groups": 295976 },5977 "rougeL": {5978 "mean": 0.6812878044464332,5979 "ci_low": 0.6624147893762609,5980 "ci_high": 0.6980100340006599,5981 "n_items": 1536,5982 "n_groups": 295983 },5984 "exact_match": {5985 "mean": 0.0,5986 "ci_low": 0.0,5987 "ci_high": 0.0,5988 "n_items": 1536,5989 "n_groups": 295990 },5991 "number_recall": {5992 "mean": 0.9953087730934026,5993 "ci_low": 0.9919970120142564,5994 "ci_high": 0.9981696924593036,5995 "n_items": 1536,5996 "n_groups": 295997 },5998 "placeholders_exact": {5999 "mean": 0.9954427083333334,6000 "ci_low": 0.9900493380274706,6001 "ci_high": 0.9993519641927116,6002 "n_items": 1536,6003 "n_groups": 296004 }6005 },6006 "statistics": {6007 "n": 828,6008 "chrf": {6009 "mean": 70.35176849018778,6010 "ci_low": 67.88144713567112,6011 "ci_high": 73.025526953385,6012 "n_items": 828,6013 "n_groups": 96014 },6015 "edit_sim": {6016 "mean": 0.6873783223582055,6017 "ci_low": 0.6664509664622803,6018 "ci_high": 0.7103100269238481,6019 "n_items": 828,6020 "n_groups": 96021 },6022 "rougeL": {6023 "mean": 0.7093999264827233,6024 "ci_low": 0.685442970786985,6025 "ci_high": 0.7337941509795421,6026 "n_items": 828,6027 "n_groups": 96028 },6029 "exact_match": {6030 "mean": 0.0,6031 "ci_low": 0.0,6032 "ci_high": 0.0,6033 "n_items": 828,6034 "n_groups": 96035 },6036 "number_recall": {6037 "mean": 0.9884218476992405,6038 "ci_low": 0.9713583954275179,6039 "ci_high": 0.9985141154016443,6040 "n_items": 828,6041 "n_groups": 96042 },6043 "placeholders_exact": {6044 "mean": 0.9818840579710145,6045 "ci_low": 0.9694371854975588,6046 "ci_high": 0.9934285100315363,6047 "n_items": 828,6048 "n_groups": 96049 }6050 }6051 },6052 "by_era": {6053 "1900-1949": {6054 "n": 1164,6055 "chrf": {6056 "mean": 63.96110362204815,6057 "ci_low": 61.819141183360365,6058 "ci_high": 66.87685664437674,6059 "n_items": 1164,6060 "n_groups": 186061 },6062 "edit_sim": {6063 "mean": 0.6551090611651436,6064 "ci_low": 0.6317919961024266,6065 "ci_high": 0.6917949807830714,6066 "n_items": 1164,6067 "n_groups": 186068 },6069 "rougeL": {6070 "mean": 0.66383231604586,6071 "ci_low": 0.6386653939697314,6072 "ci_high": 0.7045855087510586,6073 "n_items": 1164,6074 "n_groups": 186075 },6076 "exact_match": {6077 "mean": 0.0,6078 "ci_low": 0.0,6079 "ci_high": 0.0,6080 "n_items": 1164,6081 "n_groups": 186082 },6083 "number_recall": {6084 "mean": 1.0,6085 "ci_low": 1.0,6086 "ci_high": 1.0,6087 "n_items": 1164,6088 "n_groups": 186089 },6090 "placeholders_exact": {6091 "mean": 1.0,6092 "ci_low": 1.0,6093 "ci_high": 1.0,6094 "n_items": 1164,6095 "n_groups": 186096 }6097 },6098 "1950-1979": {6099 "n": 206,6100 "chrf": {6101 "mean": 62.72054307944101,6102 "ci_low": 60.197491899263625,6103 "ci_high": 63.32850721924278,6104 "n_items": 206,6105 "n_groups": 26106 },6107 "edit_sim": {6108 "mean": 0.6480250807442639,6109 "ci_low": 0.6100800660017132,6110 "ci_high": 0.6571684577906617,6111 "n_items": 206,6112 "n_groups": 26113 },6114 "rougeL": {6115 "mean": 0.6514552617296495,6116 "ci_low": 0.6138879830094754,6117 "ci_high": 0.6605076180477637,6118 "n_items": 206,6119 "n_groups": 26120 },6121 "exact_match": {6122 "mean": 0.0,6123 "ci_low": 0.0,6124 "ci_high": 0.0,6125 "n_items": 206,6126 "n_groups": 26127 },6128 "number_recall": {6129 "mean": 1.0,6130 "ci_low": 1.0,6131 "ci_high": 1.0,6132 "n_items": 206,6133 "n_groups": 26134 },6135 "placeholders_exact": {6136 "mean": 1.0,6137 "ci_low": 1.0,6138 "ci_high": 1.0,6139 "n_items": 206,6140 "n_groups": 26141 }6142 },6143 "1980-1999": {6144 "n": 151,6145 "chrf": {6146 "mean": 64.03681922210659,6147 "ci_low": 62.67775814753882,6148 "ci_high": 79.5991701045698,6149 "n_items": 151,6150 "n_groups": 46151 },6152 "edit_sim": {6153 "mean": 0.6612750477010307,6154 "ci_low": 0.6491894117032223,6155 "ci_high": 0.811885306614453,6156 "n_items": 151,6157 "n_groups": 46158 },6159 "rougeL": {6160 "mean": 0.6622424755431139,6161 "ci_low": 0.6508271043122386,6162 "ci_high": 0.7965636353579528,6163 "n_items": 151,6164 "n_groups": 46165 },6166 "exact_match": {6167 "mean": 0.0,6168 "ci_low": 0.0,6169 "ci_high": 0.0,6170 "n_items": 151,6171 "n_groups": 46172 },6173 "number_recall": {6174 "mean": 1.0,6175 "ci_low": 1.0,6176 "ci_high": 1.0,6177 "n_items": 151,6178 "n_groups": 46179 },6180 "placeholders_exact": {6181 "mean": 1.0,6182 "ci_low": 1.0,6183 "ci_high": 1.0,6184 "n_items": 151,6185 "n_groups": 46186 }6187 },6188 "2000-2009": {6189 "n": 1545,6190 "chrf": {6191 "mean": 69.53523749402474,6192 "ci_low": 68.27262873093034,6193 "ci_high": 70.82234449989355,6194 "n_items": 1545,6195 "n_groups": 696196 },6197 "edit_sim": {6198 "mean": 0.6884846472771889,6199 "ci_low": 0.6763625977384558,6200 "ci_high": 0.7007809868102988,6201 "n_items": 1545,6202 "n_groups": 696203 },6204 "rougeL": {6205 "mean": 0.6968603839201064,6206 "ci_low": 0.6860753190068178,6207 "ci_high": 0.7084758390533519,6208 "n_items": 1545,6209 "n_groups": 696210 },6211 "exact_match": {6212 "mean": 0.0,6213 "ci_low": 0.0,6214 "ci_high": 0.0,6215 "n_items": 1545,6216 "n_groups": 696217 },6218 "number_recall": {6219 "mean": 0.9898743671245099,6220 "ci_low": 0.9810278589679023,6221 "ci_high": 0.9953490179525893,6222 "n_items": 1545,6223 "n_groups": 696224 },6225 "placeholders_exact": {6226 "mean": 0.9935275080906149,6227 "ci_low": 0.9881180537225589,6228 "ci_high": 0.9981069118807416,6229 "n_items": 1545,6230 "n_groups": 696231 }6232 },6233 "2010-2017": {6234 "n": 12583,6235 "chrf": {6236 "mean": 69.58611903182285,6237 "ci_low": 69.09944591550719,6238 "ci_high": 70.08417162648652,6239 "n_items": 12583,6240 "n_groups": 5596241 },6242 "edit_sim": {6243 "mean": 0.6813730764731852,6244 "ci_low": 0.6760035123595244,6245 "ci_high": 0.6862004784695818,6246 "n_items": 12583,6247 "n_groups": 5596248 },6249 "rougeL": {6250 "mean": 0.6902486940581328,6251 "ci_low": 0.6844679860185257,6252 "ci_high": 0.6955234358082935,6253 "n_items": 12583,6254 "n_groups": 5596255 },6256 "exact_match": {6257 "mean": 0.0,6258 "ci_low": 0.0,6259 "ci_high": 0.0,6260 "n_items": 12583,6261 "n_groups": 5596262 },6263 "number_recall": {6264 "mean": 0.9887967078763696,6265 "ci_low": 0.9865268086295622,6266 "ci_high": 0.9908928208831475,6267 "n_items": 12583,6268 "n_groups": 5596269 },6270 "placeholders_exact": {6271 "mean": 0.9893507112771199,6272 "ci_low": 0.985814103973794,6273 "ci_high": 0.9922014314028086,6274 "n_items": 12583,6275 "n_groups": 5596276 }6277 }6278 },6279 "by_role": {6280 "abstract": {6281 "n": 1255,6282 "chrf": {6283 "mean": 70.02191926441192,6284 "ci_low": 69.22259017788438,6285 "ci_high": 70.91027386535471,6286 "n_items": 1255,6287 "n_groups": 1956288 },6289 "edit_sim": {6290 "mean": 0.6785002949443628,6291 "ci_low": 0.6686658943606187,6292 "ci_high": 0.6884205686244844,6293 "n_items": 1255,6294 "n_groups": 1956295 },6296 "rougeL": {6297 "mean": 0.6823786293837133,6298 "ci_low": 0.6728339637857261,6299 "ci_high": 0.692068212598652,6300 "n_items": 1255,6301 "n_groups": 1956302 },6303 "exact_match": {6304 "mean": 0.0,6305 "ci_low": 0.0,6306 "ci_high": 0.0,6307 "n_items": 1255,6308 "n_groups": 1956309 },6310 "number_recall": {6311 "mean": 0.9940662738026731,6312 "ci_low": 0.99117437232079,6313 "ci_high": 0.9967074469225992,6314 "n_items": 1255,6315 "n_groups": 1956316 },6317 "placeholders_exact": {6318 "mean": 0.999203187250996,6319 "ci_low": 0.9974894345326819,6320 "ci_high": 1.0,6321 "n_items": 1255,6322 "n_groups": 1956323 }6324 },6325 "background": {6326 "n": 964,6327 "chrf": {6328 "mean": 69.565536574466,6329 "ci_low": 68.43026242921121,6330 "ci_high": 70.72355423428147,6331 "n_items": 964,6332 "n_groups": 846333 },6334 "edit_sim": {6335 "mean": 0.6863635528854057,6336 "ci_low": 0.6734706356259803,6337 "ci_high": 0.6994692181189905,6338 "n_items": 964,6339 "n_groups": 846340 },6341 "rougeL": {6342 "mean": 0.6923749756238317,6343 "ci_low": 0.6771266911513084,6344 "ci_high": 0.7069455688866471,6345 "n_items": 964,6346 "n_groups": 846347 },6348 "exact_match": {6349 "mean": 0.0,6350 "ci_low": 0.0,6351 "ci_high": 0.0,6352 "n_items": 964,6353 "n_groups": 846354 },6355 "number_recall": {6356 "mean": 0.9952010472238688,6357 "ci_low": 0.9923788436084422,6358 "ci_high": 0.9977818459117955,6359 "n_items": 964,6360 "n_groups": 846361 },6362 "placeholders_exact": {6363 "mean": 0.9844398340248963,6364 "ci_low": 0.9697942827529472,6365 "ci_high": 0.9956475611486966,6366 "n_items": 964,6367 "n_groups": 846368 }6369 },6370 "chapter": {6371 "n": 1287,6372 "chrf": {6373 "mean": 64.05268734613583,6374 "ci_low": 62.79839765160633,6375 "ci_high": 65.82975178917653,6376 "n_items": 1287,6377 "n_groups": 216378 },6379 "edit_sim": {6380 "mean": 0.6526880643394547,6381 "ci_low": 0.6402247448796569,6382 "ci_high": 0.6750536683676341,6383 "n_items": 1287,6384 "n_groups": 216385 },6386 "rougeL": {6387 "mean": 0.6612752856447852,6388 "ci_low": 0.6489838054225943,6389 "ci_high": 0.6832774229313401,6390 "n_items": 1287,6391 "n_groups": 216392 },6393 "exact_match": {6394 "mean": 0.0,6395 "ci_low": 0.0,6396 "ci_high": 0.0,6397 "n_items": 1287,6398 "n_groups": 216399 },6400 "number_recall": {6401 "mean": 0.9998445998445998,6402 "ci_low": 0.9995327034526457,6403 "ci_high": 1.0,6404 "n_items": 1287,6405 "n_groups": 216406 },6407 "placeholders_exact": {6408 "mean": 1.0,6409 "ci_low": 1.0,6410 "ci_high": 1.0,6411 "n_items": 1287,6412 "n_groups": 216413 }6414 },6415 "conclusion": {6416 "n": 1168,6417 "chrf": {6418 "mean": 67.30988480745845,6419 "ci_low": 66.39127934664764,6420 "ci_high": 68.21184271834066,6421 "n_items": 1168,6422 "n_groups": 1546423 },6424 "edit_sim": {6425 "mean": 0.6617671769460592,6426 "ci_low": 0.6515527890139584,6427 "ci_high": 0.6720847357159555,6428 "n_items": 1168,6429 "n_groups": 1546430 },6431 "rougeL": {6432 "mean": 0.6613005676374901,6433 "ci_low": 0.6510069684233234,6434 "ci_high": 0.6714422396789579,6435 "n_items": 1168,6436 "n_groups": 1546437 },6438 "exact_match": {6439 "mean": 0.0,6440 "ci_low": 0.0,6441 "ci_high": 0.0,6442 "n_items": 1168,6443 "n_groups": 1546444 },6445 "number_recall": {6446 "mean": 0.9946667939176501,6447 "ci_low": 0.9902140834996088,6448 "ci_high": 0.9981629158977154,6449 "n_items": 1168,6450 "n_groups": 1546451 },6452 "placeholders_exact": {6453 "mean": 0.9957191780821918,6454 "ci_low": 0.9879587450353579,6455 "ci_high": 1.0,6456 "n_items": 1168,6457 "n_groups": 1546458 }6459 },6460 "data": {6461 "n": 912,6462 "chrf": {6463 "mean": 70.01129403710583,6464 "ci_low": 69.04445204078813,6465 "ci_high": 71.07376983443336,6466 "n_items": 912,6467 "n_groups": 1046468 },6469 "edit_sim": {6470 "mean": 0.682974948454661,6471 "ci_low": 0.6720238242296611,6472 "ci_high": 0.6939285098401347,6473 "n_items": 912,6474 "n_groups": 1046475 },6476 "rougeL": {6477 "mean": 0.7019911211876788,6478 "ci_low": 0.6907128748784845,6479 "ci_high": 0.7135450865584894,6480 "n_items": 912,6481 "n_groups": 1046482 },6483 "exact_match": {6484 "mean": 0.0,6485 "ci_low": 0.0,6486 "ci_high": 0.0,6487 "n_items": 912,6488 "n_groups": 1046489 },6490 "number_recall": {6491 "mean": 0.9834667563248218,6492 "ci_low": 0.9719978893085892,6493 "ci_high": 0.9913744799477804,6494 "n_items": 912,6495 "n_groups": 1046496 },6497 "placeholders_exact": {6498 "mean": 0.9857456140350878,6499 "ci_low": 0.9693649565865353,6500 "ci_high": 0.9978540772532188,6501 "n_items": 912,6502 "n_groups": 1046503 }6504 },6505 "discussion": {6506 "n": 1601,6507 "chrf": {6508 "mean": 69.14433431519538,6509 "ci_low": 68.2432588473697,6510 "ci_high": 70.01981141460413,6511 "n_items": 1601,6512 "n_groups": 1426513 },6514 "edit_sim": {6515 "mean": 0.6795471165865967,6516 "ci_low": 0.6701705395087078,6517 "ci_high": 0.6887794777256925,6518 "n_items": 1601,6519 "n_groups": 1426520 },6521 "rougeL": {6522 "mean": 0.6818261025105343,6523 "ci_low": 0.6718259180421201,6524 "ci_high": 0.6916901420778068,6525 "n_items": 1601,6526 "n_groups": 1426527 },6528 "exact_match": {6529 "mean": 0.0,6530 "ci_low": 0.0,6531 "ci_high": 0.0,6532 "n_items": 1601,6533 "n_groups": 1426534 },6535 "number_recall": {6536 "mean": 0.9894592898579379,6537 "ci_low": 0.9838565702913094,6538 "ci_high": 0.9941100780435825,6539 "n_items": 1601,6540 "n_groups": 1426541 },6542 "placeholders_exact": {6543 "mean": 0.9850093691442848,6544 "ci_low": 0.9734313368437865,6545 "ci_high": 0.993531432049387,6546 "n_items": 1601,6547 "n_groups": 1426548 }6549 },6550 "introduction": {6551 "n": 1789,6552 "chrf": {6553 "mean": 69.03765883386846,6554 "ci_low": 68.06667096420883,6555 "ci_high": 70.00911155905378,6556 "n_items": 1789,6557 "n_groups": 1766558 },6559 "edit_sim": {6560 "mean": 0.6785635241961148,6561 "ci_low": 0.6684327835366373,6562 "ci_high": 0.6891287871286085,6563 "n_items": 1789,6564 "n_groups": 1766565 },6566 "rougeL": {6567 "mean": 0.6793883706491162,6568 "ci_low": 0.6688278177135862,6569 "ci_high": 0.6898670892834424,6570 "n_items": 1789,6571 "n_groups": 1766572 },6573 "exact_match": {6574 "mean": 0.0,6575 "ci_low": 0.0,6576 "ci_high": 0.0,6577 "n_items": 1789,6578 "n_groups": 1766579 },6580 "number_recall": {6581 "mean": 0.9921574923740938,6582 "ci_low": 0.9870034971813012,6583 "ci_high": 0.9963426825713767,6584 "n_items": 1789,6585 "n_groups": 1766586 },6587 "placeholders_exact": {6588 "mean": 0.9860257126886529,6589 "ci_low": 0.9768462045555298,6590 "ci_high": 0.9933986636377224,6591 "n_items": 1789,6592 "n_groups": 1766593 }6594 },6595 "limitations": {6596 "n": 425,6597 "chrf": {6598 "mean": 67.83409792253659,6599 "ci_low": 66.18001055211182,6600 "ci_high": 69.59574824656757,6601 "n_items": 425,6602 "n_groups": 416603 },6604 "edit_sim": {6605 "mean": 0.665752076141154,6606 "ci_low": 0.6493964543663799,6607 "ci_high": 0.6838569105336358,6608 "n_items": 425,6609 "n_groups": 416610 },6611 "rougeL": {6612 "mean": 0.6697802311553349,6613 "ci_low": 0.6488450381371652,6614 "ci_high": 0.6925642336685937,6615 "n_items": 425,6616 "n_groups": 416617 },6618 "exact_match": {6619 "mean": 0.0,6620 "ci_low": 0.0,6621 "ci_high": 0.0,6622 "n_items": 425,6623 "n_groups": 416624 },6625 "number_recall": {6626 "mean": 0.9971503267973856,6627 "ci_low": 0.9935930558875345,6628 "ci_high": 0.9997083888728568,6629 "n_items": 425,6630 "n_groups": 416631 },6632 "placeholders_exact": {6633 "mean": 0.9952941176470588,6634 "ci_low": 0.9842094847937786,6635 "ci_high": 1.0,6636 "n_items": 425,6637 "n_groups": 416638 }6639 },6640 "methods": {6641 "n": 1528,6642 "chrf": {6643 "mean": 70.82390798689254,6644 "ci_low": 69.99514678135078,6645 "ci_high": 71.70764735946909,6646 "n_items": 1528,6647 "n_groups": 1516648 },6649 "edit_sim": {6650 "mean": 0.6914548270314929,6651 "ci_low": 0.682385909724709,6652 "ci_high": 0.7006094360424793,6653 "n_items": 1528,6654 "n_groups": 1516655 },6656 "rougeL": {6657 "mean": 0.7111081797463366,6658 "ci_low": 0.7015431266430922,6659 "ci_high": 0.7209130490307971,6660 "n_items": 1528,6661 "n_groups": 1516662 },6663 "exact_match": {6664 "mean": 0.0,6665 "ci_low": 0.0,6666 "ci_high": 0.0,6667 "n_items": 1528,6668 "n_groups": 1516669 },6670 "number_recall": {6671 "mean": 0.9870862262304011,6672 "ci_low": 0.9824474644541691,6673 "ci_high": 0.9911827810632619,6674 "n_items": 1528,6675 "n_groups": 1516676 },6677 "placeholders_exact": {6678 "mean": 0.9921465968586387,6679 "ci_low": 0.9844559585492227,6680 "ci_high": 0.9979438674910244,6681 "n_items": 1528,6682 "n_groups": 1516683 }6684 },6685 "other": {6686 "n": 1387,6687 "chrf": {6688 "mean": 69.79495734235353,6689 "ci_low": 68.7790390533219,6690 "ci_high": 70.82741219842806,6691 "n_items": 1387,6692 "n_groups": 1196693 },6694 "edit_sim": {6695 "mean": 0.6872145100729146,6696 "ci_low": 0.6775471332562572,6697 "ci_high": 0.6975424762978732,6698 "n_items": 1387,6699 "n_groups": 1196700 },6701 "rougeL": {6702 "mean": 0.6950282719495018,6703 "ci_low": 0.6844982839788387,6704 "ci_high": 0.7055535358285571,6705 "n_items": 1387,6706 "n_groups": 1196707 },6708 "exact_match": {6709 "mean": 0.0,6710 "ci_low": 0.0,6711 "ci_high": 0.0,6712 "n_items": 1387,6713 "n_groups": 1196714 },6715 "number_recall": {6716 "mean": 0.9924318891874768,6717 "ci_low": 0.9876722358898687,6718 "ci_high": 0.9960942646108109,6719 "n_items": 1387,6720 "n_groups": 1196721 },6722 "placeholders_exact": {6723 "mean": 0.9740447007930786,6724 "ci_low": 0.9570491167597583,6725 "ci_high": 0.9889950684300043,6726 "n_items": 1387,6727 "n_groups": 1196728 }6729 },6730 "preface": {6731 "n": 362,6732 "chrf": {6733 "mean": 63.37857453260035,6734 "ci_low": 59.087106266625405,6735 "ci_high": 67.82959335556615,6736 "n_items": 362,6737 "n_groups": 136738 },6739 "edit_sim": {6740 "mean": 0.6522735128659819,6741 "ci_low": 0.6065719812961196,6742 "ci_high": 0.7016177984072716,6743 "n_items": 362,6744 "n_groups": 136745 },6746 "rougeL": {6747 "mean": 0.6584143813745079,6748 "ci_low": 0.6061379589154136,6749 "ci_high": 0.7157613879648854,6750 "n_items": 362,6751 "n_groups": 136752 },6753 "exact_match": {6754 "mean": 0.0,6755 "ci_low": 0.0,6756 "ci_high": 0.0,6757 "n_items": 362,6758 "n_groups": 136759 },6760 "number_recall": {6761 "mean": 1.0,6762 "ci_low": 1.0,6763 "ci_high": 1.0,6764 "n_items": 362,6765 "n_groups": 136766 },6767 "placeholders_exact": {6768 "mean": 1.0,6769 "ci_low": 1.0,6770 "ci_high": 1.0,6771 "n_items": 362,6772 "n_groups": 136773 }6774 },6775 "related_work": {6776 "n": 557,6777 "chrf": {6778 "mean": 70.92574201014928,6779 "ci_low": 69.36328440003206,6780 "ci_high": 72.5106446876912,6781 "n_items": 557,6782 "n_groups": 396783 },6784 "edit_sim": {6785 "mean": 0.6916486844777997,6786 "ci_low": 0.6741802751019264,6787 "ci_high": 0.7115549918610958,6788 "n_items": 557,6789 "n_groups": 396790 },6791 "rougeL": {6792 "mean": 0.6974580814882045,6793 "ci_low": 0.6790103523556767,6794 "ci_high": 0.7167772785387436,6795 "n_items": 557,6796 "n_groups": 396797 },6798 "exact_match": {6799 "mean": 0.0,6800 "ci_low": 0.0,6801 "ci_high": 0.0,6802 "n_items": 557,6803 "n_groups": 396804 },6805 "number_recall": {6806 "mean": 0.9856889924241279,6807 "ci_low": 0.9730212419294805,6808 "ci_high": 0.9950316919080868,6809 "n_items": 557,6810 "n_groups": 396811 },6812 "placeholders_exact": {6813 "mean": 0.9964093357271095,6814 "ci_low": 0.9871506527595496,6815 "ci_high": 1.0,6816 "n_items": 557,6817 "n_groups": 396818 }6819 },6820 "results": {6821 "n": 1501,6822 "chrf": {6823 "mean": 70.22842633640657,6824 "ci_low": 69.08248054407255,6825 "ci_high": 71.44331780483003,6826 "n_items": 1501,6827 "n_groups": 1536828 },6829 "edit_sim": {6830 "mean": 0.6873648816086674,6831 "ci_low": 0.6766290255514724,6832 "ci_high": 0.6986422015631379,6833 "n_items": 1501,6834 "n_groups": 1536835 },6836 "rougeL": {6837 "mean": 0.7085032479147827,6838 "ci_low": 0.6973070653534893,6839 "ci_high": 0.7205040452717155,6840 "n_items": 1501,6841 "n_groups": 1536842 },6843 "exact_match": {6844 "mean": 0.0,6845 "ci_low": 0.0,6846 "ci_high": 0.0,6847 "n_items": 1501,6848 "n_groups": 1536849 },6850 "number_recall": {6851 "mean": 0.9707674854247886,6852 "ci_low": 0.9604408534937859,6853 "ci_high": 0.9796706082207092,6854 "n_items": 1501,6855 "n_groups": 1536856 },6857 "placeholders_exact": {6858 "mean": 0.9953364423717521,6859 "ci_low": 0.9912625565930956,6860 "ci_high": 0.9987007891289496,6861 "n_items": 1501,6862 "n_groups": 1536863 }6864 },6865 "theory": {6866 "n": 913,6867 "chrf": {6868 "mean": 70.43595155958128,6869 "ci_low": 69.23433737867595,6870 "ci_high": 71.59296277512043,6871 "n_items": 913,6872 "n_groups": 796873 },6874 "edit_sim": {6875 "mean": 0.6973215000537266,6876 "ci_low": 0.6837064448629666,6877 "ci_high": 0.7102898095500778,6878 "n_items": 913,6879 "n_groups": 796880 },6881 "rougeL": {6882 "mean": 0.7107118090904946,6883 "ci_low": 0.6959872766703609,6884 "ci_high": 0.7249117924879619,6885 "n_items": 913,6886 "n_groups": 796887 },6888 "exact_match": {6889 "mean": 0.0,6890 "ci_low": 0.0,6891 "ci_high": 0.0,6892 "n_items": 913,6893 "n_groups": 796894 },6895 "number_recall": {6896 "mean": 0.9903185958498116,6897 "ci_low": 0.9852485966120663,6898 "ci_high": 0.9950554354616508,6899 "n_items": 913,6900 "n_groups": 796901 },6902 "placeholders_exact": {6903 "mean": 0.9978094194961665,6904 "ci_low": 0.992617337305272,6905 "ci_high": 1.0,6906 "n_items": 913,6907 "n_groups": 796908 }6909 }6910 }6911 },6912 "htr-m1-tiny-s2": {6913 "overall": {6914 "n": 15649,6915 "chrf": {6916 "mean": 69.30112145626076,6917 "ci_low": 68.75783318766283,6918 "ci_high": 69.83661131837826,6919 "n_items": 15649,6920 "n_groups": 6526921 },6922 "edit_sim": {6923 "mean": 0.6852269884289295,6924 "ci_low": 0.6803993044943123,6925 "ci_high": 0.6901187342093942,6926 "n_items": 15649,6927 "n_groups": 6526928 },6929 "rougeL": {6930 "mean": 0.6939885388493415,6931 "ci_low": 0.6886609436240922,6932 "ci_high": 0.6993164513207847,6933 "n_items": 15649,6934 "n_groups": 6526935 },6936 "exact_match": {6937 "mean": 0.0,6938 "ci_low": 0.0,6939 "ci_high": 0.0,6940 "n_items": 15649,6941 "n_groups": 6526942 },6943 "number_recall": {6944 "mean": 0.990785759516322,6945 "ci_low": 0.9889139982798781,6946 "ci_high": 0.992469925341139,6947 "n_items": 15649,6948 "n_groups": 6526949 },6950 "placeholders_exact": {6951 "mean": 0.9922678765416321,6952 "ci_low": 0.9897290295083007,6953 "ci_high": 0.9944591585793943,6954 "n_items": 15649,6955 "n_groups": 6526956 }6957 },6958 "by_variant": {6959 "A": {6960 "n": 2664,6961 "chrf": {6962 "mean": 68.8741503949282,6963 "ci_low": 68.26573548680302,6964 "ci_high": 69.48802012802577,6965 "n_items": 2664,6966 "n_groups": 6306967 },6968 "edit_sim": {6969 "mean": 0.6778089540277614,6970 "ci_low": 0.6721262699859534,6971 "ci_high": 0.6839167622523119,6972 "n_items": 2664,6973 "n_groups": 6306974 },6975 "rougeL": {6976 "mean": 0.6840001611199743,6977 "ci_low": 0.6780953473944267,6978 "ci_high": 0.6902234471737745,6979 "n_items": 2664,6980 "n_groups": 6306981 },6982 "exact_match": {6983 "mean": 0.0,6984 "ci_low": 0.0,6985 "ci_high": 0.0,6986 "n_items": 2664,6987 "n_groups": 6306988 },6989 "number_recall": {6990 "mean": 0.9900107162051032,6991 "ci_low": 0.9874461951174001,6992 "ci_high": 0.992370528071504,6993 "n_items": 2664,6994 "n_groups": 6306995 },6996 "placeholders_exact": {6997 "mean": 0.9917417417417418,6998 "ci_low": 0.9880351643025103,6999 "ci_high": 0.9949335461047872,7000 "n_items": 2664,7001 "n_groups": 6307002 }7003 },7004 "B": {7005 "n": 2539,7006 "chrf": {7007 "mean": 74.77380509807446,7008 "ci_low": 74.17701798349742,7009 "ci_high": 75.3600498525392,7010 "n_items": 2539,7011 "n_groups": 6147012 },7013 "edit_sim": {7014 "mean": 0.7506329722898478,7015 "ci_low": 0.7448973642285339,7016 "ci_high": 0.7564564850028144,7017 "n_items": 2539,7018 "n_groups": 6147019 },7020 "rougeL": {7021 "mean": 0.7576618711799052,7022 "ci_low": 0.7515985761623556,7023 "ci_high": 0.7636371638965657,7024 "n_items": 2539,7025 "n_groups": 6147026 },7027 "exact_match": {7028 "mean": 0.0,7029 "ci_low": 0.0,7030 "ci_high": 0.0,7031 "n_items": 2539,7032 "n_groups": 6147033 },7034 "number_recall": {7035 "mean": 0.9909839705982028,7036 "ci_low": 0.9884742607453267,7037 "ci_high": 0.9932109825343726,7038 "n_items": 2539,7039 "n_groups": 6147040 },7041 "placeholders_exact": {7042 "mean": 0.9909413154785348,7043 "ci_low": 0.9870171010872328,7044 "ci_high": 0.9945850715715328,7045 "n_items": 2539,7046 "n_groups": 6147047 }7048 },7049 "C": {7050 "n": 2663,7051 "chrf": {7052 "mean": 71.59150826864825,7053 "ci_low": 71.0598798070749,7054 "ci_high": 72.1823257454903,7055 "n_items": 2663,7056 "n_groups": 6387057 },7058 "edit_sim": {7059 "mean": 0.7265044545712032,7060 "ci_low": 0.7212991556080303,7061 "ci_high": 0.7320437212222076,7062 "n_items": 2663,7063 "n_groups": 6387064 },7065 "rougeL": {7066 "mean": 0.7459104283742102,7067 "ci_low": 0.7403717100746524,7068 "ci_high": 0.75184488970933,7069 "n_items": 2663,7070 "n_groups": 6387071 },7072 "exact_match": {7073 "mean": 0.0,7074 "ci_low": 0.0,7075 "ci_high": 0.0,7076 "n_items": 2663,7077 "n_groups": 6387078 },7079 "number_recall": {7080 "mean": 0.9921999858033814,7081 "ci_low": 0.9901072907276278,7082 "ci_high": 0.9940606484407047,7083 "n_items": 2663,7084 "n_groups": 6387085 },7086 "placeholders_exact": {7087 "mean": 0.9943672549755914,7088 "ci_low": 0.9912068891176271,7089 "ci_high": 0.9969837985210757,7090 "n_items": 2663,7091 "n_groups": 6387092 }7093 },7094 "D": {7095 "n": 2708,7096 "chrf": {7097 "mean": 70.02409308831977,7098 "ci_low": 69.43116270754726,7099 "ci_high": 70.61932008865544,7100 "n_items": 2708,7101 "n_groups": 6387102 },7103 "edit_sim": {7104 "mean": 0.6974829795422209,7105 "ci_low": 0.6922090883164504,7106 "ci_high": 0.7028519497719516,7107 "n_items": 2708,7108 "n_groups": 6387109 },7110 "rougeL": {7111 "mean": 0.7024183912622769,7112 "ci_low": 0.6971051611712485,7113 "ci_high": 0.7078569397594433,7114 "n_items": 2708,7115 "n_groups": 6387116 },7117 "exact_match": {7118 "mean": 0.0,7119 "ci_low": 0.0,7120 "ci_high": 0.0,7121 "n_items": 2708,7122 "n_groups": 6387123 },7124 "number_recall": {7125 "mean": 0.9904037192752878,7126 "ci_low": 0.9881963029894406,7127 "ci_high": 0.9924510393987427,7128 "n_items": 2708,7129 "n_groups": 6387130 },7131 "placeholders_exact": {7132 "mean": 0.9937223042836041,7133 "ci_low": 0.9905578908500641,7134 "ci_high": 0.9964344076227645,7135 "n_items": 2708,7136 "n_groups": 6387137 }7138 },7139 "E": {7140 "n": 5075,7141 "chrf": {7142 "mean": 65.1996830089349,7143 "ci_low": 64.58369103810458,7144 "ci_high": 65.78957855378343,7145 "n_items": 5075,7146 "n_groups": 6237147 },7148 "edit_sim": {7149 "mean": 0.6281993498772394,7150 "ci_low": 0.6228756798761718,7151 "ci_high": 0.6336755805598004,7152 "n_items": 5075,7153 "n_groups": 6237154 },7155 "rougeL": {7156 "mean": 0.6356331527103816,7157 "ci_low": 0.629482305171479,7158 "ci_high": 0.6418886252467971,7159 "n_items": 5075,7160 "n_groups": 6237161 },7162 "exact_match": {7163 "mean": 0.0,7164 "ci_low": 0.0,7165 "ci_high": 0.0,7166 "n_items": 5075,7167 "n_groups": 6237168 },7169 "number_recall": {7170 "mean": 0.990555205391095,7171 "ci_low": 0.988475643974277,7172 "ci_high": 0.9926077406621749,7173 "n_items": 5075,7174 "n_groups": 6237175 },7176 "placeholders_exact": {7177 "mean": 0.9913300492610837,7178 "ci_low": 0.9881848593743349,7179 "ci_high": 0.9942388311572964,7180 "n_items": 5075,7181 "n_groups": 6237182 }7183 }7184 },7185 "by_discipline": {7186 "biomedicine": {7187 "n": 2154,7188 "chrf": {7189 "mean": 69.57573046281628,7190 "ci_low": 68.41136699105905,7191 "ci_high": 70.67484470569899,7192 "n_items": 2154,7193 "n_groups": 2447194 },7195 "edit_sim": {7196 "mean": 0.6827941810470985,7197 "ci_low": 0.6743275211263848,7198 "ci_high": 0.6918491445563286,7199 "n_items": 2154,7200 "n_groups": 2447201 },7202 "rougeL": {7203 "mean": 0.6920164692719426,7204 "ci_low": 0.6824482054662663,7205 "ci_high": 0.7016228354112127,7206 "n_items": 2154,7207 "n_groups": 2447208 },7209 "exact_match": {7210 "mean": 0.0,7211 "ci_low": 0.0,7212 "ci_high": 0.0,7213 "n_items": 2154,7214 "n_groups": 2447215 },7216 "number_recall": {7217 "mean": 0.9909869439158312,7218 "ci_low": 0.9872606912283334,7219 "ci_high": 0.9943758443490976,7220 "n_items": 2154,7221 "n_groups": 2447222 },7223 "placeholders_exact": {7224 "mean": 0.9939647168059424,7225 "ci_low": 0.988487434051777,7226 "ci_high": 0.9982332544848155,7227 "n_items": 2154,7228 "n_groups": 2447229 }7230 },7231 "chemistry": {7232 "n": 837,7233 "chrf": {7234 "mean": 72.3140564562555,7235 "ci_low": 70.80556761835899,7236 "ci_high": 73.7529066898527,7237 "n_items": 837,7238 "n_groups": 137239 },7240 "edit_sim": {7241 "mean": 0.6972693495231354,7242 "ci_low": 0.6811467863908949,7243 "ci_high": 0.7147257396923565,7244 "n_items": 837,7245 "n_groups": 137246 },7247 "rougeL": {7248 "mean": 0.7147032977669409,7249 "ci_low": 0.6993320952479061,7250 "ci_high": 0.7303124058386632,7251 "n_items": 837,7252 "n_groups": 137253 },7254 "exact_match": {7255 "mean": 0.0,7256 "ci_low": 0.0,7257 "ci_high": 0.0,7258 "n_items": 837,7259 "n_groups": 137260 },7261 "number_recall": {7262 "mean": 0.9828053449862248,7263 "ci_low": 0.9744616941791583,7264 "ci_high": 0.9914032619418428,7265 "n_items": 837,7266 "n_groups": 137267 },7268 "placeholders_exact": {7269 "mean": 0.989247311827957,7270 "ci_low": 0.973791204522895,7271 "ci_high": 1.0,7272 "n_items": 837,7273 "n_groups": 137274 }7275 },7276 "computer_science": {7277 "n": 1375,7278 "chrf": {7279 "mean": 69.53556911047538,7280 "ci_low": 68.10805159923986,7281 "ci_high": 70.82154874865755,7282 "n_items": 1375,7283 "n_groups": 207284 },7285 "edit_sim": {7286 "mean": 0.6926354408305135,7287 "ci_low": 0.6772995967254277,7288 "ci_high": 0.7053935147590606,7289 "n_items": 1375,7290 "n_groups": 207291 },7292 "rougeL": {7293 "mean": 0.6974864011295593,7294 "ci_low": 0.681078467581017,7295 "ci_high": 0.7109307315037489,7296 "n_items": 1375,7297 "n_groups": 207298 },7299 "exact_match": {7300 "mean": 0.0,7301 "ci_low": 0.0,7302 "ci_high": 0.0,7303 "n_items": 1375,7304 "n_groups": 207305 },7306 "number_recall": {7307 "mean": 0.9932046176046176,7308 "ci_low": 0.9879886776284127,7309 "ci_high": 0.997113958288963,7310 "n_items": 1375,7311 "n_groups": 207312 },7313 "placeholders_exact": {7314 "mean": 0.9934545454545455,7315 "ci_low": 0.9856372588048089,7316 "ci_high": 0.9991468482954002,7317 "n_items": 1375,7318 "n_groups": 207319 }7320 },7321 "economics": {7322 "n": 1944,7323 "chrf": {7324 "mean": 68.6379958510658,7325 "ci_low": 67.83511869678885,7326 "ci_high": 69.4124132544584,7327 "n_items": 1944,7328 "n_groups": 1037329 },7330 "edit_sim": {7331 "mean": 0.6818889761897385,7332 "ci_low": 0.6727405930285615,7333 "ci_high": 0.6908980598162164,7334 "n_items": 1944,7335 "n_groups": 1037336 },7337 "rougeL": {7338 "mean": 0.6857665386200135,7339 "ci_low": 0.6755379178486033,7340 "ci_high": 0.6959132379287485,7341 "n_items": 1944,7342 "n_groups": 1037343 },7344 "exact_match": {7345 "mean": 0.0,7346 "ci_low": 0.0,7347 "ci_high": 0.0,7348 "n_items": 1944,7349 "n_groups": 1037350 },7351 "number_recall": {7352 "mean": 0.9900319473621942,7353 "ci_low": 0.9846436614079243,7354 "ci_high": 0.9944602183162179,7355 "n_items": 1944,7356 "n_groups": 1037357 },7358 "placeholders_exact": {7359 "mean": 0.9969135802469136,7360 "ci_low": 0.9927535221513616,7361 "ci_high": 0.9995157793992541,7362 "n_items": 1944,7363 "n_groups": 1037364 }7365 },7366 "engineering": {7367 "n": 1296,7368 "chrf": {7369 "mean": 67.02785556976515,7370 "ci_low": 65.41761452934497,7371 "ci_high": 68.66585759762046,7372 "n_items": 1296,7373 "n_groups": 177374 },7375 "edit_sim": {7376 "mean": 0.6610716171018431,7377 "ci_low": 0.6460361673067625,7378 "ci_high": 0.6758649680583203,7379 "n_items": 1296,7380 "n_groups": 177381 },7382 "rougeL": {7383 "mean": 0.6716878866103848,7384 "ci_low": 0.6581764740764984,7385 "ci_high": 0.6858206986955601,7386 "n_items": 1296,7387 "n_groups": 177388 },7389 "exact_match": {7390 "mean": 0.0,7391 "ci_low": 0.0,7392 "ci_high": 0.0,7393 "n_items": 1296,7394 "n_groups": 177395 },7396 "number_recall": {7397 "mean": 0.9913428558256774,7398 "ci_low": 0.9862719368473145,7399 "ci_high": 0.9957160549371598,7400 "n_items": 1296,7401 "n_groups": 177402 },7403 "placeholders_exact": {7404 "mean": 0.9891975308641975,7405 "ci_low": 0.9822131189480282,7406 "ci_high": 0.996045472853178,7407 "n_items": 1296,7408 "n_groups": 177409 }7410 },7411 "finance": {7412 "n": 2043,7413 "chrf": {7414 "mean": 68.2721807812834,7415 "ci_low": 66.9667665122713,7416 "ci_high": 69.72058889466105,7417 "n_items": 2043,7418 "n_groups": 517419 },7420 "edit_sim": {7421 "mean": 0.6782458123508857,7422 "ci_low": 0.6650321501190372,7423 "ci_high": 0.6930549760474575,7424 "n_items": 2043,7425 "n_groups": 517426 },7427 "rougeL": {7428 "mean": 0.685359147437289,7429 "ci_low": 0.6713873051945285,7430 "ci_high": 0.7011569103113171,7431 "n_items": 2043,7432 "n_groups": 517433 },7434 "exact_match": {7435 "mean": 0.0,7436 "ci_low": 0.0,7437 "ci_high": 0.0,7438 "n_items": 2043,7439 "n_groups": 517440 },7441 "number_recall": {7442 "mean": 0.9924866335781656,7443 "ci_low": 0.9873290299036578,7444 "ci_high": 0.9961312621903095,7445 "n_items": 2043,7446 "n_groups": 517447 },7448 "placeholders_exact": {7449 "mean": 0.9970631424375918,7450 "ci_low": 0.992137107999177,7451 "ci_high": 1.0,7452 "n_items": 2043,7453 "n_groups": 517454 }7455 },7456 "general_reference": {7457 "n": 118,7458 "chrf": {7459 "mean": 74.6336473102041,7460 "ci_low": 61.042088019062064,7461 "ci_high": 76.03091041490093,7462 "n_items": 118,7463 "n_groups": 27464 },7465 "edit_sim": {7466 "mean": 0.781773145990267,7467 "ci_low": 0.6081704468801207,7468 "ci_high": 0.7996201524408427,7469 "n_items": 118,7470 "n_groups": 27471 },7472 "rougeL": {7473 "mean": 0.8098884377871205,7474 "ci_low": 0.618237739776691,7475 "ci_high": 0.8295908459938001,7476 "n_items": 118,7477 "n_groups": 27478 },7479 "exact_match": {7480 "mean": 0.0,7481 "ci_low": 0.0,7482 "ci_high": 0.0,7483 "n_items": 118,7484 "n_groups": 27485 },7486 "number_recall": {7487 "mean": 0.9987893462469734,7488 "ci_low": 0.9986648865153538,7489 "ci_high": 1.0,7490 "n_items": 118,7491 "n_groups": 27492 },7493 "placeholders_exact": {7494 "mean": 1.0,7495 "ci_low": 1.0,7496 "ci_high": 1.0,7497 "n_items": 118,7498 "n_groups": 27499 }7500 },7501 "humanities": {7502 "n": 263,7503 "chrf": {7504 "mean": 63.481804722681446,7505 "ci_low": 59.638377591212056,7506 "ci_high": 64.08826518416305,7507 "n_items": 263,7508 "n_groups": 37509 },7510 "edit_sim": {7511 "mean": 0.6572255500013914,7512 "ci_low": 0.6188748221601789,7513 "ci_high": 0.6608056887511837,7514 "n_items": 263,7515 "n_groups": 37516 },7517 "rougeL": {7518 "mean": 0.6646905929471342,7519 "ci_low": 0.6299559331208235,7520 "ci_high": 0.6670002308404711,7521 "n_items": 263,7522 "n_groups": 37523 },7524 "exact_match": {7525 "mean": 0.0,7526 "ci_low": 0.0,7527 "ci_high": 0.0,7528 "n_items": 263,7529 "n_groups": 37530 },7531 "number_recall": {7532 "mean": 1.0,7533 "ci_low": 1.0,7534 "ci_high": 1.0,7535 "n_items": 263,7536 "n_groups": 37537 },7538 "placeholders_exact": {7539 "mean": 1.0,7540 "ci_low": 1.0,7541 "ci_high": 1.0,7542 "n_items": 263,7543 "n_groups": 37544 }7545 },7546 "life_sciences": {7547 "n": 1874,7548 "chrf": {7549 "mean": 71.77628539216494,7550 "ci_low": 69.89624563753144,7551 "ci_high": 73.34188704384512,7552 "n_items": 1874,7553 "n_groups": 1437554 },7555 "edit_sim": {7556 "mean": 0.706401248870516,7557 "ci_low": 0.6925410241106431,7558 "ci_high": 0.7199088776320882,7559 "n_items": 1874,7560 "n_groups": 1437561 },7562 "rougeL": {7563 "mean": 0.717099596596834,7564 "ci_low": 0.702721812050978,7565 "ci_high": 0.7309900715820028,7566 "n_items": 1874,7567 "n_groups": 1437568 },7569 "exact_match": {7570 "mean": 0.0,7571 "ci_low": 0.0,7572 "ci_high": 0.0,7573 "n_items": 1874,7574 "n_groups": 1437575 },7576 "number_recall": {7577 "mean": 0.9892682154387262,7578 "ci_low": 0.9843362552157364,7579 "ci_high": 0.993258801844302,7580 "n_items": 1874,7581 "n_groups": 1437582 },7583 "placeholders_exact": {7584 "mean": 0.9770544290288153,7585 "ci_low": 0.9615597597612703,7586 "ci_high": 0.9891438825677763,7587 "n_items": 1874,7588 "n_groups": 1437589 }7590 },7591 "mathematics": {7592 "n": 712,7593 "chrf": {7594 "mean": 68.36627940044808,7595 "ci_low": 65.36563445863308,7596 "ci_high": 71.70567504066369,7597 "n_items": 712,7598 "n_groups": 57599 },7600 "edit_sim": {7601 "mean": 0.6908152878705758,7602 "ci_low": 0.664400940507765,7603 "ci_high": 0.711246324012562,7604 "n_items": 712,7605 "n_groups": 57606 },7607 "rougeL": {7608 "mean": 0.6912143658939708,7609 "ci_low": 0.6659187795325728,7610 "ci_high": 0.7233321636437149,7611 "n_items": 712,7612 "n_groups": 57613 },7614 "exact_match": {7615 "mean": 0.0,7616 "ci_low": 0.0,7617 "ci_high": 0.0,7618 "n_items": 712,7619 "n_groups": 57620 },7621 "number_recall": {7622 "mean": 0.9953697987405853,7623 "ci_low": 0.9910003789314134,7624 "ci_high": 0.9987799467613133,7625 "n_items": 712,7626 "n_groups": 57627 },7628 "placeholders_exact": {7629 "mean": 0.9929775280898876,7630 "ci_low": 0.9737903225806451,7631 "ci_high": 1.0,7632 "n_items": 712,7633 "n_groups": 57634 }7635 },7636 "other": {7637 "n": 669,7638 "chrf": {7639 "mean": 68.97870819882844,7640 "ci_low": 66.60169643217824,7641 "ci_high": 72.1251732937606,7642 "n_items": 669,7643 "n_groups": 137644 },7645 "edit_sim": {7646 "mean": 0.673377401210023,7647 "ci_low": 0.6533499158260869,7648 "ci_high": 0.7009871424031499,7649 "n_items": 669,7650 "n_groups": 137651 },7652 "rougeL": {7653 "mean": 0.6829288894745044,7654 "ci_low": 0.6609875794822255,7655 "ci_high": 0.7122548218742031,7656 "n_items": 669,7657 "n_groups": 137658 },7659 "exact_match": {7660 "mean": 0.0,7661 "ci_low": 0.0,7662 "ci_high": 0.0,7663 "n_items": 669,7664 "n_groups": 137665 },7666 "number_recall": {7667 "mean": 0.9832431727050562,7668 "ci_low": 0.9544473004039559,7669 "ci_high": 0.9959250688343859,7670 "n_items": 669,7671 "n_groups": 137672 },7673 "placeholders_exact": {7674 "mean": 0.9955156950672646,7675 "ci_low": 0.9845195238438093,7676 "ci_high": 1.0,7677 "n_items": 669,7678 "n_groups": 137679 }7680 },7681 "social_sciences": {7682 "n": 1536,7683 "chrf": {7684 "mean": 68.68015443116364,7685 "ci_low": 66.58487112814349,7686 "ci_high": 70.17984866221994,7687 "n_items": 1536,7688 "n_groups": 297689 },7690 "edit_sim": {7691 "mean": 0.6795709850289992,7692 "ci_low": 0.6623064797455737,7693 "ci_high": 0.6947419742768198,7694 "n_items": 1536,7695 "n_groups": 297696 },7697 "rougeL": {7698 "mean": 0.6866668819724223,7699 "ci_low": 0.6671696095370121,7700 "ci_high": 0.7035316959334602,7701 "n_items": 1536,7702 "n_groups": 297703 },7704 "exact_match": {7705 "mean": 0.0,7706 "ci_low": 0.0,7707 "ci_high": 0.0,7708 "n_items": 1536,7709 "n_groups": 297710 },7711 "number_recall": {7712 "mean": 0.995058811734116,7713 "ci_low": 0.9914997426952421,7714 "ci_high": 0.9981660161600566,7715 "n_items": 1536,7716 "n_groups": 297717 },7718 "placeholders_exact": {7719 "mean": 0.99609375,7720 "ci_low": 0.9921402405615638,7721 "ci_high": 0.9993234214501441,7722 "n_items": 1536,7723 "n_groups": 297724 }7725 },7726 "statistics": {7727 "n": 828,7728 "chrf": {7729 "mean": 70.50835218392542,7730 "ci_low": 67.92621437456296,7731 "ci_high": 73.19339924198417,7732 "n_items": 828,7733 "n_groups": 97734 },7735 "edit_sim": {7736 "mean": 0.6924234643815037,7737 "ci_low": 0.6708816500647601,7738 "ci_high": 0.7162108474842944,7739 "n_items": 828,7740 "n_groups": 97741 },7742 "rougeL": {7743 "mean": 0.7132570357581235,7744 "ci_low": 0.6892522797744045,7745 "ci_high": 0.7373061289522895,7746 "n_items": 828,7747 "n_groups": 97748 },7749 "exact_match": {7750 "mean": 0.0,7751 "ci_low": 0.0,7752 "ci_high": 0.0,7753 "n_items": 828,7754 "n_groups": 97755 },7756 "number_recall": {7757 "mean": 0.9846066650218955,7758 "ci_low": 0.9691107575321166,7759 "ci_high": 0.9949444080405252,7760 "n_items": 828,7761 "n_groups": 97762 },7763 "placeholders_exact": {7764 "mean": 0.9915458937198067,7765 "ci_low": 0.9867629055857419,7766 "ci_high": 0.9964994165694282,7767 "n_items": 828,7768 "n_groups": 97769 }7770 }7771 },7772 "by_era": {7773 "1900-1949": {7774 "n": 1164,7775 "chrf": {7776 "mean": 64.10904585711121,7777 "ci_low": 61.87634680656502,7778 "ci_high": 67.14512323726936,7779 "n_items": 1164,7780 "n_groups": 187781 },7782 "edit_sim": {7783 "mean": 0.6586575848222803,7784 "ci_low": 0.635084052557831,7785 "ci_high": 0.6952367391887684,7786 "n_items": 1164,7787 "n_groups": 187788 },7789 "rougeL": {7790 "mean": 0.6673506087774369,7791 "ci_low": 0.6423312213184834,7792 "ci_high": 0.7085637889089785,7793 "n_items": 1164,7794 "n_groups": 187795 },7796 "exact_match": {7797 "mean": 0.0,7798 "ci_low": 0.0,7799 "ci_high": 0.0,7800 "n_items": 1164,7801 "n_groups": 187802 },7803 "number_recall": {7804 "mean": 0.9998772704958272,7805 "ci_low": 0.9995933760876836,7806 "ci_high": 1.0,7807 "n_items": 1164,7808 "n_groups": 187809 },7810 "placeholders_exact": {7811 "mean": 1.0,7812 "ci_low": 1.0,7813 "ci_high": 1.0,7814 "n_items": 1164,7815 "n_groups": 187816 }7817 },7818 "1950-1979": {7819 "n": 206,7820 "chrf": {7821 "mean": 62.975518446489126,7822 "ci_low": 61.01013074149864,7823 "ci_high": 63.44910584528203,7824 "n_items": 206,7825 "n_groups": 27826 },7827 "edit_sim": {7828 "mean": 0.6525264739415852,7829 "ci_low": 0.6181677324817508,7830 "ci_high": 0.6608056887511837,7831 "n_items": 206,7832 "n_groups": 27833 },7834 "rougeL": {7835 "mean": 0.657798622244935,7836 "ci_low": 0.6236845264062563,7837 "ci_high": 0.666018886302448,7838 "n_items": 206,7839 "n_groups": 27840 },7841 "exact_match": {7842 "mean": 0.0,7843 "ci_low": 0.0,7844 "ci_high": 0.0,7845 "n_items": 206,7846 "n_groups": 27847 },7848 "number_recall": {7849 "mean": 1.0,7850 "ci_low": 1.0,7851 "ci_high": 1.0,7852 "n_items": 206,7853 "n_groups": 27854 },7855 "placeholders_exact": {7856 "mean": 1.0,7857 "ci_low": 1.0,7858 "ci_high": 1.0,7859 "n_items": 206,7860 "n_groups": 27861 }7862 },7863 "1980-1999": {7864 "n": 151,7865 "chrf": {7866 "mean": 64.12284709898762,7867 "ci_low": 62.68833829299638,7868 "ci_high": 79.07079126230954,7869 "n_items": 151,7870 "n_groups": 47871 },7872 "edit_sim": {7873 "mean": 0.6668064435778865,7874 "ci_low": 0.6537007758470956,7875 "ci_high": 0.8105780193144613,7876 "n_items": 151,7877 "n_groups": 47878 },7879 "rougeL": {7880 "mean": 0.6685015929028992,7881 "ci_low": 0.6569684346761903,7882 "ci_high": 0.7905485865019557,7883 "n_items": 151,7884 "n_groups": 47885 },7886 "exact_match": {7887 "mean": 0.0,7888 "ci_low": 0.0,7889 "ci_high": 0.0,7890 "n_items": 151,7891 "n_groups": 47892 },7893 "number_recall": {7894 "mean": 1.0,7895 "ci_low": 1.0,7896 "ci_high": 1.0,7897 "n_items": 151,7898 "n_groups": 47899 },7900 "placeholders_exact": {7901 "mean": 1.0,7902 "ci_low": 1.0,7903 "ci_high": 1.0,7904 "n_items": 151,7905 "n_groups": 47906 }7907 },7908 "2000-2009": {7909 "n": 1545,7910 "chrf": {7911 "mean": 69.91478469891322,7912 "ci_low": 68.57871900660999,7913 "ci_high": 71.28507870744183,7914 "n_items": 1545,7915 "n_groups": 697916 },7917 "edit_sim": {7918 "mean": 0.6941020376870649,7919 "ci_low": 0.6818566924894947,7920 "ci_high": 0.7070463221030786,7921 "n_items": 1545,7922 "n_groups": 697923 },7924 "rougeL": {7925 "mean": 0.7042873619133365,7926 "ci_low": 0.691916573179798,7927 "ci_high": 0.7166045899050936,7928 "n_items": 1545,7929 "n_groups": 697930 },7931 "exact_match": {7932 "mean": 0.0,7933 "ci_low": 0.0,7934 "ci_high": 0.0,7935 "n_items": 1545,7936 "n_groups": 697937 },7938 "number_recall": {7939 "mean": 0.990692064508455,7940 "ci_low": 0.9852267151827103,7941 "ci_high": 0.9950517396072913,7942 "n_items": 1545,7943 "n_groups": 697944 },7945 "placeholders_exact": {7946 "mean": 0.9935275080906149,7947 "ci_low": 0.9862559678944577,7948 "ci_high": 0.9986018093861909,7949 "n_items": 1545,7950 "n_groups": 697951 }7952 },7953 "2010-2017": {7954 "n": 12583,7955 "chrf": {7956 "mean": 69.87176915040948,7957 "ci_low": 69.37269419987825,7958 "ci_high": 70.35971553721531,7959 "n_items": 12583,7960 "n_groups": 5597961 },7962 "edit_sim": {7963 "mean": 0.6873514931536548,7964 "ci_low": 0.6823099261457803,7965 "ci_high": 0.692064971920711,7966 "n_items": 12583,7967 "n_groups": 5597968 },7969 "rougeL": {7970 "mean": 0.6960864901032751,7971 "ci_low": 0.6904430399986039,7972 "ci_high": 0.7013022053104149,7973 "n_items": 12583,7974 "n_groups": 5597975 },7976 "exact_match": {7977 "mean": 0.0,7978 "ci_low": 0.0,7979 "ci_high": 0.0,7980 "n_items": 12583,7981 "n_groups": 5597982 },7983 "number_recall": {7984 "mean": 0.9896948238216814,7985 "ci_low": 0.9873989800034251,7986 "ci_high": 0.9917708873496389,7987 "n_items": 12583,7988 "n_groups": 5597989 },7990 "placeholders_exact": {7991 "mean": 0.991178574266868,7992 "ci_low": 0.9883684481475283,7993 "ci_high": 0.9937546811828385,7994 "n_items": 12583,7995 "n_groups": 5597996 }7997 }7998 },7999 "by_role": {8000 "abstract": {8001 "n": 1255,8002 "chrf": {8003 "mean": 70.30567496261119,8004 "ci_low": 69.47484119308947,8005 "ci_high": 71.20900160182168,8006 "n_items": 1255,8007 "n_groups": 1958008 },8009 "edit_sim": {8010 "mean": 0.6848308545346399,8011 "ci_low": 0.6751416895759149,8012 "ci_high": 0.6950786261511226,8013 "n_items": 1255,8014 "n_groups": 1958015 },8016 "rougeL": {8017 "mean": 0.6878653382553992,8018 "ci_low": 0.6784606310227381,8019 "ci_high": 0.6974698149466263,8020 "n_items": 1255,8021 "n_groups": 1958022 },8023 "exact_match": {8024 "mean": 0.0,8025 "ci_low": 0.0,8026 "ci_high": 0.0,8027 "n_items": 1255,8028 "n_groups": 1958029 },8030 "number_recall": {8031 "mean": 0.9963260516978405,8032 "ci_low": 0.9942170606845674,8033 "ci_high": 0.9981525901514529,8034 "n_items": 1255,8035 "n_groups": 1958036 },8037 "placeholders_exact": {8038 "mean": 1.0,8039 "ci_low": 1.0,8040 "ci_high": 1.0,8041 "n_items": 1255,8042 "n_groups": 1958043 }8044 },8045 "background": {8046 "n": 964,8047 "chrf": {8048 "mean": 69.8941155896641,8049 "ci_low": 68.83762067329734,8050 "ci_high": 71.00261468985329,8051 "n_items": 964,8052 "n_groups": 848053 },8054 "edit_sim": {8055 "mean": 0.6925680542952741,8056 "ci_low": 0.6804153978042821,8057 "ci_high": 0.704489158220134,8058 "n_items": 964,8059 "n_groups": 848060 },8061 "rougeL": {8062 "mean": 0.698375343698084,8063 "ci_low": 0.6834744753862863,8064 "ci_high": 0.7124347874378926,8065 "n_items": 964,8066 "n_groups": 848067 },8068 "exact_match": {8069 "mean": 0.0,8070 "ci_low": 0.0,8071 "ci_high": 0.0,8072 "n_items": 964,8073 "n_groups": 848074 },8075 "number_recall": {8076 "mean": 0.9956719686491471,8077 "ci_low": 0.9922379664401525,8078 "ci_high": 0.998279410147013,8079 "n_items": 964,8080 "n_groups": 848081 },8082 "placeholders_exact": {8083 "mean": 0.9896265560165975,8084 "ci_low": 0.9770763769865682,8085 "ci_high": 0.9977999007365062,8086 "n_items": 964,8087 "n_groups": 848088 }8089 },8090 "chapter": {8091 "n": 1287,8092 "chrf": {8093 "mean": 64.22214271665759,8094 "ci_low": 62.94200964886674,8095 "ci_high": 65.98944985443569,8096 "n_items": 1287,8097 "n_groups": 218098 },8099 "edit_sim": {8100 "mean": 0.6573947669835715,8101 "ci_low": 0.6452396224689515,8102 "ci_high": 0.6788620177499239,8103 "n_items": 1287,8104 "n_groups": 218105 },8106 "rougeL": {8107 "mean": 0.6664126265494463,8108 "ci_low": 0.6542593802930519,8109 "ci_high": 0.6873601445960459,8110 "n_items": 1287,8111 "n_groups": 218112 },8113 "exact_match": {8114 "mean": 0.0,8115 "ci_low": 0.0,8116 "ci_high": 0.0,8117 "n_items": 1287,8118 "n_groups": 218119 },8120 "number_recall": {8121 "mean": 0.9998889998889999,8122 "ci_low": 0.9995489521717198,8123 "ci_high": 1.0,8124 "n_items": 1287,8125 "n_groups": 218126 },8127 "placeholders_exact": {8128 "mean": 1.0,8129 "ci_low": 1.0,8130 "ci_high": 1.0,8131 "n_items": 1287,8132 "n_groups": 218133 }8134 },8135 "conclusion": {8136 "n": 1168,8137 "chrf": {8138 "mean": 67.5423774054605,8139 "ci_low": 66.65515151228765,8140 "ci_high": 68.47938344672275,8141 "n_items": 1168,8142 "n_groups": 1548143 },8144 "edit_sim": {8145 "mean": 0.6672545952074462,8146 "ci_low": 0.6568475775196359,8147 "ci_high": 0.6777281156395177,8148 "n_items": 1168,8149 "n_groups": 1548150 },8151 "rougeL": {8152 "mean": 0.6663206071906462,8153 "ci_low": 0.6558716121543462,8154 "ci_high": 0.6770439654570802,8155 "n_items": 1168,8156 "n_groups": 1548157 },8158 "exact_match": {8159 "mean": 0.0,8160 "ci_low": 0.0,8161 "ci_high": 0.0,8162 "n_items": 1168,8163 "n_groups": 1548164 },8165 "number_recall": {8166 "mean": 0.9922407168554429,8167 "ci_low": 0.98683660164488,8168 "ci_high": 0.996507931606141,8169 "n_items": 1168,8170 "n_groups": 1548171 },8172 "placeholders_exact": {8173 "mean": 0.9940068493150684,8174 "ci_low": 0.9825335918503285,8175 "ci_high": 1.0,8176 "n_items": 1168,8177 "n_groups": 1548178 }8179 },8180 "data": {8181 "n": 912,8182 "chrf": {8183 "mean": 70.65183723001535,8184 "ci_low": 69.68418033118637,8185 "ci_high": 71.7142090366239,8186 "n_items": 912,8187 "n_groups": 1048188 },8189 "edit_sim": {8190 "mean": 0.6907306744817281,8191 "ci_low": 0.6794270588559641,8192 "ci_high": 0.7018274733900463,8193 "n_items": 912,8194 "n_groups": 1048195 },8196 "rougeL": {8197 "mean": 0.711238784158441,8198 "ci_low": 0.6998291651218509,8199 "ci_high": 0.7222563016211317,8200 "n_items": 912,8201 "n_groups": 1048202 },8203 "exact_match": {8204 "mean": 0.0,8205 "ci_low": 0.0,8206 "ci_high": 0.0,8207 "n_items": 912,8208 "n_groups": 1048209 },8210 "number_recall": {8211 "mean": 0.985443696328154,8212 "ci_low": 0.9768501398804685,8213 "ci_high": 0.9919253266853232,8214 "n_items": 912,8215 "n_groups": 1048216 },8217 "placeholders_exact": {8218 "mean": 0.9945175438596491,8219 "ci_low": 0.9846555478754636,8220 "ci_high": 1.0,8221 "n_items": 912,8222 "n_groups": 1048223 }8224 },8225 "discussion": {8226 "n": 1601,8227 "chrf": {8228 "mean": 69.29412010450686,8229 "ci_low": 68.46154246110756,8230 "ci_high": 70.11653699883425,8231 "n_items": 1601,8232 "n_groups": 1428233 },8234 "edit_sim": {8235 "mean": 0.6832117543669257,8236 "ci_low": 0.6741066671399688,8237 "ci_high": 0.6918894123415142,8238 "n_items": 1601,8239 "n_groups": 1428240 },8241 "rougeL": {8242 "mean": 0.6858916872529216,8243 "ci_low": 0.6762710624251091,8244 "ci_high": 0.6953422269281814,8245 "n_items": 1601,8246 "n_groups": 1428247 },8248 "exact_match": {8249 "mean": 0.0,8250 "ci_low": 0.0,8251 "ci_high": 0.0,8252 "n_items": 1601,8253 "n_groups": 1428254 },8255 "number_recall": {8256 "mean": 0.9892050766325116,8257 "ci_low": 0.9839982879897103,8258 "ci_high": 0.993937999525361,8259 "n_items": 1601,8260 "n_groups": 1428261 },8262 "placeholders_exact": {8263 "mean": 0.9881324172392255,8264 "ci_low": 0.9779642882827262,8265 "ci_high": 0.9953658058502801,8266 "n_items": 1601,8267 "n_groups": 1428268 }8269 },8270 "introduction": {8271 "n": 1789,8272 "chrf": {8273 "mean": 69.22957899639322,8274 "ci_low": 68.27309355031463,8275 "ci_high": 70.20447123190938,8276 "n_items": 1789,8277 "n_groups": 1768278 },8279 "edit_sim": {8280 "mean": 0.6836008381759561,8281 "ci_low": 0.6736313198672559,8282 "ci_high": 0.6938704059127799,8283 "n_items": 1789,8284 "n_groups": 1768285 },8286 "rougeL": {8287 "mean": 0.6847607297071834,8288 "ci_low": 0.6744910852566055,8289 "ci_high": 0.6949404472007298,8290 "n_items": 1789,8291 "n_groups": 1768292 },8293 "exact_match": {8294 "mean": 0.0,8295 "ci_low": 0.0,8296 "ci_high": 0.0,8297 "n_items": 1789,8298 "n_groups": 1768299 },8300 "number_recall": {8301 "mean": 0.9905184057294175,8302 "ci_low": 0.983895094998135,8303 "ci_high": 0.99576068924983,8304 "n_items": 1789,8305 "n_groups": 1768306 },8307 "placeholders_exact": {8308 "mean": 0.9888205701509223,8309 "ci_low": 0.9787597248656049,8310 "ci_high": 0.9961025041116535,8311 "n_items": 1789,8312 "n_groups": 1768313 }8314 },8315 "limitations": {8316 "n": 425,8317 "chrf": {8318 "mean": 68.057839883496,8319 "ci_low": 66.4187007828767,8320 "ci_high": 69.70490577235692,8321 "n_items": 425,8322 "n_groups": 418323 },8324 "edit_sim": {8325 "mean": 0.6697090488434229,8326 "ci_low": 0.6526742812511599,8327 "ci_high": 0.6874818261897183,8328 "n_items": 425,8329 "n_groups": 418330 },8331 "rougeL": {8332 "mean": 0.6724474669811078,8333 "ci_low": 0.6512774688126259,8334 "ci_high": 0.69433373380858,8335 "n_items": 425,8336 "n_groups": 418337 },8338 "exact_match": {8339 "mean": 0.0,8340 "ci_low": 0.0,8341 "ci_high": 0.0,8342 "n_items": 425,8343 "n_groups": 418344 },8345 "number_recall": {8346 "mean": 0.9977254901960784,8347 "ci_low": 0.9951952699124691,8348 "ci_high": 0.9996211309523808,8349 "n_items": 425,8350 "n_groups": 418351 },8352 "placeholders_exact": {8353 "mean": 0.9905882352941177,8354 "ci_low": 0.9779945714808871,8355 "ci_high": 1.0,8356 "n_items": 425,8357 "n_groups": 418358 }8359 },8360 "methods": {8361 "n": 1528,8362 "chrf": {8363 "mean": 71.23846668124085,8364 "ci_low": 70.4147682767886,8365 "ci_high": 72.11390014845527,8366 "n_items": 1528,8367 "n_groups": 1518368 },8369 "edit_sim": {8370 "mean": 0.6991771878506233,8371 "ci_low": 0.6901033369593256,8372 "ci_high": 0.7082172044524453,8373 "n_items": 1528,8374 "n_groups": 1518375 },8376 "rougeL": {8377 "mean": 0.7184466813133122,8378 "ci_low": 0.708850046031888,8379 "ci_high": 0.7284599331514845,8380 "n_items": 1528,8381 "n_groups": 1518382 },8383 "exact_match": {8384 "mean": 0.0,8385 "ci_low": 0.0,8386 "ci_high": 0.0,8387 "n_items": 1528,8388 "n_groups": 1518389 },8390 "number_recall": {8391 "mean": 0.9896993143645572,8392 "ci_low": 0.9844676799918297,8393 "ci_high": 0.9939030276670021,8394 "n_items": 1528,8395 "n_groups": 1518396 },8397 "placeholders_exact": {8398 "mean": 0.9928010471204188,8399 "ci_low": 0.9848064244320859,8400 "ci_high": 0.9985638271965712,8401 "n_items": 1528,8402 "n_groups": 1518403 }8404 },8405 "other": {8406 "n": 1387,8407 "chrf": {8408 "mean": 70.03714045830638,8409 "ci_low": 68.98110233731741,8410 "ci_high": 71.11903103294907,8411 "n_items": 1387,8412 "n_groups": 1198413 },8414 "edit_sim": {8415 "mean": 0.6925153611275168,8416 "ci_low": 0.6827551524001717,8417 "ci_high": 0.7031313870817595,8418 "n_items": 1387,8419 "n_groups": 1198420 },8421 "rougeL": {8422 "mean": 0.7005420226169156,8423 "ci_low": 0.689420890177345,8424 "ci_high": 0.7112350943113166,8425 "n_items": 1387,8426 "n_groups": 1198427 },8428 "exact_match": {8429 "mean": 0.0,8430 "ci_low": 0.0,8431 "ci_high": 0.0,8432 "n_items": 1387,8433 "n_groups": 1198434 },8435 "number_recall": {8436 "mean": 0.9913968451639685,8437 "ci_low": 0.9860169763353558,8438 "ci_high": 0.995494771536971,8439 "n_items": 1387,8440 "n_groups": 1198441 },8442 "placeholders_exact": {8443 "mean": 0.9841384282624369,8444 "ci_low": 0.9716540279655702,8445 "ci_high": 0.9938135132946159,8446 "n_items": 1387,8447 "n_groups": 1198448 }8449 },8450 "preface": {8451 "n": 362,8452 "chrf": {8453 "mean": 63.53991894852006,8454 "ci_low": 59.11369896455676,8455 "ci_high": 68.13494574838653,8456 "n_items": 362,8457 "n_groups": 138458 },8459 "edit_sim": {8460 "mean": 0.6549664895351123,8461 "ci_low": 0.6077236766324375,8462 "ci_high": 0.7057663879825687,8463 "n_items": 362,8464 "n_groups": 138465 },8466 "rougeL": {8467 "mean": 0.661340026069186,8468 "ci_low": 0.6074592321844531,8469 "ci_high": 0.7206640251253945,8470 "n_items": 362,8471 "n_groups": 138472 },8473 "exact_match": {8474 "mean": 0.0,8475 "ci_low": 0.0,8476 "ci_high": 0.0,8477 "n_items": 362,8478 "n_groups": 138479 },8480 "number_recall": {8481 "mean": 1.0,8482 "ci_low": 1.0,8483 "ci_high": 1.0,8484 "n_items": 362,8485 "n_groups": 138486 },8487 "placeholders_exact": {8488 "mean": 1.0,8489 "ci_low": 1.0,8490 "ci_high": 1.0,8491 "n_items": 362,8492 "n_groups": 138493 }8494 },8495 "related_work": {8496 "n": 557,8497 "chrf": {8498 "mean": 71.06708865070895,8499 "ci_low": 69.4887240762573,8500 "ci_high": 72.64382304899047,8501 "n_items": 557,8502 "n_groups": 398503 },8504 "edit_sim": {8505 "mean": 0.6954437966218031,8506 "ci_low": 0.6790311133918358,8507 "ci_high": 0.7141555347678211,8508 "n_items": 557,8509 "n_groups": 398510 },8511 "rougeL": {8512 "mean": 0.7021506315151027,8513 "ci_low": 0.6838871834965378,8514 "ci_high": 0.7215396064859474,8515 "n_items": 557,8516 "n_groups": 398517 },8518 "exact_match": {8519 "mean": 0.0,8520 "ci_low": 0.0,8521 "ci_high": 0.0,8522 "n_items": 557,8523 "n_groups": 398524 },8525 "number_recall": {8526 "mean": 0.9871194519916666,8527 "ci_low": 0.9726489752247873,8528 "ci_high": 0.9974322692937085,8529 "n_items": 557,8530 "n_groups": 398531 },8532 "placeholders_exact": {8533 "mean": 0.9982046678635548,8534 "ci_low": 0.9935753263797747,8535 "ci_high": 1.0,8536 "n_items": 557,8537 "n_groups": 398538 }8539 },8540 "results": {8541 "n": 1501,8542 "chrf": {8543 "mean": 70.60630152609706,8544 "ci_low": 69.39875828964108,8545 "ci_high": 71.86687368295698,8546 "n_items": 1501,8547 "n_groups": 1538548 },8549 "edit_sim": {8550 "mean": 0.6947886649978933,8551 "ci_low": 0.6839659268417613,8552 "ci_high": 0.7060047980424914,8553 "n_items": 1501,8554 "n_groups": 1538555 },8556 "rougeL": {8557 "mean": 0.716221522338401,8558 "ci_low": 0.7045880204151803,8559 "ci_high": 0.7283834706686412,8560 "n_items": 1501,8561 "n_groups": 1538562 },8563 "exact_match": {8564 "mean": 0.0,8565 "ci_low": 0.0,8566 "ci_high": 0.0,8567 "n_items": 1501,8568 "n_groups": 1538569 },8570 "number_recall": {8571 "mean": 0.9759744973204093,8572 "ci_low": 0.9675150084616794,8573 "ci_high": 0.9840153751303675,8574 "n_items": 1501,8575 "n_groups": 1538576 },8577 "placeholders_exact": {8578 "mean": 0.9920053297801465,8579 "ci_low": 0.9838479731763035,8580 "ci_high": 0.9981850572573757,8581 "n_items": 1501,8582 "n_groups": 1538583 }8584 },8585 "theory": {8586 "n": 913,8587 "chrf": {8588 "mean": 70.78628316252427,8589 "ci_low": 69.55280235108333,8590 "ci_high": 71.97614491800024,8591 "n_items": 913,8592 "n_groups": 798593 },8594 "edit_sim": {8595 "mean": 0.7043180117163325,8596 "ci_low": 0.6903043798266749,8597 "ci_high": 0.7177743627139238,8598 "n_items": 913,8599 "n_groups": 798600 },8601 "rougeL": {8602 "mean": 0.7176418423386705,8603 "ci_low": 0.7027673783058247,8604 "ci_high": 0.7317818398640672,8605 "n_items": 913,8606 "n_groups": 798607 },8608 "exact_match": {8609 "mean": 0.0,8610 "ci_low": 0.0,8611 "ci_high": 0.0,8612 "n_items": 913,8613 "n_groups": 798614 },8615 "number_recall": {8616 "mean": 0.9925422849026354,8617 "ci_low": 0.9881419382963715,8618 "ci_high": 0.9963991393965312,8619 "n_items": 913,8620 "n_groups": 798621 },8622 "placeholders_exact": {8623 "mean": 0.9890470974808324,8624 "ci_low": 0.9785960800506721,8625 "ci_high": 0.9976635514018691,8626 "n_items": 913,8627 "n_groups": 798628 }8629 }8630 }8631 },8632 "htr-m1-tiny-s3": {8633 "overall": {8634 "n": 15649,8635 "chrf": {8636 "mean": 69.35230829744043,8637 "ci_low": 68.81096347611687,8638 "ci_high": 69.88013621212468,8639 "n_items": 15649,8640 "n_groups": 6528641 },8642 "edit_sim": {8643 "mean": 0.6844550769491311,8644 "ci_low": 0.6796575587840488,8645 "ci_high": 0.689314179901323,8646 "n_items": 15649,8647 "n_groups": 6528648 },8649 "rougeL": {8650 "mean": 0.6929338230606534,8651 "ci_low": 0.6876514393166581,8652 "ci_high": 0.6981895362752856,8653 "n_items": 15649,8654 "n_groups": 6528655 },8656 "exact_match": {8657 "mean": 0.0,8658 "ci_low": 0.0,8659 "ci_high": 0.0,8660 "n_items": 15649,8661 "n_groups": 6528662 },8663 "number_recall": {8664 "mean": 0.9913003908021117,8665 "ci_low": 0.9896339025155289,8666 "ci_high": 0.9928010133363148,8667 "n_items": 15649,8668 "n_groups": 6528669 },8670 "placeholders_exact": {8671 "mean": 0.9921400728481053,8672 "ci_low": 0.9896479541036461,8673 "ci_high": 0.9943451312730507,8674 "n_items": 15649,8675 "n_groups": 6528676 }8677 },8678 "by_variant": {8679 "A": {8680 "n": 2664,8681 "chrf": {8682 "mean": 68.90853716644733,8683 "ci_low": 68.27777421234282,8684 "ci_high": 69.5254953621699,8685 "n_items": 2664,8686 "n_groups": 6308687 },8688 "edit_sim": {8689 "mean": 0.6765305304965151,8690 "ci_low": 0.6709592935263432,8691 "ci_high": 0.6827695525756792,8692 "n_items": 2664,8693 "n_groups": 6308694 },8695 "rougeL": {8696 "mean": 0.6820222434960526,8697 "ci_low": 0.676080623038938,8698 "ci_high": 0.688188200718473,8699 "n_items": 2664,8700 "n_groups": 6308701 },8702 "exact_match": {8703 "mean": 0.0,8704 "ci_low": 0.0,8705 "ci_high": 0.0,8706 "n_items": 2664,8707 "n_groups": 6308708 },8709 "number_recall": {8710 "mean": 0.9905120013379679,8711 "ci_low": 0.9880137445655055,8712 "ci_high": 0.9928202252251878,8713 "n_items": 2664,8714 "n_groups": 6308715 },8716 "placeholders_exact": {8717 "mean": 0.9898648648648649,8718 "ci_low": 0.9857913264650102,8719 "ci_high": 0.9935582269741753,8720 "n_items": 2664,8721 "n_groups": 6308722 }8723 },8724 "B": {8725 "n": 2539,8726 "chrf": {8727 "mean": 74.84692256114637,8728 "ci_low": 74.25618730553678,8729 "ci_high": 75.42252714025122,8730 "n_items": 2539,8731 "n_groups": 6148732 },8733 "edit_sim": {8734 "mean": 0.7508403835540756,8735 "ci_low": 0.7452938372570725,8736 "ci_high": 0.7565555934705956,8737 "n_items": 2539,8738 "n_groups": 6148739 },8740 "rougeL": {8741 "mean": 0.7574496897911921,8742 "ci_low": 0.7515731835979075,8743 "ci_high": 0.763307677903906,8744 "n_items": 2539,8745 "n_groups": 6148746 },8747 "exact_match": {8748 "mean": 0.0,8749 "ci_low": 0.0,8750 "ci_high": 0.0,8751 "n_items": 2539,8752 "n_groups": 6148753 },8754 "number_recall": {8755 "mean": 0.9922015622070871,8756 "ci_low": 0.9899265713069739,8757 "ci_high": 0.994098672725829,8758 "n_items": 2539,8759 "n_groups": 6148760 },8761 "placeholders_exact": {8762 "mean": 0.9917290271760536,8763 "ci_low": 0.9877934583089111,8764 "ci_high": 0.9948702429723197,8765 "n_items": 2539,8766 "n_groups": 6148767 }8768 },8769 "C": {8770 "n": 2663,8771 "chrf": {8772 "mean": 71.68625520883695,8773 "ci_low": 71.14643067699888,8774 "ci_high": 72.27883107089993,8775 "n_items": 2663,8776 "n_groups": 6388777 },8778 "edit_sim": {8779 "mean": 0.7259582895799321,8780 "ci_low": 0.720656521395216,8781 "ci_high": 0.731476756501756,8782 "n_items": 2663,8783 "n_groups": 6388784 },8785 "rougeL": {8786 "mean": 0.7455405543420366,8787 "ci_low": 0.7399123585597084,8788 "ci_high": 0.7515476898510892,8789 "n_items": 2663,8790 "n_groups": 6388791 },8792 "exact_match": {8793 "mean": 0.0,8794 "ci_low": 0.0,8795 "ci_high": 0.0,8796 "n_items": 2663,8797 "n_groups": 6388798 },8799 "number_recall": {8800 "mean": 0.9914250010723678,8801 "ci_low": 0.9894051538799246,8802 "ci_high": 0.9932928542057274,8803 "n_items": 2663,8804 "n_groups": 6388805 },8806 "placeholders_exact": {8807 "mean": 0.9954938039804732,8808 "ci_low": 0.9925722095398644,8809 "ci_high": 0.9980784565541639,8810 "n_items": 2663,8811 "n_groups": 6388812 }8813 },8814 "D": {8815 "n": 2708,8816 "chrf": {8817 "mean": 70.06522348467263,8818 "ci_low": 69.47092463772093,8819 "ci_high": 70.65711157063464,8820 "n_items": 2708,8821 "n_groups": 6388822 },8823 "edit_sim": {8824 "mean": 0.6960246111695941,8825 "ci_low": 0.6906576455833267,8826 "ci_high": 0.7013335728443123,8827 "n_items": 2708,8828 "n_groups": 6388829 },8830 "rougeL": {8831 "mean": 0.7008078254507095,8832 "ci_low": 0.6954150842192911,8833 "ci_high": 0.7063027867311276,8834 "n_items": 2708,8835 "n_groups": 6388836 },8837 "exact_match": {8838 "mean": 0.0,8839 "ci_low": 0.0,8840 "ci_high": 0.0,8841 "n_items": 2708,8842 "n_groups": 6388843 },8844 "number_recall": {8845 "mean": 0.990938168170497,8846 "ci_low": 0.9887886001500649,8847 "ci_high": 0.9928208666571694,8848 "n_items": 2708,8849 "n_groups": 6388850 },8851 "placeholders_exact": {8852 "mean": 0.9929837518463811,8853 "ci_low": 0.9895130431366387,8854 "ci_high": 0.9962065886766704,8855 "n_items": 2708,8856 "n_groups": 6388857 }8858 },8859 "E": {8860 "n": 5075,8861 "chrf": {8862 "mean": 65.23122568174438,8863 "ci_low": 64.62190421699206,8864 "ci_high": 65.8237866896297,8865 "n_items": 5075,8866 "n_groups": 6238867 },8868 "edit_sim": {8869 "mean": 0.6274512039195701,8870 "ci_low": 0.6221315863802398,8871 "ci_high": 0.6328848189951398,8872 "n_items": 5075,8873 "n_groups": 6238874 },8875 "rougeL": {8876 "mean": 0.634578776451129,8877 "ci_low": 0.6286035197755063,8878 "ci_high": 0.640880406414931,8879 "n_items": 5075,8880 "n_groups": 6238881 },8882 "exact_match": {8883 "mean": 0.0,8884 "ci_low": 0.0,8885 "ci_high": 0.0,8886 "n_items": 5075,8887 "n_groups": 6238888 },8889 "number_recall": {8890 "mean": 0.9913912788951106,8891 "ci_low": 0.9891357935501662,8892 "ci_high": 0.9933770968747592,8893 "n_items": 5075,8894 "n_groups": 6238895 },8896 "placeholders_exact": {8897 "mean": 0.9913300492610837,8898 "ci_low": 0.9882182481710825,8899 "ci_high": 0.9941662066982877,8900 "n_items": 5075,8901 "n_groups": 6238902 }8903 }8904 },8905 "by_discipline": {8906 "biomedicine": {8907 "n": 2154,8908 "chrf": {8909 "mean": 69.56534593832373,8910 "ci_low": 68.42104754551032,8911 "ci_high": 70.65348517042445,8912 "n_items": 2154,8913 "n_groups": 2448914 },8915 "edit_sim": {8916 "mean": 0.6812963511236176,8917 "ci_low": 0.6729309758296109,8918 "ci_high": 0.6902417486301813,8919 "n_items": 2154,8920 "n_groups": 2448921 },8922 "rougeL": {8923 "mean": 0.6905166845936243,8924 "ci_low": 0.6811443984428484,8925 "ci_high": 0.7000787778689009,8926 "n_items": 2154,8927 "n_groups": 2448928 },8929 "exact_match": {8930 "mean": 0.0,8931 "ci_low": 0.0,8932 "ci_high": 0.0,8933 "n_items": 2154,8934 "n_groups": 2448935 },8936 "number_recall": {8937 "mean": 0.9896970981406913,8938 "ci_low": 0.9852910945249256,8939 "ci_high": 0.9935401029132649,8940 "n_items": 2154,8941 "n_groups": 2448942 },8943 "placeholders_exact": {8944 "mean": 0.9944289693593314,8945 "ci_low": 0.9902043259433309,8946 "ci_high": 0.9978439910473977,8947 "n_items": 2154,8948 "n_groups": 2448949 }8950 },8951 "chemistry": {8952 "n": 837,8953 "chrf": {8954 "mean": 72.51473941488726,8955 "ci_low": 71.04736856032441,8956 "ci_high": 73.90345606126202,8957 "n_items": 837,8958 "n_groups": 138959 },8960 "edit_sim": {8961 "mean": 0.6987539767053086,8962 "ci_low": 0.6836469445602806,8963 "ci_high": 0.7151106953996335,8964 "n_items": 837,8965 "n_groups": 138966 },8967 "rougeL": {8968 "mean": 0.7145330025656574,8969 "ci_low": 0.6998384967000227,8970 "ci_high": 0.7296174500148298,8971 "n_items": 837,8972 "n_groups": 138973 },8974 "exact_match": {8975 "mean": 0.0,8976 "ci_low": 0.0,8977 "ci_high": 0.0,8978 "n_items": 837,8979 "n_groups": 138980 },8981 "number_recall": {8982 "mean": 0.98705621325325,8983 "ci_low": 0.9821624149343627,8984 "ci_high": 0.9919342969525512,8985 "n_items": 837,8986 "n_groups": 138987 },8988 "placeholders_exact": {8989 "mean": 0.985663082437276,8990 "ci_low": 0.9700571311467215,8991 "ci_high": 0.9967167727852526,8992 "n_items": 837,8993 "n_groups": 138994 }8995 },8996 "computer_science": {8997 "n": 1375,8998 "chrf": {8999 "mean": 69.61811301347271,9000 "ci_low": 68.19018713072596,9001 "ci_high": 70.91970946191073,9002 "n_items": 1375,9003 "n_groups": 209004 },9005 "edit_sim": {9006 "mean": 0.6917905432523018,9007 "ci_low": 0.6765328837306455,9008 "ci_high": 0.7049153620177683,9009 "n_items": 1375,9010 "n_groups": 209011 },9012 "rougeL": {9013 "mean": 0.6966182137335222,9014 "ci_low": 0.6802648798443117,9015 "ci_high": 0.7096680174573892,9016 "n_items": 1375,9017 "n_groups": 209018 },9019 "exact_match": {9020 "mean": 0.0,9021 "ci_low": 0.0,9022 "ci_high": 0.0,9023 "n_items": 1375,9024 "n_groups": 209025 },9026 "number_recall": {9027 "mean": 0.9893171454807818,9028 "ci_low": 0.9802239722434389,9029 "ci_high": 0.9970444621971881,9030 "n_items": 1375,9031 "n_groups": 209032 },9033 "placeholders_exact": {9034 "mean": 0.9912727272727273,9035 "ci_low": 0.9809449543129962,9036 "ci_high": 0.9986188559233298,9037 "n_items": 1375,9038 "n_groups": 209039 }9040 },9041 "economics": {9042 "n": 1944,9043 "chrf": {9044 "mean": 68.70183159306958,9045 "ci_low": 67.91131765597287,9046 "ci_high": 69.45741399699497,9047 "n_items": 1944,9048 "n_groups": 1039049 },9050 "edit_sim": {9051 "mean": 0.6817820232526973,9052 "ci_low": 0.6731992199476798,9053 "ci_high": 0.690386616045751,9054 "n_items": 1944,9055 "n_groups": 1039056 },9057 "rougeL": {9058 "mean": 0.6855796757269083,9059 "ci_low": 0.6755637705913788,9060 "ci_high": 0.6952498539515543,9061 "n_items": 1944,9062 "n_groups": 1039063 },9064 "exact_match": {9065 "mean": 0.0,9066 "ci_low": 0.0,9067 "ci_high": 0.0,9068 "n_items": 1944,9069 "n_groups": 1039070 },9071 "number_recall": {9072 "mean": 0.9927534636716735,9073 "ci_low": 0.9892099200282575,9074 "ci_high": 0.995647835093767,9075 "n_items": 1944,9076 "n_groups": 1039077 },9078 "placeholders_exact": {9079 "mean": 0.9953703703703703,9080 "ci_low": 0.9888471949519887,9081 "ci_high": 1.0,9082 "n_items": 1944,9083 "n_groups": 1039084 }9085 },9086 "engineering": {9087 "n": 1296,9088 "chrf": {9089 "mean": 66.95021396179972,9090 "ci_low": 65.30883077666071,9091 "ci_high": 68.58492152115593,9092 "n_items": 1296,9093 "n_groups": 179094 },9095 "edit_sim": {9096 "mean": 0.6591994394499316,9097 "ci_low": 0.6447824903294325,9098 "ci_high": 0.6734349770648625,9099 "n_items": 1296,9100 "n_groups": 179101 },9102 "rougeL": {9103 "mean": 0.6691887906905468,9104 "ci_low": 0.6554518043410564,9105 "ci_high": 0.683503947510861,9106 "n_items": 1296,9107 "n_groups": 179108 },9109 "exact_match": {9110 "mean": 0.0,9111 "ci_low": 0.0,9112 "ci_high": 0.0,9113 "n_items": 1296,9114 "n_groups": 179115 },9116 "number_recall": {9117 "mean": 0.9901590973868021,9118 "ci_low": 0.9852567972082374,9119 "ci_high": 0.9943462360215471,9120 "n_items": 1296,9121 "n_groups": 179122 },9123 "placeholders_exact": {9124 "mean": 0.9907407407407407,9125 "ci_low": 0.9841548299229338,9126 "ci_high": 0.9966053408486684,9127 "n_items": 1296,9128 "n_groups": 179129 }9130 },9131 "finance": {9132 "n": 2043,9133 "chrf": {9134 "mean": 68.31898494994492,9135 "ci_low": 67.0220839081992,9136 "ci_high": 69.72455212614165,9137 "n_items": 2043,9138 "n_groups": 519139 },9140 "edit_sim": {9141 "mean": 0.6771037618169672,9142 "ci_low": 0.6639906673349414,9143 "ci_high": 0.691406310814176,9144 "n_items": 2043,9145 "n_groups": 519146 },9147 "rougeL": {9148 "mean": 0.6847123895669708,9149 "ci_low": 0.6712103882045256,9150 "ci_high": 0.6998610510517855,9151 "n_items": 2043,9152 "n_groups": 519153 },9154 "exact_match": {9155 "mean": 0.0,9156 "ci_low": 0.0,9157 "ci_high": 0.0,9158 "n_items": 2043,9159 "n_groups": 519160 },9161 "number_recall": {9162 "mean": 0.993695591676502,9163 "ci_low": 0.9910394264631391,9164 "ci_high": 0.9960122737069002,9165 "n_items": 2043,9166 "n_groups": 519167 },9168 "placeholders_exact": {9169 "mean": 0.9941262848751835,9170 "ci_low": 0.9885309783920811,9171 "ci_high": 0.9987877998166578,9172 "n_items": 2043,9173 "n_groups": 519174 }9175 },9176 "general_reference": {9177 "n": 118,9178 "chrf": {9179 "mean": 74.56296400042295,9180 "ci_low": 61.10776567137356,9181 "ci_high": 75.94620868845605,9182 "n_items": 118,9183 "n_groups": 29184 },9185 "edit_sim": {9186 "mean": 0.775640850581766,9187 "ci_low": 0.6036328783246864,9188 "ci_high": 0.7933239131502507,9189 "n_items": 118,9190 "n_groups": 29191 },9192 "rougeL": {9193 "mean": 0.8044298313996228,9194 "ci_low": 0.62088158193102,9195 "ci_high": 0.8232992776066752,9196 "n_items": 118,9197 "n_groups": 29198 },9199 "exact_match": {9200 "mean": 0.0,9201 "ci_low": 0.0,9202 "ci_high": 0.0,9203 "n_items": 118,9204 "n_groups": 29205 },9206 "number_recall": {9207 "mean": 0.9975786924939468,9208 "ci_low": 0.9973297730307077,9209 "ci_high": 1.0,9210 "n_items": 118,9211 "n_groups": 29212 },9213 "placeholders_exact": {9214 "mean": 1.0,9215 "ci_low": 1.0,9216 "ci_high": 1.0,9217 "n_items": 118,9218 "n_groups": 29219 }9220 },9221 "humanities": {9222 "n": 263,9223 "chrf": {9224 "mean": 63.547376496212735,9225 "ci_low": 59.40515191092428,9226 "ci_high": 64.30566634479347,9227 "n_items": 263,9228 "n_groups": 39229 },9230 "edit_sim": {9231 "mean": 0.6569622749528743,9232 "ci_low": 0.6180371010647988,9233 "ci_high": 0.65941204497217,9234 "n_items": 263,9235 "n_groups": 39236 },9237 "rougeL": {9238 "mean": 0.6641715308203574,9239 "ci_low": 0.6275711840010834,9240 "ci_high": 0.6680628013570836,9241 "n_items": 263,9242 "n_groups": 39243 },9244 "exact_match": {9245 "mean": 0.0,9246 "ci_low": 0.0,9247 "ci_high": 0.0,9248 "n_items": 263,9249 "n_groups": 39250 },9251 "number_recall": {9252 "mean": 1.0,9253 "ci_low": 1.0,9254 "ci_high": 1.0,9255 "n_items": 263,9256 "n_groups": 39257 },9258 "placeholders_exact": {9259 "mean": 1.0,9260 "ci_low": 1.0,9261 "ci_high": 1.0,9262 "n_items": 263,9263 "n_groups": 39264 }9265 },9266 "life_sciences": {9267 "n": 1874,9268 "chrf": {9269 "mean": 71.80723785143547,9270 "ci_low": 69.94094698278634,9271 "ci_high": 73.37828825472548,9272 "n_items": 1874,9273 "n_groups": 1439274 },9275 "edit_sim": {9276 "mean": 0.7056286140156993,9277 "ci_low": 0.6918963621436698,9278 "ci_high": 0.7191625601170242,9279 "n_items": 1874,9280 "n_groups": 1439281 },9282 "rougeL": {9283 "mean": 0.7150168228424557,9284 "ci_low": 0.7008382409533878,9285 "ci_high": 0.7287440843272023,9286 "n_items": 1874,9287 "n_groups": 1439288 },9289 "exact_match": {9290 "mean": 0.0,9291 "ci_low": 0.0,9292 "ci_high": 0.0,9293 "n_items": 1874,9294 "n_groups": 1439295 },9296 "number_recall": {9297 "mean": 0.9887222146450639,9298 "ci_low": 0.9831366229216354,9299 "ci_high": 0.9930587950582487,9300 "n_items": 1874,9301 "n_groups": 1439302 },9303 "placeholders_exact": {9304 "mean": 0.9797225186766275,9305 "ci_low": 0.9654935790819629,9306 "ci_high": 0.9911398394847075,9307 "n_items": 1874,9308 "n_groups": 1439309 }9310 },9311 "mathematics": {9312 "n": 712,9313 "chrf": {9314 "mean": 68.52231327999132,9315 "ci_low": 65.60794786367201,9316 "ci_high": 71.74479417333333,9317 "n_items": 712,9318 "n_groups": 59319 },9320 "edit_sim": {9321 "mean": 0.6906864298578782,9322 "ci_low": 0.6648596762823681,9323 "ci_high": 0.7110495320500171,9324 "n_items": 712,9325 "n_groups": 59326 },9327 "rougeL": {9328 "mean": 0.6907962447438107,9329 "ci_low": 0.6647469579926454,9330 "ci_high": 0.7244665091347448,9331 "n_items": 712,9332 "n_groups": 59333 },9334 "exact_match": {9335 "mean": 0.0,9336 "ci_low": 0.0,9337 "ci_high": 0.0,9338 "n_items": 712,9339 "n_groups": 59340 },9341 "number_recall": {9342 "mean": 0.9968024134105594,9343 "ci_low": 0.9952972606715921,9344 "ci_high": 0.998558118899734,9345 "n_items": 712,9346 "n_groups": 59347 },9348 "placeholders_exact": {9349 "mean": 0.9957865168539326,9350 "ci_low": 0.9862385321100917,9351 "ci_high": 1.0,9352 "n_items": 712,9353 "n_groups": 59354 }9355 },9356 "other": {9357 "n": 669,9358 "chrf": {9359 "mean": 69.19704081567902,9360 "ci_low": 66.83449169586345,9361 "ci_high": 72.28614948897521,9362 "n_items": 669,9363 "n_groups": 139364 },9365 "edit_sim": {9366 "mean": 0.6734428652092447,9367 "ci_low": 0.6532183596320007,9368 "ci_high": 0.7008092220755995,9369 "n_items": 669,9370 "n_groups": 139371 },9372 "rougeL": {9373 "mean": 0.6828607277876542,9374 "ci_low": 0.661327070794445,9375 "ci_high": 0.7114836413587776,9376 "n_items": 669,9377 "n_groups": 139378 },9379 "exact_match": {9380 "mean": 0.0,9381 "ci_low": 0.0,9382 "ci_high": 0.0,9383 "n_items": 669,9384 "n_groups": 139385 },9386 "number_recall": {9387 "mean": 0.9915421026407574,9388 "ci_low": 0.9790679994342376,9389 "ci_high": 0.9980431571194308,9390 "n_items": 669,9391 "n_groups": 139392 },9393 "placeholders_exact": {9394 "mean": 0.9985052316890882,9395 "ci_low": 0.993403267136451,9396 "ci_high": 1.0,9397 "n_items": 669,9398 "n_groups": 139399 }9400 },9401 "social_sciences": {9402 "n": 1536,9403 "chrf": {9404 "mean": 68.7159426867709,9405 "ci_low": 66.59032889738243,9406 "ci_high": 70.250242952072,9407 "n_items": 1536,9408 "n_groups": 299409 },9410 "edit_sim": {9411 "mean": 0.6797594320781911,9412 "ci_low": 0.6614850801449768,9413 "ci_high": 0.6955863633504343,9414 "n_items": 1536,9415 "n_groups": 299416 },9417 "rougeL": {9418 "mean": 0.6856225307837143,9419 "ci_low": 0.6658293544450875,9420 "ci_high": 0.7024322240489287,9421 "n_items": 1536,9422 "n_groups": 299423 },9424 "exact_match": {9425 "mean": 0.0,9426 "ci_low": 0.0,9427 "ci_high": 0.0,9428 "n_items": 1536,9429 "n_groups": 299430 },9431 "number_recall": {9432 "mean": 0.9939309961871428,9433 "ci_low": 0.990648161429556,9434 "ci_high": 0.9971470474560234,9435 "n_items": 1536,9436 "n_groups": 299437 },9438 "placeholders_exact": {9439 "mean": 0.99609375,9440 "ci_low": 0.9926873379829945,9441 "ci_high": 0.9990883836199826,9442 "n_items": 1536,9443 "n_groups": 299444 }9445 },9446 "statistics": {9447 "n": 828,9448 "chrf": {9449 "mean": 70.5612344389928,9450 "ci_low": 67.9644560567226,9451 "ci_high": 73.29831602621444,9452 "n_items": 828,9453 "n_groups": 99454 },9455 "edit_sim": {9456 "mean": 0.69004727941719,9457 "ci_low": 0.6683270595241279,9458 "ci_high": 0.7139053879151956,9459 "n_items": 828,9460 "n_groups": 99461 },9462 "rougeL": {9463 "mean": 0.712793475903478,9464 "ci_low": 0.6888496399227332,9465 "ci_high": 0.7367136956378213,9466 "n_items": 828,9467 "n_groups": 99468 },9469 "exact_match": {9470 "mean": 0.0,9471 "ci_low": 0.0,9472 "ci_high": 0.0,9473 "n_items": 828,9474 "n_groups": 99475 },9476 "number_recall": {9477 "mean": 0.9878905944860606,9478 "ci_low": 0.9742886267129233,9479 "ci_high": 0.9965284555213857,9480 "n_items": 828,9481 "n_groups": 99482 },9483 "placeholders_exact": {9484 "mean": 0.9927536231884058,9485 "ci_low": 0.9853897404731358,9486 "ci_high": 0.9988572080143346,9487 "n_items": 828,9488 "n_groups": 99489 }9490 }9491 },9492 "by_era": {9493 "1900-1949": {9494 "n": 1164,9495 "chrf": {9496 "mean": 64.20290315297876,9497 "ci_low": 61.97180568008955,9498 "ci_high": 67.18121468962863,9499 "n_items": 1164,9500 "n_groups": 189501 },9502 "edit_sim": {9503 "mean": 0.6580132024523929,9504 "ci_low": 0.6347742582689709,9505 "ci_high": 0.694040441509984,9506 "n_items": 1164,9507 "n_groups": 189508 },9509 "rougeL": {9510 "mean": 0.6666171179093966,9511 "ci_low": 0.6419732250778949,9512 "ci_high": 0.7066480994202858,9513 "n_items": 1164,9514 "n_groups": 189515 },9516 "exact_match": {9517 "mean": 0.0,9518 "ci_low": 0.0,9519 "ci_high": 0.0,9520 "n_items": 1164,9521 "n_groups": 189522 },9523 "number_recall": {9524 "mean": 0.9988954344624448,9525 "ci_low": 0.99750956166892,9526 "ci_high": 1.0,9527 "n_items": 1164,9528 "n_groups": 189529 },9530 "placeholders_exact": {9531 "mean": 1.0,9532 "ci_low": 1.0,9533 "ci_high": 1.0,9534 "n_items": 1164,9535 "n_groups": 189536 }9537 },9538 "1950-1979": {9539 "n": 206,9540 "chrf": {9541 "mean": 62.83225117735559,9542 "ci_low": 60.233179656746,9543 "ci_high": 63.45853347147838,9544 "n_items": 206,9545 "n_groups": 29546 },9547 "edit_sim": {9548 "mean": 0.6493496506088774,9549 "ci_low": 0.6075907140012127,9550 "ci_high": 0.6594120449721701,9551 "n_items": 206,9552 "n_groups": 29553 },9554 "rougeL": {9555 "mean": 0.654468307053668,9556 "ci_low": 0.6114887742666676,9557 "ci_high": 0.6648248209782464,9558 "n_items": 206,9559 "n_groups": 29560 },9561 "exact_match": {9562 "mean": 0.0,9563 "ci_low": 0.0,9564 "ci_high": 0.0,9565 "n_items": 206,9566 "n_groups": 29567 },9568 "number_recall": {9569 "mean": 1.0,9570 "ci_low": 1.0,9571 "ci_high": 1.0,9572 "n_items": 206,9573 "n_groups": 29574 },9575 "placeholders_exact": {9576 "mean": 1.0,9577 "ci_low": 1.0,9578 "ci_high": 1.0,9579 "n_items": 206,9580 "n_groups": 29581 }9582 },9583 "1980-1999": {9584 "n": 151,9585 "chrf": {9586 "mean": 64.02891266252675,9587 "ci_low": 62.68627838557996,9588 "ci_high": 77.61958225305128,9589 "n_items": 151,9590 "n_groups": 49591 },9592 "edit_sim": {9593 "mean": 0.6668986360047516,9594 "ci_low": 0.6545946692997667,9595 "ci_high": 0.789912264505462,9596 "n_items": 151,9597 "n_groups": 49598 },9599 "rougeL": {9600 "mean": 0.6657759021471092,9601 "ci_low": 0.6547344618129507,9602 "ci_high": 0.7761826498004414,9603 "n_items": 151,9604 "n_groups": 49605 },9606 "exact_match": {9607 "mean": 0.0,9608 "ci_low": 0.0,9609 "ci_high": 0.0,9610 "n_items": 151,9611 "n_groups": 49612 },9613 "number_recall": {9614 "mean": 0.9990539262062441,9615 "ci_low": 0.9989547038327525,9616 "ci_high": 1.0,9617 "n_items": 151,9618 "n_groups": 49619 },9620 "placeholders_exact": {9621 "mean": 1.0,9622 "ci_low": 1.0,9623 "ci_high": 1.0,9624 "n_items": 151,9625 "n_groups": 49626 }9627 },9628 "2000-2009": {9629 "n": 1545,9630 "chrf": {9631 "mean": 70.05737097350793,9632 "ci_low": 68.72104018238575,9633 "ci_high": 71.43970900036706,9634 "n_items": 1545,9635 "n_groups": 699636 },9637 "edit_sim": {9638 "mean": 0.6951886234339126,9639 "ci_low": 0.6823994009772321,9640 "ci_high": 0.7080849472650186,9641 "n_items": 1545,9642 "n_groups": 699643 },9644 "rougeL": {9645 "mean": 0.7036427914826536,9646 "ci_low": 0.6917622188356104,9647 "ci_high": 0.7161724471615235,9648 "n_items": 1545,9649 "n_groups": 699650 },9651 "exact_match": {9652 "mean": 0.0,9653 "ci_low": 0.0,9654 "ci_high": 0.0,9655 "n_items": 1545,9656 "n_groups": 699657 },9658 "number_recall": {9659 "mean": 0.9881829156101001,9660 "ci_low": 0.979955800565558,9661 "ci_high": 0.9950325018823156,9662 "n_items": 1545,9663 "n_groups": 699664 },9665 "placeholders_exact": {9666 "mean": 0.9909385113268608,9667 "ci_low": 0.9829828113278684,9668 "ci_high": 0.9972213538612175,9669 "n_items": 1545,9670 "n_groups": 699671 }9672 },9673 "2010-2017": {9674 "n": 12583,9675 "chrf": {9676 "mean": 69.91271124278244,9677 "ci_low": 69.43339404752989,9678 "ci_high": 70.40874202513838,9679 "n_items": 12583,9680 "n_groups": 5599681 },9682 "edit_sim": {9683 "mean": 0.6863685914531372,9684 "ci_low": 0.6813266890558097,9685 "ci_high": 0.6910872954433971,9686 "n_items": 12583,9687 "n_groups": 5599688 },9689 "rougeL": {9690 "mean": 0.6950090063189747,9691 "ci_low": 0.6894624373809571,9692 "ci_high": 0.7002177838736213,9693 "n_items": 12583,9694 "n_groups": 5599695 },9696 "exact_match": {9697 "mean": 0.0,9698 "ci_low": 0.0,9699 "ci_high": 0.0,9700 "n_items": 12583,9701 "n_groups": 5599702 },9703 "number_recall": {9704 "mean": 0.9907451150340312,9705 "ci_low": 0.9890040232962334,9706 "ci_high": 0.9923015014447032,9707 "n_items": 12583,9708 "n_groups": 5599709 },9710 "placeholders_exact": {9711 "mean": 0.9913375188746721,9712 "ci_low": 0.9883635711711455,9713 "ci_high": 0.9939273804061691,9714 "n_items": 12583,9715 "n_groups": 5599716 }9717 }9718 },9719 "by_role": {9720 "abstract": {9721 "n": 1255,9722 "chrf": {9723 "mean": 70.26023399600975,9724 "ci_low": 69.46236500627451,9725 "ci_high": 71.15561284393542,9726 "n_items": 1255,9727 "n_groups": 1959728 },9729 "edit_sim": {9730 "mean": 0.683009927669533,9731 "ci_low": 0.673493450339037,9732 "ci_high": 0.6930292457022478,9733 "n_items": 1255,9734 "n_groups": 1959735 },9736 "rougeL": {9737 "mean": 0.6854921680510767,9738 "ci_low": 0.6763653889733372,9739 "ci_high": 0.6948188003904624,9740 "n_items": 1255,9741 "n_groups": 1959742 },9743 "exact_match": {9744 "mean": 0.0,9745 "ci_low": 0.0,9746 "ci_high": 0.0,9747 "n_items": 1255,9748 "n_groups": 1959749 },9750 "number_recall": {9751 "mean": 0.9942380052821049,9752 "ci_low": 0.9903109425376845,9753 "ci_high": 0.9970797967840113,9754 "n_items": 1255,9755 "n_groups": 1959756 },9757 "placeholders_exact": {9758 "mean": 0.9976095617529881,9759 "ci_low": 0.9924683035980458,9760 "ci_high": 1.0,9761 "n_items": 1255,9762 "n_groups": 1959763 }9764 },9765 "background": {9766 "n": 964,9767 "chrf": {9768 "mean": 69.90214687743544,9769 "ci_low": 68.82968668854367,9770 "ci_high": 71.00125212779254,9771 "n_items": 964,9772 "n_groups": 849773 },9774 "edit_sim": {9775 "mean": 0.6913809911817876,9776 "ci_low": 0.6792069710584209,9777 "ci_high": 0.7035443708874702,9778 "n_items": 964,9779 "n_groups": 849780 },9781 "rougeL": {9782 "mean": 0.6973123032541343,9783 "ci_low": 0.6825841368950917,9784 "ci_high": 0.7111973683202687,9785 "n_items": 964,9786 "n_groups": 849787 },9788 "exact_match": {9789 "mean": 0.0,9790 "ci_low": 0.0,9791 "ci_high": 0.0,9792 "n_items": 964,9793 "n_groups": 849794 },9795 "number_recall": {9796 "mean": 0.9920474379239939,9797 "ci_low": 0.9870224268544378,9798 "ci_high": 0.9967720010236981,9799 "n_items": 964,9800 "n_groups": 849801 },9802 "placeholders_exact": {9803 "mean": 0.991701244813278,9804 "ci_low": 0.9813238817574537,9805 "ci_high": 0.998962709294434,9806 "n_items": 964,9807 "n_groups": 849808 }9809 },9810 "chapter": {9811 "n": 1287,9812 "chrf": {9813 "mean": 64.28887058884402,9814 "ci_low": 63.00459782825768,9815 "ci_high": 65.96845443228605,9816 "n_items": 1287,9817 "n_groups": 219818 },9819 "edit_sim": {9820 "mean": 0.6563778708018237,9821 "ci_low": 0.6444747232650682,9822 "ci_high": 0.6766435467085197,9823 "n_items": 1287,9824 "n_groups": 219825 },9826 "rougeL": {9827 "mean": 0.6648728635236141,9828 "ci_low": 0.6528618910356448,9829 "ci_high": 0.6851510748239098,9830 "n_items": 1287,9831 "n_groups": 219832 },9833 "exact_match": {9834 "mean": 0.0,9835 "ci_low": 0.0,9836 "ci_high": 0.0,9837 "n_items": 1287,9838 "n_groups": 219839 },9840 "number_recall": {9841 "mean": 0.9978712645379311,9842 "ci_low": 0.995856820469601,9843 "ci_high": 0.9998391696261963,9844 "n_items": 1287,9845 "n_groups": 219846 },9847 "placeholders_exact": {9848 "mean": 1.0,9849 "ci_low": 1.0,9850 "ci_high": 1.0,9851 "n_items": 1287,9852 "n_groups": 219853 }9854 },9855 "conclusion": {9856 "n": 1168,9857 "chrf": {9858 "mean": 67.63679024559481,9859 "ci_low": 66.74250172108641,9860 "ci_high": 68.53974822552439,9861 "n_items": 1168,9862 "n_groups": 1549863 },9864 "edit_sim": {9865 "mean": 0.6673318913389197,9866 "ci_low": 0.6572098379326243,9867 "ci_high": 0.6776040869727549,9868 "n_items": 1168,9869 "n_groups": 1549870 },9871 "rougeL": {9872 "mean": 0.6660207526727153,9873 "ci_low": 0.6558287423155917,9874 "ci_high": 0.676159957956302,9875 "n_items": 1168,9876 "n_groups": 1549877 },9878 "exact_match": {9879 "mean": 0.0,9880 "ci_low": 0.0,9881 "ci_high": 0.0,9882 "n_items": 1168,9883 "n_groups": 1549884 },9885 "number_recall": {9886 "mean": 0.9934121053984067,9887 "ci_low": 0.9857513049343724,9888 "ci_high": 0.998465083625996,9889 "n_items": 1168,9890 "n_groups": 1549891 },9892 "placeholders_exact": {9893 "mean": 0.9948630136986302,9894 "ci_low": 0.9853874594242314,9895 "ci_high": 1.0,9896 "n_items": 1168,9897 "n_groups": 1549898 }9899 },9900 "data": {9901 "n": 912,9902 "chrf": {9903 "mean": 70.65460045629654,9904 "ci_low": 69.69482049163294,9905 "ci_high": 71.72984994002206,9906 "n_items": 912,9907 "n_groups": 1049908 },9909 "edit_sim": {9910 "mean": 0.6901292649097752,9911 "ci_low": 0.6786237539626575,9912 "ci_high": 0.7008720374814336,9913 "n_items": 912,9914 "n_groups": 1049915 },9916 "rougeL": {9917 "mean": 0.7091205130608214,9918 "ci_low": 0.6980879630007515,9919 "ci_high": 0.7202575367509211,9920 "n_items": 912,9921 "n_groups": 1049922 },9923 "exact_match": {9924 "mean": 0.0,9925 "ci_low": 0.0,9926 "ci_high": 0.0,9927 "n_items": 912,9928 "n_groups": 1049929 },9930 "number_recall": {9931 "mean": 0.9871824840592663,9932 "ci_low": 0.9805937656550199,9933 "ci_high": 0.9926370954173702,9934 "n_items": 912,9935 "n_groups": 1049936 },9937 "placeholders_exact": {9938 "mean": 0.9912280701754386,9939 "ci_low": 0.981167424620496,9940 "ci_high": 0.9987470234188964,9941 "n_items": 912,9942 "n_groups": 1049943 }9944 },9945 "discussion": {9946 "n": 1601,9947 "chrf": {9948 "mean": 69.39025980783907,9949 "ci_low": 68.50857520801668,9950 "ci_high": 70.2412941082151,9951 "n_items": 1601,9952 "n_groups": 1429953 },9954 "edit_sim": {9955 "mean": 0.6823781719904054,9956 "ci_low": 0.6733227290012113,9957 "ci_high": 0.6913648726403449,9958 "n_items": 1601,9959 "n_groups": 1429960 },9961 "rougeL": {9962 "mean": 0.6851531116457031,9963 "ci_low": 0.6749888999202305,9964 "ci_high": 0.6948699562668985,9965 "n_items": 1601,9966 "n_groups": 1429967 },9968 "exact_match": {9969 "mean": 0.0,9970 "ci_low": 0.0,9971 "ci_high": 0.0,9972 "n_items": 1601,9973 "n_groups": 1429974 },9975 "number_recall": {9976 "mean": 0.9913425261649716,9977 "ci_low": 0.9864570860664814,9978 "ci_high": 0.9954533734509108,9979 "n_items": 1601,9980 "n_groups": 1429981 },9982 "placeholders_exact": {9983 "mean": 0.9868831980012492,9984 "ci_low": 0.9753558795290312,9985 "ci_high": 0.9956533757077235,9986 "n_items": 1601,9987 "n_groups": 1429988 }9989 },9990 "introduction": {9991 "n": 1789,9992 "chrf": {9993 "mean": 69.32396932738621,9994 "ci_low": 68.4003365279058,9995 "ci_high": 70.2670619987792,9996 "n_items": 1789,9997 "n_groups": 1769998 },9999 "edit_sim": {10000 "mean": 0.6833196448273029,10001 "ci_low": 0.6735521769825988,10002 "ci_high": 0.6934270566053277,10003 "n_items": 1789,10004 "n_groups": 17610005 },10006 "rougeL": {10007 "mean": 0.6846278245271632,10008 "ci_low": 0.6750545126617237,10009 "ci_high": 0.6943503215361873,10010 "n_items": 1789,10011 "n_groups": 17610012 },10013 "exact_match": {10014 "mean": 0.0,10015 "ci_low": 0.0,10016 "ci_high": 0.0,10017 "n_items": 1789,10018 "n_groups": 17610019 },10020 "number_recall": {10021 "mean": 0.9944962861187009,10022 "ci_low": 0.9903601627503612,10023 "ci_high": 0.9977056422082171,10024 "n_items": 1789,10025 "n_groups": 17610026 },10027 "placeholders_exact": {10028 "mean": 0.9877026271660145,10029 "ci_low": 0.978448264404453,10030 "ci_high": 0.9945917189185545,10031 "n_items": 1789,10032 "n_groups": 17610033 }10034 },10035 "limitations": {10036 "n": 425,10037 "chrf": {10038 "mean": 68.20481171531313,10039 "ci_low": 66.54172688040208,10040 "ci_high": 69.89757884418609,10041 "n_items": 425,10042 "n_groups": 4110043 },10044 "edit_sim": {10045 "mean": 0.6689425261322314,10046 "ci_low": 0.6512445967166521,10047 "ci_high": 0.688187499431284,10048 "n_items": 425,10049 "n_groups": 4110050 },10051 "rougeL": {10052 "mean": 0.6727834583106119,10053 "ci_low": 0.6513652845424593,10054 "ci_high": 0.6958749414364648,10055 "n_items": 425,10056 "n_groups": 4110057 },10058 "exact_match": {10059 "mean": 0.0,10060 "ci_low": 0.0,10061 "ci_high": 0.0,10062 "n_items": 425,10063 "n_groups": 4110064 },10065 "number_recall": {10066 "mean": 0.997202614379085,10067 "ci_low": 0.9943522454646138,10068 "ci_high": 0.9995728905597328,10069 "n_items": 425,10070 "n_groups": 4110071 },10072 "placeholders_exact": {10073 "mean": 0.9929411764705882,10074 "ci_low": 0.976314227190668,10075 "ci_high": 1.0,10076 "n_items": 425,10077 "n_groups": 4110078 }10079 },10080 "methods": {10081 "n": 1528,10082 "chrf": {10083 "mean": 71.33418240022822,10084 "ci_low": 70.51927679055633,10085 "ci_high": 72.17650945730115,10086 "n_items": 1528,10087 "n_groups": 15110088 },10089 "edit_sim": {10090 "mean": 0.6986855054159254,10091 "ci_low": 0.6897940895660079,10092 "ci_high": 0.707794569635013,10093 "n_items": 1528,10094 "n_groups": 15110095 },10096 "rougeL": {10097 "mean": 0.7172746208149948,10098 "ci_low": 0.7079921325334096,10099 "ci_high": 0.7269277724554719,10100 "n_items": 1528,10101 "n_groups": 15110102 },10103 "exact_match": {10104 "mean": 0.0,10105 "ci_low": 0.0,10106 "ci_high": 0.0,10107 "n_items": 1528,10108 "n_groups": 15110109 },10110 "number_recall": {10111 "mean": 0.9892991635153381,10112 "ci_low": 0.9848798195120687,10113 "ci_high": 0.9929584958466456,10114 "n_items": 1528,10115 "n_groups": 15110116 },10117 "placeholders_exact": {10118 "mean": 0.9895287958115183,10119 "ci_low": 0.9803664921465969,10120 "ci_high": 0.9966220757047369,10121 "n_items": 1528,10122 "n_groups": 15110123 }10124 },10125 "other": {10126 "n": 1387,10127 "chrf": {10128 "mean": 70.1340673934275,10129 "ci_low": 69.05597303993751,10130 "ci_high": 71.22983058445027,10131 "n_items": 1387,10132 "n_groups": 11910133 },10134 "edit_sim": {10135 "mean": 0.692053021320386,10136 "ci_low": 0.6816984833611437,10137 "ci_high": 0.7029888795352528,10138 "n_items": 1387,10139 "n_groups": 11910140 },10141 "rougeL": {10142 "mean": 0.6995019638447699,10143 "ci_low": 0.6883455226923066,10144 "ci_high": 0.709979096681401,10145 "n_items": 1387,10146 "n_groups": 11910147 },10148 "exact_match": {10149 "mean": 0.0,10150 "ci_low": 0.0,10151 "ci_high": 0.0,10152 "n_items": 1387,10153 "n_groups": 11910154 },10155 "number_recall": {10156 "mean": 0.9918600205370212,10157 "ci_low": 0.9865456448022998,10158 "ci_high": 0.9962797355162831,10159 "n_items": 1387,10160 "n_groups": 11910161 },10162 "placeholders_exact": {10163 "mean": 0.989185291997116,10164 "ci_low": 0.9815885041503738,10165 "ci_high": 0.9955403561094828,10166 "n_items": 1387,10167 "n_groups": 11910168 }10169 },10170 "preface": {10171 "n": 362,10172 "chrf": {10173 "mean": 63.60115111846642,10174 "ci_low": 59.073011192734604,10175 "ci_high": 68.25316201040098,10176 "n_items": 362,10177 "n_groups": 1310178 },10179 "edit_sim": {10180 "mean": 0.6544110149193293,10181 "ci_low": 0.6076843880488485,10182 "ci_high": 0.7039289731876429,10183 "n_items": 362,10184 "n_groups": 1310185 },10186 "rougeL": {10187 "mean": 0.6607693642657672,10188 "ci_low": 0.608294193310184,10189 "ci_high": 0.7191780809465798,10190 "n_items": 362,10191 "n_groups": 1310192 },10193 "exact_match": {10194 "mean": 0.0,10195 "ci_low": 0.0,10196 "ci_high": 0.0,10197 "n_items": 362,10198 "n_groups": 1310199 },10200 "number_recall": {10201 "mean": 1.0,10202 "ci_low": 1.0,10203 "ci_high": 1.0,10204 "n_items": 362,10205 "n_groups": 1310206 },10207 "placeholders_exact": {10208 "mean": 1.0,10209 "ci_low": 1.0,10210 "ci_high": 1.0,10211 "n_items": 362,10212 "n_groups": 1310213 }10214 },10215 "related_work": {10216 "n": 557,10217 "chrf": {10218 "mean": 71.17705531511247,10219 "ci_low": 69.66266933415689,10220 "ci_high": 72.73678643456118,10221 "n_items": 557,10222 "n_groups": 3910223 },10224 "edit_sim": {10225 "mean": 0.6949754430862558,10226 "ci_low": 0.6785232556427546,10227 "ci_high": 0.7136621316565449,10228 "n_items": 557,10229 "n_groups": 3910230 },10231 "rougeL": {10232 "mean": 0.7018964943192777,10233 "ci_low": 0.6846470637294134,10234 "ci_high": 0.7208217029628108,10235 "n_items": 557,10236 "n_groups": 3910237 },10238 "exact_match": {10239 "mean": 0.0,10240 "ci_low": 0.0,10241 "ci_high": 0.0,10242 "n_items": 557,10243 "n_groups": 3910244 },10245 "number_recall": {10246 "mean": 0.9917012520692952,10247 "ci_low": 0.9847789802572174,10248 "ci_high": 0.9968085855781095,10249 "n_items": 557,10250 "n_groups": 3910251 },10252 "placeholders_exact": {10253 "mean": 0.9892280071813285,10254 "ci_low": 0.975609756097561,10255 "ci_high": 1.0,10256 "n_items": 557,10257 "n_groups": 3910258 }10259 },10260 "results": {10261 "n": 1501,10262 "chrf": {10263 "mean": 70.5208064468443,10264 "ci_low": 69.33060644170877,10265 "ci_high": 71.79492903484292,10266 "n_items": 1501,10267 "n_groups": 15310268 },10269 "edit_sim": {10270 "mean": 0.693328002496201,10271 "ci_low": 0.6825087257437094,10272 "ci_high": 0.704489905511151,10273 "n_items": 1501,10274 "n_groups": 15310275 },10276 "rougeL": {10277 "mean": 0.7146362611594155,10278 "ci_low": 0.7031013844756853,10279 "ci_high": 0.7271086020137543,10280 "n_items": 1501,10281 "n_groups": 15310282 },10283 "exact_match": {10284 "mean": 0.0,10285 "ci_low": 0.0,10286 "ci_high": 0.0,10287 "n_items": 1501,10288 "n_groups": 15310289 },10290 "number_recall": {10291 "mean": 0.9763711779117589,10292 "ci_low": 0.9693779608665986,10293 "ci_high": 0.98323500301982,10294 "n_items": 1501,10295 "n_groups": 15310296 },10297 "placeholders_exact": {10298 "mean": 0.9933377748167888,10299 "ci_low": 0.9869536855838226,10300 "ci_high": 0.9985011113596877,10301 "n_items": 1501,10302 "n_groups": 15310303 }10304 },10305 "theory": {10306 "n": 913,10307 "chrf": {10308 "mean": 70.81980831168136,10309 "ci_low": 69.60833594064972,10310 "ci_high": 72.00497115666394,10311 "n_items": 913,10312 "n_groups": 7910313 },10314 "edit_sim": {10315 "mean": 0.7035811617705308,10316 "ci_low": 0.6891572760806816,10317 "ci_high": 0.7171749425137843,10318 "n_items": 913,10319 "n_groups": 7910320 },10321 "rougeL": {10322 "mean": 0.7165466968047914,10323 "ci_low": 0.701676185941675,10324 "ci_high": 0.7311559326576869,10325 "n_items": 913,10326 "n_groups": 7910327 },10328 "exact_match": {10329 "mean": 0.0,10330 "ci_low": 0.0,10331 "ci_high": 0.0,10332 "n_items": 913,10333 "n_groups": 7910334 },10335 "number_recall": {10336 "mean": 0.9928885538825298,10337 "ci_low": 0.9885969000170945,10338 "ci_high": 0.9964068538990624,10339 "n_items": 913,10340 "n_groups": 7910341 },10342 "placeholders_exact": {10343 "mean": 0.9945235487404163,10344 "ci_low": 0.9888475836431226,10345 "ci_high": 0.998935206315398,10346 "n_items": 913,10347 "n_groups": 7910348 }10349 }10350 }10351 },10352 "htr-m1-tiny": {10353 "overall": {10354 "n": 15649,10355 "chrf": {10356 "mean": 69.31459725023585,10357 "ci_low": 68.77193901804117,10358 "ci_high": 69.84751341400792,10359 "n_items": 15649,10360 "n_groups": 65210361 },10362 "edit_sim": {10363 "mean": 0.6839679087518882,10364 "ci_low": 0.6791272088065745,10365 "ci_high": 0.6889361218827476,10366 "n_items": 15649,10367 "n_groups": 65210368 },10369 "rougeL": {10370 "mean": 0.6925558206147612,10371 "ci_low": 0.6872373147280966,10372 "ci_high": 0.6978800725907695,10373 "n_items": 15649,10374 "n_groups": 65210375 },10376 "exact_match": {10377 "mean": 0.0,10378 "ci_low": 0.0,10379 "ci_high": 0.0,10380 "n_items": 15649,10381 "n_groups": 65210382 },10383 "number_recall": {10384 "mean": 0.990571778811134,10385 "ci_low": 0.9887716922817096,10386 "ci_high": 0.9921640091708509,10387 "n_items": 15649,10388 "n_groups": 65210389 },10390 "placeholders_exact": {10391 "mean": 0.9922039746948687,10392 "ci_low": 0.9896790966562596,10393 "ci_high": 0.9944908940941147,10394 "n_items": 15649,10395 "n_groups": 65210396 }10397 },10398 "by_variant": {10399 "A": {10400 "n": 2664,10401 "chrf": {10402 "mean": 68.85156855121525,10403 "ci_low": 68.2292332394279,10404 "ci_high": 69.4678889279604,10405 "n_items": 2664,10406 "n_groups": 63010407 },10408 "edit_sim": {10409 "mean": 0.6764029928902577,10410 "ci_low": 0.670705548689613,10411 "ci_high": 0.6826447820967315,10412 "n_items": 2664,10413 "n_groups": 63010414 },10415 "rougeL": {10416 "mean": 0.6821129773968475,10417 "ci_low": 0.676223208378586,10418 "ci_high": 0.688415937270361,10419 "n_items": 2664,10420 "n_groups": 63010421 },10422 "exact_match": {10423 "mean": 0.0,10424 "ci_low": 0.0,10425 "ci_high": 0.0,10426 "n_items": 2664,10427 "n_groups": 63010428 },10429 "number_recall": {10430 "mean": 0.9905100276913384,10431 "ci_low": 0.9882397958483243,10432 "ci_high": 0.9926431611994011,10433 "n_items": 2664,10434 "n_groups": 63010435 },10436 "placeholders_exact": {10437 "mean": 0.9917417417417418,10438 "ci_low": 0.9882439938432711,10439 "ci_high": 0.9949986945813476,10440 "n_items": 2664,10441 "n_groups": 63010442 }10443 },10444 "B": {10445 "n": 2539,10446 "chrf": {10447 "mean": 74.83639804352013,10448 "ci_low": 74.24074542768459,10449 "ci_high": 75.42034915910158,10450 "n_items": 2539,10451 "n_groups": 61410452 },10453 "edit_sim": {10454 "mean": 0.7500706516849709,10455 "ci_low": 0.744447925123815,10456 "ci_high": 0.755922036860647,10457 "n_items": 2539,10458 "n_groups": 61410459 },10460 "rougeL": {10461 "mean": 0.7570409538006246,10462 "ci_low": 0.7509650109749166,10463 "ci_high": 0.7630101001152341,10464 "n_items": 2539,10465 "n_groups": 61410466 },10467 "exact_match": {10468 "mean": 0.0,10469 "ci_low": 0.0,10470 "ci_high": 0.0,10471 "n_items": 2539,10472 "n_groups": 61410473 },10474 "number_recall": {10475 "mean": 0.9921579557773091,10476 "ci_low": 0.9899222250220273,10477 "ci_high": 0.9941762874874142,10478 "n_items": 2539,10479 "n_groups": 61410480 },10481 "placeholders_exact": {10482 "mean": 0.9929105947223317,10483 "ci_low": 0.9895104189595715,10484 "ci_high": 0.9959275096177777,10485 "n_items": 2539,10486 "n_groups": 61410487 }10488 },10489 "C": {10490 "n": 2663,10491 "chrf": {10492 "mean": 71.67564758757042,10493 "ci_low": 71.14797040743473,10494 "ci_high": 72.24799134503037,10495 "n_items": 2663,10496 "n_groups": 63810497 },10498 "edit_sim": {10499 "mean": 0.7250126922688801,10500 "ci_low": 0.7198610395755554,10501 "ci_high": 0.7306092237436189,10502 "n_items": 2663,10503 "n_groups": 63810504 },10505 "rougeL": {10506 "mean": 0.744681491017062,10507 "ci_low": 0.7391233243395757,10508 "ci_high": 0.7507597206598438,10509 "n_items": 2663,10510 "n_groups": 63810511 },10512 "exact_match": {10513 "mean": 0.0,10514 "ci_low": 0.0,10515 "ci_high": 0.0,10516 "n_items": 2663,10517 "n_groups": 63810518 },10519 "number_recall": {10520 "mean": 0.990259426997322,10521 "ci_low": 0.9877755179625426,10522 "ci_high": 0.9925720505981717,10523 "n_items": 2663,10524 "n_groups": 63810525 },10526 "placeholders_exact": {10527 "mean": 0.992114156965828,10528 "ci_low": 0.988427575835179,10529 "ci_high": 0.9955007729198521,10530 "n_items": 2663,10531 "n_groups": 63810532 }10533 },10534 "D": {10535 "n": 2708,10536 "chrf": {10537 "mean": 69.9557030922966,10538 "ci_low": 69.35532148985654,10539 "ci_high": 70.55067481306354,10540 "n_items": 2708,10541 "n_groups": 63810542 },10543 "edit_sim": {10544 "mean": 0.6951210300332599,10545 "ci_low": 0.6898131846862136,10546 "ci_high": 0.7004489122401887,10547 "n_items": 2708,10548 "n_groups": 63810549 },10550 "rougeL": {10551 "mean": 0.6998782518965727,10552 "ci_low": 0.6945418892037525,10553 "ci_high": 0.7053166830248928,10554 "n_items": 2708,10555 "n_groups": 63810556 },10557 "exact_match": {10558 "mean": 0.0,10559 "ci_low": 0.0,10560 "ci_high": 0.0,10561 "n_items": 2708,10562 "n_groups": 63810563 },10564 "number_recall": {10565 "mean": 0.9903128216731166,10566 "ci_low": 0.9882436838058299,10567 "ci_high": 0.9921194172135176,10568 "n_items": 2708,10569 "n_groups": 63810570 },10571 "placeholders_exact": {10572 "mean": 0.9929837518463811,10573 "ci_low": 0.9897134081996112,10574 "ci_high": 0.9959504456025075,10575 "n_items": 2708,10576 "n_groups": 63810577 }10578 },10579 "E": {10580 "n": 5075,10581 "chrf": {10582 "mean": 65.2141173628309,10583 "ci_low": 64.60558400045488,10584 "ci_high": 65.80916547145263,10585 "n_items": 5075,10586 "n_groups": 62310587 },10588 "edit_sim": {10589 "mean": 0.6273793689711162,10590 "ci_low": 0.6219879583744441,10591 "ci_high": 0.6328602817476062,10592 "n_items": 5075,10593 "n_groups": 62310594 },10595 "rougeL": {10596 "mean": 0.6345168407095674,10597 "ci_low": 0.6285011608213377,10598 "ci_high": 0.6405832042366156,10599 "n_items": 5075,10600 "n_groups": 62310601 },10602 "exact_match": {10603 "mean": 0.0,10604 "ci_low": 0.0,10605 "ci_high": 0.0,10606 "n_items": 5075,10607 "n_groups": 62310608 },10609 "number_recall": {10610 "mean": 0.9901127148655083,10611 "ci_low": 0.9880517095302361,10612 "ci_high": 0.9920992539780275,10613 "n_items": 5075,10614 "n_groups": 62310615 },10616 "placeholders_exact": {10617 "mean": 0.9917241379310345,10618 "ci_low": 0.9885549069254563,10619 "ci_high": 0.9946249455275703,10620 "n_items": 5075,10621 "n_groups": 62310622 }10623 }10624 },10625 "by_discipline": {10626 "biomedicine": {10627 "n": 2154,10628 "chrf": {10629 "mean": 69.58893584205656,10630 "ci_low": 68.45945675366771,10631 "ci_high": 70.66089438740237,10632 "n_items": 2154,10633 "n_groups": 24410634 },10635 "edit_sim": {10636 "mean": 0.6816963555542307,10637 "ci_low": 0.6730733343212221,10638 "ci_high": 0.69069874690228,10639 "n_items": 2154,10640 "n_groups": 24410641 },10642 "rougeL": {10643 "mean": 0.6906600545207263,10644 "ci_low": 0.6812596824475737,10645 "ci_high": 0.7002663103497081,10646 "n_items": 2154,10647 "n_groups": 24410648 },10649 "exact_match": {10650 "mean": 0.0,10651 "ci_low": 0.0,10652 "ci_high": 0.0,10653 "n_items": 2154,10654 "n_groups": 24410655 },10656 "number_recall": {10657 "mean": 0.9896241912668259,10658 "ci_low": 0.9850533457356135,10659 "ci_high": 0.9934600571941317,10660 "n_items": 2154,10661 "n_groups": 24410662 },10663 "placeholders_exact": {10664 "mean": 0.9939647168059424,10665 "ci_low": 0.9887893656539197,10666 "ci_high": 0.99828949879231,10667 "n_items": 2154,10668 "n_groups": 24410669 }10670 },10671 "chemistry": {10672 "n": 837,10673 "chrf": {10674 "mean": 72.419517227588,10675 "ci_low": 70.8354263282526,10676 "ci_high": 73.90964160316321,10677 "n_items": 837,10678 "n_groups": 1310679 },10680 "edit_sim": {10681 "mean": 0.6969190660456015,10682 "ci_low": 0.6795524529651039,10683 "ci_high": 0.7156266160331785,10684 "n_items": 837,10685 "n_groups": 1310686 },10687 "rougeL": {10688 "mean": 0.71294366367398,10689 "ci_low": 0.6964076886068936,10690 "ci_high": 0.730070335643586,10691 "n_items": 837,10692 "n_groups": 1310693 },10694 "exact_match": {10695 "mean": 0.0,10696 "ci_low": 0.0,10697 "ci_high": 0.0,10698 "n_items": 837,10699 "n_groups": 1310700 },10701 "number_recall": {10702 "mean": 0.9824369263232778,10703 "ci_low": 0.9757238772261807,10704 "ci_high": 0.9894028278256936,10705 "n_items": 837,10706 "n_groups": 1310707 },10708 "placeholders_exact": {10709 "mean": 0.991636798088411,10710 "ci_low": 0.9811568348612205,10711 "ci_high": 0.9988082110531993,10712 "n_items": 837,10713 "n_groups": 1310714 }10715 },10716 "computer_science": {10717 "n": 1375,10718 "chrf": {10719 "mean": 69.40390636401753,10720 "ci_low": 67.89352738113715,10721 "ci_high": 70.78885839567639,10722 "n_items": 1375,10723 "n_groups": 2010724 },10725 "edit_sim": {10726 "mean": 0.6899142852989097,10727 "ci_low": 0.6739117856188976,10728 "ci_high": 0.7038201417161667,10729 "n_items": 1375,10730 "n_groups": 2010731 },10732 "rougeL": {10733 "mean": 0.6954471818796345,10734 "ci_low": 0.6787956196371364,10735 "ci_high": 0.7095758982089613,10736 "n_items": 1375,10737 "n_groups": 2010738 },10739 "exact_match": {10740 "mean": 0.0,10741 "ci_low": 0.0,10742 "ci_high": 0.0,10743 "n_items": 1375,10744 "n_groups": 2010745 },10746 "number_recall": {10747 "mean": 0.992723853923854,10748 "ci_low": 0.9888171545244818,10749 "ci_high": 0.9960428830735645,10750 "n_items": 1375,10751 "n_groups": 2010752 },10753 "placeholders_exact": {10754 "mean": 0.9978181818181818,10755 "ci_low": 0.9951690821256038,10756 "ci_high": 1.0,10757 "n_items": 1375,10758 "n_groups": 2010759 }10760 },10761 "economics": {10762 "n": 1944,10763 "chrf": {10764 "mean": 68.66887152439533,10765 "ci_low": 67.89314713033323,10766 "ci_high": 69.4240485472441,10767 "n_items": 1944,10768 "n_groups": 10310769 },10770 "edit_sim": {10771 "mean": 0.68104698547609,10772 "ci_low": 0.6722875835460163,10773 "ci_high": 0.6899804853116213,10774 "n_items": 1944,10775 "n_groups": 10310776 },10777 "rougeL": {10778 "mean": 0.6854579862959256,10779 "ci_low": 0.6753662796904055,10780 "ci_high": 0.695220073574813,10781 "n_items": 1944,10782 "n_groups": 10310783 },10784 "exact_match": {10785 "mean": 0.0,10786 "ci_low": 0.0,10787 "ci_high": 0.0,10788 "n_items": 1944,10789 "n_groups": 10310790 },10791 "number_recall": {10792 "mean": 0.989970975526531,10793 "ci_low": 0.9864782559726193,10794 "ci_high": 0.9931640869494652,10795 "n_items": 1944,10796 "n_groups": 10310797 },10798 "placeholders_exact": {10799 "mean": 0.9943415637860082,10800 "ci_low": 0.9868992053833489,10801 "ci_high": 0.9994869360811345,10802 "n_items": 1944,10803 "n_groups": 10310804 }10805 },10806 "engineering": {10807 "n": 1296,10808 "chrf": {10809 "mean": 67.10816643004323,10810 "ci_low": 65.44189143961434,10811 "ci_high": 68.76869386905425,10812 "n_items": 1296,10813 "n_groups": 1710814 },10815 "edit_sim": {10816 "mean": 0.6602343495621162,10817 "ci_low": 0.6458384486051025,10818 "ci_high": 0.674719882406674,10819 "n_items": 1296,10820 "n_groups": 1710821 },10822 "rougeL": {10823 "mean": 0.670071334568091,10824 "ci_low": 0.656016900335678,10825 "ci_high": 0.6849834954236118,10826 "n_items": 1296,10827 "n_groups": 1710828 },10829 "exact_match": {10830 "mean": 0.0,10831 "ci_low": 0.0,10832 "ci_high": 0.0,10833 "n_items": 1296,10834 "n_groups": 1710835 },10836 "number_recall": {10837 "mean": 0.9920216565075239,10838 "ci_low": 0.9882265922596475,10839 "ci_high": 0.9955806363701631,10840 "n_items": 1296,10841 "n_groups": 1710842 },10843 "placeholders_exact": {10844 "mean": 0.9915123456790124,10845 "ci_low": 0.9840491780998547,10846 "ci_high": 0.9979955411848975,10847 "n_items": 1296,10848 "n_groups": 1710849 }10850 },10851 "finance": {10852 "n": 2043,10853 "chrf": {10854 "mean": 68.24747758438942,10855 "ci_low": 66.96021516165278,10856 "ci_high": 69.67846228708206,10857 "n_items": 2043,10858 "n_groups": 5110859 },10860 "edit_sim": {10861 "mean": 0.6756758001045535,10862 "ci_low": 0.6630299589274299,10863 "ci_high": 0.6899252116318577,10864 "n_items": 2043,10865 "n_groups": 5110866 },10867 "rougeL": {10868 "mean": 0.6828410229685472,10869 "ci_low": 0.6694872510059435,10870 "ci_high": 0.6982288965207447,10871 "n_items": 2043,10872 "n_groups": 5110873 },10874 "exact_match": {10875 "mean": 0.0,10876 "ci_low": 0.0,10877 "ci_high": 0.0,10878 "n_items": 2043,10879 "n_groups": 5110880 },10881 "number_recall": {10882 "mean": 0.9927825030247936,10883 "ci_low": 0.9877098673019347,10884 "ci_high": 0.9964157595033313,10885 "n_items": 2043,10886 "n_groups": 5110887 },10888 "placeholders_exact": {10889 "mean": 0.9946157611355849,10890 "ci_low": 0.9893412404263896,10891 "ci_high": 0.998718220338983,10892 "n_items": 2043,10893 "n_groups": 5110894 }10895 },10896 "general_reference": {10897 "n": 118,10898 "chrf": {10899 "mean": 74.54310506873402,10900 "ci_low": 60.75177000312197,10901 "ci_high": 75.96090586987171,10902 "n_items": 118,10903 "n_groups": 210904 },10905 "edit_sim": {10906 "mean": 0.7782433434218748,10907 "ci_low": 0.6021276271938825,10908 "ci_high": 0.7963486974266216,10909 "n_items": 118,10910 "n_groups": 210911 },10912 "rougeL": {10913 "mean": 0.8062281875039967,10914 "ci_low": 0.6183116823587061,10915 "ci_high": 0.8255467067245403,10916 "n_items": 118,10917 "n_groups": 210918 },10919 "exact_match": {10920 "mean": 0.0,10921 "ci_low": 0.0,10922 "ci_high": 0.0,10923 "n_items": 118,10924 "n_groups": 210925 },10926 "number_recall": {10927 "mean": 0.9994703389830508,10928 "ci_low": 0.9994158878504673,10929 "ci_high": 1.0,10930 "n_items": 118,10931 "n_groups": 210932 },10933 "placeholders_exact": {10934 "mean": 1.0,10935 "ci_low": 1.0,10936 "ci_high": 1.0,10937 "n_items": 118,10938 "n_groups": 210939 }10940 },10941 "humanities": {10942 "n": 263,10943 "chrf": {10944 "mean": 63.37846803053981,10945 "ci_low": 59.66339132848722,10946 "ci_high": 63.977477150998766,10947 "n_items": 263,10948 "n_groups": 310949 },10950 "edit_sim": {10951 "mean": 0.6536895291063545,10952 "ci_low": 0.6165568873485019,10953 "ci_high": 0.6564561584369045,10954 "n_items": 263,10955 "n_groups": 310956 },10957 "rougeL": {10958 "mean": 0.6614180911151935,10959 "ci_low": 0.6213132650409963,10960 "ci_high": 0.6668424622296281,10961 "n_items": 263,10962 "n_groups": 310963 },10964 "exact_match": {10965 "mean": 0.0,10966 "ci_low": 0.0,10967 "ci_high": 0.0,10968 "n_items": 263,10969 "n_groups": 310970 },10971 "number_recall": {10972 "mean": 1.0,10973 "ci_low": 1.0,10974 "ci_high": 1.0,10975 "n_items": 263,10976 "n_groups": 310977 },10978 "placeholders_exact": {10979 "mean": 1.0,10980 "ci_low": 1.0,10981 "ci_high": 1.0,10982 "n_items": 263,10983 "n_groups": 310984 }10985 },10986 "life_sciences": {10987 "n": 1874,10988 "chrf": {10989 "mean": 71.76701644283386,10990 "ci_low": 69.94741714547183,10991 "ci_high": 73.31283061173967,10992 "n_items": 1874,10993 "n_groups": 14310994 },10995 "edit_sim": {10996 "mean": 0.7044856807920036,10997 "ci_low": 0.6910903762048681,10998 "ci_high": 0.7180715250954856,10999 "n_items": 1874,11000 "n_groups": 14311001 },11002 "rougeL": {11003 "mean": 0.714766514676355,11004 "ci_low": 0.7008431838835606,11005 "ci_high": 0.728524244015662,11006 "n_items": 1874,11007 "n_groups": 14311008 },11009 "exact_match": {11010 "mean": 0.0,11011 "ci_low": 0.0,11012 "ci_high": 0.0,11013 "n_items": 1874,11014 "n_groups": 14311015 },11016 "number_recall": {11017 "mean": 0.9855796408684347,11018 "ci_low": 0.978639906673301,11019 "ci_high": 0.991236904366682,11020 "n_items": 1874,11021 "n_groups": 14311022 },11023 "placeholders_exact": {11024 "mean": 0.9813233724653149,11025 "ci_low": 0.9668734789823009,11026 "ci_high": 0.9923085208233605,11027 "n_items": 1874,11028 "n_groups": 14311029 }11030 },11031 "mathematics": {11032 "n": 712,11033 "chrf": {11034 "mean": 68.52220049621808,11035 "ci_low": 65.40860295336915,11036 "ci_high": 71.71444240765403,11037 "n_items": 712,11038 "n_groups": 511039 },11040 "edit_sim": {11041 "mean": 0.6914495002167412,11042 "ci_low": 0.6643432586280673,11043 "ci_high": 0.7113543879316822,11044 "n_items": 712,11045 "n_groups": 511046 },11047 "rougeL": {11048 "mean": 0.6911081863139087,11049 "ci_low": 0.664090852264922,11050 "ci_high": 0.7234907555429982,11051 "n_items": 712,11052 "n_groups": 511053 },11054 "exact_match": {11055 "mean": 0.0,11056 "ci_low": 0.0,11057 "ci_high": 0.0,11058 "n_items": 712,11059 "n_groups": 511060 },11061 "number_recall": {11062 "mean": 0.9959820142404412,11063 "ci_low": 0.9925132119788609,11064 "ci_high": 0.998902552473981,11065 "n_items": 712,11066 "n_groups": 511067 },11068 "placeholders_exact": {11069 "mean": 0.9831460674157303,11070 "ci_low": 0.9507575757575758,11071 "ci_high": 1.0,11072 "n_items": 712,11073 "n_groups": 511074 }11075 },11076 "other": {11077 "n": 669,11078 "chrf": {11079 "mean": 69.07028084379631,11080 "ci_low": 66.66522554640022,11081 "ci_high": 72.2558325386044,11082 "n_items": 669,11083 "n_groups": 1311084 },11085 "edit_sim": {11086 "mean": 0.6732156283616988,11087 "ci_low": 0.6529701117648554,11088 "ci_high": 0.7001335693358365,11089 "n_items": 669,11090 "n_groups": 1311091 },11092 "rougeL": {11093 "mean": 0.6819303234443674,11094 "ci_low": 0.6600007001058256,11095 "ci_high": 0.7110749576462658,11096 "n_items": 669,11097 "n_groups": 1311098 },11099 "exact_match": {11100 "mean": 0.0,11101 "ci_low": 0.0,11102 "ci_high": 0.0,11103 "n_items": 669,11104 "n_groups": 1311105 },11106 "number_recall": {11107 "mean": 0.9915676086079673,11108 "ci_low": 0.9793653714979991,11109 "ci_high": 0.9978823657879741,11110 "n_items": 669,11111 "n_groups": 1311112 },11113 "placeholders_exact": {11114 "mean": 0.9955156950672646,11115 "ci_low": 0.9872053156911001,11116 "ci_high": 1.0,11117 "n_items": 669,11118 "n_groups": 1311119 }11120 },11121 "social_sciences": {11122 "n": 1536,11123 "chrf": {11124 "mean": 68.61396475230724,11125 "ci_low": 66.55993236565489,11126 "ci_high": 70.07052640836083,11127 "n_items": 1536,11128 "n_groups": 2911129 },11130 "edit_sim": {11131 "mean": 0.679192272080821,11132 "ci_low": 0.6619374597812304,11133 "ci_high": 0.6943099471371392,11134 "n_items": 1536,11135 "n_groups": 2911136 },11137 "rougeL": {11138 "mean": 0.6860080426605625,11139 "ci_low": 0.6671967324519944,11140 "ci_high": 0.7021453229482475,11141 "n_items": 1536,11142 "n_groups": 2911143 },11144 "exact_match": {11145 "mean": 0.0,11146 "ci_low": 0.0,11147 "ci_high": 0.0,11148 "n_items": 1536,11149 "n_groups": 2911150 },11151 "number_recall": {11152 "mean": 0.9935708426121379,11153 "ci_low": 0.9898347765729836,11154 "ci_high": 0.9972263344481287,11155 "n_items": 1536,11156 "n_groups": 2911157 },11158 "placeholders_exact": {11159 "mean": 0.9947916666666666,11160 "ci_low": 0.9907900028887244,11161 "ci_high": 0.9983337798845836,11162 "n_items": 1536,11163 "n_groups": 2911164 }11165 },11166 "statistics": {11167 "n": 828,11168 "chrf": {11169 "mean": 70.6849081547147,11170 "ci_low": 67.99392925674236,11171 "ci_high": 73.43159388118323,11172 "n_items": 828,11173 "n_groups": 911174 },11175 "edit_sim": {11176 "mean": 0.6922341561464824,11177 "ci_low": 0.6703084125897407,11178 "ci_high": 0.7159921582713945,11179 "n_items": 828,11180 "n_groups": 911181 },11182 "rougeL": {11183 "mean": 0.7133025021016914,11184 "ci_low": 0.6887834736258696,11185 "ci_high": 0.7370796547565557,11186 "n_items": 828,11187 "n_groups": 911188 },11189 "exact_match": {11190 "mean": 0.0,11191 "ci_low": 0.0,11192 "ci_high": 0.0,11193 "n_items": 828,11194 "n_groups": 911195 },11196 "number_recall": {11197 "mean": 0.9873882483988086,11198 "ci_low": 0.971158256103583,11199 "ci_high": 0.9971639778925208,11200 "n_items": 828,11201 "n_groups": 911202 },11203 "placeholders_exact": {11204 "mean": 0.9903381642512077,11205 "ci_low": 0.9833333333333333,11206 "ci_high": 0.9975934775645188,11207 "n_items": 828,11208 "n_groups": 911209 }11210 }11211 },11212 "by_era": {11213 "1900-1949": {11214 "n": 1164,11215 "chrf": {11216 "mean": 64.24571583368854,11217 "ci_low": 62.034286083698575,11218 "ci_high": 67.20640200208898,11219 "n_items": 1164,11220 "n_groups": 1811221 },11222 "edit_sim": {11223 "mean": 0.658989896407144,11224 "ci_low": 0.6355251094455027,11225 "ci_high": 0.6953492609824711,11226 "n_items": 1164,11227 "n_groups": 1811228 },11229 "rougeL": {11230 "mean": 0.6678520178619695,11231 "ci_low": 0.6431791657359223,11232 "ci_high": 0.7081114780680454,11233 "n_items": 1164,11234 "n_groups": 1811235 },11236 "exact_match": {11237 "mean": 0.0,11238 "ci_low": 0.0,11239 "ci_high": 0.0,11240 "n_items": 1164,11241 "n_groups": 1811242 },11243 "number_recall": {11244 "mean": 0.9998389175257731,11245 "ci_low": 0.9994850092332825,11246 "ci_high": 1.0,11247 "n_items": 1164,11248 "n_groups": 1811249 },11250 "placeholders_exact": {11251 "mean": 1.0,11252 "ci_low": 1.0,11253 "ci_high": 1.0,11254 "n_items": 1164,11255 "n_groups": 1811256 }11257 },11258 "1950-1979": {11259 "n": 206,11260 "chrf": {11261 "mean": 62.8104388381855,11262 "ci_low": 60.61148906027455,11263 "ci_high": 63.34030625454959,11264 "n_items": 206,11265 "n_groups": 211266 },11267 "edit_sim": {11268 "mean": 0.6480488152543298,11269 "ci_low": 0.6131583410466449,11270 "ci_high": 0.6564561584369044,11271 "n_items": 206,11272 "n_groups": 211273 },11274 "rougeL": {11275 "mean": 0.6533510967673157,11276 "ci_low": 0.6193684110195369,11277 "ci_high": 0.6615396957426841,11278 "n_items": 206,11279 "n_groups": 211280 },11281 "exact_match": {11282 "mean": 0.0,11283 "ci_low": 0.0,11284 "ci_high": 0.0,11285 "n_items": 206,11286 "n_groups": 211287 },11288 "number_recall": {11289 "mean": 1.0,11290 "ci_low": 1.0,11291 "ci_high": 1.0,11292 "n_items": 206,11293 "n_groups": 211294 },11295 "placeholders_exact": {11296 "mean": 1.0,11297 "ci_low": 1.0,11298 "ci_high": 1.0,11299 "n_items": 206,11300 "n_groups": 211301 }11302 },11303 "1980-1999": {11304 "n": 151,11305 "chrf": {11306 "mean": 64.06163388819148,11307 "ci_low": 62.59221152951138,11308 "ci_high": 79.05292198647894,11309 "n_items": 151,11310 "n_groups": 411311 },11312 "edit_sim": {11313 "mean": 0.6632542964934349,11314 "ci_low": 0.6495512631321201,11315 "ci_high": 0.8059067364122774,11316 "n_items": 151,11317 "n_groups": 411318 },11319 "rougeL": {11320 "mean": 0.6640039226198408,11321 "ci_low": 0.6514812239146761,11322 "ci_high": 0.7912066484891833,11323 "n_items": 151,11324 "n_groups": 411325 },11326 "exact_match": {11327 "mean": 0.0,11328 "ci_low": 0.0,11329 "ci_high": 0.0,11330 "n_items": 151,11331 "n_groups": 411332 },11333 "number_recall": {11334 "mean": 0.9990539262062441,11335 "ci_low": 0.9989547038327525,11336 "ci_high": 1.0,11337 "n_items": 151,11338 "n_groups": 411339 },11340 "placeholders_exact": {11341 "mean": 1.0,11342 "ci_low": 1.0,11343 "ci_high": 1.0,11344 "n_items": 151,11345 "n_groups": 411346 }11347 },11348 "2000-2009": {11349 "n": 1545,11350 "chrf": {11351 "mean": 69.85604346028634,11352 "ci_low": 68.46788436495753,11353 "ci_high": 71.29761809166959,11354 "n_items": 1545,11355 "n_groups": 6911356 },11357 "edit_sim": {11358 "mean": 0.692878494871823,11359 "ci_low": 0.6804103900547923,11360 "ci_high": 0.7062553345731987,11361 "n_items": 1545,11362 "n_groups": 6911363 },11364 "rougeL": {11365 "mean": 0.7022769828815059,11366 "ci_low": 0.6896252471012477,11367 "ci_high": 0.7154398564218541,11368 "n_items": 1545,11369 "n_groups": 6911370 },11371 "exact_match": {11372 "mean": 0.0,11373 "ci_low": 0.0,11374 "ci_high": 0.0,11375 "n_items": 1545,11376 "n_groups": 6911377 },11378 "number_recall": {11379 "mean": 0.9890841315441543,11380 "ci_low": 0.9822309443939262,11381 "ci_high": 0.9938335162343773,11382 "n_items": 1545,11383 "n_groups": 6911384 },11385 "placeholders_exact": {11386 "mean": 0.9935275080906149,11387 "ci_low": 0.9844496278575225,11388 "ci_high": 0.9993531903620579,11389 "n_items": 1545,11390 "n_groups": 6911391 }11392 },11393 "2010-2017": {11394 "n": 12583,11395 "chrf": {11396 "mean": 69.88653539494574,11397 "ci_low": 69.39718030410933,11398 "ci_high": 70.38130870428067,11399 "n_items": 12583,11400 "n_groups": 55911401 },11402 "edit_sim": {11403 "mean": 0.6860210470754602,11404 "ci_low": 0.6809015080275572,11405 "ci_high": 0.6907660394478203,11406 "n_items": 12583,11407 "n_groups": 55911408 },11409 "rougeL": {11410 "mean": 0.6946319185573769,11411 "ci_low": 0.6890293878844569,11412 "ci_high": 0.6997815778987048,11413 "n_items": 12583,11414 "n_groups": 55911415 },11416 "exact_match": {11417 "mean": 0.0,11418 "ci_low": 0.0,11419 "ci_high": 0.0,11420 "n_items": 12583,11421 "n_groups": 55911422 },11423 "number_recall": {11424 "mean": 0.989641034770927,11425 "ci_low": 0.9876185014922012,11426 "ci_high": 0.9915076354410126,11427 "n_items": 12583,11428 "n_groups": 55911429 },11430 "placeholders_exact": {11431 "mean": 0.9910991019629659,11432 "ci_low": 0.9882225766794438,11433 "ci_high": 0.9937117632923327,11434 "n_items": 12583,11435 "n_groups": 55911436 }11437 }11438 },11439 "by_role": {11440 "abstract": {11441 "n": 1255,11442 "chrf": {11443 "mean": 70.22578329675613,11444 "ci_low": 69.39657316681303,11445 "ci_high": 71.1451869065129,11446 "n_items": 1255,11447 "n_groups": 19511448 },11449 "edit_sim": {11450 "mean": 0.682109728433698,11451 "ci_low": 0.6720209982141361,11452 "ci_high": 0.6927147133573348,11453 "n_items": 1255,11454 "n_groups": 19511455 },11456 "rougeL": {11457 "mean": 0.6857723012598331,11458 "ci_low": 0.676237575940985,11459 "ci_high": 0.6955571697790311,11460 "n_items": 1255,11461 "n_groups": 19511462 },11463 "exact_match": {11464 "mean": 0.0,11465 "ci_low": 0.0,11466 "ci_high": 0.0,11467 "n_items": 1255,11468 "n_groups": 19511469 },11470 "number_recall": {11471 "mean": 0.9939528112817714,11472 "ci_low": 0.9906552365515574,11473 "ci_high": 0.9967296130664567,11474 "n_items": 1255,11475 "n_groups": 19511476 },11477 "placeholders_exact": {11478 "mean": 0.9976095617529881,11479 "ci_low": 0.9924683035980458,11480 "ci_high": 1.0,11481 "n_items": 1255,11482 "n_groups": 19511483 }11484 },11485 "background": {11486 "n": 964,11487 "chrf": {11488 "mean": 69.81362638298451,11489 "ci_low": 68.75230565939859,11490 "ci_high": 70.91626097398891,11491 "n_items": 964,11492 "n_groups": 8411493 },11494 "edit_sim": {11495 "mean": 0.6901750140869158,11496 "ci_low": 0.6781125247752312,11497 "ci_high": 0.7025513758176539,11498 "n_items": 964,11499 "n_groups": 8411500 },11501 "rougeL": {11502 "mean": 0.6965190874227541,11503 "ci_low": 0.6820302667237951,11504 "ci_high": 0.7105337098706581,11505 "n_items": 964,11506 "n_groups": 8411507 },11508 "exact_match": {11509 "mean": 0.0,11510 "ci_low": 0.0,11511 "ci_high": 0.0,11512 "n_items": 964,11513 "n_groups": 8411514 },11515 "number_recall": {11516 "mean": 0.9911743397220575,11517 "ci_low": 0.9852245406328743,11518 "ci_high": 0.9958568307963469,11519 "n_items": 964,11520 "n_groups": 8411521 },11522 "placeholders_exact": {11523 "mean": 0.9896265560165975,11524 "ci_low": 0.9765807962529274,11525 "ci_high": 0.9978052062438694,11526 "n_items": 964,11527 "n_groups": 8411528 }11529 },11530 "chapter": {11531 "n": 1287,11532 "chrf": {11533 "mean": 64.25593894188422,11534 "ci_low": 62.97583929425123,11535 "ci_high": 65.93200778210996,11536 "n_items": 1287,11537 "n_groups": 2111538 },11539 "edit_sim": {11540 "mean": 0.6559681942684356,11541 "ci_low": 0.6442276343779324,11542 "ci_high": 0.6765592299435246,11543 "n_items": 1287,11544 "n_groups": 2111545 },11546 "rougeL": {11547 "mean": 0.6643187886922335,11548 "ci_low": 0.6525098167911788,11549 "ci_high": 0.6850177096306814,11550 "n_items": 1287,11551 "n_groups": 2111552 },11553 "exact_match": {11554 "mean": 0.0,11555 "ci_low": 0.0,11556 "ci_high": 0.0,11557 "n_items": 1287,11558 "n_groups": 2111559 },11560 "number_recall": {11561 "mean": 0.9988594738594738,11562 "ci_low": 0.9969766372380059,11563 "ci_high": 1.0,11564 "n_items": 1287,11565 "n_groups": 2111566 },11567 "placeholders_exact": {11568 "mean": 1.0,11569 "ci_low": 1.0,11570 "ci_high": 1.0,11571 "n_items": 1287,11572 "n_groups": 2111573 }11574 },11575 "conclusion": {11576 "n": 1168,11577 "chrf": {11578 "mean": 67.59008485490995,11579 "ci_low": 66.67509567743593,11580 "ci_high": 68.5391890473466,11581 "n_items": 1168,11582 "n_groups": 15411583 },11584 "edit_sim": {11585 "mean": 0.6668552237987024,11586 "ci_low": 0.6566975148176891,11587 "ci_high": 0.6773227332755792,11588 "n_items": 1168,11589 "n_groups": 15411590 },11591 "rougeL": {11592 "mean": 0.6665563172606376,11593 "ci_low": 0.6563519407462743,11594 "ci_high": 0.6767799153385041,11595 "n_items": 1168,11596 "n_groups": 15411597 },11598 "exact_match": {11599 "mean": 0.0,11600 "ci_low": 0.0,11601 "ci_high": 0.0,11602 "n_items": 1168,11603 "n_groups": 15411604 },11605 "number_recall": {11606 "mean": 0.9954597652157585,11607 "ci_low": 0.9923398343345458,11608 "ci_high": 0.9981624990406686,11609 "n_items": 1168,11610 "n_groups": 15411611 },11612 "placeholders_exact": {11613 "mean": 0.997431506849315,11614 "ci_low": 0.9918402500686957,11615 "ci_high": 1.0,11616 "n_items": 1168,11617 "n_groups": 15411618 }11619 },11620 "data": {11621 "n": 912,11622 "chrf": {11623 "mean": 70.5526310755715,11624 "ci_low": 69.56291856475775,11625 "ci_high": 71.61865939148488,11626 "n_items": 912,11627 "n_groups": 10411628 },11629 "edit_sim": {11630 "mean": 0.6880528258262808,11631 "ci_low": 0.6771683576389217,11632 "ci_high": 0.6985564457687224,11633 "n_items": 912,11634 "n_groups": 10411635 },11636 "rougeL": {11637 "mean": 0.7074815162639053,11638 "ci_low": 0.6962988622778538,11639 "ci_high": 0.7189889131250805,11640 "n_items": 912,11641 "n_groups": 10411642 },11643 "exact_match": {11644 "mean": 0.0,11645 "ci_low": 0.0,11646 "ci_high": 0.0,11647 "n_items": 912,11648 "n_groups": 10411649 },11650 "number_recall": {11651 "mean": 0.9825950014422599,11652 "ci_low": 0.9746029159484566,11653 "ci_high": 0.9896042192545407,11654 "n_items": 912,11655 "n_groups": 10411656 },11657 "placeholders_exact": {11658 "mean": 0.9923245614035088,11659 "ci_low": 0.9820398270503127,11660 "ci_high": 0.9989473684210526,11661 "n_items": 912,11662 "n_groups": 10411663 }11664 },11665 "discussion": {11666 "n": 1601,11667 "chrf": {11668 "mean": 69.34309164154122,11669 "ci_low": 68.48108894835036,11670 "ci_high": 70.18178144366146,11671 "n_items": 1601,11672 "n_groups": 14211673 },11674 "edit_sim": {11675 "mean": 0.6828879213563428,11676 "ci_low": 0.6736970809380252,11677 "ci_high": 0.6917544953733489,11678 "n_items": 1601,11679 "n_groups": 14211680 },11681 "rougeL": {11682 "mean": 0.6844798146544745,11683 "ci_low": 0.6748664193997673,11684 "ci_high": 0.694000629829307,11685 "n_items": 1601,11686 "n_groups": 14211687 },11688 "exact_match": {11689 "mean": 0.0,11690 "ci_low": 0.0,11691 "ci_high": 0.0,11692 "n_items": 1601,11693 "n_groups": 14211694 },11695 "number_recall": {11696 "mean": 0.9920367303698495,11697 "ci_low": 0.9877396788772659,11698 "ci_high": 0.9956540861913019,11699 "n_items": 1601,11700 "n_groups": 14211701 },11702 "placeholders_exact": {11703 "mean": 0.9918800749531543,11704 "ci_low": 0.9850422659433136,11705 "ci_high": 0.9969995573987172,11706 "n_items": 1601,11707 "n_groups": 14211708 }11709 },11710 "introduction": {11711 "n": 1789,11712 "chrf": {11713 "mean": 69.26341614740625,11714 "ci_low": 68.3128692713487,11715 "ci_high": 70.2260296172349,11716 "n_items": 1789,11717 "n_groups": 17611718 },11719 "edit_sim": {11720 "mean": 0.6833897812360635,11721 "ci_low": 0.6738520301969919,11722 "ci_high": 0.693780156324902,11723 "n_items": 1789,11724 "n_groups": 17611725 },11726 "rougeL": {11727 "mean": 0.6849567182201027,11728 "ci_low": 0.675109920214073,11729 "ci_high": 0.6949653314868671,11730 "n_items": 1789,11731 "n_groups": 17611732 },11733 "exact_match": {11734 "mean": 0.0,11735 "ci_low": 0.0,11736 "ci_high": 0.0,11737 "n_items": 1789,11738 "n_groups": 17611739 },11740 "number_recall": {11741 "mean": 0.9926223324839871,11742 "ci_low": 0.9864591822775934,11743 "ci_high": 0.9971007110532593,11744 "n_items": 1789,11745 "n_groups": 17611746 },11747 "placeholders_exact": {11748 "mean": 0.9888205701509223,11749 "ci_low": 0.978734175955194,11750 "ci_high": 0.9966105033240179,11751 "n_items": 1789,11752 "n_groups": 17611753 }11754 },11755 "limitations": {11756 "n": 425,11757 "chrf": {11758 "mean": 67.85049840923165,11759 "ci_low": 66.29001692395155,11760 "ci_high": 69.51860788070454,11761 "n_items": 425,11762 "n_groups": 4111763 },11764 "edit_sim": {11765 "mean": 0.6657146971601373,11766 "ci_low": 0.6483686796119041,11767 "ci_high": 0.6843180711532404,11768 "n_items": 425,11769 "n_groups": 4111770 },11771 "rougeL": {11772 "mean": 0.6692120194414314,11773 "ci_low": 0.6488323464968369,11774 "ci_high": 0.6908930499433333,11775 "n_items": 425,11776 "n_groups": 4111777 },11778 "exact_match": {11779 "mean": 0.0,11780 "ci_low": 0.0,11781 "ci_high": 0.0,11782 "n_items": 425,11783 "n_groups": 4111784 },11785 "number_recall": {11786 "mean": 0.9927320261437909,11787 "ci_low": 0.9833009000306416,11788 "ci_high": 0.9991709237318561,11789 "n_items": 425,11790 "n_groups": 4111791 },11792 "placeholders_exact": {11793 "mean": 0.9788235294117648,11794 "ci_low": 0.9541984732824428,11795 "ci_high": 0.9977116704805492,11796 "n_items": 425,11797 "n_groups": 4111798 }11799 },11800 "methods": {11801 "n": 1528,11802 "chrf": {11803 "mean": 71.41580018358728,11804 "ci_low": 70.5911045658394,11805 "ci_high": 72.28258918968429,11806 "n_items": 1528,11807 "n_groups": 15111808 },11809 "edit_sim": {11810 "mean": 0.6992174754200554,11811 "ci_low": 0.6902251163249568,11812 "ci_high": 0.7082553122542578,11813 "n_items": 1528,11814 "n_groups": 15111815 },11816 "rougeL": {11817 "mean": 0.7179519578593355,11818 "ci_low": 0.7086106648568363,11819 "ci_high": 0.7274050601760192,11820 "n_items": 1528,11821 "n_groups": 15111822 },11823 "exact_match": {11824 "mean": 0.0,11825 "ci_low": 0.0,11826 "ci_high": 0.0,11827 "n_items": 1528,11828 "n_groups": 15111829 },11830 "number_recall": {11831 "mean": 0.988974025568043,11832 "ci_low": 0.9837604119093357,11833 "ci_high": 0.9931628752244049,11834 "n_items": 1528,11835 "n_groups": 15111836 },11837 "placeholders_exact": {11838 "mean": 0.9921465968586387,11839 "ci_low": 0.9837238037440638,11840 "ci_high": 0.9981777295399015,11841 "n_items": 1528,11842 "n_groups": 15111843 }11844 },11845 "other": {11846 "n": 1387,11847 "chrf": {11848 "mean": 70.05800514601565,11849 "ci_low": 68.99449676003154,11850 "ci_high": 71.14498221873104,11851 "n_items": 1387,11852 "n_groups": 11911853 },11854 "edit_sim": {11855 "mean": 0.6915663565495047,11856 "ci_low": 0.6812710066970736,11857 "ci_high": 0.7023166720869359,11858 "n_items": 1387,11859 "n_groups": 11911860 },11861 "rougeL": {11862 "mean": 0.6991692324281364,11863 "ci_low": 0.6877870365822382,11864 "ci_high": 0.70986030289227,11865 "n_items": 1387,11866 "n_groups": 11911867 },11868 "exact_match": {11869 "mean": 0.0,11870 "ci_low": 0.0,11871 "ci_high": 0.0,11872 "n_items": 1387,11873 "n_groups": 11911874 },11875 "number_recall": {11876 "mean": 0.9931180691454665,11877 "ci_low": 0.9890572684365229,11878 "ci_high": 0.9963757808154708,11879 "n_items": 1387,11880 "n_groups": 11911881 },11882 "placeholders_exact": {11883 "mean": 0.9790915645277577,11884 "ci_low": 0.9649008207308799,11885 "ci_high": 0.9925020094806266,11886 "n_items": 1387,11887 "n_groups": 11911888 }11889 },11890 "preface": {11891 "n": 362,11892 "chrf": {11893 "mean": 63.66310079093407,11894 "ci_low": 59.19295461116251,11895 "ci_high": 68.34401528955522,11896 "n_items": 362,11897 "n_groups": 1311898 },11899 "edit_sim": {11900 "mean": 0.6556880703097481,11901 "ci_low": 0.607737524199232,11902 "ci_high": 0.7069786392053565,11903 "n_items": 362,11904 "n_groups": 1311905 },11906 "rougeL": {11907 "mean": 0.6628393415417723,11908 "ci_low": 0.6099080965956136,11909 "ci_high": 0.7212639179287493,11910 "n_items": 362,11911 "n_groups": 1311912 },11913 "exact_match": {11914 "mean": 0.0,11915 "ci_low": 0.0,11916 "ci_high": 0.0,11917 "n_items": 362,11918 "n_groups": 1311919 },11920 "number_recall": {11921 "mean": 0.9998273480662984,11922 "ci_low": 0.9995559436898639,11923 "ci_high": 1.0,11924 "n_items": 362,11925 "n_groups": 1311926 },11927 "placeholders_exact": {11928 "mean": 1.0,11929 "ci_low": 1.0,11930 "ci_high": 1.0,11931 "n_items": 362,11932 "n_groups": 1311933 }11934 },11935 "related_work": {11936 "n": 557,11937 "chrf": {11938 "mean": 71.11375117820917,11939 "ci_low": 69.60708595435263,11940 "ci_high": 72.69510265126803,11941 "n_items": 557,11942 "n_groups": 3911943 },11944 "edit_sim": {11945 "mean": 0.6948171289283834,11946 "ci_low": 0.6778126689533961,11947 "ci_high": 0.7146602824093204,11948 "n_items": 557,11949 "n_groups": 3911950 },11951 "rougeL": {11952 "mean": 0.7003742946299152,11953 "ci_low": 0.6826637686642425,11954 "ci_high": 0.7198414264858736,11955 "n_items": 557,11956 "n_groups": 3911957 },11958 "exact_match": {11959 "mean": 0.0,11960 "ci_low": 0.0,11961 "ci_high": 0.0,11962 "n_items": 557,11963 "n_groups": 3911964 },11965 "number_recall": {11966 "mean": 0.987331395209735,11967 "ci_low": 0.9783345712831338,11968 "ci_high": 0.994838347074367,11969 "n_items": 557,11970 "n_groups": 3911971 },11972 "placeholders_exact": {11973 "mean": 0.9856373429084381,11974 "ci_low": 0.973305954825462,11975 "ci_high": 0.9965292591012515,11976 "n_items": 557,11977 "n_groups": 3911978 }11979 },11980 "results": {11981 "n": 1501,11982 "chrf": {11983 "mean": 70.59545282586956,11984 "ci_low": 69.38522148955697,11985 "ci_high": 71.84424190107326,11986 "n_items": 1501,11987 "n_groups": 15311988 },11989 "edit_sim": {11990 "mean": 0.6928253533073216,11991 "ci_low": 0.6822034086018564,11992 "ci_high": 0.7037227920040003,11993 "n_items": 1501,11994 "n_groups": 15311995 },11996 "rougeL": {11997 "mean": 0.7137570525407197,11998 "ci_low": 0.7020156970964668,11999 "ci_high": 0.725972808643748,12000 "n_items": 1501,12001 "n_groups": 15312002 },12003 "exact_match": {12004 "mean": 0.0,12005 "ci_low": 0.0,12006 "ci_high": 0.0,12007 "n_items": 1501,12008 "n_groups": 15312009 },12010 "number_recall": {12011 "mean": 0.9737899124614028,12012 "ci_low": 0.9647574769466614,12013 "ci_high": 0.9816148651055705,12014 "n_items": 1501,12015 "n_groups": 15312016 },12017 "placeholders_exact": {12018 "mean": 0.9953364423717521,12019 "ci_low": 0.9882675042930592,12020 "ci_high": 1.0,12021 "n_items": 1501,12022 "n_groups": 15312023 }12024 },12025 "theory": {12026 "n": 913,12027 "chrf": {12028 "mean": 70.75887294266974,12029 "ci_low": 69.56510178114765,12030 "ci_high": 71.90935628208787,12031 "n_items": 913,12032 "n_groups": 7912033 },12034 "edit_sim": {12035 "mean": 0.7017400801192495,12036 "ci_low": 0.6871092600047909,12037 "ci_high": 0.7154542471917601,12038 "n_items": 913,12039 "n_groups": 7912040 },12041 "rougeL": {12042 "mean": 0.7153771730406131,12043 "ci_low": 0.6999772685731795,12044 "ci_high": 0.7301762342164524,12045 "n_items": 913,12046 "n_groups": 7912047 },12048 "exact_match": {12049 "mean": 0.0,12050 "ci_low": 0.0,12051 "ci_high": 0.0,12052 "n_items": 913,12053 "n_groups": 7912054 },12055 "number_recall": {12056 "mean": 0.9924305006177951,12057 "ci_low": 0.987232374866234,12058 "ci_high": 0.9969292360040798,12059 "n_items": 913,12060 "n_groups": 7912061 },12062 "placeholders_exact": {12063 "mean": 0.9989047097480832,12064 "ci_low": 0.9962311557788944,12065 "ci_high": 1.0,12066 "n_items": 913,12067 "n_groups": 7912068 }12069 }12070 }12071 },12072 "htr-m2-tiny": {12073 "overall": {12074 "n": 15649,12075 "chrf": {12076 "mean": 69.171770652484,12077 "ci_low": 68.62572061506532,12078 "ci_high": 69.71215966397817,12079 "n_items": 15649,12080 "n_groups": 65212081 },12082 "edit_sim": {12083 "mean": 0.6829901071607405,12084 "ci_low": 0.6780465807687004,12085 "ci_high": 0.6879765387892374,12086 "n_items": 15649,12087 "n_groups": 65212088 },12089 "rougeL": {12090 "mean": 0.6916488798488484,12091 "ci_low": 0.6862994396021885,12092 "ci_high": 0.6970099639236197,12093 "n_items": 15649,12094 "n_groups": 65212095 },12096 "exact_match": {12097 "mean": 0.0,12098 "ci_low": 0.0,12099 "ci_high": 0.0,12100 "n_items": 15649,12101 "n_groups": 65212102 },12103 "number_recall": {12104 "mean": 0.9886042275679136,12105 "ci_low": 0.9863199600939387,12106 "ci_high": 0.9906388394514306,12107 "n_items": 15649,12108 "n_groups": 65212109 },12110 "placeholders_exact": {12111 "mean": 0.9930986005495559,12112 "ci_low": 0.9908498172231242,12113 "ci_high": 0.9950880085599316,12114 "n_items": 15649,12115 "n_groups": 65212116 }12117 },12118 "by_variant": {12119 "A": {12120 "n": 2664,12121 "chrf": {12122 "mean": 68.73502452327048,12123 "ci_low": 68.0858912647038,12124 "ci_high": 69.35852541293588,12125 "n_items": 2664,12126 "n_groups": 63012127 },12128 "edit_sim": {12129 "mean": 0.6751929588744778,12130 "ci_low": 0.6693890635842026,12131 "ci_high": 0.681682952452987,12132 "n_items": 2664,12133 "n_groups": 63012134 },12135 "rougeL": {12136 "mean": 0.680980241059236,12137 "ci_low": 0.6749467622525726,12138 "ci_high": 0.6872426628447192,12139 "n_items": 2664,12140 "n_groups": 63012141 },12142 "exact_match": {12143 "mean": 0.0,12144 "ci_low": 0.0,12145 "ci_high": 0.0,12146 "n_items": 2664,12147 "n_groups": 63012148 },12149 "number_recall": {12150 "mean": 0.9870271541872406,12151 "ci_low": 0.9838832829151316,12152 "ci_high": 0.9900074817442036,12153 "n_items": 2664,12154 "n_groups": 63012155 },12156 "placeholders_exact": {12157 "mean": 0.9906156156156156,12158 "ci_low": 0.9867968676576422,12159 "ci_high": 0.9940247357238412,12160 "n_items": 2664,12161 "n_groups": 63012162 }12163 },12164 "B": {12165 "n": 2539,12166 "chrf": {12167 "mean": 74.72170473883703,12168 "ci_low": 74.11097992121728,12169 "ci_high": 75.3115197656187,12170 "n_items": 2539,12171 "n_groups": 61412172 },12173 "edit_sim": {12174 "mean": 0.7492406266438758,12175 "ci_low": 0.7434426831879085,12176 "ci_high": 0.7550678552138611,12177 "n_items": 2539,12178 "n_groups": 61412179 },12180 "rougeL": {12181 "mean": 0.7563714267744133,12182 "ci_low": 0.7502738181267481,12183 "ci_high": 0.7622903394270102,12184 "n_items": 2539,12185 "n_groups": 61412186 },12187 "exact_match": {12188 "mean": 0.0,12189 "ci_low": 0.0,12190 "ci_high": 0.0,12191 "n_items": 2539,12192 "n_groups": 61412193 },12194 "number_recall": {12195 "mean": 0.9899869711275096,12196 "ci_low": 0.9873124826008868,12197 "ci_high": 0.9923410461096451,12198 "n_items": 2539,12199 "n_groups": 61412200 },12201 "placeholders_exact": {12202 "mean": 0.993304450571091,12203 "ci_low": 0.9899696718184211,12204 "ci_high": 0.9961816636523286,12205 "n_items": 2539,12206 "n_groups": 61412207 }12208 },12209 "C": {12210 "n": 2663,12211 "chrf": {12212 "mean": 71.49310210097708,12213 "ci_low": 70.95665313262676,12214 "ci_high": 72.06546279947996,12215 "n_items": 2663,12216 "n_groups": 63812217 },12218 "edit_sim": {12219 "mean": 0.7245818302241988,12220 "ci_low": 0.7192236742183704,12221 "ci_high": 0.7300764347423323,12222 "n_items": 2663,12223 "n_groups": 63812224 },12225 "rougeL": {12226 "mean": 0.744028107474532,12227 "ci_low": 0.7384456569147659,12228 "ci_high": 0.7499091277476461,12229 "n_items": 2663,12230 "n_groups": 63812231 },12232 "exact_match": {12233 "mean": 0.0,12234 "ci_low": 0.0,12235 "ci_high": 0.0,12236 "n_items": 2663,12237 "n_groups": 63812238 },12239 "number_recall": {12240 "mean": 0.9897011270168267,12241 "ci_low": 0.9871210708128744,12242 "ci_high": 0.992008167407944,12243 "n_items": 2663,12244 "n_groups": 63812245 },12246 "placeholders_exact": {12247 "mean": 0.994742771310552,12248 "ci_low": 0.9916949485629402,12249 "ci_high": 0.9973695087050601,12250 "n_items": 2663,12251 "n_groups": 63812252 }12253 },12254 "D": {12255 "n": 2708,12256 "chrf": {12257 "mean": 69.80995464992422,12258 "ci_low": 69.20422204614115,12259 "ci_high": 70.4216804446043,12260 "n_items": 2708,12261 "n_groups": 63812262 },12263 "edit_sim": {12264 "mean": 0.6941752439639293,12265 "ci_low": 0.688736847581871,12266 "ci_high": 0.6995871559187429,12267 "n_items": 2708,12268 "n_groups": 63812269 },12270 "rougeL": {12271 "mean": 0.6988944526381742,12272 "ci_low": 0.6934541931843754,12273 "ci_high": 0.7044091438021266,12274 "n_items": 2708,12275 "n_groups": 63812276 },12277 "exact_match": {12278 "mean": 0.0,12279 "ci_low": 0.0,12280 "ci_high": 0.0,12281 "n_items": 2708,12282 "n_groups": 63812283 },12284 "number_recall": {12285 "mean": 0.9883189378372856,12286 "ci_low": 0.9854718912067163,12287 "ci_high": 0.9908054132618106,12288 "n_items": 2708,12289 "n_groups": 63812290 },12291 "placeholders_exact": {12292 "mean": 0.9929837518463811,12293 "ci_low": 0.9894018076539914,12294 "ci_high": 0.9960914230957497,12295 "n_items": 2708,12296 "n_groups": 63812297 }12298 },12299 "E": {12300 "n": 5075,12301 "chrf": {12302 "mean": 65.06582013634001,12303 "ci_low": 64.45251845763262,12304 "ci_high": 65.66915986455533,12305 "n_items": 5075,12306 "n_groups": 62312307 },12308 "edit_sim": {12309 "mean": 0.6261454618574694,12310 "ci_low": 0.6206520037407666,12311 "ci_high": 0.6316522517646861,12312 "n_items": 5075,12313 "n_groups": 62312314 },12315 "rougeL": {12316 "mean": 0.633517611437189,12317 "ci_low": 0.6274445570477012,12318 "ci_high": 0.6398173877471341,12319 "n_items": 5075,12320 "n_groups": 62312321 },12322 "exact_match": {12323 "mean": 0.0,12324 "ci_low": 0.0,12325 "ci_high": 0.0,12326 "n_items": 5075,12327 "n_groups": 62312328 },12329 "number_recall": {12330 "mean": 0.9883169485425702,12331 "ci_low": 0.9854937796880572,12332 "ci_high": 0.9908139024351273,12333 "n_items": 5075,12334 "n_groups": 62312335 },12336 "placeholders_exact": {12337 "mean": 0.9934975369458128,12338 "ci_low": 0.9906867987626304,12339 "ci_high": 0.9960350739421996,12340 "n_items": 5075,12341 "n_groups": 62312342 }12343 }12344 },12345 "by_discipline": {12346 "biomedicine": {12347 "n": 2154,12348 "chrf": {12349 "mean": 69.49990550178688,12350 "ci_low": 68.3376242991186,12351 "ci_high": 70.59616949574409,12352 "n_items": 2154,12353 "n_groups": 24412354 },12355 "edit_sim": {12356 "mean": 0.6812888490758915,12357 "ci_low": 0.672706570716659,12358 "ci_high": 0.6901709123795936,12359 "n_items": 2154,12360 "n_groups": 24412361 },12362 "rougeL": {12363 "mean": 0.6903368243189553,12364 "ci_low": 0.6809377143818728,12365 "ci_high": 0.699722805811844,12366 "n_items": 2154,12367 "n_groups": 24412368 },12369 "exact_match": {12370 "mean": 0.0,12371 "ci_low": 0.0,12372 "ci_high": 0.0,12373 "n_items": 2154,12374 "n_groups": 24412375 },12376 "number_recall": {12377 "mean": 0.9882188546247207,12378 "ci_low": 0.9822879731601942,12379 "ci_high": 0.9929925312355834,12380 "n_items": 2154,12381 "n_groups": 24412382 },12383 "placeholders_exact": {12384 "mean": 0.9953574744661096,12385 "ci_low": 0.9899797445894655,12386 "ci_high": 0.9991177419682451,12387 "n_items": 2154,12388 "n_groups": 24412389 }12390 },12391 "chemistry": {12392 "n": 837,12393 "chrf": {12394 "mean": 72.31701591664353,12395 "ci_low": 70.93389283330923,12396 "ci_high": 73.70729567504331,12397 "n_items": 837,12398 "n_groups": 1312399 },12400 "edit_sim": {12401 "mean": 0.6966881613308036,12402 "ci_low": 0.6812827879119665,12403 "ci_high": 0.7137725024158166,12404 "n_items": 837,12405 "n_groups": 1312406 },12407 "rougeL": {12408 "mean": 0.7124046607546421,12409 "ci_low": 0.6979730825804763,12410 "ci_high": 0.7277349736659112,12411 "n_items": 837,12412 "n_groups": 1312413 },12414 "exact_match": {12415 "mean": 0.0,12416 "ci_low": 0.0,12417 "ci_high": 0.0,12418 "n_items": 837,12419 "n_groups": 1312420 },12421 "number_recall": {12422 "mean": 0.9765280458556153,12423 "ci_low": 0.9652287800884729,12424 "ci_high": 0.9888903868702973,12425 "n_items": 837,12426 "n_groups": 1312427 },12428 "placeholders_exact": {12429 "mean": 0.994026284348865,12430 "ci_low": 0.9848059465845926,12431 "ci_high": 1.0,12432 "n_items": 837,12433 "n_groups": 1312434 }12435 },12436 "computer_science": {12437 "n": 1375,12438 "chrf": {12439 "mean": 69.26967330772582,12440 "ci_low": 67.8295998228067,12441 "ci_high": 70.59590139327425,12442 "n_items": 1375,12443 "n_groups": 2012444 },12445 "edit_sim": {12446 "mean": 0.6890485569909914,12447 "ci_low": 0.6734430815871925,12448 "ci_high": 0.702388853450011,12449 "n_items": 1375,12450 "n_groups": 2012451 },12452 "rougeL": {12453 "mean": 0.6941205329525706,12454 "ci_low": 0.6776822593674994,12455 "ci_high": 0.7073839185799918,12456 "n_items": 1375,12457 "n_groups": 2012458 },12459 "exact_match": {12460 "mean": 0.0,12461 "ci_low": 0.0,12462 "ci_high": 0.0,12463 "n_items": 1375,12464 "n_groups": 2012465 },12466 "number_recall": {12467 "mean": 0.9926291223927588,12468 "ci_low": 0.9852277564887484,12469 "ci_high": 0.9973547833124389,12470 "n_items": 1375,12471 "n_groups": 2012472 },12473 "placeholders_exact": {12474 "mean": 0.9934545454545455,12475 "ci_low": 0.9869805874657892,12476 "ci_high": 0.9985362687296642,12477 "n_items": 1375,12478 "n_groups": 2012479 }12480 },12481 "economics": {12482 "n": 1944,12483 "chrf": {12484 "mean": 68.49021033273524,12485 "ci_low": 67.69351803451572,12486 "ci_high": 69.24838816013992,12487 "n_items": 1944,12488 "n_groups": 10312489 },12490 "edit_sim": {12491 "mean": 0.6802004532232365,12492 "ci_low": 0.6714150039361646,12493 "ci_high": 0.6889158735557414,12494 "n_items": 1944,12495 "n_groups": 10312496 },12497 "rougeL": {12498 "mean": 0.6844752507648635,12499 "ci_low": 0.6744301120130494,12500 "ci_high": 0.6939566603711912,12501 "n_items": 1944,12502 "n_groups": 10312503 },12504 "exact_match": {12505 "mean": 0.0,12506 "ci_low": 0.0,12507 "ci_high": 0.0,12508 "n_items": 1944,12509 "n_groups": 10312510 },12511 "number_recall": {12512 "mean": 0.9877481594765546,12513 "ci_low": 0.9820993783817975,12514 "ci_high": 0.9927396409008847,12515 "n_items": 1944,12516 "n_groups": 10312517 },12518 "placeholders_exact": {12519 "mean": 0.9953703703703703,12520 "ci_low": 0.989124650834644,12521 "ci_high": 0.9995102900278681,12522 "n_items": 1944,12523 "n_groups": 10312524 }12525 },12526 "engineering": {12527 "n": 1296,12528 "chrf": {12529 "mean": 66.70456223262566,12530 "ci_low": 65.08311000049333,12531 "ci_high": 68.29465497856661,12532 "n_items": 1296,12533 "n_groups": 1712534 },12535 "edit_sim": {12536 "mean": 0.6564788063554663,12537 "ci_low": 0.6418571043758192,12538 "ci_high": 0.670853284747099,12539 "n_items": 1296,12540 "n_groups": 1712541 },12542 "rougeL": {12543 "mean": 0.6673048314547421,12544 "ci_low": 0.6537882607071683,12545 "ci_high": 0.6816391431397375,12546 "n_items": 1296,12547 "n_groups": 1712548 },12549 "exact_match": {12550 "mean": 0.0,12551 "ci_low": 0.0,12552 "ci_high": 0.0,12553 "n_items": 1296,12554 "n_groups": 1712555 },12556 "number_recall": {12557 "mean": 0.9891330751589036,12558 "ci_low": 0.9837813557373993,12559 "ci_high": 0.9936016913929171,12560 "n_items": 1296,12561 "n_groups": 1712562 },12563 "placeholders_exact": {12564 "mean": 0.9907407407407407,12565 "ci_low": 0.981395254760292,12566 "ci_high": 0.9979465324982798,12567 "n_items": 1296,12568 "n_groups": 1712569 }12570 },12571 "finance": {12572 "n": 2043,12573 "chrf": {12574 "mean": 67.96101191430503,12575 "ci_low": 66.56831302517347,12576 "ci_high": 69.45585993109546,12577 "n_items": 2043,12578 "n_groups": 5112579 },12580 "edit_sim": {12581 "mean": 0.6732993103115984,12582 "ci_low": 0.6589743919861084,12583 "ci_high": 0.6888952555392672,12584 "n_items": 2043,12585 "n_groups": 5112586 },12587 "rougeL": {12588 "mean": 0.680377002690752,12589 "ci_low": 0.6661575236037808,12590 "ci_high": 0.6968108789247017,12591 "n_items": 2043,12592 "n_groups": 5112593 },12594 "exact_match": {12595 "mean": 0.0,12596 "ci_low": 0.0,12597 "ci_high": 0.0,12598 "n_items": 2043,12599 "n_groups": 5112600 },12601 "number_recall": {12602 "mean": 0.9904002851628891,12603 "ci_low": 0.9863598538698056,12604 "ci_high": 0.9940642610074496,12605 "n_items": 2043,12606 "n_groups": 5112607 },12608 "placeholders_exact": {12609 "mean": 0.9965736661771905,12610 "ci_low": 0.9902064569173296,12611 "ci_high": 1.0,12612 "n_items": 2043,12613 "n_groups": 5112614 }12615 },12616 "general_reference": {12617 "n": 118,12618 "chrf": {12619 "mean": 74.4002029291086,12620 "ci_low": 60.68775831950056,12621 "ci_high": 75.8098934964515,12622 "n_items": 118,12623 "n_groups": 212624 },12625 "edit_sim": {12626 "mean": 0.779270317566779,12627 "ci_low": 0.6083296116567939,12628 "ci_high": 0.7968436611650017,12629 "n_items": 118,12630 "n_groups": 212631 },12632 "rougeL": {12633 "mean": 0.8072254698832195,12634 "ci_low": 0.6211582637401286,12635 "ci_high": 0.82635387425307,12636 "n_items": 118,12637 "n_groups": 212638 },12639 "exact_match": {12640 "mean": 0.0,12641 "ci_low": 0.0,12642 "ci_high": 0.0,12643 "n_items": 118,12644 "n_groups": 212645 },12646 "number_recall": {12647 "mean": 0.9987893462469734,12648 "ci_low": 0.9986648865153538,12649 "ci_high": 1.0,12650 "n_items": 118,12651 "n_groups": 212652 },12653 "placeholders_exact": {12654 "mean": 1.0,12655 "ci_low": 1.0,12656 "ci_high": 1.0,12657 "n_items": 118,12658 "n_groups": 212659 }12660 },12661 "humanities": {12662 "n": 263,12663 "chrf": {12664 "mean": 63.490362047913706,12665 "ci_low": 59.14396612783386,12666 "ci_high": 63.960961669983824,12667 "n_items": 263,12668 "n_groups": 312669 },12670 "edit_sim": {12671 "mean": 0.6551415797917874,12672 "ci_low": 0.6107258806414001,12673 "ci_high": 0.6598802263077321,12674 "n_items": 263,12675 "n_groups": 312676 },12677 "rougeL": {12678 "mean": 0.6631460860691395,12679 "ci_low": 0.6283047607186387,12680 "ci_high": 0.666218687745621,12681 "n_items": 263,12682 "n_groups": 312683 },12684 "exact_match": {12685 "mean": 0.0,12686 "ci_low": 0.0,12687 "ci_high": 0.0,12688 "n_items": 263,12689 "n_groups": 312690 },12691 "number_recall": {12692 "mean": 1.0,12693 "ci_low": 1.0,12694 "ci_high": 1.0,12695 "n_items": 263,12696 "n_groups": 312697 },12698 "placeholders_exact": {12699 "mean": 1.0,12700 "ci_low": 1.0,12701 "ci_high": 1.0,12702 "n_items": 263,12703 "n_groups": 312704 }12705 },12706 "life_sciences": {12707 "n": 1874,12708 "chrf": {12709 "mean": 71.75009500069581,12710 "ci_low": 69.87258728247708,12711 "ci_high": 73.34416067039962,12712 "n_items": 1874,12713 "n_groups": 14312714 },12715 "edit_sim": {12716 "mean": 0.704666993448248,12717 "ci_low": 0.6909438516649025,12718 "ci_high": 0.718421083127238,12719 "n_items": 1874,12720 "n_groups": 14312721 },12722 "rougeL": {12723 "mean": 0.7152668633708962,12724 "ci_low": 0.7009872878682055,12725 "ci_high": 0.729351755515819,12726 "n_items": 1874,12727 "n_groups": 14312728 },12729 "exact_match": {12730 "mean": 0.0,12731 "ci_low": 0.0,12732 "ci_high": 0.0,12733 "n_items": 1874,12734 "n_groups": 14312735 },12736 "number_recall": {12737 "mean": 0.9855705334797054,12738 "ci_low": 0.9780661775794435,12739 "ci_high": 0.9913166639356866,12740 "n_items": 1874,12741 "n_groups": 14312742 },12743 "placeholders_exact": {12744 "mean": 0.9807897545357525,12745 "ci_low": 0.96875,12746 "ci_high": 0.9905947373055591,12747 "n_items": 1874,12748 "n_groups": 14312749 }12750 },12751 "mathematics": {12752 "n": 712,12753 "chrf": {12754 "mean": 68.4672449987842,12755 "ci_low": 65.56266935389766,12756 "ci_high": 71.75025702998877,12757 "n_items": 712,12758 "n_groups": 512759 },12760 "edit_sim": {12761 "mean": 0.6914149004234722,12762 "ci_low": 0.6657708129384852,12763 "ci_high": 0.711813449450969,12764 "n_items": 712,12765 "n_groups": 512766 },12767 "rougeL": {12768 "mean": 0.6903945514318298,12769 "ci_low": 0.6654987458751405,12770 "ci_high": 0.7225553024658924,12771 "n_items": 712,12772 "n_groups": 512773 },12774 "exact_match": {12775 "mean": 0.0,12776 "ci_low": 0.0,12777 "ci_high": 0.0,12778 "n_items": 712,12779 "n_groups": 512780 },12781 "number_recall": {12782 "mean": 0.99072502092165,12783 "ci_low": 0.9814658494826094,12784 "ci_high": 0.9982157838752931,12785 "n_items": 712,12786 "n_groups": 512787 },12788 "placeholders_exact": {12789 "mean": 0.9887640449438202,12790 "ci_low": 0.9702380952380952,12791 "ci_high": 0.9986631016042781,12792 "n_items": 712,12793 "n_groups": 512794 }12795 },12796 "other": {12797 "n": 669,12798 "chrf": {12799 "mean": 69.20912686191942,12800 "ci_low": 66.78887179921583,12801 "ci_high": 72.4168396407128,12802 "n_items": 669,12803 "n_groups": 1312804 },12805 "edit_sim": {12806 "mean": 0.6740640875529873,12807 "ci_low": 0.653184358382253,12808 "ci_high": 0.7032196308858574,12809 "n_items": 669,12810 "n_groups": 1312811 },12812 "rougeL": {12813 "mean": 0.6840215763155472,12814 "ci_low": 0.6615654362703596,12815 "ci_high": 0.7137470415237936,12816 "n_items": 669,12817 "n_groups": 1312818 },12819 "exact_match": {12820 "mean": 0.0,12821 "ci_low": 0.0,12822 "ci_high": 0.0,12823 "n_items": 669,12824 "n_groups": 1312825 },12826 "number_recall": {12827 "mean": 0.9874718248036634,12828 "ci_low": 0.9587659444418941,12829 "ci_high": 0.9976053632254924,12830 "n_items": 669,12831 "n_groups": 1312832 },12833 "placeholders_exact": {12834 "mean": 0.9985052316890882,12835 "ci_low": 0.9934047619047619,12836 "ci_high": 1.0,12837 "n_items": 669,12838 "n_groups": 1312839 }12840 },12841 "social_sciences": {12842 "n": 1536,12843 "chrf": {12844 "mean": 68.53610551514517,12845 "ci_low": 66.4457808004418,12846 "ci_high": 70.04964815619026,12847 "n_items": 1536,12848 "n_groups": 2912849 },12850 "edit_sim": {12851 "mean": 0.6782181710351455,12852 "ci_low": 0.660514771884782,12853 "ci_high": 0.6931826229371788,12854 "n_items": 1536,12855 "n_groups": 2912856 },12857 "rougeL": {12858 "mean": 0.6849427400271694,12859 "ci_low": 0.6655779326721528,12860 "ci_high": 0.7013922632233103,12861 "n_items": 1536,12862 "n_groups": 2912863 },12864 "exact_match": {12865 "mean": 0.0,12866 "ci_low": 0.0,12867 "ci_high": 0.0,12868 "n_items": 1536,12869 "n_groups": 2912870 },12871 "number_recall": {12872 "mean": 0.993797875118807,12873 "ci_low": 0.9897006158966087,12874 "ci_high": 0.9978897103532065,12875 "n_items": 1536,12876 "n_groups": 2912877 },12878 "placeholders_exact": {12879 "mean": 0.9954427083333334,12880 "ci_low": 0.9913620592648162,12881 "ci_high": 0.9988117864209283,12882 "n_items": 1536,12883 "n_groups": 2912884 }12885 },12886 "statistics": {12887 "n": 828,12888 "chrf": {12889 "mean": 70.40430061801045,12890 "ci_low": 67.68706453390996,12891 "ci_high": 73.21291901778044,12892 "n_items": 828,12893 "n_groups": 912894 },12895 "edit_sim": {12896 "mean": 0.6903479118582485,12897 "ci_low": 0.6682057395901111,12898 "ci_high": 0.7143595546027599,12899 "n_items": 828,12900 "n_groups": 912901 },12902 "rougeL": {12903 "mean": 0.7115442872765377,12904 "ci_low": 0.686292249964933,12905 "ci_high": 0.7366170855406439,12906 "n_items": 828,12907 "n_groups": 912908 },12909 "exact_match": {12910 "mean": 0.0,12911 "ci_low": 0.0,12912 "ci_high": 0.0,12913 "n_items": 828,12914 "n_groups": 912915 },12916 "number_recall": {12917 "mean": 0.9831325268005203,12918 "ci_low": 0.9671343169349096,12919 "ci_high": 0.9939075771042231,12920 "n_items": 828,12921 "n_groups": 912922 },12923 "placeholders_exact": {12924 "mean": 0.9951690821256038,12925 "ci_low": 0.9895274180214935,12926 "ci_high": 1.0,12927 "n_items": 828,12928 "n_groups": 912929 }12930 }12931 },12932 "by_era": {12933 "1900-1949": {12934 "n": 1164,12935 "chrf": {12936 "mean": 63.86146321032778,12937 "ci_low": 61.707757957625105,12938 "ci_high": 66.89025114253288,12939 "n_items": 1164,12940 "n_groups": 1812941 },12942 "edit_sim": {12943 "mean": 0.6551000904251038,12944 "ci_low": 0.6303596183994521,12945 "ci_high": 0.6928172518780213,12946 "n_items": 1164,12947 "n_groups": 1812948 },12949 "rougeL": {12950 "mean": 0.6638972719116826,12951 "ci_low": 0.6383320143401332,12952 "ci_high": 0.7053192941965942,12953 "n_items": 1164,12954 "n_groups": 1812955 },12956 "exact_match": {12957 "mean": 0.0,12958 "ci_low": 0.0,12959 "ci_high": 0.0,12960 "n_items": 1164,12961 "n_groups": 1812962 },12963 "number_recall": {12964 "mean": 0.9996744258986527,12965 "ci_low": 0.999308728806772,12966 "ci_high": 1.0,12967 "n_items": 1164,12968 "n_groups": 1812969 },12970 "placeholders_exact": {12971 "mean": 1.0,12972 "ci_low": 1.0,12973 "ci_high": 1.0,12974 "n_items": 1164,12975 "n_groups": 1812976 }12977 },12978 "1950-1979": {12979 "n": 206,12980 "chrf": {12981 "mean": 63.104000105877944,12982 "ci_low": 61.19670346730459,12983 "ci_high": 63.56358965734142,12984 "n_items": 206,12985 "n_groups": 212986 },12987 "edit_sim": {12988 "mean": 0.6517384084119482,12989 "ci_low": 0.6179498641444447,12990 "ci_high": 0.6598802263077321,12991 "n_items": 206,12992 "n_groups": 212993 },12994 "rougeL": {12995 "mean": 0.6572997638580632,12996 "ci_low": 0.6202862297246983,12997 "ci_high": 0.666218687745621,12998 "n_items": 206,12999 "n_groups": 213000 },13001 "exact_match": {13002 "mean": 0.0,13003 "ci_low": 0.0,13004 "ci_high": 0.0,13005 "n_items": 206,13006 "n_groups": 213007 },13008 "number_recall": {13009 "mean": 1.0,13010 "ci_low": 1.0,13011 "ci_high": 1.0,13012 "n_items": 206,13013 "n_groups": 213014 },13015 "placeholders_exact": {13016 "mean": 1.0,13017 "ci_low": 1.0,13018 "ci_high": 1.0,13019 "n_items": 206,13020 "n_groups": 213021 }13022 },13023 "1980-1999": {13024 "n": 151,13025 "chrf": {13026 "mean": 63.72600405714502,13027 "ci_low": 62.268047808539535,13028 "ci_high": 78.43479546435279,13029 "n_items": 151,13030 "n_groups": 413031 },13032 "edit_sim": {13033 "mean": 0.6585351669374755,13034 "ci_low": 0.6452314153042416,13035 "ci_high": 0.7966373785191088,13036 "n_items": 151,13037 "n_groups": 413038 },13039 "rougeL": {13040 "mean": 0.6611263550692039,13041 "ci_low": 0.6490510371286289,13042 "ci_high": 0.7833546708268242,13043 "n_items": 151,13044 "n_groups": 413045 },13046 "exact_match": {13047 "mean": 0.0,13048 "ci_low": 0.0,13049 "ci_high": 0.0,13050 "n_items": 151,13051 "n_groups": 413052 },13053 "number_recall": {13054 "mean": 0.9990539262062441,13055 "ci_low": 0.9989547038327525,13056 "ci_high": 1.0,13057 "n_items": 151,13058 "n_groups": 413059 },13060 "placeholders_exact": {13061 "mean": 1.0,13062 "ci_low": 1.0,13063 "ci_high": 1.0,13064 "n_items": 151,13065 "n_groups": 413066 }13067 },13068 "2000-2009": {13069 "n": 1545,13070 "chrf": {13071 "mean": 69.63411137692519,13072 "ci_low": 68.28637214731698,13073 "ci_high": 71.02185000881512,13074 "n_items": 1545,13075 "n_groups": 6913076 },13077 "edit_sim": {13078 "mean": 0.6913122613904882,13079 "ci_low": 0.6790516179900392,13080 "ci_high": 0.7042512659920748,13081 "n_items": 1545,13082 "n_groups": 6913083 },13084 "rougeL": {13085 "mean": 0.7009686001998073,13086 "ci_low": 0.6888706925907757,13087 "ci_high": 0.7134211054628032,13088 "n_items": 1545,13089 "n_groups": 6913090 },13091 "exact_match": {13092 "mean": 0.0,13093 "ci_low": 0.0,13094 "ci_high": 0.0,13095 "n_items": 1545,13096 "n_groups": 6913097 },13098 "number_recall": {13099 "mean": 0.9892146554610861,13100 "ci_low": 0.9811104243005963,13101 "ci_high": 0.9947402842651896,13102 "n_items": 1545,13103 "n_groups": 6913104 },13105 "placeholders_exact": {13106 "mean": 0.9941747572815534,13107 "ci_low": 0.9880298953334938,13108 "ci_high": 0.9991632497094859,13109 "n_items": 1545,13110 "n_groups": 6913111 }13112 },13113 "2010-2017": {13114 "n": 12583,13115 "chrf": {13116 "mean": 69.77092450545271,13117 "ci_low": 69.28378000999096,13118 "ci_high": 70.26428391845798,13119 "n_items": 12583,13120 "n_groups": 55913121 },13122 "edit_sim": {13123 "mean": 0.6853533589378434,13124 "ci_low": 0.6802038130737401,13125 "ci_high": 0.6901570887178042,13126 "n_items": 12583,13127 "n_groups": 55913128 },13129 "rougeL": {13130 "mean": 0.6940003638218641,13131 "ci_low": 0.6884883442247052,13132 "ci_high": 0.6993025123995994,13133 "n_items": 12583,13134 "n_groups": 55913135 },13136 "exact_match": {13137 "mean": 0.0,13138 "ci_low": 0.0,13139 "ci_high": 0.0,13140 "n_items": 12583,13141 "n_groups": 55913142 },13143 "number_recall": {13144 "mean": 0.9871932559739114,13145 "ci_low": 0.984555730546943,13146 "ci_high": 0.9895841403467829,13147 "n_items": 12583,13148 "n_groups": 55913149 },13150 "placeholders_exact": {13151 "mean": 0.9921322419136931,13152 "ci_low": 0.9895443979767569,13153 "ci_high": 0.9943602631191195,13154 "n_items": 12583,13155 "n_groups": 55913156 }13157 }13158 },13159 "by_role": {13160 "abstract": {13161 "n": 1255,13162 "chrf": {13163 "mean": 70.03051234508368,13164 "ci_low": 69.20408118150718,13165 "ci_high": 70.92543747559516,13166 "n_items": 1255,13167 "n_groups": 19513168 },13169 "edit_sim": {13170 "mean": 0.6816216480228036,13171 "ci_low": 0.6718222186567198,13172 "ci_high": 0.6917874491595,13173 "n_items": 1255,13174 "n_groups": 19513175 },13176 "rougeL": {13177 "mean": 0.6844988471393689,13178 "ci_low": 0.6750582351935153,13179 "ci_high": 0.6942838553959576,13180 "n_items": 1255,13181 "n_groups": 19513182 },13183 "exact_match": {13184 "mean": 0.0,13185 "ci_low": 0.0,13186 "ci_high": 0.0,13187 "n_items": 1255,13188 "n_groups": 19513189 },13190 "number_recall": {13191 "mean": 0.9902701425171888,13192 "ci_low": 0.9843273772471174,13193 "ci_high": 0.9947595033662514,13194 "n_items": 1255,13195 "n_groups": 19513196 },13197 "placeholders_exact": {13198 "mean": 1.0,13199 "ci_low": 1.0,13200 "ci_high": 1.0,13201 "n_items": 1255,13202 "n_groups": 19513203 }13204 },13205 "background": {13206 "n": 964,13207 "chrf": {13208 "mean": 69.6697054206268,13209 "ci_low": 68.61855888655221,13210 "ci_high": 70.78896247621672,13211 "n_items": 964,13212 "n_groups": 8413213 },13214 "edit_sim": {13215 "mean": 0.6889673839007938,13216 "ci_low": 0.6768392534924578,13217 "ci_high": 0.7011347411874751,13218 "n_items": 964,13219 "n_groups": 8413220 },13221 "rougeL": {13222 "mean": 0.6957957559047507,13223 "ci_low": 0.68094729518974,13224 "ci_high": 0.7100140545573135,13225 "n_items": 964,13226 "n_groups": 8413227 },13228 "exact_match": {13229 "mean": 0.0,13230 "ci_low": 0.0,13231 "ci_high": 0.0,13232 "n_items": 964,13233 "n_groups": 8413234 },13235 "number_recall": {13236 "mean": 0.9923973358361325,13237 "ci_low": 0.9865950972278322,13238 "ci_high": 0.9969033110186397,13239 "n_items": 964,13240 "n_groups": 8413241 },13242 "placeholders_exact": {13243 "mean": 0.9968879668049793,13244 "ci_low": 0.9930415764121737,13245 "ci_high": 1.0,13246 "n_items": 964,13247 "n_groups": 8413248 }13249 },13250 "chapter": {13251 "n": 1287,13252 "chrf": {13253 "mean": 64.04585752131817,13254 "ci_low": 62.73983675329634,13255 "ci_high": 65.78901114096949,13256 "n_items": 1287,13257 "n_groups": 2113258 },13259 "edit_sim": {13260 "mean": 0.6541622522151266,13261 "ci_low": 0.6418112727885957,13262 "ci_high": 0.6756612876731657,13263 "n_items": 1287,13264 "n_groups": 2113265 },13266 "rougeL": {13267 "mean": 0.6637902888101085,13268 "ci_low": 0.6512151553750746,13269 "ci_high": 0.685303873530972,13270 "n_items": 1287,13271 "n_groups": 2113272 },13273 "exact_match": {13274 "mean": 0.0,13275 "ci_low": 0.0,13276 "ci_high": 0.0,13277 "n_items": 1287,13278 "n_groups": 2113279 },13280 "number_recall": {13281 "mean": 0.9990506407173074,13282 "ci_low": 0.9979934379058845,13283 "ci_high": 0.9998123762527539,13284 "n_items": 1287,13285 "n_groups": 2113286 },13287 "placeholders_exact": {13288 "mean": 1.0,13289 "ci_low": 1.0,13290 "ci_high": 1.0,13291 "n_items": 1287,13292 "n_groups": 2113293 }13294 },13295 "conclusion": {13296 "n": 1168,13297 "chrf": {13298 "mean": 67.2927414027126,13299 "ci_low": 66.37825533948558,13300 "ci_high": 68.21160810133472,13301 "n_items": 1168,13302 "n_groups": 15413303 },13304 "edit_sim": {13305 "mean": 0.6644328050360199,13306 "ci_low": 0.6546386633098972,13307 "ci_high": 0.6742335305487729,13308 "n_items": 1168,13309 "n_groups": 15413310 },13311 "rougeL": {13312 "mean": 0.6634279153810058,13313 "ci_low": 0.6535151400121065,13314 "ci_high": 0.6733484237267938,13315 "n_items": 1168,13316 "n_groups": 15413317 },13318 "exact_match": {13319 "mean": 0.0,13320 "ci_low": 0.0,13321 "ci_high": 0.0,13322 "n_items": 1168,13323 "n_groups": 15413324 },13325 "number_recall": {13326 "mean": 0.994218172428789,13327 "ci_low": 0.9875740374018784,13328 "ci_high": 0.9985368984115306,13329 "n_items": 1168,13330 "n_groups": 15413331 },13332 "placeholders_exact": {13333 "mean": 0.9965753424657534,13334 "ci_low": 0.9905729038657837,13335 "ci_high": 1.0,13336 "n_items": 1168,13337 "n_groups": 15413338 }13339 },13340 "data": {13341 "n": 912,13342 "chrf": {13343 "mean": 70.58472313626125,13344 "ci_low": 69.59242145780652,13345 "ci_high": 71.65009137089042,13346 "n_items": 912,13347 "n_groups": 10413348 },13349 "edit_sim": {13350 "mean": 0.6874831667346286,13351 "ci_low": 0.676247540523934,13352 "ci_high": 0.6984051254914682,13353 "n_items": 912,13354 "n_groups": 10413355 },13356 "rougeL": {13357 "mean": 0.707814807453433,13358 "ci_low": 0.6963550927241802,13359 "ci_high": 0.7191069430827596,13360 "n_items": 912,13361 "n_groups": 10413362 },13363 "exact_match": {13364 "mean": 0.0,13365 "ci_low": 0.0,13366 "ci_high": 0.0,13367 "n_items": 912,13368 "n_groups": 10413369 },13370 "number_recall": {13371 "mean": 0.9795167697730195,13372 "ci_low": 0.9668575325803699,13373 "ci_high": 0.989100494831217,13374 "n_items": 912,13375 "n_groups": 10413376 },13377 "placeholders_exact": {13378 "mean": 0.9923245614035088,13379 "ci_low": 0.9798480576803088,13380 "ci_high": 1.0,13381 "n_items": 912,13382 "n_groups": 10413383 }13384 },13385 "discussion": {13386 "n": 1601,13387 "chrf": {13388 "mean": 69.2230303993805,13389 "ci_low": 68.35183025799103,13390 "ci_high": 70.05853387182295,13391 "n_items": 1601,13392 "n_groups": 14213393 },13394 "edit_sim": {13395 "mean": 0.6824062496857053,13396 "ci_low": 0.6731257545349719,13397 "ci_high": 0.6914237231902459,13398 "n_items": 1601,13399 "n_groups": 14213400 },13401 "rougeL": {13402 "mean": 0.6848226483415021,13403 "ci_low": 0.6751425594962435,13404 "ci_high": 0.694735704571686,13405 "n_items": 1601,13406 "n_groups": 14213407 },13408 "exact_match": {13409 "mean": 0.0,13410 "ci_low": 0.0,13411 "ci_high": 0.0,13412 "n_items": 1601,13413 "n_groups": 14213414 },13415 "number_recall": {13416 "mean": 0.9878077584827962,13417 "ci_low": 0.9815365858800547,13418 "ci_high": 0.9932948119399749,13419 "n_items": 1601,13420 "n_groups": 14213421 },13422 "placeholders_exact": {13423 "mean": 0.9875078076202374,13424 "ci_low": 0.9778222077900948,13425 "ci_high": 0.9953080553250632,13426 "n_items": 1601,13427 "n_groups": 14213428 }13429 },13430 "introduction": {13431 "n": 1789,13432 "chrf": {13433 "mean": 69.04854227863508,13434 "ci_low": 68.0659337484909,13435 "ci_high": 70.01155570301367,13436 "n_items": 1789,13437 "n_groups": 17613438 },13439 "edit_sim": {13440 "mean": 0.6812439149363115,13441 "ci_low": 0.6713018195023658,13442 "ci_high": 0.6917340136543128,13443 "n_items": 1789,13444 "n_groups": 17613445 },13446 "rougeL": {13447 "mean": 0.6817082611085785,13448 "ci_low": 0.6717607678287918,13449 "ci_high": 0.6915733595564653,13450 "n_items": 1789,13451 "n_groups": 17613452 },13453 "exact_match": {13454 "mean": 0.0,13455 "ci_low": 0.0,13456 "ci_high": 0.0,13457 "n_items": 1789,13458 "n_groups": 17613459 },13460 "number_recall": {13461 "mean": 0.9930699408969392,13462 "ci_low": 0.9888368023321128,13463 "ci_high": 0.9967889580091073,13464 "n_items": 1789,13465 "n_groups": 17613466 },13467 "placeholders_exact": {13468 "mean": 0.9877026271660145,13469 "ci_low": 0.9805556246770604,13470 "ci_high": 0.9938201528274179,13471 "n_items": 1789,13472 "n_groups": 17613473 }13474 },13475 "limitations": {13476 "n": 425,13477 "chrf": {13478 "mean": 68.09320989885988,13479 "ci_low": 66.45422702752508,13480 "ci_high": 69.80535013196338,13481 "n_items": 425,13482 "n_groups": 4113483 },13484 "edit_sim": {13485 "mean": 0.6688153025903621,13486 "ci_low": 0.6521050609941119,13487 "ci_high": 0.6868999369257631,13488 "n_items": 425,13489 "n_groups": 4113490 },13491 "rougeL": {13492 "mean": 0.6721845069148102,13493 "ci_low": 0.6516306636770557,13494 "ci_high": 0.6939731287250888,13495 "n_items": 425,13496 "n_groups": 4113497 },13498 "exact_match": {13499 "mean": 0.0,13500 "ci_low": 0.0,13501 "ci_high": 0.0,13502 "n_items": 425,13503 "n_groups": 4113504 },13505 "number_recall": {13506 "mean": 0.9944741532976826,13507 "ci_low": 0.9881170859687216,13508 "ci_high": 0.9996922342446211,13509 "n_items": 425,13510 "n_groups": 4113511 },13512 "placeholders_exact": {13513 "mean": 0.9905882352941177,13514 "ci_low": 0.9684189695875572,13515 "ci_high": 1.0,13516 "n_items": 425,13517 "n_groups": 4113518 }13519 },13520 "methods": {13521 "n": 1528,13522 "chrf": {13523 "mean": 71.19806570925685,13524 "ci_low": 70.33254256067126,13525 "ci_high": 72.10592219825334,13526 "n_items": 1528,13527 "n_groups": 15113528 },13529 "edit_sim": {13530 "mean": 0.6986324001702081,13531 "ci_low": 0.6897496727788776,13532 "ci_high": 0.707696646875918,13533 "n_items": 1528,13534 "n_groups": 15113535 },13536 "rougeL": {13537 "mean": 0.7169297726768844,13538 "ci_low": 0.7071866024896676,13539 "ci_high": 0.7268412740014967,13540 "n_items": 1528,13541 "n_groups": 15113542 },13543 "exact_match": {13544 "mean": 0.0,13545 "ci_low": 0.0,13546 "ci_high": 0.0,13547 "n_items": 1528,13548 "n_groups": 15113549 },13550 "number_recall": {13551 "mean": 0.9867317352673778,13552 "ci_low": 0.9808530439237672,13553 "ci_high": 0.9913697675049653,13554 "n_items": 1528,13555 "n_groups": 15113556 },13557 "placeholders_exact": {13558 "mean": 0.9914921465968587,13559 "ci_low": 0.9820681395829032,13560 "ci_high": 0.9982057416267942,13561 "n_items": 1528,13562 "n_groups": 15113563 }13564 },13565 "other": {13566 "n": 1387,13567 "chrf": {13568 "mean": 70.00390453647921,13569 "ci_low": 68.95110423109044,13570 "ci_high": 71.08496187953315,13571 "n_items": 1387,13572 "n_groups": 11913573 },13574 "edit_sim": {13575 "mean": 0.6915011469123719,13576 "ci_low": 0.6811407441068057,13577 "ci_high": 0.7023241668784171,13578 "n_items": 1387,13579 "n_groups": 11913580 },13581 "rougeL": {13582 "mean": 0.6997392174449943,13583 "ci_low": 0.6887492968806863,13584 "ci_high": 0.7105408139757757,13585 "n_items": 1387,13586 "n_groups": 11913587 },13588 "exact_match": {13589 "mean": 0.0,13590 "ci_low": 0.0,13591 "ci_high": 0.0,13592 "n_items": 1387,13593 "n_groups": 11913594 },13595 "number_recall": {13596 "mean": 0.9893961501928336,13597 "ci_low": 0.9834144658896664,13598 "ci_high": 0.9942656904762154,13599 "n_items": 1387,13600 "n_groups": 11913601 },13602 "placeholders_exact": {13603 "mean": 0.9841384282624369,13604 "ci_low": 0.9737695991430462,13605 "ci_high": 0.9930992820547871,13606 "n_items": 1387,13607 "n_groups": 11913608 }13609 },13610 "preface": {13611 "n": 362,13612 "chrf": {13613 "mean": 63.442122795820325,13614 "ci_low": 58.9961632747837,13615 "ci_high": 68.09478131562992,13616 "n_items": 362,13617 "n_groups": 1313618 },13619 "edit_sim": {13620 "mean": 0.6526347170214746,13621 "ci_low": 0.6053874994426491,13622 "ci_high": 0.7038404145124173,13623 "n_items": 362,13624 "n_groups": 1313625 },13626 "rougeL": {13627 "mean": 0.6581187363147728,13628 "ci_low": 0.6048399728042396,13629 "ci_high": 0.7182961868790358,13630 "n_items": 362,13631 "n_groups": 1313632 },13633 "exact_match": {13634 "mean": 0.0,13635 "ci_low": 0.0,13636 "ci_high": 0.0,13637 "n_items": 362,13638 "n_groups": 1313639 },13640 "number_recall": {13641 "mean": 1.0,13642 "ci_low": 1.0,13643 "ci_high": 1.0,13644 "n_items": 362,13645 "n_groups": 1313646 },13647 "placeholders_exact": {13648 "mean": 1.0,13649 "ci_low": 1.0,13650 "ci_high": 1.0,13651 "n_items": 362,13652 "n_groups": 1313653 }13654 },13655 "related_work": {13656 "n": 557,13657 "chrf": {13658 "mean": 71.10866064457892,13659 "ci_low": 69.5388244556588,13660 "ci_high": 72.75747230983387,13661 "n_items": 557,13662 "n_groups": 3913663 },13664 "edit_sim": {13665 "mean": 0.6957123170320094,13666 "ci_low": 0.6785049101063415,13667 "ci_high": 0.7152968375914832,13668 "n_items": 557,13669 "n_groups": 3913670 },13671 "rougeL": {13672 "mean": 0.7016872222700189,13673 "ci_low": 0.6828571990106774,13674 "ci_high": 0.7215008569077297,13675 "n_items": 557,13676 "n_groups": 3913677 },13678 "exact_match": {13679 "mean": 0.0,13680 "ci_low": 0.0,13681 "ci_high": 0.0,13682 "n_items": 557,13683 "n_groups": 3913684 },13685 "number_recall": {13686 "mean": 0.9860079530424867,13687 "ci_low": 0.9725527196493272,13688 "ci_high": 0.9953889168557211,13689 "n_items": 557,13690 "n_groups": 3913691 },13692 "placeholders_exact": {13693 "mean": 0.992818671454219,13694 "ci_low": 0.9829217956827064,13695 "ci_high": 1.0,13696 "n_items": 557,13697 "n_groups": 3913698 }13699 },13700 "results": {13701 "n": 1501,13702 "chrf": {13703 "mean": 70.45184721476919,13704 "ci_low": 69.26635933914335,13705 "ci_high": 71.71295571108368,13706 "n_items": 1501,13707 "n_groups": 15313708 },13709 "edit_sim": {13710 "mean": 0.6911995799731305,13711 "ci_low": 0.6805241323202067,13712 "ci_high": 0.7025795850063186,13713 "n_items": 1501,13714 "n_groups": 15313715 },13716 "rougeL": {13717 "mean": 0.7130323910522897,13718 "ci_low": 0.7013331972085043,13719 "ci_high": 0.725353042114894,13720 "n_items": 1501,13721 "n_groups": 15313722 },13723 "exact_match": {13724 "mean": 0.0,13725 "ci_low": 0.0,13726 "ci_high": 0.0,13727 "n_items": 1501,13728 "n_groups": 15313729 },13730 "number_recall": {13731 "mean": 0.9693125250137559,13732 "ci_low": 0.957469712785767,13733 "ci_high": 0.9795668075178428,13734 "n_items": 1501,13735 "n_groups": 15313736 },13737 "placeholders_exact": {13738 "mean": 0.9993337774816788,13739 "ci_low": 0.9979422807687413,13740 "ci_high": 1.0,13741 "n_items": 1501,13742 "n_groups": 15313743 }13744 },13745 "theory": {13746 "n": 913,13747 "chrf": {13748 "mean": 70.66764372875566,13749 "ci_low": 69.46876294785785,13750 "ci_high": 71.84189420763846,13751 "n_items": 913,13752 "n_groups": 7913753 },13754 "edit_sim": {13755 "mean": 0.7011617837677278,13756 "ci_low": 0.6866425209754269,13757 "ci_high": 0.7145508614282657,13758 "n_items": 913,13759 "n_groups": 7913760 },13761 "rougeL": {13762 "mean": 0.7142477782237437,13763 "ci_low": 0.6993492859764443,13764 "ci_high": 0.7289111121831072,13765 "n_items": 913,13766 "n_groups": 7913767 },13768 "exact_match": {13769 "mean": 0.0,13770 "ci_low": 0.0,13771 "ci_high": 0.0,13772 "n_items": 913,13773 "n_groups": 7913774 },13775 "number_recall": {13776 "mean": 0.9901054327806792,13777 "ci_low": 0.9853607435535127,13778 "ci_high": 0.9945203268097342,13779 "n_items": 913,13780 "n_groups": 7913781 },13782 "placeholders_exact": {13783 "mean": 0.9912376779846659,13784 "ci_low": 0.9808768519644504,13785 "ci_high": 1.0,13786 "n_items": 913,13787 "n_groups": 7913788 }13789 }13790 }13791 },13792 "htr-m3light-tiny": {13793 "overall": {13794 "n": 15649,13795 "chrf": {13796 "mean": 69.00428001334986,13797 "ci_low": 68.45207032766994,13798 "ci_high": 69.54652007189968,13799 "n_items": 15649,13800 "n_groups": 65213801 },13802 "edit_sim": {13803 "mean": 0.6817086827704703,13804 "ci_low": 0.6767708919210578,13805 "ci_high": 0.6865945556916252,13806 "n_items": 15649,13807 "n_groups": 65213808 },13809 "rougeL": {13810 "mean": 0.6902458173274331,13811 "ci_low": 0.6848490303393244,13812 "ci_high": 0.6956135132210121,13813 "n_items": 15649,13814 "n_groups": 65213815 },13816 "exact_match": {13817 "mean": 0.0,13818 "ci_low": 0.0,13819 "ci_high": 0.0,13820 "n_items": 15649,13821 "n_groups": 65213822 },13823 "number_recall": {13824 "mean": 0.9886487225816375,13825 "ci_low": 0.9865371659648432,13826 "ci_high": 0.9904979182713185,13827 "n_items": 15649,13828 "n_groups": 65213829 },13830 "placeholders_exact": {13831 "mean": 0.9925873857754489,13832 "ci_low": 0.9900598533508731,13833 "ci_high": 0.9947780720930952,13834 "n_items": 15649,13835 "n_groups": 65213836 }13837 },13838 "by_variant": {13839 "A": {13840 "n": 2664,13841 "chrf": {13842 "mean": 68.4860751931019,13843 "ci_low": 67.86619839260922,13844 "ci_high": 69.09011619180012,13845 "n_items": 2664,13846 "n_groups": 63013847 },13848 "edit_sim": {13849 "mean": 0.6733362971268871,13850 "ci_low": 0.667670631461884,13851 "ci_high": 0.6794861401197461,13852 "n_items": 2664,13853 "n_groups": 63013854 },13855 "rougeL": {13856 "mean": 0.6792107387465998,13857 "ci_low": 0.6733698669410515,13858 "ci_high": 0.6853976879482463,13859 "n_items": 2664,13860 "n_groups": 63013861 },13862 "exact_match": {13863 "mean": 0.0,13864 "ci_low": 0.0,13865 "ci_high": 0.0,13866 "n_items": 2664,13867 "n_groups": 63013868 },13869 "number_recall": {13870 "mean": 0.9873913470369213,13871 "ci_low": 0.9843978338743828,13872 "ci_high": 0.9903504539716762,13873 "n_items": 2664,13874 "n_groups": 63013875 },13876 "placeholders_exact": {13877 "mean": 0.9894894894894894,13878 "ci_low": 0.9850308735701994,13879 "ci_high": 0.9932559196641059,13880 "n_items": 2664,13881 "n_groups": 63013882 }13883 },13884 "B": {13885 "n": 2539,13886 "chrf": {13887 "mean": 74.55440070025287,13888 "ci_low": 73.94378963782457,13889 "ci_high": 75.13713604837879,13890 "n_items": 2539,13891 "n_groups": 61413892 },13893 "edit_sim": {13894 "mean": 0.7478521783314667,13895 "ci_low": 0.742107808560772,13896 "ci_high": 0.7535420312344927,13897 "n_items": 2539,13898 "n_groups": 61413899 },13900 "rougeL": {13901 "mean": 0.7550452749657507,13902 "ci_low": 0.7490592868568502,13903 "ci_high": 0.7609609623810473,13904 "n_items": 2539,13905 "n_groups": 61413906 },13907 "exact_match": {13908 "mean": 0.0,13909 "ci_low": 0.0,13910 "ci_high": 0.0,13911 "n_items": 2539,13912 "n_groups": 61413913 },13914 "number_recall": {13915 "mean": 0.9900396059692813,13916 "ci_low": 0.9872875648921324,13917 "ci_high": 0.992431745058921,13918 "n_items": 2539,13919 "n_groups": 61413920 },13921 "placeholders_exact": {13922 "mean": 0.9925167388735723,13923 "ci_low": 0.9890329674323931,13924 "ci_high": 0.9956352624581408,13925 "n_items": 2539,13926 "n_groups": 61413927 }13928 },13929 "C": {13930 "n": 2663,13931 "chrf": {13932 "mean": 71.35097079455022,13933 "ci_low": 70.80985946441731,13934 "ci_high": 71.92581881891661,13935 "n_items": 2663,13936 "n_groups": 63813937 },13938 "edit_sim": {13939 "mean": 0.7233333379143608,13940 "ci_low": 0.7180590578206922,13941 "ci_high": 0.728911549507664,13942 "n_items": 2663,13943 "n_groups": 63813944 },13945 "rougeL": {13946 "mean": 0.7425550282041817,13947 "ci_low": 0.7370000130237032,13948 "ci_high": 0.7484484986998632,13949 "n_items": 2663,13950 "n_groups": 63813951 },13952 "exact_match": {13953 "mean": 0.0,13954 "ci_low": 0.0,13955 "ci_high": 0.0,13956 "n_items": 2663,13957 "n_groups": 63813958 },13959 "number_recall": {13960 "mean": 0.9896439793104208,13961 "ci_low": 0.9865865731444098,13962 "ci_high": 0.9920918786909341,13963 "n_items": 2663,13964 "n_groups": 63813965 },13966 "placeholders_exact": {13967 "mean": 0.9958693203154337,13968 "ci_low": 0.993293871677211,13969 "ci_high": 0.9981139370555406,13970 "n_items": 2663,13971 "n_groups": 63813972 }13973 },13974 "D": {13975 "n": 2708,13976 "chrf": {13977 "mean": 69.7036712452992,13978 "ci_low": 69.09761158975479,13979 "ci_high": 70.32156315242693,13980 "n_items": 2708,13981 "n_groups": 63813982 },13983 "edit_sim": {13984 "mean": 0.6934018461443816,13985 "ci_low": 0.6880185740741447,13986 "ci_high": 0.6987371867213941,13987 "n_items": 2708,13988 "n_groups": 63813989 },13990 "rougeL": {13991 "mean": 0.6978095063716374,13992 "ci_low": 0.6923565025952292,13993 "ci_high": 0.7034437105527946,13994 "n_items": 2708,13995 "n_groups": 63813996 },13997 "exact_match": {13998 "mean": 0.0,13999 "ci_low": 0.0,14000 "ci_high": 0.0,14001 "n_items": 2708,14002 "n_groups": 63814003 },14004 "number_recall": {14005 "mean": 0.9881792105303884,14006 "ci_low": 0.9853479141371472,14007 "ci_high": 0.9907405331428066,14008 "n_items": 2708,14009 "n_groups": 63814010 },14011 "placeholders_exact": {14012 "mean": 0.9933530280649926,14013 "ci_low": 0.9899999038091574,14014 "ci_high": 0.9963018869142946,14015 "n_items": 2708,14016 "n_groups": 63814017 }14018 },14019 "E": {14020 "n": 5075,14021 "chrf": {14022 "mean": 64.89502921741648,14023 "ci_low": 64.27575286613867,14024 "ci_high": 65.49706884412986,14025 "n_items": 5075,14026 "n_groups": 62314027 },14028 "edit_sim": {14029 "mean": 0.6249311767725202,14030 "ci_low": 0.6194959670172826,14031 "ci_high": 0.6305923875877006,14032 "n_items": 5075,14033 "n_groups": 62314034 },14035 "rougeL": {14036 "mean": 0.6321354188839182,14037 "ci_low": 0.6259137761457658,14038 "ci_high": 0.6384356346518114,14039 "n_items": 5075,14040 "n_groups": 62314041 },14042 "exact_match": {14043 "mean": 0.0,14044 "ci_low": 0.0,14045 "ci_high": 0.0,14046 "n_items": 5075,14047 "n_groups": 62314048 },14049 "number_recall": {14050 "mean": 0.9883411886892095,14051 "ci_low": 0.9859915096633058,14052 "ci_high": 0.9905028438322326,14053 "n_items": 5075,14054 "n_groups": 62314055 },14056 "placeholders_exact": {14057 "mean": 0.9921182266009853,14058 "ci_low": 0.9886456887045977,14059 "ci_high": 0.9950080785810024,14060 "n_items": 5075,14061 "n_groups": 62314062 }14063 }14064 },14065 "by_discipline": {14066 "biomedicine": {14067 "n": 2154,14068 "chrf": {14069 "mean": 69.40040517519239,14070 "ci_low": 68.25100107308297,14071 "ci_high": 70.50340545739628,14072 "n_items": 2154,14073 "n_groups": 24414074 },14075 "edit_sim": {14076 "mean": 0.6799088503142311,14077 "ci_low": 0.6713221518243256,14078 "ci_high": 0.6887163751851806,14079 "n_items": 2154,14080 "n_groups": 24414081 },14082 "rougeL": {14083 "mean": 0.6898124550681332,14084 "ci_low": 0.6804998943766962,14085 "ci_high": 0.6994832484594834,14086 "n_items": 2154,14087 "n_groups": 24414088 },14089 "exact_match": {14090 "mean": 0.0,14091 "ci_low": 0.0,14092 "ci_high": 0.0,14093 "n_items": 2154,14094 "n_groups": 24414095 },14096 "number_recall": {14097 "mean": 0.9888589384411112,14098 "ci_low": 0.9835928008797111,14099 "ci_high": 0.9932982306052753,14100 "n_items": 2154,14101 "n_groups": 24414102 },14103 "placeholders_exact": {14104 "mean": 0.9939647168059424,14105 "ci_low": 0.9871719448390929,14106 "ci_high": 0.9986731681364435,14107 "n_items": 2154,14108 "n_groups": 24414109 }14110 },14111 "chemistry": {14112 "n": 837,14113 "chrf": {14114 "mean": 72.1532163078208,14115 "ci_low": 70.63463043420421,14116 "ci_high": 73.58187466492723,14117 "n_items": 837,14118 "n_groups": 1314119 },14120 "edit_sim": {14121 "mean": 0.695130681218159,14122 "ci_low": 0.6790925181580079,14123 "ci_high": 0.7123089941066039,14124 "n_items": 837,14125 "n_groups": 1314126 },14127 "rougeL": {14128 "mean": 0.7104892162513907,14129 "ci_low": 0.6943524184916894,14130 "ci_high": 0.7267354801818643,14131 "n_items": 837,14132 "n_groups": 1314133 },14134 "exact_match": {14135 "mean": 0.0,14136 "ci_low": 0.0,14137 "ci_high": 0.0,14138 "n_items": 837,14139 "n_groups": 1314140 },14141 "number_recall": {14142 "mean": 0.9788230204799695,14143 "ci_low": 0.9675263813515728,14144 "ci_high": 0.9883195880672783,14145 "n_items": 837,14146 "n_groups": 1314147 },14148 "placeholders_exact": {14149 "mean": 0.989247311827957,14150 "ci_low": 0.9777441709884594,14151 "ci_high": 0.9973383888539579,14152 "n_items": 837,14153 "n_groups": 1314154 }14155 },14156 "computer_science": {14157 "n": 1375,14158 "chrf": {14159 "mean": 69.09329619447628,14160 "ci_low": 67.61103039850993,14161 "ci_high": 70.46453439698735,14162 "n_items": 1375,14163 "n_groups": 2014164 },14165 "edit_sim": {14166 "mean": 0.6879452310517015,14167 "ci_low": 0.6721137239821525,14168 "ci_high": 0.7017084854312745,14169 "n_items": 1375,14170 "n_groups": 2014171 },14172 "rougeL": {14173 "mean": 0.692648264894515,14174 "ci_low": 0.6753604279943708,14175 "ci_high": 0.7068942370581479,14176 "n_items": 1375,14177 "n_groups": 2014178 },14179 "exact_match": {14180 "mean": 0.0,14181 "ci_low": 0.0,14182 "ci_high": 0.0,14183 "n_items": 1375,14184 "n_groups": 2014185 },14186 "number_recall": {14187 "mean": 0.9891208972845337,14188 "ci_low": 0.9798980394023682,14189 "ci_high": 0.9963727546001606,14190 "n_items": 1375,14191 "n_groups": 2014192 },14193 "placeholders_exact": {14194 "mean": 0.9898181818181818,14195 "ci_low": 0.9790112876885649,14196 "ci_high": 1.0,14197 "n_items": 1375,14198 "n_groups": 2014199 }14200 },14201 "economics": {14202 "n": 1944,14203 "chrf": {14204 "mean": 68.34937795353574,14205 "ci_low": 67.52712628855475,14206 "ci_high": 69.12945719550892,14207 "n_items": 1944,14208 "n_groups": 10314209 },14210 "edit_sim": {14211 "mean": 0.6783036025022522,14212 "ci_low": 0.6695385874102909,14213 "ci_high": 0.6870815415064208,14214 "n_items": 1944,14215 "n_groups": 10314216 },14217 "rougeL": {14218 "mean": 0.6824864467902342,14219 "ci_low": 0.6726037759184595,14220 "ci_high": 0.6922635979311381,14221 "n_items": 1944,14222 "n_groups": 10314223 },14224 "exact_match": {14225 "mean": 0.0,14226 "ci_low": 0.0,14227 "ci_high": 0.0,14228 "n_items": 1944,14229 "n_groups": 10314230 },14231 "number_recall": {14232 "mean": 0.9890117978158102,14233 "ci_low": 0.9842831459500162,14234 "ci_high": 0.9931803706717729,14235 "n_items": 1944,14236 "n_groups": 10314237 },14238 "placeholders_exact": {14239 "mean": 0.9984567901234568,14240 "ci_low": 0.9965052631364052,14241 "ci_high": 1.0,14242 "n_items": 1944,14243 "n_groups": 10314244 }14245 },14246 "engineering": {14247 "n": 1296,14248 "chrf": {14249 "mean": 66.50072179747521,14250 "ci_low": 64.88646263799119,14251 "ci_high": 68.09671319668423,14252 "n_items": 1296,14253 "n_groups": 1714254 },14255 "edit_sim": {14256 "mean": 0.6572987920003389,14257 "ci_low": 0.6431737209740053,14258 "ci_high": 0.671056591035541,14259 "n_items": 1296,14260 "n_groups": 1714261 },14262 "rougeL": {14263 "mean": 0.6661320316126792,14264 "ci_low": 0.6527458411453485,14265 "ci_high": 0.6797729039712626,14266 "n_items": 1296,14267 "n_groups": 1714268 },14269 "exact_match": {14270 "mean": 0.0,14271 "ci_low": 0.0,14272 "ci_high": 0.0,14273 "n_items": 1296,14274 "n_groups": 1714275 },14276 "number_recall": {14277 "mean": 0.9905763421114299,14278 "ci_low": 0.9868635956231437,14279 "ci_high": 0.9939287074312276,14280 "n_items": 1296,14281 "n_groups": 1714282 },14283 "placeholders_exact": {14284 "mean": 0.9907407407407407,14285 "ci_low": 0.9825145711906744,14286 "ci_high": 0.9973948503979315,14287 "n_items": 1296,14288 "n_groups": 1714289 }14290 },14291 "finance": {14292 "n": 2043,14293 "chrf": {14294 "mean": 67.793042352459,14295 "ci_low": 66.44207914014741,14296 "ci_high": 69.27476314836292,14297 "n_items": 2043,14298 "n_groups": 5114299 },14300 "edit_sim": {14301 "mean": 0.6711733750760602,14302 "ci_low": 0.6576727469105312,14303 "ci_high": 0.685886212131818,14304 "n_items": 2043,14305 "n_groups": 5114306 },14307 "rougeL": {14308 "mean": 0.6786389413314902,14309 "ci_low": 0.6645116234191053,14310 "ci_high": 0.6945292868730987,14311 "n_items": 2043,14312 "n_groups": 5114313 },14314 "exact_match": {14315 "mean": 0.0,14316 "ci_low": 0.0,14317 "ci_high": 0.0,14318 "n_items": 2043,14319 "n_groups": 5114320 },14321 "number_recall": {14322 "mean": 0.9914038292158702,14323 "ci_low": 0.9878884988192208,14324 "ci_high": 0.9947233894945893,14325 "n_items": 2043,14326 "n_groups": 5114327 },14328 "placeholders_exact": {14329 "mean": 0.9970631424375918,14330 "ci_low": 0.9923122261218905,14331 "ci_high": 1.0,14332 "n_items": 2043,14333 "n_groups": 5114334 }14335 },14336 "general_reference": {14337 "n": 118,14338 "chrf": {14339 "mean": 73.80589568361161,14340 "ci_low": 60.662158704838994,14341 "ci_high": 75.15712098049478,14342 "n_items": 118,14343 "n_groups": 214344 },14345 "edit_sim": {14346 "mean": 0.7706210653060238,14347 "ci_low": 0.6031126454693507,14348 "ci_high": 0.7878415570649342,14349 "n_items": 118,14350 "n_groups": 214351 },14352 "rougeL": {14353 "mean": 0.7992572725235481,14354 "ci_low": 0.6174889690415608,14355 "ci_high": 0.8179437336291732,14356 "n_items": 118,14357 "n_groups": 214358 },14359 "exact_match": {14360 "mean": 0.0,14361 "ci_low": 0.0,14362 "ci_high": 0.0,14363 "n_items": 118,14364 "n_groups": 214365 },14366 "number_recall": {14367 "mean": 1.0,14368 "ci_low": 1.0,14369 "ci_high": 1.0,14370 "n_items": 118,14371 "n_groups": 214372 },14373 "placeholders_exact": {14374 "mean": 1.0,14375 "ci_low": 1.0,14376 "ci_high": 1.0,14377 "n_items": 118,14378 "n_groups": 214379 }14380 },14381 "humanities": {14382 "n": 263,14383 "chrf": {14384 "mean": 63.0102896830317,14385 "ci_low": 60.092261847895685,14386 "ci_high": 63.39178149385393,14387 "n_items": 263,14388 "n_groups": 314389 },14390 "edit_sim": {14391 "mean": 0.6516062483221596,14392 "ci_low": 0.6232590049310679,14393 "ci_high": 0.6552752614188093,14394 "n_items": 263,14395 "n_groups": 314396 },14397 "rougeL": {14398 "mean": 0.657673962438395,14399 "ci_low": 0.6271799999197479,14400 "ci_high": 0.6600340460928229,14401 "n_items": 263,14402 "n_groups": 314403 },14404 "exact_match": {14405 "mean": 0.0,14406 "ci_low": 0.0,14407 "ci_high": 0.0,14408 "n_items": 263,14409 "n_groups": 314410 },14411 "number_recall": {14412 "mean": 1.0,14413 "ci_low": 1.0,14414 "ci_high": 1.0,14415 "n_items": 263,14416 "n_groups": 314417 },14418 "placeholders_exact": {14419 "mean": 1.0,14420 "ci_low": 1.0,14421 "ci_high": 1.0,14422 "n_items": 263,14423 "n_groups": 314424 }14425 },14426 "life_sciences": {14427 "n": 1874,14428 "chrf": {14429 "mean": 71.54186535827012,14430 "ci_low": 69.69691871738748,14431 "ci_high": 73.11403586434557,14432 "n_items": 1874,14433 "n_groups": 14314434 },14435 "edit_sim": {14436 "mean": 0.7039948316184165,14437 "ci_low": 0.6903174194478927,14438 "ci_high": 0.7173504675619121,14439 "n_items": 1874,14440 "n_groups": 14314441 },14442 "rougeL": {14443 "mean": 0.7144047753233723,14444 "ci_low": 0.7003404114367451,14445 "ci_high": 0.7279670308385423,14446 "n_items": 1874,14447 "n_groups": 14314448 },14449 "exact_match": {14450 "mean": 0.0,14451 "ci_low": 0.0,14452 "ci_high": 0.0,14453 "n_items": 1874,14454 "n_groups": 14314455 },14456 "number_recall": {14457 "mean": 0.9821789065539087,14458 "ci_low": 0.9740648253074756,14459 "ci_high": 0.9885364477999595,14460 "n_items": 1874,14461 "n_groups": 14314462 },14463 "placeholders_exact": {14464 "mean": 0.9797225186766275,14465 "ci_low": 0.9661119568386833,14466 "ci_high": 0.9908364867012296,14467 "n_items": 1874,14468 "n_groups": 14314469 }14470 },14471 "mathematics": {14472 "n": 712,14473 "chrf": {14474 "mean": 68.30536055220873,14475 "ci_low": 65.44611166232245,14476 "ci_high": 71.46815740063383,14477 "n_items": 712,14478 "n_groups": 514479 },14480 "edit_sim": {14481 "mean": 0.6900209754388676,14482 "ci_low": 0.6651252663311856,14483 "ci_high": 0.709655810357057,14484 "n_items": 712,14485 "n_groups": 514486 },14487 "rougeL": {14488 "mean": 0.6898618039947446,14489 "ci_low": 0.6650894475680467,14490 "ci_high": 0.7212809634575075,14491 "n_items": 712,14492 "n_groups": 514493 },14494 "exact_match": {14495 "mean": 0.0,14496 "ci_low": 0.0,14497 "ci_high": 0.0,14498 "n_items": 712,14499 "n_groups": 514500 },14501 "number_recall": {14502 "mean": 0.9926199736592995,14503 "ci_low": 0.9863760721679978,14504 "ci_high": 0.9983861996898806,14505 "n_items": 712,14506 "n_groups": 514507 },14508 "placeholders_exact": {14509 "mean": 0.9915730337078652,14510 "ci_low": 0.967741935483871,14511 "ci_high": 1.0,14512 "n_items": 712,14513 "n_groups": 514514 }14515 },14516 "other": {14517 "n": 669,14518 "chrf": {14519 "mean": 68.87569681271958,14520 "ci_low": 66.44762054564487,14521 "ci_high": 72.05803242269073,14522 "n_items": 669,14523 "n_groups": 1314524 },14525 "edit_sim": {14526 "mean": 0.6717190450909535,14527 "ci_low": 0.6496074174530638,14528 "ci_high": 0.7007413700472371,14529 "n_items": 669,14530 "n_groups": 1314531 },14532 "rougeL": {14533 "mean": 0.6810217242039058,14534 "ci_low": 0.6580564506461841,14535 "ci_high": 0.7112055481931391,14536 "n_items": 669,14537 "n_groups": 1314538 },14539 "exact_match": {14540 "mean": 0.0,14541 "ci_low": 0.0,14542 "ci_high": 0.0,14543 "n_items": 669,14544 "n_groups": 1314545 },14546 "number_recall": {14547 "mean": 0.9860992478705484,14548 "ci_low": 0.966386133799584,14549 "ci_high": 0.9981441449144386,14550 "n_items": 669,14551 "n_groups": 1314552 },14553 "placeholders_exact": {14554 "mean": 0.9985052316890882,14555 "ci_low": 0.993403267136451,14556 "ci_high": 1.0,14557 "n_items": 669,14558 "n_groups": 1314559 }14560 },14561 "social_sciences": {14562 "n": 1536,14563 "chrf": {14564 "mean": 68.41767040409208,14565 "ci_low": 66.28429148818405,14566 "ci_high": 69.95419710956946,14567 "n_items": 1536,14568 "n_groups": 2914569 },14570 "edit_sim": {14571 "mean": 0.6773583632508634,14572 "ci_low": 0.6593255812976803,14573 "ci_high": 0.693051711076456,14574 "n_items": 1536,14575 "n_groups": 2914576 },14577 "rougeL": {14578 "mean": 0.6841327370638112,14579 "ci_low": 0.6644401958621446,14580 "ci_high": 0.701272732174074,14581 "n_items": 1536,14582 "n_groups": 2914583 },14584 "exact_match": {14585 "mean": 0.0,14586 "ci_low": 0.0,14587 "ci_high": 0.0,14588 "n_items": 1536,14589 "n_groups": 2914590 },14591 "number_recall": {14592 "mean": 0.9926544621740326,14593 "ci_low": 0.9899460883968874,14594 "ci_high": 0.9957727170150751,14595 "n_items": 1536,14596 "n_groups": 2914597 },14598 "placeholders_exact": {14599 "mean": 0.9973958333333334,14600 "ci_low": 0.9943740813821237,14601 "ci_high": 1.0,14602 "n_items": 1536,14603 "n_groups": 2914604 }14605 },14606 "statistics": {14607 "n": 828,14608 "chrf": {14609 "mean": 70.35701928375867,14610 "ci_low": 67.60091821490064,14611 "ci_high": 73.17038554275824,14612 "n_items": 828,14613 "n_groups": 914614 },14615 "edit_sim": {14616 "mean": 0.6901066813356761,14617 "ci_low": 0.6674707768735959,14618 "ci_high": 0.7150391703165595,14619 "n_items": 828,14620 "n_groups": 914621 },14622 "rougeL": {14623 "mean": 0.7107749093425406,14624 "ci_low": 0.6851043791027966,14625 "ci_high": 0.7361001640782798,14626 "n_items": 828,14627 "n_groups": 914628 },14629 "exact_match": {14630 "mean": 0.0,14631 "ci_low": 0.0,14632 "ci_high": 0.0,14633 "n_items": 828,14634 "n_groups": 914635 },14636 "number_recall": {14637 "mean": 0.9872166233084476,14638 "ci_low": 0.9702107831533662,14639 "ci_high": 0.9972312686059662,14640 "n_items": 828,14641 "n_groups": 914642 },14643 "placeholders_exact": {14644 "mean": 0.9879227053140096,14645 "ci_low": 0.9814590417212798,14646 "ci_high": 0.9952324195470799,14647 "n_items": 828,14648 "n_groups": 914649 }14650 }14651 },14652 "by_era": {14653 "1900-1949": {14654 "n": 1164,14655 "chrf": {14656 "mean": 63.69311301305732,14657 "ci_low": 61.551109229180895,14658 "ci_high": 66.64860790876905,14659 "n_items": 1164,14660 "n_groups": 1814661 },14662 "edit_sim": {14663 "mean": 0.654201029447764,14664 "ci_low": 0.6304960479129473,14665 "ci_high": 0.6901073032558063,14666 "n_items": 1164,14667 "n_groups": 1814668 },14669 "rougeL": {14670 "mean": 0.6622245751411177,14671 "ci_low": 0.6365793772626963,14672 "ci_high": 0.7021298900922642,14673 "n_items": 1164,14674 "n_groups": 1814675 },14676 "exact_match": {14677 "mean": 0.0,14678 "ci_low": 0.0,14679 "ci_high": 0.0,14680 "n_items": 1164,14681 "n_groups": 1814682 },14683 "number_recall": {14684 "mean": 0.9981743986254296,14685 "ci_low": 0.9952811544935681,14686 "ci_high": 1.0,14687 "n_items": 1164,14688 "n_groups": 1814689 },14690 "placeholders_exact": {14691 "mean": 1.0,14692 "ci_low": 1.0,14693 "ci_high": 1.0,14694 "n_items": 1164,14695 "n_groups": 1814696 }14697 },14698 "1950-1979": {14699 "n": 206,14700 "chrf": {14701 "mean": 62.44629091889063,14702 "ci_low": 60.040957795161674,14703 "ci_high": 63.025889261957836,14704 "n_items": 206,14705 "n_groups": 214706 },14707 "edit_sim": {14708 "mean": 0.6461269541518403,14709 "ci_low": 0.6081614789939188,14710 "ci_high": 0.6552752614188093,14711 "n_items": 206,14712 "n_groups": 214713 },14714 "rougeL": {14715 "mean": 0.650988495541077,14716 "ci_low": 0.6134494607513314,14717 "ci_high": 0.6600340460928229,14718 "n_items": 206,14719 "n_groups": 214720 },14721 "exact_match": {14722 "mean": 0.0,14723 "ci_low": 0.0,14724 "ci_high": 0.0,14725 "n_items": 206,14726 "n_groups": 214727 },14728 "number_recall": {14729 "mean": 1.0,14730 "ci_low": 1.0,14731 "ci_high": 1.0,14732 "n_items": 206,14733 "n_groups": 214734 },14735 "placeholders_exact": {14736 "mean": 1.0,14737 "ci_low": 1.0,14738 "ci_high": 1.0,14739 "n_items": 206,14740 "n_groups": 214741 }14742 },14743 "1980-1999": {14744 "n": 151,14745 "chrf": {14746 "mean": 63.65491113626487,14747 "ci_low": 62.31561386004004,14748 "ci_high": 77.00069127878137,14749 "n_items": 151,14750 "n_groups": 414751 },14752 "edit_sim": {14753 "mean": 0.6594922456871021,14754 "ci_low": 0.6475754415122409,14755 "ci_high": 0.7879048592819179,14756 "n_items": 151,14757 "n_groups": 414758 },14759 "rougeL": {14760 "mean": 0.6605295315415333,14761 "ci_low": 0.6501191266437478,14762 "ci_high": 0.7673564919140851,14763 "n_items": 151,14764 "n_groups": 414765 },14766 "exact_match": {14767 "mean": 0.0,14768 "ci_low": 0.0,14769 "ci_high": 0.0,14770 "n_items": 151,14771 "n_groups": 414772 },14773 "number_recall": {14774 "mean": 0.9990539262062441,14775 "ci_low": 0.9989547038327525,14776 "ci_high": 1.0,14777 "n_items": 151,14778 "n_groups": 414779 },14780 "placeholders_exact": {14781 "mean": 1.0,14782 "ci_low": 1.0,14783 "ci_high": 1.0,14784 "n_items": 151,14785 "n_groups": 414786 }14787 },14788 "2000-2009": {14789 "n": 1545,14790 "chrf": {14791 "mean": 69.50148195139043,14792 "ci_low": 68.1256184004381,14793 "ci_high": 70.92027623507035,14794 "n_items": 1545,14795 "n_groups": 6914796 },14797 "edit_sim": {14798 "mean": 0.6900505650756307,14799 "ci_low": 0.677142140517218,14800 "ci_high": 0.704025307865969,14801 "n_items": 1545,14802 "n_groups": 6914803 },14804 "rougeL": {14805 "mean": 0.7001790835404281,14806 "ci_low": 0.6871395621516846,14807 "ci_high": 0.7134817643710544,14808 "n_items": 1545,14809 "n_groups": 6914810 },14811 "exact_match": {14812 "mean": 0.0,14813 "ci_low": 0.0,14814 "ci_high": 0.0,14815 "n_items": 1545,14816 "n_groups": 6914817 },14818 "number_recall": {14819 "mean": 0.9854047642397157,14820 "ci_low": 0.9752541430635152,14821 "ci_high": 0.9938142490423888,14822 "n_items": 1545,14823 "n_groups": 6914824 },14825 "placeholders_exact": {14826 "mean": 0.9889967637540453,14827 "ci_low": 0.9793962358617236,14828 "ci_high": 0.9974717938266455,14829 "n_items": 1545,14830 "n_groups": 6914831 }14832 },14833 "2010-2017": {14834 "n": 12583,14835 "chrf": {14836 "mean": 69.60610166541741,14837 "ci_low": 69.11897418177597,14838 "ci_high": 70.1020905896794,14839 "n_items": 12583,14840 "n_groups": 55914841 },14842 "edit_sim": {14843 "mean": 0.6840781668681564,14844 "ci_low": 0.6789796380060913,14845 "ci_high": 0.6887837760902209,14846 "n_items": 12583,14847 "n_groups": 55914848 },14849 "rougeL": {14850 "mean": 0.6926175885304412,14851 "ci_low": 0.6870493264215292,14852 "ci_high": 0.6979394496096971,14853 "n_items": 12583,14854 "n_groups": 55914855 },14856 "exact_match": {14857 "mean": 0.0,14858 "ci_low": 0.0,14859 "ci_high": 0.0,14860 "n_items": 12583,14861 "n_groups": 55914862 },14863 "number_recall": {14864 "mean": 0.9878551502878916,14865 "ci_low": 0.9856047198888765,14866 "ci_high": 0.9897746206693789,14867 "n_items": 12583,14868 "n_groups": 55914869 },14870 "placeholders_exact": {14871 "mean": 0.9921322419136931,14872 "ci_low": 0.989208340214793,14873 "ci_high": 0.9945121689186223,14874 "n_items": 12583,14875 "n_groups": 55914876 }14877 }14878 },14879 "by_role": {14880 "abstract": {14881 "n": 1255,14882 "chrf": {14883 "mean": 70.05531011948007,14884 "ci_low": 69.20882315078916,14885 "ci_high": 70.97458614955093,14886 "n_items": 1255,14887 "n_groups": 19514888 },14889 "edit_sim": {14890 "mean": 0.6821190295108054,14891 "ci_low": 0.6724585603019997,14892 "ci_high": 0.6921788744592868,14893 "n_items": 1255,14894 "n_groups": 19514895 },14896 "rougeL": {14897 "mean": 0.6849014061058792,14898 "ci_low": 0.6754987529796334,14899 "ci_high": 0.694706027126149,14900 "n_items": 1255,14901 "n_groups": 19514902 },14903 "exact_match": {14904 "mean": 0.0,14905 "ci_low": 0.0,14906 "ci_high": 0.0,14907 "n_items": 1255,14908 "n_groups": 19514909 },14910 "number_recall": {14911 "mean": 0.9909891155233922,14912 "ci_low": 0.985674623350656,14913 "ci_high": 0.9953245022187918,14914 "n_items": 1255,14915 "n_groups": 19514916 },14917 "placeholders_exact": {14918 "mean": 0.998406374501992,14919 "ci_low": 0.9949788690653639,14920 "ci_high": 1.0,14921 "n_items": 1255,14922 "n_groups": 19514923 }14924 },14925 "background": {14926 "n": 964,14927 "chrf": {14928 "mean": 69.40454933252487,14929 "ci_low": 68.30047461774322,14930 "ci_high": 70.5351342274151,14931 "n_items": 964,14932 "n_groups": 8414933 },14934 "edit_sim": {14935 "mean": 0.6874877853066053,14936 "ci_low": 0.6748644092059694,14937 "ci_high": 0.7000378840985297,14938 "n_items": 964,14939 "n_groups": 8414940 },14941 "rougeL": {14942 "mean": 0.6941178861692631,14943 "ci_low": 0.6786351449656707,14944 "ci_high": 0.7085995424078382,14945 "n_items": 964,14946 "n_groups": 8414947 },14948 "exact_match": {14949 "mean": 0.0,14950 "ci_low": 0.0,14951 "ci_high": 0.0,14952 "n_items": 964,14953 "n_groups": 8414954 },14955 "number_recall": {14956 "mean": 0.9928941908713694,14957 "ci_low": 0.9887288554773596,14958 "ci_high": 0.9964922996411483,14959 "n_items": 964,14960 "n_groups": 8414961 },14962 "placeholders_exact": {14963 "mean": 0.991701244813278,14964 "ci_low": 0.9793806028686687,14965 "ci_high": 0.9990283468599794,14966 "n_items": 964,14967 "n_groups": 8414968 }14969 },14970 "chapter": {14971 "n": 1287,14972 "chrf": {14973 "mean": 63.88157935333338,14974 "ci_low": 62.634752668568495,14975 "ci_high": 65.57056183061086,14976 "n_items": 1287,14977 "n_groups": 2114978 },14979 "edit_sim": {14980 "mean": 0.6528066036054404,14981 "ci_low": 0.6410704166987493,14982 "ci_high": 0.6741328921886347,14983 "n_items": 1287,14984 "n_groups": 2114985 },14986 "rougeL": {14987 "mean": 0.6620087510407923,14988 "ci_low": 0.6501735723765533,14989 "ci_high": 0.6828043919973346,14990 "n_items": 1287,14991 "n_groups": 2114992 },14993 "exact_match": {14994 "mean": 0.0,14995 "ci_low": 0.0,14996 "ci_high": 0.0,14997 "n_items": 1287,14998 "n_groups": 2114999 },15000 "number_recall": {15001 "mean": 0.9961227044560379,15002 "ci_low": 0.9919980699855698,15003 "ci_high": 0.9998712766480502,15004 "n_items": 1287,15005 "n_groups": 2115006 },15007 "placeholders_exact": {15008 "mean": 1.0,15009 "ci_low": 1.0,15010 "ci_high": 1.0,15011 "n_items": 1287,15012 "n_groups": 2115013 }15014 },15015 "conclusion": {15016 "n": 1168,15017 "chrf": {15018 "mean": 67.20246865886801,15019 "ci_low": 66.29181937899423,15020 "ci_high": 68.1181925024204,15021 "n_items": 1168,15022 "n_groups": 15415023 },15024 "edit_sim": {15025 "mean": 0.6638731041888202,15026 "ci_low": 0.654116770161933,15027 "ci_high": 0.6736929342236314,15028 "n_items": 1168,15029 "n_groups": 15415030 },15031 "rougeL": {15032 "mean": 0.6629196076996011,15033 "ci_low": 0.6528896226870718,15034 "ci_high": 0.6729141735999749,15035 "n_items": 1168,15036 "n_groups": 15415037 },15038 "exact_match": {15039 "mean": 0.0,15040 "ci_low": 0.0,15041 "ci_high": 0.0,15042 "n_items": 1168,15043 "n_groups": 15415044 },15045 "number_recall": {15046 "mean": 0.9915637230919766,15047 "ci_low": 0.9844885590741488,15048 "ci_high": 0.9968875863169563,15049 "n_items": 1168,15050 "n_groups": 15415051 },15052 "placeholders_exact": {15053 "mean": 0.9982876712328768,15054 "ci_low": 0.9955631467347886,15055 "ci_high": 1.0,15056 "n_items": 1168,15057 "n_groups": 15415058 }15059 },15060 "data": {15061 "n": 912,15062 "chrf": {15063 "mean": 70.34318492007442,15064 "ci_low": 69.31777991369488,15065 "ci_high": 71.44054447697167,15066 "n_items": 912,15067 "n_groups": 10415068 },15069 "edit_sim": {15070 "mean": 0.6845889730548074,15071 "ci_low": 0.6732357545086691,15072 "ci_high": 0.6955751509239797,15073 "n_items": 912,15074 "n_groups": 10415075 },15076 "rougeL": {15077 "mean": 0.7054856282337714,15078 "ci_low": 0.6940117918693116,15079 "ci_high": 0.7166985389824972,15080 "n_items": 912,15081 "n_groups": 10415082 },15083 "exact_match": {15084 "mean": 0.0,15085 "ci_low": 0.0,15086 "ci_high": 0.0,15087 "n_items": 912,15088 "n_groups": 10415089 },15090 "number_recall": {15091 "mean": 0.9784349029302793,15092 "ci_low": 0.9674538014211116,15093 "ci_high": 0.9873595430420192,15094 "n_items": 912,15095 "n_groups": 10415096 },15097 "placeholders_exact": {15098 "mean": 0.9923245614035088,15099 "ci_low": 0.9788147172205144,15100 "ci_high": 1.0,15101 "n_items": 912,15102 "n_groups": 10415103 }15104 },15105 "discussion": {15106 "n": 1601,15107 "chrf": {15108 "mean": 69.07052830586277,15109 "ci_low": 68.1860719807976,15110 "ci_high": 69.93243652680175,15111 "n_items": 1601,15112 "n_groups": 14215113 },15114 "edit_sim": {15115 "mean": 0.681058414840427,15116 "ci_low": 0.6721528230243852,15117 "ci_high": 0.6899717894282288,15118 "n_items": 1601,15119 "n_groups": 14215120 },15121 "rougeL": {15122 "mean": 0.6825021294255772,15123 "ci_low": 0.6724971496259922,15124 "ci_high": 0.6920858527876416,15125 "n_items": 1601,15126 "n_groups": 14215127 },15128 "exact_match": {15129 "mean": 0.0,15130 "ci_low": 0.0,15131 "ci_high": 0.0,15132 "n_items": 1601,15133 "n_groups": 14215134 },15135 "number_recall": {15136 "mean": 0.9906859312157472,15137 "ci_low": 0.9854912885103307,15138 "ci_high": 0.9950515368850106,15139 "n_items": 1601,15140 "n_groups": 14215141 },15142 "placeholders_exact": {15143 "mean": 0.9893816364772018,15144 "ci_low": 0.977748815041217,15145 "ci_high": 0.9968212152102793,15146 "n_items": 1601,15147 "n_groups": 14215148 }15149 },15150 "introduction": {15151 "n": 1789,15152 "chrf": {15153 "mean": 68.8898175742862,15154 "ci_low": 67.87853886689325,15155 "ci_high": 69.88538374466883,15156 "n_items": 1789,15157 "n_groups": 17615158 },15159 "edit_sim": {15160 "mean": 0.6800708522143127,15161 "ci_low": 0.669935087922874,15162 "ci_high": 0.690571972328051,15163 "n_items": 1789,15164 "n_groups": 17615165 },15166 "rougeL": {15167 "mean": 0.6806845130301861,15168 "ci_low": 0.6700512230461305,15169 "ci_high": 0.6912658652030238,15170 "n_items": 1789,15171 "n_groups": 17615172 },15173 "exact_match": {15174 "mean": 0.0,15175 "ci_low": 0.0,15176 "ci_high": 0.0,15177 "n_items": 1789,15178 "n_groups": 17615179 },15180 "number_recall": {15181 "mean": 0.9935530643817396,15182 "ci_low": 0.9897820933064446,15183 "ci_high": 0.9968400196373627,15184 "n_items": 1789,15185 "n_groups": 17615186 },15187 "placeholders_exact": {15188 "mean": 0.9910564561207379,15189 "ci_low": 0.9822935442499316,15190 "ci_high": 0.9969204205298596,15191 "n_items": 1789,15192 "n_groups": 17615193 }15194 },15195 "limitations": {15196 "n": 425,15197 "chrf": {15198 "mean": 67.86161840575065,15199 "ci_low": 66.13621854985259,15200 "ci_high": 69.68730176066215,15201 "n_items": 425,15202 "n_groups": 4115203 },15204 "edit_sim": {15205 "mean": 0.6673324124049423,15206 "ci_low": 0.6494506797651252,15207 "ci_high": 0.6865856877804472,15208 "n_items": 425,15209 "n_groups": 4115210 },15211 "rougeL": {15212 "mean": 0.670370860082697,15213 "ci_low": 0.6480411079057987,15214 "ci_high": 0.6944692479619042,15215 "n_items": 425,15216 "n_groups": 4115217 },15218 "exact_match": {15219 "mean": 0.0,15220 "ci_low": 0.0,15221 "ci_high": 0.0,15222 "n_items": 425,15223 "n_groups": 4115224 },15225 "number_recall": {15226 "mean": 0.9913986928104574,15227 "ci_low": 0.9805753223733311,15228 "ci_high": 0.9991268867315808,15229 "n_items": 425,15230 "n_groups": 4115231 },15232 "placeholders_exact": {15233 "mean": 0.9952941176470588,15234 "ci_low": 0.9842094847937786,15235 "ci_high": 1.0,15236 "n_items": 425,15237 "n_groups": 4115238 }15239 },15240 "methods": {15241 "n": 1528,15242 "chrf": {15243 "mean": 70.97325960214766,15244 "ci_low": 70.14122744713686,15245 "ci_high": 71.85956062003424,15246 "n_items": 1528,15247 "n_groups": 15115248 },15249 "edit_sim": {15250 "mean": 0.694754965405896,15251 "ci_low": 0.6859592914562346,15252 "ci_high": 0.7037279357144701,15253 "n_items": 1528,15254 "n_groups": 15115255 },15256 "rougeL": {15257 "mean": 0.714237301413421,15258 "ci_low": 0.7050183460119371,15259 "ci_high": 0.724005436684415,15260 "n_items": 1528,15261 "n_groups": 15115262 },15263 "exact_match": {15264 "mean": 0.0,15265 "ci_low": 0.0,15266 "ci_high": 0.0,15267 "n_items": 1528,15268 "n_groups": 15115269 },15270 "number_recall": {15271 "mean": 0.9891257786047969,15272 "ci_low": 0.9840617841356452,15273 "ci_high": 0.9931218307473046,15274 "n_items": 1528,15275 "n_groups": 15115276 },15277 "placeholders_exact": {15278 "mean": 0.9908376963350786,15279 "ci_low": 0.9825975260711474,15280 "ci_high": 0.9971235832137003,15281 "n_items": 1528,15282 "n_groups": 15115283 }15284 },15285 "other": {15286 "n": 1387,15287 "chrf": {15288 "mean": 69.78934886835026,15289 "ci_low": 68.76775069442972,15290 "ci_high": 70.83884401744065,15291 "n_items": 1387,15292 "n_groups": 11915293 },15294 "edit_sim": {15295 "mean": 0.6903162509873807,15296 "ci_low": 0.6805418190487424,15297 "ci_high": 0.700550960365901,15298 "n_items": 1387,15299 "n_groups": 11915300 },15301 "rougeL": {15302 "mean": 0.69808809629485,15303 "ci_low": 0.6874025088632851,15304 "ci_high": 0.7084816001903074,15305 "n_items": 1387,15306 "n_groups": 11915307 },15308 "exact_match": {15309 "mean": 0.0,15310 "ci_low": 0.0,15311 "ci_high": 0.0,15312 "n_items": 1387,15313 "n_groups": 11915314 },15315 "number_recall": {15316 "mean": 0.9914949786254762,15317 "ci_low": 0.9863991431217555,15318 "ci_high": 0.9956439557646692,15319 "n_items": 1387,15320 "n_groups": 11915321 },15322 "placeholders_exact": {15323 "mean": 0.9826964671953857,15324 "ci_low": 0.9701790586230921,15325 "ci_high": 0.9936442919126963,15326 "n_items": 1387,15327 "n_groups": 11915328 }15329 },15330 "preface": {15331 "n": 362,15332 "chrf": {15333 "mean": 63.047740328517655,15334 "ci_low": 58.69328876656696,15335 "ci_high": 67.6830803216547,15336 "n_items": 362,15337 "n_groups": 1315338 },15339 "edit_sim": {15340 "mean": 0.6499477876823915,15341 "ci_low": 0.6036030247646972,15342 "ci_high": 0.7001735323537868,15343 "n_items": 362,15344 "n_groups": 1315345 },15346 "rougeL": {15347 "mean": 0.6540428191716317,15348 "ci_low": 0.6007080776551993,15349 "ci_high": 0.7141579720052492,15350 "n_items": 362,15351 "n_groups": 1315352 },15353 "exact_match": {15354 "mean": 0.0,15355 "ci_low": 0.0,15356 "ci_high": 0.0,15357 "n_items": 362,15358 "n_groups": 1315359 },15360 "number_recall": {15361 "mean": 1.0,15362 "ci_low": 1.0,15363 "ci_high": 1.0,15364 "n_items": 362,15365 "n_groups": 1315366 },15367 "placeholders_exact": {15368 "mean": 1.0,15369 "ci_low": 1.0,15370 "ci_high": 1.0,15371 "n_items": 362,15372 "n_groups": 1315373 }15374 },15375 "related_work": {15376 "n": 557,15377 "chrf": {15378 "mean": 70.77398336915817,15379 "ci_low": 69.16846956413376,15380 "ci_high": 72.42337667502832,15381 "n_items": 557,15382 "n_groups": 3915383 },15384 "edit_sim": {15385 "mean": 0.6922246300643571,15386 "ci_low": 0.6745837650804684,15387 "ci_high": 0.7117791651934413,15388 "n_items": 557,15389 "n_groups": 3915390 },15391 "rougeL": {15392 "mean": 0.6990359680943715,15393 "ci_low": 0.6804307319841376,15394 "ci_high": 0.7190215444997249,15395 "n_items": 557,15396 "n_groups": 3915397 },15398 "exact_match": {15399 "mean": 0.0,15400 "ci_low": 0.0,15401 "ci_high": 0.0,15402 "n_items": 557,15403 "n_groups": 3915404 },15405 "number_recall": {15406 "mean": 0.9900713987787596,15407 "ci_low": 0.9816200621724628,15408 "ci_high": 0.9964725467262646,15409 "n_items": 557,15410 "n_groups": 3915411 },15412 "placeholders_exact": {15413 "mean": 0.9856373429084381,15414 "ci_low": 0.9579142960250001,15415 "ci_high": 1.0,15416 "n_items": 557,15417 "n_groups": 3915418 }15419 },15420 "results": {15421 "n": 1501,15422 "chrf": {15423 "mean": 70.33104263630635,15424 "ci_low": 69.09693776725045,15425 "ci_high": 71.60620292141596,15426 "n_items": 1501,15427 "n_groups": 15315428 },15429 "edit_sim": {15430 "mean": 0.6914743240221288,15431 "ci_low": 0.6805684937742924,15432 "ci_high": 0.7028962671889726,15433 "n_items": 1501,15434 "n_groups": 15315435 },15436 "rougeL": {15437 "mean": 0.7129653669361562,15438 "ci_low": 0.7011859715642065,15439 "ci_high": 0.7250790296069457,15440 "n_items": 1501,15441 "n_groups": 15315442 },15443 "exact_match": {15444 "mean": 0.0,15445 "ci_low": 0.0,15446 "ci_high": 0.0,15447 "n_items": 1501,15448 "n_groups": 15315449 },15450 "number_recall": {15451 "mean": 0.9652008799901597,15452 "ci_low": 0.9545623844773848,15453 "ci_high": 0.9751671624409517,15454 "n_items": 1501,15455 "n_groups": 15315456 },15457 "placeholders_exact": {15458 "mean": 0.9940039973351099,15459 "ci_low": 0.9876880541663379,15460 "ci_high": 0.9987155196812343,15461 "n_items": 1501,15462 "n_groups": 15315463 }15464 },15465 "theory": {15466 "n": 913,15467 "chrf": {15468 "mean": 70.57861658088977,15469 "ci_low": 69.3468575636357,15470 "ci_high": 71.79490526944554,15471 "n_items": 913,15472 "n_groups": 7915473 },15474 "edit_sim": {15475 "mean": 0.7019776384423987,15476 "ci_low": 0.6872635781717827,15477 "ci_high": 0.7157928250360587,15478 "n_items": 913,15479 "n_groups": 7915480 },15481 "rougeL": {15482 "mean": 0.7141831061096261,15483 "ci_low": 0.699264773715217,15484 "ci_high": 0.7287568228217484,15485 "n_items": 913,15486 "n_groups": 7915487 },15488 "exact_match": {15489 "mean": 0.0,15490 "ci_low": 0.0,15491 "ci_high": 0.0,15492 "n_items": 913,15493 "n_groups": 7915494 },15495 "number_recall": {15496 "mean": 0.9904824441105932,15497 "ci_low": 0.9863302938894363,15498 "ci_high": 0.9944580755937391,15499 "n_items": 913,15500 "n_groups": 7915501 },15502 "placeholders_exact": {15503 "mean": 0.9923329682365827,15504 "ci_low": 0.9829308683425857,15505 "ci_high": 0.9989452584831401,15506 "n_items": 913,15507 "n_groups": 7915508 }15509 }15510 }15511 },15512 "htr-m3tokenonly-tiny-s2": {15513 "overall": {15514 "n": 15649,15515 "chrf": {15516 "mean": 69.2335278140233,15517 "ci_low": 68.69206590055704,15518 "ci_high": 69.76692031026671,15519 "n_items": 15649,15520 "n_groups": 65215521 },15522 "edit_sim": {15523 "mean": 0.6844252709778453,15524 "ci_low": 0.6795679685362034,15525 "ci_high": 0.6893164833653483,15526 "n_items": 15649,15527 "n_groups": 65215528 },15529 "rougeL": {15530 "mean": 0.693422008878853,15531 "ci_low": 0.6881089415755971,15532 "ci_high": 0.6987203301933703,15533 "n_items": 15649,15534 "n_groups": 65215535 },15536 "exact_match": {15537 "mean": 0.0,15538 "ci_low": 0.0,15539 "ci_high": 0.0,15540 "n_items": 15649,15541 "n_groups": 65215542 },15543 "number_recall": {15544 "mean": 0.9911714765353429,15545 "ci_low": 0.9891375667708869,15546 "ci_high": 0.9929668195366234,15547 "n_items": 15649,15548 "n_groups": 65215549 },15550 "placeholders_exact": {15551 "mean": 0.9925234839286855,15552 "ci_low": 0.9899739208740059,15553 "ci_high": 0.9947627316655633,15554 "n_items": 15649,15555 "n_groups": 65215556 }15557 },15558 "by_variant": {15559 "A": {15560 "n": 2664,15561 "chrf": {15562 "mean": 68.72857170081193,15563 "ci_low": 68.1102006278688,15564 "ci_high": 69.35234020139843,15565 "n_items": 2664,15566 "n_groups": 63015567 },15568 "edit_sim": {15569 "mean": 0.6763480318929661,15570 "ci_low": 0.6705845509974978,15571 "ci_high": 0.6826603997851247,15572 "n_items": 2664,15573 "n_groups": 63015574 },15575 "rougeL": {15576 "mean": 0.6821493195488619,15577 "ci_low": 0.6763529442326316,15578 "ci_high": 0.6883882298639993,15579 "n_items": 2664,15580 "n_groups": 63015581 },15582 "exact_match": {15583 "mean": 0.0,15584 "ci_low": 0.0,15585 "ci_high": 0.0,15586 "n_items": 2664,15587 "n_groups": 63015588 },15589 "number_recall": {15590 "mean": 0.9911508790638591,15591 "ci_low": 0.9888211654981994,15592 "ci_high": 0.993400224667362,15593 "n_items": 2664,15594 "n_groups": 63015595 },15596 "placeholders_exact": {15597 "mean": 0.9928678678678678,15598 "ci_low": 0.9895442095039156,15599 "ci_high": 0.9957774322343432,15600 "n_items": 2664,15601 "n_groups": 63015602 }15603 },15604 "B": {15605 "n": 2539,15606 "chrf": {15607 "mean": 74.85144838644533,15608 "ci_low": 74.25604038044597,15609 "ci_high": 75.42031229757904,15610 "n_items": 2539,15611 "n_groups": 61415612 },15613 "edit_sim": {15614 "mean": 0.7514553886838022,15615 "ci_low": 0.7458590096530733,15616 "ci_high": 0.7572311532153125,15617 "n_items": 2539,15618 "n_groups": 61415619 },15620 "rougeL": {15621 "mean": 0.7589709032659554,15622 "ci_low": 0.7530992640263865,15623 "ci_high": 0.7649134612856257,15624 "n_items": 2539,15625 "n_groups": 61415626 },15627 "exact_match": {15628 "mean": 0.0,15629 "ci_low": 0.0,15630 "ci_high": 0.0,15631 "n_items": 2539,15632 "n_groups": 61415633 },15634 "number_recall": {15635 "mean": 0.9913849062645052,15636 "ci_low": 0.9886653310089979,15637 "ci_high": 0.9937731850185606,15638 "n_items": 2539,15639 "n_groups": 61415640 },15641 "placeholders_exact": {15642 "mean": 0.9913351713272942,15643 "ci_low": 0.9877172049433359,15644 "ci_high": 0.9946931346462857,15645 "n_items": 2539,15646 "n_groups": 61415647 }15648 },15649 "C": {15650 "n": 2663,15651 "chrf": {15652 "mean": 71.60915765517072,15653 "ci_low": 71.07646895176707,15654 "ci_high": 72.1933557100887,15655 "n_items": 2663,15656 "n_groups": 63815657 },15658 "edit_sim": {15659 "mean": 0.7263531875753687,15660 "ci_low": 0.7211153603757005,15661 "ci_high": 0.731849453496296,15662 "n_items": 2663,15663 "n_groups": 63815664 },15665 "rougeL": {15666 "mean": 0.7461529825173642,15667 "ci_low": 0.7405975553624119,15668 "ci_high": 0.7520734645004591,15669 "n_items": 2663,15670 "n_groups": 63815671 },15672 "exact_match": {15673 "mean": 0.0,15674 "ci_low": 0.0,15675 "ci_high": 0.0,15676 "n_items": 2663,15677 "n_groups": 63815678 },15679 "number_recall": {15680 "mean": 0.9922388759139256,15681 "ci_low": 0.9901198243768055,15682 "ci_high": 0.9941369313142565,15683 "n_items": 2663,15684 "n_groups": 63815685 },15686 "placeholders_exact": {15687 "mean": 0.9928651896357491,15688 "ci_low": 0.9892758168208974,15689 "ci_high": 0.9959394985145865,15690 "n_items": 2663,15691 "n_groups": 63815692 }15693 },15694 "D": {15695 "n": 2708,15696 "chrf": {15697 "mean": 69.86043781305222,15698 "ci_low": 69.2657086673119,15699 "ci_high": 70.45636431630726,15700 "n_items": 2708,15701 "n_groups": 63815702 },15703 "edit_sim": {15704 "mean": 0.6955688801769506,15705 "ci_low": 0.6903594745817274,15706 "ci_high": 0.7008293414518895,15707 "n_items": 2708,15708 "n_groups": 63815709 },15710 "rougeL": {15711 "mean": 0.7007691680748251,15712 "ci_low": 0.6954153012846374,15713 "ci_high": 0.7063257293285653,15714 "n_items": 2708,15715 "n_groups": 63815716 },15717 "exact_match": {15718 "mean": 0.0,15719 "ci_low": 0.0,15720 "ci_high": 0.0,15721 "n_items": 2708,15722 "n_groups": 63815723 },15724 "number_recall": {15725 "mean": 0.9902429627714058,15726 "ci_low": 0.9875833059127054,15727 "ci_high": 0.9925614463977516,15728 "n_items": 2708,15729 "n_groups": 63815730 },15731 "placeholders_exact": {15732 "mean": 0.9929837518463811,15733 "ci_low": 0.9897129694761211,15734 "ci_high": 0.9959121151464957,15735 "n_items": 2708,15736 "n_groups": 63815737 }15738 },15739 "E": {15740 "n": 5075,15741 "chrf": {15742 "mean": 65.10689297813558,15743 "ci_low": 64.49060780015859,15744 "ci_high": 65.7169447052277,15745 "n_items": 5075,15746 "n_groups": 62315747 },15748 "edit_sim": {15749 "mean": 0.6271833715603701,15750 "ci_low": 0.6217828727027989,15751 "ci_high": 0.6326755470078542,15752 "n_items": 5075,15753 "n_groups": 62315754 },15755 "rougeL": {15756 "mean": 0.6349556269328817,15757 "ci_low": 0.6287763959461103,15758 "ci_high": 0.6411793985409348,15759 "n_items": 5075,15760 "n_groups": 62315761 },15762 "exact_match": {15763 "mean": 0.0,15764 "ci_low": 0.0,15765 "ci_high": 0.0,15766 "n_items": 5075,15767 "n_groups": 62315768 },15769 "number_recall": {15770 "mean": 0.9910108665470206,15771 "ci_low": 0.9885672222887619,15772 "ci_high": 0.993179316197323,15773 "n_items": 5075,15774 "n_groups": 62315775 },15776 "placeholders_exact": {15777 "mean": 0.992512315270936,15778 "ci_low": 0.9892790907643427,15779 "ci_high": 0.9952900629801384,15780 "n_items": 5075,15781 "n_groups": 62315782 }15783 }15784 },15785 "by_discipline": {15786 "biomedicine": {15787 "n": 2154,15788 "chrf": {15789 "mean": 69.41250681672605,15790 "ci_low": 68.26797023320513,15791 "ci_high": 70.51455632237433,15792 "n_items": 2154,15793 "n_groups": 24415794 },15795 "edit_sim": {15796 "mean": 0.6810634901782376,15797 "ci_low": 0.6725203039511649,15798 "ci_high": 0.6899387113358574,15799 "n_items": 2154,15800 "n_groups": 24415801 },15802 "rougeL": {15803 "mean": 0.69047427458361,15804 "ci_low": 0.6809337643088554,15805 "ci_high": 0.6999933817304116,15806 "n_items": 2154,15807 "n_groups": 24415808 },15809 "exact_match": {15810 "mean": 0.0,15811 "ci_low": 0.0,15812 "ci_high": 0.0,15813 "n_items": 2154,15814 "n_groups": 24415815 },15816 "number_recall": {15817 "mean": 0.9901570806924731,15818 "ci_low": 0.9834993385683404,15819 "ci_high": 0.9949942346036816,15820 "n_items": 2154,15821 "n_groups": 24415822 },15823 "placeholders_exact": {15824 "mean": 0.9925719591457753,15825 "ci_low": 0.9855722026852811,15826 "ci_high": 0.9976518359026717,15827 "n_items": 2154,15828 "n_groups": 24415829 }15830 },15831 "chemistry": {15832 "n": 837,15833 "chrf": {15834 "mean": 72.38281676608833,15835 "ci_low": 70.93477558673287,15836 "ci_high": 73.69594294921691,15837 "n_items": 837,15838 "n_groups": 1315839 },15840 "edit_sim": {15841 "mean": 0.6983910899729505,15842 "ci_low": 0.6834054432679642,15843 "ci_high": 0.7146405743002248,15844 "n_items": 837,15845 "n_groups": 1315846 },15847 "rougeL": {15848 "mean": 0.7143504685467803,15849 "ci_low": 0.6998298531828326,15850 "ci_high": 0.7287904930505352,15851 "n_items": 837,15852 "n_groups": 1315853 },15854 "exact_match": {15855 "mean": 0.0,15856 "ci_low": 0.0,15857 "ci_high": 0.0,15858 "n_items": 837,15859 "n_groups": 1315860 },15861 "number_recall": {15862 "mean": 0.9811893818386865,15863 "ci_low": 0.9723571304877368,15864 "ci_high": 0.9908081673732717,15865 "n_items": 837,15866 "n_groups": 1315867 },15868 "placeholders_exact": {15869 "mean": 0.998805256869773,15870 "ci_low": 0.9958556332075703,15871 "ci_high": 1.0,15872 "n_items": 837,15873 "n_groups": 1315874 }15875 },15876 "computer_science": {15877 "n": 1375,15878 "chrf": {15879 "mean": 69.39358894022432,15880 "ci_low": 67.87287159489404,15881 "ci_high": 70.73640699432973,15882 "n_items": 1375,15883 "n_groups": 2015884 },15885 "edit_sim": {15886 "mean": 0.6905106715564303,15887 "ci_low": 0.674905115081077,15888 "ci_high": 0.7039141370115617,15889 "n_items": 1375,15890 "n_groups": 2015891 },15892 "rougeL": {15893 "mean": 0.6960422728436725,15894 "ci_low": 0.6794615814439419,15895 "ci_high": 0.7100305271041688,15896 "n_items": 1375,15897 "n_groups": 2015898 },15899 "exact_match": {15900 "mean": 0.0,15901 "ci_low": 0.0,15902 "ci_high": 0.0,15903 "n_items": 1375,15904 "n_groups": 2015905 },15906 "number_recall": {15907 "mean": 0.9917445625081988,15908 "ci_low": 0.9838105961622844,15909 "ci_high": 0.9972412125472369,15910 "n_items": 1375,15911 "n_groups": 2015912 },15913 "placeholders_exact": {15914 "mean": 0.9905454545454545,15915 "ci_low": 0.9790791610238582,15916 "ci_high": 0.999185490349398,15917 "n_items": 1375,15918 "n_groups": 2015919 }15920 },15921 "economics": {15922 "n": 1944,15923 "chrf": {15924 "mean": 68.52352524631716,15925 "ci_low": 67.69975255455664,15926 "ci_high": 69.32120149316621,15927 "n_items": 1944,15928 "n_groups": 10315929 },15930 "edit_sim": {15931 "mean": 0.6806605257672685,15932 "ci_low": 0.6715173782211903,15933 "ci_high": 0.6898479706618554,15934 "n_items": 1944,15935 "n_groups": 10315936 },15937 "rougeL": {15938 "mean": 0.6848720043998507,15939 "ci_low": 0.6747048483241912,15940 "ci_high": 0.6953034453965972,15941 "n_items": 1944,15942 "n_groups": 10315943 },15944 "exact_match": {15945 "mean": 0.0,15946 "ci_low": 0.0,15947 "ci_high": 0.0,15948 "n_items": 1944,15949 "n_groups": 10315950 },15951 "number_recall": {15952 "mean": 0.9904291640287011,15953 "ci_low": 0.9859229087077369,15954 "ci_high": 0.9941150245112,15955 "n_items": 1944,15956 "n_groups": 10315957 },15958 "placeholders_exact": {15959 "mean": 0.9974279835390947,15960 "ci_low": 0.9943414618374509,15961 "ci_high": 0.9995119570522206,15962 "n_items": 1944,15963 "n_groups": 10315964 }15965 },15966 "engineering": {15967 "n": 1296,15968 "chrf": {15969 "mean": 66.88436388491039,15970 "ci_low": 65.2964682713486,15971 "ci_high": 68.52825025643695,15972 "n_items": 1296,15973 "n_groups": 1715974 },15975 "edit_sim": {15976 "mean": 0.6603443492028077,15977 "ci_low": 0.6458400752448524,15978 "ci_high": 0.6749780325070248,15979 "n_items": 1296,15980 "n_groups": 1715981 },15982 "rougeL": {15983 "mean": 0.6701583861261686,15984 "ci_low": 0.6558339022272218,15985 "ci_high": 0.6847311961846261,15986 "n_items": 1296,15987 "n_groups": 1715988 },15989 "exact_match": {15990 "mean": 0.0,15991 "ci_low": 0.0,15992 "ci_high": 0.0,15993 "n_items": 1296,15994 "n_groups": 1715995 },15996 "number_recall": {15997 "mean": 0.9915855915977748,15998 "ci_low": 0.9868591776927822,15999 "ci_high": 0.9956657529614179,16000 "n_items": 1296,16001 "n_groups": 1716002 },16003 "placeholders_exact": {16004 "mean": 0.9899691358024691,16005 "ci_low": 0.9815892162972195,16006 "ci_high": 0.9969974452064004,16007 "n_items": 1296,16008 "n_groups": 1716009 }16010 },16011 "finance": {16012 "n": 2043,16013 "chrf": {16014 "mean": 68.16820845867848,16015 "ci_low": 66.85426302292196,16016 "ci_high": 69.59473004483596,16017 "n_items": 2043,16018 "n_groups": 5116019 },16020 "edit_sim": {16021 "mean": 0.6752844654343627,16022 "ci_low": 0.6623727276716109,16023 "ci_high": 0.6896584007081485,16024 "n_items": 2043,16025 "n_groups": 5116026 },16027 "rougeL": {16028 "mean": 0.6835255463253982,16029 "ci_low": 0.670079788272988,16030 "ci_high": 0.6988257456586388,16031 "n_items": 2043,16032 "n_groups": 5116033 },16034 "exact_match": {16035 "mean": 0.0,16036 "ci_low": 0.0,16037 "ci_high": 0.0,16038 "n_items": 2043,16039 "n_groups": 5116040 },16041 "number_recall": {16042 "mean": 0.9922195876674585,16043 "ci_low": 0.9869192425708422,16044 "ci_high": 0.9965329340176822,16045 "n_items": 2043,16046 "n_groups": 5116047 },16048 "placeholders_exact": {16049 "mean": 0.9946157611355849,16050 "ci_low": 0.9893449248461407,16051 "ci_high": 0.9989406919857157,16052 "n_items": 2043,16053 "n_groups": 5116054 }16055 },16056 "general_reference": {16057 "n": 118,16058 "chrf": {16059 "mean": 75.15754176042478,16060 "ci_low": 61.33922976350254,16061 "ci_high": 76.5781158909495,16062 "n_items": 118,16063 "n_groups": 216064 },16065 "edit_sim": {16066 "mean": 0.7866282436132094,16067 "ci_low": 0.6148738709776356,16068 "ci_high": 0.8042852351925671,16069 "n_items": 118,16070 "n_groups": 216071 },16072 "rougeL": {16073 "mean": 0.8145033292010107,16074 "ci_low": 0.6260399555447562,16075 "ci_high": 0.8338780685488498,16076 "n_items": 118,16077 "n_groups": 216078 },16079 "exact_match": {16080 "mean": 0.0,16081 "ci_low": 0.0,16082 "ci_high": 0.0,16083 "n_items": 118,16084 "n_groups": 216085 },16086 "number_recall": {16087 "mean": 1.0,16088 "ci_low": 1.0,16089 "ci_high": 1.0,16090 "n_items": 118,16091 "n_groups": 216092 },16093 "placeholders_exact": {16094 "mean": 1.0,16095 "ci_low": 1.0,16096 "ci_high": 1.0,16097 "n_items": 118,16098 "n_groups": 216099 }16100 },16101 "humanities": {16102 "n": 263,16103 "chrf": {16104 "mean": 63.469276244304346,16105 "ci_low": 59.57361922862734,16106 "ci_high": 64.27380892053496,16107 "n_items": 263,16108 "n_groups": 316109 },16110 "edit_sim": {16111 "mean": 0.6573703715815024,16112 "ci_low": 0.6243540269353786,16113 "ci_high": 0.6597219248686521,16114 "n_items": 263,16115 "n_groups": 316116 },16117 "rougeL": {16118 "mean": 0.6653202259503732,16119 "ci_low": 0.630560838073882,16120 "ci_high": 0.6699938930066149,16121 "n_items": 263,16122 "n_groups": 316123 },16124 "exact_match": {16125 "mean": 0.0,16126 "ci_low": 0.0,16127 "ci_high": 0.0,16128 "n_items": 263,16129 "n_groups": 316130 },16131 "number_recall": {16132 "mean": 1.0,16133 "ci_low": 1.0,16134 "ci_high": 1.0,16135 "n_items": 263,16136 "n_groups": 316137 },16138 "placeholders_exact": {16139 "mean": 1.0,16140 "ci_low": 1.0,16141 "ci_high": 1.0,16142 "n_items": 263,16143 "n_groups": 316144 }16145 },16146 "life_sciences": {16147 "n": 1874,16148 "chrf": {16149 "mean": 71.70447011844372,16150 "ci_low": 69.8826370503714,16151 "ci_high": 73.25871241724495,16152 "n_items": 1874,16153 "n_groups": 14316154 },16155 "edit_sim": {16156 "mean": 0.7057563315569556,16157 "ci_low": 0.6925504693728848,16158 "ci_high": 0.7188386389521123,16159 "n_items": 1874,16160 "n_groups": 14316161 },16162 "rougeL": {16163 "mean": 0.7167002095982484,16164 "ci_low": 0.7029831129185035,16165 "ci_high": 0.730427296857636,16166 "n_items": 1874,16167 "n_groups": 14316168 },16169 "exact_match": {16170 "mean": 0.0,16171 "ci_low": 0.0,16172 "ci_high": 0.0,16173 "n_items": 1874,16174 "n_groups": 14316175 },16176 "number_recall": {16177 "mean": 0.9917568783570755,16178 "ci_low": 0.9877677026560308,16179 "ci_high": 0.9947647582457056,16180 "n_items": 1874,16181 "n_groups": 14316182 },16183 "placeholders_exact": {16184 "mean": 0.9786552828175027,16185 "ci_low": 0.96264135120068,16186 "ci_high": 0.990257281553398,16187 "n_items": 1874,16188 "n_groups": 14316189 }16190 },16191 "mathematics": {16192 "n": 712,16193 "chrf": {16194 "mean": 68.46692269614519,16195 "ci_low": 65.68452096667632,16196 "ci_high": 71.59881577968784,16197 "n_items": 712,16198 "n_groups": 516199 },16200 "edit_sim": {16201 "mean": 0.691809892767415,16202 "ci_low": 0.6683224812619587,16203 "ci_high": 0.712149059466616,16204 "n_items": 712,16205 "n_groups": 516206 },16207 "rougeL": {16208 "mean": 0.6915190709724631,16209 "ci_low": 0.6673781355725305,16210 "ci_high": 0.7241206325291653,16211 "n_items": 712,16212 "n_groups": 516213 },16214 "exact_match": {16215 "mean": 0.0,16216 "ci_low": 0.0,16217 "ci_high": 0.0,16218 "n_items": 712,16219 "n_groups": 516220 },16221 "number_recall": {16222 "mean": 0.9958323901441879,16223 "ci_low": 0.9943582651915985,16224 "ci_high": 0.9977510234863176,16225 "n_items": 712,16226 "n_groups": 516227 },16228 "placeholders_exact": {16229 "mean": 0.9915730337078652,16230 "ci_low": 0.9724770642201835,16231 "ci_high": 0.9988317757009346,16232 "n_items": 712,16233 "n_groups": 516234 }16235 },16236 "other": {16237 "n": 669,16238 "chrf": {16239 "mean": 69.080932388519,16240 "ci_low": 66.73312309869976,16241 "ci_high": 72.1893679022287,16242 "n_items": 669,16243 "n_groups": 1316244 },16245 "edit_sim": {16246 "mean": 0.6746234068700665,16247 "ci_low": 0.6532259690186356,16248 "ci_high": 0.7030685561077213,16249 "n_items": 669,16250 "n_groups": 1316251 },16252 "rougeL": {16253 "mean": 0.6840723176555178,16254 "ci_low": 0.6628621175699178,16255 "ci_high": 0.7125247937825759,16256 "n_items": 669,16257 "n_groups": 1316258 },16259 "exact_match": {16260 "mean": 0.0,16261 "ci_low": 0.0,16262 "ci_high": 0.0,16263 "n_items": 669,16264 "n_groups": 1316265 },16266 "number_recall": {16267 "mean": 0.9898314233516029,16268 "ci_low": 0.9695510027306601,16269 "ci_high": 0.9985585994697808,16270 "n_items": 669,16271 "n_groups": 1316272 },16273 "placeholders_exact": {16274 "mean": 1.0,16275 "ci_low": 1.0,16276 "ci_high": 1.0,16277 "n_items": 669,16278 "n_groups": 1316279 }16280 },16281 "social_sciences": {16282 "n": 1536,16283 "chrf": {16284 "mean": 68.60198914941499,16285 "ci_low": 66.52464493982089,16286 "ci_high": 70.1306125306944,16287 "n_items": 1536,16288 "n_groups": 2916289 },16290 "edit_sim": {16291 "mean": 0.6803142787848712,16292 "ci_low": 0.6628957179620252,16293 "ci_high": 0.6956439093284221,16294 "n_items": 1536,16295 "n_groups": 2916296 },16297 "rougeL": {16298 "mean": 0.687904122532271,16299 "ci_low": 0.6685247782280744,16300 "ci_high": 0.7046525066618279,16301 "n_items": 1536,16302 "n_groups": 2916303 },16304 "exact_match": {16305 "mean": 0.0,16306 "ci_low": 0.0,16307 "ci_high": 0.0,16308 "n_items": 1536,16309 "n_groups": 2916310 },16311 "number_recall": {16312 "mean": 0.995358902224686,16313 "ci_low": 0.9916103814896324,16314 "ci_high": 0.9987471069510089,16315 "n_items": 1536,16316 "n_groups": 2916317 },16318 "placeholders_exact": {16319 "mean": 0.9973958333333334,16320 "ci_low": 0.9943740813821237,16321 "ci_high": 1.0,16322 "n_items": 1536,16323 "n_groups": 2916324 }16325 },16326 "statistics": {16327 "n": 828,16328 "chrf": {16329 "mean": 70.63934958286502,16330 "ci_low": 68.1662534267173,16331 "ci_high": 73.2865286432469,16332 "n_items": 828,16333 "n_groups": 916334 },16335 "edit_sim": {16336 "mean": 0.6929781999759071,16337 "ci_low": 0.6712071329519579,16338 "ci_high": 0.7168652988057482,16339 "n_items": 828,16340 "n_groups": 916341 },16342 "rougeL": {16343 "mean": 0.714900156680517,16344 "ci_low": 0.6911992357919746,16345 "ci_high": 0.7391960023377601,16346 "n_items": 828,16347 "n_groups": 916348 },16349 "exact_match": {16350 "mean": 0.0,16351 "ci_low": 0.0,16352 "ci_high": 0.0,16353 "n_items": 828,16354 "n_groups": 916355 },16356 "number_recall": {16357 "mean": 0.9853773084443821,16358 "ci_low": 0.9689348297109371,16359 "ci_high": 0.9964941698798759,16360 "n_items": 828,16361 "n_groups": 916362 },16363 "placeholders_exact": {16364 "mean": 0.9903381642512077,16365 "ci_low": 0.9808665200860502,16366 "ci_high": 0.9978640350877193,16367 "n_items": 828,16368 "n_groups": 916369 }16370 }16371 },16372 "by_era": {16373 "1900-1949": {16374 "n": 1164,16375 "chrf": {16376 "mean": 64.19012548187334,16377 "ci_low": 61.93371131733902,16378 "ci_high": 67.2873959272385,16379 "n_items": 1164,16380 "n_groups": 1816381 },16382 "edit_sim": {16383 "mean": 0.6600640810405588,16384 "ci_low": 0.6356936243858741,16385 "ci_high": 0.6975953486880805,16386 "n_items": 1164,16387 "n_groups": 1816388 },16389 "rougeL": {16390 "mean": 0.668840561670243,16391 "ci_low": 0.6430030400297003,16392 "ci_high": 0.7111964258832706,16393 "n_items": 1164,16394 "n_groups": 1816395 },16396 "exact_match": {16397 "mean": 0.0,16398 "ci_low": 0.0,16399 "ci_high": 0.0,16400 "n_items": 1164,16401 "n_groups": 1816402 },16403 "number_recall": {16404 "mean": 1.0,16405 "ci_low": 1.0,16406 "ci_high": 1.0,16407 "n_items": 1164,16408 "n_groups": 1816409 },16410 "placeholders_exact": {16411 "mean": 0.9991408934707904,16412 "ci_low": 0.9976945244956772,16413 "ci_high": 1.0,16414 "n_items": 1164,16415 "n_groups": 1816416 }16417 },16418 "1950-1979": {16419 "n": 206,16420 "chrf": {16421 "mean": 62.69964851789864,16422 "ci_low": 60.04662828560195,16423 "ci_high": 63.3389305015846,16424 "n_items": 206,16425 "n_groups": 216426 },16427 "edit_sim": {16428 "mean": 0.6494967916352613,16429 "ci_low": 0.60706248871669,16430 "ci_high": 0.659721924868652,16431 "n_items": 206,16432 "n_groups": 216433 },16434 "rougeL": {16435 "mean": 0.6548426538945041,16436 "ci_low": 0.6108644559942138,16437 "ci_high": 0.665439810015056,16438 "n_items": 206,16439 "n_groups": 216440 },16441 "exact_match": {16442 "mean": 0.0,16443 "ci_low": 0.0,16444 "ci_high": 0.0,16445 "n_items": 206,16446 "n_groups": 216447 },16448 "number_recall": {16449 "mean": 1.0,16450 "ci_low": 1.0,16451 "ci_high": 1.0,16452 "n_items": 206,16453 "n_groups": 216454 },16455 "placeholders_exact": {16456 "mean": 1.0,16457 "ci_low": 1.0,16458 "ci_high": 1.0,16459 "n_items": 206,16460 "n_groups": 216461 }16462 },16463 "1980-1999": {16464 "n": 151,16465 "chrf": {16466 "mean": 64.3230406565896,16467 "ci_low": 62.87508679638751,16468 "ci_high": 79.2200372901965,16469 "n_items": 151,16470 "n_groups": 416471 },16472 "edit_sim": {16473 "mean": 0.6669456475701615,16474 "ci_low": 0.6538580867886228,16475 "ci_high": 0.7995032688420284,16476 "n_items": 151,16477 "n_groups": 416478 },16479 "rougeL": {16480 "mean": 0.667462811449036,16481 "ci_low": 0.6552689741309572,16482 "ci_high": 0.788396543548046,16483 "n_items": 151,16484 "n_groups": 416485 },16486 "exact_match": {16487 "mean": 0.0,16488 "ci_low": 0.0,16489 "ci_high": 0.0,16490 "n_items": 151,16491 "n_groups": 416492 },16493 "number_recall": {16494 "mean": 1.0,16495 "ci_low": 1.0,16496 "ci_high": 1.0,16497 "n_items": 151,16498 "n_groups": 416499 },16500 "placeholders_exact": {16501 "mean": 1.0,16502 "ci_low": 1.0,16503 "ci_high": 1.0,16504 "n_items": 151,16505 "n_groups": 416506 }16507 },16508 "2000-2009": {16509 "n": 1545,16510 "chrf": {16511 "mean": 69.91232702366477,16512 "ci_low": 68.61434344177093,16513 "ci_high": 71.28048916859694,16514 "n_items": 1545,16515 "n_groups": 6916516 },16517 "edit_sim": {16518 "mean": 0.6933796094353935,16519 "ci_low": 0.6807702403081591,16520 "ci_high": 0.706099001634184,16521 "n_items": 1545,16522 "n_groups": 6916523 },16524 "rougeL": {16525 "mean": 0.7039722278509684,16526 "ci_low": 0.6918725173942404,16527 "ci_high": 0.7166732747430621,16528 "n_items": 1545,16529 "n_groups": 6916530 },16531 "exact_match": {16532 "mean": 0.0,16533 "ci_low": 0.0,16534 "ci_high": 0.0,16535 "n_items": 1545,16536 "n_groups": 6916537 },16538 "number_recall": {16539 "mean": 0.9937815098580376,16540 "ci_low": 0.9896077913303613,16541 "ci_high": 0.9969365084073498,16542 "n_items": 1545,16543 "n_groups": 6916544 },16545 "placeholders_exact": {16546 "mean": 0.9896440129449838,16547 "ci_low": 0.9796521743047408,16548 "ci_high": 0.9974983809631647,16549 "n_items": 1545,16550 "n_groups": 6916551 }16552 },16553 "2010-2017": {16554 "n": 12583,16555 "chrf": {16556 "mean": 69.78262089448907,16557 "ci_low": 69.30286520168102,16558 "ci_high": 70.28017675542822,16559 "n_items": 12583,16560 "n_groups": 55916561 },16562 "edit_sim": {16563 "mean": 0.6863609510262616,16564 "ci_low": 0.6813747341902251,16565 "ci_high": 0.6910984328218327,16566 "n_items": 12583,16567 "n_groups": 55916568 },16569 "rougeL": {16570 "mean": 0.6953436414130326,16571 "ci_low": 0.6898495752146193,16572 "ci_high": 0.7005500229388323,16573 "n_items": 12583,16574 "n_groups": 55916575 },16576 "exact_match": {16577 "mean": 0.0,16578 "ci_low": 0.0,16579 "ci_high": 0.0,16580 "n_items": 12583,16581 "n_groups": 55916582 },16583 "number_recall": {16584 "mean": 0.9897838356171749,16585 "ci_low": 0.9872831027680129,16586 "ci_high": 0.991890089971453,16587 "n_items": 12583,16588 "n_groups": 55916589 },16590 "placeholders_exact": {16591 "mean": 0.9920527696097909,16592 "ci_low": 0.98916791398992,16593 "ci_high": 0.9945005016011,16594 "n_items": 12583,16595 "n_groups": 55916596 }16597 }16598 },16599 "by_role": {16600 "abstract": {16601 "n": 1255,16602 "chrf": {16603 "mean": 69.9860656560198,16604 "ci_low": 69.14426608610538,16605 "ci_high": 70.90143240307903,16606 "n_items": 1255,16607 "n_groups": 19516608 },16609 "edit_sim": {16610 "mean": 0.6831059843494437,16611 "ci_low": 0.6734568946291815,16612 "ci_high": 0.6932945949423726,16613 "n_items": 1255,16614 "n_groups": 19516615 },16616 "rougeL": {16617 "mean": 0.6857824348078598,16618 "ci_low": 0.6764145545584167,16619 "ci_high": 0.6956540963772571,16620 "n_items": 1255,16621 "n_groups": 19516622 },16623 "exact_match": {16624 "mean": 0.0,16625 "ci_low": 0.0,16626 "ci_high": 0.0,16627 "n_items": 1255,16628 "n_groups": 19516629 },16630 "number_recall": {16631 "mean": 0.9925178449185869,16632 "ci_low": 0.9888212873790864,16633 "ci_high": 0.9956424723424834,16634 "n_items": 1255,16635 "n_groups": 19516636 },16637 "placeholders_exact": {16638 "mean": 1.0,16639 "ci_low": 1.0,16640 "ci_high": 1.0,16641 "n_items": 1255,16642 "n_groups": 19516643 }16644 },16645 "background": {16646 "n": 964,16647 "chrf": {16648 "mean": 69.79369227160318,16649 "ci_low": 68.7234872093984,16650 "ci_high": 70.91709037348708,16651 "n_items": 964,16652 "n_groups": 8416653 },16654 "edit_sim": {16655 "mean": 0.6907899255945368,16656 "ci_low": 0.6783721927824059,16657 "ci_high": 0.7028310789318678,16658 "n_items": 964,16659 "n_groups": 8416660 },16661 "rougeL": {16662 "mean": 0.6975010903285562,16663 "ci_low": 0.6820848145300258,16664 "ci_high": 0.7115979934671381,16665 "n_items": 964,16666 "n_groups": 8416667 },16668 "exact_match": {16669 "mean": 0.0,16670 "ci_low": 0.0,16671 "ci_high": 0.0,16672 "n_items": 964,16673 "n_groups": 8416674 },16675 "number_recall": {16676 "mean": 0.9938553810182441,16677 "ci_low": 0.9893173665468555,16678 "ci_high": 0.99751376415659,16679 "n_items": 964,16680 "n_groups": 8416681 },16682 "placeholders_exact": {16683 "mean": 0.983402489626556,16684 "ci_low": 0.9694576161971407,16685 "ci_high": 0.993902593784821,16686 "n_items": 964,16687 "n_groups": 8416688 }16689 },16690 "chapter": {16691 "n": 1287,16692 "chrf": {16693 "mean": 64.23144991731726,16694 "ci_low": 62.939250862101744,16695 "ci_high": 66.05544150756491,16696 "n_items": 1287,16697 "n_groups": 2116698 },16699 "edit_sim": {16700 "mean": 0.6573376162129839,16701 "ci_low": 0.6450106719403007,16702 "ci_high": 0.6791895432329543,16703 "n_items": 1287,16704 "n_groups": 2116705 },16706 "rougeL": {16707 "mean": 0.6667698721682018,16708 "ci_low": 0.6541848482773855,16709 "ci_high": 0.6885178495710997,16710 "n_items": 1287,16711 "n_groups": 2116712 },16713 "exact_match": {16714 "mean": 0.0,16715 "ci_low": 0.0,16716 "ci_high": 0.0,16717 "n_items": 1287,16718 "n_groups": 2116719 },16720 "number_recall": {16721 "mean": 0.9996719330052664,16722 "ci_low": 0.9990134850666963,16723 "ci_high": 1.0,16724 "n_items": 1287,16725 "n_groups": 2116726 },16727 "placeholders_exact": {16728 "mean": 0.9992229992229992,16729 "ci_low": 0.9977760479180322,16730 "ci_high": 1.0,16731 "n_items": 1287,16732 "n_groups": 2116733 }16734 },16735 "conclusion": {16736 "n": 1168,16737 "chrf": {16738 "mean": 67.47054110047661,16739 "ci_low": 66.49418926434055,16740 "ci_high": 68.42811929211828,16741 "n_items": 1168,16742 "n_groups": 15416743 },16744 "edit_sim": {16745 "mean": 0.6661816348019413,16746 "ci_low": 0.6556258176860923,16747 "ci_high": 0.6767365969976852,16748 "n_items": 1168,16749 "n_groups": 15416750 },16751 "rougeL": {16752 "mean": 0.6658508895162537,16753 "ci_low": 0.6553118911150478,16754 "ci_high": 0.6766384290140506,16755 "n_items": 1168,16756 "n_groups": 15416757 },16758 "exact_match": {16759 "mean": 0.0,16760 "ci_low": 0.0,16761 "ci_high": 0.0,16762 "n_items": 1168,16763 "n_groups": 15416764 },16765 "number_recall": {16766 "mean": 0.99561135449406,16767 "ci_low": 0.9898276374714389,16768 "ci_high": 0.9992699857430956,16769 "n_items": 1168,16770 "n_groups": 15416771 },16772 "placeholders_exact": {16773 "mean": 0.9922945205479452,16774 "ci_low": 0.9806478389800826,16775 "ci_high": 1.0,16776 "n_items": 1168,16777 "n_groups": 15416778 }16779 },16780 "data": {16781 "n": 912,16782 "chrf": {16783 "mean": 70.45746880944581,16784 "ci_low": 69.52970130382141,16785 "ci_high": 71.4887359688263,16786 "n_items": 912,16787 "n_groups": 10416788 },16789 "edit_sim": {16790 "mean": 0.6888149966567653,16791 "ci_low": 0.6780507617050056,16792 "ci_high": 0.6991612516100925,16793 "n_items": 912,16794 "n_groups": 10416795 },16796 "rougeL": {16797 "mean": 0.7094308953965495,16798 "ci_low": 0.6983451274288509,16799 "ci_high": 0.7202338897994257,16800 "n_items": 912,16801 "n_groups": 10416802 },16803 "exact_match": {16804 "mean": 0.0,16805 "ci_low": 0.0,16806 "ci_high": 0.0,16807 "n_items": 912,16808 "n_groups": 10416809 },16810 "number_recall": {16811 "mean": 0.9792686564451322,16812 "ci_low": 0.9645303123830546,16813 "ci_high": 0.9897093502797398,16814 "n_items": 912,16815 "n_groups": 10416816 },16817 "placeholders_exact": {16818 "mean": 0.9923245614035088,16819 "ci_low": 0.9797829466515711,16820 "ci_high": 1.0,16821 "n_items": 912,16822 "n_groups": 10416823 }16824 },16825 "discussion": {16826 "n": 1601,16827 "chrf": {16828 "mean": 69.29185207606368,16829 "ci_low": 68.43099284189522,16830 "ci_high": 70.1333879669714,16831 "n_items": 1601,16832 "n_groups": 14216833 },16834 "edit_sim": {16835 "mean": 0.6831596547693511,16836 "ci_low": 0.6739965417744581,16837 "ci_high": 0.6921218112088392,16838 "n_items": 1601,16839 "n_groups": 14216840 },16841 "rougeL": {16842 "mean": 0.6855278360378614,16843 "ci_low": 0.6760311265262192,16844 "ci_high": 0.6950291687458832,16845 "n_items": 1601,16846 "n_groups": 14216847 },16848 "exact_match": {16849 "mean": 0.0,16850 "ci_low": 0.0,16851 "ci_high": 0.0,16852 "n_items": 1601,16853 "n_groups": 14216854 },16855 "number_recall": {16856 "mean": 0.990506876193212,16857 "ci_low": 0.9857693599013662,16858 "ci_high": 0.9947552723732135,16859 "n_items": 1601,16860 "n_groups": 14216861 },16862 "placeholders_exact": {16863 "mean": 0.9906308557151781,16864 "ci_low": 0.9807830888623572,16865 "ci_high": 0.9978873611124878,16866 "n_items": 1601,16867 "n_groups": 14216868 }16869 },16870 "introduction": {16871 "n": 1789,16872 "chrf": {16873 "mean": 69.12221093955087,16874 "ci_low": 68.16239921506866,16875 "ci_high": 70.06504461826697,16876 "n_items": 1789,16877 "n_groups": 17616878 },16879 "edit_sim": {16880 "mean": 0.682336155136171,16881 "ci_low": 0.6726202467596825,16882 "ci_high": 0.6925061990095192,16883 "n_items": 1789,16884 "n_groups": 17616885 },16886 "rougeL": {16887 "mean": 0.6835304288532932,16888 "ci_low": 0.6733702808847918,16889 "ci_high": 0.6936749645686748,16890 "n_items": 1789,16891 "n_groups": 17616892 },16893 "exact_match": {16894 "mean": 0.0,16895 "ci_low": 0.0,16896 "ci_high": 0.0,16897 "n_items": 1789,16898 "n_groups": 17616899 },16900 "number_recall": {16901 "mean": 0.9925050471235491,16902 "ci_low": 0.9862401962350642,16903 "ci_high": 0.9971046258744916,16904 "n_items": 1789,16905 "n_groups": 17616906 },16907 "placeholders_exact": {16908 "mean": 0.9865846841811068,16909 "ci_low": 0.9756360910785188,16910 "ci_high": 0.9949573919057243,16911 "n_items": 1789,16912 "n_groups": 17616913 }16914 },16915 "limitations": {16916 "n": 425,16917 "chrf": {16918 "mean": 67.93526674797624,16919 "ci_low": 66.23505692217957,16920 "ci_high": 69.70806189721188,16921 "n_items": 425,16922 "n_groups": 4116923 },16924 "edit_sim": {16925 "mean": 0.6671752783973348,16926 "ci_low": 0.649288882424134,16927 "ci_high": 0.6858138895448693,16928 "n_items": 425,16929 "n_groups": 4116930 },16931 "rougeL": {16932 "mean": 0.6711113185491859,16933 "ci_low": 0.6491458053000163,16934 "ci_high": 0.6946065407279168,16935 "n_items": 425,16936 "n_groups": 4116937 },16938 "exact_match": {16939 "mean": 0.0,16940 "ci_low": 0.0,16941 "ci_high": 0.0,16942 "n_items": 425,16943 "n_groups": 4116944 },16945 "number_recall": {16946 "mean": 0.9978692810457516,16947 "ci_low": 0.995451644575356,16948 "ci_high": 0.9997481736464883,16949 "n_items": 425,16950 "n_groups": 4116951 },16952 "placeholders_exact": {16953 "mean": 0.9882352941176471,16954 "ci_low": 0.9703629814353006,16955 "ci_high": 1.0,16956 "n_items": 425,16957 "n_groups": 4116958 }16959 },16960 "methods": {16961 "n": 1528,16962 "chrf": {16963 "mean": 71.26373879457122,16964 "ci_low": 70.41166676226636,16965 "ci_high": 72.14966333755795,16966 "n_items": 1528,16967 "n_groups": 15116968 },16969 "edit_sim": {16970 "mean": 0.69964492711729,16971 "ci_low": 0.6907279247019802,16972 "ci_high": 0.7087921977241656,16973 "n_items": 1528,16974 "n_groups": 15116975 },16976 "rougeL": {16977 "mean": 0.7187052720582218,16978 "ci_low": 0.7090614414217437,16979 "ci_high": 0.728685688411645,16980 "n_items": 1528,16981 "n_groups": 15116982 },16983 "exact_match": {16984 "mean": 0.0,16985 "ci_low": 0.0,16986 "ci_high": 0.0,16987 "n_items": 1528,16988 "n_groups": 15116989 },16990 "number_recall": {16991 "mean": 0.9906030230616136,16992 "ci_low": 0.9860747582845697,16993 "ci_high": 0.994540807974134,16994 "n_items": 1528,16995 "n_groups": 15116996 },16997 "placeholders_exact": {16998 "mean": 0.9928010471204188,16999 "ci_low": 0.9853241768405475,17000 "ci_high": 0.9985278329171202,17001 "n_items": 1528,17002 "n_groups": 15117003 }17004 },17005 "other": {17006 "n": 1387,17007 "chrf": {17008 "mean": 70.06142642122929,17009 "ci_low": 69.04461468835757,17010 "ci_high": 71.12301546742265,17011 "n_items": 1387,17012 "n_groups": 11917013 },17014 "edit_sim": {17015 "mean": 0.6927786913181414,17016 "ci_low": 0.6830154436459893,17017 "ci_high": 0.7032690520989725,17018 "n_items": 1387,17019 "n_groups": 11917020 },17021 "rougeL": {17022 "mean": 0.7007649676459756,17023 "ci_low": 0.6899725789596953,17024 "ci_high": 0.7112321199148831,17025 "n_items": 1387,17026 "n_groups": 11917027 },17028 "exact_match": {17029 "mean": 0.0,17030 "ci_low": 0.0,17031 "ci_high": 0.0,17032 "n_items": 1387,17033 "n_groups": 11917034 },17035 "number_recall": {17036 "mean": 0.9933732473566649,17037 "ci_low": 0.9887643453432927,17038 "ci_high": 0.9970913553098704,17039 "n_items": 1387,17040 "n_groups": 11917041 },17042 "placeholders_exact": {17043 "mean": 0.9841384282624369,17044 "ci_low": 0.9712458296813593,17045 "ci_high": 0.9940389699098715,17046 "n_items": 1387,17047 "n_groups": 11917048 }17049 },17050 "preface": {17051 "n": 362,17052 "chrf": {17053 "mean": 63.82081992099244,17054 "ci_low": 59.28071222776859,17055 "ci_high": 68.5511355072367,17056 "n_items": 362,17057 "n_groups": 1317058 },17059 "edit_sim": {17060 "mean": 0.6578973197661426,17061 "ci_low": 0.6107870480982768,17062 "ci_high": 0.7090106969318751,17063 "n_items": 362,17064 "n_groups": 1317065 },17066 "rougeL": {17067 "mean": 0.6642560623198814,17068 "ci_low": 0.6100831978903076,17069 "ci_high": 0.724281187536476,17070 "n_items": 362,17071 "n_groups": 1317072 },17073 "exact_match": {17074 "mean": 0.0,17075 "ci_low": 0.0,17076 "ci_high": 0.0,17077 "n_items": 362,17078 "n_groups": 1317079 },17080 "number_recall": {17081 "mean": 1.0,17082 "ci_low": 1.0,17083 "ci_high": 1.0,17084 "n_items": 362,17085 "n_groups": 1317086 },17087 "placeholders_exact": {17088 "mean": 1.0,17089 "ci_low": 1.0,17090 "ci_high": 1.0,17091 "n_items": 362,17092 "n_groups": 1317093 }17094 },17095 "related_work": {17096 "n": 557,17097 "chrf": {17098 "mean": 70.78811972100522,17099 "ci_low": 69.19561406943264,17100 "ci_high": 72.4172755721794,17101 "n_items": 557,17102 "n_groups": 3917103 },17104 "edit_sim": {17105 "mean": 0.6930685614300918,17106 "ci_low": 0.6761773520574168,17107 "ci_high": 0.7126382944000769,17108 "n_items": 557,17109 "n_groups": 3917110 },17111 "rougeL": {17112 "mean": 0.7007478499753301,17113 "ci_low": 0.6823319252006885,17114 "ci_high": 0.720870210679723,17115 "n_items": 557,17116 "n_groups": 3917117 },17118 "exact_match": {17119 "mean": 0.0,17120 "ci_low": 0.0,17121 "ci_high": 0.0,17122 "n_items": 557,17123 "n_groups": 3917124 },17125 "number_recall": {17126 "mean": 0.9878275726807778,17127 "ci_low": 0.9752297855790432,17128 "ci_high": 0.9965762484018894,17129 "n_items": 557,17130 "n_groups": 3917131 },17132 "placeholders_exact": {17133 "mean": 0.9964093357271095,17134 "ci_low": 0.9904942965779467,17135 "ci_high": 1.0,17136 "n_items": 557,17137 "n_groups": 3917138 }17139 },17140 "results": {17141 "n": 1501,17142 "chrf": {17143 "mean": 70.50010328110909,17144 "ci_low": 69.32812830463342,17145 "ci_high": 71.73154202958865,17146 "n_items": 1501,17147 "n_groups": 15317148 },17149 "edit_sim": {17150 "mean": 0.6936876951018781,17151 "ci_low": 0.6830854741515422,17152 "ci_high": 0.70479555471628,17153 "n_items": 1501,17154 "n_groups": 15317155 },17156 "rougeL": {17157 "mean": 0.715588437955548,17158 "ci_low": 0.7042738487601413,17159 "ci_high": 0.7275202073301946,17160 "n_items": 1501,17161 "n_groups": 15317162 },17163 "exact_match": {17164 "mean": 0.0,17165 "ci_low": 0.0,17166 "ci_high": 0.0,17167 "n_items": 1501,17168 "n_groups": 15317169 },17170 "number_recall": {17171 "mean": 0.9790860789561531,17172 "ci_low": 0.9711821565103382,17173 "ci_high": 0.9860647064218523,17174 "n_items": 1501,17175 "n_groups": 15317176 },17177 "placeholders_exact": {17178 "mean": 0.9986675549633578,17179 "ci_low": 0.9966008939265713,17180 "ci_high": 1.0,17181 "n_items": 1501,17182 "n_groups": 15317183 }17184 },17185 "theory": {17186 "n": 913,17187 "chrf": {17188 "mean": 70.87165460300527,17189 "ci_low": 69.67919317160437,17190 "ci_high": 72.0295353200717,17191 "n_items": 913,17192 "n_groups": 7917193 },17194 "edit_sim": {17195 "mean": 0.7028547688700504,17196 "ci_low": 0.6891473656547604,17197 "ci_high": 0.7160323052650703,17198 "n_items": 913,17199 "n_groups": 7917200 },17201 "rougeL": {17202 "mean": 0.717260567197851,17203 "ci_low": 0.7026820876230346,17204 "ci_high": 0.7316920733752095,17205 "n_items": 913,17206 "n_groups": 7917207 },17208 "exact_match": {17209 "mean": 0.0,17210 "ci_low": 0.0,17211 "ci_high": 0.0,17212 "n_items": 913,17213 "n_groups": 7917214 },17215 "number_recall": {17216 "mean": 0.9921635714899679,17217 "ci_low": 0.9874591812681796,17218 "ci_high": 0.9964228739063952,17219 "n_items": 913,17220 "n_groups": 7917221 },17222 "placeholders_exact": {17223 "mean": 0.9967141292442497,17224 "ci_low": 0.9912563517856823,17225 "ci_high": 1.0,17226 "n_items": 913,17227 "n_groups": 7917228 }17229 }17230 }17231 },17232 "htr-m3tokenonly-tiny": {17233 "overall": {17234 "n": 15649,17235 "chrf": {17236 "mean": 69.3090508900104,17237 "ci_low": 68.76049562987308,17238 "ci_high": 69.85135614226019,17239 "n_items": 15649,17240 "n_groups": 65217241 },17242 "edit_sim": {17243 "mean": 0.6855462907829691,17244 "ci_low": 0.6806080285169313,17245 "ci_high": 0.6904814173072322,17246 "n_items": 15649,17247 "n_groups": 65217248 },17249 "rougeL": {17250 "mean": 0.6944514662305556,17251 "ci_low": 0.6890428702543632,17252 "ci_high": 0.6998479124924262,17253 "n_items": 15649,17254 "n_groups": 65217255 },17256 "exact_match": {17257 "mean": 0.0,17258 "ci_low": 0.0,17259 "ci_high": 0.0,17260 "n_items": 15649,17261 "n_groups": 65217262 },17263 "number_recall": {17264 "mean": 0.9906008009439554,17265 "ci_low": 0.9886819226479713,17266 "ci_high": 0.9922998373209982,17267 "n_items": 15649,17268 "n_groups": 65217269 },17270 "placeholders_exact": {17271 "mean": 0.9936098153236629,17272 "ci_low": 0.991407231968133,17273 "ci_high": 0.9955752583073212,17274 "n_items": 15649,17275 "n_groups": 65217276 }17277 },17278 "by_variant": {17279 "A": {17280 "n": 2664,17281 "chrf": {17282 "mean": 68.78900441509262,17283 "ci_low": 68.16999130925286,17284 "ci_high": 69.41353686647842,17285 "n_items": 2664,17286 "n_groups": 63017287 },17288 "edit_sim": {17289 "mean": 0.677218933625404,17290 "ci_low": 0.6714805462629857,17291 "ci_high": 0.683520554095369,17292 "n_items": 2664,17293 "n_groups": 63017294 },17295 "rougeL": {17296 "mean": 0.6830929045697162,17297 "ci_low": 0.6771767875162844,17298 "ci_high": 0.6892852256207576,17299 "n_items": 2664,17300 "n_groups": 63017301 },17302 "exact_match": {17303 "mean": 0.0,17304 "ci_low": 0.0,17305 "ci_high": 0.0,17306 "n_items": 2664,17307 "n_groups": 63017308 },17309 "number_recall": {17310 "mean": 0.9898868396101907,17311 "ci_low": 0.9875171011188791,17312 "ci_high": 0.9921765900799909,17313 "n_items": 2664,17314 "n_groups": 63017315 },17316 "placeholders_exact": {17317 "mean": 0.990990990990991,17318 "ci_low": 0.9870850634366118,17319 "ci_high": 0.9943103782251193,17320 "n_items": 2664,17321 "n_groups": 63017322 }17323 },17324 "B": {17325 "n": 2539,17326 "chrf": {17327 "mean": 75.05520502397462,17328 "ci_low": 74.43365370543991,17329 "ci_high": 75.64297012003132,17330 "n_items": 2539,17331 "n_groups": 61417332 },17333 "edit_sim": {17334 "mean": 0.7538025180862225,17335 "ci_low": 0.7479693175635997,17336 "ci_high": 0.7595664173436673,17337 "n_items": 2539,17338 "n_groups": 61417339 },17340 "rougeL": {17341 "mean": 0.7609575488408744,17342 "ci_low": 0.7549029341545584,17343 "ci_high": 0.7670260485456547,17344 "n_items": 2539,17345 "n_groups": 61417346 },17347 "exact_match": {17348 "mean": 0.0,17349 "ci_low": 0.0,17350 "ci_high": 0.0,17351 "n_items": 2539,17352 "n_groups": 61417353 },17354 "number_recall": {17355 "mean": 0.9915214533189894,17356 "ci_low": 0.9891013067280228,17357 "ci_high": 0.9935972718784069,17358 "n_items": 2539,17359 "n_groups": 61417360 },17361 "placeholders_exact": {17362 "mean": 0.9956675856636471,17363 "ci_low": 0.992897181509047,17364 "ci_high": 0.9979798794724167,17365 "n_items": 2539,17366 "n_groups": 61417367 }17368 },17369 "C": {17370 "n": 2663,17371 "chrf": {17372 "mean": 71.77907156134769,17373 "ci_low": 71.23864722145349,17374 "ci_high": 72.35387151935575,17375 "n_items": 2663,17376 "n_groups": 63817377 },17378 "edit_sim": {17379 "mean": 0.7282645942082604,17380 "ci_low": 0.7229838638041874,17381 "ci_high": 0.7339669287234839,17382 "n_items": 2663,17383 "n_groups": 63817384 },17385 "rougeL": {17386 "mean": 0.7481394564144653,17387 "ci_low": 0.7424292167254307,17388 "ci_high": 0.7540924237620971,17389 "n_items": 2663,17390 "n_groups": 63817391 },17392 "exact_match": {17393 "mean": 0.0,17394 "ci_low": 0.0,17395 "ci_high": 0.0,17396 "n_items": 2663,17397 "n_groups": 63817398 },17399 "number_recall": {17400 "mean": 0.9923176775230885,17401 "ci_low": 0.9899724745786027,17402 "ci_high": 0.9943429444261271,17403 "n_items": 2663,17404 "n_groups": 63817405 },17406 "placeholders_exact": {17407 "mean": 0.994742771310552,17408 "ci_low": 0.9919224110773006,17409 "ci_high": 0.9972249439095737,17410 "n_items": 2663,17411 "n_groups": 63817412 }17413 },17414 "D": {17415 "n": 2708,17416 "chrf": {17417 "mean": 69.88031966372314,17418 "ci_low": 69.29438592094681,17419 "ci_high": 70.4806586442523,17420 "n_items": 2708,17421 "n_groups": 63817422 },17423 "edit_sim": {17424 "mean": 0.695874455263972,17425 "ci_low": 0.6904848776569249,17426 "ci_high": 0.7010983235921591,17427 "n_items": 2708,17428 "n_groups": 63817429 },17430 "rougeL": {17431 "mean": 0.7011142428459722,17432 "ci_low": 0.6957211450343332,17433 "ci_high": 0.7066155371095061,17434 "n_items": 2708,17435 "n_groups": 63817436 },17437 "exact_match": {17438 "mean": 0.0,17439 "ci_low": 0.0,17440 "ci_high": 0.0,17441 "n_items": 2708,17442 "n_groups": 63817443 },17444 "number_recall": {17445 "mean": 0.9895321247993389,17446 "ci_low": 0.9870393519642889,17447 "ci_high": 0.9917193228098672,17448 "n_items": 2708,17449 "n_groups": 63817450 },17451 "placeholders_exact": {17452 "mean": 0.9929837518463811,17453 "ci_low": 0.9891076436495077,17454 "ci_high": 0.996003304805402,17455 "n_items": 2708,17456 "n_groups": 63817457 }17458 },17459 "E": {17460 "n": 5075,17461 "chrf": {17462 "mean": 65.10634302322427,17463 "ci_low": 64.48935898771636,17464 "ci_high": 65.71921272617863,17465 "n_items": 5075,17466 "n_groups": 62317467 },17468 "edit_sim": {17469 "mean": 0.6278426468240897,17470 "ci_low": 0.6224635423159801,17471 "ci_high": 0.6333802418212146,17472 "n_items": 5075,17473 "n_groups": 62317474 },17475 "rougeL": {17476 "mean": 0.6354142933404231,17477 "ci_low": 0.629287169831791,17478 "ci_high": 0.6416551156283865,17479 "n_items": 5075,17480 "n_groups": 62317481 },17482 "exact_match": {17483 "mean": 0.0,17484 "ci_low": 0.0,17485 "ci_high": 0.0,17486 "n_items": 5075,17487 "n_groups": 62317488 },17489 "number_recall": {17490 "mean": 0.9901843259256947,17491 "ci_low": 0.98780580119862,17492 "ci_high": 0.9924444313284229,17493 "n_items": 5075,17494 "n_groups": 62317495 },17496 "placeholders_exact": {17497 "mean": 0.9936945812807881,17498 "ci_low": 0.991022215690292,17499 "ci_high": 0.9960892815677552,17500 "n_items": 5075,17501 "n_groups": 62317502 }17503 }17504 },17505 "by_discipline": {17506 "biomedicine": {17507 "n": 2154,17508 "chrf": {17509 "mean": 69.52982686074955,17510 "ci_low": 68.38668450243277,17511 "ci_high": 70.62888868043981,17512 "n_items": 2154,17513 "n_groups": 24417514 },17515 "edit_sim": {17516 "mean": 0.681882052118638,17517 "ci_low": 0.6732917979948314,17518 "ci_high": 0.6908196031957204,17519 "n_items": 2154,17520 "n_groups": 24417521 },17522 "rougeL": {17523 "mean": 0.6917447628692672,17524 "ci_low": 0.6824162097425773,17525 "ci_high": 0.7013433047374508,17526 "n_items": 2154,17527 "n_groups": 24417528 },17529 "exact_match": {17530 "mean": 0.0,17531 "ci_low": 0.0,17532 "ci_high": 0.0,17533 "n_items": 2154,17534 "n_groups": 24417535 },17536 "number_recall": {17537 "mean": 0.9887128542636081,17538 "ci_low": 0.9830318431958386,17539 "ci_high": 0.9932774030328112,17540 "n_items": 2154,17541 "n_groups": 24417542 },17543 "placeholders_exact": {17544 "mean": 0.9939647168059424,17545 "ci_low": 0.9889112734501133,17546 "ci_high": 0.9981203889178858,17547 "n_items": 2154,17548 "n_groups": 24417549 }17550 },17551 "chemistry": {17552 "n": 837,17553 "chrf": {17554 "mean": 72.4690708233147,17555 "ci_low": 71.03596500279137,17556 "ci_high": 73.84517245403306,17557 "n_items": 837,17558 "n_groups": 1317559 },17560 "edit_sim": {17561 "mean": 0.6993538656403854,17562 "ci_low": 0.684120918044425,17563 "ci_high": 0.7165008702396914,17564 "n_items": 837,17565 "n_groups": 1317566 },17567 "rougeL": {17568 "mean": 0.7164773345056248,17569 "ci_low": 0.7012980386294129,17570 "ci_high": 0.7313878094832816,17571 "n_items": 837,17572 "n_groups": 1317573 },17574 "exact_match": {17575 "mean": 0.0,17576 "ci_low": 0.0,17577 "ci_high": 0.0,17578 "n_items": 837,17579 "n_groups": 1317580 },17581 "number_recall": {17582 "mean": 0.9866494031545507,17583 "ci_low": 0.9820086307260211,17584 "ci_high": 0.991350519188941,17585 "n_items": 837,17586 "n_groups": 1317587 },17588 "placeholders_exact": {17589 "mean": 0.989247311827957,17590 "ci_low": 0.9799409814204105,17591 "ci_high": 0.9959019533146906,17592 "n_items": 837,17593 "n_groups": 1317594 }17595 },17596 "computer_science": {17597 "n": 1375,17598 "chrf": {17599 "mean": 69.45231264685623,17600 "ci_low": 67.98107157325903,17601 "ci_high": 70.77549661980392,17602 "n_items": 1375,17603 "n_groups": 2017604 },17605 "edit_sim": {17606 "mean": 0.6920390704257767,17607 "ci_low": 0.6758181121865267,17608 "ci_high": 0.705614968023774,17609 "n_items": 1375,17610 "n_groups": 2017611 },17612 "rougeL": {17613 "mean": 0.6969513278159866,17614 "ci_low": 0.6799253096872401,17615 "ci_high": 0.710940349436808,17616 "n_items": 1375,17617 "n_groups": 2017618 },17619 "exact_match": {17620 "mean": 0.0,17621 "ci_low": 0.0,17622 "ci_high": 0.0,17623 "n_items": 1375,17624 "n_groups": 2017625 },17626 "number_recall": {17627 "mean": 0.9942135379771743,17628 "ci_low": 0.9893046856559283,17629 "ci_high": 0.9975307585321161,17630 "n_items": 1375,17631 "n_groups": 2017632 },17633 "placeholders_exact": {17634 "mean": 0.9956363636363637,17635 "ci_low": 0.990670622139148,17636 "ci_high": 0.9992412890392662,17637 "n_items": 1375,17638 "n_groups": 2017639 }17640 },17641 "economics": {17642 "n": 1944,17643 "chrf": {17644 "mean": 68.60601935430134,17645 "ci_low": 67.74150872342766,17646 "ci_high": 69.40674049268887,17647 "n_items": 1944,17648 "n_groups": 10317649 },17650 "edit_sim": {17651 "mean": 0.6823849901710433,17652 "ci_low": 0.6731638630466769,17653 "ci_high": 0.6916259082359819,17654 "n_items": 1944,17655 "n_groups": 10317656 },17657 "rougeL": {17658 "mean": 0.6863696933683585,17659 "ci_low": 0.6760909233330235,17660 "ci_high": 0.6965290790438798,17661 "n_items": 1944,17662 "n_groups": 10317663 },17664 "exact_match": {17665 "mean": 0.0,17666 "ci_low": 0.0,17667 "ci_high": 0.0,17668 "n_items": 1944,17669 "n_groups": 10317670 },17671 "number_recall": {17672 "mean": 0.9914793970889649,17673 "ci_low": 0.9877005554835935,17674 "ci_high": 0.9947654472961027,17675 "n_items": 1944,17676 "n_groups": 10317677 },17678 "placeholders_exact": {17679 "mean": 0.9994855967078189,17680 "ci_low": 0.9983349742153015,17681 "ci_high": 1.0,17682 "n_items": 1944,17683 "n_groups": 10317684 }17685 },17686 "engineering": {17687 "n": 1296,17688 "chrf": {17689 "mean": 66.94539228196126,17690 "ci_low": 65.34721003082595,17691 "ci_high": 68.54469552490107,17692 "n_items": 1296,17693 "n_groups": 1717694 },17695 "edit_sim": {17696 "mean": 0.6616824567885804,17697 "ci_low": 0.6473632345145739,17698 "ci_high": 0.6754753118573056,17699 "n_items": 1296,17700 "n_groups": 1717701 },17702 "rougeL": {17703 "mean": 0.6717445013314366,17704 "ci_low": 0.658318867216859,17705 "ci_high": 0.6857891217405996,17706 "n_items": 1296,17707 "n_groups": 1717708 },17709 "exact_match": {17710 "mean": 0.0,17711 "ci_low": 0.0,17712 "ci_high": 0.0,17713 "n_items": 1296,17714 "n_groups": 1717715 },17716 "number_recall": {17717 "mean": 0.9888082127604545,17718 "ci_low": 0.9835211416534257,17719 "ci_high": 0.993535294946664,17720 "n_items": 1296,17721 "n_groups": 1717722 },17723 "placeholders_exact": {17724 "mean": 0.9922839506172839,17725 "ci_low": 0.979882361953046,17726 "ci_high": 1.0,17727 "n_items": 1296,17728 "n_groups": 1717729 }17730 },17731 "finance": {17732 "n": 2043,17733 "chrf": {17734 "mean": 68.19453315502693,17735 "ci_low": 66.86893716232811,17736 "ci_high": 69.65998531715368,17737 "n_items": 2043,17738 "n_groups": 5117739 },17740 "edit_sim": {17741 "mean": 0.6769831038163227,17742 "ci_low": 0.6637032262662151,17743 "ci_high": 0.6917664621430963,17744 "n_items": 2043,17745 "n_groups": 5117746 },17747 "rougeL": {17748 "mean": 0.6850569986763542,17749 "ci_low": 0.671121376845489,17750 "ci_high": 0.7007836506120607,17751 "n_items": 2043,17752 "n_groups": 5117753 },17754 "exact_match": {17755 "mean": 0.0,17756 "ci_low": 0.0,17757 "ci_high": 0.0,17758 "n_items": 2043,17759 "n_groups": 5117760 },17761 "number_recall": {17762 "mean": 0.9930724806275467,17763 "ci_low": 0.9874419109273236,17764 "ci_high": 0.9974781765940793,17765 "n_items": 2043,17766 "n_groups": 5117767 },17768 "placeholders_exact": {17769 "mean": 0.9941262848751835,17770 "ci_low": 0.9878389037303179,17771 "ci_high": 0.998988818506717,17772 "n_items": 2043,17773 "n_groups": 5117774 }17775 },17776 "general_reference": {17777 "n": 118,17778 "chrf": {17779 "mean": 75.46940593248637,17780 "ci_low": 61.20746723193373,17781 "ci_high": 76.93558654656185,17782 "n_items": 118,17783 "n_groups": 217784 },17785 "edit_sim": {17786 "mean": 0.7886862115527772,17787 "ci_low": 0.6169626650453547,17788 "ci_high": 0.8063400340909233,17789 "n_items": 118,17790 "n_groups": 217791 },17792 "rougeL": {17793 "mean": 0.8155524659829768,17794 "ci_low": 0.6298656965334799,17795 "ci_high": 0.8346417600385326,17796 "n_items": 118,17797 "n_groups": 217798 },17799 "exact_match": {17800 "mean": 0.0,17801 "ci_low": 0.0,17802 "ci_high": 0.0,17803 "n_items": 118,17804 "n_groups": 217805 },17806 "number_recall": {17807 "mean": 1.0,17808 "ci_low": 1.0,17809 "ci_high": 1.0,17810 "n_items": 118,17811 "n_groups": 217812 },17813 "placeholders_exact": {17814 "mean": 1.0,17815 "ci_low": 1.0,17816 "ci_high": 1.0,17817 "n_items": 118,17818 "n_groups": 217819 }17820 },17821 "humanities": {17822 "n": 263,17823 "chrf": {17824 "mean": 63.45115872344487,17825 "ci_low": 59.623097111327716,17826 "ci_high": 63.98589422019986,17827 "n_items": 263,17828 "n_groups": 317829 },17830 "edit_sim": {17831 "mean": 0.6565448666937592,17832 "ci_low": 0.6212514574842485,17833 "ci_high": 0.6604963636648639,17834 "n_items": 263,17835 "n_groups": 317836 },17837 "rougeL": {17838 "mean": 0.6643307076811903,17839 "ci_low": 0.6311768077029437,17840 "ci_high": 0.6661492822228259,17841 "n_items": 263,17842 "n_groups": 317843 },17844 "exact_match": {17845 "mean": 0.0,17846 "ci_low": 0.0,17847 "ci_high": 0.0,17848 "n_items": 263,17849 "n_groups": 317850 },17851 "number_recall": {17852 "mean": 1.0,17853 "ci_low": 1.0,17854 "ci_high": 1.0,17855 "n_items": 263,17856 "n_groups": 317857 },17858 "placeholders_exact": {17859 "mean": 1.0,17860 "ci_low": 1.0,17861 "ci_high": 1.0,17862 "n_items": 263,17863 "n_groups": 317864 }17865 },17866 "life_sciences": {17867 "n": 1874,17868 "chrf": {17869 "mean": 71.86480752713553,17870 "ci_low": 70.04738889732455,17871 "ci_high": 73.41105962107055,17872 "n_items": 1874,17873 "n_groups": 14317874 },17875 "edit_sim": {17876 "mean": 0.7074006808367396,17877 "ci_low": 0.6940168966497996,17878 "ci_high": 0.7207926627297073,17879 "n_items": 1874,17880 "n_groups": 14317881 },17882 "rougeL": {17883 "mean": 0.7176472396511263,17884 "ci_low": 0.703789550353011,17885 "ci_high": 0.7315233412911262,17886 "n_items": 1874,17887 "n_groups": 14317888 },17889 "exact_match": {17890 "mean": 0.0,17891 "ci_low": 0.0,17892 "ci_high": 0.0,17893 "n_items": 1874,17894 "n_groups": 14317895 },17896 "number_recall": {17897 "mean": 0.9861459596944528,17898 "ci_low": 0.9793809128427017,17899 "ci_high": 0.991729015601768,17900 "n_items": 1874,17901 "n_groups": 14317902 },17903 "placeholders_exact": {17904 "mean": 0.9855923159018143,17905 "ci_low": 0.9724710793259839,17906 "ci_high": 0.9951069343731406,17907 "n_items": 1874,17908 "n_groups": 14317909 }17910 },17911 "mathematics": {17912 "n": 712,17913 "chrf": {17914 "mean": 68.46968743293633,17915 "ci_low": 65.67685945517876,17916 "ci_high": 71.78320589876691,17917 "n_items": 712,17918 "n_groups": 517919 },17920 "edit_sim": {17921 "mean": 0.6925095792073453,17922 "ci_low": 0.668491967880054,17923 "ci_high": 0.7136126905778503,17924 "n_items": 712,17925 "n_groups": 517926 },17927 "rougeL": {17928 "mean": 0.6911758888617856,17929 "ci_low": 0.666250797438964,17930 "ci_high": 0.7243156671104547,17931 "n_items": 712,17932 "n_groups": 517933 },17934 "exact_match": {17935 "mean": 0.0,17936 "ci_low": 0.0,17937 "ci_high": 0.0,17938 "n_items": 712,17939 "n_groups": 517940 },17941 "number_recall": {17942 "mean": 0.9931955333991851,17943 "ci_low": 0.9903738839285715,17944 "ci_high": 0.9974002849002849,17945 "n_items": 712,17946 "n_groups": 517947 },17948 "placeholders_exact": {17949 "mean": 0.9859550561797753,17950 "ci_low": 0.9722222222222222,17951 "ci_high": 0.9920454545454546,17952 "n_items": 712,17953 "n_groups": 517954 }17955 },17956 "other": {17957 "n": 669,17958 "chrf": {17959 "mean": 69.1763819100046,17960 "ci_low": 66.7839381332832,17961 "ci_high": 72.31565866620187,17962 "n_items": 669,17963 "n_groups": 1317964 },17965 "edit_sim": {17966 "mean": 0.6749442413562747,17967 "ci_low": 0.6543236069962298,17968 "ci_high": 0.7029960849490323,17969 "n_items": 669,17970 "n_groups": 1317971 },17972 "rougeL": {17973 "mean": 0.6854842351683329,17974 "ci_low": 0.6637210842259615,17975 "ci_high": 0.7151576841420626,17976 "n_items": 669,17977 "n_groups": 1317978 },17979 "exact_match": {17980 "mean": 0.0,17981 "ci_low": 0.0,17982 "ci_high": 0.0,17983 "n_items": 669,17984 "n_groups": 1317985 },17986 "number_recall": {17987 "mean": 0.9884280019930244,17988 "ci_low": 0.9641805786854614,17989 "ci_high": 0.9980128700666548,17990 "n_items": 669,17991 "n_groups": 1317992 },17993 "placeholders_exact": {17994 "mean": 1.0,17995 "ci_low": 1.0,17996 "ci_high": 1.0,17997 "n_items": 669,17998 "n_groups": 1317999 }18000 },18001 "social_sciences": {18002 "n": 1536,18003 "chrf": {18004 "mean": 68.68575036151738,18005 "ci_low": 66.58131222722972,18006 "ci_high": 70.21423753672008,18007 "n_items": 1536,18008 "n_groups": 2918009 },18010 "edit_sim": {18011 "mean": 0.6803442245064683,18012 "ci_low": 0.6625327888781498,18013 "ci_high": 0.696203298514142,18014 "n_items": 1536,18015 "n_groups": 2918016 },18017 "rougeL": {18018 "mean": 0.6875224298891185,18019 "ci_low": 0.6678750970592267,18020 "ci_high": 0.7047173428798106,18021 "n_items": 1536,18022 "n_groups": 2918023 },18024 "exact_match": {18025 "mean": 0.0,18026 "ci_low": 0.0,18027 "ci_high": 0.0,18028 "n_items": 1536,18029 "n_groups": 2918030 },18031 "number_recall": {18032 "mean": 0.995798264550887,18033 "ci_low": 0.9935307087738697,18034 "ci_high": 0.998196519839902,18035 "n_items": 1536,18036 "n_groups": 2918037 },18038 "placeholders_exact": {18039 "mean": 0.99609375,18040 "ci_low": 0.9923450895560164,18041 "ci_high": 0.9992790454196973,18042 "n_items": 1536,18043 "n_groups": 2918044 }18045 },18046 "statistics": {18047 "n": 828,18048 "chrf": {18049 "mean": 70.58618772679581,18050 "ci_low": 67.91050207107402,18051 "ci_high": 73.38197920199508,18052 "n_items": 828,18053 "n_groups": 918054 },18055 "edit_sim": {18056 "mean": 0.693520888090322,18057 "ci_low": 0.6713304225196904,18058 "ci_high": 0.7176112058233826,18059 "n_items": 828,18060 "n_groups": 918061 },18062 "rougeL": {18063 "mean": 0.7154981068172763,18064 "ci_low": 0.6911056018030155,18065 "ci_high": 0.740361892581559,18066 "n_items": 828,18067 "n_groups": 918068 },18069 "exact_match": {18070 "mean": 0.0,18071 "ci_low": 0.0,18072 "ci_high": 0.0,18073 "n_items": 828,18074 "n_groups": 918075 },18076 "number_recall": {18077 "mean": 0.9837917816394655,18078 "ci_low": 0.967282422682484,18079 "ci_high": 0.9950528418596345,18080 "n_items": 828,18081 "n_groups": 918082 },18083 "placeholders_exact": {18084 "mean": 0.9927536231884058,18085 "ci_low": 0.9856455032518695,18086 "ci_high": 1.0,18087 "n_items": 828,18088 "n_groups": 918089 }18090 }18091 },18092 "by_era": {18093 "1900-1949": {18094 "n": 1164,18095 "chrf": {18096 "mean": 64.20121261141671,18097 "ci_low": 61.93917347184631,18098 "ci_high": 67.34921906631175,18099 "n_items": 1164,18100 "n_groups": 1818101 },18102 "edit_sim": {18103 "mean": 0.6597627085952975,18104 "ci_low": 0.6356139673690647,18105 "ci_high": 0.697895007682173,18106 "n_items": 1164,18107 "n_groups": 1818108 },18109 "rougeL": {18110 "mean": 0.6685420330169207,18111 "ci_low": 0.6428008650613622,18112 "ci_high": 0.7106912571404761,18113 "n_items": 1164,18114 "n_groups": 1818115 },18116 "exact_match": {18117 "mean": 0.0,18118 "ci_low": 0.0,18119 "ci_high": 0.0,18120 "n_items": 1164,18121 "n_groups": 1818122 },18123 "number_recall": {18124 "mean": 1.0,18125 "ci_low": 1.0,18126 "ci_high": 1.0,18127 "n_items": 1164,18128 "n_groups": 1818129 },18130 "placeholders_exact": {18131 "mean": 1.0,18132 "ci_low": 1.0,18133 "ci_high": 1.0,18134 "n_items": 1164,18135 "n_groups": 1818136 }18137 },18138 "1950-1979": {18139 "n": 206,18140 "chrf": {18141 "mean": 62.87432609448147,18142 "ci_low": 60.46836513125254,18143 "ci_high": 63.45407572417518,18144 "n_items": 206,18145 "n_groups": 218146 },18147 "edit_sim": {18148 "mean": 0.6512860597600224,18149 "ci_low": 0.6130632985549304,18150 "ci_high": 0.6604963636648639,18151 "n_items": 206,18152 "n_groups": 218153 },18154 "rougeL": {18155 "mean": 0.6562201596674523,18156 "ci_low": 0.6150143010626522,18157 "ci_high": 0.6661492822228259,18158 "n_items": 206,18159 "n_groups": 218160 },18161 "exact_match": {18162 "mean": 0.0,18163 "ci_low": 0.0,18164 "ci_high": 0.0,18165 "n_items": 206,18166 "n_groups": 218167 },18168 "number_recall": {18169 "mean": 1.0,18170 "ci_low": 1.0,18171 "ci_high": 1.0,18172 "n_items": 206,18173 "n_groups": 218174 },18175 "placeholders_exact": {18176 "mean": 1.0,18177 "ci_low": 1.0,18178 "ci_high": 1.0,18179 "n_items": 206,18180 "n_groups": 218181 }18182 },18183 "1980-1999": {18184 "n": 151,18185 "chrf": {18186 "mean": 64.05455237623806,18187 "ci_low": 62.63839435864236,18188 "ci_high": 78.51511896592187,18189 "n_items": 151,18190 "n_groups": 418191 },18192 "edit_sim": {18193 "mean": 0.665445588092676,18194 "ci_low": 0.6521506010433363,18195 "ci_high": 0.8037093064655468,18196 "n_items": 151,18197 "n_groups": 418198 },18199 "rougeL": {18200 "mean": 0.6682974604298696,18201 "ci_low": 0.6559748228137595,18202 "ci_high": 0.8013722514547204,18203 "n_items": 151,18204 "n_groups": 418205 },18206 "exact_match": {18207 "mean": 0.0,18208 "ci_low": 0.0,18209 "ci_high": 0.0,18210 "n_items": 151,18211 "n_groups": 418212 },18213 "number_recall": {18214 "mean": 1.0,18215 "ci_low": 1.0,18216 "ci_high": 1.0,18217 "n_items": 151,18218 "n_groups": 418219 },18220 "placeholders_exact": {18221 "mean": 1.0,18222 "ci_low": 1.0,18223 "ci_high": 1.0,18224 "n_items": 151,18225 "n_groups": 418226 }18227 },18228 "2000-2009": {18229 "n": 1545,18230 "chrf": {18231 "mean": 69.897627794429,18232 "ci_low": 68.57960508464278,18233 "ci_high": 71.25005934166174,18234 "n_items": 1545,18235 "n_groups": 6918236 },18237 "edit_sim": {18238 "mean": 0.6944282295421323,18239 "ci_low": 0.6819243650965972,18240 "ci_high": 0.7074831067346306,18241 "n_items": 1545,18242 "n_groups": 6918243 },18244 "rougeL": {18245 "mean": 0.7040314237810569,18246 "ci_low": 0.6917599375842498,18247 "ci_high": 0.716975393611965,18248 "n_items": 1545,18249 "n_groups": 6918250 },18251 "exact_match": {18252 "mean": 0.0,18253 "ci_low": 0.0,18254 "ci_high": 0.0,18255 "n_items": 1545,18256 "n_groups": 6918257 },18258 "number_recall": {18259 "mean": 0.9918965037226032,18260 "ci_low": 0.9849857155712645,18261 "ci_high": 0.9962570474845516,18262 "n_items": 1545,18263 "n_groups": 6918264 },18265 "placeholders_exact": {18266 "mean": 0.996116504854369,18267 "ci_low": 0.9918763580405909,18268 "ci_high": 0.999312128174258,18269 "n_items": 1545,18270 "n_groups": 6918271 }18272 },18273 "2010-2017": {18274 "n": 12583,18275 "chrf": {18276 "mean": 69.87768754441832,18277 "ci_low": 69.38256513902954,18278 "ci_high": 70.37789468617449,18279 "n_items": 12583,18280 "n_groups": 55918281 },18282 "edit_sim": {18283 "mean": 0.6876429535804343,18284 "ci_low": 0.6825450282839668,18285 "ci_high": 0.6924630617528238,18286 "n_items": 12583,18287 "n_groups": 55918288 },18289 "rougeL": {18290 "mean": 0.6966117181476701,18291 "ci_low": 0.6910178820355043,18292 "ci_high": 0.7020107311005273,18293 "n_items": 12583,18294 "n_groups": 55918295 },18296 "exact_match": {18297 "mean": 0.0,18298 "ci_low": 0.0,18299 "ci_high": 0.0,18300 "n_items": 12583,18301 "n_groups": 55918302 },18303 "number_recall": {18304 "mean": 0.989305557952836,18305 "ci_low": 0.9870245747295817,18306 "ci_high": 0.9912982113054486,18307 "n_items": 12583,18308 "n_groups": 55918309 },18310 "placeholders_exact": {18311 "mean": 0.9925296034332035,18312 "ci_low": 0.9898559674198919,18313 "ci_high": 0.9947949994153196,18314 "n_items": 12583,18315 "n_groups": 55918316 }18317 }18318 },18319 "by_role": {18320 "abstract": {18321 "n": 1255,18322 "chrf": {18323 "mean": 70.17911621857122,18324 "ci_low": 69.35132093903327,18325 "ci_high": 71.11319634245594,18326 "n_items": 1255,18327 "n_groups": 19518328 },18329 "edit_sim": {18330 "mean": 0.6841009217434973,18331 "ci_low": 0.6743764219934009,18332 "ci_high": 0.6945986912594003,18333 "n_items": 1255,18334 "n_groups": 19518335 },18336 "rougeL": {18337 "mean": 0.6873451662488546,18338 "ci_low": 0.6780085800760518,18339 "ci_high": 0.6971578394097048,18340 "n_items": 1255,18341 "n_groups": 19518342 },18343 "exact_match": {18344 "mean": 0.0,18345 "ci_low": 0.0,18346 "ci_high": 0.0,18347 "n_items": 1255,18348 "n_groups": 19518349 },18350 "number_recall": {18351 "mean": 0.9948724159325892,18352 "ci_low": 0.9922205145315207,18353 "ci_high": 0.9971798033261134,18354 "n_items": 1255,18355 "n_groups": 19518356 },18357 "placeholders_exact": {18358 "mean": 1.0,18359 "ci_low": 1.0,18360 "ci_high": 1.0,18361 "n_items": 1255,18362 "n_groups": 19518363 }18364 },18365 "background": {18366 "n": 964,18367 "chrf": {18368 "mean": 69.81718441856123,18369 "ci_low": 68.77221695881393,18370 "ci_high": 70.92231240178715,18371 "n_items": 964,18372 "n_groups": 8418373 },18374 "edit_sim": {18375 "mean": 0.6909986942930593,18376 "ci_low": 0.6785132953927563,18377 "ci_high": 0.7031144550455216,18378 "n_items": 964,18379 "n_groups": 8418380 },18381 "rougeL": {18382 "mean": 0.6979428794689966,18383 "ci_low": 0.6830881887516806,18384 "ci_high": 0.7122236045341648,18385 "n_items": 964,18386 "n_groups": 8418387 },18388 "exact_match": {18389 "mean": 0.0,18390 "ci_low": 0.0,18391 "ci_high": 0.0,18392 "n_items": 964,18393 "n_groups": 8418394 },18395 "number_recall": {18396 "mean": 0.9944271553711387,18397 "ci_low": 0.9904796701209408,18398 "ci_high": 0.9975842217112597,18399 "n_items": 964,18400 "n_groups": 8418401 },18402 "placeholders_exact": {18403 "mean": 0.9937759336099585,18404 "ci_low": 0.9858351917706387,18405 "ci_high": 0.9990300678952473,18406 "n_items": 964,18407 "n_groups": 8418408 }18409 },18410 "chapter": {18411 "n": 1287,18412 "chrf": {18413 "mean": 64.30722503110114,18414 "ci_low": 63.02683353104621,18415 "ci_high": 66.08083846566701,18416 "n_items": 1287,18417 "n_groups": 2118418 },18419 "edit_sim": {18420 "mean": 0.6579401240457025,18421 "ci_low": 0.6458969772203529,18422 "ci_high": 0.6792088436385056,18423 "n_items": 1287,18424 "n_groups": 2118425 },18426 "rougeL": {18427 "mean": 0.6673166564530703,18428 "ci_low": 0.6552013703684489,18429 "ci_high": 0.6884388773321607,18430 "n_items": 1287,18431 "n_groups": 2118432 },18433 "exact_match": {18434 "mean": 0.0,18435 "ci_low": 0.0,18436 "ci_high": 0.0,18437 "n_items": 1287,18438 "n_groups": 2118439 },18440 "number_recall": {18441 "mean": 0.9994388327721662,18442 "ci_low": 0.9983125402456648,18443 "ci_high": 1.0,18444 "n_items": 1287,18445 "n_groups": 2118446 },18447 "placeholders_exact": {18448 "mean": 1.0,18449 "ci_low": 1.0,18450 "ci_high": 1.0,18451 "n_items": 1287,18452 "n_groups": 2118453 }18454 },18455 "conclusion": {18456 "n": 1168,18457 "chrf": {18458 "mean": 67.49117018514218,18459 "ci_low": 66.53176059396645,18460 "ci_high": 68.44263251522091,18461 "n_items": 1168,18462 "n_groups": 15418463 },18464 "edit_sim": {18465 "mean": 0.6671711876910397,18466 "ci_low": 0.6564232437804078,18467 "ci_high": 0.6778306538311801,18468 "n_items": 1168,18469 "n_groups": 15418470 },18471 "rougeL": {18472 "mean": 0.6660321518474007,18473 "ci_low": 0.6551110748290904,18474 "ci_high": 0.6769570745796247,18475 "n_items": 1168,18476 "n_groups": 15418477 },18478 "exact_match": {18479 "mean": 0.0,18480 "ci_low": 0.0,18481 "ci_high": 0.0,18482 "n_items": 1168,18483 "n_groups": 15418484 },18485 "number_recall": {18486 "mean": 0.9948921702346359,18487 "ci_low": 0.9904233948019159,18488 "ci_high": 0.9983993121264626,18489 "n_items": 1168,18490 "n_groups": 15418491 },18492 "placeholders_exact": {18493 "mean": 0.9914383561643836,18494 "ci_low": 0.9785930202681257,18495 "ci_high": 1.0,18496 "n_items": 1168,18497 "n_groups": 15418498 }18499 },18500 "data": {18501 "n": 912,18502 "chrf": {18503 "mean": 70.77385836719013,18504 "ci_low": 69.73902917439408,18505 "ci_high": 71.8624701500901,18506 "n_items": 912,18507 "n_groups": 10418508 },18509 "edit_sim": {18510 "mean": 0.6906735747583781,18511 "ci_low": 0.6791407738866533,18512 "ci_high": 0.7016055975646475,18513 "n_items": 912,18514 "n_groups": 10418515 },18516 "rougeL": {18517 "mean": 0.7118040559101789,18518 "ci_low": 0.6997719009410177,18519 "ci_high": 0.7234448489356039,18520 "n_items": 912,18521 "n_groups": 10418522 },18523 "exact_match": {18524 "mean": 0.0,18525 "ci_low": 0.0,18526 "ci_high": 0.0,18527 "n_items": 912,18528 "n_groups": 10418529 },18530 "number_recall": {18531 "mean": 0.9838649571917049,18532 "ci_low": 0.972556651397314,18533 "ci_high": 0.9921606083366676,18534 "n_items": 912,18535 "n_groups": 10418536 },18537 "placeholders_exact": {18538 "mean": 0.9945175438596491,18539 "ci_low": 0.9868417113142136,18540 "ci_high": 1.0,18541 "n_items": 912,18542 "n_groups": 10418543 }18544 },18545 "discussion": {18546 "n": 1601,18547 "chrf": {18548 "mean": 69.28379580449878,18549 "ci_low": 68.38581010951863,18550 "ci_high": 70.17193278146141,18551 "n_items": 1601,18552 "n_groups": 14218553 },18554 "edit_sim": {18555 "mean": 0.6837363677623624,18556 "ci_low": 0.6745931702335944,18557 "ci_high": 0.6930159872038826,18558 "n_items": 1601,18559 "n_groups": 14218560 },18561 "rougeL": {18562 "mean": 0.686896872222173,18563 "ci_low": 0.6769829807939325,18564 "ci_high": 0.6965992122560075,18565 "n_items": 1601,18566 "n_groups": 14218567 },18568 "exact_match": {18569 "mean": 0.0,18570 "ci_low": 0.0,18571 "ci_high": 0.0,18572 "n_items": 1601,18573 "n_groups": 14218574 },18575 "number_recall": {18576 "mean": 0.9894252540415783,18577 "ci_low": 0.9837306524856942,18578 "ci_high": 0.9941835594855014,18579 "n_items": 1601,18580 "n_groups": 14218581 },18582 "placeholders_exact": {18583 "mean": 0.9887570268582137,18584 "ci_low": 0.979565967371178,18585 "ci_high": 0.9954707530188398,18586 "n_items": 1601,18587 "n_groups": 14218588 }18589 },18590 "introduction": {18591 "n": 1789,18592 "chrf": {18593 "mean": 69.13670653959194,18594 "ci_low": 68.16860915341196,18595 "ci_high": 70.10156995024435,18596 "n_items": 1789,18597 "n_groups": 17618598 },18599 "edit_sim": {18600 "mean": 0.6834242581111252,18601 "ci_low": 0.6735223645430236,18602 "ci_high": 0.6936705831365235,18603 "n_items": 1789,18604 "n_groups": 17618605 },18606 "rougeL": {18607 "mean": 0.6846253906281329,18608 "ci_low": 0.6747264576155936,18609 "ci_high": 0.6945855745774134,18610 "n_items": 1789,18611 "n_groups": 17618612 },18613 "exact_match": {18614 "mean": 0.0,18615 "ci_low": 0.0,18616 "ci_high": 0.0,18617 "n_items": 1789,18618 "n_groups": 17618619 },18620 "number_recall": {18621 "mean": 0.9922859715900522,18622 "ci_low": 0.9862619544418428,18623 "ci_high": 0.9966559855395088,18624 "n_items": 1789,18625 "n_groups": 17618626 },18627 "placeholders_exact": {18628 "mean": 0.9910564561207379,18629 "ci_low": 0.9820648013176622,18630 "ci_high": 0.9975115384236283,18631 "n_items": 1789,18632 "n_groups": 17618633 }18634 },18635 "limitations": {18636 "n": 425,18637 "chrf": {18638 "mean": 68.00998891007248,18639 "ci_low": 66.33188151466638,18640 "ci_high": 69.7432378864806,18641 "n_items": 425,18642 "n_groups": 4118643 },18644 "edit_sim": {18645 "mean": 0.669219078315387,18646 "ci_low": 0.651527742199468,18647 "ci_high": 0.688385893371189,18648 "n_items": 425,18649 "n_groups": 4118650 },18651 "rougeL": {18652 "mean": 0.6732301312208937,18653 "ci_low": 0.6517935532747007,18654 "ci_high": 0.6958924407305525,18655 "n_items": 425,18656 "n_groups": 4118657 },18658 "exact_match": {18659 "mean": 0.0,18660 "ci_low": 0.0,18661 "ci_high": 0.0,18662 "n_items": 425,18663 "n_groups": 4118664 },18665 "number_recall": {18666 "mean": 0.9975686274509805,18667 "ci_low": 0.9937123120742306,18668 "ci_high": 1.0,18669 "n_items": 425,18670 "n_groups": 4118671 },18672 "placeholders_exact": {18673 "mean": 0.9929411764705882,18674 "ci_low": 0.976314227190668,18675 "ci_high": 1.0,18676 "n_items": 425,18677 "n_groups": 4118678 }18679 },18680 "methods": {18681 "n": 1528,18682 "chrf": {18683 "mean": 71.28187662054957,18684 "ci_low": 70.45495585872298,18685 "ci_high": 72.16424834648456,18686 "n_items": 1528,18687 "n_groups": 15118688 },18689 "edit_sim": {18690 "mean": 0.699901540031606,18691 "ci_low": 0.6908348563530651,18692 "ci_high": 0.708954335810537,18693 "n_items": 1528,18694 "n_groups": 15118695 },18696 "rougeL": {18697 "mean": 0.719306168455429,18698 "ci_low": 0.7099093213677772,18699 "ci_high": 0.7293102512519619,18700 "n_items": 1528,18701 "n_groups": 15118702 },18703 "exact_match": {18704 "mean": 0.0,18705 "ci_low": 0.0,18706 "ci_high": 0.0,18707 "n_items": 1528,18708 "n_groups": 15118709 },18710 "number_recall": {18711 "mean": 0.987623410826246,18712 "ci_low": 0.9819740649014777,18713 "ci_high": 0.9923076099067115,18714 "n_items": 1528,18715 "n_groups": 15118716 },18717 "placeholders_exact": {18718 "mean": 0.9901832460732984,18719 "ci_low": 0.9808467573075742,18720 "ci_high": 0.9974027236535338,18721 "n_items": 1528,18722 "n_groups": 15118723 }18724 },18725 "other": {18726 "n": 1387,18727 "chrf": {18728 "mean": 70.13608742383511,18729 "ci_low": 69.06264665525818,18730 "ci_high": 71.20984177407571,18731 "n_items": 1387,18732 "n_groups": 11918733 },18734 "edit_sim": {18735 "mean": 0.6941306336237902,18736 "ci_low": 0.684171317077317,18737 "ci_high": 0.7046159133764397,18738 "n_items": 1387,18739 "n_groups": 11918740 },18741 "rougeL": {18742 "mean": 0.7023696173440699,18743 "ci_low": 0.6914174870879185,18744 "ci_high": 0.7131488169408119,18745 "n_items": 1387,18746 "n_groups": 11918747 },18748 "exact_match": {18749 "mean": 0.0,18750 "ci_low": 0.0,18751 "ci_high": 0.0,18752 "n_items": 1387,18753 "n_groups": 11918754 },18755 "number_recall": {18756 "mean": 0.9926928935039965,18757 "ci_low": 0.9879253072495555,18758 "ci_high": 0.9966581415478905,18759 "n_items": 1387,18760 "n_groups": 11918761 },18762 "placeholders_exact": {18763 "mean": 0.9906272530641672,18764 "ci_low": 0.9846014954064962,18765 "ci_high": 0.9967613298188929,18766 "n_items": 1387,18767 "n_groups": 11918768 }18769 },18770 "preface": {18771 "n": 362,18772 "chrf": {18773 "mean": 63.65296139054946,18774 "ci_low": 58.919246364114336,18775 "ci_high": 68.62953229853352,18776 "n_items": 362,18777 "n_groups": 1318778 },18779 "edit_sim": {18780 "mean": 0.6558896018569466,18781 "ci_low": 0.6065943471892252,18782 "ci_high": 0.7085941105730083,18783 "n_items": 362,18784 "n_groups": 1318785 },18786 "rougeL": {18787 "mean": 0.661938475632646,18788 "ci_low": 0.6071827406247151,18789 "ci_high": 0.7232872275451471,18790 "n_items": 362,18791 "n_groups": 1318792 },18793 "exact_match": {18794 "mean": 0.0,18795 "ci_low": 0.0,18796 "ci_high": 0.0,18797 "n_items": 362,18798 "n_groups": 1318799 },18800 "number_recall": {18801 "mean": 1.0,18802 "ci_low": 1.0,18803 "ci_high": 1.0,18804 "n_items": 362,18805 "n_groups": 1318806 },18807 "placeholders_exact": {18808 "mean": 1.0,18809 "ci_low": 1.0,18810 "ci_high": 1.0,18811 "n_items": 362,18812 "n_groups": 1318813 }18814 },18815 "related_work": {18816 "n": 557,18817 "chrf": {18818 "mean": 71.04865128879372,18819 "ci_low": 69.45947089607544,18820 "ci_high": 72.65920814430477,18821 "n_items": 557,18822 "n_groups": 3918823 },18824 "edit_sim": {18825 "mean": 0.6972809905432474,18826 "ci_low": 0.6800336522218574,18827 "ci_high": 0.716566193872899,18828 "n_items": 557,18829 "n_groups": 3918830 },18831 "rougeL": {18832 "mean": 0.7049786033080536,18833 "ci_low": 0.6866916940980928,18834 "ci_high": 0.7252117965416943,18835 "n_items": 557,18836 "n_groups": 3918837 },18838 "exact_match": {18839 "mean": 0.0,18840 "ci_low": 0.0,18841 "ci_high": 0.0,18842 "n_items": 557,18843 "n_groups": 3918844 },18845 "number_recall": {18846 "mean": 0.9896829168531565,18847 "ci_low": 0.9792749517875685,18848 "ci_high": 0.9970738394065773,18849 "n_items": 557,18850 "n_groups": 3918851 },18852 "placeholders_exact": {18853 "mean": 0.9910233393177738,18854 "ci_low": 0.979659287443791,18855 "ci_high": 1.0,18856 "n_items": 557,18857 "n_groups": 3918858 }18859 },18860 "results": {18861 "n": 1501,18862 "chrf": {18863 "mean": 70.66568535512285,18864 "ci_low": 69.4737991758533,18865 "ci_high": 71.96159049657793,18866 "n_items": 1501,18867 "n_groups": 15318868 },18869 "edit_sim": {18870 "mean": 0.6961236925651947,18871 "ci_low": 0.6853895121406798,18872 "ci_high": 0.707266689645448,18873 "n_items": 1501,18874 "n_groups": 15318875 },18876 "rougeL": {18877 "mean": 0.7164644079544777,18878 "ci_low": 0.7047720924701666,18879 "ci_high": 0.728788711202147,18880 "n_items": 1501,18881 "n_groups": 15318882 },18883 "exact_match": {18884 "mean": 0.0,18885 "ci_low": 0.0,18886 "ci_high": 0.0,18887 "n_items": 1501,18888 "n_groups": 15318889 },18890 "number_recall": {18891 "mean": 0.9745192190009122,18892 "ci_low": 0.9658354588540491,18893 "ci_high": 0.9823145277277388,18894 "n_items": 1501,18895 "n_groups": 15318896 },18897 "placeholders_exact": {18898 "mean": 0.9980013324450366,18899 "ci_low": 0.9947703818369453,18900 "ci_high": 1.0,18901 "n_items": 1501,18902 "n_groups": 15318903 }18904 },18905 "theory": {18906 "n": 913,18907 "chrf": {18908 "mean": 70.86926715265425,18909 "ci_low": 69.66120243838137,18910 "ci_high": 72.07538551400333,18911 "n_items": 913,18912 "n_groups": 7918913 },18914 "edit_sim": {18915 "mean": 0.7041526137398196,18916 "ci_low": 0.6897177717290176,18917 "ci_high": 0.7182657775707749,18918 "n_items": 913,18919 "n_groups": 7918920 },18921 "rougeL": {18922 "mean": 0.7168396419944002,18923 "ci_low": 0.7017672107920678,18924 "ci_high": 0.7317492786002738,18925 "n_items": 913,18926 "n_groups": 7918927 },18928 "exact_match": {18929 "mean": 0.0,18930 "ci_low": 0.0,18931 "ci_high": 0.0,18932 "n_items": 913,18933 "n_groups": 7918934 },18935 "number_recall": {18936 "mean": 0.9900615023287531,18937 "ci_low": 0.9835882683624805,18938 "ci_high": 0.996181695406226,18939 "n_items": 913,18940 "n_groups": 7918941 },18942 "placeholders_exact": {18943 "mean": 0.9934282584884995,18944 "ci_low": 0.9832020596330756,18945 "ci_high": 1.0,18946 "n_items": 913,18947 "n_groups": 7918948 }18949 }18950 }18951 }18952 },18953 "paired_vs_baseline": {18954 "B1_generic_paraphrase": {18955 "chrf": {18956 "mean": -2.6912359531397954,18957 "ci_low": -2.792499561261091,18958 "ci_high": -2.5939201459687227,18959 "n_items": 15649,18960 "n_groups": 652,18961 "p_value_two_sided": 0.0,18962 "p_holm": 0.0,18963 "significant_holm_0_05": true18964 },18965 "edit_sim": {18966 "mean": -0.11255485827815079,18967 "ci_low": -0.11480713801752275,18968 "ci_high": -0.11025263037269453,18969 "n_items": 15649,18970 "n_groups": 652,18971 "p_value_two_sided": 0.0,18972 "p_holm": 0.0,18973 "significant_holm_0_05": true18974 },18975 "rougeL": {18976 "mean": -0.08327831507087344,18977 "ci_low": -0.08494608884438835,18978 "ci_high": -0.08162981428544003,18979 "n_items": 15649,18980 "n_groups": 652,18981 "p_value_two_sided": 0.0,18982 "p_holm": 0.0,18983 "significant_holm_0_05": true18984 },18985 "exact_match": {18986 "mean": 0.0,18987 "ci_low": 0.0,18988 "ci_high": 0.0,18989 "n_items": 15649,18990 "n_groups": 652,18991 "p_value_two_sided": 0.0,18992 "p_holm": 0.0,18993 "significant_holm_0_05": true18994 },18995 "number_recall": {18996 "mean": -0.00010195467581343927,18997 "ci_low": -0.00020755602552784242,18998 "ci_high": -2.4090579084739082e-05,18999 "n_items": 15649,19000 "n_groups": 652,19001 "p_value_two_sided": 0.0,19002 "p_holm": 0.0,19003 "significant_holm_0_05": true19004 },19005 "placeholders_exact": {19006 "mean": 0.0,19007 "ci_low": 0.0,19008 "ci_high": 0.0,19009 "n_items": 15649,19010 "n_groups": 652,19011 "p_value_two_sided": 0.0,19012 "p_holm": 0.0,19013 "significant_holm_0_05": true19014 }19015 },19016 "B2_t5-small": {19017 "chrf": {19018 "mean": -0.08257707176661969,19019 "ci_low": -0.2609388359562681,19020 "ci_high": 0.08767754862191852,19021 "n_items": 15649,19022 "n_groups": 652,19023 "p_value_two_sided": 0.35939999999999994,19024 "p_holm": 0.35939999999999994,19025 "significant_holm_0_05": false19026 },19027 "edit_sim": {19028 "mean": 0.0020384737995723574,19029 "ci_low": 0.0002670803695251623,19030 "ci_high": 0.00364220308432957,19031 "n_items": 15649,19032 "n_groups": 652,19033 "p_value_two_sided": 0.0252,19034 "p_holm": 0.0504,19035 "significant_holm_0_05": false19036 },19037 "rougeL": {19038 "mean": 0.004312702689575098,19039 "ci_low": 0.002573523601125297,19040 "ci_high": 0.005925857992136571,19041 "n_items": 15649,19042 "n_groups": 652,19043 "p_value_two_sided": 0.0,19044 "p_holm": 0.0,19045 "significant_holm_0_05": true19046 },19047 "exact_match": {19048 "mean": 0.0,19049 "ci_low": 0.0,19050 "ci_high": 0.0,19051 "n_items": 15649,19052 "n_groups": 652,19053 "p_value_two_sided": 0.0,19054 "p_holm": 0.0,19055 "significant_holm_0_05": true19056 },19057 "number_recall": {19058 "mean": -0.01358055697149321,19059 "ci_low": -0.01725619926797575,19060 "ci_high": -0.010310360211962945,19061 "n_items": 15649,19062 "n_groups": 652,19063 "p_value_two_sided": 0.0,19064 "p_holm": 0.0,19065 "significant_holm_0_05": true19066 },19067 "placeholders_exact": {19068 "mean": -0.26672630839031247,19069 "ci_low": -0.2948445873534794,19070 "ci_high": -0.23932712807658552,19071 "n_items": 15649,19072 "n_groups": 652,19073 "p_value_two_sided": 0.0,19074 "p_holm": 0.0,19075 "significant_holm_0_05": true19076 }19077 },19078 "htr-m1-small": {19079 "chrf": {19080 "mean": 0.10579269701303463,19081 "ci_low": -0.03235828899599141,19082 "ci_high": 0.24774467898410066,19083 "n_items": 15649,19084 "n_groups": 652,19085 "p_value_two_sided": 0.1368,19086 "p_holm": 0.2736,19087 "significant_holm_0_05": false19088 },19089 "edit_sim": {19090 "mean": -0.0025846703161147956,19091 "ci_low": -0.0038281911950576275,19092 "ci_high": -0.001308127752609619,19093 "n_items": 15649,19094 "n_groups": 652,19095 "p_value_two_sided": 0.0,19096 "p_holm": 0.0,19097 "significant_holm_0_05": true19098 },19099 "rougeL": {19100 "mean": -0.0007386941851856583,19101 "ci_low": -0.002238706047984575,19102 "ci_high": 0.0007734876473737952,19103 "n_items": 15649,19104 "n_groups": 652,19105 "p_value_two_sided": 0.34119999999999995,19106 "p_holm": 0.34119999999999995,19107 "significant_holm_0_05": false19108 },19109 "exact_match": {19110 "mean": 0.0,19111 "ci_low": 0.0,19112 "ci_high": 0.0,19113 "n_items": 15649,19114 "n_groups": 652,19115 "p_value_two_sided": 0.0,19116 "p_holm": 0.0,19117 "significant_holm_0_05": true19118 },19119 "number_recall": {19120 "mean": -0.010007995883716108,19121 "ci_low": -0.012006743479566626,19122 "ci_high": -0.008257010110863546,19123 "n_items": 15649,19124 "n_groups": 652,19125 "p_value_two_sided": 0.0,19126 "p_holm": 0.0,19127 "significant_holm_0_05": true19128 },19129 "placeholders_exact": {19130 "mean": -0.00920186593392549,19131 "ci_low": -0.012045030941341572,19132 "ci_high": -0.006722547420540243,19133 "n_items": 15649,19134 "n_groups": 652,19135 "p_value_two_sided": 0.0,19136 "p_holm": 0.0,19137 "significant_holm_0_05": true19138 }19139 },19140 "htr-m1-tiny-s2": {19141 "chrf": {19142 "mean": 0.3881401805814748,19143 "ci_low": 0.2513889164889205,19144 "ci_high": 0.527140781321981,19145 "n_items": 15649,19146 "n_groups": 652,19147 "p_value_two_sided": 0.0,19148 "p_holm": 0.0,19149 "significant_holm_0_05": true19150 },19151 "edit_sim": {19152 "mean": 0.0031536065441681643,19153 "ci_low": 0.0018820238973707546,19154 "ci_high": 0.004434415018045834,19155 "n_items": 15649,19156 "n_groups": 652,19157 "p_value_two_sided": 0.0,19158 "p_holm": 0.0,19159 "significant_holm_0_05": true19160 },19161 "rougeL": {19162 "mean": 0.005094191006366269,19163 "ci_low": 0.003613537725193392,19164 "ci_high": 0.006575112967365781,19165 "n_items": 15649,19166 "n_groups": 652,19167 "p_value_two_sided": 0.0,19168 "p_holm": 0.0,19169 "significant_holm_0_05": true19170 },19171 "exact_match": {19172 "mean": 0.0,19173 "ci_low": 0.0,19174 "ci_high": 0.0,19175 "n_items": 15649,19176 "n_groups": 652,19177 "p_value_two_sided": 0.0,19178 "p_holm": 0.0,19179 "significant_holm_0_05": true19180 },19181 "number_recall": {19182 "mean": -0.009214240483678016,19183 "ci_low": -0.011086001720121886,19184 "ci_high": -0.007530074658860918,19185 "n_items": 15649,19186 "n_groups": 652,19187 "p_value_two_sided": 0.0,19188 "p_holm": 0.0,19189 "significant_holm_0_05": true19190 },19191 "placeholders_exact": {19192 "mean": -0.0077321234583679465,19193 "ci_low": -0.010270970491699406,19194 "ci_high": -0.005540841420605738,19195 "n_items": 15649,19196 "n_groups": 652,19197 "p_value_two_sided": 0.0,19198 "p_holm": 0.0,19199 "significant_holm_0_05": true19200 }19201 },19202 "htr-m1-tiny-s3": {19203 "chrf": {19204 "mean": 0.4393270217611467,19205 "ci_low": 0.301255128067977,19206 "ci_high": 0.5799850117391716,19207 "n_items": 15649,19208 "n_groups": 652,19209 "p_value_two_sided": 0.0,19210 "p_holm": 0.0,19211 "significant_holm_0_05": true19212 },19213 "edit_sim": {19214 "mean": 0.002381695064369802,19215 "ci_low": 0.0011287648392381844,19216 "ci_high": 0.0036386401898721855,19217 "n_items": 15649,19218 "n_groups": 652,19219 "p_value_two_sided": 0.0,19220 "p_holm": 0.0,19221 "significant_holm_0_05": true19222 },19223 "rougeL": {19224 "mean": 0.004039475217678161,19225 "ci_low": 0.0025457670237275356,19226 "ci_high": 0.005527734443346322,19227 "n_items": 15649,19228 "n_groups": 652,19229 "p_value_two_sided": 0.0,19230 "p_holm": 0.0,19231 "significant_holm_0_05": true19232 },19233 "exact_match": {19234 "mean": 0.0,19235 "ci_low": 0.0,19236 "ci_high": 0.0,19237 "n_items": 15649,19238 "n_groups": 652,19239 "p_value_two_sided": 0.0,19240 "p_holm": 0.0,19241 "significant_holm_0_05": true19242 },19243 "number_recall": {19244 "mean": -0.008699609197888203,19245 "ci_low": -0.01036609748447114,19246 "ci_high": -0.007198986663685183,19247 "n_items": 15649,19248 "n_groups": 652,19249 "p_value_two_sided": 0.0,19250 "p_holm": 0.0,19251 "significant_holm_0_05": true19252 },19253 "placeholders_exact": {19254 "mean": -0.00785992715189469,19255 "ci_low": -0.010352045896353895,19256 "ci_high": -0.005654868726949307,19257 "n_items": 15649,19258 "n_groups": 652,19259 "p_value_two_sided": 0.0,19260 "p_holm": 0.0,19261 "significant_holm_0_05": true19262 }19263 },19264 "htr-m1-tiny": {19265 "chrf": {19266 "mean": 0.4016159745565867,19267 "ci_low": 0.26459057541153885,19268 "ci_high": 0.5438923262191449,19269 "n_items": 15649,19270 "n_groups": 652,19271 "p_value_two_sided": 0.0,19272 "p_holm": 0.0,19273 "significant_holm_0_05": true19274 },19275 "edit_sim": {19276 "mean": 0.001894526867126882,19277 "ci_low": 0.0005878324365882827,19278 "ci_high": 0.0032146266970660476,19279 "n_items": 15649,19280 "n_groups": 652,19281 "p_value_two_sided": 0.004,19282 "p_holm": 0.004,19283 "significant_holm_0_05": true19284 },19285 "rougeL": {19286 "mean": 0.0036614727717858824,19287 "ci_low": 0.0021446821560567003,19288 "ci_high": 0.005193797321865961,19289 "n_items": 15649,19290 "n_groups": 652,19291 "p_value_two_sided": 0.0,19292 "p_holm": 0.0,19293 "significant_holm_0_05": true19294 },19295 "exact_match": {19296 "mean": 0.0,19297 "ci_low": 0.0,19298 "ci_high": 0.0,19299 "n_items": 15649,19300 "n_groups": 652,19301 "p_value_two_sided": 0.0,19302 "p_holm": 0.0,19303 "significant_holm_0_05": true19304 },19305 "number_recall": {19306 "mean": -0.009428221188866028,19307 "ci_low": -0.011228307718290415,19308 "ci_high": -0.007835990829148987,19309 "n_items": 15649,19310 "n_groups": 652,19311 "p_value_two_sided": 0.0,19312 "p_holm": 0.0,19313 "significant_holm_0_05": true19314 },19315 "placeholders_exact": {19316 "mean": -0.0077960253051313185,19317 "ci_low": -0.010320903343740325,19318 "ci_high": -0.005509105905885257,19319 "n_items": 15649,19320 "n_groups": 652,19321 "p_value_two_sided": 0.0,19322 "p_holm": 0.0,19323 "significant_holm_0_05": true19324 }19325 },19326 "htr-m2-tiny": {19327 "chrf": {19328 "mean": 0.25878937680471575,19329 "ci_low": 0.11719620542078074,19330 "ci_high": 0.40280318201860604,19331 "n_items": 15649,19332 "n_groups": 652,19333 "p_value_two_sided": 0.0002,19334 "p_holm": 0.0006000000000000001,19335 "significant_holm_0_05": true19336 },19337 "edit_sim": {19338 "mean": 0.0009167252759792137,19339 "ci_low": -0.0003985679995843044,19340 "ci_high": 0.002219308041911707,19341 "n_items": 15649,19342 "n_groups": 652,19343 "p_value_two_sided": 0.1646,19344 "p_holm": 0.1646,19345 "significant_holm_0_05": false19346 },19347 "rougeL": {19348 "mean": 0.0027545320058731584,19349 "ci_low": 0.001259468157954675,19350 "ci_high": 0.004248127760750029,19351 "n_items": 15649,19352 "n_groups": 652,19353 "p_value_two_sided": 0.0002,19354 "p_holm": 0.0006000000000000001,19355 "significant_holm_0_05": true19356 },19357 "exact_match": {19358 "mean": 0.0,19359 "ci_low": 0.0,19360 "ci_high": 0.0,19361 "n_items": 15649,19362 "n_groups": 652,19363 "p_value_two_sided": 0.0,19364 "p_holm": 0.0,19365 "significant_holm_0_05": true19366 },19367 "number_recall": {19368 "mean": -0.011395772432086412,19369 "ci_low": -0.013680039906061365,19370 "ci_high": -0.009361160548569497,19371 "n_items": 15649,19372 "n_groups": 652,19373 "p_value_two_sided": 0.0,19374 "p_holm": 0.0,19375 "significant_holm_0_05": true19376 },19377 "placeholders_exact": {19378 "mean": -0.006901399450444118,19379 "ci_low": -0.009150182776875829,19380 "ci_high": -0.004911991440068347,19381 "n_items": 15649,19382 "n_groups": 652,19383 "p_value_two_sided": 0.0,19384 "p_holm": 0.0,19385 "significant_holm_0_05": true19386 }19387 },19388 "htr-m3light-tiny": {19389 "chrf": {19390 "mean": 0.09129873767055649,19391 "ci_low": -0.05250861341969687,19392 "ci_high": 0.2382500799407589,19393 "n_items": 15649,19394 "n_groups": 652,19395 "p_value_two_sided": 0.2168,19396 "p_holm": 0.4336,19397 "significant_holm_0_05": false19398 },19399 "edit_sim": {19400 "mean": -0.00036469911429103124,19401 "ci_low": -0.0016627299932376295,19402 "ci_high": 0.0009187512191394081,19403 "n_items": 15649,19404 "n_groups": 652,19405 "p_value_two_sided": 0.5780000000000001,19406 "p_holm": 0.5780000000000001,19407 "significant_holm_0_05": false19408 },19409 "rougeL": {19410 "mean": 0.0013514694844577162,19411 "ci_low": -0.00017219239787584687,19412 "ci_high": 0.002884948659863833,19413 "n_items": 15649,19414 "n_groups": 652,19415 "p_value_two_sided": 0.082,19416 "p_holm": 0.246,19417 "significant_holm_0_05": false19418 },19419 "exact_match": {19420 "mean": 0.0,19421 "ci_low": 0.0,19422 "ci_high": 0.0,19423 "n_items": 15649,19424 "n_groups": 652,19425 "p_value_two_sided": 0.0,19426 "p_holm": 0.0,19427 "significant_holm_0_05": true19428 },19429 "number_recall": {19430 "mean": -0.01135127741836256,19431 "ci_low": -0.013462834035156855,19432 "ci_high": -0.009502081728681411,19433 "n_items": 15649,19434 "n_groups": 652,19435 "p_value_two_sided": 0.0,19436 "p_holm": 0.0,19437 "significant_holm_0_05": true19438 },19439 "placeholders_exact": {19440 "mean": -0.007412614224551089,19441 "ci_low": -0.009940146649126852,19442 "ci_high": -0.005221927906904719,19443 "n_items": 15649,19444 "n_groups": 652,19445 "p_value_two_sided": 0.0,19446 "p_holm": 0.0,19447 "significant_holm_0_05": true19448 }19449 },19450 "htr-m3tokenonly-tiny-s2": {19451 "chrf": {19452 "mean": 0.3205465383440267,19453 "ci_low": 0.18709718118504093,19454 "ci_high": 0.4554266058525327,19455 "n_items": 15649,19456 "n_groups": 652,19457 "p_value_two_sided": 0.0,19458 "p_holm": 0.0,19459 "significant_holm_0_05": true19460 },19461 "edit_sim": {19462 "mean": 0.0023518890930840732,19463 "ci_low": 0.0012015715522335378,19464 "ci_high": 0.0035206278970056405,19465 "n_items": 15649,19466 "n_groups": 652,19467 "p_value_two_sided": 0.0,19468 "p_holm": 0.0,19469 "significant_holm_0_05": true19470 },19471 "rougeL": {19472 "mean": 0.004527661035877719,19473 "ci_low": 0.003118833820936699,19474 "ci_high": 0.005922165772136451,19475 "n_items": 15649,19476 "n_groups": 652,19477 "p_value_two_sided": 0.0,19478 "p_holm": 0.0,19479 "significant_holm_0_05": true19480 },19481 "exact_match": {19482 "mean": 0.0,19483 "ci_low": 0.0,19484 "ci_high": 0.0,19485 "n_items": 15649,19486 "n_groups": 652,19487 "p_value_two_sided": 0.0,19488 "p_holm": 0.0,19489 "significant_holm_0_05": true19490 },19491 "number_recall": {19492 "mean": -0.008828523464657198,19493 "ci_low": -0.010862433229112995,19494 "ci_high": -0.007033180463376589,19495 "n_items": 15649,19496 "n_groups": 652,19497 "p_value_two_sided": 0.0,19498 "p_holm": 0.0,19499 "significant_holm_0_05": true19500 },19501 "placeholders_exact": {19502 "mean": -0.007476516071314461,19503 "ci_low": -0.010026079125994096,19504 "ci_high": -0.005237268334436791,19505 "n_items": 15649,19506 "n_groups": 652,19507 "p_value_two_sided": 0.0,19508 "p_holm": 0.0,19509 "significant_holm_0_05": true19510 }19511 },19512 "htr-m3tokenonly-tiny": {19513 "chrf": {19514 "mean": 0.3960696143311079,19515 "ci_low": 0.2662890855650418,19516 "ci_high": 0.5275571218080413,19517 "n_items": 15649,19518 "n_groups": 652,19519 "p_value_two_sided": 0.0,19520 "p_holm": 0.0,19521 "significant_holm_0_05": true19522 },19523 "edit_sim": {19524 "mean": 0.003472908898207777,19525 "ci_low": 0.0023348866243692273,19526 "ci_high": 0.004614616369956254,19527 "n_items": 15649,19528 "n_groups": 652,19529 "p_value_two_sided": 0.0,19530 "p_holm": 0.0,19531 "significant_holm_0_05": true19532 },19533 "rougeL": {19534 "mean": 0.005557118387580416,19535 "ci_low": 0.004159040354152851,19536 "ci_high": 0.006929469991217244,19537 "n_items": 15649,19538 "n_groups": 652,19539 "p_value_two_sided": 0.0,19540 "p_holm": 0.0,19541 "significant_holm_0_05": true19542 },19543 "exact_match": {19544 "mean": 0.0,19545 "ci_low": 0.0,19546 "ci_high": 0.0,19547 "n_items": 15649,19548 "n_groups": 652,19549 "p_value_two_sided": 0.0,19550 "p_holm": 0.0,19551 "significant_holm_0_05": true19552 },19553 "number_recall": {19554 "mean": -0.00939919905604462,19555 "ci_low": -0.011318077352028822,19556 "ci_high": -0.007700162679001894,19557 "n_items": 15649,19558 "n_groups": 652,19559 "p_value_two_sided": 0.0,19560 "p_holm": 0.0,19561 "significant_holm_0_05": true19562 },19563 "placeholders_exact": {19564 "mean": -0.006390184676337146,19565 "ci_low": -0.008592768031867058,19566 "ci_high": -0.004424741692678787,19567 "n_items": 15649,19568 "n_groups": 652,19569 "p_value_two_sided": 0.0,19570 "p_holm": 0.0,19571 "significant_holm_0_05": true19572 }19573 }19574 },19575 "stylometry": {19576 "rewrite_vs_original": {19577 "W1_mean_sent_len": 0.13586334618092094,19578 "W1_sd_sent_len": 0.1358382347060873,19579 "W1_ttr": 0.4566952263489768,19580 "W1_mtld": 0.5584887187546115,19581 "W1_mean_word_len": 0.2571910489680955,19582 "W1_long_word_rate": 0.054271064966647,19583 "W1_comma_rate": 0.38048944393566503,19584 "W1_semicolon_rate": 0.03538292194609528,19585 "W1_paren_rate": 0.012886495987912836,19586 "W1_discourse_rate": 0.06145513990909634,19587 "W1_passive_rate": 0.06896949736277014,19588 "W1_nominal_rate": 0.06244692533512726,19589 "W1_first_person_rate": 0.07052029963891414,19590 "W1_subord_rate": 0.15394515435383047,19591 "W1_hedge_rate": 0.13327797181659232,19592 "W1_negation_rate": 0.025818416140458475,19593 "W1_digit_rate": 0.015479401312075019,19594 "W1_flesch": 0.14833499893223653,19595 "W1_mean": 0.153741905922006319596 },19597 "feature_means": {19598 "original": {19599 "mean_sent_len": 25.72852548600517,19600 "sd_sent_len": 9.197416365558983,19601 "ttr": 0.6472657474661079,19602 "mtld": 74.65744995224912,19603 "mean_word_len": 5.371683177168126,19604 "long_word_rate": 0.11088397342054179,19605 "comma_rate": 0.05584927351877594,19606 "semicolon_rate": 0.002695552789831473,19607 "paren_rate": 0.01514222680637077,19608 "discourse_rate": 0.00942104560277705,19609 "passive_rate": 0.40036407287174697,19610 "nominal_rate": 0.061589327913883246,19611 "first_person_rate": 0.006267311915431799,19612 "subord_rate": 0.030075423413131207,19613 "hedge_rate": 0.006615811490659336,19614 "negation_rate": 0.006152871411356443,19615 "digit_rate": 0.009612952517159828,19616 "flesch": 24.11655030268192219617 },19618 "rewrite": {19619 "mean_sent_len": 25.101671468950578,19620 "sd_sent_len": 8.442844935810857,19621 "ttr": 0.6894922200791272,19622 "mtld": 91.1507901442518,19623 "mean_word_len": 5.50765226664498,19624 "long_word_rate": 0.11327001760936985,19625 "comma_rate": 0.06851095737657771,19626 "semicolon_rate": 0.0025729415047492945,19627 "paren_rate": 0.015171764258018684,19628 "discourse_rate": 0.010010922011870867,19629 "passive_rate": 0.3750009243838806,19630 "nominal_rate": 0.059610548201261486,19631 "first_person_rate": 0.005536125338684862,19632 "subord_rate": 0.03284371945171514,19633 "hedge_rate": 0.007832905901293007,19634 "negation_rate": 0.00605098634120837,19635 "digit_rate": 0.009775379203144596,19636 "flesch": 21.87961903275602519637 }19638 },19639 "feature_sds": {19640 "original": {19641 "mean_sent_len": 7.880691131788288,19642 "sd_sent_len": 5.806416552830741,19643 "ttr": 0.09090385037876975,19644 "mtld": 26.63163183370464,19645 "mean_word_len": 0.5291570163351649,19646 "long_word_rate": 0.04671820688705637,19647 "comma_rate": 0.033494901891903385,19648 "semicolon_rate": 0.008828275606899364,19649 "paren_rate": 0.020021653774826002,19650 "discourse_rate": 0.010017359868750462,19651 "passive_rate": 0.3615439780046958,19652 "nominal_rate": 0.0324998185358136,19653 "first_person_rate": 0.011568583641865568,19654 "subord_rate": 0.018376510139990657,19655 "hedge_rate": 0.009616658393178972,19656 "negation_rate": 0.00895318262241134,19657 "digit_rate": 0.01562673624980254,19658 "flesch": 17.53987152838938719659 },19660 "rewrite": {19661 "mean_sent_len": 6.989278683660729,19662 "sd_sent_len": 5.0392162136572,19663 "ttr": 0.08964544536135766,19664 "mtld": 33.11687516572051,19665 "mean_word_len": 0.5293825312648183,19666 "long_word_rate": 0.04678058243611106,19667 "comma_rate": 0.032287829772784785,19668 "semicolon_rate": 0.007914504447783719,19669 "paren_rate": 0.020304638925291527,19670 "discourse_rate": 0.010221720509265751,19671 "passive_rate": 0.34649710630147884,19672 "nominal_rate": 0.03206780217909125,19673 "first_person_rate": 0.010864451203788974,19674 "subord_rate": 0.01823594051522143,19675 "hedge_rate": 0.010461212834399736,19676 "negation_rate": 0.008984329420770522,19677 "digit_rate": 0.015919578311550685,19678 "flesch": 16.92135900447713619679 }19680 },19681 "B0_identity": {19682 "vs_original": {19683 "W1_mean_sent_len": 0.13586334618092094,19684 "W1_sd_sent_len": 0.1358382347060873,19685 "W1_ttr": 0.4566952263489768,19686 "W1_mtld": 0.5584887187546115,19687 "W1_mean_word_len": 0.2571910489680955,19688 "W1_long_word_rate": 0.054271064966647,19689 "W1_comma_rate": 0.38048944393566503,19690 "W1_semicolon_rate": 0.03538292194609528,19691 "W1_paren_rate": 0.012886495987912836,19692 "W1_discourse_rate": 0.06145513990909634,19693 "W1_passive_rate": 0.06896949736277014,19694 "W1_nominal_rate": 0.06244692533512726,19695 "W1_first_person_rate": 0.07052029963891414,19696 "W1_subord_rate": 0.15394515435383047,19697 "W1_hedge_rate": 0.13327797181659232,19698 "W1_negation_rate": 0.025818416140458475,19699 "W1_digit_rate": 0.015479401312075019,19700 "W1_flesch": 0.14833499893223653,19701 "W1_mean": 0.153741905922006319702 },19703 "feature_means": {19704 "mean_sent_len": 25.101671468950578,19705 "sd_sent_len": 8.442844935810857,19706 "ttr": 0.6894922200791272,19707 "mtld": 91.1507901442518,19708 "mean_word_len": 5.50765226664498,19709 "long_word_rate": 0.11327001760936985,19710 "comma_rate": 0.06851095737657771,19711 "semicolon_rate": 0.0025729415047492945,19712 "paren_rate": 0.015171764258018684,19713 "discourse_rate": 0.010010922011870867,19714 "passive_rate": 0.3750009243838806,19715 "nominal_rate": 0.059610548201261486,19716 "first_person_rate": 0.005536125338684862,19717 "subord_rate": 0.03284371945171514,19718 "hedge_rate": 0.007832905901293007,19719 "negation_rate": 0.00605098634120837,19720 "digit_rate": 0.009775379203144596,19721 "flesch": 21.87961903275602519722 },19723 "probe": {19724 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19725 "probe_acc_heldout": 0.6511182108626198,19726 "eval_mean_p_original": 0.43422964454664326,19727 "eval_frac_classified_original": 0.3637932136238737319728 }19729 },19730 "B1_generic_paraphrase": {19731 "vs_original": {19732 "W1_mean_sent_len": 0.5741318025056042,19733 "W1_sd_sent_len": 0.41905460857862736,19734 "W1_ttr": 0.4203076167304636,19735 "W1_mtld": 0.5169489627245033,19736 "W1_mean_word_len": 0.3850322914101888,19737 "W1_long_word_rate": 0.22092624094119107,19738 "W1_comma_rate": 0.37112702096820976,19739 "W1_semicolon_rate": 0.03629078148412874,19740 "W1_paren_rate": 0.013058245496132367,19741 "W1_discourse_rate": 0.09352848158296564,19742 "W1_passive_rate": 0.19736998430934616,19743 "W1_nominal_rate": 0.028976771213079948,19744 "W1_first_person_rate": 0.05646246015194984,19745 "W1_subord_rate": 0.11933626046106002,19746 "W1_hedge_rate": 0.04827162754415548,19747 "W1_negation_rate": 0.026568894730715626,19748 "W1_digit_rate": 0.011183078081646513,19749 "W1_flesch": 0.539368715908436,19750 "W1_mean": 0.226552435823466919751 },19752 "feature_means": {19753 "mean_sent_len": 29.747031830039838,19754 "sd_sent_len": 11.360459595343764,19755 "ttr": 0.6861011305936566,19756 "mtld": 89.85586373512595,19757 "mean_word_len": 5.576583351526285,19758 "long_word_rate": 0.12114961079299175,19759 "comma_rate": 0.06818925084817132,19760 "semicolon_rate": 0.002563026689345418,19761 "paren_rate": 0.015114776656001708,19762 "discourse_rate": 0.00850160836833708,19763 "passive_rate": 0.4585172150204184,19764 "nominal_rate": 0.0625116423840628,19765 "first_person_rate": 0.005682499520720685,19766 "subord_rate": 0.032192495981368946,19767 "hedge_rate": 0.00617767664003287,19768 "negation_rate": 0.006019025968004454,19769 "digit_rate": 0.009662494656653604,19770 "flesch": 15.124251058208719771 },19772 "probe": {19773 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19774 "probe_acc_heldout": 0.6511182108626198,19775 "eval_mean_p_original": 0.4658268277985937,19776 "eval_frac_classified_original": 0.438366668796728219777 }19778 },19779 "B2_t5-small": {19780 "vs_original": {19781 "W1_mean_sent_len": 0.1376731893207922,19782 "W1_sd_sent_len": 0.1702673836000213,19783 "W1_ttr": 0.24193626391893747,19784 "W1_mtld": 0.21449306521618944,19785 "W1_mean_word_len": 0.1280651856535787,19786 "W1_long_word_rate": 0.03122460258986455,19787 "W1_comma_rate": 0.2998088999173119,19788 "W1_semicolon_rate": 0.650571634890281,19789 "W1_paren_rate": 0.02935170861221771,19790 "W1_discourse_rate": 0.1401219481207483,19791 "W1_passive_rate": 0.07208229134076533,19792 "W1_nominal_rate": 0.05034661951322321,19793 "W1_first_person_rate": 0.06931158023920699,19794 "W1_subord_rate": 0.053604216242725856,19795 "W1_hedge_rate": 0.10870693056427937,19796 "W1_negation_rate": 0.030540230285366995,19797 "W1_digit_rate": 0.02445700886108618,19798 "W1_flesch": 0.08293675484331414,19799 "W1_mean": 0.1408610840961061519800 },19801 "feature_means": {19802 "mean_sent_len": 25.072207098801943,19803 "sd_sent_len": 8.442841158430705,19804 "ttr": 0.6693640407653388,19805 "mtld": 81.05767544148365,19806 "mean_word_len": 5.438062321885181,19807 "long_word_rate": 0.11205560097674143,19808 "comma_rate": 0.0657942599860116,19809 "semicolon_rate": 0.0021940661754900046,19810 "paren_rate": 0.015118749615373612,19811 "discourse_rate": 0.010823535056912005,19812 "passive_rate": 0.4230030007388321,19813 "nominal_rate": 0.06008498543879227,19814 "first_person_rate": 0.005549070692541313,19815 "subord_rate": 0.03078331125767553,19816 "hedge_rate": 0.007585046923739806,19817 "negation_rate": 0.006349341892481149,19818 "digit_rate": 0.009911643221642102,19819 "flesch": 23.10182214742175719820 },19821 "probe": {19822 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19823 "probe_acc_heldout": 0.6511182108626198,19824 "eval_mean_p_original": 0.494278349850405,19825 "eval_frac_classified_original": 0.504249472809764219826 }19827 },19828 "htr-m1-small": {19829 "vs_original": {19830 "W1_mean_sent_len": 0.13055834722913656,19831 "W1_sd_sent_len": 0.15463808410352578,19832 "W1_ttr": 0.1747799393695244,19833 "W1_mtld": 0.10451009791064869,19834 "W1_mean_word_len": 0.015624654578572941,19835 "W1_long_word_rate": 0.06161491813703858,19836 "W1_comma_rate": 0.2425668874745689,19837 "W1_semicolon_rate": 0.09368966673716565,19838 "W1_paren_rate": 0.00926868734940237,19839 "W1_discourse_rate": 0.10819648555599637,19840 "W1_passive_rate": 0.1292885286527694,19841 "W1_nominal_rate": 0.07062950103568628,19842 "W1_first_person_rate": 0.07408045742377088,19843 "W1_subord_rate": 0.08460530961675129,19844 "W1_hedge_rate": 0.07988201630063672,19845 "W1_negation_rate": 0.047695482828227,19846 "W1_digit_rate": 0.023560871935883843,19847 "W1_flesch": 0.07685252675746426,19848 "W1_mean": 0.0934468034998205419849 },19850 "feature_means": {19851 "mean_sent_len": 25.108853081673256,19852 "sd_sent_len": 8.519462414094573,19853 "ttr": 0.6632050436203237,19854 "mtld": 77.76154237268447,19855 "mean_word_len": 5.371443546955026,19856 "long_word_rate": 0.10820780783644572,19857 "comma_rate": 0.06377984500019623,19858 "semicolon_rate": 0.001962699254351835,19859 "paren_rate": 0.015105007855188965,19860 "discourse_rate": 0.01049217285757521,19861 "passive_rate": 0.44188678193433456,19862 "nominal_rate": 0.05930400317870086,19863 "first_person_rate": 0.005492502822469131,19864 "subord_rate": 0.03154632397984741,19865 "hedge_rate": 0.007372793657738914,19866 "negation_rate": 0.006558211558979054,19867 "digit_rate": 0.009807456956169197,19868 "flesch": 25.01484959566846619869 },19870 "probe": {19871 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19872 "probe_acc_heldout": 0.6511182108626198,19873 "eval_mean_p_original": 0.5167520170913489,19874 "eval_frac_classified_original": 0.561825036743561919875 }19876 },19877 "htr-m1-tiny-s2": {19878 "vs_original": {19879 "W1_mean_sent_len": 0.14011947204147113,19880 "W1_sd_sent_len": 0.1657043541882848,19881 "W1_ttr": 0.2329798485701219,19882 "W1_mtld": 0.19082572246952162,19883 "W1_mean_word_len": 0.035295945770641275,19884 "W1_long_word_rate": 0.0510623607870546,19885 "W1_comma_rate": 0.23553653780718153,19886 "W1_semicolon_rate": 0.11867102691800888,19887 "W1_paren_rate": 0.012714386472509243,19888 "W1_discourse_rate": 0.08358041281619175,19889 "W1_passive_rate": 0.1009347080203029,19890 "W1_nominal_rate": 0.06366767185702289,19891 "W1_first_person_rate": 0.07290184823186398,19892 "W1_subord_rate": 0.042290294491054675,19893 "W1_hedge_rate": 0.10637714898661306,19894 "W1_negation_rate": 0.05354076836091253,19895 "W1_digit_rate": 0.025179087671732443,19896 "W1_flesch": 0.05373838826676708,19897 "W1_mean": 0.09917333242929219898 },19899 "feature_means": {19900 "mean_sent_len": 24.9882924720165,19901 "sd_sent_len": 8.455968460237836,19902 "ttr": 0.6685024154201427,19903 "mtld": 79.74499110432592,19904 "mean_word_len": 5.387154542048749,19905 "long_word_rate": 0.10871769817534394,19906 "comma_rate": 0.06359602667930811,19907 "semicolon_rate": 0.0018198358202870175,19908 "paren_rate": 0.015203906837839025,19909 "discourse_rate": 0.010230171385795999,19910 "passive_rate": 0.43559848897434855,19911 "nominal_rate": 0.059509465530635915,19912 "first_person_rate": 0.005484770068184936,19913 "subord_rate": 0.030745827543752657,19914 "hedge_rate": 0.007562415676070519,19915 "negation_rate": 0.006593017664344536,19916 "digit_rate": 0.009881423655932583,19917 "flesch": 24.6305010383614819918 },19919 "probe": {19920 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19921 "probe_acc_heldout": 0.6511182108626198,19922 "eval_mean_p_original": 0.5090464473299587,19923 "eval_frac_classified_original": 0.538245255287877819924 }19925 },19926 "htr-m1-tiny-s3": {19927 "vs_original": {19928 "W1_mean_sent_len": 0.12897637904029666,19929 "W1_sd_sent_len": 0.14976132082714988,19930 "W1_ttr": 0.21329016769159567,19931 "W1_mtld": 0.17957311033496978,19932 "W1_mean_word_len": 0.021312077387824032,19933 "W1_long_word_rate": 0.06078717430896013,19934 "W1_comma_rate": 0.2662547651824606,19935 "W1_semicolon_rate": 0.11910818653290568,19936 "W1_paren_rate": 0.013758015888809772,19937 "W1_discourse_rate": 0.10042800559616775,19938 "W1_passive_rate": 0.1547562911447517,19939 "W1_nominal_rate": 0.07294559900422094,19940 "W1_first_person_rate": 0.06910678456845759,19941 "W1_subord_rate": 0.08009153037620081,19942 "W1_hedge_rate": 0.09729408056834876,19943 "W1_negation_rate": 0.055295967653734374,19944 "W1_digit_rate": 0.022840184227687223,19945 "W1_flesch": 0.06203661704862915,19946 "W1_mean": 0.1037564587435094719947 },19948 "feature_means": {19949 "mean_sent_len": 25.112385111092305,19950 "sd_sent_len": 8.491851553474458,19951 "ttr": 0.6667484610698319,19952 "mtld": 79.39865074067623,19953 "mean_word_len": 5.376065750965444,19954 "long_word_rate": 0.1082538432477232,19955 "comma_rate": 0.06468203151407087,19956 "semicolon_rate": 0.0018157470178419535,19957 "paren_rate": 0.015100767347042151,19958 "discourse_rate": 0.010419247188836755,19959 "passive_rate": 0.4453664900205213,19960 "nominal_rate": 0.05924433942167589,19961 "first_person_rate": 0.005559819187547003,19962 "subord_rate": 0.031409755979976355,19963 "hedge_rate": 0.007478071443703152,19964 "negation_rate": 0.006624728507423136,19965 "digit_rate": 0.009854557147609848,19966 "flesch": 24.79938965258711619967 },19968 "probe": {19969 "probe_auc_orig_vs_rewrite": 0.7120012234415909,19970 "probe_acc_heldout": 0.6511182108626198,19971 "eval_mean_p_original": 0.507775873381298,19972 "eval_frac_classified_original": 0.534602850022365619973 }19974 },19975 "htr-m1-tiny": {19976 "vs_original": {19977 "W1_mean_sent_len": 0.1350982793773148,19978 "W1_sd_sent_len": 0.1301796796304316,19979 "W1_ttr": 0.20315242219444757,19980 "W1_mtld": 0.16315958798679964,19981 "W1_mean_word_len": 0.01737953908840148,19982 "W1_long_word_rate": 0.060670876160634914,19983 "W1_comma_rate": 0.28425656154517165,19984 "W1_semicolon_rate": 0.12547638264826977,19985 "W1_paren_rate": 0.01290387625951219,19986 "W1_discourse_rate": 0.10409666251939671,19987 "W1_passive_rate": 0.12041026069455561,19988 "W1_nominal_rate": 0.07049463974745585,19989 "W1_first_person_rate": 0.06581078666277838,19990 "W1_subord_rate": 0.05850515691968674,19991 "W1_hedge_rate": 0.08197974459769752,19992 "W1_negation_rate": 0.039999262671739574,19993 "W1_digit_rate": 0.022285994140162555,19994 "W1_flesch": 0.06467814736678794,19995 "W1_mean": 0.0978076589006246919996 },19997 "feature_means": {19998 "mean_sent_len": 25.090770580857264,19999 "sd_sent_len": 8.50606845344004,20000 "ttr": 0.6657623099949359,20001 "mtld": 78.87661429720923,20002 "mean_word_len": 5.37483712482147,20003 "long_word_rate": 0.10818776232173458,20004 "comma_rate": 0.06525568290388613,20005 "semicolon_rate": 0.0017395398130274726,20006 "paren_rate": 0.015167447593551268,20007 "discourse_rate": 0.010421701418992985,20008 "passive_rate": 0.43880033282992875,20009 "nominal_rate": 0.059363292019520494,20010 "first_person_rate": 0.005575379403301645,20011 "subord_rate": 0.031078292063983114,20012 "hedge_rate": 0.007359436830758639,20013 "negation_rate": 0.006483213723461885,20014 "digit_rate": 0.009815994163897022,20015 "flesch": 24.8530384116812320016 },20017 "probe": {20018 "probe_auc_orig_vs_rewrite": 0.7120012234415909,20019 "probe_acc_heldout": 0.6511182108626198,20020 "eval_mean_p_original": 0.5090295202033313,20021 "eval_frac_classified_original": 0.540162310690778920022 }20023 },20024 "htr-m2-tiny": {20025 "vs_original": {20026 "W1_mean_sent_len": 0.14253518215521044,20027 "W1_sd_sent_len": 0.1607376124502832,20028 "W1_ttr": 0.22263078437106,20029 "W1_mtld": 0.17930482805460426,20030 "W1_mean_word_len": 0.03252098478921136,20031 "W1_long_word_rate": 0.04932066370533169,20032 "W1_comma_rate": 0.2399409437814999,20033 "W1_semicolon_rate": 0.09473603666566373,20034 "W1_paren_rate": 0.010790312666870354,20035 "W1_discourse_rate": 0.1112466764550601,20036 "W1_passive_rate": 0.12016434777638453,20037 "W1_nominal_rate": 0.0615298068470107,20038 "W1_first_person_rate": 0.06324172785062859,20039 "W1_subord_rate": 0.07981584022945949,20040 "W1_hedge_rate": 0.09315499310221771,20041 "W1_negation_rate": 0.053325722545503225,20042 "W1_digit_rate": 0.016492686423565824,20043 "W1_flesch": 0.05802263827687601,20044 "W1_mean": 0.0994173215636911720045 },20046 "feature_means": {20047 "mean_sent_len": 25.009883990359018,20048 "sd_sent_len": 8.489823617734443,20049 "ttr": 0.667572433885368,20050 "mtld": 79.4228372904787,20051 "mean_word_len": 5.385726049914318,20052 "long_word_rate": 0.10880057957540934,20053 "comma_rate": 0.06372461325215088,20054 "semicolon_rate": 0.0018983055384403046,20055 "paren_rate": 0.015117228588011334,20056 "discourse_rate": 0.010517664886911233,20057 "passive_rate": 0.44280312759938023,20058 "nominal_rate": 0.059618817945059424,20059 "first_person_rate": 0.005614118022793773,20060 "subord_rate": 0.03145594026596695,20061 "hedge_rate": 0.0074600686307393855,20062 "negation_rate": 0.006591969104071306,20063 "digit_rate": 0.009816118127148861,20064 "flesch": 24.71100744384346720065 },20066 "probe": {20067 "probe_auc_orig_vs_rewrite": 0.7120012234415909,20068 "probe_acc_heldout": 0.6511182108626198,20069 "eval_mean_p_original": 0.5092176436345082,20070 "eval_frac_classified_original": 0.538884273755511520071 }20072 },20073 "htr-m3light-tiny": {20074 "vs_original": {20075 "W1_mean_sent_len": 0.13863544810664122,20076 "W1_sd_sent_len": 0.16460141138966855,20077 "W1_ttr": 0.20929228849453435,20078 "W1_mtld": 0.16178238625678137,20079 "W1_mean_word_len": 0.02522661043133804,20080 "W1_long_word_rate": 0.05549587702154908,20081 "W1_comma_rate": 0.24375415568824738,20082 "W1_semicolon_rate": 0.10484761639940311,20083 "W1_paren_rate": 0.011039894473307424,20084 "W1_discourse_rate": 0.11889182248925334,20085 "W1_passive_rate": 0.130232491693838,20086 "W1_nominal_rate": 0.06604748997767636,20087 "W1_first_person_rate": 0.06239740085452728,20088 "W1_subord_rate": 0.0704109861197629,20089 "W1_hedge_rate": 0.08600220792772127,20090 "W1_negation_rate": 0.05291296118658056,20091 "W1_digit_rate": 0.023843950521278665,20092 "W1_flesch": 0.0668978482801018,20093 "W1_mean": 0.0995729359617894520094 },20095 "feature_means": {20096 "mean_sent_len": 24.985451191311327,20097 "sd_sent_len": 8.474543341454911,20098 "ttr": 0.6663648609486302,20099 "mtld": 78.83239314135409,20100 "mean_word_len": 5.377174750397381,20101 "long_word_rate": 0.10851099303173703,20102 "comma_rate": 0.06387010910137697,20103 "semicolon_rate": 0.001838263645433297,20104 "paren_rate": 0.015131410386106452,20105 "discourse_rate": 0.010561494867277555,20106 "passive_rate": 0.4468146415831844,20107 "nominal_rate": 0.05945078064065433,20108 "first_person_rate": 0.0056137727122930695,20109 "subord_rate": 0.03128883930783114,20110 "hedge_rate": 0.00741481130288334,20111 "negation_rate": 0.006591319185302972,20112 "digit_rate": 0.009866251140771566,20113 "flesch": 24.93339637719733320114 },20115 "probe": {20116 "probe_auc_orig_vs_rewrite": 0.7120012234415909,20117 "probe_acc_heldout": 0.6511182108626198,20118 "eval_mean_p_original": 0.5121671661425897,20119 "eval_frac_classified_original": 0.550003195092338220120 }20121 },20122 "htr-m3tokenonly-tiny-s2": {20123 "vs_original": {20124 "W1_mean_sent_len": 0.14678538751216458,20125 "W1_sd_sent_len": 0.16787792096273355,20126 "W1_ttr": 0.2544412991888046,20127 "W1_mtld": 0.21986761334145638,20128 "W1_mean_word_len": 0.050719963128761474,20129 "W1_long_word_rate": 0.04645952402479384,20130 "W1_comma_rate": 0.2405145736883235,20131 "W1_semicolon_rate": 0.09004212868308625,20132 "W1_paren_rate": 0.014246808301756673,20133 "W1_discourse_rate": 0.12423384917717156,20134 "W1_passive_rate": 0.11535467325497943,20135 "W1_nominal_rate": 0.0756005695180263,20136 "W1_first_person_rate": 0.06828385730626024,20137 "W1_subord_rate": 0.053630662776918726,20138 "W1_hedge_rate": 0.11422980187190218,20139 "W1_negation_rate": 0.04734319291644695,20140 "W1_digit_rate": 0.024652162604119596,20141 "W1_flesch": 0.04762546829896119,20142 "W1_mean": 0.1056616364753703920143 },20144 "feature_means": {20145 "mean_sent_len": 24.946432082837045,20146 "sd_sent_len": 8.452657354611052,20147 "ttr": 0.6705563778181974,20148 "mtld": 80.66732612559795,20149 "mean_word_len": 5.396721733585433,20150 "long_word_rate": 0.10895372363607649,20151 "comma_rate": 0.06375378700101839,20152 "semicolon_rate": 0.0019609445203492247,20153 "paren_rate": 0.01523069448255422,20154 "discourse_rate": 0.010600747399900775,20155 "passive_rate": 0.4355258041427591,20156 "nominal_rate": 0.05911653781927724,20157 "first_person_rate": 0.005551249616687439,20158 "subord_rate": 0.03094514524765505,20159 "hedge_rate": 0.007647196665306686,20160 "negation_rate": 0.006547572056070659,20161 "digit_rate": 0.009873375901578555,20162 "flesch": 24.41850824452284720163 },20164 "probe": {20165 "probe_auc_orig_vs_rewrite": 0.7120012234415909,20166 "probe_acc_heldout": 0.6511182108626198,20167 "eval_mean_p_original": 0.5030228376915324,20168 "eval_frac_classified_original": 0.525656591475493620169 }20170 },20171 "htr-m3tokenonly-tiny": {20172 "vs_original": {20173 "W1_mean_sent_len": 0.13695923025403045,20174 "W1_sd_sent_len": 0.16147352023570383,20175 "W1_ttr": 0.26787598542718033,20176 "W1_mtld": 0.24119784283091045,20177 "W1_mean_word_len": 0.057671458778969065,20178 "W1_long_word_rate": 0.03911124836277633,20179 "W1_comma_rate": 0.24426272575547606,20180 "W1_semicolon_rate": 0.10771680500186362,20181 "W1_paren_rate": 0.012332162804125683,20182 "W1_discourse_rate": 0.11761836075620714,20183 "W1_passive_rate": 0.08383175347889876,20184 "W1_nominal_rate": 0.06501490516159876,20185 "W1_first_person_rate": 0.07070882292468637,20186 "W1_subord_rate": 0.0830827394556459,20187 "W1_hedge_rate": 0.08376377662501966,20188 "W1_negation_rate": 0.04855737698572012,20189 "W1_digit_rate": 0.0188454895395133,20190 "W1_flesch": 0.04175088826163236,20191 "W1_mean": 0.1045430607022199120192 },20193 "feature_means": {20194 "mean_sent_len": 25.036449055497386,20195 "sd_sent_len": 8.463688144047287,20196 "ttr": 0.6717531951388349,20197 "mtld": 81.33532313997175,20198 "mean_word_len": 5.400608661611035,20199 "long_word_rate": 0.1093182501625941,20200 "comma_rate": 0.06386304072058362,20201 "semicolon_rate": 0.0017823157046944797,20202 "paren_rate": 0.015177118010616978,20203 "discourse_rate": 0.01058513271234361,20204 "passive_rate": 0.4297814448117493,20205 "nominal_rate": 0.05949902164772219,20206 "first_person_rate": 0.0055343293019750805,20207 "subord_rate": 0.031558645269320056,20208 "hedge_rate": 0.007350469066732961,20209 "negation_rate": 0.006591216383536782,20210 "digit_rate": 0.009842232869915783,20211 "flesch": 24.22589926685801520212 },20213 "probe": {20214 "probe_auc_orig_vs_rewrite": 0.7120012234415909,20215 "probe_acc_heldout": 0.6511182108626198,20216 "eval_mean_p_original": 0.4993485048840113,20217 "eval_frac_classified_original": 0.518371780944469320218 }20219 }20220 },20221 "confirmatory": {20222 "preregistration_frozen": true,20223 "n_boot": 1000020224 }20225}