Repository Public Research preview
1{2 "created_at": "2026-11-10T17:12:16Z",3 "git": {4 "commit": "9178980fcbab1715e63a8936afb0d2ff0556deb2",5 "branch": "main",6 "dirty": true7 },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": 2574,31 "systems": {32 "B0_identity": {33 "overall": {34 "n": 2574,35 "chrf": {36 "mean": 63.99944708238914,37 "ci_low": 61.89767146477627,38 "ci_high": 65.8244910220833,39 "n_items": 2574,40 "n_groups": 9241 },42 "edit_sim": {43 "mean": 0.6488173540047721,44 "ci_low": 0.6314348406007124,45 "ci_high": 0.6642545169608809,46 "n_items": 2574,47 "n_groups": 9248 },49 "rougeL": {50 "mean": 0.65389952389332,51 "ci_low": 0.6351311517501724,52 "ci_high": 0.670622784991075,53 "n_items": 2574,54 "n_groups": 9255 },56 "exact_match": {57 "mean": 0.0,58 "ci_low": 0.0,59 "ci_high": 0.0,60 "n_items": 2574,61 "n_groups": 9262 },63 "number_recall": {64 "mean": 1.0,65 "ci_low": 1.0,66 "ci_high": 1.0,67 "n_items": 2574,68 "n_groups": 9269 },70 "placeholders_exact": {71 "mean": 1.0,72 "ci_low": 1.0,73 "ci_high": 1.0,74 "n_items": 2574,75 "n_groups": 9276 }77 },78 "by_variant": {79 "A": {80 "n": 436,81 "chrf": {82 "mean": 62.85615506281071,83 "ci_low": 60.53155103398149,84 "ci_high": 64.72531878599109,85 "n_items": 436,86 "n_groups": 9187 },88 "edit_sim": {89 "mean": 0.6350266867931046,90 "ci_low": 0.6155907918783824,91 "ci_high": 0.6506639382590403,92 "n_items": 436,93 "n_groups": 9194 },95 "rougeL": {96 "mean": 0.6391701545352995,97 "ci_low": 0.6180202579186084,98 "ci_high": 0.6562769561773716,99 "n_items": 436,100 "n_groups": 91101 },102 "exact_match": {103 "mean": 0.0,104 "ci_low": 0.0,105 "ci_high": 0.0,106 "n_items": 436,107 "n_groups": 91108 },109 "number_recall": {110 "mean": 1.0,111 "ci_low": 1.0,112 "ci_high": 1.0,113 "n_items": 436,114 "n_groups": 91115 },116 "placeholders_exact": {117 "mean": 1.0,118 "ci_low": 1.0,119 "ci_high": 1.0,120 "n_items": 436,121 "n_groups": 91122 }123 },124 "B": {125 "n": 416,126 "chrf": {127 "mean": 70.71035384965916,128 "ci_low": 68.0509988454996,129 "ci_high": 73.12158437953659,130 "n_items": 416,131 "n_groups": 90132 },133 "edit_sim": {134 "mean": 0.7172331980533493,135 "ci_low": 0.6921997563805663,136 "ci_high": 0.7396689555231676,137 "n_items": 416,138 "n_groups": 90139 },140 "rougeL": {141 "mean": 0.7257690220821554,142 "ci_low": 0.7002895482517408,143 "ci_high": 0.7484189147799599,144 "n_items": 416,145 "n_groups": 90146 },147 "exact_match": {148 "mean": 0.0,149 "ci_low": 0.0,150 "ci_high": 0.0,151 "n_items": 416,152 "n_groups": 90153 },154 "number_recall": {155 "mean": 1.0,156 "ci_low": 1.0,157 "ci_high": 1.0,158 "n_items": 416,159 "n_groups": 90160 },161 "placeholders_exact": {162 "mean": 1.0,163 "ci_low": 1.0,164 "ci_high": 1.0,165 "n_items": 416,166 "n_groups": 90167 }168 },169 "C": {170 "n": 438,171 "chrf": {172 "mean": 70.05629809189891,173 "ci_low": 68.09942726477466,174 "ci_high": 71.98732862987994,175 "n_items": 438,176 "n_groups": 91177 },178 "edit_sim": {179 "mean": 0.7241755330483522,180 "ci_low": 0.7062295308685829,181 "ci_high": 0.7418004200265136,182 "n_items": 438,183 "n_groups": 91184 },185 "rougeL": {186 "mean": 0.7426661560995227,187 "ci_low": 0.7234791277677214,188 "ci_high": 0.7610770017196561,189 "n_items": 438,190 "n_groups": 91191 },192 "exact_match": {193 "mean": 0.0,194 "ci_low": 0.0,195 "ci_high": 0.0,196 "n_items": 438,197 "n_groups": 91198 },199 "number_recall": {200 "mean": 1.0,201 "ci_low": 1.0,202 "ci_high": 1.0,203 "n_items": 438,204 "n_groups": 91205 },206 "placeholders_exact": {207 "mean": 1.0,208 "ci_low": 1.0,209 "ci_high": 1.0,210 "n_items": 438,211 "n_groups": 91212 }213 },214 "D": {215 "n": 431,216 "chrf": {217 "mean": 62.92757927205354,218 "ci_low": 60.544352355851075,219 "ci_high": 64.93090688478624,220 "n_items": 431,221 "n_groups": 90222 },223 "edit_sim": {224 "mean": 0.6454734416776389,225 "ci_low": 0.6238479354033922,226 "ci_high": 0.662039218562738,227 "n_items": 431,228 "n_groups": 90229 },230 "rougeL": {231 "mean": 0.6466168162646139,232 "ci_low": 0.6244416874407689,233 "ci_high": 0.6648501755945485,234 "n_items": 431,235 "n_groups": 90236 },237 "exact_match": {238 "mean": 0.0,239 "ci_low": 0.0,240 "ci_high": 0.0,241 "n_items": 431,242 "n_groups": 90243 },244 "number_recall": {245 "mean": 1.0,246 "ci_low": 1.0,247 "ci_high": 1.0,248 "n_items": 431,249 "n_groups": 90250 },251 "placeholders_exact": {252 "mean": 1.0,253 "ci_low": 1.0,254 "ci_high": 1.0,255 "n_items": 431,256 "n_groups": 90257 }258 },259 "E": {260 "n": 853,261 "chrf": {262 "mean": 58.74248622593104,263 "ci_low": 56.6145166355214,264 "ci_high": 60.57302334898286,265 "n_items": 853,266 "n_groups": 91267 },268 "edit_sim": {269 "mean": 0.5854950604197606,270 "ci_low": 0.5695107554886489,271 "ci_high": 0.6007765861814817,272 "n_items": 853,273 "n_groups": 91274 },275 "rougeL": {276 "mean": 0.5844779012382167,277 "ci_low": 0.566233992013178,278 "ci_high": 0.6015491045639946,279 "n_items": 853,280 "n_groups": 91281 },282 "exact_match": {283 "mean": 0.0,284 "ci_low": 0.0,285 "ci_high": 0.0,286 "n_items": 853,287 "n_groups": 91288 },289 "number_recall": {290 "mean": 1.0,291 "ci_low": 1.0,292 "ci_high": 1.0,293 "n_items": 853,294 "n_groups": 91295 },296 "placeholders_exact": {297 "mean": 1.0,298 "ci_low": 1.0,299 "ci_high": 1.0,300 "n_items": 853,301 "n_groups": 91302 }303 }304 },305 "by_discipline": {306 "biomedicine": {307 "n": 438,308 "chrf": {309 "mean": 64.9254380774771,310 "ci_low": 58.81385957305288,311 "ci_high": 69.63004428586139,312 "n_items": 438,313 "n_groups": 22314 },315 "edit_sim": {316 "mean": 0.6502942537950974,317 "ci_low": 0.5977994990709982,318 "ci_high": 0.6905857007933726,319 "n_items": 438,320 "n_groups": 22321 },322 "rougeL": {323 "mean": 0.6570054387912583,324 "ci_low": 0.5974290353115929,325 "ci_high": 0.7014432300213587,326 "n_items": 438,327 "n_groups": 22328 },329 "exact_match": {330 "mean": 0.0,331 "ci_low": 0.0,332 "ci_high": 0.0,333 "n_items": 438,334 "n_groups": 22335 },336 "number_recall": {337 "mean": 1.0,338 "ci_low": 1.0,339 "ci_high": 1.0,340 "n_items": 438,341 "n_groups": 22342 },343 "placeholders_exact": {344 "mean": 1.0,345 "ci_low": 1.0,346 "ci_high": 1.0,347 "n_items": 438,348 "n_groups": 22349 }350 },351 "chemistry": {352 "n": 183,353 "chrf": {354 "mean": 65.8553950203832,355 "ci_low": 65.8553950203832,356 "ci_high": 65.8553950203832,357 "n_items": 183,358 "n_groups": 1359 },360 "edit_sim": {361 "mean": 0.6552121755535624,362 "ci_low": 0.6552121755535624,363 "ci_high": 0.6552121755535624,364 "n_items": 183,365 "n_groups": 1366 },367 "rougeL": {368 "mean": 0.663481276757275,369 "ci_low": 0.663481276757275,370 "ci_high": 0.663481276757275,371 "n_items": 183,372 "n_groups": 1373 },374 "exact_match": {375 "mean": 0.0,376 "ci_low": 0.0,377 "ci_high": 0.0,378 "n_items": 183,379 "n_groups": 1380 },381 "number_recall": {382 "mean": 1.0,383 "ci_low": 1.0,384 "ci_high": 1.0,385 "n_items": 183,386 "n_groups": 1387 },388 "placeholders_exact": {389 "mean": 1.0,390 "ci_low": 1.0,391 "ci_high": 1.0,392 "n_items": 183,393 "n_groups": 1394 }395 },396 "earth_sciences": {397 "n": 101,398 "chrf": {399 "mean": 62.7395764899059,400 "ci_low": 62.7395764899059,401 "ci_high": 62.7395764899059,402 "n_items": 101,403 "n_groups": 1404 },405 "edit_sim": {406 "mean": 0.6179181776956794,407 "ci_low": 0.6179181776956794,408 "ci_high": 0.6179181776956794,409 "n_items": 101,410 "n_groups": 1411 },412 "rougeL": {413 "mean": 0.6297734800043978,414 "ci_low": 0.6297734800043978,415 "ci_high": 0.6297734800043978,416 "n_items": 101,417 "n_groups": 1418 },419 "exact_match": {420 "mean": 0.0,421 "ci_low": 0.0,422 "ci_high": 0.0,423 "n_items": 101,424 "n_groups": 1425 },426 "number_recall": {427 "mean": 1.0,428 "ci_low": 1.0,429 "ci_high": 1.0,430 "n_items": 101,431 "n_groups": 1432 },433 "placeholders_exact": {434 "mean": 1.0,435 "ci_low": 1.0,436 "ci_high": 1.0,437 "n_items": 101,438 "n_groups": 1439 }440 },441 "economics": {442 "n": 569,443 "chrf": {444 "mean": 68.57782936318105,445 "ci_low": 63.244643867349204,446 "ci_high": 71.82017311456747,447 "n_items": 569,448 "n_groups": 8449 },450 "edit_sim": {451 "mean": 0.685221876079505,452 "ci_low": 0.6414071761858918,453 "ci_high": 0.712876490871604,454 "n_items": 569,455 "n_groups": 8456 },457 "rougeL": {458 "mean": 0.691525477790516,459 "ci_low": 0.6473375945737695,460 "ci_high": 0.7241787518748191,461 "n_items": 569,462 "n_groups": 8463 },464 "exact_match": {465 "mean": 0.0,466 "ci_low": 0.0,467 "ci_high": 0.0,468 "n_items": 569,469 "n_groups": 8470 },471 "number_recall": {472 "mean": 1.0,473 "ci_low": 1.0,474 "ci_high": 1.0,475 "n_items": 569,476 "n_groups": 8477 },478 "placeholders_exact": {479 "mean": 1.0,480 "ci_low": 1.0,481 "ci_high": 1.0,482 "n_items": 569,483 "n_groups": 8484 }485 },486 "engineering": {487 "n": 167,488 "chrf": {489 "mean": 60.33842100331852,490 "ci_low": 56.431732530027105,491 "ci_high": 61.965734011314495,492 "n_items": 167,493 "n_groups": 8494 },495 "edit_sim": {496 "mean": 0.610642454496027,497 "ci_low": 0.577830740792169,498 "ci_high": 0.6271112842606297,499 "n_items": 167,500 "n_groups": 8501 },502 "rougeL": {503 "mean": 0.6185459067314265,504 "ci_low": 0.5758305159115242,505 "ci_high": 0.6386590075970825,506 "n_items": 167,507 "n_groups": 8508 },509 "exact_match": {510 "mean": 0.0,511 "ci_low": 0.0,512 "ci_high": 0.0,513 "n_items": 167,514 "n_groups": 8515 },516 "number_recall": {517 "mean": 1.0,518 "ci_low": 1.0,519 "ci_high": 1.0,520 "n_items": 167,521 "n_groups": 8522 },523 "placeholders_exact": {524 "mean": 1.0,525 "ci_low": 1.0,526 "ci_high": 1.0,527 "n_items": 167,528 "n_groups": 8529 }530 },531 "finance": {532 "n": 75,533 "chrf": {534 "mean": 58.726295040291724,535 "ci_low": 57.428597034994695,536 "ci_high": 59.02412736937628,537 "n_items": 75,538 "n_groups": 2539 },540 "edit_sim": {541 "mean": 0.5923305213830021,542 "ci_low": 0.5699880286562786,543 "ci_high": 0.5974583065989716,544 "n_items": 75,545 "n_groups": 2546 },547 "rougeL": {548 "mean": 0.5895036531801899,549 "ci_low": 0.5683934557849601,550 "ci_high": 0.5943486165168,551 "n_items": 75,552 "n_groups": 2553 },554 "exact_match": {555 "mean": 0.0,556 "ci_low": 0.0,557 "ci_high": 0.0,558 "n_items": 75,559 "n_groups": 2560 },561 "number_recall": {562 "mean": 1.0,563 "ci_low": 1.0,564 "ci_high": 1.0,565 "n_items": 75,566 "n_groups": 2567 },568 "placeholders_exact": {569 "mean": 1.0,570 "ci_low": 1.0,571 "ci_high": 1.0,572 "n_items": 75,573 "n_groups": 2574 }575 },576 "general_reference": {577 "n": 256,578 "chrf": {579 "mean": 62.50155461171026,580 "ci_low": 59.14033159113068,581 "ci_high": 65.08697151422805,582 "n_items": 256,583 "n_groups": 12584 },585 "edit_sim": {586 "mean": 0.6478309079166366,587 "ci_low": 0.6077219418069565,588 "ci_high": 0.6740509272531243,589 "n_items": 256,590 "n_groups": 12591 },592 "rougeL": {593 "mean": 0.6498803140882436,594 "ci_low": 0.6061125094292216,595 "ci_high": 0.6777555449622311,596 "n_items": 256,597 "n_groups": 12598 },599 "exact_match": {600 "mean": 0.0,601 "ci_low": 0.0,602 "ci_high": 0.0,603 "n_items": 256,604 "n_groups": 12605 },606 "number_recall": {607 "mean": 1.0,608 "ci_low": 1.0,609 "ci_high": 1.0,610 "n_items": 256,611 "n_groups": 12612 },613 "placeholders_exact": {614 "mean": 1.0,615 "ci_low": 1.0,616 "ci_high": 1.0,617 "n_items": 256,618 "n_groups": 12619 }620 },621 "humanities": {622 "n": 253,623 "chrf": {624 "mean": 64.08281563813617,625 "ci_low": 60.41277333377432,626 "ci_high": 67.29817062061139,627 "n_items": 253,628 "n_groups": 9629 },630 "edit_sim": {631 "mean": 0.6603111708582151,632 "ci_low": 0.6262051007448073,633 "ci_high": 0.6986663432103171,634 "n_items": 253,635 "n_groups": 9636 },637 "rougeL": {638 "mean": 0.662722965922615,639 "ci_low": 0.6298290068768064,640 "ci_high": 0.6991021988691032,641 "n_items": 253,642 "n_groups": 9643 },644 "exact_match": {645 "mean": 0.0,646 "ci_low": 0.0,647 "ci_high": 0.0,648 "n_items": 253,649 "n_groups": 9650 },651 "number_recall": {652 "mean": 1.0,653 "ci_low": 1.0,654 "ci_high": 1.0,655 "n_items": 253,656 "n_groups": 9657 },658 "placeholders_exact": {659 "mean": 1.0,660 "ci_low": 1.0,661 "ci_high": 1.0,662 "n_items": 253,663 "n_groups": 9664 }665 },666 "life_sciences": {667 "n": 233,668 "chrf": {669 "mean": 61.670608490890025,670 "ci_low": 58.93212394017237,671 "ci_high": 64.74425675387941,672 "n_items": 233,673 "n_groups": 8674 },675 "edit_sim": {676 "mean": 0.6245438613217449,677 "ci_low": 0.6001815033781803,678 "ci_high": 0.6540180625716845,679 "n_items": 233,680 "n_groups": 8681 },682 "rougeL": {683 "mean": 0.632338858071035,684 "ci_low": 0.6053877365433781,685 "ci_high": 0.6644537776584715,686 "n_items": 233,687 "n_groups": 8688 },689 "exact_match": {690 "mean": 0.0,691 "ci_low": 0.0,692 "ci_high": 0.0,693 "n_items": 233,694 "n_groups": 8695 },696 "number_recall": {697 "mean": 1.0,698 "ci_low": 1.0,699 "ci_high": 1.0,700 "n_items": 233,701 "n_groups": 8702 },703 "placeholders_exact": {704 "mean": 1.0,705 "ci_low": 1.0,706 "ci_high": 1.0,707 "n_items": 233,708 "n_groups": 8709 }710 },711 "social_sciences": {712 "n": 299,713 "chrf": {714 "mean": 59.614130231686666,715 "ci_low": 57.111846075572615,716 "ci_high": 61.891268929062406,717 "n_items": 299,718 "n_groups": 21719 },720 "edit_sim": {721 "mean": 0.6294245389194356,722 "ci_low": 0.604790320153869,723 "ci_high": 0.6527311231072632,724 "n_items": 299,725 "n_groups": 21726 },727 "rougeL": {728 "mean": 0.6287078100092972,729 "ci_low": 0.6011321041435055,730 "ci_high": 0.6553881921349803,731 "n_items": 299,732 "n_groups": 21733 },734 "exact_match": {735 "mean": 0.0,736 "ci_low": 0.0,737 "ci_high": 0.0,738 "n_items": 299,739 "n_groups": 21740 },741 "number_recall": {742 "mean": 1.0,743 "ci_low": 1.0,744 "ci_high": 1.0,745 "n_items": 299,746 "n_groups": 21747 },748 "placeholders_exact": {749 "mean": 1.0,750 "ci_low": 1.0,751 "ci_high": 1.0,752 "n_items": 299,753 "n_groups": 21754 }755 }756 },757 "by_era": {758 "1900-1949": {759 "n": 74,760 "chrf": {761 "mean": 65.64610663681265,762 "ci_low": 62.65952282579613,763 "ci_high": 75.79393007677739,764 "n_items": 74,765 "n_groups": 5766 },767 "edit_sim": {768 "mean": 0.6843068174110488,769 "ci_low": 0.6318363532943063,770 "ci_high": 0.7340428818159833,771 "n_items": 74,772 "n_groups": 5773 },774 "rougeL": {775 "mean": 0.6786099790244803,776 "ci_low": 0.6134081382338876,777 "ci_high": 0.7467124836481459,778 "n_items": 74,779 "n_groups": 5780 },781 "exact_match": {782 "mean": 0.0,783 "ci_low": 0.0,784 "ci_high": 0.0,785 "n_items": 74,786 "n_groups": 5787 },788 "number_recall": {789 "mean": 1.0,790 "ci_low": 1.0,791 "ci_high": 1.0,792 "n_items": 74,793 "n_groups": 5794 },795 "placeholders_exact": {796 "mean": 1.0,797 "ci_low": 1.0,798 "ci_high": 1.0,799 "n_items": 74,800 "n_groups": 5801 }802 },803 "2010-2017": {804 "n": 527,805 "chrf": {806 "mean": 71.45435880464584,807 "ci_low": 67.91470395759085,808 "ci_high": 73.97119130953234,809 "n_items": 527,810 "n_groups": 4811 },812 "edit_sim": {813 "mean": 0.7065711045746813,814 "ci_low": 0.6754780725089824,815 "ci_high": 0.7286794617902269,816 "n_items": 527,817 "n_groups": 4818 },819 "rougeL": {820 "mean": 0.7147489643520705,821 "ci_low": 0.6743413033473679,822 "ci_high": 0.7434803856508687,823 "n_items": 527,824 "n_groups": 4825 },826 "exact_match": {827 "mean": 0.0,828 "ci_low": 0.0,829 "ci_high": 0.0,830 "n_items": 527,831 "n_groups": 4832 },833 "number_recall": {834 "mean": 1.0,835 "ci_low": 1.0,836 "ci_high": 1.0,837 "n_items": 527,838 "n_groups": 4839 },840 "placeholders_exact": {841 "mean": 1.0,842 "ci_low": 1.0,843 "ci_high": 1.0,844 "n_items": 527,845 "n_groups": 4846 }847 },848 "pre1900": {849 "n": 1973,850 "chrf": {851 "mean": 61.94643578758092,852 "ci_low": 60.52658310688107,853 "ci_high": 63.19245924626208,854 "n_items": 1973,855 "n_groups": 83856 },857 "edit_sim": {858 "mean": 0.6320599050223055,859 "ci_low": 0.6198290767996547,860 "ci_high": 0.6435337463194236,861 "n_items": 1973,862 "n_groups": 83863 },864 "rougeL": {865 "mean": 0.6367194788849736,866 "ci_low": 0.6232021730963995,867 "ci_high": 0.6488910498362768,868 "n_items": 1973,869 "n_groups": 83870 },871 "exact_match": {872 "mean": 0.0,873 "ci_low": 0.0,874 "ci_high": 0.0,875 "n_items": 1973,876 "n_groups": 83877 },878 "number_recall": {879 "mean": 1.0,880 "ci_low": 1.0,881 "ci_high": 1.0,882 "n_items": 1973,883 "n_groups": 83884 },885 "placeholders_exact": {886 "mean": 1.0,887 "ci_low": 1.0,888 "ci_high": 1.0,889 "n_items": 1973,890 "n_groups": 83891 }892 }893 },894 "by_role": {895 "abstract": {896 "n": 36,897 "chrf": {898 "mean": 68.95571226214852,899 "ci_low": 62.37875558948855,900 "ci_high": 74.9446536547026,901 "n_items": 36,902 "n_groups": 6903 },904 "edit_sim": {905 "mean": 0.6767492820814547,906 "ci_low": 0.6070052586142838,907 "ci_high": 0.7386519353860821,908 "n_items": 36,909 "n_groups": 6910 },911 "rougeL": {912 "mean": 0.6641650446834659,913 "ci_low": 0.5859844950667642,914 "ci_high": 0.7335947276849049,915 "n_items": 36,916 "n_groups": 6917 },918 "exact_match": {919 "mean": 0.0,920 "ci_low": 0.0,921 "ci_high": 0.0,922 "n_items": 36,923 "n_groups": 6924 },925 "number_recall": {926 "mean": 1.0,927 "ci_low": 1.0,928 "ci_high": 1.0,929 "n_items": 36,930 "n_groups": 6931 },932 "placeholders_exact": {933 "mean": 1.0,934 "ci_low": 1.0,935 "ci_high": 1.0,936 "n_items": 36,937 "n_groups": 6938 }939 },940 "chapter": {941 "n": 819,942 "chrf": {943 "mean": 62.750521729649655,944 "ci_low": 61.273140879729866,945 "ci_high": 64.10961049061893,946 "n_items": 819,947 "n_groups": 52948 },949 "edit_sim": {950 "mean": 0.637525708006685,951 "ci_low": 0.6223212889939643,952 "ci_high": 0.6517241697092807,953 "n_items": 819,954 "n_groups": 52955 },956 "rougeL": {957 "mean": 0.6445589742542261,958 "ci_low": 0.6277926079450082,959 "ci_high": 0.6593419721468882,960 "n_items": 819,961 "n_groups": 52962 },963 "exact_match": {964 "mean": 0.0,965 "ci_low": 0.0,966 "ci_high": 0.0,967 "n_items": 819,968 "n_groups": 52969 },970 "number_recall": {971 "mean": 1.0,972 "ci_low": 1.0,973 "ci_high": 1.0,974 "n_items": 819,975 "n_groups": 52976 },977 "placeholders_exact": {978 "mean": 1.0,979 "ci_low": 1.0,980 "ci_high": 1.0,981 "n_items": 819,982 "n_groups": 52983 }984 },985 "conclusion": {986 "n": 104,987 "chrf": {988 "mean": 71.38153113629575,989 "ci_low": 66.08795574821528,990 "ci_high": 76.66340240431285,991 "n_items": 104,992 "n_groups": 3993 },994 "edit_sim": {995 "mean": 0.7046406424899468,996 "ci_low": 0.6529736877139212,997 "ci_high": 0.7714604328469854,998 "n_items": 104,999 "n_groups": 31000 },1001 "rougeL": {1002 "mean": 0.7052279680163108,1003 "ci_low": 0.6429921055924467,1004 "ci_high": 0.7532845772022937,1005 "n_items": 104,1006 "n_groups": 31007 },1008 "exact_match": {1009 "mean": 0.0,1010 "ci_low": 0.0,1011 "ci_high": 0.0,1012 "n_items": 104,1013 "n_groups": 31014 },1015 "number_recall": {1016 "mean": 1.0,1017 "ci_low": 1.0,1018 "ci_high": 1.0,1019 "n_items": 104,1020 "n_groups": 31021 },1022 "placeholders_exact": {1023 "mean": 1.0,1024 "ci_low": 1.0,1025 "ci_high": 1.0,1026 "n_items": 104,1027 "n_groups": 31028 }1029 },1030 "data": {1031 "n": 11,1032 "chrf": {1033 "mean": 75.7413564411527,1034 "ci_low": 75.7413564411527,1035 "ci_high": 75.7413564411527,1036 "n_items": 11,1037 "n_groups": 11038 },1039 "edit_sim": {1040 "mean": 0.7598944205562982,1041 "ci_low": 0.7598944205562982,1042 "ci_high": 0.7598944205562982,1043 "n_items": 11,1044 "n_groups": 11045 },1046 "rougeL": {1047 "mean": 0.7709414052748312,1048 "ci_low": 0.7709414052748312,1049 "ci_high": 0.7709414052748312,1050 "n_items": 11,1051 "n_groups": 11052 },1053 "exact_match": {1054 "mean": 0.0,1055 "ci_low": 0.0,1056 "ci_high": 0.0,1057 "n_items": 11,1058 "n_groups": 11059 },1060 "number_recall": {1061 "mean": 1.0,1062 "ci_low": 1.0,1063 "ci_high": 1.0,1064 "n_items": 11,1065 "n_groups": 11066 },1067 "placeholders_exact": {1068 "mean": 1.0,1069 "ci_low": 1.0,1070 "ci_high": 1.0,1071 "n_items": 11,1072 "n_groups": 11073 }1074 },1075 "introduction": {1076 "n": 574,1077 "chrf": {1078 "mean": 62.60885091200246,1079 "ci_low": 59.92837985505705,1080 "ci_high": 64.54394523801085,1081 "n_items": 574,1082 "n_groups": 231083 },1084 "edit_sim": {1085 "mean": 0.6396909574630915,1086 "ci_low": 0.6128947040029951,1087 "ci_high": 0.6597776659746889,1088 "n_items": 574,1089 "n_groups": 231090 },1091 "rougeL": {1092 "mean": 0.6414231684269657,1093 "ci_low": 0.6146719105487655,1094 "ci_high": 0.6617508032594018,1095 "n_items": 574,1096 "n_groups": 231097 },1098 "exact_match": {1099 "mean": 0.0,1100 "ci_low": 0.0,1101 "ci_high": 0.0,1102 "n_items": 574,1103 "n_groups": 231104 },1105 "number_recall": {1106 "mean": 1.0,1107 "ci_low": 1.0,1108 "ci_high": 1.0,1109 "n_items": 574,1110 "n_groups": 231111 },1112 "placeholders_exact": {1113 "mean": 1.0,1114 "ci_low": 1.0,1115 "ci_high": 1.0,1116 "n_items": 574,1117 "n_groups": 231118 }1119 },1120 "methods": {1121 "n": 93,1122 "chrf": {1123 "mean": 71.73717241258542,1124 "ci_low": 68.79003297234811,1125 "ci_high": 78.43872757925446,1126 "n_items": 93,1127 "n_groups": 31128 },1129 "edit_sim": {1130 "mean": 0.7122987189383926,1131 "ci_low": 0.6847743145745996,1132 "ci_high": 0.8021818197375677,1133 "n_items": 93,1134 "n_groups": 31135 },1136 "rougeL": {1137 "mean": 0.7330951462373052,1138 "ci_low": 0.6961393682007592,1139 "ci_high": 0.8196585384325109,1140 "n_items": 93,1141 "n_groups": 31142 },1143 "exact_match": {1144 "mean": 0.0,1145 "ci_low": 0.0,1146 "ci_high": 0.0,1147 "n_items": 93,1148 "n_groups": 31149 },1150 "number_recall": {1151 "mean": 1.0,1152 "ci_low": 1.0,1153 "ci_high": 1.0,1154 "n_items": 93,1155 "n_groups": 31156 },1157 "placeholders_exact": {1158 "mean": 1.0,1159 "ci_low": 1.0,1160 "ci_high": 1.0,1161 "n_items": 93,1162 "n_groups": 31163 }1164 },1165 "other": {1166 "n": 163,1167 "chrf": {1168 "mean": 65.72867007086899,1169 "ci_low": 60.19070297351797,1170 "ci_high": 70.50492624446802,1171 "n_items": 163,1172 "n_groups": 91173 },1174 "edit_sim": {1175 "mean": 0.6775083017093715,1176 "ci_low": 0.6496213665282522,1177 "ci_high": 0.7081095298570069,1178 "n_items": 163,1179 "n_groups": 91180 },1181 "rougeL": {1182 "mean": 0.6849513527788677,1183 "ci_low": 0.6552866318111753,1184 "ci_high": 0.7157708759340021,1185 "n_items": 163,1186 "n_groups": 91187 },1188 "exact_match": {1189 "mean": 0.0,1190 "ci_low": 0.0,1191 "ci_high": 0.0,1192 "n_items": 163,1193 "n_groups": 91194 },1195 "number_recall": {1196 "mean": 1.0,1197 "ci_low": 1.0,1198 "ci_high": 1.0,1199 "n_items": 163,1200 "n_groups": 91201 },1202 "placeholders_exact": {1203 "mean": 1.0,1204 "ci_low": 1.0,1205 "ci_high": 1.0,1206 "n_items": 163,1207 "n_groups": 91208 }1209 },1210 "preface": {1211 "n": 562,1212 "chrf": {1213 "mean": 60.55035971219919,1214 "ci_low": 58.652536095845385,1215 "ci_high": 62.50461971236778,1216 "n_items": 562,1217 "n_groups": 481218 },1219 "edit_sim": {1220 "mean": 0.6194725672418172,1221 "ci_low": 0.6008745025707206,1222 "ci_high": 0.6387159860003614,1223 "n_items": 562,1224 "n_groups": 481225 },1226 "rougeL": {1227 "mean": 0.6216114559419788,1228 "ci_low": 0.601170782642842,1229 "ci_high": 0.6420415669534449,1230 "n_items": 562,1231 "n_groups": 481232 },1233 "exact_match": {1234 "mean": 0.0,1235 "ci_low": 0.0,1236 "ci_high": 0.0,1237 "n_items": 562,1238 "n_groups": 481239 },1240 "number_recall": {1241 "mean": 1.0,1242 "ci_low": 1.0,1243 "ci_high": 1.0,1244 "n_items": 562,1245 "n_groups": 481246 },1247 "placeholders_exact": {1248 "mean": 1.0,1249 "ci_low": 1.0,1250 "ci_high": 1.0,1251 "n_items": 562,1252 "n_groups": 481253 }1254 },1255 "related_work": {1256 "n": 18,1257 "chrf": {1258 "mean": 72.3052739429657,1259 "ci_low": 72.3052739429657,1260 "ci_high": 72.3052739429657,1261 "n_items": 18,1262 "n_groups": 11263 },1264 "edit_sim": {1265 "mean": 0.7229951120453381,1266 "ci_low": 0.7229951120453381,1267 "ci_high": 0.7229951120453381,1268 "n_items": 18,1269 "n_groups": 11270 },1271 "rougeL": {1272 "mean": 0.7060674890231744,1273 "ci_low": 0.7060674890231744,1274 "ci_high": 0.7060674890231744,1275 "n_items": 18,1276 "n_groups": 11277 },1278 "exact_match": {1279 "mean": 0.0,1280 "ci_low": 0.0,1281 "ci_high": 0.0,1282 "n_items": 18,1283 "n_groups": 11284 },1285 "number_recall": {1286 "mean": 1.0,1287 "ci_low": 1.0,1288 "ci_high": 1.0,1289 "n_items": 18,1290 "n_groups": 11291 },1292 "placeholders_exact": {1293 "mean": 1.0,1294 "ci_low": 1.0,1295 "ci_high": 1.0,1296 "n_items": 18,1297 "n_groups": 11298 }1299 },1300 "results": {1301 "n": 158,1302 "chrf": {1303 "mean": 71.32864265116359,1304 "ci_low": 68.7258411664295,1305 "ci_high": 76.99991379680031,1306 "n_items": 158,1307 "n_groups": 31308 },1309 "edit_sim": {1310 "mean": 0.6955794507389441,1311 "ci_low": 0.6747947376122235,1312 "ci_high": 0.724461273244573,1313 "n_items": 158,1314 "n_groups": 31315 },1316 "rougeL": {1317 "mean": 0.7114498757345004,1318 "ci_low": 0.6846941347127179,1319 "ci_high": 0.7548116462520746,1320 "n_items": 158,1321 "n_groups": 31322 },1323 "exact_match": {1324 "mean": 0.0,1325 "ci_low": 0.0,1326 "ci_high": 0.0,1327 "n_items": 158,1328 "n_groups": 31329 },1330 "number_recall": {1331 "mean": 1.0,1332 "ci_low": 1.0,1333 "ci_high": 1.0,1334 "n_items": 158,1335 "n_groups": 31336 },1337 "placeholders_exact": {1338 "mean": 1.0,1339 "ci_low": 1.0,1340 "ci_high": 1.0,1341 "n_items": 158,1342 "n_groups": 31343 }1344 },1345 "theory": {1346 "n": 36,1347 "chrf": {1348 "mean": 74.42017737491996,1349 "ci_low": 70.7601819717746,1350 "ci_high": 75.15217645554904,1351 "n_items": 36,1352 "n_groups": 21353 },1354 "edit_sim": {1355 "mean": 0.749960641767202,1356 "ci_low": 0.7486521250513761,1357 "ci_high": 0.7565032253463305,1358 "n_items": 36,1359 "n_groups": 21360 },1361 "rougeL": {1362 "mean": 0.7512171571918573,1363 "ci_low": 0.7342904062791326,1364 "ci_high": 0.7546025073744024,1365 "n_items": 36,1366 "n_groups": 21367 },1368 "exact_match": {1369 "mean": 0.0,1370 "ci_low": 0.0,1371 "ci_high": 0.0,1372 "n_items": 36,1373 "n_groups": 21374 },1375 "number_recall": {1376 "mean": 1.0,1377 "ci_low": 1.0,1378 "ci_high": 1.0,1379 "n_items": 36,1380 "n_groups": 21381 },1382 "placeholders_exact": {1383 "mean": 1.0,1384 "ci_low": 1.0,1385 "ci_high": 1.0,1386 "n_items": 36,1387 "n_groups": 21388 }1389 }1390 }1391 },1392 "B1_generic_paraphrase": {1393 "overall": {1394 "n": 2574,1395 "chrf": {1396 "mean": 61.95026347981732,1397 "ci_low": 60.144865479736254,1398 "ci_high": 63.49402541459499,1399 "n_items": 2574,1400 "n_groups": 921401 },1402 "edit_sim": {1403 "mean": 0.5334813142485878,1404 "ci_low": 0.5196156089890461,1405 "ci_high": 0.5460868875604556,1406 "n_items": 2574,1407 "n_groups": 921408 },1409 "rougeL": {1410 "mean": 0.5704931258550896,1411 "ci_low": 0.5543789331218507,1412 "ci_high": 0.5852137948012773,1413 "n_items": 2574,1414 "n_groups": 921415 },1416 "exact_match": {1417 "mean": 0.0,1418 "ci_low": 0.0,1419 "ci_high": 0.0,1420 "n_items": 2574,1421 "n_groups": 921422 },1423 "number_recall": {1424 "mean": 1.0,1425 "ci_low": 1.0,1426 "ci_high": 1.0,1427 "n_items": 2574,1428 "n_groups": 921429 },1430 "placeholders_exact": {1431 "mean": 1.0,1432 "ci_low": 1.0,1433 "ci_high": 1.0,1434 "n_items": 2574,1435 "n_groups": 921436 }1437 },1438 "by_variant": {1439 "A": {1440 "n": 436,1441 "chrf": {1442 "mean": 61.06375513514538,1443 "ci_low": 59.0101457526497,1444 "ci_high": 62.706362557882805,1445 "n_items": 436,1446 "n_groups": 911447 },1448 "edit_sim": {1449 "mean": 0.5292943480277754,1450 "ci_low": 0.5150739382930789,1451 "ci_high": 0.540943827022873,1452 "n_items": 436,1453 "n_groups": 911454 },1455 "rougeL": {1456 "mean": 0.5641859636278338,1457 "ci_low": 0.547116117298073,1458 "ci_high": 0.5787200369304426,1459 "n_items": 436,1460 "n_groups": 911461 },1462 "exact_match": {1463 "mean": 0.0,1464 "ci_low": 0.0,1465 "ci_high": 0.0,1466 "n_items": 436,1467 "n_groups": 911468 },1469 "number_recall": {1470 "mean": 1.0,1471 "ci_low": 1.0,1472 "ci_high": 1.0,1473 "n_items": 436,1474 "n_groups": 911475 },1476 "placeholders_exact": {1477 "mean": 1.0,1478 "ci_low": 1.0,1479 "ci_high": 1.0,1480 "n_items": 436,1481 "n_groups": 911482 }1483 },1484 "B": {1485 "n": 416,1486 "chrf": {1487 "mean": 67.87137431025907,1488 "ci_low": 65.7258358521548,1489 "ci_high": 69.80673313199921,1490 "n_items": 416,1491 "n_groups": 901492 },1493 "edit_sim": {1494 "mean": 0.5771015754912718,1495 "ci_low": 0.5575645858750686,1496 "ci_high": 0.5941383364637394,1497 "n_items": 416,1498 "n_groups": 901499 },1500 "rougeL": {1501 "mean": 0.6263649628503898,1502 "ci_low": 0.6034152606054319,1503 "ci_high": 0.6466069878686374,1504 "n_items": 416,1505 "n_groups": 901506 },1507 "exact_match": {1508 "mean": 0.0,1509 "ci_low": 0.0,1510 "ci_high": 0.0,1511 "n_items": 416,1512 "n_groups": 901513 },1514 "number_recall": {1515 "mean": 1.0,1516 "ci_low": 1.0,1517 "ci_high": 1.0,1518 "n_items": 416,1519 "n_groups": 901520 },1521 "placeholders_exact": {1522 "mean": 1.0,1523 "ci_low": 1.0,1524 "ci_high": 1.0,1525 "n_items": 416,1526 "n_groups": 901527 }1528 },1529 "C": {1530 "n": 438,1531 "chrf": {1532 "mean": 67.26319597469887,1533 "ci_low": 65.61135436020908,1534 "ci_high": 68.90694838857921,1535 "n_items": 438,1536 "n_groups": 911537 },1538 "edit_sim": {1539 "mean": 0.5850713008324954,1540 "ci_low": 0.5685409669312422,1541 "ci_high": 0.600620523230842,1542 "n_items": 438,1543 "n_groups": 911544 },1545 "rougeL": {1546 "mean": 0.6346318925418479,1547 "ci_low": 0.6171833117496406,1548 "ci_high": 0.650535296978561,1549 "n_items": 438,1550 "n_groups": 911551 },1552 "exact_match": {1553 "mean": 0.0,1554 "ci_low": 0.0,1555 "ci_high": 0.0,1556 "n_items": 438,1557 "n_groups": 911558 },1559 "number_recall": {1560 "mean": 1.0,1561 "ci_low": 1.0,1562 "ci_high": 1.0,1563 "n_items": 438,1564 "n_groups": 911565 },1566 "placeholders_exact": {1567 "mean": 1.0,1568 "ci_low": 1.0,1569 "ci_high": 1.0,1570 "n_items": 438,1571 "n_groups": 911572 }1573 },1574 "D": {1575 "n": 431,1576 "chrf": {1577 "mean": 61.0106029910069,1578 "ci_low": 58.86600075981962,1579 "ci_high": 62.77154776521119,1580 "n_items": 431,1581 "n_groups": 901582 },1583 "edit_sim": {1584 "mean": 0.53340741902563,1585 "ci_low": 0.5132649458520095,1586 "ci_high": 0.5504158323898384,1587 "n_items": 431,1588 "n_groups": 901589 },1590 "rougeL": {1591 "mean": 0.5662542740500905,1592 "ci_low": 0.5459151537854872,1593 "ci_high": 0.5829326411304466,1594 "n_items": 431,1595 "n_groups": 901596 },1597 "exact_match": {1598 "mean": 0.0,1599 "ci_low": 0.0,1600 "ci_high": 0.0,1601 "n_items": 431,1602 "n_groups": 901603 },1604 "number_recall": {1605 "mean": 1.0,1606 "ci_low": 1.0,1607 "ci_high": 1.0,1608 "n_items": 431,1609 "n_groups": 901610 },1611 "placeholders_exact": {1612 "mean": 1.0,1613 "ci_low": 1.0,1614 "ci_high": 1.0,1615 "n_items": 431,1616 "n_groups": 901617 }1618 },1619 "E": {1620 "n": 853,1621 "chrf": {1622 "mean": 57.26241444198892,1623 "ci_low": 55.31828248127718,1624 "ci_high": 58.8657020089396,1625 "n_items": 853,1626 "n_groups": 911627 },1628 "edit_sim": {1629 "mean": 0.4878950578742161,1630 "ci_low": 0.4736857216864583,1631 "ci_high": 0.5016842261883262,1632 "n_items": 853,1633 "n_groups": 911634 },1635 "rougeL": {1636 "mean": 0.5156764832527366,1637 "ci_low": 0.49997029657187997,1638 "ci_high": 0.5312619931747842,1639 "n_items": 853,1640 "n_groups": 911641 },1642 "exact_match": {1643 "mean": 0.0,1644 "ci_low": 0.0,1645 "ci_high": 0.0,1646 "n_items": 853,1647 "n_groups": 911648 },1649 "number_recall": {1650 "mean": 1.0,1651 "ci_low": 1.0,1652 "ci_high": 1.0,1653 "n_items": 853,1654 "n_groups": 911655 },1656 "placeholders_exact": {1657 "mean": 1.0,1658 "ci_low": 1.0,1659 "ci_high": 1.0,1660 "n_items": 853,1661 "n_groups": 911662 }1663 }1664 },1665 "by_discipline": {1666 "biomedicine": {1667 "n": 438,1668 "chrf": {1669 "mean": 62.71712640165419,1670 "ci_low": 57.35059506811734,1671 "ci_high": 66.62380119444333,1672 "n_items": 438,1673 "n_groups": 221674 },1675 "edit_sim": {1676 "mean": 0.536445858442019,1677 "ci_low": 0.4942231038279407,1678 "ci_high": 0.5665471264070565,1679 "n_items": 438,1680 "n_groups": 221681 },1682 "rougeL": {1683 "mean": 0.57559383019852,1684 "ci_low": 0.5239887920784685,1685 "ci_high": 0.6116200142269719,1686 "n_items": 438,1687 "n_groups": 221688 },1689 "exact_match": {1690 "mean": 0.0,1691 "ci_low": 0.0,1692 "ci_high": 0.0,1693 "n_items": 438,1694 "n_groups": 221695 },1696 "number_recall": {1697 "mean": 1.0,1698 "ci_low": 1.0,1699 "ci_high": 1.0,1700 "n_items": 438,1701 "n_groups": 221702 },1703 "placeholders_exact": {1704 "mean": 1.0,1705 "ci_low": 1.0,1706 "ci_high": 1.0,1707 "n_items": 438,1708 "n_groups": 221709 }1710 },1711 "chemistry": {1712 "n": 183,1713 "chrf": {1714 "mean": 63.73887421129732,1715 "ci_low": 63.73887421129732,1716 "ci_high": 63.73887421129732,1717 "n_items": 183,1718 "n_groups": 11719 },1720 "edit_sim": {1721 "mean": 0.531678466343424,1722 "ci_low": 0.531678466343424,1723 "ci_high": 0.531678466343424,1724 "n_items": 183,1725 "n_groups": 11726 },1727 "rougeL": {1728 "mean": 0.5706893714980146,1729 "ci_low": 0.5706893714980146,1730 "ci_high": 0.5706893714980146,1731 "n_items": 183,1732 "n_groups": 11733 },1734 "exact_match": {1735 "mean": 0.0,1736 "ci_low": 0.0,1737 "ci_high": 0.0,1738 "n_items": 183,1739 "n_groups": 11740 },1741 "number_recall": {1742 "mean": 1.0,1743 "ci_low": 1.0,1744 "ci_high": 1.0,1745 "n_items": 183,1746 "n_groups": 11747 },1748 "placeholders_exact": {1749 "mean": 1.0,1750 "ci_low": 1.0,1751 "ci_high": 1.0,1752 "n_items": 183,1753 "n_groups": 11754 }1755 },1756 "earth_sciences": {1757 "n": 101,1758 "chrf": {1759 "mean": 61.06462587104876,1760 "ci_low": 61.06462587104876,1761 "ci_high": 61.06462587104876,1762 "n_items": 101,1763 "n_groups": 11764 },1765 "edit_sim": {1766 "mean": 0.4947292110811029,1767 "ci_low": 0.4947292110811029,1768 "ci_high": 0.4947292110811029,1769 "n_items": 101,1770 "n_groups": 11771 },1772 "rougeL": {1773 "mean": 0.5391315133692819,1774 "ci_low": 0.5391315133692819,1775 "ci_high": 0.5391315133692819,1776 "n_items": 101,1777 "n_groups": 11778 },1779 "exact_match": {1780 "mean": 0.0,1781 "ci_low": 0.0,1782 "ci_high": 0.0,1783 "n_items": 101,1784 "n_groups": 11785 },1786 "number_recall": {1787 "mean": 1.0,1788 "ci_low": 1.0,1789 "ci_high": 1.0,1790 "n_items": 101,1791 "n_groups": 11792 },1793 "placeholders_exact": {1794 "mean": 1.0,1795 "ci_low": 1.0,1796 "ci_high": 1.0,1797 "n_items": 101,1798 "n_groups": 11799 }1800 },1801 "economics": {1802 "n": 569,1803 "chrf": {1804 "mean": 65.70962783286393,1805 "ci_low": 61.103883583596165,1806 "ci_high": 68.45097876600073,1807 "n_items": 569,1808 "n_groups": 81809 },1810 "edit_sim": {1811 "mean": 0.5603893190253577,1812 "ci_low": 0.5207067811933755,1813 "ci_high": 0.5812654753434963,1814 "n_items": 569,1815 "n_groups": 81816 },1817 "rougeL": {1818 "mean": 0.5989535101722757,1819 "ci_low": 0.5573034632619471,1820 "ci_high": 0.6285529119015291,1821 "n_items": 569,1822 "n_groups": 81823 },1824 "exact_match": {1825 "mean": 0.0,1826 "ci_low": 0.0,1827 "ci_high": 0.0,1828 "n_items": 569,1829 "n_groups": 81830 },1831 "number_recall": {1832 "mean": 1.0,1833 "ci_low": 1.0,1834 "ci_high": 1.0,1835 "n_items": 569,1836 "n_groups": 81837 },1838 "placeholders_exact": {1839 "mean": 1.0,1840 "ci_low": 1.0,1841 "ci_high": 1.0,1842 "n_items": 569,1843 "n_groups": 81844 }1845 },1846 "engineering": {1847 "n": 167,1848 "chrf": {1849 "mean": 58.9378981613345,1850 "ci_low": 55.321507331247744,1851 "ci_high": 60.39843858135444,1852 "n_items": 167,1853 "n_groups": 81854 },1855 "edit_sim": {1856 "mean": 0.5214040625290941,1857 "ci_low": 0.49820833277419674,1858 "ci_high": 0.5426777513324086,1859 "n_items": 167,1860 "n_groups": 81861 },1862 "rougeL": {1863 "mean": 0.5548030322599071,1864 "ci_low": 0.5160723473386032,1865 "ci_high": 0.5754884841963746,1866 "n_items": 167,1867 "n_groups": 81868 },1869 "exact_match": {1870 "mean": 0.0,1871 "ci_low": 0.0,1872 "ci_high": 0.0,1873 "n_items": 167,1874 "n_groups": 81875 },1876 "number_recall": {1877 "mean": 1.0,1878 "ci_low": 1.0,1879 "ci_high": 1.0,1880 "n_items": 167,1881 "n_groups": 81882 },1883 "placeholders_exact": {1884 "mean": 1.0,1885 "ci_low": 1.0,1886 "ci_high": 1.0,1887 "n_items": 167,1888 "n_groups": 81889 }1890 },1891 "finance": {1892 "n": 75,1893 "chrf": {1894 "mean": 57.323741326266315,1895 "ci_low": 55.96992024013606,1896 "ci_high": 57.63445436242736,1897 "n_items": 75,1898 "n_groups": 21899 },1900 "edit_sim": {1901 "mean": 0.4931947635745549,1902 "ci_low": 0.4870252535239305,1903 "ci_high": 0.5200762002237042,1904 "n_items": 75,1905 "n_groups": 21906 },1907 "rougeL": {1908 "mean": 0.5139399539749974,1909 "ci_low": 0.5114604493952133,1910 "ci_high": 0.5247435096440564,1911 "n_items": 75,1912 "n_groups": 21913 },1914 "exact_match": {1915 "mean": 0.0,1916 "ci_low": 0.0,1917 "ci_high": 0.0,1918 "n_items": 75,1919 "n_groups": 21920 },1921 "number_recall": {1922 "mean": 1.0,1923 "ci_low": 1.0,1924 "ci_high": 1.0,1925 "n_items": 75,1926 "n_groups": 21927 },1928 "placeholders_exact": {1929 "mean": 1.0,1930 "ci_low": 1.0,1931 "ci_high": 1.0,1932 "n_items": 75,1933 "n_groups": 21934 }1935 },1936 "general_reference": {1937 "n": 256,1938 "chrf": {1939 "mean": 60.79659452288393,1940 "ci_low": 57.65027264451892,1941 "ci_high": 63.39866498998666,1942 "n_items": 256,1943 "n_groups": 121944 },1945 "edit_sim": {1946 "mean": 0.5418516383328331,1947 "ci_low": 0.5063425164164876,1948 "ci_high": 0.564461038216024,1949 "n_items": 256,1950 "n_groups": 121951 },1952 "rougeL": {1953 "mean": 0.5760171173030098,1954 "ci_low": 0.5353884192545337,1955 "ci_high": 0.6028299276714263,1956 "n_items": 256,1957 "n_groups": 121958 },1959 "exact_match": {1960 "mean": 0.0,1961 "ci_low": 0.0,1962 "ci_high": 0.0,1963 "n_items": 256,1964 "n_groups": 121965 },1966 "number_recall": {1967 "mean": 1.0,1968 "ci_low": 1.0,1969 "ci_high": 1.0,1970 "n_items": 256,1971 "n_groups": 121972 },1973 "placeholders_exact": {1974 "mean": 1.0,1975 "ci_low": 1.0,1976 "ci_high": 1.0,1977 "n_items": 256,1978 "n_groups": 121979 }1980 },1981 "humanities": {1982 "n": 253,1983 "chrf": {1984 "mean": 61.988819332330436,1985 "ci_low": 58.64446548660641,1986 "ci_high": 65.32472004435365,1987 "n_items": 253,1988 "n_groups": 91989 },1990 "edit_sim": {1991 "mean": 0.5378938536206815,1992 "ci_low": 0.5182807598861194,1993 "ci_high": 0.5693173467452783,1994 "n_items": 253,1995 "n_groups": 91996 },1997 "rougeL": {1998 "mean": 0.5777441160747941,1999 "ci_low": 0.5539883993047662,2000 "ci_high": 0.6102906037705159,2001 "n_items": 253,2002 "n_groups": 92003 },2004 "exact_match": {2005 "mean": 0.0,2006 "ci_low": 0.0,2007 "ci_high": 0.0,2008 "n_items": 253,2009 "n_groups": 92010 },2011 "number_recall": {2012 "mean": 1.0,2013 "ci_low": 1.0,2014 "ci_high": 1.0,2015 "n_items": 253,2016 "n_groups": 92017 },2018 "placeholders_exact": {2019 "mean": 1.0,2020 "ci_low": 1.0,2021 "ci_high": 1.0,2022 "n_items": 253,2023 "n_groups": 92024 }2025 },2026 "life_sciences": {2027 "n": 233,2028 "chrf": {2029 "mean": 60.03606728068648,2030 "ci_low": 57.24849987256594,2031 "ci_high": 63.19250738019483,2032 "n_items": 233,2033 "n_groups": 82034 },2035 "edit_sim": {2036 "mean": 0.5061561767223423,2037 "ci_low": 0.4869433522762658,2038 "ci_high": 0.5325874501099752,2039 "n_items": 233,2040 "n_groups": 82041 },2042 "rougeL": {2043 "mean": 0.5453147917116062,2044 "ci_low": 0.5218748757152637,2045 "ci_high": 0.5763013803739294,2046 "n_items": 233,2047 "n_groups": 82048 },2049 "exact_match": {2050 "mean": 0.0,2051 "ci_low": 0.0,2052 "ci_high": 0.0,2053 "n_items": 233,2054 "n_groups": 82055 },2056 "number_recall": {2057 "mean": 1.0,2058 "ci_low": 1.0,2059 "ci_high": 1.0,2060 "n_items": 233,2061 "n_groups": 82062 },2063 "placeholders_exact": {2064 "mean": 1.0,2065 "ci_low": 1.0,2066 "ci_high": 1.0,2067 "n_items": 233,2068 "n_groups": 82069 }2070 },2071 "social_sciences": {2072 "n": 299,2073 "chrf": {2074 "mean": 58.16703894592532,2075 "ci_low": 55.81570389904578,2076 "ci_high": 60.32736573877665,2077 "n_items": 299,2078 "n_groups": 212079 },2080 "edit_sim": {2081 "mean": 0.5193700515946504,2082 "ci_low": 0.4928082147621954,2083 "ci_high": 0.5465272447683005,2084 "n_items": 299,2085 "n_groups": 212086 },2087 "rougeL": {2088 "mean": 0.5510388976614142,2089 "ci_low": 0.5212025978652893,2090 "ci_high": 0.5802925710933681,2091 "n_items": 299,2092 "n_groups": 212093 },2094 "exact_match": {2095 "mean": 0.0,2096 "ci_low": 0.0,2097 "ci_high": 0.0,2098 "n_items": 299,2099 "n_groups": 212100 },2101 "number_recall": {2102 "mean": 1.0,2103 "ci_low": 1.0,2104 "ci_high": 1.0,2105 "n_items": 299,2106 "n_groups": 212107 },2108 "placeholders_exact": {2109 "mean": 1.0,2110 "ci_low": 1.0,2111 "ci_high": 1.0,2112 "n_items": 299,2113 "n_groups": 212114 }2115 }2116 },2117 "by_era": {2118 "1900-1949": {2119 "n": 74,2120 "chrf": {2121 "mean": 63.84465688053108,2122 "ci_low": 60.65607518816218,2123 "ci_high": 72.58037938514916,2124 "n_items": 74,2125 "n_groups": 52126 },2127 "edit_sim": {2128 "mean": 0.5748639162447151,2129 "ci_low": 0.5163165532814609,2130 "ci_high": 0.6154847870669189,2131 "n_items": 74,2132 "n_groups": 52133 },2134 "rougeL": {2135 "mean": 0.6065498099180707,2136 "ci_low": 0.5366014590829109,2137 "ci_high": 0.6659857919050227,2138 "n_items": 74,2139 "n_groups": 52140 },2141 "exact_match": {2142 "mean": 0.0,2143 "ci_low": 0.0,2144 "ci_high": 0.0,2145 "n_items": 74,2146 "n_groups": 52147 },2148 "number_recall": {2149 "mean": 1.0,2150 "ci_low": 1.0,2151 "ci_high": 1.0,2152 "n_items": 74,2153 "n_groups": 52154 },2155 "placeholders_exact": {2156 "mean": 1.0,2157 "ci_low": 1.0,2158 "ci_high": 1.0,2159 "n_items": 74,2160 "n_groups": 52161 }2162 },2163 "2010-2017": {2164 "n": 527,2165 "chrf": {2166 "mean": 68.05210985790323,2167 "ci_low": 65.0011576307012,2168 "ci_high": 70.22145575971246,2169 "n_items": 527,2170 "n_groups": 42171 },2172 "edit_sim": {2173 "mean": 0.5759560832870316,2174 "ci_low": 0.5506108545661897,2175 "ci_high": 0.5939775283839938,2176 "n_items": 527,2177 "n_groups": 42178 },2179 "rougeL": {2180 "mean": 0.6179243186341252,2181 "ci_low": 0.5798503257193923,2182 "ci_high": 0.6449964109988218,2183 "n_items": 527,2184 "n_groups": 42185 },2186 "exact_match": {2187 "mean": 0.0,2188 "ci_low": 0.0,2189 "ci_high": 0.0,2190 "n_items": 527,2191 "n_groups": 42192 },2193 "number_recall": {2194 "mean": 1.0,2195 "ci_low": 1.0,2196 "ci_high": 1.0,2197 "n_items": 527,2198 "n_groups": 42199 },2200 "placeholders_exact": {2201 "mean": 1.0,2202 "ci_low": 1.0,2203 "ci_high": 1.0,2204 "n_items": 527,2205 "n_groups": 42206 }2207 },2208 "pre1900": {2209 "n": 1973,2210 "chrf": {2211 "mean": 60.24937237342903,2212 "ci_low": 58.892285159862695,2213 "ci_high": 61.42228625752474,2214 "n_items": 1973,2215 "n_groups": 832216 },2217 "edit_sim": {2218 "mean": 0.5205839418051142,2219 "ci_low": 0.5108634502532481,2220 "ci_high": 0.5303623329188405,2221 "n_items": 1973,2222 "n_groups": 832223 },2224 "rougeL": {2225 "mean": 0.5564716189036387,2226 "ci_low": 0.5446501423496656,2227 "ci_high": 0.567843863659828,2228 "n_items": 1973,2229 "n_groups": 832230 },2231 "exact_match": {2232 "mean": 0.0,2233 "ci_low": 0.0,2234 "ci_high": 0.0,2235 "n_items": 1973,2236 "n_groups": 832237 },2238 "number_recall": {2239 "mean": 1.0,2240 "ci_low": 1.0,2241 "ci_high": 1.0,2242 "n_items": 1973,2243 "n_groups": 832244 },2245 "placeholders_exact": {2246 "mean": 1.0,2247 "ci_low": 1.0,2248 "ci_high": 1.0,2249 "n_items": 1973,2250 "n_groups": 832251 }2252 }2253 },2254 "by_role": {2255 "abstract": {2256 "n": 36,2257 "chrf": {2258 "mean": 66.85029288056049,2259 "ci_low": 60.633149576730844,2260 "ci_high": 72.18310558583765,2261 "n_items": 36,2262 "n_groups": 62263 },2264 "edit_sim": {2265 "mean": 0.5761926230407205,2266 "ci_low": 0.49683629811150765,2267 "ci_high": 0.6576022144084166,2268 "n_items": 36,2269 "n_groups": 62270 },2271 "rougeL": {2272 "mean": 0.5904939079489961,2273 "ci_low": 0.5049684370371156,2274 "ci_high": 0.668645509264556,2275 "n_items": 36,2276 "n_groups": 62277 },2278 "exact_match": {2279 "mean": 0.0,2280 "ci_low": 0.0,2281 "ci_high": 0.0,2282 "n_items": 36,2283 "n_groups": 62284 },2285 "number_recall": {2286 "mean": 1.0,2287 "ci_low": 1.0,2288 "ci_high": 1.0,2289 "n_items": 36,2290 "n_groups": 62291 },2292 "placeholders_exact": {2293 "mean": 1.0,2294 "ci_low": 1.0,2295 "ci_high": 1.0,2296 "n_items": 36,2297 "n_groups": 62298 }2299 },2300 "chapter": {2301 "n": 819,2302 "chrf": {2303 "mean": 60.99412675316885,2304 "ci_low": 59.57336111692297,2305 "ci_high": 62.27474480071903,2306 "n_items": 819,2307 "n_groups": 522308 },2309 "edit_sim": {2310 "mean": 0.5291196028970369,2311 "ci_low": 0.5142254101081837,2312 "ci_high": 0.5446837217187751,2313 "n_items": 819,2314 "n_groups": 522315 },2316 "rougeL": {2317 "mean": 0.5668291106592754,2318 "ci_low": 0.5496146232404818,2319 "ci_high": 0.5832558050913984,2320 "n_items": 819,2321 "n_groups": 522322 },2323 "exact_match": {2324 "mean": 0.0,2325 "ci_low": 0.0,2326 "ci_high": 0.0,2327 "n_items": 819,2328 "n_groups": 522329 },2330 "number_recall": {2331 "mean": 1.0,2332 "ci_low": 1.0,2333 "ci_high": 1.0,2334 "n_items": 819,2335 "n_groups": 522336 },2337 "placeholders_exact": {2338 "mean": 1.0,2339 "ci_low": 1.0,2340 "ci_high": 1.0,2341 "n_items": 819,2342 "n_groups": 522343 }2344 },2345 "conclusion": {2346 "n": 104,2347 "chrf": {2348 "mean": 68.0395085390351,2349 "ci_low": 63.86987559938589,2350 "ci_high": 70.94758765591861,2351 "n_items": 104,2352 "n_groups": 32353 },2354 "edit_sim": {2355 "mean": 0.5727534017224272,2356 "ci_low": 0.5466438047917168,2357 "ci_high": 0.6507373863504919,2358 "n_items": 104,2359 "n_groups": 32360 },2361 "rougeL": {2362 "mean": 0.6064006820560239,2363 "ci_low": 0.563224585154559,2364 "ci_high": 0.6480466175802273,2365 "n_items": 104,2366 "n_groups": 32367 },2368 "exact_match": {2369 "mean": 0.0,2370 "ci_low": 0.0,2371 "ci_high": 0.0,2372 "n_items": 104,2373 "n_groups": 32374 },2375 "number_recall": {2376 "mean": 1.0,2377 "ci_low": 1.0,2378 "ci_high": 1.0,2379 "n_items": 104,2380 "n_groups": 32381 },2382 "placeholders_exact": {2383 "mean": 1.0,2384 "ci_low": 1.0,2385 "ci_high": 1.0,2386 "n_items": 104,2387 "n_groups": 32388 }2389 },2390 "data": {2391 "n": 11,2392 "chrf": {2393 "mean": 73.06759751972446,2394 "ci_low": 73.06759751972446,2395 "ci_high": 73.06759751972446,2396 "n_items": 11,2397 "n_groups": 12398 },2399 "edit_sim": {2400 "mean": 0.6219387080979671,2401 "ci_low": 0.6219387080979671,2402 "ci_high": 0.6219387080979671,2403 "n_items": 11,2404 "n_groups": 12405 },2406 "rougeL": {2407 "mean": 0.6666379347126354,2408 "ci_low": 0.6666379347126354,2409 "ci_high": 0.6666379347126354,2410 "n_items": 11,2411 "n_groups": 12412 },2413 "exact_match": {2414 "mean": 0.0,2415 "ci_low": 0.0,2416 "ci_high": 0.0,2417 "n_items": 11,2418 "n_groups": 12419 },2420 "number_recall": {2421 "mean": 1.0,2422 "ci_low": 1.0,2423 "ci_high": 1.0,2424 "n_items": 11,2425 "n_groups": 12426 },2427 "placeholders_exact": {2428 "mean": 1.0,2429 "ci_low": 1.0,2430 "ci_high": 1.0,2431 "n_items": 11,2432 "n_groups": 12433 }2434 },2435 "introduction": {2436 "n": 574,2437 "chrf": {2438 "mean": 60.60694303430162,2439 "ci_low": 58.03567798321224,2440 "ci_high": 62.4248812464981,2441 "n_items": 574,2442 "n_groups": 232443 },2444 "edit_sim": {2445 "mean": 0.5214370711151883,2446 "ci_low": 0.4995569684185669,2447 "ci_high": 0.5387237048294649,2448 "n_items": 574,2449 "n_groups": 232450 },2451 "rougeL": {2452 "mean": 0.5551748997732724,2453 "ci_low": 0.5310114237735251,2454 "ci_high": 0.5743195851300883,2455 "n_items": 574,2456 "n_groups": 232457 },2458 "exact_match": {2459 "mean": 0.0,2460 "ci_low": 0.0,2461 "ci_high": 0.0,2462 "n_items": 574,2463 "n_groups": 232464 },2465 "number_recall": {2466 "mean": 1.0,2467 "ci_low": 1.0,2468 "ci_high": 1.0,2469 "n_items": 574,2470 "n_groups": 232471 },2472 "placeholders_exact": {2473 "mean": 1.0,2474 "ci_low": 1.0,2475 "ci_high": 1.0,2476 "n_items": 574,2477 "n_groups": 232478 }2479 },2480 "methods": {2481 "n": 93,2482 "chrf": {2483 "mean": 68.83656978796643,2484 "ci_low": 66.08483667792237,2485 "ci_high": 76.8414149164182,2486 "n_items": 93,2487 "n_groups": 32488 },2489 "edit_sim": {2490 "mean": 0.5778844498795325,2491 "ci_low": 0.5331797007674168,2492 "ci_high": 0.7271341001508592,2493 "n_items": 93,2494 "n_groups": 32495 },2496 "rougeL": {2497 "mean": 0.6363022753829289,2498 "ci_low": 0.585059673209504,2499 "ci_high": 0.7741643138793904,2500 "n_items": 93,2501 "n_groups": 32502 },2503 "exact_match": {2504 "mean": 0.0,2505 "ci_low": 0.0,2506 "ci_high": 0.0,2507 "n_items": 93,2508 "n_groups": 32509 },2510 "number_recall": {2511 "mean": 1.0,2512 "ci_low": 1.0,2513 "ci_high": 1.0,2514 "n_items": 93,2515 "n_groups": 32516 },2517 "placeholders_exact": {2518 "mean": 1.0,2519 "ci_low": 1.0,2520 "ci_high": 1.0,2521 "n_items": 93,2522 "n_groups": 32523 }2524 },2525 "other": {2526 "n": 163,2527 "chrf": {2528 "mean": 63.22734806529833,2529 "ci_low": 58.58890222978441,2530 "ci_high": 66.99764069914245,2531 "n_items": 163,2532 "n_groups": 92533 },2534 "edit_sim": {2535 "mean": 0.5543792092092076,2536 "ci_low": 0.5231595051596732,2537 "ci_high": 0.586713542406686,2538 "n_items": 163,2539 "n_groups": 92540 },2541 "rougeL": {2542 "mean": 0.6001272009439224,2543 "ci_low": 0.5600001207794363,2544 "ci_high": 0.6314054415577947,2545 "n_items": 163,2546 "n_groups": 92547 },2548 "exact_match": {2549 "mean": 0.0,2550 "ci_low": 0.0,2551 "ci_high": 0.0,2552 "n_items": 163,2553 "n_groups": 92554 },2555 "number_recall": {2556 "mean": 1.0,2557 "ci_low": 1.0,2558 "ci_high": 1.0,2559 "n_items": 163,2560 "n_groups": 92561 },2562 "placeholders_exact": {2563 "mean": 1.0,2564 "ci_low": 1.0,2565 "ci_high": 1.0,2566 "n_items": 163,2567 "n_groups": 92568 }2569 },2570 "preface": {2571 "n": 562,2572 "chrf": {2573 "mean": 59.13907477494464,2574 "ci_low": 57.32380100512407,2575 "ci_high": 61.015547633413696,2576 "n_items": 562,2577 "n_groups": 482578 },2579 "edit_sim": {2580 "mean": 0.5084925184036619,2581 "ci_low": 0.49276460675718775,2582 "ci_high": 0.526234648941043,2583 "n_items": 562,2584 "n_groups": 482585 },2586 "rougeL": {2587 "mean": 0.5423328823927577,2588 "ci_low": 0.5239587557901894,2589 "ci_high": 0.5619311539459746,2590 "n_items": 562,2591 "n_groups": 482592 },2593 "exact_match": {2594 "mean": 0.0,2595 "ci_low": 0.0,2596 "ci_high": 0.0,2597 "n_items": 562,2598 "n_groups": 482599 },2600 "number_recall": {2601 "mean": 1.0,2602 "ci_low": 1.0,2603 "ci_high": 1.0,2604 "n_items": 562,2605 "n_groups": 482606 },2607 "placeholders_exact": {2608 "mean": 1.0,2609 "ci_low": 1.0,2610 "ci_high": 1.0,2611 "n_items": 562,2612 "n_groups": 482613 }2614 },2615 "related_work": {2616 "n": 18,2617 "chrf": {2618 "mean": 71.09207404443468,2619 "ci_low": 71.09207404443468,2620 "ci_high": 71.09207404443468,2621 "n_items": 18,2622 "n_groups": 12623 },2624 "edit_sim": {2625 "mean": 0.5889367446187903,2626 "ci_low": 0.5889367446187903,2627 "ci_high": 0.5889367446187903,2628 "n_items": 18,2629 "n_groups": 12630 },2631 "rougeL": {2632 "mean": 0.6252802133777317,2633 "ci_low": 0.6252802133777317,2634 "ci_high": 0.6252802133777317,2635 "n_items": 18,2636 "n_groups": 12637 },2638 "exact_match": {2639 "mean": 0.0,2640 "ci_low": 0.0,2641 "ci_high": 0.0,2642 "n_items": 18,2643 "n_groups": 12644 },2645 "number_recall": {2646 "mean": 1.0,2647 "ci_low": 1.0,2648 "ci_high": 1.0,2649 "n_items": 18,2650 "n_groups": 12651 },2652 "placeholders_exact": {2653 "mean": 1.0,2654 "ci_low": 1.0,2655 "ci_high": 1.0,2656 "n_items": 18,2657 "n_groups": 12658 }2659 },2660 "results": {2661 "n": 158,2662 "chrf": {2663 "mean": 67.2866597795359,2664 "ci_low": 64.86632765360707,2665 "ci_high": 71.49115228814487,2666 "n_items": 158,2667 "n_groups": 32668 },2669 "edit_sim": {2670 "mean": 0.5730479326309833,2671 "ci_low": 0.5696129293607832,2672 "ci_high": 0.6355576236359766,2673 "n_items": 158,2674 "n_groups": 32675 },2676 "rougeL": {2677 "mean": 0.6141503039110919,2678 "ci_low": 0.5948812379990409,2679 "ci_high": 0.6757463513590313,2680 "n_items": 158,2681 "n_groups": 32682 },2683 "exact_match": {2684 "mean": 0.0,2685 "ci_low": 0.0,2686 "ci_high": 0.0,2687 "n_items": 158,2688 "n_groups": 32689 },2690 "number_recall": {2691 "mean": 1.0,2692 "ci_low": 1.0,2693 "ci_high": 1.0,2694 "n_items": 158,2695 "n_groups": 32696 },2697 "placeholders_exact": {2698 "mean": 1.0,2699 "ci_low": 1.0,2700 "ci_high": 1.0,2701 "n_items": 158,2702 "n_groups": 32703 }2704 },2705 "theory": {2706 "n": 36,2707 "chrf": {2708 "mean": 71.55477093412983,2709 "ci_low": 69.3272848860366,2710 "ci_high": 72.00026814374846,2711 "n_items": 36,2712 "n_groups": 22713 },2714 "edit_sim": {2715 "mean": 0.6209488956613549,2716 "ci_low": 0.6130079558164632,2717 "ci_high": 0.6606535948858139,2718 "n_items": 36,2719 "n_groups": 22720 },2721 "rougeL": {2722 "mean": 0.6614079394836945,2723 "ci_low": 0.6574345019902335,2724 "ci_high": 0.681275126950999,2725 "n_items": 36,2726 "n_groups": 22727 },2728 "exact_match": {2729 "mean": 0.0,2730 "ci_low": 0.0,2731 "ci_high": 0.0,2732 "n_items": 36,2733 "n_groups": 22734 },2735 "number_recall": {2736 "mean": 1.0,2737 "ci_low": 1.0,2738 "ci_high": 1.0,2739 "n_items": 36,2740 "n_groups": 22741 },2742 "placeholders_exact": {2743 "mean": 1.0,2744 "ci_low": 1.0,2745 "ci_high": 1.0,2746 "n_items": 36,2747 "n_groups": 22748 }2749 }2750 }2751 },2752 "htr-m1-small": {2753 "overall": {2754 "n": 2574,2755 "chrf": {2756 "mean": 63.33299515396802,2757 "ci_low": 61.317100807999424,2758 "ci_high": 65.08375949024646,2759 "n_items": 2574,2760 "n_groups": 922761 },2762 "edit_sim": {2763 "mean": 0.6402938176156161,2764 "ci_low": 0.6233538041663931,2765 "ci_high": 0.6554148009660206,2766 "n_items": 2574,2767 "n_groups": 922768 },2769 "rougeL": {2770 "mean": 0.6452003847360067,2771 "ci_low": 0.6278086378213198,2772 "ci_high": 0.6607164683633016,2773 "n_items": 2574,2774 "n_groups": 922775 },2776 "exact_match": {2777 "mean": 0.0,2778 "ci_low": 0.0,2779 "ci_high": 0.0,2780 "n_items": 2574,2781 "n_groups": 922782 },2783 "number_recall": {2784 "mean": 0.9924467367649185,2785 "ci_low": 0.9841753079262276,2786 "ci_high": 0.9981481583962755,2787 "n_items": 2574,2788 "n_groups": 922789 },2790 "placeholders_exact": {2791 "mean": 0.9992229992229992,2792 "ci_low": 0.9977083875398027,2793 "ci_high": 1.0,2794 "n_items": 2574,2795 "n_groups": 922796 }2797 },2798 "by_variant": {2799 "A": {2800 "n": 436,2801 "chrf": {2802 "mean": 62.59923646576355,2803 "ci_low": 60.436839858017166,2804 "ci_high": 64.38625169950224,2805 "n_items": 436,2806 "n_groups": 912807 },2808 "edit_sim": {2809 "mean": 0.6304409424733547,2810 "ci_low": 0.6120975498600278,2811 "ci_high": 0.645512461557595,2812 "n_items": 436,2813 "n_groups": 912814 },2815 "rougeL": {2816 "mean": 0.6344305673280367,2817 "ci_low": 0.6158229966357222,2818 "ci_high": 0.6497431132420548,2819 "n_items": 436,2820 "n_groups": 912821 },2822 "exact_match": {2823 "mean": 0.0,2824 "ci_low": 0.0,2825 "ci_high": 0.0,2826 "n_items": 436,2827 "n_groups": 912828 },2829 "number_recall": {2830 "mean": 0.9934633027522936,2831 "ci_low": 0.9854589020473705,2832 "ci_high": 0.9993428293611387,2833 "n_items": 436,2834 "n_groups": 912835 },2836 "placeholders_exact": {2837 "mean": 1.0,2838 "ci_low": 1.0,2839 "ci_high": 1.0,2840 "n_items": 436,2841 "n_groups": 912842 }2843 },2844 "B": {2845 "n": 416,2846 "chrf": {2847 "mean": 68.47910589899718,2848 "ci_low": 66.09933939975177,2849 "ci_high": 70.67831661798867,2850 "n_items": 416,2851 "n_groups": 902852 },2853 "edit_sim": {2854 "mean": 0.6948447954331206,2855 "ci_low": 0.6727653147578996,2856 "ci_high": 0.7152042577390029,2857 "n_items": 416,2858 "n_groups": 902859 },2860 "rougeL": {2861 "mean": 0.7018324893556218,2862 "ci_low": 0.6793318737591608,2863 "ci_high": 0.7225391963388277,2864 "n_items": 416,2865 "n_groups": 902866 },2867 "exact_match": {2868 "mean": 0.0,2869 "ci_low": 0.0,2870 "ci_high": 0.0,2871 "n_items": 416,2872 "n_groups": 902873 },2874 "number_recall": {2875 "mean": 0.9909855769230769,2876 "ci_low": 0.9836326734059719,2877 "ci_high": 0.998692829863537,2878 "n_items": 416,2879 "n_groups": 902880 },2881 "placeholders_exact": {2882 "mean": 0.9975961538461539,2883 "ci_low": 0.9927536231884058,2884 "ci_high": 1.0,2885 "n_items": 416,2886 "n_groups": 902887 }2888 },2889 "C": {2890 "n": 438,2891 "chrf": {2892 "mean": 68.38493261025322,2893 "ci_low": 66.55419936928163,2894 "ci_high": 70.22941674219665,2895 "n_items": 438,2896 "n_groups": 912897 },2898 "edit_sim": {2899 "mean": 0.7063084622516071,2900 "ci_low": 0.6888115911067688,2901 "ci_high": 0.7235197679245916,2902 "n_items": 438,2903 "n_groups": 912904 },2905 "rougeL": {2906 "mean": 0.7211354345453419,2907 "ci_low": 0.7036169901563541,2908 "ci_high": 0.7385168170568965,2909 "n_items": 438,2910 "n_groups": 912911 },2912 "exact_match": {2913 "mean": 0.0,2914 "ci_low": 0.0,2915 "ci_high": 0.0,2916 "n_items": 438,2917 "n_groups": 912918 },2919 "number_recall": {2920 "mean": 0.9944254185692541,2921 "ci_low": 0.9860496001999001,2922 "ci_high": 0.9995316432839414,2923 "n_items": 438,2924 "n_groups": 912925 },2926 "placeholders_exact": {2927 "mean": 1.0,2928 "ci_low": 1.0,2929 "ci_high": 1.0,2930 "n_items": 438,2931 "n_groups": 912932 }2933 },2934 "D": {2935 "n": 431,2936 "chrf": {2937 "mean": 62.7778380088752,2938 "ci_low": 60.50920736989985,2939 "ci_high": 64.69820929512007,2940 "n_items": 431,2941 "n_groups": 902942 },2943 "edit_sim": {2944 "mean": 0.6400380402472907,2945 "ci_low": 0.6194773692694637,2946 "ci_high": 0.6561138982371276,2947 "n_items": 431,2948 "n_groups": 902949 },2950 "rougeL": {2951 "mean": 0.6422276919011286,2952 "ci_low": 0.6214049836944315,2953 "ci_high": 0.65926871428137,2954 "n_items": 431,2955 "n_groups": 902956 },2957 "exact_match": {2958 "mean": 0.0,2959 "ci_low": 0.0,2960 "ci_high": 0.0,2961 "n_items": 431,2962 "n_groups": 902963 },2964 "number_recall": {2965 "mean": 0.9919180201082753,2966 "ci_low": 0.9821067743447904,2967 "ci_high": 0.9990133403545727,2968 "n_items": 431,2969 "n_groups": 902970 },2971 "placeholders_exact": {2972 "mean": 0.9976798143851509,2973 "ci_low": 0.9929898315124391,2974 "ci_high": 1.0,2975 "n_items": 431,2976 "n_groups": 902977 }2978 },2979 "E": {2980 "n": 853,2981 "chrf": {2982 "mean": 58.884766363589506,2983 "ci_low": 56.82320089797505,2984 "ci_high": 60.698344495444786,2985 "n_items": 853,2986 "n_groups": 912987 },2988 "edit_sim": {2989 "mean": 0.584957911970983,2990 "ci_low": 0.5690506656934534,2991 "ci_high": 0.6002251325990207,2992 "n_items": 853,2993 "n_groups": 912994 },2995 "rougeL": {2996 "mean": 0.585597059605243,2997 "ci_low": 0.568264543005668,2998 "ci_high": 0.6020450959068722,2999 "n_items": 853,3000 "n_groups": 913001 },3002 "exact_match": {3003 "mean": 0.0,3004 "ci_low": 0.0,3005 "ci_high": 0.0,3006 "n_items": 853,3007 "n_groups": 913008 },3009 "number_recall": {3010 "mean": 0.9918908563105514,3011 "ci_low": 0.9834135521915455,3012 "ci_high": 0.9981238054634158,3013 "n_items": 853,3014 "n_groups": 913015 },3016 "placeholders_exact": {3017 "mean": 1.0,3018 "ci_low": 1.0,3019 "ci_high": 1.0,3020 "n_items": 853,3021 "n_groups": 913022 }3023 }3024 },3025 "by_discipline": {3026 "biomedicine": {3027 "n": 438,3028 "chrf": {3029 "mean": 63.745781059312556,3030 "ci_low": 57.737351323427525,3031 "ci_high": 68.37700075187297,3032 "n_items": 438,3033 "n_groups": 223034 },3035 "edit_sim": {3036 "mean": 0.6394145151458711,3037 "ci_low": 0.5872120200119876,3038 "ci_high": 0.6792550968030904,3039 "n_items": 438,3040 "n_groups": 223041 },3042 "rougeL": {3043 "mean": 0.6393931011668122,3044 "ci_low": 0.5840157541634545,3045 "ci_high": 0.680054756564522,3046 "n_items": 438,3047 "n_groups": 223048 },3049 "exact_match": {3050 "mean": 0.0,3051 "ci_low": 0.0,3052 "ci_high": 0.0,3053 "n_items": 438,3054 "n_groups": 223055 },3056 "number_recall": {3057 "mean": 0.9722222222222222,3058 "ci_low": 0.9464278571428572,3059 "ci_high": 1.0,3060 "n_items": 438,3061 "n_groups": 223062 },3063 "placeholders_exact": {3064 "mean": 1.0,3065 "ci_low": 1.0,3066 "ci_high": 1.0,3067 "n_items": 438,3068 "n_groups": 223069 }3070 },3071 "chemistry": {3072 "n": 183,3073 "chrf": {3074 "mean": 64.90219537491659,3075 "ci_low": 64.90219537491659,3076 "ci_high": 64.90219537491659,3077 "n_items": 183,3078 "n_groups": 13079 },3080 "edit_sim": {3081 "mean": 0.6478957163222847,3082 "ci_low": 0.6478957163222847,3083 "ci_high": 0.6478957163222847,3084 "n_items": 183,3085 "n_groups": 13086 },3087 "rougeL": {3088 "mean": 0.6545051778069841,3089 "ci_low": 0.6545051778069841,3090 "ci_high": 0.6545051778069841,3091 "n_items": 183,3092 "n_groups": 13093 },3094 "exact_match": {3095 "mean": 0.0,3096 "ci_low": 0.0,3097 "ci_high": 0.0,3098 "n_items": 183,3099 "n_groups": 13100 },3101 "number_recall": {3102 "mean": 0.9941712204007286,3103 "ci_low": 0.9941712204007286,3104 "ci_high": 0.9941712204007286,3105 "n_items": 183,3106 "n_groups": 13107 },3108 "placeholders_exact": {3109 "mean": 1.0,3110 "ci_low": 1.0,3111 "ci_high": 1.0,3112 "n_items": 183,3113 "n_groups": 13114 }3115 },3116 "earth_sciences": {3117 "n": 101,3118 "chrf": {3119 "mean": 61.82417375763714,3120 "ci_low": 61.82417375763714,3121 "ci_high": 61.82417375763714,3122 "n_items": 101,3123 "n_groups": 13124 },3125 "edit_sim": {3126 "mean": 0.6102662542447489,3127 "ci_low": 0.6102662542447489,3128 "ci_high": 0.6102662542447489,3129 "n_items": 101,3130 "n_groups": 13131 },3132 "rougeL": {3133 "mean": 0.623499441694191,3134 "ci_low": 0.623499441694191,3135 "ci_high": 0.623499441694191,3136 "n_items": 101,3137 "n_groups": 13138 },3139 "exact_match": {3140 "mean": 0.0,3141 "ci_low": 0.0,3142 "ci_high": 0.0,3143 "n_items": 101,3144 "n_groups": 13145 },3146 "number_recall": {3147 "mean": 0.9905940594059406,3148 "ci_low": 0.9905940594059406,3149 "ci_high": 0.9905940594059406,3150 "n_items": 101,3151 "n_groups": 13152 },3153 "placeholders_exact": {3154 "mean": 1.0,3155 "ci_low": 1.0,3156 "ci_high": 1.0,3157 "n_items": 101,3158 "n_groups": 13159 }3160 },3161 "economics": {3162 "n": 569,3163 "chrf": {3164 "mean": 67.71403637291569,3165 "ci_low": 62.86042676627782,3166 "ci_high": 70.86206651358191,3167 "n_items": 569,3168 "n_groups": 83169 },3170 "edit_sim": {3171 "mean": 0.673951739856812,3172 "ci_low": 0.6351831756145091,3173 "ci_high": 0.7033321793900189,3174 "n_items": 569,3175 "n_groups": 83176 },3177 "rougeL": {3178 "mean": 0.6794101158911501,3179 "ci_low": 0.6379646265513825,3180 "ci_high": 0.7116839255740567,3181 "n_items": 569,3182 "n_groups": 83183 },3184 "exact_match": {3185 "mean": 0.0,3186 "ci_low": 0.0,3187 "ci_high": 0.0,3188 "n_items": 569,3189 "n_groups": 83190 },3191 "number_recall": {3192 "mean": 0.991269143861411,3193 "ci_low": 0.9874344862797424,3194 "ci_high": 0.9995004995004996,3195 "n_items": 569,3196 "n_groups": 83197 },3198 "placeholders_exact": {3199 "mean": 0.9964850615114236,3200 "ci_low": 0.9913419913419913,3201 "ci_high": 1.0,3202 "n_items": 569,3203 "n_groups": 83204 }3205 },3206 "engineering": {3207 "n": 167,3208 "chrf": {3209 "mean": 59.99811062056428,3210 "ci_low": 56.59546123360033,3211 "ci_high": 61.54582554287919,3212 "n_items": 167,3213 "n_groups": 83214 },3215 "edit_sim": {3216 "mean": 0.597495189293865,3217 "ci_low": 0.5749299418138398,3218 "ci_high": 0.6092680976276981,3219 "n_items": 167,3220 "n_groups": 83221 },3222 "rougeL": {3223 "mean": 0.6107920753367032,3224 "ci_low": 0.5786995563791942,3225 "ci_high": 0.6269812730317714,3226 "n_items": 167,3227 "n_groups": 83228 },3229 "exact_match": {3230 "mean": 0.0,3231 "ci_low": 0.0,3232 "ci_high": 0.0,3233 "n_items": 167,3234 "n_groups": 83235 },3236 "number_recall": {3237 "mean": 0.9988023952095809,3238 "ci_low": 0.9972599597838381,3239 "ci_high": 1.0,3240 "n_items": 167,3241 "n_groups": 83242 },3243 "placeholders_exact": {3244 "mean": 1.0,3245 "ci_low": 1.0,3246 "ci_high": 1.0,3247 "n_items": 167,3248 "n_groups": 83249 }3250 },3251 "finance": {3252 "n": 75,3253 "chrf": {3254 "mean": 57.92331180830725,3255 "ci_low": 57.627868789202104,3256 "ci_high": 57.991118402855975,3257 "n_items": 75,3258 "n_groups": 23259 },3260 "edit_sim": {3261 "mean": 0.584984981421467,3262 "ci_low": 0.5738666495026105,3263 "ci_high": 0.5875367297307128,3264 "n_items": 75,3265 "n_groups": 23266 },3267 "rougeL": {3268 "mean": 0.5860428389581598,3269 "ci_low": 0.5779971474825889,3270 "ci_high": 0.587889391100094,3271 "n_items": 75,3272 "n_groups": 23273 },3274 "exact_match": {3275 "mean": 0.0,3276 "ci_low": 0.0,3277 "ci_high": 0.0,3278 "n_items": 75,3279 "n_groups": 23280 },3281 "number_recall": {3282 "mean": 1.0,3283 "ci_low": 1.0,3284 "ci_high": 1.0,3285 "n_items": 75,3286 "n_groups": 23287 },3288 "placeholders_exact": {3289 "mean": 1.0,3290 "ci_low": 1.0,3291 "ci_high": 1.0,3292 "n_items": 75,3293 "n_groups": 23294 }3295 },3296 "general_reference": {3297 "n": 256,3298 "chrf": {3299 "mean": 62.535835309392525,3300 "ci_low": 59.621545841639396,3301 "ci_high": 64.72521156095057,3302 "n_items": 256,3303 "n_groups": 123304 },3305 "edit_sim": {3306 "mean": 0.645050345974367,3307 "ci_low": 0.6092821130469264,3308 "ci_high": 0.6696023057794952,3309 "n_items": 256,3310 "n_groups": 123311 },3312 "rougeL": {3313 "mean": 0.6481045481591494,3314 "ci_low": 0.6068826370339596,3315 "ci_high": 0.6716879413799606,3316 "n_items": 256,3317 "n_groups": 123318 },3319 "exact_match": {3320 "mean": 0.0,3321 "ci_low": 0.0,3322 "ci_high": 0.0,3323 "n_items": 256,3324 "n_groups": 123325 },3326 "number_recall": {3327 "mean": 1.0,3328 "ci_low": 1.0,3329 "ci_high": 1.0,3330 "n_items": 256,3331 "n_groups": 123332 },3333 "placeholders_exact": {3334 "mean": 1.0,3335 "ci_low": 1.0,3336 "ci_high": 1.0,3337 "n_items": 256,3338 "n_groups": 123339 }3340 },3341 "humanities": {3342 "n": 253,3343 "chrf": {3344 "mean": 63.2587696394782,3345 "ci_low": 59.70111879315486,3346 "ci_high": 66.5097438830748,3347 "n_items": 253,3348 "n_groups": 93349 },3350 "edit_sim": {3351 "mean": 0.6514698313523113,3352 "ci_low": 0.6185862542087868,3353 "ci_high": 0.6909008183189493,3354 "n_items": 253,3355 "n_groups": 93356 },3357 "rougeL": {3358 "mean": 0.6576321855695724,3359 "ci_low": 0.6243433867187325,3360 "ci_high": 0.6936702401463488,3361 "n_items": 253,3362 "n_groups": 93363 },3364 "exact_match": {3365 "mean": 0.0,3366 "ci_low": 0.0,3367 "ci_high": 0.0,3368 "n_items": 253,3369 "n_groups": 93370 },3371 "number_recall": {3372 "mean": 1.0,3373 "ci_low": 1.0,3374 "ci_high": 1.0,3375 "n_items": 253,3376 "n_groups": 93377 },3378 "placeholders_exact": {3379 "mean": 1.0,3380 "ci_low": 1.0,3381 "ci_high": 1.0,3382 "n_items": 253,3383 "n_groups": 93384 }3385 },3386 "life_sciences": {3387 "n": 233,3388 "chrf": {3389 "mean": 61.10465758240952,3390 "ci_low": 58.571924723675636,3391 "ci_high": 63.9895831161161,3392 "n_items": 233,3393 "n_groups": 83394 },3395 "edit_sim": {3396 "mean": 0.6193762783147577,3397 "ci_low": 0.5970555769551086,3398 "ci_high": 0.645506366353816,3399 "n_items": 233,3400 "n_groups": 83401 },3402 "rougeL": {3403 "mean": 0.6288566390811636,3404 "ci_low": 0.6022053370619653,3405 "ci_high": 0.6590514833656236,3406 "n_items": 233,3407 "n_groups": 83408 },3409 "exact_match": {3410 "mean": 0.0,3411 "ci_low": 0.0,3412 "ci_high": 0.0,3413 "n_items": 233,3414 "n_groups": 83415 },3416 "number_recall": {3417 "mean": 0.9996098322278579,3418 "ci_low": 0.9987313528679536,3419 "ci_high": 1.0,3420 "n_items": 233,3421 "n_groups": 83422 },3423 "placeholders_exact": {3424 "mean": 1.0,3425 "ci_low": 1.0,3426 "ci_high": 1.0,3427 "n_items": 233,3428 "n_groups": 83429 }3430 },3431 "social_sciences": {3432 "n": 299,3433 "chrf": {3434 "mean": 59.641761836332826,3435 "ci_low": 56.91946443872114,3436 "ci_high": 61.92011722759696,3437 "n_items": 299,3438 "n_groups": 213439 },3440 "edit_sim": {3441 "mean": 0.6235698401233566,3442 "ci_low": 0.596968558083357,3443 "ci_high": 0.6465929988401861,3444 "n_items": 299,3445 "n_groups": 213446 },3447 "rougeL": {3448 "mean": 0.624028666290017,3449 "ci_low": 0.5925577802231112,3450 "ci_high": 0.6508293851317833,3451 "n_items": 299,3452 "n_groups": 213453 },3454 "exact_match": {3455 "mean": 0.0,3456 "ci_low": 0.0,3457 "ci_high": 0.0,3458 "n_items": 299,3459 "n_groups": 213460 },3461 "number_recall": {3462 "mean": 1.0,3463 "ci_low": 1.0,3464 "ci_high": 1.0,3465 "n_items": 299,3466 "n_groups": 213467 },3468 "placeholders_exact": {3469 "mean": 1.0,3470 "ci_low": 1.0,3471 "ci_high": 1.0,3472 "n_items": 299,3473 "n_groups": 213474 }3475 }3476 },3477 "by_era": {3478 "1900-1949": {3479 "n": 74,3480 "chrf": {3481 "mean": 64.59010210211882,3482 "ci_low": 62.272936994959174,3483 "ci_high": 69.9737842313578,3484 "n_items": 74,3485 "n_groups": 53486 },3487 "edit_sim": {3488 "mean": 0.6710906729170533,3489 "ci_low": 0.6018761672063354,3490 "ci_high": 0.6949896561285931,3491 "n_items": 74,3492 "n_groups": 53493 },3494 "rougeL": {3495 "mean": 0.6603312674661432,3496 "ci_low": 0.5836252589539326,3497 "ci_high": 0.6873278779788174,3498 "n_items": 74,3499 "n_groups": 53500 },3501 "exact_match": {3502 "mean": 0.0,3503 "ci_low": 0.0,3504 "ci_high": 0.0,3505 "n_items": 74,3506 "n_groups": 53507 },3508 "number_recall": {3509 "mean": 0.9864864864864865,3510 "ci_low": 0.9000000000000001,3511 "ci_high": 1.0,3512 "n_items": 74,3513 "n_groups": 53514 },3515 "placeholders_exact": {3516 "mean": 1.0,3517 "ci_low": 1.0,3518 "ci_high": 1.0,3519 "n_items": 74,3520 "n_groups": 53521 }3522 },3523 "2010-2017": {3524 "n": 527,3525 "chrf": {3526 "mean": 70.37743566652537,3527 "ci_low": 66.95626539205422,3528 "ci_high": 72.81002102402273,3529 "n_items": 527,3530 "n_groups": 43531 },3532 "edit_sim": {3533 "mean": 0.6937144118399203,3534 "ci_low": 0.6605579769401949,3535 "ci_high": 0.7172899288627772,3536 "n_items": 527,3537 "n_groups": 43538 },3539 "rougeL": {3540 "mean": 0.6979519940552268,3541 "ci_low": 0.660640098180858,3542 "ci_high": 0.7265547228649405,3543 "n_items": 527,3544 "n_groups": 43545 },3546 "exact_match": {3547 "mean": 0.0,3548 "ci_low": 0.0,3549 "ci_high": 0.0,3550 "n_items": 527,3551 "n_groups": 43552 },3553 "number_recall": {3554 "mean": 0.9715528146742568,3555 "ci_low": 0.9344086021505377,3556 "ci_high": 0.9905913978494624,3557 "n_items": 527,3558 "n_groups": 43559 },3560 "placeholders_exact": {3561 "mean": 0.9962049335863378,3562 "ci_low": 0.9908675799086758,3563 "ci_high": 1.0,3564 "n_items": 527,3565 "n_groups": 43566 }3567 },3568 "pre1900": {3569 "n": 1973,3570 "chrf": {3571 "mean": 61.404233844144976,3572 "ci_low": 60.04545819222098,3573 "ci_high": 62.616796743117355,3574 "n_items": 1973,3575 "n_groups": 833576 },3577 "edit_sim": {3578 "mean": 0.6248697829230084,3579 "ci_low": 0.6127270362586152,3580 "ci_high": 0.6367047211534947,3581 "n_items": 1973,3582 "n_groups": 833583 },3584 "rougeL": {3585 "mean": 0.6305426131023224,3586 "ci_low": 0.6171818843867259,3587 "ci_high": 0.6426877982364594,3588 "n_items": 1973,3589 "n_groups": 833590 },3591 "exact_match": {3592 "mean": 0.0,3593 "ci_low": 0.0,3594 "ci_high": 0.0,3595 "n_items": 1973,3596 "n_groups": 833597 },3598 "number_recall": {3599 "mean": 0.9982511744042408,3600 "ci_low": 0.9967345459236977,3601 "ci_high": 0.9997420497265465,3602 "n_items": 1973,3603 "n_groups": 833604 },3605 "placeholders_exact": {3606 "mean": 1.0,3607 "ci_low": 1.0,3608 "ci_high": 1.0,3609 "n_items": 1973,3610 "n_groups": 833611 }3612 }3613 },3614 "by_role": {3615 "abstract": {3616 "n": 36,3617 "chrf": {3618 "mean": 66.05248538767745,3619 "ci_low": 61.541961236463614,3620 "ci_high": 70.07178024054278,3621 "n_items": 36,3622 "n_groups": 63623 },3624 "edit_sim": {3625 "mean": 0.6393945050488947,3626 "ci_low": 0.5872943588989895,3627 "ci_high": 0.6928413303547907,3628 "n_items": 36,3629 "n_groups": 63630 },3631 "rougeL": {3632 "mean": 0.6199783124232867,3633 "ci_low": 0.5617029640140311,3634 "ci_high": 0.6804815028517299,3635 "n_items": 36,3636 "n_groups": 63637 },3638 "exact_match": {3639 "mean": 0.0,3640 "ci_low": 0.0,3641 "ci_high": 0.0,3642 "n_items": 36,3643 "n_groups": 63644 },3645 "number_recall": {3646 "mean": 0.9722222222222222,3647 "ci_low": 0.9166666666666666,3648 "ci_high": 1.0,3649 "n_items": 36,3650 "n_groups": 63651 },3652 "placeholders_exact": {3653 "mean": 1.0,3654 "ci_low": 1.0,3655 "ci_high": 1.0,3656 "n_items": 36,3657 "n_groups": 63658 }3659 },3660 "chapter": {3661 "n": 819,3662 "chrf": {3663 "mean": 62.06007061591967,3664 "ci_low": 60.661427699706124,3665 "ci_high": 63.3757226226727,3666 "n_items": 819,3667 "n_groups": 523668 },3669 "edit_sim": {3670 "mean": 0.6300702368108526,3671 "ci_low": 0.6150688014897961,3672 "ci_high": 0.6446438356908262,3673 "n_items": 819,3674 "n_groups": 523675 },3676 "rougeL": {3677 "mean": 0.6381498012637382,3678 "ci_low": 0.6225045917949111,3679 "ci_high": 0.6529248133784638,3680 "n_items": 819,3681 "n_groups": 523682 },3683 "exact_match": {3684 "mean": 0.0,3685 "ci_low": 0.0,3686 "ci_high": 0.0,3687 "n_items": 819,3688 "n_groups": 523689 },3690 "number_recall": {3691 "mean": 0.9962056462056462,3692 "ci_low": 0.9927387327592176,3693 "ci_high": 0.9994178635434283,3694 "n_items": 819,3695 "n_groups": 523696 },3697 "placeholders_exact": {3698 "mean": 1.0,3699 "ci_low": 1.0,3700 "ci_high": 1.0,3701 "n_items": 819,3702 "n_groups": 523703 }3704 },3705 "conclusion": {3706 "n": 104,3707 "chrf": {3708 "mean": 69.6565723604259,3709 "ci_low": 63.390641887900884,3710 "ci_high": 73.0923816102083,3711 "n_items": 104,3712 "n_groups": 33713 },3714 "edit_sim": {3715 "mean": 0.6838611169077249,3716 "ci_low": 0.6177568752569456,3717 "ci_high": 0.7432488369264733,3718 "n_items": 104,3719 "n_groups": 33720 },3721 "rougeL": {3722 "mean": 0.6817669830918114,3723 "ci_low": 0.6064170989932115,3724 "ci_high": 0.7267802429691708,3725 "n_items": 104,3726 "n_groups": 33727 },3728 "exact_match": {3729 "mean": 0.0,3730 "ci_low": 0.0,3731 "ci_high": 0.0,3732 "n_items": 104,3733 "n_groups": 33734 },3735 "number_recall": {3736 "mean": 0.9903846153846154,3737 "ci_low": 0.9722222222222222,3738 "ci_high": 1.0,3739 "n_items": 104,3740 "n_groups": 33741 },3742 "placeholders_exact": {3743 "mean": 1.0,3744 "ci_low": 1.0,3745 "ci_high": 1.0,3746 "n_items": 104,3747 "n_groups": 33748 }3749 },3750 "data": {3751 "n": 11,3752 "chrf": {3753 "mean": 77.75905510303065,3754 "ci_low": 77.75905510303065,3755 "ci_high": 77.75905510303065,3756 "n_items": 11,3757 "n_groups": 13758 },3759 "edit_sim": {3760 "mean": 0.7886859111167468,3761 "ci_low": 0.7886859111167468,3762 "ci_high": 0.7886859111167468,3763 "n_items": 11,3764 "n_groups": 13765 },3766 "rougeL": {3767 "mean": 0.8060120342862859,3768 "ci_low": 0.8060120342862859,3769 "ci_high": 0.8060120342862859,3770 "n_items": 11,3771 "n_groups": 13772 },3773 "exact_match": {3774 "mean": 0.0,3775 "ci_low": 0.0,3776 "ci_high": 0.0,3777 "n_items": 11,3778 "n_groups": 13779 },3780 "number_recall": {3781 "mean": 1.0,3782 "ci_low": 1.0,3783 "ci_high": 1.0,3784 "n_items": 11,3785 "n_groups": 13786 },3787 "placeholders_exact": {3788 "mean": 1.0,3789 "ci_low": 1.0,3790 "ci_high": 1.0,3791 "n_items": 11,3792 "n_groups": 13793 }3794 },3795 "introduction": {3796 "n": 574,3797 "chrf": {3798 "mean": 62.29915169930764,3799 "ci_low": 59.3861030794742,3800 "ci_high": 64.35859710690846,3801 "n_items": 574,3802 "n_groups": 233803 },3804 "edit_sim": {3805 "mean": 0.6351319986538899,3806 "ci_low": 0.6067469435734776,3807 "ci_high": 0.6552848161876527,3808 "n_items": 574,3809 "n_groups": 233810 },3811 "rougeL": {3812 "mean": 0.6380464013370378,3813 "ci_low": 0.6103689586224853,3814 "ci_high": 0.6587904316361906,3815 "n_items": 574,3816 "n_groups": 233817 },3818 "exact_match": {3819 "mean": 0.0,3820 "ci_low": 0.0,3821 "ci_high": 0.0,3822 "n_items": 574,3823 "n_groups": 233824 },3825 "number_recall": {3826 "mean": 0.99940268790443,3827 "ci_low": 0.9983220009047664,3828 "ci_high": 1.0,3829 "n_items": 574,3830 "n_groups": 233831 },3832 "placeholders_exact": {3833 "mean": 1.0,3834 "ci_low": 1.0,3835 "ci_high": 1.0,3836 "n_items": 574,3837 "n_groups": 233838 }3839 },3840 "methods": {3841 "n": 93,3842 "chrf": {3843 "mean": 70.19620395074176,3844 "ci_low": 66.73584756320317,3845 "ci_high": 78.486259884846,3846 "n_items": 93,3847 "n_groups": 33848 },3849 "edit_sim": {3850 "mean": 0.6899908659341634,3851 "ci_low": 0.6538204607619088,3852 "ci_high": 0.7796841424732871,3853 "n_items": 93,3854 "n_groups": 33855 },3856 "rougeL": {3857 "mean": 0.7100182754748678,3858 "ci_low": 0.6665923789147087,3859 "ci_high": 0.808139788729974,3860 "n_items": 93,3861 "n_groups": 33862 },3863 "exact_match": {3864 "mean": 0.0,3865 "ci_low": 0.0,3866 "ci_high": 0.0,3867 "n_items": 93,3868 "n_groups": 33869 },3870 "number_recall": {3871 "mean": 0.9723118279569892,3872 "ci_low": 0.96875,3873 "ci_high": 0.9755102040816329,3874 "n_items": 93,3875 "n_groups": 33876 },3877 "placeholders_exact": {3878 "mean": 0.989247311827957,3879 "ci_low": 0.9722222222222222,3880 "ci_high": 1.0,3881 "n_items": 93,3882 "n_groups": 33883 }3884 },3885 "other": {3886 "n": 163,3887 "chrf": {3888 "mean": 65.01444045296364,3889 "ci_low": 59.519813012067644,3890 "ci_high": 69.7694476800861,3891 "n_items": 163,3892 "n_groups": 93893 },3894 "edit_sim": {3895 "mean": 0.6702584904770209,3896 "ci_low": 0.639547885776469,3897 "ci_high": 0.699846673538338,3898 "n_items": 163,3899 "n_groups": 93900 },3901 "rougeL": {3902 "mean": 0.6729759826458434,3903 "ci_low": 0.6421075703151926,3904 "ci_high": 0.7024804947389754,3905 "n_items": 163,3906 "n_groups": 93907 },3908 "exact_match": {3909 "mean": 0.0,3910 "ci_low": 0.0,3911 "ci_high": 0.0,3912 "n_items": 163,3913 "n_groups": 93914 },3915 "number_recall": {3916 "mean": 0.9969325153374233,3917 "ci_low": 0.9900662251655629,3918 "ci_high": 1.0,3919 "n_items": 163,3920 "n_groups": 93921 },3922 "placeholders_exact": {3923 "mean": 1.0,3924 "ci_low": 1.0,3925 "ci_high": 1.0,3926 "n_items": 163,3927 "n_groups": 93928 }3929 },3930 "preface": {3931 "n": 562,3932 "chrf": {3933 "mean": 60.18789479261127,3934 "ci_low": 58.36537528520645,3935 "ci_high": 62.02295498017994,3936 "n_items": 562,3937 "n_groups": 483938 },3939 "edit_sim": {3940 "mean": 0.6115897418180355,3941 "ci_low": 0.5934729679406261,3942 "ci_high": 0.6304129542663217,3943 "n_items": 562,3944 "n_groups": 483945 },3946 "rougeL": {3947 "mean": 0.6157485035391103,3948 "ci_low": 0.5953875288236196,3949 "ci_high": 0.6365042497972487,3950 "n_items": 562,3951 "n_groups": 483952 },3953 "exact_match": {3954 "mean": 0.0,3955 "ci_low": 0.0,3956 "ci_high": 0.0,3957 "n_items": 562,3958 "n_groups": 483959 },3960 "number_recall": {3961 "mean": 1.0,3962 "ci_low": 1.0,3963 "ci_high": 1.0,3964 "n_items": 562,3965 "n_groups": 483966 },3967 "placeholders_exact": {3968 "mean": 1.0,3969 "ci_low": 1.0,3970 "ci_high": 1.0,3971 "n_items": 562,3972 "n_groups": 483973 }3974 },3975 "related_work": {3976 "n": 18,3977 "chrf": {3978 "mean": 71.54413348056173,3979 "ci_low": 71.54413348056173,3980 "ci_high": 71.54413348056173,3981 "n_items": 18,3982 "n_groups": 13983 },3984 "edit_sim": {3985 "mean": 0.7135588134386669,3986 "ci_low": 0.7135588134386669,3987 "ci_high": 0.7135588134386669,3988 "n_items": 18,3989 "n_groups": 13990 },3991 "rougeL": {3992 "mean": 0.6980819455262934,3993 "ci_low": 0.6980819455262934,3994 "ci_high": 0.6980819455262934,3995 "n_items": 18,3996 "n_groups": 13997 },3998 "exact_match": {3999 "mean": 0.0,4000 "ci_low": 0.0,4001 "ci_high": 0.0,4002 "n_items": 18,4003 "n_groups": 14004 },4005 "number_recall": {4006 "mean": 1.0,4007 "ci_low": 1.0,4008 "ci_high": 1.0,4009 "n_items": 18,4010 "n_groups": 14011 },4012 "placeholders_exact": {4013 "mean": 0.9444444444444444,4014 "ci_low": 0.9444444444444444,4015 "ci_high": 0.9444444444444444,4016 "n_items": 18,4017 "n_groups": 14018 }4019 },4020 "results": {4021 "n": 158,4022 "chrf": {4023 "mean": 69.97855209339052,4024 "ci_low": 67.86479543814133,4025 "ci_high": 76.23737815860925,4026 "n_items": 158,4027 "n_groups": 34028 },4029 "edit_sim": {4030 "mean": 0.6852096649351349,4031 "ci_low": 0.6687047610117186,4032 "ci_high": 0.7316560965896693,4033 "n_items": 158,4034 "n_groups": 34035 },4036 "rougeL": {4037 "mean": 0.6903321031822012,4038 "ci_low": 0.6809402595496625,4039 "ci_high": 0.7395038093653015,4040 "n_items": 158,4041 "n_groups": 34042 },4043 "exact_match": {4044 "mean": 0.0,4045 "ci_low": 0.0,4046 "ci_high": 0.0,4047 "n_items": 158,4048 "n_groups": 34049 },4050 "number_recall": {4051 "mean": 0.9309071729957805,4052 "ci_low": 0.8712121212121212,4053 "ci_high": 0.9933333333333333,4054 "n_items": 158,4055 "n_groups": 34056 },4057 "placeholders_exact": {4058 "mean": 1.0,4059 "ci_low": 1.0,4060 "ci_high": 1.0,4061 "n_items": 158,4062 "n_groups": 34063 }4064 },4065 "theory": {4066 "n": 36,4067 "chrf": {4068 "mean": 73.86368729981929,4069 "ci_low": 68.77030006874803,4070 "ci_high": 74.88236474603356,4071 "n_items": 36,4072 "n_groups": 24073 },4074 "edit_sim": {4075 "mean": 0.735160747825329,4076 "ci_low": 0.6826365286646426,4077 "ci_high": 0.7456655916574664,4078 "n_items": 36,4079 "n_groups": 24080 },4081 "rougeL": {4082 "mean": 0.7321655483446643,4083 "ci_low": 0.6609509686826605,4084 "ci_high": 0.746408464277065,4085 "n_items": 36,4086 "n_groups": 24087 },4088 "exact_match": {4089 "mean": 0.0,4090 "ci_low": 0.0,4091 "ci_high": 0.0,4092 "n_items": 36,4093 "n_groups": 24094 },4095 "number_recall": {4096 "mean": 1.0,4097 "ci_low": 1.0,4098 "ci_high": 1.0,4099 "n_items": 36,4100 "n_groups": 24101 },4102 "placeholders_exact": {4103 "mean": 1.0,4104 "ci_low": 1.0,4105 "ci_high": 1.0,4106 "n_items": 36,4107 "n_groups": 24108 }4109 }4110 }4111 },4112 "htr-m1-tiny-s2": {4113 "overall": {4114 "n": 2574,4115 "chrf": {4116 "mean": 63.455310035878966,4117 "ci_low": 61.37435670824173,4118 "ci_high": 65.27200232768021,4119 "n_items": 2574,4120 "n_groups": 924121 },4122 "edit_sim": {4123 "mean": 0.6443087753988949,4124 "ci_low": 0.6270777890559293,4125 "ci_high": 0.659896369262855,4126 "n_items": 2574,4127 "n_groups": 924128 },4129 "rougeL": {4130 "mean": 0.6490291980452317,4131 "ci_low": 0.6315414457895513,4132 "ci_high": 0.6648875971384092,4133 "n_items": 2574,4134 "n_groups": 924135 },4136 "exact_match": {4137 "mean": 0.0,4138 "ci_low": 0.0,4139 "ci_high": 0.0,4140 "n_items": 2574,4141 "n_groups": 924142 },4143 "number_recall": {4144 "mean": 0.9944337789034757,4145 "ci_low": 0.9887447269252178,4146 "ci_high": 0.9987636860568391,4147 "n_items": 2574,4148 "n_groups": 924149 },4150 "placeholders_exact": {4151 "mean": 0.9968919968919969,4152 "ci_low": 0.9925092073059446,4153 "ci_high": 1.0,4154 "n_items": 2574,4155 "n_groups": 924156 }4157 },4158 "by_variant": {4159 "A": {4160 "n": 436,4161 "chrf": {4162 "mean": 62.62393064490964,4163 "ci_low": 60.405497161979184,4164 "ci_high": 64.45218938423442,4165 "n_items": 436,4166 "n_groups": 914167 },4168 "edit_sim": {4169 "mean": 0.6344551226903569,4170 "ci_low": 0.615796507218174,4171 "ci_high": 0.6497628953928162,4172 "n_items": 436,4173 "n_groups": 914174 },4175 "rougeL": {4176 "mean": 0.6379402264756655,4177 "ci_low": 0.6184362478124341,4178 "ci_high": 0.6533330984389226,4179 "n_items": 436,4180 "n_groups": 914181 },4182 "exact_match": {4183 "mean": 0.0,4184 "ci_low": 0.0,4185 "ci_high": 0.0,4186 "n_items": 436,4187 "n_groups": 914188 },4189 "number_recall": {4190 "mean": 0.9940494393476045,4191 "ci_low": 0.9882851849270513,4192 "ci_high": 0.998863764911559,4193 "n_items": 436,4194 "n_groups": 914195 },4196 "placeholders_exact": {4197 "mean": 0.9954128440366973,4198 "ci_low": 0.9860772638034819,4199 "ci_high": 1.0,4200 "n_items": 436,4201 "n_groups": 914202 }4203 },4204 "B": {4205 "n": 416,4206 "chrf": {4207 "mean": 68.51403926186077,4208 "ci_low": 66.07829918373073,4209 "ci_high": 70.74672690633939,4210 "n_items": 416,4211 "n_groups": 904212 },4213 "edit_sim": {4214 "mean": 0.697778612517091,4215 "ci_low": 0.675403045800543,4216 "ci_high": 0.7186128252711197,4217 "n_items": 416,4218 "n_groups": 904219 },4220 "rougeL": {4221 "mean": 0.7041085061784333,4222 "ci_low": 0.6816163302665547,4223 "ci_high": 0.7250212683746469,4224 "n_items": 416,4225 "n_groups": 904226 },4227 "exact_match": {4228 "mean": 0.0,4229 "ci_low": 0.0,4230 "ci_high": 0.0,4231 "n_items": 416,4232 "n_groups": 904233 },4234 "number_recall": {4235 "mean": 0.9948317307692308,4236 "ci_low": 0.9895477696602517,4237 "ci_high": 0.9994398150321581,4238 "n_items": 416,4239 "n_groups": 904240 },4241 "placeholders_exact": {4242 "mean": 0.9951923076923077,4243 "ci_low": 0.9895174070222355,4244 "ci_high": 1.0,4245 "n_items": 416,4246 "n_groups": 904247 }4248 },4249 "C": {4250 "n": 438,4251 "chrf": {4252 "mean": 68.40085837722417,4253 "ci_low": 66.60248591111058,4254 "ci_high": 70.20650638004852,4255 "n_items": 438,4256 "n_groups": 914257 },4258 "edit_sim": {4259 "mean": 0.7065539289641654,4260 "ci_low": 0.6901953902248923,4261 "ci_high": 0.7229767634904829,4262 "n_items": 438,4263 "n_groups": 914264 },4265 "rougeL": {4266 "mean": 0.7229045451868623,4267 "ci_low": 0.7055828192510788,4268 "ci_high": 0.7399998855622415,4269 "n_items": 438,4270 "n_groups": 914271 },4272 "exact_match": {4273 "mean": 0.0,4274 "ci_low": 0.0,4275 "ci_high": 0.0,4276 "n_items": 438,4277 "n_groups": 914278 },4279 "number_recall": {4280 "mean": 0.9922789539227895,4281 "ci_low": 0.9843019789146215,4282 "ci_high": 0.9985840639688544,4283 "n_items": 438,4284 "n_groups": 914285 },4286 "placeholders_exact": {4287 "mean": 0.9954337899543378,4288 "ci_low": 0.9895394751254135,4289 "ci_high": 1.0,4290 "n_items": 438,4291 "n_groups": 914292 }4293 },4294 "D": {4295 "n": 431,4296 "chrf": {4297 "mean": 62.91026127935563,4298 "ci_low": 60.542291048699624,4299 "ci_high": 64.8913946193051,4300 "n_items": 431,4301 "n_groups": 904302 },4303 "edit_sim": {4304 "mean": 0.6444631977552129,4305 "ci_low": 0.6235341524219474,4306 "ci_high": 0.6609683066276367,4307 "n_items": 431,4308 "n_groups": 904309 },4310 "rougeL": {4311 "mean": 0.6461731982103484,4312 "ci_low": 0.6256917395758188,4313 "ci_high": 0.6635882446561675,4314 "n_items": 431,4315 "n_groups": 904316 },4317 "exact_match": {4318 "mean": 0.0,4319 "ci_low": 0.0,4320 "ci_high": 0.0,4321 "n_items": 431,4322 "n_groups": 904323 },4324 "number_recall": {4325 "mean": 0.9934454756380511,4326 "ci_low": 0.9865621514107612,4327 "ci_high": 0.999057828715605,4328 "n_items": 431,4329 "n_groups": 904330 },4331 "placeholders_exact": {4332 "mean": 0.9976798143851509,4333 "ci_low": 0.9929898315124391,4334 "ci_high": 1.0,4335 "n_items": 431,4336 "n_groups": 904337 }4338 },4339 "E": {4340 "n": 853,4341 "chrf": {4342 "mean": 59.149115307867895,4343 "ci_low": 57.00380871975701,4344 "ci_high": 61.09131947791382,4345 "n_items": 853,4346 "n_groups": 914347 },4348 "edit_sim": {4349 "mean": 0.5912288305484745,4350 "ci_low": 0.5742385741822941,4351 "ci_high": 0.6075901960585611,4352 "n_items": 853,4353 "n_groups": 914354 },4355 "rougeL": {4356 "mean": 0.5913449463473649,4357 "ci_low": 0.5737412015662497,4358 "ci_high": 0.6082446675651125,4359 "n_items": 853,4360 "n_groups": 914361 },4362 "exact_match": {4363 "mean": 0.0,4364 "ci_low": 0.0,4365 "ci_high": 0.0,4366 "n_items": 853,4367 "n_groups": 914368 },4369 "number_recall": {4370 "mean": 0.9960419806844192,4371 "ci_low": 0.9908300375018758,4372 "ci_high": 0.9998126079923,4373 "n_items": 853,4374 "n_groups": 914375 },4376 "placeholders_exact": {4377 "mean": 0.9988276670574443,4378 "ci_low": 0.9962546816479401,4379 "ci_high": 1.0,4380 "n_items": 853,4381 "n_groups": 914382 }4383 }4384 },4385 "by_discipline": {4386 "biomedicine": {4387 "n": 438,4388 "chrf": {4389 "mean": 64.07724917281415,4390 "ci_low": 58.03464930825784,4391 "ci_high": 68.70790498099574,4392 "n_items": 438,4393 "n_groups": 224394 },4395 "edit_sim": {4396 "mean": 0.6465501482381611,4397 "ci_low": 0.5927319197504758,4398 "ci_high": 0.6881007042434666,4399 "n_items": 438,4400 "n_groups": 224401 },4402 "rougeL": {4403 "mean": 0.6451733674051334,4404 "ci_low": 0.5893512317635927,4405 "ci_high": 0.6863412033289189,4406 "n_items": 438,4407 "n_groups": 224408 },4409 "exact_match": {4410 "mean": 0.0,4411 "ci_low": 0.0,4412 "ci_high": 0.0,4413 "n_items": 438,4414 "n_groups": 224415 },4416 "number_recall": {4417 "mean": 0.9838470319634703,4418 "ci_low": 0.9656391357892482,4419 "ci_high": 1.0,4420 "n_items": 438,4421 "n_groups": 224422 },4423 "placeholders_exact": {4424 "mean": 0.9885844748858448,4425 "ci_low": 0.9752883031301482,4426 "ci_high": 1.0,4427 "n_items": 438,4428 "n_groups": 224429 }4430 },4431 "chemistry": {4432 "n": 183,4433 "chrf": {4434 "mean": 64.99613170909421,4435 "ci_low": 64.99613170909421,4436 "ci_high": 64.99613170909421,4437 "n_items": 183,4438 "n_groups": 14439 },4440 "edit_sim": {4441 "mean": 0.6497015800346039,4442 "ci_low": 0.6497015800346039,4443 "ci_high": 0.6497015800346039,4444 "n_items": 183,4445 "n_groups": 14446 },4447 "rougeL": {4448 "mean": 0.6568676729215132,4449 "ci_low": 0.6568676729215132,4450 "ci_high": 0.6568676729215132,4451 "n_items": 183,4452 "n_groups": 14453 },4454 "exact_match": {4455 "mean": 0.0,4456 "ci_low": 0.0,4457 "ci_high": 0.0,4458 "n_items": 183,4459 "n_groups": 14460 },4461 "number_recall": {4462 "mean": 1.0,4463 "ci_low": 1.0,4464 "ci_high": 1.0,4465 "n_items": 183,4466 "n_groups": 14467 },4468 "placeholders_exact": {4469 "mean": 1.0,4470 "ci_low": 1.0,4471 "ci_high": 1.0,4472 "n_items": 183,4473 "n_groups": 14474 }4475 },4476 "earth_sciences": {4477 "n": 101,4478 "chrf": {4479 "mean": 61.0857717875801,4480 "ci_low": 61.0857717875801,4481 "ci_high": 61.0857717875801,4482 "n_items": 101,4483 "n_groups": 14484 },4485 "edit_sim": {4486 "mean": 0.6090909831045286,4487 "ci_low": 0.6090909831045286,4488 "ci_high": 0.6090909831045286,4489 "n_items": 101,4490 "n_groups": 14491 },4492 "rougeL": {4493 "mean": 0.6227177716228193,4494 "ci_low": 0.6227177716228193,4495 "ci_high": 0.6227177716228193,4496 "n_items": 101,4497 "n_groups": 14498 },4499 "exact_match": {4500 "mean": 0.0,4501 "ci_low": 0.0,4502 "ci_high": 0.0,4503 "n_items": 101,4504 "n_groups": 14505 },4506 "number_recall": {4507 "mean": 0.9777227722772277,4508 "ci_low": 0.9777227722772277,4509 "ci_high": 0.9777227722772277,4510 "n_items": 101,4511 "n_groups": 14512 },4513 "placeholders_exact": {4514 "mean": 1.0,4515 "ci_low": 1.0,4516 "ci_high": 1.0,4517 "n_items": 101,4518 "n_groups": 14519 }4520 },4521 "economics": {4522 "n": 569,4523 "chrf": {4524 "mean": 67.95556260360574,4525 "ci_low": 62.82335029456128,4526 "ci_high": 71.3203854773674,4527 "n_items": 569,4528 "n_groups": 84529 },4530 "edit_sim": {4531 "mean": 0.6779375333662438,4532 "ci_low": 0.6387266913404833,4533 "ci_high": 0.7079510040450999,4534 "n_items": 569,4535 "n_groups": 84536 },4537 "rougeL": {4538 "mean": 0.6833970258695047,4539 "ci_low": 0.6419610732963748,4540 "ci_high": 0.7162706491986385,4541 "n_items": 569,4542 "n_groups": 84543 },4544 "exact_match": {4545 "mean": 0.0,4546 "ci_low": 0.0,4547 "ci_high": 0.0,4548 "n_items": 569,4549 "n_groups": 84550 },4551 "number_recall": {4552 "mean": 0.9919992036863742,4553 "ci_low": 0.9896727816809784,4554 "ci_high": 0.9971694971694972,4555 "n_items": 569,4556 "n_groups": 84557 },4558 "placeholders_exact": {4559 "mean": 0.9947275922671354,4560 "ci_low": 0.987012987012987,4561 "ci_high": 1.0,4562 "n_items": 569,4563 "n_groups": 84564 }4565 },4566 "engineering": {4567 "n": 167,4568 "chrf": {4569 "mean": 60.374843359557595,4570 "ci_low": 56.831525045403225,4571 "ci_high": 61.85458376230953,4572 "n_items": 167,4573 "n_groups": 84574 },4575 "edit_sim": {4576 "mean": 0.6068732093028871,4577 "ci_low": 0.5806260342840659,4578 "ci_high": 0.6196571240695438,4579 "n_items": 167,4580 "n_groups": 84581 },4582 "rougeL": {4583 "mean": 0.6185910942398866,4584 "ci_low": 0.5814990708581861,4585 "ci_high": 0.6363953243897823,4586 "n_items": 167,4587 "n_groups": 84588 },4589 "exact_match": {4590 "mean": 0.0,4591 "ci_low": 0.0,4592 "ci_high": 0.0,4593 "n_items": 167,4594 "n_groups": 84595 },4596 "number_recall": {4597 "mean": 0.9988023952095809,4598 "ci_low": 0.9972599597838381,4599 "ci_high": 1.0,4600 "n_items": 167,4601 "n_groups": 84602 },4603 "placeholders_exact": {4604 "mean": 1.0,4605 "ci_low": 1.0,4606 "ci_high": 1.0,4607 "n_items": 167,4608 "n_groups": 84609 }4610 },4611 "finance": {4612 "n": 75,4613 "chrf": {4614 "mean": 58.118880018470215,4615 "ci_low": 57.94568234224719,4616 "ci_high": 58.87352703629905,4617 "n_items": 75,4618 "n_groups": 24619 },4620 "edit_sim": {4621 "mean": 0.5905751157891886,4622 "ci_low": 0.5901841819503721,4623 "ci_high": 0.5906648383095731,4624 "n_items": 75,4625 "n_groups": 24626 },4627 "rougeL": {4628 "mean": 0.592006195708031,4629 "ci_low": 0.5893645146011514,4630 "ci_high": 0.5926124831751838,4631 "n_items": 75,4632 "n_groups": 24633 },4634 "exact_match": {4635 "mean": 0.0,4636 "ci_low": 0.0,4637 "ci_high": 0.0,4638 "n_items": 75,4639 "n_groups": 24640 },4641 "number_recall": {4642 "mean": 1.0,4643 "ci_low": 1.0,4644 "ci_high": 1.0,4645 "n_items": 75,4646 "n_groups": 24647 },4648 "placeholders_exact": {4649 "mean": 1.0,4650 "ci_low": 1.0,4651 "ci_high": 1.0,4652 "n_items": 75,4653 "n_groups": 24654 }4655 },4656 "general_reference": {4657 "n": 256,4658 "chrf": {4659 "mean": 62.46454941366411,4660 "ci_low": 59.36788462326321,4661 "ci_high": 64.7285958947725,4662 "n_items": 256,4663 "n_groups": 124664 },4665 "edit_sim": {4666 "mean": 0.6459691022901638,4667 "ci_low": 0.6064216313181631,4668 "ci_high": 0.6699594375798852,4669 "n_items": 256,4670 "n_groups": 124671 },4672 "rougeL": {4673 "mean": 0.6497045464432012,4674 "ci_low": 0.6050132320790613,4675 "ci_high": 0.673683155682437,4676 "n_items": 256,4677 "n_groups": 124678 },4679 "exact_match": {4680 "mean": 0.0,4681 "ci_low": 0.0,4682 "ci_high": 0.0,4683 "n_items": 256,4684 "n_groups": 124685 },4686 "number_recall": {4687 "mean": 1.0,4688 "ci_low": 1.0,4689 "ci_high": 1.0,4690 "n_items": 256,4691 "n_groups": 124692 },4693 "placeholders_exact": {4694 "mean": 1.0,4695 "ci_low": 1.0,4696 "ci_high": 1.0,4697 "n_items": 256,4698 "n_groups": 124699 }4700 },4701 "humanities": {4702 "n": 253,4703 "chrf": {4704 "mean": 63.34685238512097,4705 "ci_low": 59.663194398874225,4706 "ci_high": 66.81958737195608,4707 "n_items": 253,4708 "n_groups": 94709 },4710 "edit_sim": {4711 "mean": 0.6563884861689295,4712 "ci_low": 0.6235809993712444,4713 "ci_high": 0.6972331318532486,4714 "n_items": 253,4715 "n_groups": 94716 },4717 "rougeL": {4718 "mean": 0.6612522502249625,4719 "ci_low": 0.6265704327459599,4720 "ci_high": 0.6983551526851777,4721 "n_items": 253,4722 "n_groups": 94723 },4724 "exact_match": {4725 "mean": 0.0,4726 "ci_low": 0.0,4727 "ci_high": 0.0,4728 "n_items": 253,4729 "n_groups": 94730 },4731 "number_recall": {4732 "mean": 1.0,4733 "ci_low": 1.0,4734 "ci_high": 1.0,4735 "n_items": 253,4736 "n_groups": 94737 },4738 "placeholders_exact": {4739 "mean": 1.0,4740 "ci_low": 1.0,4741 "ci_high": 1.0,4742 "n_items": 253,4743 "n_groups": 94744 }4745 },4746 "life_sciences": {4747 "n": 233,4748 "chrf": {4749 "mean": 60.793883265619755,4750 "ci_low": 58.14693957047332,4751 "ci_high": 63.815506504924,4752 "n_items": 233,4753 "n_groups": 84754 },4755 "edit_sim": {4756 "mean": 0.6181562738488389,4757 "ci_low": 0.5951992643566587,4758 "ci_high": 0.6460572572788976,4759 "n_items": 233,4760 "n_groups": 84761 },4762 "rougeL": {4763 "mean": 0.6280758566863902,4764 "ci_low": 0.6030325486319331,4765 "ci_high": 0.6573866861946484,4766 "n_items": 233,4767 "n_groups": 84768 },4769 "exact_match": {4770 "mean": 0.0,4771 "ci_low": 0.0,4772 "ci_high": 0.0,4773 "n_items": 233,4774 "n_groups": 84775 },4776 "number_recall": {4777 "mean": 0.9989270386266095,4778 "ci_low": 0.9965112203868725,4779 "ci_high": 1.0,4780 "n_items": 233,4781 "n_groups": 84782 },4783 "placeholders_exact": {4784 "mean": 1.0,4785 "ci_low": 1.0,4786 "ci_high": 1.0,4787 "n_items": 233,4788 "n_groups": 84789 }4790 },4791 "social_sciences": {4792 "n": 299,4793 "chrf": {4794 "mean": 59.91068486034773,4795 "ci_low": 57.2386440978688,4796 "ci_high": 62.10391036046901,4797 "n_items": 299,4798 "n_groups": 214799 },4800 "edit_sim": {4801 "mean": 0.628749295624034,4802 "ci_low": 0.6032915295047026,4803 "ci_high": 0.6515307542743625,4804 "n_items": 299,4805 "n_groups": 214806 },4807 "rougeL": {4808 "mean": 0.6300769191512408,4809 "ci_low": 0.6013680941304407,4810 "ci_high": 0.6559549326429814,4811 "n_items": 299,4812 "n_groups": 214813 },4814 "exact_match": {4815 "mean": 0.0,4816 "ci_low": 0.0,4817 "ci_high": 0.0,4818 "n_items": 299,4819 "n_groups": 214820 },4821 "number_recall": {4822 "mean": 1.0,4823 "ci_low": 1.0,4824 "ci_high": 1.0,4825 "n_items": 299,4826 "n_groups": 214827 },4828 "placeholders_exact": {4829 "mean": 1.0,4830 "ci_low": 1.0,4831 "ci_high": 1.0,4832 "n_items": 299,4833 "n_groups": 214834 }4835 }4836 },4837 "by_era": {4838 "1900-1949": {4839 "n": 74,4840 "chrf": {4841 "mean": 65.34161079247829,4842 "ci_low": 63.00327995831448,4843 "ci_high": 71.76587295435571,4844 "n_items": 74,4845 "n_groups": 54846 },4847 "edit_sim": {4848 "mean": 0.681197312451033,4849 "ci_low": 0.6158184182516013,4850 "ci_high": 0.707106547069139,4851 "n_items": 74,4852 "n_groups": 54853 },4854 "rougeL": {4855 "mean": 0.6716883825930221,4856 "ci_low": 0.6009444787377194,4857 "ci_high": 0.6972138758915336,4858 "n_items": 74,4859 "n_groups": 54860 },4861 "exact_match": {4862 "mean": 0.0,4863 "ci_low": 0.0,4864 "ci_high": 0.0,4865 "n_items": 74,4866 "n_groups": 54867 },4868 "number_recall": {4869 "mean": 0.9972972972972972,4870 "ci_low": 0.9800000000000001,4871 "ci_high": 1.0,4872 "n_items": 74,4873 "n_groups": 54874 },4875 "placeholders_exact": {4876 "mean": 1.0,4877 "ci_low": 1.0,4878 "ci_high": 1.0,4879 "n_items": 74,4880 "n_groups": 54881 }4882 },4883 "2010-2017": {4884 "n": 527,4885 "chrf": {4886 "mean": 70.84978313772112,4887 "ci_low": 67.362034988323,4888 "ci_high": 73.32970795823469,4889 "n_items": 527,4890 "n_groups": 44891 },4892 "edit_sim": {4893 "mean": 0.7011758536262802,4894 "ci_low": 0.6682187814466741,4895 "ci_high": 0.7275025322367729,4896 "n_items": 527,4897 "n_groups": 44898 },4899 "rougeL": {4900 "mean": 0.7040003872906139,4901 "ci_low": 0.6664778642790128,4902 "ci_high": 0.7317511592510154,4903 "n_items": 527,4904 "n_groups": 44905 },4906 "exact_match": {4907 "mean": 0.0,4908 "ci_low": 0.0,4909 "ci_high": 0.0,4910 "n_items": 527,4911 "n_groups": 44912 },4913 "number_recall": {4914 "mean": 0.9798521265788819,4915 "ci_low": 0.9556451612903226,4916 "ci_high": 0.9929909422867169,4917 "n_items": 527,4918 "n_groups": 44919 },4920 "placeholders_exact": {4921 "mean": 0.9848197343453511,4922 "ci_low": 0.967741935483871,4923 "ci_high": 1.0,4924 "n_items": 527,4925 "n_groups": 44926 }4927 },4928 "pre1900": {4929 "n": 1973,4930 "chrf": {4931 "mean": 61.40945419165233,4932 "ci_low": 60.07615388073745,4933 "ci_high": 62.61681860410688,4934 "n_items": 1973,4935 "n_groups": 834936 },4937 "edit_sim": {4938 "mean": 0.6277356877315404,4939 "ci_low": 0.6157512327792013,4940 "ci_high": 0.6393357625835018,4941 "n_items": 1973,4942 "n_groups": 834943 },4944 "rougeL": {4945 "mean": 0.6334962044370955,4946 "ci_low": 0.620349326991063,4947 "ci_high": 0.6454751412720559,4948 "n_items": 1973,4949 "n_groups": 834950 },4951 "exact_match": {4952 "mean": 0.0,4953 "ci_low": 0.0,4954 "ci_high": 0.0,4955 "n_items": 1973,4956 "n_groups": 834957 },4958 "number_recall": {4959 "mean": 0.9982212246277121,4960 "ci_low": 0.9959191062464163,4961 "ci_high": 0.9998865273701226,4962 "n_items": 1973,4963 "n_groups": 834964 },4965 "placeholders_exact": {4966 "mean": 1.0,4967 "ci_low": 1.0,4968 "ci_high": 1.0,4969 "n_items": 1973,4970 "n_groups": 834971 }4972 }4973 },4974 "by_role": {4975 "abstract": {4976 "n": 36,4977 "chrf": {4978 "mean": 67.03451212552801,4979 "ci_low": 62.59293876919112,4980 "ci_high": 71.28267328827857,4981 "n_items": 36,4982 "n_groups": 64983 },4984 "edit_sim": {4985 "mean": 0.6557694051409827,4986 "ci_low": 0.6016517773308194,4987 "ci_high": 0.7110538089430709,4988 "n_items": 36,4989 "n_groups": 64990 },4991 "rougeL": {4992 "mean": 0.6384019440450303,4993 "ci_low": 0.581043725620201,4994 "ci_high": 0.6907667301728387,4995 "n_items": 36,4996 "n_groups": 64997 },4998 "exact_match": {4999 "mean": 0.0,5000 "ci_low": 0.0,5001 "ci_high": 0.0,5002 "n_items": 36,5003 "n_groups": 65004 },5005 "number_recall": {5006 "mean": 0.9944444444444444,5007 "ci_low": 0.9833333333333333,5008 "ci_high": 1.0,5009 "n_items": 36,5010 "n_groups": 65011 },5012 "placeholders_exact": {5013 "mean": 1.0,5014 "ci_low": 1.0,5015 "ci_high": 1.0,5016 "n_items": 36,5017 "n_groups": 65018 }5019 },5020 "chapter": {5021 "n": 819,5022 "chrf": {5023 "mean": 61.98363126958212,5024 "ci_low": 60.62537362370712,5025 "ci_high": 63.32251565723345,5026 "n_items": 819,5027 "n_groups": 525028 },5029 "edit_sim": {5030 "mean": 0.6317082235296893,5031 "ci_low": 0.6167012102510957,5032 "ci_high": 0.6463727755006659,5033 "n_items": 819,5034 "n_groups": 525035 },5036 "rougeL": {5037 "mean": 0.6396451699930349,5038 "ci_low": 0.6241230751554395,5039 "ci_high": 0.6538773366389151,5040 "n_items": 819,5041 "n_groups": 525042 },5043 "exact_match": {5044 "mean": 0.0,5045 "ci_low": 0.0,5046 "ci_high": 0.0,5047 "n_items": 819,5048 "n_groups": 525049 },5050 "number_recall": {5051 "mean": 0.9967032967032966,5052 "ci_low": 0.9916858753083805,5053 "ci_high": 1.0,5054 "n_items": 819,5055 "n_groups": 525056 },5057 "placeholders_exact": {5058 "mean": 1.0,5059 "ci_low": 1.0,5060 "ci_high": 1.0,5061 "n_items": 819,5062 "n_groups": 525063 }5064 },5065 "conclusion": {5066 "n": 104,5067 "chrf": {5068 "mean": 70.05094254356646,5069 "ci_low": 63.64422880883735,5070 "ci_high": 73.56415847745932,5071 "n_items": 104,5072 "n_groups": 35073 },5074 "edit_sim": {5075 "mean": 0.6889403912950974,5076 "ci_low": 0.6220393864875464,5077 "ci_high": 0.7406758275736852,5078 "n_items": 104,5079 "n_groups": 35080 },5081 "rougeL": {5082 "mean": 0.6857555493438697,5083 "ci_low": 0.6105252837319404,5084 "ci_high": 0.7334063709785159,5085 "n_items": 104,5086 "n_groups": 35087 },5088 "exact_match": {5089 "mean": 0.0,5090 "ci_low": 0.0,5091 "ci_high": 0.0,5092 "n_items": 104,5093 "n_groups": 35094 },5095 "number_recall": {5096 "mean": 0.9886363636363635,5097 "ci_low": 0.9722222222222222,5098 "ci_high": 1.0,5099 "n_items": 104,5100 "n_groups": 35101 },5102 "placeholders_exact": {5103 "mean": 1.0,5104 "ci_low": 1.0,5105 "ci_high": 1.0,5106 "n_items": 104,5107 "n_groups": 35108 }5109 },5110 "data": {5111 "n": 11,5112 "chrf": {5113 "mean": 77.23683184872397,5114 "ci_low": 77.23683184872397,5115 "ci_high": 77.23683184872397,5116 "n_items": 11,5117 "n_groups": 15118 },5119 "edit_sim": {5120 "mean": 0.7884358853219248,5121 "ci_low": 0.7884358853219248,5122 "ci_high": 0.7884358853219248,5123 "n_items": 11,5124 "n_groups": 15125 },5126 "rougeL": {5127 "mean": 0.8038879066476471,5128 "ci_low": 0.8038879066476471,5129 "ci_high": 0.8038879066476471,5130 "n_items": 11,5131 "n_groups": 15132 },5133 "exact_match": {5134 "mean": 0.0,5135 "ci_low": 0.0,5136 "ci_high": 0.0,5137 "n_items": 11,5138 "n_groups": 15139 },5140 "number_recall": {5141 "mean": 1.0,5142 "ci_low": 1.0,5143 "ci_high": 1.0,5144 "n_items": 11,5145 "n_groups": 15146 },5147 "placeholders_exact": {5148 "mean": 1.0,5149 "ci_low": 1.0,5150 "ci_high": 1.0,5151 "n_items": 11,5152 "n_groups": 15153 }5154 },5155 "introduction": {5156 "n": 574,5157 "chrf": {5158 "mean": 62.296856876836195,5159 "ci_low": 59.47584493426133,5160 "ci_high": 64.26678467994628,5161 "n_items": 574,5162 "n_groups": 235163 },5164 "edit_sim": {5165 "mean": 0.637614677087437,5166 "ci_low": 0.6103670891564925,5167 "ci_high": 0.6580355662784417,5168 "n_items": 574,5169 "n_groups": 235170 },5171 "rougeL": {5172 "mean": 0.6406584697193246,5173 "ci_low": 0.6129868089051868,5174 "ci_high": 0.6613979501891033,5175 "n_items": 574,5176 "n_groups": 235177 },5178 "exact_match": {5179 "mean": 0.0,5180 "ci_low": 0.0,5181 "ci_high": 0.0,5182 "n_items": 574,5183 "n_groups": 235184 },5185 "number_recall": {5186 "mean": 0.9985896797743486,5187 "ci_low": 0.9954770979555609,5188 "ci_high": 1.0,5189 "n_items": 574,5190 "n_groups": 235191 },5192 "placeholders_exact": {5193 "mean": 1.0,5194 "ci_low": 1.0,5195 "ci_high": 1.0,5196 "n_items": 574,5197 "n_groups": 235198 }5199 },5200 "methods": {5201 "n": 93,5202 "chrf": {5203 "mean": 70.77000139825014,5204 "ci_low": 67.74681479728018,5205 "ci_high": 77.62396575622036,5206 "n_items": 93,5207 "n_groups": 35208 },5209 "edit_sim": {5210 "mean": 0.6996085991914903,5211 "ci_low": 0.6717564439322309,5212 "ci_high": 0.7955888866547326,5213 "n_items": 93,5214 "n_groups": 35215 },5216 "rougeL": {5217 "mean": 0.7174687468904122,5218 "ci_low": 0.6822210640150087,5219 "ci_high": 0.8107243678614274,5220 "n_items": 93,5221 "n_groups": 35222 },5223 "exact_match": {5224 "mean": 0.0,5225 "ci_low": 0.0,5226 "ci_high": 0.0,5227 "n_items": 93,5228 "n_groups": 35229 },5230 "number_recall": {5231 "mean": 0.9764934289127837,5232 "ci_low": 0.9732426303854875,5233 "ci_high": 0.984375,5234 "n_items": 93,5235 "n_groups": 35236 },5237 "placeholders_exact": {5238 "mean": 1.0,5239 "ci_low": 1.0,5240 "ci_high": 1.0,5241 "n_items": 93,5242 "n_groups": 35243 }5244 },5245 "other": {5246 "n": 163,5247 "chrf": {5248 "mean": 65.58004311206872,5249 "ci_low": 60.105801711986366,5250 "ci_high": 70.4164907072335,5251 "n_items": 163,5252 "n_groups": 95253 },5254 "edit_sim": {5255 "mean": 0.6754187691557351,5256 "ci_low": 0.6447665458304898,5257 "ci_high": 0.7025973181978783,5258 "n_items": 163,5259 "n_groups": 95260 },5261 "rougeL": {5262 "mean": 0.6800921201952614,5263 "ci_low": 0.649814333277977,5264 "ci_high": 0.7080539239228428,5265 "n_items": 163,5266 "n_groups": 95267 },5268 "exact_match": {5269 "mean": 0.0,5270 "ci_low": 0.0,5271 "ci_high": 0.0,5272 "n_items": 163,5273 "n_groups": 95274 },5275 "number_recall": {5276 "mean": 0.9877300613496932,5277 "ci_low": 0.9574315016072249,5278 "ci_high": 1.0,5279 "n_items": 163,5280 "n_groups": 95281 },5282 "placeholders_exact": {5283 "mean": 1.0,5284 "ci_low": 1.0,5285 "ci_high": 1.0,5286 "n_items": 163,5287 "n_groups": 95288 }5289 },5290 "preface": {5291 "n": 562,5292 "chrf": {5293 "mean": 60.284985941857585,5294 "ci_low": 58.443327612420696,5295 "ci_high": 62.20391280850361,5296 "n_items": 562,5297 "n_groups": 485298 },5299 "edit_sim": {5300 "mean": 0.6164878912925542,5301 "ci_low": 0.5985514514152959,5302 "ci_high": 0.6355849453254595,5303 "n_items": 562,5304 "n_groups": 485305 },5306 "rougeL": {5307 "mean": 0.6205556099985854,5308 "ci_low": 0.6003181341301932,5309 "ci_high": 0.6414689414700447,5310 "n_items": 562,5311 "n_groups": 485312 },5313 "exact_match": {5314 "mean": 0.0,5315 "ci_low": 0.0,5316 "ci_high": 0.0,5317 "n_items": 562,5318 "n_groups": 485319 },5320 "number_recall": {5321 "mean": 1.0,5322 "ci_low": 1.0,5323 "ci_high": 1.0,5324 "n_items": 562,5325 "n_groups": 485326 },5327 "placeholders_exact": {5328 "mean": 1.0,5329 "ci_low": 1.0,5330 "ci_high": 1.0,5331 "n_items": 562,5332 "n_groups": 485333 }5334 },5335 "related_work": {5336 "n": 18,5337 "chrf": {5338 "mean": 70.86032279033135,5339 "ci_low": 70.86032279033135,5340 "ci_high": 70.86032279033135,5341 "n_items": 18,5342 "n_groups": 15343 },5344 "edit_sim": {5345 "mean": 0.7061401157539375,5346 "ci_low": 0.7061401157539375,5347 "ci_high": 0.7061401157539375,5348 "n_items": 18,5349 "n_groups": 15350 },5351 "rougeL": {5352 "mean": 0.6873408978942739,5353 "ci_low": 0.6873408978942739,5354 "ci_high": 0.6873408978942739,5355 "n_items": 18,5356 "n_groups": 15357 },5358 "exact_match": {5359 "mean": 0.0,5360 "ci_low": 0.0,5361 "ci_high": 0.0,5362 "n_items": 18,5363 "n_groups": 15364 },5365 "number_recall": {5366 "mean": 1.0,5367 "ci_low": 1.0,5368 "ci_high": 1.0,5369 "n_items": 18,5370 "n_groups": 15371 },5372 "placeholders_exact": {5373 "mean": 0.8333333333333334,5374 "ci_low": 0.8333333333333334,5375 "ci_high": 0.8333333333333334,5376 "n_items": 18,5377 "n_groups": 15378 }5379 },5380 "results": {5381 "n": 158,5382 "chrf": {5383 "mean": 70.58959771666562,5384 "ci_low": 68.03574262729909,5385 "ci_high": 77.2665396508275,5386 "n_items": 158,5387 "n_groups": 35388 },5389 "edit_sim": {5390 "mean": 0.695527940262031,5391 "ci_low": 0.6698651665714728,5392 "ci_high": 0.722648096718808,5393 "n_items": 158,5394 "n_groups": 35395 },5396 "rougeL": {5397 "mean": 0.698690950002176,5398 "ci_low": 0.6807354164380409,5399 "ci_high": 0.7534133253109662,5400 "n_items": 158,5401 "n_groups": 35402 },5403 "exact_match": {5404 "mean": 0.0,5405 "ci_low": 0.0,5406 "ci_high": 0.0,5407 "n_items": 158,5408 "n_groups": 35409 },5410 "number_recall": {5411 "mean": 0.9667721518987342,5412 "ci_low": 0.9383116883116883,5413 "ci_high": 1.0,5414 "n_items": 158,5415 "n_groups": 35416 },5417 "placeholders_exact": {5418 "mean": 0.9683544303797469,5419 "ci_low": 0.935064935064935,5420 "ci_high": 1.0,5421 "n_items": 158,5422 "n_groups": 35423 }5424 },5425 "theory": {5426 "n": 36,5427 "chrf": {5428 "mean": 74.52419604964689,5429 "ci_low": 69.44572200693011,5430 "ci_high": 75.53989085819028,5431 "n_items": 36,5432 "n_groups": 25433 },5434 "edit_sim": {5435 "mean": 0.7481567636351026,5436 "ci_low": 0.7340454766737691,5437 "ci_high": 0.7509790210273695,5438 "n_items": 36,5439 "n_groups": 25440 },5441 "rougeL": {5442 "mean": 0.7431338250124765,5443 "ci_low": 0.6884920093617236,5444 "ci_high": 0.7540621881426272,5445 "n_items": 36,5446 "n_groups": 25447 },5448 "exact_match": {5449 "mean": 0.0,5450 "ci_low": 0.0,5451 "ci_high": 0.0,5452 "n_items": 36,5453 "n_groups": 25454 },5455 "number_recall": {5456 "mean": 1.0,5457 "ci_low": 1.0,5458 "ci_high": 1.0,5459 "n_items": 36,5460 "n_groups": 25461 },5462 "placeholders_exact": {5463 "mean": 1.0,5464 "ci_low": 1.0,5465 "ci_high": 1.0,5466 "n_items": 36,5467 "n_groups": 25468 }5469 }5470 }5471 },5472 "htr-m1-tiny-s3": {5473 "overall": {5474 "n": 2574,5475 "chrf": {5476 "mean": 63.474551100369354,5477 "ci_low": 61.407936323363,5478 "ci_high": 65.29135242097931,5479 "n_items": 2574,5480 "n_groups": 925481 },5482 "edit_sim": {5483 "mean": 0.6434657728673415,5484 "ci_low": 0.6265047733324814,5485 "ci_high": 0.6590414768428281,5486 "n_items": 2574,5487 "n_groups": 925488 },5489 "rougeL": {5490 "mean": 0.6480367969263827,5491 "ci_low": 0.6306619509354494,5492 "ci_high": 0.6642130172782358,5493 "n_items": 2574,5494 "n_groups": 925495 },5496 "exact_match": {5497 "mean": 0.0,5498 "ci_low": 0.0,5499 "ci_high": 0.0,5500 "n_items": 2574,5501 "n_groups": 925502 },5503 "number_recall": {5504 "mean": 0.9937895437895438,5505 "ci_low": 0.9882297862086029,5506 "ci_high": 0.9981493094667437,5507 "n_items": 2574,5508 "n_groups": 925509 },5510 "placeholders_exact": {5511 "mean": 0.9992229992229992,5512 "ci_low": 0.9975030691019815,5513 "ci_high": 1.0,5514 "n_items": 2574,5515 "n_groups": 925516 }5517 },5518 "by_variant": {5519 "A": {5520 "n": 436,5521 "chrf": {5522 "mean": 62.748216770300196,5523 "ci_low": 60.5039953055662,5524 "ci_high": 64.58956130120146,5525 "n_items": 436,5526 "n_groups": 915527 },5528 "edit_sim": {5529 "mean": 0.6342124070767133,5530 "ci_low": 0.6152011392245574,5531 "ci_high": 0.6499363062084965,5532 "n_items": 436,5533 "n_groups": 915534 },5535 "rougeL": {5536 "mean": 0.6381340809643968,5537 "ci_low": 0.6187549617726598,5538 "ci_high": 0.6541449584058717,5539 "n_items": 436,5540 "n_groups": 915541 },5542 "exact_match": {5543 "mean": 0.0,5544 "ci_low": 0.0,5545 "ci_high": 0.0,5546 "n_items": 436,5547 "n_groups": 915548 },5549 "number_recall": {5550 "mean": 0.9922564438619484,5551 "ci_low": 0.9856413348837098,5552 "ci_high": 0.9984292097998619,5553 "n_items": 436,5554 "n_groups": 915555 },5556 "placeholders_exact": {5557 "mean": 0.9954128440366973,5558 "ci_low": 0.9860772638034819,5559 "ci_high": 1.0,5560 "n_items": 436,5561 "n_groups": 915562 }5563 },5564 "B": {5565 "n": 416,5566 "chrf": {5567 "mean": 68.46654902978167,5568 "ci_low": 66.08125375774937,5569 "ci_high": 70.72793439636564,5570 "n_items": 416,5571 "n_groups": 905572 },5573 "edit_sim": {5574 "mean": 0.6965602279458794,5575 "ci_low": 0.6741802344803693,5576 "ci_high": 0.7175444125264733,5577 "n_items": 416,5578 "n_groups": 905579 },5580 "rougeL": {5581 "mean": 0.7029676490334327,5582 "ci_low": 0.6805394105841657,5583 "ci_high": 0.7238312284020931,5584 "n_items": 416,5585 "n_groups": 905586 },5587 "exact_match": {5588 "mean": 0.0,5589 "ci_low": 0.0,5590 "ci_high": 0.0,5591 "n_items": 416,5592 "n_groups": 905593 },5594 "number_recall": {5595 "mean": 0.9937099358974358,5596 "ci_low": 0.9873448046195074,5597 "ci_high": 0.9996438999368686,5598 "n_items": 416,5599 "n_groups": 905600 },5601 "placeholders_exact": {5602 "mean": 1.0,5603 "ci_low": 1.0,5604 "ci_high": 1.0,5605 "n_items": 416,5606 "n_groups": 905607 }5608 },5609 "C": {5610 "n": 438,5611 "chrf": {5612 "mean": 68.34048783140905,5613 "ci_low": 66.5020662605963,5614 "ci_high": 70.23639408207882,5615 "n_items": 438,5616 "n_groups": 915617 },5618 "edit_sim": {5619 "mean": 0.7062011749987047,5620 "ci_low": 0.6888459575127175,5621 "ci_high": 0.7235107487254411,5622 "n_items": 438,5623 "n_groups": 915624 },5625 "rougeL": {5626 "mean": 0.7222113832480558,5627 "ci_low": 0.7042953957633027,5628 "ci_high": 0.7401973373360556,5629 "n_items": 438,5630 "n_groups": 915631 },5632 "exact_match": {5633 "mean": 0.0,5634 "ci_low": 0.0,5635 "ci_high": 0.0,5636 "n_items": 438,5637 "n_groups": 915638 },5639 "number_recall": {5640 "mean": 0.9951103500761035,5641 "ci_low": 0.9877682606934843,5642 "ci_high": 0.9997573108672201,5643 "n_items": 438,5644 "n_groups": 915645 },5646 "placeholders_exact": {5647 "mean": 1.0,5648 "ci_low": 1.0,5649 "ci_high": 1.0,5650 "n_items": 438,5651 "n_groups": 915652 }5653 },5654 "D": {5655 "n": 431,5656 "chrf": {5657 "mean": 62.962111543324006,5658 "ci_low": 60.602806088547794,5659 "ci_high": 64.92687849025964,5660 "n_items": 431,5661 "n_groups": 905662 },5663 "edit_sim": {5664 "mean": 0.6435871096025425,5665 "ci_low": 0.6235063260309017,5666 "ci_high": 0.659921646369814,5667 "n_items": 431,5668 "n_groups": 905669 },5670 "rougeL": {5671 "mean": 0.6451577022299171,5672 "ci_low": 0.6248868400238977,5673 "ci_high": 0.6622718105237916,5674 "n_items": 431,5675 "n_groups": 905676 },5677 "exact_match": {5678 "mean": 0.0,5679 "ci_low": 0.0,5680 "ci_high": 0.0,5681 "n_items": 431,5682 "n_groups": 905683 },5684 "number_recall": {5685 "mean": 0.9926914153132251,5686 "ci_low": 0.9867711289194722,5687 "ci_high": 0.9981184984764107,5688 "n_items": 431,5689 "n_groups": 905690 },5691 "placeholders_exact": {5692 "mean": 1.0,5693 "ci_low": 1.0,5694 "ci_high": 1.0,5695 "n_items": 431,5696 "n_groups": 905697 }5698 },5699 "E": {5700 "n": 853,5701 "chrf": {5702 "mean": 59.17161064335385,5703 "ci_low": 57.07437154023599,5704 "ci_high": 61.041573295822886,5705 "n_items": 853,5706 "n_groups": 915707 },5708 "edit_sim": {5709 "mean": 0.5900270529442859,5710 "ci_low": 0.5741234601945692,5711 "ci_high": 0.6057090932899581,5712 "n_items": 853,5713 "n_groups": 915714 },5715 "rougeL": {5716 "mean": 0.5896766218832138,5717 "ci_low": 0.5719992741359402,5718 "ci_high": 0.6063365045644118,5719 "n_items": 853,5720 "n_groups": 915721 },5722 "exact_match": {5723 "mean": 0.0,5724 "ci_low": 0.0,5725 "ci_high": 0.0,5726 "n_items": 853,5727 "n_groups": 915728 },5729 "number_recall": {5730 "mean": 0.9944886395355328,5731 "ci_low": 0.9897796812236659,5732 "ci_high": 0.9986235722768727,5733 "n_items": 853,5734 "n_groups": 915735 },5736 "placeholders_exact": {5737 "mean": 1.0,5738 "ci_low": 1.0,5739 "ci_high": 1.0,5740 "n_items": 853,5741 "n_groups": 915742 }5743 }5744 },5745 "by_discipline": {5746 "biomedicine": {5747 "n": 438,5748 "chrf": {5749 "mean": 64.07858003286506,5750 "ci_low": 57.94835369809642,5751 "ci_high": 68.77936005739235,5752 "n_items": 438,5753 "n_groups": 225754 },5755 "edit_sim": {5756 "mean": 0.6470307056713842,5757 "ci_low": 0.5929433248247337,5758 "ci_high": 0.6888536459041962,5759 "n_items": 438,5760 "n_groups": 225761 },5762 "rougeL": {5763 "mean": 0.6455489547808974,5764 "ci_low": 0.5895400613694352,5765 "ci_high": 0.6862572412019005,5766 "n_items": 438,5767 "n_groups": 225768 },5769 "exact_match": {5770 "mean": 0.0,5771 "ci_low": 0.0,5772 "ci_high": 0.0,5773 "n_items": 438,5774 "n_groups": 225775 },5776 "number_recall": {5777 "mean": 0.9822271145901283,5778 "ci_low": 0.9639302109270871,5779 "ci_high": 1.0,5780 "n_items": 438,5781 "n_groups": 225782 },5783 "placeholders_exact": {5784 "mean": 0.9954337899543378,5785 "ci_low": 0.9901153212520593,5786 "ci_high": 1.0,5787 "n_items": 438,5788 "n_groups": 225789 }5790 },5791 "chemistry": {5792 "n": 183,5793 "chrf": {5794 "mean": 65.16545646980622,5795 "ci_low": 65.16545646980622,5796 "ci_high": 65.16545646980622,5797 "n_items": 183,5798 "n_groups": 15799 },5800 "edit_sim": {5801 "mean": 0.6496673677495658,5802 "ci_low": 0.6496673677495658,5803 "ci_high": 0.6496673677495658,5804 "n_items": 183,5805 "n_groups": 15806 },5807 "rougeL": {5808 "mean": 0.6573829417134269,5809 "ci_low": 0.6573829417134269,5810 "ci_high": 0.6573829417134269,5811 "n_items": 183,5812 "n_groups": 15813 },5814 "exact_match": {5815 "mean": 0.0,5816 "ci_low": 0.0,5817 "ci_high": 0.0,5818 "n_items": 183,5819 "n_groups": 15820 },5821 "number_recall": {5822 "mean": 0.9890710382513661,5823 "ci_low": 0.9890710382513661,5824 "ci_high": 0.9890710382513661,5825 "n_items": 183,5826 "n_groups": 15827 },5828 "placeholders_exact": {5829 "mean": 1.0,5830 "ci_low": 1.0,5831 "ci_high": 1.0,5832 "n_items": 183,5833 "n_groups": 15834 }5835 },5836 "earth_sciences": {5837 "n": 101,5838 "chrf": {5839 "mean": 61.51992684330755,5840 "ci_low": 61.51992684330755,5841 "ci_high": 61.51992684330755,5842 "n_items": 101,5843 "n_groups": 15844 },5845 "edit_sim": {5846 "mean": 0.6056031275034426,5847 "ci_low": 0.6056031275034426,5848 "ci_high": 0.6056031275034426,5849 "n_items": 101,5850 "n_groups": 15851 },5852 "rougeL": {5853 "mean": 0.6186601253079029,5854 "ci_low": 0.6186601253079029,5855 "ci_high": 0.6186601253079029,5856 "n_items": 101,5857 "n_groups": 15858 },5859 "exact_match": {5860 "mean": 0.0,5861 "ci_low": 0.0,5862 "ci_high": 0.0,5863 "n_items": 101,5864 "n_groups": 15865 },5866 "number_recall": {5867 "mean": 0.9900990099009901,5868 "ci_low": 0.9900990099009901,5869 "ci_high": 0.9900990099009901,5870 "n_items": 101,5871 "n_groups": 15872 },5873 "placeholders_exact": {5874 "mean": 1.0,5875 "ci_low": 1.0,5876 "ci_high": 1.0,5877 "n_items": 101,5878 "n_groups": 15879 }5880 },5881 "economics": {5882 "n": 569,5883 "chrf": {5884 "mean": 67.85301784455204,5885 "ci_low": 62.964064896197804,5886 "ci_high": 71.29659424870454,5887 "n_items": 569,5888 "n_groups": 85889 },5890 "edit_sim": {5891 "mean": 0.6748085081261566,5892 "ci_low": 0.6357499220645547,5893 "ci_high": 0.7066130425470893,5894 "n_items": 569,5895 "n_groups": 85896 },5897 "rougeL": {5898 "mean": 0.6806007215955242,5899 "ci_low": 0.638779420924612,5900 "ci_high": 0.7149635477905282,5901 "n_items": 569,5902 "n_groups": 85903 },5904 "exact_match": {5905 "mean": 0.0,5906 "ci_low": 0.0,5907 "ci_high": 0.0,5908 "n_items": 569,5909 "n_groups": 85910 },5911 "number_recall": {5912 "mean": 0.9924554356013054,5913 "ci_low": 0.9879220246329214,5914 "ci_high": 0.9995004995004996,5915 "n_items": 569,5916 "n_groups": 85917 },5918 "placeholders_exact": {5919 "mean": 1.0,5920 "ci_low": 1.0,5921 "ci_high": 1.0,5922 "n_items": 569,5923 "n_groups": 85924 }5925 },5926 "engineering": {5927 "n": 167,5928 "chrf": {5929 "mean": 60.382067659406175,5930 "ci_low": 56.99969169741526,5931 "ci_high": 62.010809397752865,5932 "n_items": 167,5933 "n_groups": 85934 },5935 "edit_sim": {5936 "mean": 0.6061320398903699,5937 "ci_low": 0.5825214282443242,5938 "ci_high": 0.619288466137394,5939 "n_items": 167,5940 "n_groups": 85941 },5942 "rougeL": {5943 "mean": 0.6170933290644132,5944 "ci_low": 0.5830681276070977,5945 "ci_high": 0.634210295988579,5946 "n_items": 167,5947 "n_groups": 85948 },5949 "exact_match": {5950 "mean": 0.0,5951 "ci_low": 0.0,5952 "ci_high": 0.0,5953 "n_items": 167,5954 "n_groups": 85955 },5956 "number_recall": {5957 "mean": 0.9988023952095809,5958 "ci_low": 0.9972599597838381,5959 "ci_high": 1.0,5960 "n_items": 167,5961 "n_groups": 85962 },5963 "placeholders_exact": {5964 "mean": 1.0,5965 "ci_low": 1.0,5966 "ci_high": 1.0,5967 "n_items": 167,5968 "n_groups": 85969 }5970 },5971 "finance": {5972 "n": 75,5973 "chrf": {5974 "mean": 58.51185443122204,5975 "ci_low": 58.32856364008017,5976 "ci_high": 59.31047859262593,5977 "n_items": 75,5978 "n_groups": 25979 },5980 "edit_sim": {5981 "mean": 0.5948032641589848,5982 "ci_low": 0.5903870563852172,5983 "ci_high": 0.5958168200414888,5984 "n_items": 75,5985 "n_groups": 25986 },5987 "rougeL": {5988 "mean": 0.5947352011594309,5989 "ci_low": 0.5914999744798409,5990 "ci_high": 0.5954777122006482,5991 "n_items": 75,5992 "n_groups": 25993 },5994 "exact_match": {5995 "mean": 0.0,5996 "ci_low": 0.0,5997 "ci_high": 0.0,5998 "n_items": 75,5999 "n_groups": 26000 },6001 "number_recall": {6002 "mean": 1.0,6003 "ci_low": 1.0,6004 "ci_high": 1.0,6005 "n_items": 75,6006 "n_groups": 26007 },6008 "placeholders_exact": {6009 "mean": 1.0,6010 "ci_low": 1.0,6011 "ci_high": 1.0,6012 "n_items": 75,6013 "n_groups": 26014 }6015 },6016 "general_reference": {6017 "n": 256,6018 "chrf": {6019 "mean": 62.39619250047674,6020 "ci_low": 59.216392990242056,6021 "ci_high": 64.66504851829815,6022 "n_items": 256,6023 "n_groups": 126024 },6025 "edit_sim": {6026 "mean": 0.6440647297684736,6027 "ci_low": 0.6057495933799943,6028 "ci_high": 0.6677546441238521,6029 "n_items": 256,6030 "n_groups": 126031 },6032 "rougeL": {6033 "mean": 0.6475901395561844,6034 "ci_low": 0.6016535982522895,6035 "ci_high": 0.6712592420801794,6036 "n_items": 256,6037 "n_groups": 126038 },6039 "exact_match": {6040 "mean": 0.0,6041 "ci_low": 0.0,6042 "ci_high": 0.0,6043 "n_items": 256,6044 "n_groups": 126045 },6046 "number_recall": {6047 "mean": 0.9986979166666666,6048 "ci_low": 0.9944743707796194,6049 "ci_high": 1.0,6050 "n_items": 256,6051 "n_groups": 126052 },6053 "placeholders_exact": {6054 "mean": 1.0,6055 "ci_low": 1.0,6056 "ci_high": 1.0,6057 "n_items": 256,6058 "n_groups": 126059 }6060 },6061 "humanities": {6062 "n": 253,6063 "chrf": {6064 "mean": 63.5205288443821,6065 "ci_low": 60.15539782030353,6066 "ci_high": 67.00202268299174,6067 "n_items": 253,6068 "n_groups": 96069 },6070 "edit_sim": {6071 "mean": 0.6558708888240486,6072 "ci_low": 0.6256629490886136,6073 "ci_high": 0.6982397828274497,6074 "n_items": 253,6075 "n_groups": 96076 },6077 "rougeL": {6078 "mean": 0.6611815006367338,6079 "ci_low": 0.6291705806286066,6080 "ci_high": 0.6987857949554275,6081 "n_items": 253,6082 "n_groups": 96083 },6084 "exact_match": {6085 "mean": 0.0,6086 "ci_low": 0.0,6087 "ci_high": 0.0,6088 "n_items": 253,6089 "n_groups": 96090 },6091 "number_recall": {6092 "mean": 1.0,6093 "ci_low": 1.0,6094 "ci_high": 1.0,6095 "n_items": 253,6096 "n_groups": 96097 },6098 "placeholders_exact": {6099 "mean": 1.0,6100 "ci_low": 1.0,6101 "ci_high": 1.0,6102 "n_items": 253,6103 "n_groups": 96104 }6105 },6106 "life_sciences": {6107 "n": 233,6108 "chrf": {6109 "mean": 60.76304904257558,6110 "ci_low": 58.10767970058243,6111 "ci_high": 63.811743649546344,6112 "n_items": 233,6113 "n_groups": 86114 },6115 "edit_sim": {6116 "mean": 0.6190886109068078,6117 "ci_low": 0.5962514346263595,6118 "ci_high": 0.6448489787399078,6119 "n_items": 233,6120 "n_groups": 86121 },6122 "rougeL": {6123 "mean": 0.6281077577523666,6124 "ci_low": 0.602058379763831,6125 "ci_high": 0.6570586390124875,6126 "n_items": 233,6127 "n_groups": 86128 },6129 "exact_match": {6130 "mean": 0.0,6131 "ci_low": 0.0,6132 "ci_high": 0.0,6133 "n_items": 233,6134 "n_groups": 86135 },6136 "number_recall": {6137 "mean": 0.9983905579399142,6138 "ci_low": 0.9947668305803086,6139 "ci_high": 1.0,6140 "n_items": 233,6141 "n_groups": 86142 },6143 "placeholders_exact": {6144 "mean": 1.0,6145 "ci_low": 1.0,6146 "ci_high": 1.0,6147 "n_items": 233,6148 "n_groups": 86149 }6150 },6151 "social_sciences": {6152 "n": 299,6153 "chrf": {6154 "mean": 59.85222171613306,6155 "ci_low": 57.3968622075126,6156 "ci_high": 62.02838324198945,6157 "n_items": 299,6158 "n_groups": 216159 },6160 "edit_sim": {6161 "mean": 0.6286371821690775,6162 "ci_low": 0.6048370543124871,6163 "ci_high": 0.6509856388182773,6164 "n_items": 299,6165 "n_groups": 216166 },6167 "rougeL": {6168 "mean": 0.6293574666637958,6169 "ci_low": 0.6016755389085302,6170 "ci_high": 0.6554750242228783,6171 "n_items": 299,6172 "n_groups": 216173 },6174 "exact_match": {6175 "mean": 0.0,6176 "ci_low": 0.0,6177 "ci_high": 0.0,6178 "n_items": 299,6179 "n_groups": 216180 },6181 "number_recall": {6182 "mean": 1.0,6183 "ci_low": 1.0,6184 "ci_high": 1.0,6185 "n_items": 299,6186 "n_groups": 216187 },6188 "placeholders_exact": {6189 "mean": 1.0,6190 "ci_low": 1.0,6191 "ci_high": 1.0,6192 "n_items": 299,6193 "n_groups": 216194 }6195 }6196 },6197 "by_era": {6198 "1900-1949": {6199 "n": 74,6200 "chrf": {6201 "mean": 65.02110089820836,6202 "ci_low": 62.90760046412842,6203 "ci_high": 71.49395087590581,6204 "n_items": 74,6205 "n_groups": 56206 },6207 "edit_sim": {6208 "mean": 0.6763275488120659,6209 "ci_low": 0.6205056414486535,6210 "ci_high": 0.7000590679059737,6211 "n_items": 74,6212 "n_groups": 56213 },6214 "rougeL": {6215 "mean": 0.6679280429975806,6216 "ci_low": 0.5947639591840225,6217 "ci_high": 0.6931558492716189,6218 "n_items": 74,6219 "n_groups": 56220 },6221 "exact_match": {6222 "mean": 0.0,6223 "ci_low": 0.0,6224 "ci_high": 0.0,6225 "n_items": 74,6226 "n_groups": 56227 },6228 "number_recall": {6229 "mean": 0.991891891891892,6230 "ci_low": 0.9400000000000001,6231 "ci_high": 1.0,6232 "n_items": 74,6233 "n_groups": 56234 },6235 "placeholders_exact": {6236 "mean": 1.0,6237 "ci_low": 1.0,6238 "ci_high": 1.0,6239 "n_items": 74,6240 "n_groups": 56241 }6242 },6243 "2010-2017": {6244 "n": 527,6245 "chrf": {6246 "mean": 70.69121864036687,6247 "ci_low": 66.85465497749038,6248 "ci_high": 73.41916488117839,6249 "n_items": 527,6250 "n_groups": 46251 },6252 "edit_sim": {6253 "mean": 0.6978826587421825,6254 "ci_low": 0.660770720248898,6255 "ci_high": 0.7269715437407065,6256 "n_items": 527,6257 "n_groups": 46258 },6259 "rougeL": {6260 "mean": 0.7009924202293968,6261 "ci_low": 0.6592902975943,6262 "ci_high": 0.7316696454173419,6263 "n_items": 527,6264 "n_groups": 46265 },6266 "exact_match": {6267 "mean": 0.0,6268 "ci_low": 0.0,6269 "ci_high": 0.0,6270 "n_items": 527,6271 "n_groups": 46272 },6273 "number_recall": {6274 "mean": 0.9787634408602149,6275 "ci_low": 0.9545698924731182,6276 "ci_high": 0.9934272300469484,6277 "n_items": 527,6278 "n_groups": 46279 },6280 "placeholders_exact": {6281 "mean": 0.9962049335863378,6282 "ci_low": 0.9870967741935484,6283 "ci_high": 1.0,6284 "n_items": 527,6285 "n_groups": 46286 }6287 },6288 "pre1900": {6289 "n": 1973,6290 "chrf": {6291 "mean": 61.48893098956409,6292 "ci_low": 60.133262741116326,6293 "ci_high": 62.70454038487894,6294 "n_items": 1973,6295 "n_groups": 836296 },6297 "edit_sim": {6298 "mean": 0.6276981751603214,6299 "ci_low": 0.6158267998382692,6300 "ci_high": 0.6391549363183,6301 "n_items": 1973,6302 "n_groups": 836303 },6304 "rougeL": {6305 "mean": 0.6331459881630999,6306 "ci_low": 0.620279011380331,6307 "ci_high": 0.6451155714534675,6308 "n_items": 1973,6309 "n_groups": 836310 },6311 "exact_match": {6312 "mean": 0.0,6313 "ci_low": 0.0,6314 "ci_high": 0.0,6315 "n_items": 1973,6316 "n_groups": 836317 },6318 "number_recall": {6319 "mean": 0.9978742789563875,6320 "ci_low": 0.9960091390416443,6321 "ci_high": 0.9995584424186134,6322 "n_items": 1973,6323 "n_groups": 836324 },6325 "placeholders_exact": {6326 "mean": 1.0,6327 "ci_low": 1.0,6328 "ci_high": 1.0,6329 "n_items": 1973,6330 "n_groups": 836331 }6332 }6333 },6334 "by_role": {6335 "abstract": {6336 "n": 36,6337 "chrf": {6338 "mean": 66.59391140033574,6339 "ci_low": 62.11192721547359,6340 "ci_high": 70.8278273328549,6341 "n_items": 36,6342 "n_groups": 66343 },6344 "edit_sim": {6345 "mean": 0.6514405849188383,6346 "ci_low": 0.6008973563557538,6347 "ci_high": 0.7019838134819225,6348 "n_items": 36,6349 "n_groups": 66350 },6351 "rougeL": {6352 "mean": 0.6278831408454258,6353 "ci_low": 0.5736810329267368,6354 "ci_high": 0.6797402981865045,6355 "n_items": 36,6356 "n_groups": 66357 },6358 "exact_match": {6359 "mean": 0.0,6360 "ci_low": 0.0,6361 "ci_high": 0.0,6362 "n_items": 36,6363 "n_groups": 66364 },6365 "number_recall": {6366 "mean": 0.9833333333333333,6367 "ci_low": 0.9499999999999998,6368 "ci_high": 1.0,6369 "n_items": 36,6370 "n_groups": 66371 },6372 "placeholders_exact": {6373 "mean": 1.0,6374 "ci_low": 1.0,6375 "ci_high": 1.0,6376 "n_items": 36,6377 "n_groups": 66378 }6379 },6380 "chapter": {6381 "n": 819,6382 "chrf": {6383 "mean": 62.07296518784751,6384 "ci_low": 60.721001981091334,6385 "ci_high": 63.428120034052455,6386 "n_items": 819,6387 "n_groups": 526388 },6389 "edit_sim": {6390 "mean": 0.6316961516685653,6391 "ci_low": 0.6169169315701166,6392 "ci_high": 0.6467831585152553,6393 "n_items": 819,6394 "n_groups": 526395 },6396 "rougeL": {6397 "mean": 0.6388724397259115,6398 "ci_low": 0.6233314692484476,6399 "ci_high": 0.6537249864915924,6400 "n_items": 819,6401 "n_groups": 526402 },6403 "exact_match": {6404 "mean": 0.0,6405 "ci_low": 0.0,6406 "ci_high": 0.0,6407 "n_items": 819,6408 "n_groups": 526409 },6410 "number_recall": {6411 "mean": 0.9954604918890633,6412 "ci_low": 0.9912939637158055,6413 "ci_high": 0.9994239450940519,6414 "n_items": 819,6415 "n_groups": 526416 },6417 "placeholders_exact": {6418 "mean": 1.0,6419 "ci_low": 1.0,6420 "ci_high": 1.0,6421 "n_items": 819,6422 "n_groups": 526423 }6424 },6425 "conclusion": {6426 "n": 104,6427 "chrf": {6428 "mean": 69.87798088231267,6429 "ci_low": 62.648063414230016,6430 "ci_high": 73.97129273300428,6431 "n_items": 104,6432 "n_groups": 36433 },6434 "edit_sim": {6435 "mean": 0.6872631466930172,6436 "ci_low": 0.614483990851413,6437 "ci_high": 0.7297055982880313,6438 "n_items": 104,6439 "n_groups": 36440 },6441 "rougeL": {6442 "mean": 0.681965864011047,6443 "ci_low": 0.5961158322723166,6444 "ci_high": 0.7358705626974882,6445 "n_items": 104,6446 "n_groups": 36447 },6448 "exact_match": {6449 "mean": 0.0,6450 "ci_low": 0.0,6451 "ci_high": 0.0,6452 "n_items": 104,6453 "n_groups": 36454 },6455 "number_recall": {6456 "mean": 0.9903846153846154,6457 "ci_low": 0.9722222222222222,6458 "ci_high": 1.0,6459 "n_items": 104,6460 "n_groups": 36461 },6462 "placeholders_exact": {6463 "mean": 1.0,6464 "ci_low": 1.0,6465 "ci_high": 1.0,6466 "n_items": 104,6467 "n_groups": 36468 }6469 },6470 "data": {6471 "n": 11,6472 "chrf": {6473 "mean": 77.00568995803592,6474 "ci_low": 77.00568995803592,6475 "ci_high": 77.00568995803592,6476 "n_items": 11,6477 "n_groups": 16478 },6479 "edit_sim": {6480 "mean": 0.7821598304812752,6481 "ci_low": 0.7821598304812752,6482 "ci_high": 0.7821598304812752,6483 "n_items": 11,6484 "n_groups": 16485 },6486 "rougeL": {6487 "mean": 0.7951430917629345,6488 "ci_low": 0.7951430917629345,6489 "ci_high": 0.7951430917629345,6490 "n_items": 11,6491 "n_groups": 16492 },6493 "exact_match": {6494 "mean": 0.0,6495 "ci_low": 0.0,6496 "ci_high": 0.0,6497 "n_items": 11,6498 "n_groups": 16499 },6500 "number_recall": {6501 "mean": 1.0,6502 "ci_low": 1.0,6503 "ci_high": 1.0,6504 "n_items": 11,6505 "n_groups": 16506 },6507 "placeholders_exact": {6508 "mean": 1.0,6509 "ci_low": 1.0,6510 "ci_high": 1.0,6511 "n_items": 11,6512 "n_groups": 16513 }6514 },6515 "introduction": {6516 "n": 574,6517 "chrf": {6518 "mean": 62.337514486391704,6519 "ci_low": 59.48121955846871,6520 "ci_high": 64.44445477360799,6521 "n_items": 574,6522 "n_groups": 236523 },6524 "edit_sim": {6525 "mean": 0.636337238694109,6526 "ci_low": 0.6091270759285158,6527 "ci_high": 0.6571855176639838,6528 "n_items": 574,6529 "n_groups": 236530 },6531 "rougeL": {6532 "mean": 0.640673779770581,6533 "ci_low": 0.6130170488092719,6534 "ci_high": 0.6611884371459608,6535 "n_items": 574,6536 "n_groups": 236537 },6538 "exact_match": {6539 "mean": 0.0,6540 "ci_low": 0.0,6541 "ci_high": 0.0,6542 "n_items": 574,6543 "n_groups": 236544 },6545 "number_recall": {6546 "mean": 0.9997511199601793,6547 "ci_low": 0.9992018408156872,6548 "ci_high": 1.0,6549 "n_items": 574,6550 "n_groups": 236551 },6552 "placeholders_exact": {6553 "mean": 1.0,6554 "ci_low": 1.0,6555 "ci_high": 1.0,6556 "n_items": 574,6557 "n_groups": 236558 }6559 },6560 "methods": {6561 "n": 93,6562 "chrf": {6563 "mean": 70.7095263283305,6564 "ci_low": 67.1069751678784,6565 "ci_high": 78.29072002450205,6566 "n_items": 93,6567 "n_groups": 36568 },6569 "edit_sim": {6570 "mean": 0.693074127069031,6571 "ci_low": 0.6597299309401774,6572 "ci_high": 0.8025236648032589,6573 "n_items": 93,6574 "n_groups": 36575 },6576 "rougeL": {6577 "mean": 0.7158073513014939,6578 "ci_low": 0.6798868762468478,6579 "ci_high": 0.8094971959347884,6580 "n_items": 93,6581 "n_groups": 36582 },6583 "exact_match": {6584 "mean": 0.0,6585 "ci_low": 0.0,6586 "ci_high": 0.0,6587 "n_items": 93,6588 "n_groups": 36589 },6590 "number_recall": {6591 "mean": 0.9728494623655914,6592 "ci_low": 0.953125,6593 "ci_high": 0.9816326530612246,6594 "n_items": 93,6595 "n_groups": 36596 },6597 "placeholders_exact": {6598 "mean": 1.0,6599 "ci_low": 1.0,6600 "ci_high": 1.0,6601 "n_items": 93,6602 "n_groups": 36603 }6604 },6605 "other": {6606 "n": 163,6607 "chrf": {6608 "mean": 65.49249057330762,6609 "ci_low": 60.02781077790663,6610 "ci_high": 70.36174095380704,6611 "n_items": 163,6612 "n_groups": 96613 },6614 "edit_sim": {6615 "mean": 0.6743533911023998,6616 "ci_low": 0.6447944107994735,6617 "ci_high": 0.7013794906274091,6618 "n_items": 163,6619 "n_groups": 96620 },6621 "rougeL": {6622 "mean": 0.6789780863041548,6623 "ci_low": 0.6480470579133221,6624 "ci_high": 0.7072845171580725,6625 "n_items": 163,6626 "n_groups": 96627 },6628 "exact_match": {6629 "mean": 0.0,6630 "ci_low": 0.0,6631 "ci_high": 0.0,6632 "n_items": 163,6633 "n_groups": 96634 },6635 "number_recall": {6636 "mean": 0.99079754601227,6637 "ci_low": 0.9760190734398783,6638 "ci_high": 1.0,6639 "n_items": 163,6640 "n_groups": 96641 },6642 "placeholders_exact": {6643 "mean": 1.0,6644 "ci_low": 1.0,6645 "ci_high": 1.0,6646 "n_items": 163,6647 "n_groups": 96648 }6649 },6650 "preface": {6651 "n": 562,6652 "chrf": {6653 "mean": 60.36913587352951,6654 "ci_low": 58.57353932961878,6655 "ci_high": 62.25136109599567,6656 "n_items": 562,6657 "n_groups": 486658 },6659 "edit_sim": {6660 "mean": 0.6169754722844948,6661 "ci_low": 0.5994057367614252,6662 "ci_high": 0.6358047053867386,6663 "n_items": 562,6664 "n_groups": 486665 },6666 "rougeL": {6667 "mean": 0.6203389814581389,6668 "ci_low": 0.6004455313007715,6669 "ci_high": 0.6411623623905776,6670 "n_items": 562,6671 "n_groups": 486672 },6673 "exact_match": {6674 "mean": 0.0,6675 "ci_low": 0.0,6676 "ci_high": 0.0,6677 "n_items": 562,6678 "n_groups": 486679 },6680 "number_recall": {6681 "mean": 0.9994068801897985,6682 "ci_low": 0.998054284715467,6683 "ci_high": 1.0,6684 "n_items": 562,6685 "n_groups": 486686 },6687 "placeholders_exact": {6688 "mean": 1.0,6689 "ci_low": 1.0,6690 "ci_high": 1.0,6691 "n_items": 562,6692 "n_groups": 486693 }6694 },6695 "related_work": {6696 "n": 18,6697 "chrf": {6698 "mean": 71.46167717689589,6699 "ci_low": 71.46167717689589,6700 "ci_high": 71.46167717689589,6701 "n_items": 18,6702 "n_groups": 16703 },6704 "edit_sim": {6705 "mean": 0.7153053381393986,6706 "ci_low": 0.7153053381393986,6707 "ci_high": 0.7153053381393986,6708 "n_items": 18,6709 "n_groups": 16710 },6711 "rougeL": {6712 "mean": 0.6927079546249848,6713 "ci_low": 0.6927079546249848,6714 "ci_high": 0.6927079546249848,6715 "n_items": 18,6716 "n_groups": 16717 },6718 "exact_match": {6719 "mean": 0.0,6720 "ci_low": 0.0,6721 "ci_high": 0.0,6722 "n_items": 18,6723 "n_groups": 16724 },6725 "number_recall": {6726 "mean": 1.0,6727 "ci_low": 1.0,6728 "ci_high": 1.0,6729 "n_items": 18,6730 "n_groups": 16731 },6732 "placeholders_exact": {6733 "mean": 1.0,6734 "ci_low": 1.0,6735 "ci_high": 1.0,6736 "n_items": 18,6737 "n_groups": 16738 }6739 },6740 "results": {6741 "n": 158,6742 "chrf": {6743 "mean": 70.42353144264207,6744 "ci_low": 67.65756777778437,6745 "ci_high": 77.43381152331938,6746 "n_items": 158,6747 "n_groups": 36748 },6749 "edit_sim": {6750 "mean": 0.6915545314554292,6751 "ci_low": 0.6619372219264377,6752 "ci_high": 0.7198627301724636,6753 "n_items": 158,6754 "n_groups": 36755 },6756 "rougeL": {6757 "mean": 0.6952323633487534,6758 "ci_low": 0.6734377952341861,6759 "ci_high": 0.753645433752093,6760 "n_items": 158,6761 "n_groups": 36762 },6763 "exact_match": {6764 "mean": 0.0,6765 "ci_low": 0.0,6766 "ci_high": 0.0,6767 "n_items": 158,6768 "n_groups": 36769 },6770 "number_recall": {6771 "mean": 0.960970464135021,6772 "ci_low": 0.9264069264069265,6773 "ci_high": 1.0,6774 "n_items": 158,6775 "n_groups": 36776 },6777 "placeholders_exact": {6778 "mean": 0.9873417721518988,6779 "ci_low": 0.974025974025974,6780 "ci_high": 1.0,6781 "n_items": 158,6782 "n_groups": 36783 }6784 },6785 "theory": {6786 "n": 36,6787 "chrf": {6788 "mean": 73.89735796040915,6789 "ci_low": 67.50900825199277,6790 "ci_high": 75.17502790209245,6791 "n_items": 36,6792 "n_groups": 26793 },6794 "edit_sim": {6795 "mean": 0.7465657121570425,6796 "ci_low": 0.6998033764187447,6797 "ci_high": 0.7559181793047021,6798 "n_items": 36,6799 "n_groups": 26800 },6801 "rougeL": {6802 "mean": 0.738865131034854,6803 "ci_low": 0.6605701426950669,6804 "ci_high": 0.7545241287028114,6805 "n_items": 36,6806 "n_groups": 26807 },6808 "exact_match": {6809 "mean": 0.0,6810 "ci_low": 0.0,6811 "ci_high": 0.0,6812 "n_items": 36,6813 "n_groups": 26814 },6815 "number_recall": {6816 "mean": 1.0,6817 "ci_low": 1.0,6818 "ci_high": 1.0,6819 "n_items": 36,6820 "n_groups": 26821 },6822 "placeholders_exact": {6823 "mean": 1.0,6824 "ci_low": 1.0,6825 "ci_high": 1.0,6826 "n_items": 36,6827 "n_groups": 26828 }6829 }6830 }6831 },6832 "htr-m1-tiny": {6833 "overall": {6834 "n": 2574,6835 "chrf": {6836 "mean": 63.45848651376445,6837 "ci_low": 61.43328818002736,6838 "ci_high": 65.23819987041992,6839 "n_items": 2574,6840 "n_groups": 926841 },6842 "edit_sim": {6843 "mean": 0.6438005469627907,6844 "ci_low": 0.6273912514437981,6845 "ci_high": 0.6585479323939735,6846 "n_items": 2574,6847 "n_groups": 926848 },6849 "rougeL": {6850 "mean": 0.6483568981023919,6851 "ci_low": 0.6315627982434614,6852 "ci_high": 0.6635727981219635,6853 "n_items": 2574,6854 "n_groups": 926855 },6856 "exact_match": {6857 "mean": 0.0,6858 "ci_low": 0.0,6859 "ci_high": 0.0,6860 "n_items": 2574,6861 "n_groups": 926862 },6863 "number_recall": {6864 "mean": 0.992706325660871,6865 "ci_low": 0.984613708751833,6866 "ci_high": 0.9982913714681168,6867 "n_items": 2574,6868 "n_groups": 926869 },6870 "placeholders_exact": {6871 "mean": 0.9992229992229992,6872 "ci_low": 0.9975030691019815,6873 "ci_high": 1.0,6874 "n_items": 2574,6875 "n_groups": 926876 }6877 },6878 "by_variant": {6879 "A": {6880 "n": 436,6881 "chrf": {6882 "mean": 62.621439221740395,6883 "ci_low": 60.43657556247043,6884 "ci_high": 64.4028128814506,6885 "n_items": 436,6886 "n_groups": 916887 },6888 "edit_sim": {6889 "mean": 0.634042879294989,6890 "ci_low": 0.61610891639274,6891 "ci_high": 0.6485492354801993,6892 "n_items": 436,6893 "n_groups": 916894 },6895 "rougeL": {6896 "mean": 0.6379511906289415,6897 "ci_low": 0.6190380067118126,6898 "ci_high": 0.6531894170454774,6899 "n_items": 436,6900 "n_groups": 916901 },6902 "exact_match": {6903 "mean": 0.0,6904 "ci_low": 0.0,6905 "ci_high": 0.0,6906 "n_items": 436,6907 "n_groups": 916908 },6909 "number_recall": {6910 "mean": 0.989298373644704,6911 "ci_low": 0.9796643379011302,6912 "ci_high": 0.9970462604560492,6913 "n_items": 436,6914 "n_groups": 916915 },6916 "placeholders_exact": {6917 "mean": 0.9977064220183486,6918 "ci_low": 0.993038631901741,6919 "ci_high": 1.0,6920 "n_items": 436,6921 "n_groups": 916922 }6923 },6924 "B": {6925 "n": 416,6926 "chrf": {6927 "mean": 68.47005314181163,6928 "ci_low": 66.14080787992266,6929 "ci_high": 70.68182683615203,6930 "n_items": 416,6931 "n_groups": 906932 },6933 "edit_sim": {6934 "mean": 0.6963217198441568,6935 "ci_low": 0.6752086506351909,6936 "ci_high": 0.7161357447172407,6937 "n_items": 416,6938 "n_groups": 906939 },6940 "rougeL": {6941 "mean": 0.702393902148889,6942 "ci_low": 0.6805906436715996,6943 "ci_high": 0.7223538578375528,6944 "n_items": 416,6945 "n_groups": 906946 },6947 "exact_match": {6948 "mean": 0.0,6949 "ci_low": 0.0,6950 "ci_high": 0.0,6951 "n_items": 416,6952 "n_groups": 906953 },6954 "number_recall": {6955 "mean": 0.9939102564102563,6956 "ci_low": 0.986692286036036,6957 "ci_high": 0.9996438999368686,6958 "n_items": 416,6959 "n_groups": 906960 },6961 "placeholders_exact": {6962 "mean": 1.0,6963 "ci_low": 1.0,6964 "ci_high": 1.0,6965 "n_items": 416,6966 "n_groups": 906967 }6968 },6969 "C": {6970 "n": 438,6971 "chrf": {6972 "mean": 68.42162543710094,6973 "ci_low": 66.55008167541678,6974 "ci_high": 70.24264978847222,6975 "n_items": 438,6976 "n_groups": 916977 },6978 "edit_sim": {6979 "mean": 0.7068764108394574,6980 "ci_low": 0.689681284674487,6981 "ci_high": 0.7235088810937035,6982 "n_items": 438,6983 "n_groups": 916984 },6985 "rougeL": {6986 "mean": 0.7223860026559822,6987 "ci_low": 0.7044862078445719,6988 "ci_high": 0.7392987812397167,6989 "n_items": 438,6990 "n_groups": 916991 },6992 "exact_match": {6993 "mean": 0.0,6994 "ci_low": 0.0,6995 "ci_high": 0.0,6996 "n_items": 438,6997 "n_groups": 916998 },6999 "number_recall": {7000 "mean": 0.992789193302892,7001 "ci_low": 0.9833124825759687,7002 "ci_high": 0.9992117227100038,7003 "n_items": 438,7004 "n_groups": 917005 },7006 "placeholders_exact": {7007 "mean": 1.0,7008 "ci_low": 1.0,7009 "ci_high": 1.0,7010 "n_items": 438,7011 "n_groups": 917012 }7013 },7014 "D": {7015 "n": 431,7016 "chrf": {7017 "mean": 63.010562037604274,7018 "ci_low": 60.718011029622886,7019 "ci_high": 64.90183347485869,7020 "n_items": 431,7021 "n_groups": 907022 },7023 "edit_sim": {7024 "mean": 0.6442751784299573,7025 "ci_low": 0.6249348681077596,7026 "ci_high": 0.6595357228576122,7027 "n_items": 431,7028 "n_groups": 907029 },7030 "rougeL": {7031 "mean": 0.6459063854398764,7032 "ci_low": 0.6264496724359626,7033 "ci_high": 0.6617889623391732,7034 "n_items": 431,7035 "n_groups": 907036 },7037 "exact_match": {7038 "mean": 0.0,7039 "ci_low": 0.0,7040 "ci_high": 0.0,7041 "n_items": 431,7042 "n_groups": 907043 },7044 "number_recall": {7045 "mean": 0.9927687548337201,7046 "ci_low": 0.9835543748120936,7047 "ci_high": 0.9994401575344034,7048 "n_items": 431,7049 "n_groups": 907050 },7051 "placeholders_exact": {7052 "mean": 1.0,7053 "ci_low": 1.0,7054 "ci_high": 1.0,7055 "n_items": 431,7056 "n_groups": 907057 }7058 },7059 "E": {7060 "n": 853,7061 "chrf": {7062 "mean": 59.120082648416876,7063 "ci_low": 57.041596368669936,7064 "ci_high": 60.983202294032445,7065 "n_items": 853,7066 "n_groups": 917067 },7068 "edit_sim": {7069 "mean": 0.5905458466628899,7070 "ci_low": 0.5748521746404168,7071 "ci_high": 0.6057066443995466,7072 "n_items": 853,7073 "n_groups": 917074 },7075 "rougeL": {7076 "mean": 0.5905478921682223,7077 "ci_low": 0.5736643037297176,7078 "ci_high": 0.6065762542878644,7079 "n_items": 853,7080 "n_groups": 917081 },7082 "exact_match": {7083 "mean": 0.0,7084 "ci_low": 0.0,7085 "ci_high": 0.0,7086 "n_items": 853,7087 "n_groups": 917088 },7089 "number_recall": {7090 "mean": 0.9937870160320336,7091 "ci_low": 0.9869676885069343,7092 "ci_high": 0.9989580753923496,7093 "n_items": 853,7094 "n_groups": 917095 },7096 "placeholders_exact": {7097 "mean": 0.9988276670574443,7098 "ci_low": 0.9962546816479401,7099 "ci_high": 1.0,7100 "n_items": 853,7101 "n_groups": 917102 }7103 }7104 },7105 "by_discipline": {7106 "biomedicine": {7107 "n": 438,7108 "chrf": {7109 "mean": 63.958090219526625,7110 "ci_low": 58.03877865619311,7111 "ci_high": 68.45278222266784,7112 "n_items": 438,7113 "n_groups": 227114 },7115 "edit_sim": {7116 "mean": 0.6457300244015479,7117 "ci_low": 0.5943913149607558,7118 "ci_high": 0.6852574845200907,7119 "n_items": 438,7120 "n_groups": 227121 },7122 "rougeL": {7123 "mean": 0.6436119483964217,7124 "ci_low": 0.5907031019071548,7125 "ci_high": 0.6820688784010402,7126 "n_items": 438,7127 "n_groups": 227128 },7129 "exact_match": {7130 "mean": 0.0,7131 "ci_low": 0.0,7132 "ci_high": 0.0,7133 "n_items": 438,7134 "n_groups": 227135 },7136 "number_recall": {7137 "mean": 0.9768264840182649,7138 "ci_low": 0.9510542964940197,7139 "ci_high": 1.0,7140 "n_items": 438,7141 "n_groups": 227142 },7143 "placeholders_exact": {7144 "mean": 0.9954337899543378,7145 "ci_low": 0.9901153212520593,7146 "ci_high": 1.0,7147 "n_items": 438,7148 "n_groups": 227149 }7150 },7151 "chemistry": {7152 "n": 183,7153 "chrf": {7154 "mean": 64.94603732675378,7155 "ci_low": 64.94603732675378,7156 "ci_high": 64.94603732675378,7157 "n_items": 183,7158 "n_groups": 17159 },7160 "edit_sim": {7161 "mean": 0.6494394186301609,7162 "ci_low": 0.6494394186301609,7163 "ci_high": 0.6494394186301609,7164 "n_items": 183,7165 "n_groups": 17166 },7167 "rougeL": {7168 "mean": 0.6574955518542438,7169 "ci_low": 0.6574955518542438,7170 "ci_high": 0.6574955518542438,7171 "n_items": 183,7172 "n_groups": 17173 },7174 "exact_match": {7175 "mean": 0.0,7176 "ci_low": 0.0,7177 "ci_high": 0.0,7178 "n_items": 183,7179 "n_groups": 17180 },7181 "number_recall": {7182 "mean": 0.9995032290114257,7183 "ci_low": 0.9995032290114257,7184 "ci_high": 0.9995032290114257,7185 "n_items": 183,7186 "n_groups": 17187 },7188 "placeholders_exact": {7189 "mean": 1.0,7190 "ci_low": 1.0,7191 "ci_high": 1.0,7192 "n_items": 183,7193 "n_groups": 17194 }7195 },7196 "earth_sciences": {7197 "n": 101,7198 "chrf": {7199 "mean": 61.66126873255568,7200 "ci_low": 61.66126873255568,7201 "ci_high": 61.66126873255568,7202 "n_items": 101,7203 "n_groups": 17204 },7205 "edit_sim": {7206 "mean": 0.6148149848048586,7207 "ci_low": 0.6148149848048586,7208 "ci_high": 0.6148149848048586,7209 "n_items": 101,7210 "n_groups": 17211 },7212 "rougeL": {7213 "mean": 0.6239776229604977,7214 "ci_low": 0.6239776229604977,7215 "ci_high": 0.6239776229604977,7216 "n_items": 101,7217 "n_groups": 17218 },7219 "exact_match": {7220 "mean": 0.0,7221 "ci_low": 0.0,7222 "ci_high": 0.0,7223 "n_items": 101,7224 "n_groups": 17225 },7226 "number_recall": {7227 "mean": 0.995049504950495,7228 "ci_low": 0.995049504950495,7229 "ci_high": 0.995049504950495,7230 "n_items": 101,7231 "n_groups": 17232 },7233 "placeholders_exact": {7234 "mean": 1.0,7235 "ci_low": 1.0,7236 "ci_high": 1.0,7237 "n_items": 101,7238 "n_groups": 17239 }7240 },7241 "economics": {7242 "n": 569,7243 "chrf": {7244 "mean": 67.89833099974581,7245 "ci_low": 63.05209395355781,7246 "ci_high": 71.15959582644933,7247 "n_items": 569,7248 "n_groups": 87249 },7250 "edit_sim": {7251 "mean": 0.6756698561463381,7252 "ci_low": 0.6375203093782293,7253 "ci_high": 0.7044980480902473,7254 "n_items": 569,7255 "n_groups": 87256 },7257 "rougeL": {7258 "mean": 0.6815024163692117,7259 "ci_low": 0.6402870831938922,7260 "ci_high": 0.7131079417326099,7261 "n_items": 569,7262 "n_groups": 87263 },7264 "exact_match": {7265 "mean": 0.0,7266 "ci_low": 0.0,7267 "ci_high": 0.0,7268 "n_items": 569,7269 "n_groups": 87270 },7271 "number_recall": {7272 "mean": 0.990434345970374,7273 "ci_low": 0.9861309015537121,7274 "ci_high": 0.9995004995004996,7275 "n_items": 569,7276 "n_groups": 87277 },7278 "placeholders_exact": {7279 "mean": 1.0,7280 "ci_low": 1.0,7281 "ci_high": 1.0,7282 "n_items": 569,7283 "n_groups": 87284 }7285 },7286 "engineering": {7287 "n": 167,7288 "chrf": {7289 "mean": 60.16474282628129,7290 "ci_low": 56.412790733924986,7291 "ci_high": 61.85116990889338,7292 "n_items": 167,7293 "n_groups": 87294 },7295 "edit_sim": {7296 "mean": 0.6054415027428817,7297 "ci_low": 0.5797952289556485,7298 "ci_high": 0.6180587646611064,7299 "n_items": 167,7300 "n_groups": 87301 },7302 "rougeL": {7303 "mean": 0.6157747431440281,7304 "ci_low": 0.5791774083237674,7305 "ci_high": 0.6339529537839975,7306 "n_items": 167,7307 "n_groups": 87308 },7309 "exact_match": {7310 "mean": 0.0,7311 "ci_low": 0.0,7312 "ci_high": 0.0,7313 "n_items": 167,7314 "n_groups": 87315 },7316 "number_recall": {7317 "mean": 0.9928143712574851,7318 "ci_low": 0.9722149122807018,7319 "ci_high": 1.0,7320 "n_items": 167,7321 "n_groups": 87322 },7323 "placeholders_exact": {7324 "mean": 1.0,7325 "ci_low": 1.0,7326 "ci_high": 1.0,7327 "n_items": 167,7328 "n_groups": 87329 }7330 },7331 "finance": {7332 "n": 75,7333 "chrf": {7334 "mean": 58.36652713283301,7335 "ci_low": 58.23379017610892,7336 "ci_high": 58.944881015702215,7337 "n_items": 75,7338 "n_groups": 27339 },7340 "edit_sim": {7341 "mean": 0.5929364405409309,7342 "ci_low": 0.5901275434923133,7343 "ci_high": 0.5935811054373351,7344 "n_items": 75,7345 "n_groups": 27346 },7347 "rougeL": {7348 "mean": 0.5940297770687595,7349 "ci_low": 0.5895056894874514,7350 "ci_high": 0.5950680922513549,7351 "n_items": 75,7352 "n_groups": 27353 },7354 "exact_match": {7355 "mean": 0.0,7356 "ci_low": 0.0,7357 "ci_high": 0.0,7358 "n_items": 75,7359 "n_groups": 27360 },7361 "number_recall": {7362 "mean": 1.0,7363 "ci_low": 1.0,7364 "ci_high": 1.0,7365 "n_items": 75,7366 "n_groups": 27367 },7368 "placeholders_exact": {7369 "mean": 1.0,7370 "ci_low": 1.0,7371 "ci_high": 1.0,7372 "n_items": 75,7373 "n_groups": 27374 }7375 },7376 "general_reference": {7377 "n": 256,7378 "chrf": {7379 "mean": 62.49446091179055,7380 "ci_low": 59.29635410920114,7381 "ci_high": 64.61970950055306,7382 "n_items": 256,7383 "n_groups": 127384 },7385 "edit_sim": {7386 "mean": 0.6454940735200461,7387 "ci_low": 0.60700200856849,7388 "ci_high": 0.6671351152770439,7389 "n_items": 256,7390 "n_groups": 127391 },7392 "rougeL": {7393 "mean": 0.6494916509555452,7394 "ci_low": 0.6056336857473285,7395 "ci_high": 0.6722202505177743,7396 "n_items": 256,7397 "n_groups": 127398 },7399 "exact_match": {7400 "mean": 0.0,7401 "ci_low": 0.0,7402 "ci_high": 0.0,7403 "n_items": 256,7404 "n_groups": 127405 },7406 "number_recall": {7407 "mean": 0.9967447916666666,7408 "ci_low": 0.9932201472505561,7409 "ci_high": 1.0,7410 "n_items": 256,7411 "n_groups": 127412 },7413 "placeholders_exact": {7414 "mean": 1.0,7415 "ci_low": 1.0,7416 "ci_high": 1.0,7417 "n_items": 256,7418 "n_groups": 127419 }7420 },7421 "humanities": {7422 "n": 253,7423 "chrf": {7424 "mean": 63.47867036348178,7425 "ci_low": 60.0641619429327,7426 "ci_high": 66.93121300487896,7427 "n_items": 253,7428 "n_groups": 97429 },7430 "edit_sim": {7431 "mean": 0.6567884567758971,7432 "ci_low": 0.62589044473522,7433 "ci_high": 0.6982999062357962,7434 "n_items": 253,7435 "n_groups": 97436 },7437 "rougeL": {7438 "mean": 0.6611983832043816,7439 "ci_low": 0.6285882145295866,7440 "ci_high": 0.6982790835098305,7441 "n_items": 253,7442 "n_groups": 97443 },7444 "exact_match": {7445 "mean": 0.0,7446 "ci_low": 0.0,7447 "ci_high": 0.0,7448 "n_items": 253,7449 "n_groups": 97450 },7451 "number_recall": {7452 "mean": 1.0,7453 "ci_low": 1.0,7454 "ci_high": 1.0,7455 "n_items": 253,7456 "n_groups": 97457 },7458 "placeholders_exact": {7459 "mean": 1.0,7460 "ci_low": 1.0,7461 "ci_high": 1.0,7462 "n_items": 253,7463 "n_groups": 97464 }7465 },7466 "life_sciences": {7467 "n": 233,7468 "chrf": {7469 "mean": 60.923664371442726,7470 "ci_low": 58.327843990551294,7471 "ci_high": 63.80216072817968,7472 "n_items": 233,7473 "n_groups": 87474 },7475 "edit_sim": {7476 "mean": 0.6183452611782926,7477 "ci_low": 0.5963818195664977,7478 "ci_high": 0.6441628565076529,7479 "n_items": 233,7480 "n_groups": 87481 },7482 "rougeL": {7483 "mean": 0.6287809868860488,7484 "ci_low": 0.6037838510782497,7485 "ci_high": 0.6573474859300358,7486 "n_items": 233,7487 "n_groups": 87488 },7489 "exact_match": {7490 "mean": 0.0,7491 "ci_low": 0.0,7492 "ci_high": 0.0,7493 "n_items": 233,7494 "n_groups": 87495 },7496 "number_recall": {7497 "mean": 0.9976102223956301,7498 "ci_low": 0.9922295363162157,7499 "ci_high": 1.0,7500 "n_items": 233,7501 "n_groups": 87502 },7503 "placeholders_exact": {7504 "mean": 1.0,7505 "ci_low": 1.0,7506 "ci_high": 1.0,7507 "n_items": 233,7508 "n_groups": 87509 }7510 },7511 "social_sciences": {7512 "n": 299,7513 "chrf": {7514 "mean": 59.87470393899909,7515 "ci_low": 57.19439996277057,7516 "ci_high": 62.20516416154515,7517 "n_items": 299,7518 "n_groups": 217519 },7520 "edit_sim": {7521 "mean": 0.6282461864008756,7522 "ci_low": 0.6036224869945032,7523 "ci_high": 0.6502078969530244,7524 "n_items": 299,7525 "n_groups": 217526 },7527 "rougeL": {7528 "mean": 0.6301159952191256,7529 "ci_low": 0.6015257100849709,7530 "ci_high": 0.6559520755254901,7531 "n_items": 299,7532 "n_groups": 217533 },7534 "exact_match": {7535 "mean": 0.0,7536 "ci_low": 0.0,7537 "ci_high": 0.0,7538 "n_items": 299,7539 "n_groups": 217540 },7541 "number_recall": {7542 "mean": 1.0,7543 "ci_low": 1.0,7544 "ci_high": 1.0,7545 "n_items": 299,7546 "n_groups": 217547 },7548 "placeholders_exact": {7549 "mean": 1.0,7550 "ci_low": 1.0,7551 "ci_high": 1.0,7552 "n_items": 299,7553 "n_groups": 217554 }7555 }7556 },7557 "by_era": {7558 "1900-1949": {7559 "n": 74,7560 "chrf": {7561 "mean": 65.03615433334691,7562 "ci_low": 63.14280374004683,7563 "ci_high": 72.01690693616446,7564 "n_items": 74,7565 "n_groups": 57566 },7567 "edit_sim": {7568 "mean": 0.678088391125824,7569 "ci_low": 0.6312103666172884,7570 "ci_high": 0.7103369148342459,7571 "n_items": 74,7572 "n_groups": 57573 },7574 "rougeL": {7575 "mean": 0.6689614259401482,7576 "ci_low": 0.6089055922859266,7577 "ci_high": 0.6916722318640219,7578 "n_items": 74,7579 "n_groups": 57580 },7581 "exact_match": {7582 "mean": 0.0,7583 "ci_low": 0.0,7584 "ci_high": 0.0,7585 "n_items": 74,7586 "n_groups": 57587 },7588 "number_recall": {7589 "mean": 0.9945945945945945,7590 "ci_low": 0.9600000000000001,7591 "ci_high": 1.0,7592 "n_items": 74,7593 "n_groups": 57594 },7595 "placeholders_exact": {7596 "mean": 1.0,7597 "ci_low": 1.0,7598 "ci_high": 1.0,7599 "n_items": 74,7600 "n_groups": 57601 }7602 },7603 "2010-2017": {7604 "n": 527,7605 "chrf": {7606 "mean": 70.53376121694359,7607 "ci_low": 67.00781117653347,7608 "ci_high": 73.0408490703521,7609 "n_items": 527,7610 "n_groups": 47611 },7612 "edit_sim": {7613 "mean": 0.6959478678606281,7614 "ci_low": 0.6627758897626971,7615 "ci_high": 0.7203530747799866,7616 "n_items": 527,7617 "n_groups": 47618 },7619 "rougeL": {7620 "mean": 0.6991775736669644,7621 "ci_low": 0.6628615482630081,7622 "ci_high": 0.7279552999170918,7623 "n_items": 527,7624 "n_groups": 47625 },7626 "exact_match": {7627 "mean": 0.0,7628 "ci_low": 0.0,7629 "ci_high": 0.0,7630 "n_items": 527,7631 "n_groups": 47632 },7633 "number_recall": {7634 "mean": 0.9714421252371918,7635 "ci_low": 0.9370967741935484,7636 "ci_high": 0.989247311827957,7637 "n_items": 527,7638 "n_groups": 47639 },7640 "placeholders_exact": {7641 "mean": 0.9962049335863378,7642 "ci_low": 0.9870967741935484,7643 "ci_high": 1.0,7644 "n_items": 527,7645 "n_groups": 47646 }7647 },7648 "pre1900": {7649 "n": 1973,7650 "chrf": {7651 "mean": 61.509466145176255,7652 "ci_low": 60.17980205828687,7653 "ci_high": 62.703892030470946,7654 "n_items": 1973,7655 "n_groups": 837656 },7657 "edit_sim": {7658 "mean": 0.628585676926691,7659 "ci_low": 0.616735894893071,7660 "ci_high": 0.6401154751976299,7661 "n_items": 1973,7662 "n_groups": 837663 },7664 "rougeL": {7665 "mean": 0.6340095939551422,7666 "ci_low": 0.6209597560111526,7667 "ci_high": 0.6460661958609429,7668 "n_items": 1973,7669 "n_groups": 837670 },7671 "exact_match": {7672 "mean": 0.0,7673 "ci_low": 0.0,7674 "ci_high": 0.0,7675 "n_items": 1973,7676 "n_groups": 837677 },7678 "number_recall": {7679 "mean": 0.9983152976437315,7680 "ci_low": 0.9967919257968878,7681 "ci_high": 0.9994211687108787,7682 "n_items": 1973,7683 "n_groups": 837684 },7685 "placeholders_exact": {7686 "mean": 1.0,7687 "ci_low": 1.0,7688 "ci_high": 1.0,7689 "n_items": 1973,7690 "n_groups": 837691 }7692 }7693 },7694 "by_role": {7695 "abstract": {7696 "n": 36,7697 "chrf": {7698 "mean": 67.59324308610759,7699 "ci_low": 63.252220800876024,7700 "ci_high": 71.81271128799132,7701 "n_items": 36,7702 "n_groups": 67703 },7704 "edit_sim": {7705 "mean": 0.6651479317154756,7706 "ci_low": 0.6139351885262444,7707 "ci_high": 0.7157176679062643,7708 "n_items": 36,7709 "n_groups": 67710 },7711 "rougeL": {7712 "mean": 0.6395186154602757,7713 "ci_low": 0.5882371662924064,7714 "ci_high": 0.6870520206848109,7715 "n_items": 36,7716 "n_groups": 67717 },7718 "exact_match": {7719 "mean": 0.0,7720 "ci_low": 0.0,7721 "ci_high": 0.0,7722 "n_items": 36,7723 "n_groups": 67724 },7725 "number_recall": {7726 "mean": 0.9888888888888889,7727 "ci_low": 0.9666666666666666,7728 "ci_high": 1.0,7729 "n_items": 36,7730 "n_groups": 67731 },7732 "placeholders_exact": {7733 "mean": 1.0,7734 "ci_low": 1.0,7735 "ci_high": 1.0,7736 "n_items": 36,7737 "n_groups": 67738 }7739 },7740 "chapter": {7741 "n": 819,7742 "chrf": {7743 "mean": 62.06898754322154,7744 "ci_low": 60.758498129124675,7745 "ci_high": 63.37450309481725,7746 "n_items": 819,7747 "n_groups": 527748 },7749 "edit_sim": {7750 "mean": 0.6321952614749002,7751 "ci_low": 0.6180364015651421,7752 "ci_high": 0.6459681311356965,7753 "n_items": 819,7754 "n_groups": 527755 },7756 "rougeL": {7757 "mean": 0.6393293026555399,7758 "ci_low": 0.6241356413570728,7759 "ci_high": 0.6533954233897982,7760 "n_items": 819,7761 "n_groups": 527762 },7763 "exact_match": {7764 "mean": 0.0,7765 "ci_low": 0.0,7766 "ci_high": 0.0,7767 "n_items": 819,7768 "n_groups": 527769 },7770 "number_recall": {7771 "mean": 0.9972444222444222,7772 "ci_low": 0.9937933621482551,7773 "ci_high": 0.9997227395812693,7774 "n_items": 819,7775 "n_groups": 527776 },7777 "placeholders_exact": {7778 "mean": 1.0,7779 "ci_low": 1.0,7780 "ci_high": 1.0,7781 "n_items": 819,7782 "n_groups": 527783 }7784 },7785 "conclusion": {7786 "n": 104,7787 "chrf": {7788 "mean": 69.57681438152213,7789 "ci_low": 62.77894911344651,7790 "ci_high": 73.63759810266731,7791 "n_items": 104,7792 "n_groups": 37793 },7794 "edit_sim": {7795 "mean": 0.6799343395648874,7796 "ci_low": 0.6111539660323061,7797 "ci_high": 0.7187346003755369,7798 "n_items": 104,7799 "n_groups": 37800 },7801 "rougeL": {7802 "mean": 0.6781895016698951,7803 "ci_low": 0.6045963678766959,7804 "ci_high": 0.7280525083921168,7805 "n_items": 104,7806 "n_groups": 37807 },7808 "exact_match": {7809 "mean": 0.0,7810 "ci_low": 0.0,7811 "ci_high": 0.0,7812 "n_items": 104,7813 "n_groups": 37814 },7815 "number_recall": {7816 "mean": 0.9903846153846154,7817 "ci_low": 0.9722222222222222,7818 "ci_high": 1.0,7819 "n_items": 104,7820 "n_groups": 37821 },7822 "placeholders_exact": {7823 "mean": 1.0,7824 "ci_low": 1.0,7825 "ci_high": 1.0,7826 "n_items": 104,7827 "n_groups": 37828 }7829 },7830 "data": {7831 "n": 11,7832 "chrf": {7833 "mean": 77.09969377157732,7834 "ci_low": 77.09969377157732,7835 "ci_high": 77.09969377157732,7836 "n_items": 11,7837 "n_groups": 17838 },7839 "edit_sim": {7840 "mean": 0.7799724663148967,7841 "ci_low": 0.7799724663148967,7842 "ci_high": 0.7799724663148967,7843 "n_items": 11,7844 "n_groups": 17845 },7846 "rougeL": {7847 "mean": 0.79141479233625,7848 "ci_low": 0.79141479233625,7849 "ci_high": 0.79141479233625,7850 "n_items": 11,7851 "n_groups": 17852 },7853 "exact_match": {7854 "mean": 0.0,7855 "ci_low": 0.0,7856 "ci_high": 0.0,7857 "n_items": 11,7858 "n_groups": 17859 },7860 "number_recall": {7861 "mean": 1.0,7862 "ci_low": 1.0,7863 "ci_high": 1.0,7864 "n_items": 11,7865 "n_groups": 17866 },7867 "placeholders_exact": {7868 "mean": 1.0,7869 "ci_low": 1.0,7870 "ci_high": 1.0,7871 "n_items": 11,7872 "n_groups": 17873 }7874 },7875 "introduction": {7876 "n": 574,7877 "chrf": {7878 "mean": 62.35624822483756,7879 "ci_low": 59.52915583011426,7880 "ci_high": 64.39744370093071,7881 "n_items": 574,7882 "n_groups": 237883 },7884 "edit_sim": {7885 "mean": 0.6379360404251818,7886 "ci_low": 0.6099203135973673,7887 "ci_high": 0.6583651978869548,7888 "n_items": 574,7889 "n_groups": 237890 },7891 "rougeL": {7892 "mean": 0.6419655850272443,7893 "ci_low": 0.6145182152508988,7894 "ci_high": 0.6622303978498204,7895 "n_items": 574,7896 "n_groups": 237897 },7898 "exact_match": {7899 "mean": 0.0,7900 "ci_low": 0.0,7901 "ci_high": 0.0,7902 "n_items": 574,7903 "n_groups": 237904 },7905 "number_recall": {7906 "mean": 0.9987216616136477,7907 "ci_low": 0.9973118279569892,7908 "ci_high": 1.0,7909 "n_items": 574,7910 "n_groups": 237911 },7912 "placeholders_exact": {7913 "mean": 1.0,7914 "ci_low": 1.0,7915 "ci_high": 1.0,7916 "n_items": 574,7917 "n_groups": 237918 }7919 },7920 "methods": {7921 "n": 93,7922 "chrf": {7923 "mean": 70.37827471491232,7924 "ci_low": 67.27158636672998,7925 "ci_high": 77.19947855065455,7926 "n_items": 93,7927 "n_groups": 37928 },7929 "edit_sim": {7930 "mean": 0.6938155436102929,7931 "ci_low": 0.6694930644850481,7932 "ci_high": 0.7916412622610158,7933 "n_items": 93,7934 "n_groups": 37935 },7936 "rougeL": {7937 "mean": 0.7127963083625816,7938 "ci_low": 0.6787461172093808,7939 "ci_high": 0.7981148546816468,7940 "n_items": 93,7941 "n_groups": 37942 },7943 "exact_match": {7944 "mean": 0.0,7945 "ci_low": 0.0,7946 "ci_high": 0.0,7947 "n_items": 93,7948 "n_groups": 37949 },7950 "number_recall": {7951 "mean": 0.9537634408602151,7952 "ci_low": 0.9375,7953 "ci_high": 0.9583333333333334,7954 "n_items": 93,7955 "n_groups": 37956 },7957 "placeholders_exact": {7958 "mean": 1.0,7959 "ci_low": 1.0,7960 "ci_high": 1.0,7961 "n_items": 93,7962 "n_groups": 37963 }7964 },7965 "other": {7966 "n": 163,7967 "chrf": {7968 "mean": 65.16625505974419,7969 "ci_low": 59.465643766200444,7970 "ci_high": 70.14336399450107,7971 "n_items": 163,7972 "n_groups": 97973 },7974 "edit_sim": {7975 "mean": 0.671564624314714,7976 "ci_low": 0.6418223767207075,7977 "ci_high": 0.7002441219511767,7978 "n_items": 163,7979 "n_groups": 97980 },7981 "rougeL": {7982 "mean": 0.6750839333006512,7983 "ci_low": 0.6440263181232005,7984 "ci_high": 0.7044686935638655,7985 "n_items": 163,7986 "n_groups": 97987 },7988 "exact_match": {7989 "mean": 0.0,7990 "ci_low": 0.0,7991 "ci_high": 0.0,7992 "n_items": 163,7993 "n_groups": 97994 },7995 "number_recall": {7996 "mean": 0.9984662576687117,7997 "ci_low": 0.9946789377009031,7998 "ci_high": 1.0,7999 "n_items": 163,8000 "n_groups": 98001 },8002 "placeholders_exact": {8003 "mean": 1.0,8004 "ci_low": 1.0,8005 "ci_high": 1.0,8006 "n_items": 163,8007 "n_groups": 98008 }8009 },8010 "preface": {8011 "n": 562,8012 "chrf": {8013 "mean": 60.4727994230929,8014 "ci_low": 58.60401543476522,8015 "ci_high": 62.407147066959695,8016 "n_items": 562,8017 "n_groups": 488018 },8019 "edit_sim": {8020 "mean": 0.6179938674943566,8021 "ci_low": 0.6000393171801032,8022 "ci_high": 0.6374403982184944,8023 "n_items": 562,8024 "n_groups": 488025 },8026 "rougeL": {8027 "mean": 0.6215579371539957,8028 "ci_low": 0.6014451395197596,8029 "ci_high": 0.6429080517019662,8030 "n_items": 562,8031 "n_groups": 488032 },8033 "exact_match": {8034 "mean": 0.0,8035 "ci_low": 0.0,8036 "ci_high": 0.0,8037 "n_items": 562,8038 "n_groups": 488039 },8040 "number_recall": {8041 "mean": 0.9994068801897985,8042 "ci_low": 0.998054284715467,8043 "ci_high": 1.0,8044 "n_items": 562,8045 "n_groups": 488046 },8047 "placeholders_exact": {8048 "mean": 1.0,8049 "ci_low": 1.0,8050 "ci_high": 1.0,8051 "n_items": 562,8052 "n_groups": 488053 }8054 },8055 "related_work": {8056 "n": 18,8057 "chrf": {8058 "mean": 71.70970877062143,8059 "ci_low": 71.70970877062143,8060 "ci_high": 71.70970877062143,8061 "n_items": 18,8062 "n_groups": 18063 },8064 "edit_sim": {8065 "mean": 0.7079206629982308,8066 "ci_low": 0.7079206629982308,8067 "ci_high": 0.7079206629982308,8068 "n_items": 18,8069 "n_groups": 18070 },8071 "rougeL": {8072 "mean": 0.6980737494755481,8073 "ci_low": 0.6980737494755481,8074 "ci_high": 0.6980737494755481,8075 "n_items": 18,8076 "n_groups": 18077 },8078 "exact_match": {8079 "mean": 0.0,8080 "ci_low": 0.0,8081 "ci_high": 0.0,8082 "n_items": 18,8083 "n_groups": 18084 },8085 "number_recall": {8086 "mean": 1.0,8087 "ci_low": 1.0,8088 "ci_high": 1.0,8089 "n_items": 18,8090 "n_groups": 18091 },8092 "placeholders_exact": {8093 "mean": 1.0,8094 "ci_low": 1.0,8095 "ci_high": 1.0,8096 "n_items": 18,8097 "n_groups": 18098 }8099 },8100 "results": {8101 "n": 158,8102 "chrf": {8103 "mean": 70.1741052708718,8104 "ci_low": 68.13704452701577,8105 "ci_high": 73.4326956533371,8106 "n_items": 158,8107 "n_groups": 38108 },8109 "edit_sim": {8110 "mean": 0.6906758831126678,8111 "ci_low": 0.6699305534604509,8112 "ci_high": 0.7113101816259182,8113 "n_items": 158,8114 "n_groups": 38115 },8116 "rougeL": {8117 "mean": 0.693990283383651,8118 "ci_low": 0.6827325568228008,8119 "ci_high": 0.7137828780239,8120 "n_items": 158,8121 "n_groups": 38122 },8123 "exact_match": {8124 "mean": 0.0,8125 "ci_low": 0.0,8126 "ci_high": 0.0,8127 "n_items": 158,8128 "n_groups": 38129 },8130 "number_recall": {8131 "mean": 0.939873417721519,8132 "ci_low": 0.8831168831168831,8133 "ci_high": 1.0,8134 "n_items": 158,8135 "n_groups": 38136 },8137 "placeholders_exact": {8138 "mean": 0.9873417721518988,8139 "ci_low": 0.974025974025974,8140 "ci_high": 1.0,8141 "n_items": 158,8142 "n_groups": 38143 }8144 },8145 "theory": {8146 "n": 36,8147 "chrf": {8148 "mean": 74.06775387601907,8149 "ci_low": 67.57212276815419,8150 "ci_high": 75.36688009759204,8151 "n_items": 36,8152 "n_groups": 28153 },8154 "edit_sim": {8155 "mean": 0.7441503674334061,8156 "ci_low": 0.6974340283662513,8157 "ci_high": 0.7534936352468369,8158 "n_items": 36,8159 "n_groups": 28160 },8161 "rougeL": {8162 "mean": 0.7403244232679197,8163 "ci_low": 0.6701351535206679,8164 "ci_high": 0.75436227721737,8165 "n_items": 36,8166 "n_groups": 28167 },8168 "exact_match": {8169 "mean": 0.0,8170 "ci_low": 0.0,8171 "ci_high": 0.0,8172 "n_items": 36,8173 "n_groups": 28174 },8175 "number_recall": {8176 "mean": 1.0,8177 "ci_low": 1.0,8178 "ci_high": 1.0,8179 "n_items": 36,8180 "n_groups": 28181 },8182 "placeholders_exact": {8183 "mean": 1.0,8184 "ci_low": 1.0,8185 "ci_high": 1.0,8186 "n_items": 36,8187 "n_groups": 28188 }8189 }8190 }8191 },8192 "htr-m2-tiny": {8193 "overall": {8194 "n": 2574,8195 "chrf": {8196 "mean": 63.26414354952189,8197 "ci_low": 61.137791396276945,8198 "ci_high": 65.1155782591761,8199 "n_items": 2574,8200 "n_groups": 928201 },8202 "edit_sim": {8203 "mean": 0.6414941662896875,8204 "ci_low": 0.623971033692917,8205 "ci_high": 0.6573479637094873,8206 "n_items": 2574,8207 "n_groups": 928208 },8209 "rougeL": {8210 "mean": 0.6466359735306143,8211 "ci_low": 0.6288088648814474,8212 "ci_high": 0.6626223842460168,8213 "n_items": 2574,8214 "n_groups": 928215 },8216 "exact_match": {8217 "mean": 0.0,8218 "ci_low": 0.0,8219 "ci_high": 0.0,8220 "n_items": 2574,8221 "n_groups": 928222 },8223 "number_recall": {8224 "mean": 0.9922570695297968,8225 "ci_low": 0.985398515859105,8226 "ci_high": 0.9975693441208574,8227 "n_items": 2574,8228 "n_groups": 928229 },8230 "placeholders_exact": {8231 "mean": 0.9968919968919969,8232 "ci_low": 0.9900122764079261,8233 "ci_high": 1.0,8234 "n_items": 2574,8235 "n_groups": 928236 }8237 },8238 "by_variant": {8239 "A": {8240 "n": 436,8241 "chrf": {8242 "mean": 62.47972229317754,8243 "ci_low": 60.21414714719397,8244 "ci_high": 64.36633624181353,8245 "n_items": 436,8246 "n_groups": 918247 },8248 "edit_sim": {8249 "mean": 0.6323395886774895,8250 "ci_low": 0.6126486336939293,8251 "ci_high": 0.6482732094976265,8252 "n_items": 436,8253 "n_groups": 918254 },8255 "rougeL": {8256 "mean": 0.6361411946110109,8257 "ci_low": 0.6155362778857763,8258 "ci_high": 0.6522234188764169,8259 "n_items": 436,8260 "n_groups": 918261 },8262 "exact_match": {8263 "mean": 0.0,8264 "ci_low": 0.0,8265 "ci_high": 0.0,8266 "n_items": 436,8267 "n_groups": 918268 },8269 "number_recall": {8270 "mean": 0.9893539755351682,8271 "ci_low": 0.980518448000091,8272 "ci_high": 0.9973138739177084,8273 "n_items": 436,8274 "n_groups": 918275 },8276 "placeholders_exact": {8277 "mean": 0.9931192660550459,8278 "ci_low": 0.979115895705223,8279 "ci_high": 1.0,8280 "n_items": 436,8281 "n_groups": 918282 }8283 },8284 "B": {8285 "n": 416,8286 "chrf": {8287 "mean": 68.3383348813475,8288 "ci_low": 65.84831356716877,8289 "ci_high": 70.61328066023992,8290 "n_items": 416,8291 "n_groups": 908292 },8293 "edit_sim": {8294 "mean": 0.6958625807607809,8295 "ci_low": 0.6729355751501201,8296 "ci_high": 0.7173211757947986,8297 "n_items": 416,8298 "n_groups": 908299 },8300 "rougeL": {8301 "mean": 0.7024127780129334,8302 "ci_low": 0.6789111139695024,8303 "ci_high": 0.7235222144302356,8304 "n_items": 416,8305 "n_groups": 908306 },8307 "exact_match": {8308 "mean": 0.0,8309 "ci_low": 0.0,8310 "ci_high": 0.0,8311 "n_items": 416,8312 "n_groups": 908313 },8314 "number_recall": {8315 "mean": 0.9931909236596735,8316 "ci_low": 0.986660167638775,8317 "ci_high": 0.999350733246082,8318 "n_items": 416,8319 "n_groups": 908320 },8321 "placeholders_exact": {8322 "mean": 0.9975961538461539,8323 "ci_low": 0.992571931065287,8324 "ci_high": 1.0,8325 "n_items": 416,8326 "n_groups": 908327 }8328 },8329 "C": {8330 "n": 438,8331 "chrf": {8332 "mean": 68.18586084215974,8333 "ci_low": 66.30880663889334,8334 "ci_high": 70.10222408599947,8335 "n_items": 438,8336 "n_groups": 918337 },8338 "edit_sim": {8339 "mean": 0.7038144768306378,8340 "ci_low": 0.6863292597540323,8341 "ci_high": 0.7208083854159155,8342 "n_items": 438,8343 "n_groups": 918344 },8345 "rougeL": {8346 "mean": 0.720193496776499,8347 "ci_low": 0.7023717975210133,8348 "ci_high": 0.7378738226211826,8349 "n_items": 438,8350 "n_groups": 918351 },8352 "exact_match": {8353 "mean": 0.0,8354 "ci_low": 0.0,8355 "ci_high": 0.0,8356 "n_items": 438,8357 "n_groups": 918358 },8359 "number_recall": {8360 "mean": 0.9922979797979798,8361 "ci_low": 0.98365961896519,8362 "ci_high": 0.9985388471177944,8363 "n_items": 438,8364 "n_groups": 918365 },8366 "placeholders_exact": {8367 "mean": 1.0,8368 "ci_low": 1.0,8369 "ci_high": 1.0,8370 "n_items": 438,8371 "n_groups": 918372 }8373 },8374 "D": {8375 "n": 431,8376 "chrf": {8377 "mean": 62.67324141563221,8378 "ci_low": 60.2068365206638,8379 "ci_high": 64.74215577051537,8380 "n_items": 431,8381 "n_groups": 908382 },8383 "edit_sim": {8384 "mean": 0.6406395667882344,8385 "ci_low": 0.6193378633418776,8386 "ci_high": 0.6577214584753257,8387 "n_items": 431,8388 "n_groups": 908389 },8390 "rougeL": {8391 "mean": 0.6428664196398142,8392 "ci_low": 0.6212860918858538,8393 "ci_high": 0.6605746467828606,8394 "n_items": 431,8395 "n_groups": 908396 },8397 "exact_match": {8398 "mean": 0.0,8399 "ci_low": 0.0,8400 "ci_high": 0.0,8401 "n_items": 431,8402 "n_groups": 908403 },8404 "number_recall": {8405 "mean": 0.9925947409126064,8406 "ci_low": 0.983819540125695,8407 "ci_high": 0.9983992109774945,8408 "n_items": 431,8409 "n_groups": 908410 },8411 "placeholders_exact": {8412 "mean": 0.9953596287703016,8413 "ci_low": 0.9844352923341251,8414 "ci_high": 1.0,8415 "n_items": 431,8416 "n_groups": 908417 }8418 },8419 "E": {8420 "n": 853,8421 "chrf": {8422 "mean": 58.961811450175794,8423 "ci_low": 56.847981660398005,8424 "ci_high": 60.860191572944935,8425 "n_items": 853,8426 "n_groups": 918427 },8428 "edit_sim": {8429 "mean": 0.5880899128162215,8430 "ci_low": 0.5716773026576323,8431 "ci_high": 0.6038674342643181,8432 "n_items": 853,8433 "n_groups": 918434 },8435 "rougeL": {8436 "mean": 0.5889326388172962,8437 "ci_low": 0.5714889208511811,8438 "ci_high": 0.6055478164064673,8439 "n_items": 853,8440 "n_groups": 918441 },8442 "exact_match": {8443 "mean": 0.0,8444 "ci_low": 0.0,8445 "ci_high": 0.0,8446 "n_items": 853,8447 "n_groups": 918448 },8449 "number_recall": {8450 "mean": 0.9930938932111264,8451 "ci_low": 0.9878236768214091,8452 "ci_high": 0.9980595441101731,8453 "n_items": 853,8454 "n_groups": 918455 },8456 "placeholders_exact": {8457 "mean": 0.9976553341148886,8458 "ci_low": 0.9925093632958801,8459 "ci_high": 1.0,8460 "n_items": 853,8461 "n_groups": 918462 }8463 }8464 },8465 "by_discipline": {8466 "biomedicine": {8467 "n": 438,8468 "chrf": {8469 "mean": 63.72935849680238,8470 "ci_low": 57.54952496020569,8471 "ci_high": 68.51060417256383,8472 "n_items": 438,8473 "n_groups": 228474 },8475 "edit_sim": {8476 "mean": 0.642187649122046,8477 "ci_low": 0.5894817831760663,8478 "ci_high": 0.683124701437974,8479 "n_items": 438,8480 "n_groups": 228481 },8482 "rougeL": {8483 "mean": 0.6407976760080524,8484 "ci_low": 0.5848823641213899,8485 "ci_high": 0.6815908381947583,8486 "n_items": 438,8487 "n_groups": 228488 },8489 "exact_match": {8490 "mean": 0.0,8491 "ci_low": 0.0,8492 "ci_high": 0.0,8493 "n_items": 438,8494 "n_groups": 228495 },8496 "number_recall": {8497 "mean": 0.9796993911719939,8498 "ci_low": 0.9578876373896666,8499 "ci_high": 1.0,8500 "n_items": 438,8501 "n_groups": 228502 },8503 "placeholders_exact": {8504 "mean": 0.9817351598173516,8505 "ci_low": 0.9604612850082372,8506 "ci_high": 1.0,8507 "n_items": 438,8508 "n_groups": 228509 }8510 },8511 "chemistry": {8512 "n": 183,8513 "chrf": {8514 "mean": 64.96192697497341,8515 "ci_low": 64.96192697497341,8516 "ci_high": 64.96192697497341,8517 "n_items": 183,8518 "n_groups": 18519 },8520 "edit_sim": {8521 "mean": 0.6494591020499584,8522 "ci_low": 0.6494591020499584,8523 "ci_high": 0.6494591020499584,8524 "n_items": 183,8525 "n_groups": 18526 },8527 "rougeL": {8528 "mean": 0.6593738415065374,8529 "ci_low": 0.6593738415065374,8530 "ci_high": 0.6593738415065374,8531 "n_items": 183,8532 "n_groups": 18533 },8534 "exact_match": {8535 "mean": 0.0,8536 "ci_low": 0.0,8537 "ci_high": 0.0,8538 "n_items": 183,8539 "n_groups": 18540 },8541 "number_recall": {8542 "mean": 1.0,8543 "ci_low": 1.0,8544 "ci_high": 1.0,8545 "n_items": 183,8546 "n_groups": 18547 },8548 "placeholders_exact": {8549 "mean": 1.0,8550 "ci_low": 1.0,8551 "ci_high": 1.0,8552 "n_items": 183,8553 "n_groups": 18554 }8555 },8556 "earth_sciences": {8557 "n": 101,8558 "chrf": {8559 "mean": 60.9323963397525,8560 "ci_low": 60.9323963397525,8561 "ci_high": 60.9323963397525,8562 "n_items": 101,8563 "n_groups": 18564 },8565 "edit_sim": {8566 "mean": 0.6025063535950995,8567 "ci_low": 0.6025063535950995,8568 "ci_high": 0.6025063535950995,8569 "n_items": 101,8570 "n_groups": 18571 },8572 "rougeL": {8573 "mean": 0.6190688951901131,8574 "ci_low": 0.6190688951901131,8575 "ci_high": 0.6190688951901131,8576 "n_items": 101,8577 "n_groups": 18578 },8579 "exact_match": {8580 "mean": 0.0,8581 "ci_low": 0.0,8582 "ci_high": 0.0,8583 "n_items": 101,8584 "n_groups": 18585 },8586 "number_recall": {8587 "mean": 0.9767326732673268,8588 "ci_low": 0.9767326732673268,8589 "ci_high": 0.9767326732673268,8590 "n_items": 101,8591 "n_groups": 18592 },8593 "placeholders_exact": {8594 "mean": 1.0,8595 "ci_low": 1.0,8596 "ci_high": 1.0,8597 "n_items": 101,8598 "n_groups": 18599 }8600 },8601 "economics": {8602 "n": 569,8603 "chrf": {8604 "mean": 67.98546576294329,8605 "ci_low": 62.88241359604631,8606 "ci_high": 71.30297269741202,8607 "n_items": 569,8608 "n_groups": 88609 },8610 "edit_sim": {8611 "mean": 0.6772115416807503,8612 "ci_low": 0.6364297547951693,8613 "ci_high": 0.7070129018657827,8614 "n_items": 569,8615 "n_groups": 88616 },8617 "rougeL": {8618 "mean": 0.6825294340688587,8619 "ci_low": 0.6398799677037118,8620 "ci_high": 0.7153360455613336,8621 "n_items": 569,8622 "n_groups": 88623 },8624 "exact_match": {8625 "mean": 0.0,8626 "ci_low": 0.0,8627 "ci_high": 0.0,8628 "n_items": 569,8629 "n_groups": 88630 },8631 "number_recall": {8632 "mean": 0.9887548596687438,8633 "ci_low": 0.9857058196041246,8634 "ci_high": 0.9967948717948717,8635 "n_items": 569,8636 "n_groups": 88637 },8638 "placeholders_exact": {8639 "mean": 1.0,8640 "ci_low": 1.0,8641 "ci_high": 1.0,8642 "n_items": 569,8643 "n_groups": 88644 }8645 },8646 "engineering": {8647 "n": 167,8648 "chrf": {8649 "mean": 59.899750195643826,8650 "ci_low": 56.61100870337881,8651 "ci_high": 61.367973334253016,8652 "n_items": 167,8653 "n_groups": 88654 },8655 "edit_sim": {8656 "mean": 0.6020452494195764,8657 "ci_low": 0.5796249604958932,8658 "ci_high": 0.615752344803312,8659 "n_items": 167,8660 "n_groups": 88661 },8662 "rougeL": {8663 "mean": 0.6144274937237317,8664 "ci_low": 0.5777183298529035,8665 "ci_high": 0.6334184805231595,8666 "n_items": 167,8667 "n_groups": 88668 },8669 "exact_match": {8670 "mean": 0.0,8671 "ci_low": 0.0,8672 "ci_high": 0.0,8673 "n_items": 167,8674 "n_groups": 88675 },8676 "number_recall": {8677 "mean": 0.9916167664670659,8678 "ci_low": 0.9769230769230769,8679 "ci_high": 1.0,8680 "n_items": 167,8681 "n_groups": 88682 },8683 "placeholders_exact": {8684 "mean": 1.0,8685 "ci_low": 1.0,8686 "ci_high": 1.0,8687 "n_items": 167,8688 "n_groups": 88689 }8690 },8691 "finance": {8692 "n": 75,8693 "chrf": {8694 "mean": 57.83382001800459,8695 "ci_low": 57.69649454391633,8696 "ci_high": 58.432166726532046,8697 "n_items": 75,8698 "n_groups": 28699 },8700 "edit_sim": {8701 "mean": 0.58673794587566,8702 "ci_low": 0.5813147688004968,8703 "ci_high": 0.5879826094666811,8704 "n_items": 75,8705 "n_groups": 28706 },8707 "rougeL": {8708 "mean": 0.5896532282861885,8709 "ci_low": 0.5880505961669599,8710 "ci_high": 0.5900210454938805,8711 "n_items": 75,8712 "n_groups": 28713 },8714 "exact_match": {8715 "mean": 0.0,8716 "ci_low": 0.0,8717 "ci_high": 0.0,8718 "n_items": 75,8719 "n_groups": 28720 },8721 "number_recall": {8722 "mean": 1.0,8723 "ci_low": 1.0,8724 "ci_high": 1.0,8725 "n_items": 75,8726 "n_groups": 28727 },8728 "placeholders_exact": {8729 "mean": 1.0,8730 "ci_low": 1.0,8731 "ci_high": 1.0,8732 "n_items": 75,8733 "n_groups": 28734 }8735 },8736 "general_reference": {8737 "n": 256,8738 "chrf": {8739 "mean": 62.0853204785615,8740 "ci_low": 59.02644540961171,8741 "ci_high": 64.28721818071497,8742 "n_items": 256,8743 "n_groups": 128744 },8745 "edit_sim": {8746 "mean": 0.6429066022459656,8747 "ci_low": 0.6038329862323029,8748 "ci_high": 0.6665448046576117,8749 "n_items": 256,8750 "n_groups": 128751 },8752 "rougeL": {8753 "mean": 0.6467941531416914,8754 "ci_low": 0.601795634792169,8755 "ci_high": 0.6695567822325807,8756 "n_items": 256,8757 "n_groups": 128758 },8759 "exact_match": {8760 "mean": 0.0,8761 "ci_low": 0.0,8762 "ci_high": 0.0,8763 "n_items": 256,8764 "n_groups": 128765 },8766 "number_recall": {8767 "mean": 0.9977213541666666,8768 "ci_low": 0.9903301488643339,8769 "ci_high": 1.0,8770 "n_items": 256,8771 "n_groups": 128772 },8773 "placeholders_exact": {8774 "mean": 1.0,8775 "ci_low": 1.0,8776 "ci_high": 1.0,8777 "n_items": 256,8778 "n_groups": 128779 }8780 },8781 "humanities": {8782 "n": 253,8783 "chrf": {8784 "mean": 63.36406909970445,8785 "ci_low": 59.87410390616333,8786 "ci_high": 66.85563689845745,8787 "n_items": 253,8788 "n_groups": 98789 },8790 "edit_sim": {8791 "mean": 0.6545050192978246,8792 "ci_low": 0.6234996816838224,8793 "ci_high": 0.6982536365438113,8794 "n_items": 253,8795 "n_groups": 98796 },8797 "rougeL": {8798 "mean": 0.6602329305739684,8799 "ci_low": 0.6277818466332108,8800 "ci_high": 0.6997697281797103,8801 "n_items": 253,8802 "n_groups": 98803 },8804 "exact_match": {8805 "mean": 0.0,8806 "ci_low": 0.0,8807 "ci_high": 0.0,8808 "n_items": 253,8809 "n_groups": 98810 },8811 "number_recall": {8812 "mean": 1.0,8813 "ci_low": 1.0,8814 "ci_high": 1.0,8815 "n_items": 253,8816 "n_groups": 98817 },8818 "placeholders_exact": {8819 "mean": 1.0,8820 "ci_low": 1.0,8821 "ci_high": 1.0,8822 "n_items": 253,8823 "n_groups": 98824 }8825 },8826 "life_sciences": {8827 "n": 233,8828 "chrf": {8829 "mean": 60.258115060233195,8830 "ci_low": 57.715990554435734,8831 "ci_high": 63.24188187574218,8832 "n_items": 233,8833 "n_groups": 88834 },8835 "edit_sim": {8836 "mean": 0.6132962908240843,8837 "ci_low": 0.5913652935636223,8838 "ci_high": 0.6385474185799581,8839 "n_items": 233,8840 "n_groups": 88841 },8842 "rougeL": {8843 "mean": 0.6231715195934445,8844 "ci_low": 0.5978084191705759,8845 "ci_high": 0.6521850177937707,8846 "n_items": 233,8847 "n_groups": 88848 },8849 "exact_match": {8850 "mean": 0.0,8851 "ci_low": 0.0,8852 "ci_high": 0.0,8853 "n_items": 233,8854 "n_groups": 88855 },8856 "number_recall": {8857 "mean": 0.9986831837690207,8858 "ci_low": 0.9957183159293433,8859 "ci_high": 1.0,8860 "n_items": 233,8861 "n_groups": 88862 },8863 "placeholders_exact": {8864 "mean": 1.0,8865 "ci_low": 1.0,8866 "ci_high": 1.0,8867 "n_items": 233,8868 "n_groups": 88869 }8870 },8871 "social_sciences": {8872 "n": 299,8873 "chrf": {8874 "mean": 59.854932010788886,8875 "ci_low": 57.276361390669514,8876 "ci_high": 62.080601111016286,8877 "n_items": 299,8878 "n_groups": 218879 },8880 "edit_sim": {8881 "mean": 0.6263259889516146,8882 "ci_low": 0.6012759595423126,8883 "ci_high": 0.6492378029009662,8884 "n_items": 299,8885 "n_groups": 218886 },8887 "rougeL": {8888 "mean": 0.6273257929869864,8889 "ci_low": 0.5991038605399819,8890 "ci_high": 0.6535401731451662,8891 "n_items": 299,8892 "n_groups": 218893 },8894 "exact_match": {8895 "mean": 0.0,8896 "ci_low": 0.0,8897 "ci_high": 0.0,8898 "n_items": 299,8899 "n_groups": 218900 },8901 "number_recall": {8902 "mean": 1.0,8903 "ci_low": 1.0,8904 "ci_high": 1.0,8905 "n_items": 299,8906 "n_groups": 218907 },8908 "placeholders_exact": {8909 "mean": 1.0,8910 "ci_low": 1.0,8911 "ci_high": 1.0,8912 "n_items": 299,8913 "n_groups": 218914 }8915 }8916 },8917 "by_era": {8918 "1900-1949": {8919 "n": 74,8920 "chrf": {8921 "mean": 64.6655565330096,8922 "ci_low": 62.68877955423716,8923 "ci_high": 71.05477222672373,8924 "n_items": 74,8925 "n_groups": 58926 },8927 "edit_sim": {8928 "mean": 0.6726808715776328,8929 "ci_low": 0.6047959770481937,8930 "ci_high": 0.700693007279972,8931 "n_items": 74,8932 "n_groups": 58933 },8934 "rougeL": {8935 "mean": 0.6638757971014253,8936 "ci_low": 0.585037521310596,8937 "ci_high": 0.6918823077008783,8938 "n_items": 74,8939 "n_groups": 58940 },8941 "exact_match": {8942 "mean": 0.0,8943 "ci_low": 0.0,8944 "ci_high": 0.0,8945 "n_items": 74,8946 "n_groups": 58947 },8948 "number_recall": {8949 "mean": 0.991891891891892,8950 "ci_low": 0.9400000000000001,8951 "ci_high": 1.0,8952 "n_items": 74,8953 "n_groups": 58954 },8955 "placeholders_exact": {8956 "mean": 1.0,8957 "ci_low": 1.0,8958 "ci_high": 1.0,8959 "n_items": 74,8960 "n_groups": 58961 }8962 },8963 "2010-2017": {8964 "n": 527,8965 "chrf": {8966 "mean": 70.80907056701251,8967 "ci_low": 67.41200387192768,8968 "ci_high": 73.2245173404657,8969 "n_items": 527,8970 "n_groups": 48971 },8972 "edit_sim": {8973 "mean": 0.6994942767525347,8974 "ci_low": 0.6684702146765498,8975 "ci_high": 0.7217193706514118,8976 "n_items": 527,8977 "n_groups": 48978 },8979 "rougeL": {8980 "mean": 0.7027218926721085,8981 "ci_low": 0.6666501577695287,8982 "ci_high": 0.7312134049231594,8983 "n_items": 527,8984 "n_groups": 48985 },8986 "exact_match": {8987 "mean": 0.0,8988 "ci_low": 0.0,8989 "ci_high": 0.0,8990 "n_items": 527,8991 "n_groups": 48992 },8993 "number_recall": {8994 "mean": 0.9738643551262147,8995 "ci_low": 0.946505376344086,8996 "ci_high": 0.989247311827957,8997 "n_items": 527,8998 "n_groups": 48999 },9000 "placeholders_exact": {9001 "mean": 0.9848197343453511,9002 "ci_low": 0.9483870967741935,9003 "ci_high": 1.0,9004 "n_items": 527,9005 "n_groups": 49006 }9007 },9008 "pre1900": {9009 "n": 1973,9010 "chrf": {9011 "mean": 61.196286935737994,9012 "ci_low": 59.81733118864825,9013 "ci_high": 62.43980989391548,9014 "n_items": 1973,9015 "n_groups": 839016 },9017 "edit_sim": {9018 "mean": 0.6248322938085783,9019 "ci_low": 0.6126247124478185,9020 "ci_high": 0.6368571880543571,9021 "n_items": 1973,9022 "n_groups": 839023 },9024 "rougeL": {9025 "mean": 0.6310084893279749,9026 "ci_low": 0.6173465554854922,9027 "ci_high": 0.6435567630677573,9028 "n_items": 1973,9029 "n_groups": 839030 },9031 "exact_match": {9032 "mean": 0.0,9033 "ci_low": 0.0,9034 "ci_high": 0.0,9035 "n_items": 1973,9036 "n_groups": 839037 },9038 "number_recall": {9039 "mean": 0.9971835690918307,9040 "ci_low": 0.9944903464370843,9041 "ci_high": 0.999353685219341,9042 "n_items": 1973,9043 "n_groups": 839044 },9045 "placeholders_exact": {9046 "mean": 1.0,9047 "ci_low": 1.0,9048 "ci_high": 1.0,9049 "n_items": 1973,9050 "n_groups": 839051 }9052 }9053 },9054 "by_role": {9055 "abstract": {9056 "n": 36,9057 "chrf": {9058 "mean": 66.93263327756095,9059 "ci_low": 62.35250661223294,9060 "ci_high": 71.54875574358573,9061 "n_items": 36,9062 "n_groups": 69063 },9064 "edit_sim": {9065 "mean": 0.6524512017399362,9066 "ci_low": 0.5968776415696233,9067 "ci_high": 0.7094304320544247,9068 "n_items": 36,9069 "n_groups": 69070 },9071 "rougeL": {9072 "mean": 0.6335076010161559,9073 "ci_low": 0.5743942658276981,9074 "ci_high": 0.6910765394705871,9075 "n_items": 36,9076 "n_groups": 69077 },9078 "exact_match": {9079 "mean": 0.0,9080 "ci_low": 0.0,9081 "ci_high": 0.0,9082 "n_items": 36,9083 "n_groups": 69084 },9085 "number_recall": {9086 "mean": 0.9833333333333333,9087 "ci_low": 0.9499999999999998,9088 "ci_high": 1.0,9089 "n_items": 36,9090 "n_groups": 69091 },9092 "placeholders_exact": {9093 "mean": 1.0,9094 "ci_low": 1.0,9095 "ci_high": 1.0,9096 "n_items": 36,9097 "n_groups": 69098 }9099 },9100 "chapter": {9101 "n": 819,9102 "chrf": {9103 "mean": 61.895236670373926,9104 "ci_low": 60.49368127393227,9105 "ci_high": 63.324648900348315,9106 "n_items": 819,9107 "n_groups": 529108 },9109 "edit_sim": {9110 "mean": 0.6300610868941908,9111 "ci_low": 0.6145151925916102,9112 "ci_high": 0.6452864862845872,9113 "n_items": 819,9114 "n_groups": 529115 },9116 "rougeL": {9117 "mean": 0.6386967311052667,9118 "ci_low": 0.6227129648482675,9119 "ci_high": 0.6537549930811875,9120 "n_items": 819,9121 "n_groups": 529122 },9123 "exact_match": {9124 "mean": 0.0,9125 "ci_low": 0.0,9126 "ci_high": 0.0,9127 "n_items": 819,9128 "n_groups": 529129 },9130 "number_recall": {9131 "mean": 0.9970002220002221,9132 "ci_low": 0.9931206848772822,9133 "ci_high": 1.0,9134 "n_items": 819,9135 "n_groups": 529136 },9137 "placeholders_exact": {9138 "mean": 1.0,9139 "ci_low": 1.0,9140 "ci_high": 1.0,9141 "n_items": 819,9142 "n_groups": 529143 }9144 },9145 "conclusion": {9146 "n": 104,9147 "chrf": {9148 "mean": 69.70426112837585,9149 "ci_low": 63.60429584320055,9150 "ci_high": 73.17300570489213,9151 "n_items": 104,9152 "n_groups": 39153 },9154 "edit_sim": {9155 "mean": 0.6867617885908387,9156 "ci_low": 0.6244910028905182,9157 "ci_high": 0.7403863036356828,9158 "n_items": 104,9159 "n_groups": 39160 },9161 "rougeL": {9162 "mean": 0.6818102290867102,9163 "ci_low": 0.6128431363813024,9164 "ci_high": 0.727013013067023,9165 "n_items": 104,9166 "n_groups": 39167 },9168 "exact_match": {9169 "mean": 0.0,9170 "ci_low": 0.0,9171 "ci_high": 0.0,9172 "n_items": 104,9173 "n_groups": 39174 },9175 "number_recall": {9176 "mean": 0.979020979020979,9177 "ci_low": 0.9444444444444444,9178 "ci_high": 1.0,9179 "n_items": 104,9180 "n_groups": 39181 },9182 "placeholders_exact": {9183 "mean": 1.0,9184 "ci_low": 1.0,9185 "ci_high": 1.0,9186 "n_items": 104,9187 "n_groups": 39188 }9189 },9190 "data": {9191 "n": 11,9192 "chrf": {9193 "mean": 77.74522684125047,9194 "ci_low": 77.74522684125047,9195 "ci_high": 77.74522684125047,9196 "n_items": 11,9197 "n_groups": 19198 },9199 "edit_sim": {9200 "mean": 0.7939418454100516,9201 "ci_low": 0.7939418454100516,9202 "ci_high": 0.7939418454100516,9203 "n_items": 11,9204 "n_groups": 19205 },9206 "rougeL": {9207 "mean": 0.8036388085261325,9208 "ci_low": 0.8036388085261325,9209 "ci_high": 0.8036388085261325,9210 "n_items": 11,9211 "n_groups": 19212 },9213 "exact_match": {9214 "mean": 0.0,9215 "ci_low": 0.0,9216 "ci_high": 0.0,9217 "n_items": 11,9218 "n_groups": 19219 },9220 "number_recall": {9221 "mean": 1.0,9222 "ci_low": 1.0,9223 "ci_high": 1.0,9224 "n_items": 11,9225 "n_groups": 19226 },9227 "placeholders_exact": {9228 "mean": 1.0,9229 "ci_low": 1.0,9230 "ci_high": 1.0,9231 "n_items": 11,9232 "n_groups": 19233 }9234 },9235 "introduction": {9236 "n": 574,9237 "chrf": {9238 "mean": 61.815415168892784,9239 "ci_low": 58.89443296275139,9240 "ci_high": 63.86458868754961,9241 "n_items": 574,9242 "n_groups": 239243 },9244 "edit_sim": {9245 "mean": 0.6325045742937231,9246 "ci_low": 0.6050276910472415,9247 "ci_high": 0.6533683307843472,9248 "n_items": 574,9249 "n_groups": 239250 },9251 "rougeL": {9252 "mean": 0.6368808328806156,9253 "ci_low": 0.6079137881957496,9254 "ci_high": 0.6579421791144934,9255 "n_items": 574,9256 "n_groups": 239257 },9258 "exact_match": {9259 "mean": 0.0,9260 "ci_low": 0.0,9261 "ci_high": 0.0,9262 "n_items": 574,9263 "n_groups": 239264 },9265 "number_recall": {9266 "mean": 0.9973577235772358,9267 "ci_low": 0.9929676438293681,9268 "ci_high": 1.0,9269 "n_items": 574,9270 "n_groups": 239271 },9272 "placeholders_exact": {9273 "mean": 1.0,9274 "ci_low": 1.0,9275 "ci_high": 1.0,9276 "n_items": 574,9277 "n_groups": 239278 }9279 },9280 "methods": {9281 "n": 93,9282 "chrf": {9283 "mean": 70.92057858162562,9284 "ci_low": 67.7064509776402,9285 "ci_high": 78.83059911971661,9286 "n_items": 93,9287 "n_groups": 39288 },9289 "edit_sim": {9290 "mean": 0.7011525980403723,9291 "ci_low": 0.6683644923395397,9292 "ci_high": 0.8044559379944496,9293 "n_items": 93,9294 "n_groups": 39295 },9296 "rougeL": {9297 "mean": 0.7200029465335324,9298 "ci_low": 0.6833286346630184,9299 "ci_high": 0.8157378626449988,9300 "n_items": 93,9301 "n_groups": 39302 },9303 "exact_match": {9304 "mean": 0.0,9305 "ci_low": 0.0,9306 "ci_high": 0.0,9307 "n_items": 93,9308 "n_groups": 39309 },9310 "number_recall": {9311 "mean": 0.9739247311827958,9312 "ci_low": 0.9722222222222222,9313 "ci_high": 0.984375,9314 "n_items": 93,9315 "n_groups": 39316 },9317 "placeholders_exact": {9318 "mean": 1.0,9319 "ci_low": 1.0,9320 "ci_high": 1.0,9321 "n_items": 93,9322 "n_groups": 39323 }9324 },9325 "other": {9326 "n": 163,9327 "chrf": {9328 "mean": 65.36300273997068,9329 "ci_low": 59.961756069224776,9330 "ci_high": 70.4336547749406,9331 "n_items": 163,9332 "n_groups": 99333 },9334 "edit_sim": {9335 "mean": 0.6711105722616699,9336 "ci_low": 0.6364491802152159,9337 "ci_high": 0.7012214909436272,9338 "n_items": 163,9339 "n_groups": 99340 },9341 "rougeL": {9342 "mean": 0.676522805985836,9343 "ci_low": 0.6440439144614125,9344 "ci_high": 0.7077329541173705,9345 "n_items": 163,9346 "n_groups": 99347 },9348 "exact_match": {9349 "mean": 0.0,9350 "ci_low": 0.0,9351 "ci_high": 0.0,9352 "n_items": 163,9353 "n_groups": 99354 },9355 "number_recall": {9356 "mean": 0.9938650306748467,9357 "ci_low": 0.9801324503311258,9358 "ci_high": 1.0,9359 "n_items": 163,9360 "n_groups": 99361 },9362 "placeholders_exact": {9363 "mean": 1.0,9364 "ci_low": 1.0,9365 "ci_high": 1.0,9366 "n_items": 163,9367 "n_groups": 99368 }9369 },9370 "preface": {9371 "n": 562,9372 "chrf": {9373 "mean": 60.15543238227822,9374 "ci_low": 58.336755520271815,9375 "ci_high": 62.07965206797126,9376 "n_items": 562,9377 "n_groups": 489378 },9379 "edit_sim": {9380 "mean": 0.6140765364868503,9381 "ci_low": 0.5963469362448451,9382 "ci_high": 0.6336461395118055,9383 "n_items": 562,9384 "n_groups": 489385 },9386 "rougeL": {9387 "mean": 0.6173066178153546,9388 "ci_low": 0.5970779342070469,9389 "ci_high": 0.6389131945087815,9390 "n_items": 562,9391 "n_groups": 489392 },9393 "exact_match": {9394 "mean": 0.0,9395 "ci_low": 0.0,9396 "ci_high": 0.0,9397 "n_items": 562,9398 "n_groups": 489399 },9400 "number_recall": {9401 "mean": 0.9971826809015423,9402 "ci_low": 0.9924510046113306,9403 "ci_high": 1.0,9404 "n_items": 562,9405 "n_groups": 489406 },9407 "placeholders_exact": {9408 "mean": 1.0,9409 "ci_low": 1.0,9410 "ci_high": 1.0,9411 "n_items": 562,9412 "n_groups": 489413 }9414 },9415 "related_work": {9416 "n": 18,9417 "chrf": {9418 "mean": 71.69690813682953,9419 "ci_low": 71.69690813682953,9420 "ci_high": 71.69690813682953,9421 "n_items": 18,9422 "n_groups": 19423 },9424 "edit_sim": {9425 "mean": 0.7118388970700643,9426 "ci_low": 0.7118388970700643,9427 "ci_high": 0.7118388970700643,9428 "n_items": 18,9429 "n_groups": 19430 },9431 "rougeL": {9432 "mean": 0.6932655455303224,9433 "ci_low": 0.6932655455303224,9434 "ci_high": 0.6932655455303224,9435 "n_items": 18,9436 "n_groups": 19437 },9438 "exact_match": {9439 "mean": 0.0,9440 "ci_low": 0.0,9441 "ci_high": 0.0,9442 "n_items": 18,9443 "n_groups": 19444 },9445 "number_recall": {9446 "mean": 1.0,9447 "ci_low": 1.0,9448 "ci_high": 1.0,9449 "n_items": 18,9450 "n_groups": 19451 },9452 "placeholders_exact": {9453 "mean": 1.0,9454 "ci_low": 1.0,9455 "ci_high": 1.0,9456 "n_items": 18,9457 "n_groups": 19458 }9459 },9460 "results": {9461 "n": 158,9462 "chrf": {9463 "mean": 70.37609695110736,9464 "ci_low": 68.09707745481582,9465 "ci_high": 76.37227985497947,9466 "n_items": 158,9467 "n_groups": 39468 },9469 "edit_sim": {9470 "mean": 0.689732156210048,9471 "ci_low": 0.6724648269058207,9472 "ci_high": 0.7112033213494617,9473 "n_items": 158,9474 "n_groups": 39475 },9476 "rougeL": {9477 "mean": 0.6951855595724517,9478 "ci_low": 0.682093446965494,9479 "ci_high": 0.7499866215563317,9480 "n_items": 158,9481 "n_groups": 39482 },9483 "exact_match": {9484 "mean": 0.0,9485 "ci_low": 0.0,9486 "ci_high": 0.0,9487 "n_items": 158,9488 "n_groups": 39489 },9490 "number_recall": {9491 "mean": 0.9483122362869199,9492 "ci_low": 0.8939393939393939,9493 "ci_high": 1.0,9494 "n_items": 158,9495 "n_groups": 39496 },9497 "placeholders_exact": {9498 "mean": 0.9493670886075949,9499 "ci_low": 0.8961038961038961,9500 "ci_high": 1.0,9501 "n_items": 158,9502 "n_groups": 39503 }9504 },9505 "theory": {9506 "n": 36,9507 "chrf": {9508 "mean": 74.62608298908246,9509 "ci_low": 69.70684960455914,9510 "ci_high": 75.60992966598711,9511 "n_items": 36,9512 "n_groups": 29513 },9514 "edit_sim": {9515 "mean": 0.7495413725737552,9516 "ci_low": 0.7318943186299584,9517 "ci_high": 0.7530707833625147,9518 "n_items": 36,9519 "n_groups": 29520 },9521 "rougeL": {9522 "mean": 0.7429528282276485,9523 "ci_low": 0.6760553286310058,9524 "ci_high": 0.7563323281469769,9525 "n_items": 36,9526 "n_groups": 29527 },9528 "exact_match": {9529 "mean": 0.0,9530 "ci_low": 0.0,9531 "ci_high": 0.0,9532 "n_items": 36,9533 "n_groups": 29534 },9535 "number_recall": {9536 "mean": 1.0,9537 "ci_low": 1.0,9538 "ci_high": 1.0,9539 "n_items": 36,9540 "n_groups": 29541 },9542 "placeholders_exact": {9543 "mean": 1.0,9544 "ci_low": 1.0,9545 "ci_high": 1.0,9546 "n_items": 36,9547 "n_groups": 29548 }9549 }9550 }9551 },9552 "htr-m3light-tiny": {9553 "overall": {9554 "n": 2574,9555 "chrf": {9556 "mean": 63.142666960352784,9557 "ci_low": 61.076919995481155,9558 "ci_high": 64.95128618369624,9559 "n_items": 2574,9560 "n_groups": 929561 },9562 "edit_sim": {9563 "mean": 0.6411575210587812,9564 "ci_low": 0.6241086170847904,9565 "ci_high": 0.6564931065250885,9566 "n_items": 2574,9567 "n_groups": 929568 },9569 "rougeL": {9570 "mean": 0.6458118667186752,9571 "ci_low": 0.6283498149388503,9572 "ci_high": 0.6616921804476312,9573 "n_items": 2574,9574 "n_groups": 929575 },9576 "exact_match": {9577 "mean": 0.0,9578 "ci_low": 0.0,9579 "ci_high": 0.0,9580 "n_items": 2574,9581 "n_groups": 929582 },9583 "number_recall": {9584 "mean": 0.9930661790510276,9585 "ci_low": 0.9859440068177137,9586 "ci_high": 0.9981669063864298,9587 "n_items": 2574,9588 "n_groups": 929589 },9590 "placeholders_exact": {9591 "mean": 0.9980574980574981,9592 "ci_low": 0.9937576727549539,9593 "ci_high": 1.0,9594 "n_items": 2574,9595 "n_groups": 929596 }9597 },9598 "by_variant": {9599 "A": {9600 "n": 436,9601 "chrf": {9602 "mean": 62.38892187030972,9603 "ci_low": 60.17572750813598,9604 "ci_high": 64.18637015725797,9605 "n_items": 436,9606 "n_groups": 919607 },9608 "edit_sim": {9609 "mean": 0.631412165615046,9610 "ci_low": 0.6130679952135268,9611 "ci_high": 0.6467237688723606,9612 "n_items": 436,9613 "n_groups": 919614 },9615 "rougeL": {9616 "mean": 0.63535950862071,9617 "ci_low": 0.6154488610142416,9618 "ci_high": 0.6512296365927123,9619 "n_items": 436,9620 "n_groups": 919621 },9622 "exact_match": {9623 "mean": 0.0,9624 "ci_low": 0.0,9625 "ci_high": 0.0,9626 "n_items": 436,9627 "n_groups": 919628 },9629 "number_recall": {9630 "mean": 0.9933040265035677,9631 "ci_low": 0.9861555987646745,9632 "ci_high": 0.9983795415685964,9633 "n_items": 436,9634 "n_groups": 919635 },9636 "placeholders_exact": {9637 "mean": 0.9908256880733946,9638 "ci_low": 0.9721545276069637,9639 "ci_high": 1.0,9640 "n_items": 436,9641 "n_groups": 919642 }9643 },9644 "B": {9645 "n": 416,9646 "chrf": {9647 "mean": 68.18316088120301,9648 "ci_low": 65.76861136135308,9649 "ci_high": 70.46442597776559,9650 "n_items": 416,9651 "n_groups": 909652 },9653 "edit_sim": {9654 "mean": 0.6949406466669414,9655 "ci_low": 0.6723363615377925,9656 "ci_high": 0.7164219011404983,9657 "n_items": 416,9658 "n_groups": 909659 },9660 "rougeL": {9661 "mean": 0.7012347877349963,9662 "ci_low": 0.6784090386003997,9663 "ci_high": 0.7224385778241433,9664 "n_items": 416,9665 "n_groups": 909666 },9667 "exact_match": {9668 "mean": 0.0,9669 "ci_low": 0.0,9670 "ci_high": 0.0,9671 "n_items": 416,9672 "n_groups": 909673 },9674 "number_recall": {9675 "mean": 0.9927083333333333,9676 "ci_low": 0.9856323140945962,9677 "ci_high": 0.9992799447984739,9678 "n_items": 416,9679 "n_groups": 909680 },9681 "placeholders_exact": {9682 "mean": 1.0,9683 "ci_low": 1.0,9684 "ci_high": 1.0,9685 "n_items": 416,9686 "n_groups": 909687 }9688 },9689 "C": {9690 "n": 438,9691 "chrf": {9692 "mean": 67.9827208465438,9693 "ci_low": 66.13206960287937,9694 "ci_high": 69.86670947533118,9695 "n_items": 438,9696 "n_groups": 919697 },9698 "edit_sim": {9699 "mean": 0.7037769575922591,9700 "ci_low": 0.6861661200249657,9701 "ci_high": 0.720992390389497,9702 "n_items": 438,9703 "n_groups": 919704 },9705 "rougeL": {9706 "mean": 0.7191584855762794,9707 "ci_low": 0.7013640317433909,9708 "ci_high": 0.7370020647667764,9709 "n_items": 438,9710 "n_groups": 919711 },9712 "exact_match": {9713 "mean": 0.0,9714 "ci_low": 0.0,9715 "ci_high": 0.0,9716 "n_items": 438,9717 "n_groups": 919718 },9719 "number_recall": {9720 "mean": 0.9921205696890628,9721 "ci_low": 0.9836405469572693,9722 "ci_high": 0.9982199729874445,9723 "n_items": 438,9724 "n_groups": 919725 },9726 "placeholders_exact": {9727 "mean": 1.0,9728 "ci_low": 1.0,9729 "ci_high": 1.0,9730 "n_items": 438,9731 "n_groups": 919732 }9733 },9734 "D": {9735 "n": 431,9736 "chrf": {9737 "mean": 62.605406542703605,9738 "ci_low": 60.28257886487163,9739 "ci_high": 64.52571677949707,9740 "n_items": 431,9741 "n_groups": 909742 },9743 "edit_sim": {9744 "mean": 0.641039492620957,9745 "ci_low": 0.620935175057466,9746 "ci_high": 0.6566791469794301,9747 "n_items": 431,9748 "n_groups": 909749 },9750 "rougeL": {9751 "mean": 0.6430950269913671,9752 "ci_low": 0.6230733143898404,9753 "ci_high": 0.6596658714848915,9754 "n_items": 431,9755 "n_groups": 909756 },9757 "exact_match": {9758 "mean": 0.0,9759 "ci_low": 0.0,9760 "ci_high": 0.0,9761 "n_items": 431,9762 "n_groups": 909763 },9764 "number_recall": {9765 "mean": 0.9931747873163187,9766 "ci_low": 0.9864158364642872,9767 "ci_high": 0.9981989695092529,9768 "n_items": 431,9769 "n_groups": 909770 },9771 "placeholders_exact": {9772 "mean": 0.9976798143851509,9773 "ci_low": 0.9922176461670625,9774 "ci_high": 1.0,9775 "n_items": 431,9776 "n_groups": 909777 }9778 },9779 "E": {9780 "n": 853,9781 "chrf": {9782 "mean": 58.85591787013026,9783 "ci_low": 56.76228608475886,9784 "ci_high": 60.752475649923454,9785 "n_items": 853,9786 "n_groups": 919787 },9788 "edit_sim": {9789 "mean": 0.5878149088378115,9790 "ci_low": 0.5717422571701898,9791 "ci_high": 0.6031705622946985,9792 "n_items": 853,9793 "n_groups": 919794 },9795 "rougeL": {9796 "mean": 0.5878358196504013,9797 "ci_low": 0.5704521623428052,9798 "ci_high": 0.6047538584413154,9799 "n_items": 853,9800 "n_groups": 919801 },9802 "exact_match": {9803 "mean": 0.0,9804 "ci_low": 0.0,9805 "ci_high": 0.0,9806 "n_items": 853,9807 "n_groups": 919808 },9809 "number_recall": {9810 "mean": 0.9935498004665648,9811 "ci_low": 0.9867040926112429,9812 "ci_high": 0.9989420883217641,9813 "n_items": 853,9814 "n_groups": 919815 },9816 "placeholders_exact": {9817 "mean": 1.0,9818 "ci_low": 1.0,9819 "ci_high": 1.0,9820 "n_items": 853,9821 "n_groups": 919822 }9823 }9824 },9825 "by_discipline": {9826 "biomedicine": {9827 "n": 438,9828 "chrf": {9829 "mean": 63.68765451443134,9830 "ci_low": 57.48313803264029,9831 "ci_high": 68.49992332582028,9832 "n_items": 438,9833 "n_groups": 229834 },9835 "edit_sim": {9836 "mean": 0.6423050859189792,9837 "ci_low": 0.5882450080971073,9838 "ci_high": 0.6842793047300071,9839 "n_items": 438,9840 "n_groups": 229841 },9842 "rougeL": {9843 "mean": 0.640892532355041,9844 "ci_low": 0.5841580314036385,9845 "ci_high": 0.682344292140274,9846 "n_items": 438,9847 "n_groups": 229848 },9849 "exact_match": {9850 "mean": 0.0,9851 "ci_low": 0.0,9852 "ci_high": 0.0,9853 "n_items": 438,9854 "n_groups": 229855 },9856 "number_recall": {9857 "mean": 0.977794085670798,9858 "ci_low": 0.9555465172213757,9859 "ci_high": 1.0,9860 "n_items": 438,9861 "n_groups": 229862 },9863 "placeholders_exact": {9864 "mean": 0.9885844748858448,9865 "ci_low": 0.9752883031301482,9866 "ci_high": 1.0,9867 "n_items": 438,9868 "n_groups": 229869 }9870 },9871 "chemistry": {9872 "n": 183,9873 "chrf": {9874 "mean": 64.59403745984811,9875 "ci_low": 64.59403745984811,9876 "ci_high": 64.59403745984811,9877 "n_items": 183,9878 "n_groups": 19879 },9880 "edit_sim": {9881 "mean": 0.6459098954344498,9882 "ci_low": 0.6459098954344498,9883 "ci_high": 0.6459098954344498,9884 "n_items": 183,9885 "n_groups": 19886 },9887 "rougeL": {9888 "mean": 0.6535506648537157,9889 "ci_low": 0.6535506648537157,9890 "ci_high": 0.6535506648537157,9891 "n_items": 183,9892 "n_groups": 19893 },9894 "exact_match": {9895 "mean": 0.0,9896 "ci_low": 0.0,9897 "ci_high": 0.0,9898 "n_items": 183,9899 "n_groups": 19900 },9901 "number_recall": {9902 "mean": 1.0,9903 "ci_low": 1.0,9904 "ci_high": 1.0,9905 "n_items": 183,9906 "n_groups": 19907 },9908 "placeholders_exact": {9909 "mean": 1.0,9910 "ci_low": 1.0,9911 "ci_high": 1.0,9912 "n_items": 183,9913 "n_groups": 19914 }9915 },9916 "earth_sciences": {9917 "n": 101,9918 "chrf": {9919 "mean": 60.638792034808446,9920 "ci_low": 60.638792034808446,9921 "ci_high": 60.638792034808446,9922 "n_items": 101,9923 "n_groups": 19924 },9925 "edit_sim": {9926 "mean": 0.6031309330339449,9927 "ci_low": 0.6031309330339449,9928 "ci_high": 0.6031309330339449,9929 "n_items": 101,9930 "n_groups": 19931 },9932 "rougeL": {9933 "mean": 0.6173513665088641,9934 "ci_low": 0.6173513665088641,9935 "ci_high": 0.6173513665088641,9936 "n_items": 101,9937 "n_groups": 19938 },9939 "exact_match": {9940 "mean": 0.0,9941 "ci_low": 0.0,9942 "ci_high": 0.0,9943 "n_items": 101,9944 "n_groups": 19945 },9946 "number_recall": {9947 "mean": 0.9851485148514851,9948 "ci_low": 0.9851485148514851,9949 "ci_high": 0.9851485148514851,9950 "n_items": 101,9951 "n_groups": 19952 },9953 "placeholders_exact": {9954 "mean": 1.0,9955 "ci_low": 1.0,9956 "ci_high": 1.0,9957 "n_items": 101,9958 "n_groups": 19959 }9960 },9961 "economics": {9962 "n": 569,9963 "chrf": {9964 "mean": 67.56538399692064,9965 "ci_low": 62.71527844814817,9966 "ci_high": 70.87467925748705,9967 "n_items": 569,9968 "n_groups": 89969 },9970 "edit_sim": {9971 "mean": 0.6738438639983365,9972 "ci_low": 0.6340082251960817,9973 "ci_high": 0.7039753356499069,9974 "n_items": 569,9975 "n_groups": 89976 },9977 "rougeL": {9978 "mean": 0.6790896931126217,9979 "ci_low": 0.6366113950590755,9980 "ci_high": 0.713114813827787,9981 "n_items": 569,9982 "n_groups": 89983 },9984 "exact_match": {9985 "mean": 0.0,9986 "ci_low": 0.0,9987 "ci_high": 0.0,9988 "n_items": 569,9989 "n_groups": 89990 },9991 "number_recall": {9992 "mean": 0.9913493458308924,9993 "ci_low": 0.9859903381642512,9994 "ci_high": 0.9988344988344987,9995 "n_items": 569,9996 "n_groups": 89997 },9998 "placeholders_exact": {9999 "mean": 1.0,10000 "ci_low": 1.0,10001 "ci_high": 1.0,10002 "n_items": 569,10003 "n_groups": 810004 }10005 },10006 "engineering": {10007 "n": 167,10008 "chrf": {10009 "mean": 59.87029203719406,10010 "ci_low": 56.36379050744471,10011 "ci_high": 61.33361024876982,10012 "n_items": 167,10013 "n_groups": 810014 },10015 "edit_sim": {10016 "mean": 0.6034432601373015,10017 "ci_low": 0.5783119840538572,10018 "ci_high": 0.6181456055515241,10019 "n_items": 167,10020 "n_groups": 810021 },10022 "rougeL": {10023 "mean": 0.6143092529333862,10024 "ci_low": 0.5765307787695295,10025 "ci_high": 0.6333110194221405,10026 "n_items": 167,10027 "n_groups": 810028 },10029 "exact_match": {10030 "mean": 0.0,10031 "ci_low": 0.0,10032 "ci_high": 0.0,10033 "n_items": 167,10034 "n_groups": 810035 },10036 "number_recall": {10037 "mean": 0.9976047904191616,10038 "ci_low": 0.9945199195676762,10039 "ci_high": 1.0,10040 "n_items": 167,10041 "n_groups": 810042 },10043 "placeholders_exact": {10044 "mean": 1.0,10045 "ci_low": 1.0,10046 "ci_high": 1.0,10047 "n_items": 167,10048 "n_groups": 810049 }10050 },10051 "finance": {10052 "n": 75,10053 "chrf": {10054 "mean": 57.43079525993602,10055 "ci_low": 57.18945176677161,10056 "ci_high": 58.48236333729528,10057 "n_items": 75,10058 "n_groups": 210059 },10060 "edit_sim": {10061 "mean": 0.5833169689986316,10062 "ci_low": 0.5827468529217708,10063 "ci_high": 0.5834478153113539,10064 "n_items": 75,10065 "n_groups": 210066 },10067 "rougeL": {10068 "mean": 0.5849812152110496,10069 "ci_low": 0.5842025677259741,10070 "ci_high": 0.5883738935388785,10071 "n_items": 75,10072 "n_groups": 210073 },10074 "exact_match": {10075 "mean": 0.0,10076 "ci_low": 0.0,10077 "ci_high": 0.0,10078 "n_items": 75,10079 "n_groups": 210080 },10081 "number_recall": {10082 "mean": 1.0,10083 "ci_low": 1.0,10084 "ci_high": 1.0,10085 "n_items": 75,10086 "n_groups": 210087 },10088 "placeholders_exact": {10089 "mean": 1.0,10090 "ci_low": 1.0,10091 "ci_high": 1.0,10092 "n_items": 75,10093 "n_groups": 210094 }10095 },10096 "general_reference": {10097 "n": 256,10098 "chrf": {10099 "mean": 62.20445859415054,10100 "ci_low": 59.15486025282596,10101 "ci_high": 64.1829009252644,10102 "n_items": 256,10103 "n_groups": 1210104 },10105 "edit_sim": {10106 "mean": 0.6438472273584481,10107 "ci_low": 0.605708739980364,10108 "ci_high": 0.6659343854457916,10109 "n_items": 256,10110 "n_groups": 1210111 },10112 "rougeL": {10113 "mean": 0.6481458290900666,10114 "ci_low": 0.6027607638268287,10115 "ci_high": 0.670613549033765,10116 "n_items": 256,10117 "n_groups": 1210118 },10119 "exact_match": {10120 "mean": 0.0,10121 "ci_low": 0.0,10122 "ci_high": 0.0,10123 "n_items": 256,10124 "n_groups": 1210125 },10126 "number_recall": {10127 "mean": 0.9957682291666666,10128 "ci_low": 0.989329268292683,10129 "ci_high": 1.0,10130 "n_items": 256,10131 "n_groups": 1210132 },10133 "placeholders_exact": {10134 "mean": 1.0,10135 "ci_low": 1.0,10136 "ci_high": 1.0,10137 "n_items": 256,10138 "n_groups": 1210139 }10140 },10141 "humanities": {10142 "n": 253,10143 "chrf": {10144 "mean": 63.167893771265334,10145 "ci_low": 59.670416636802095,10146 "ci_high": 66.63604542924172,10147 "n_items": 253,10148 "n_groups": 910149 },10150 "edit_sim": {10151 "mean": 0.653966969026913,10152 "ci_low": 0.6240181075917348,10153 "ci_high": 0.6946986201613423,10154 "n_items": 253,10155 "n_groups": 910156 },10157 "rougeL": {10158 "mean": 0.6582104490897647,10159 "ci_low": 0.6266738391621189,10160 "ci_high": 0.6966421030577034,10161 "n_items": 253,10162 "n_groups": 910163 },10164 "exact_match": {10165 "mean": 0.0,10166 "ci_low": 0.0,10167 "ci_high": 0.0,10168 "n_items": 253,10169 "n_groups": 910170 },10171 "number_recall": {10172 "mean": 1.0,10173 "ci_low": 1.0,10174 "ci_high": 1.0,10175 "n_items": 253,10176 "n_groups": 910177 },10178 "placeholders_exact": {10179 "mean": 1.0,10180 "ci_low": 1.0,10181 "ci_high": 1.0,10182 "n_items": 253,10183 "n_groups": 910184 }10185 },10186 "life_sciences": {10187 "n": 233,10188 "chrf": {10189 "mean": 60.72122747280136,10190 "ci_low": 58.140405964014796,10191 "ci_high": 63.626962927279635,10192 "n_items": 233,10193 "n_groups": 810194 },10195 "edit_sim": {10196 "mean": 0.6185402555717958,10197 "ci_low": 0.5945476416235747,10198 "ci_high": 0.645054072623267,10199 "n_items": 233,10200 "n_groups": 810201 },10202 "rougeL": {10203 "mean": 0.6274320703833913,10204 "ci_low": 0.6008877959502752,10205 "ci_high": 0.6570137528457812,10206 "n_items": 233,10207 "n_groups": 810208 },10209 "exact_match": {10210 "mean": 0.0,10211 "ci_low": 0.0,10212 "ci_high": 0.0,10213 "n_items": 233,10214 "n_groups": 810215 },10216 "number_recall": {10217 "mean": 0.9990733515411627,10218 "ci_low": 0.9969869630613898,10219 "ci_high": 1.0,10220 "n_items": 233,10221 "n_groups": 810222 },10223 "placeholders_exact": {10224 "mean": 1.0,10225 "ci_low": 1.0,10226 "ci_high": 1.0,10227 "n_items": 233,10228 "n_groups": 810229 }10230 },10231 "social_sciences": {10232 "n": 299,10233 "chrf": {10234 "mean": 59.81467823949638,10235 "ci_low": 57.35605538775661,10236 "ci_high": 62.02981597025617,10237 "n_items": 299,10238 "n_groups": 2110239 },10240 "edit_sim": {10241 "mean": 0.6272666482380497,10242 "ci_low": 0.6025168053284838,10243 "ci_high": 0.6505421133855604,10244 "n_items": 299,10245 "n_groups": 2110246 },10247 "rougeL": {10248 "mean": 0.6292543011667329,10249 "ci_low": 0.6016186578222795,10250 "ci_high": 0.6554217168051095,10251 "n_items": 299,10252 "n_groups": 2110253 },10254 "exact_match": {10255 "mean": 0.0,10256 "ci_low": 0.0,10257 "ci_high": 0.0,10258 "n_items": 299,10259 "n_groups": 2110260 },10261 "number_recall": {10262 "mean": 1.0,10263 "ci_low": 1.0,10264 "ci_high": 1.0,10265 "n_items": 299,10266 "n_groups": 2110267 },10268 "placeholders_exact": {10269 "mean": 1.0,10270 "ci_low": 1.0,10271 "ci_high": 1.0,10272 "n_items": 299,10273 "n_groups": 2110274 }10275 }10276 },10277 "by_era": {10278 "1900-1949": {10279 "n": 74,10280 "chrf": {10281 "mean": 64.54150540821182,10282 "ci_low": 62.70406684124528,10283 "ci_high": 70.82763680384477,10284 "n_items": 74,10285 "n_groups": 510286 },10287 "edit_sim": {10288 "mean": 0.6736626124177715,10289 "ci_low": 0.618519787769288,10290 "ci_high": 0.6988448645867223,10291 "n_items": 74,10292 "n_groups": 510293 },10294 "rougeL": {10295 "mean": 0.6658458422228147,10296 "ci_low": 0.5933097539701152,10297 "ci_high": 0.6907293189520552,10298 "n_items": 74,10299 "n_groups": 510300 },10301 "exact_match": {10302 "mean": 0.0,10303 "ci_low": 0.0,10304 "ci_high": 0.0,10305 "n_items": 74,10306 "n_groups": 510307 },10308 "number_recall": {10309 "mean": 0.9864864864864865,10310 "ci_low": 0.9000000000000001,10311 "ci_high": 1.0,10312 "n_items": 74,10313 "n_groups": 510314 },10315 "placeholders_exact": {10316 "mean": 1.0,10317 "ci_low": 1.0,10318 "ci_high": 1.0,10319 "n_items": 74,10320 "n_groups": 510321 }10322 },10323 "2010-2017": {10324 "n": 527,10325 "chrf": {10326 "mean": 70.39228389339759,10327 "ci_low": 66.69997518078726,10328 "ci_high": 73.04930432836835,10329 "n_items": 527,10330 "n_groups": 410331 },10332 "edit_sim": {10333 "mean": 0.6961115935409282,10334 "ci_low": 0.6630152833623922,10335 "ci_high": 0.7220479968730809,10336 "n_items": 527,10337 "n_groups": 410338 },10339 "rougeL": {10340 "mean": 0.6995814325991238,10341 "ci_low": 0.661247996777987,10342 "ci_high": 0.728077324672853,10343 "n_items": 527,10344 "n_groups": 410345 },10346 "exact_match": {10347 "mean": 0.0,10348 "ci_low": 0.0,10349 "ci_high": 0.0,10350 "n_items": 527,10351 "n_groups": 410352 },10353 "number_recall": {10354 "mean": 0.9750052709255745,10355 "ci_low": 0.9446236559139785,10356 "ci_high": 0.9935837245696402,10357 "n_items": 527,10358 "n_groups": 410359 },10360 "placeholders_exact": {10361 "mean": 0.9905123339658444,10362 "ci_low": 0.967741935483871,10363 "ci_high": 1.0,10364 "n_items": 527,10365 "n_groups": 410366 }10367 },10368 "pre1900": {10369 "n": 1973,10370 "chrf": {10371 "mean": 61.15378598272673,10372 "ci_low": 59.81295791582988,10373 "ci_high": 62.35596998678302,10374 "n_items": 1973,10375 "n_groups": 8310376 },10377 "edit_sim": {10378 "mean": 0.6252598155551539,10379 "ci_low": 0.6133368693805142,10380 "ci_high": 0.6369028458477299,10381 "n_items": 1973,10382 "n_groups": 8310383 },10384 "rougeL": {10385 "mean": 0.6306982958082329,10386 "ci_low": 0.6173238937057393,10387 "ci_high": 0.6427641112954344,10388 "n_items": 1973,10389 "n_groups": 8310390 },10391 "exact_match": {10392 "mean": 0.0,10393 "ci_low": 0.0,10394 "ci_high": 0.0,10395 "n_items": 1973,10396 "n_groups": 8310397 },10398 "number_recall": {10399 "mean": 0.9981371348705358,10400 "ci_low": 0.9964099834483786,10401 "ci_high": 0.9995160880109204,10402 "n_items": 1973,10403 "n_groups": 8310404 },10405 "placeholders_exact": {10406 "mean": 1.0,10407 "ci_low": 1.0,10408 "ci_high": 1.0,10409 "n_items": 1973,10410 "n_groups": 8310411 }10412 }10413 },10414 "by_role": {10415 "abstract": {10416 "n": 36,10417 "chrf": {10418 "mean": 66.95216348515706,10419 "ci_low": 62.5225166168117,10420 "ci_high": 71.23660386981231,10421 "n_items": 36,10422 "n_groups": 610423 },10424 "edit_sim": {10425 "mean": 0.6563809373176933,10426 "ci_low": 0.6017539413333035,10427 "ci_high": 0.7091685288941424,10428 "n_items": 36,10429 "n_groups": 610430 },10431 "rougeL": {10432 "mean": 0.6321162859727307,10433 "ci_low": 0.5770334411024831,10434 "ci_high": 0.6847824287193345,10435 "n_items": 36,10436 "n_groups": 610437 },10438 "exact_match": {10439 "mean": 0.0,10440 "ci_low": 0.0,10441 "ci_high": 0.0,10442 "n_items": 36,10443 "n_groups": 610444 },10445 "number_recall": {10446 "mean": 0.9722222222222222,10447 "ci_low": 0.9166666666666666,10448 "ci_high": 1.0,10449 "n_items": 36,10450 "n_groups": 610451 },10452 "placeholders_exact": {10453 "mean": 1.0,10454 "ci_low": 1.0,10455 "ci_high": 1.0,10456 "n_items": 36,10457 "n_groups": 610458 }10459 },10460 "chapter": {10461 "n": 819,10462 "chrf": {10463 "mean": 61.77821100346861,10464 "ci_low": 60.373553964820914,10465 "ci_high": 63.165580125719806,10466 "n_items": 819,10467 "n_groups": 5210468 },10469 "edit_sim": {10470 "mean": 0.6290493406755355,10471 "ci_low": 0.6137627995743355,10472 "ci_high": 0.6439187497034032,10473 "n_items": 819,10474 "n_groups": 5210475 },10476 "rougeL": {10477 "mean": 0.6373875631547864,10478 "ci_low": 0.6215071516553744,10479 "ci_high": 0.6523460144327538,10480 "n_items": 819,10481 "n_groups": 5210482 },10483 "exact_match": {10484 "mean": 0.0,10485 "ci_low": 0.0,10486 "ci_high": 0.0,10487 "n_items": 819,10488 "n_groups": 5210489 },10490 "number_recall": {10491 "mean": 0.9974164724164724,10492 "ci_low": 0.9941004282818428,10493 "ci_high": 1.0,10494 "n_items": 819,10495 "n_groups": 5210496 },10497 "placeholders_exact": {10498 "mean": 1.0,10499 "ci_low": 1.0,10500 "ci_high": 1.0,10501 "n_items": 819,10502 "n_groups": 5210503 }10504 },10505 "conclusion": {10506 "n": 104,10507 "chrf": {10508 "mean": 69.09260167915531,10509 "ci_low": 61.72480436325037,10510 "ci_high": 73.01607109380816,10511 "n_items": 104,10512 "n_groups": 310513 },10514 "edit_sim": {10515 "mean": 0.6792793856156595,10516 "ci_low": 0.6122068927806916,10517 "ci_high": 0.7276347809761535,10518 "n_items": 104,10519 "n_groups": 310520 },10521 "rougeL": {10522 "mean": 0.6765013075583065,10523 "ci_low": 0.5986827672608847,10524 "ci_high": 0.7246181003547184,10525 "n_items": 104,10526 "n_groups": 310527 },10528 "exact_match": {10529 "mean": 0.0,10530 "ci_low": 0.0,10531 "ci_high": 0.0,10532 "n_items": 104,10533 "n_groups": 310534 },10535 "number_recall": {10536 "mean": 0.9807692307692307,10537 "ci_low": 0.9444444444444444,10538 "ci_high": 1.0,10539 "n_items": 104,10540 "n_groups": 310541 },10542 "placeholders_exact": {10543 "mean": 1.0,10544 "ci_low": 1.0,10545 "ci_high": 1.0,10546 "n_items": 104,10547 "n_groups": 310548 }10549 },10550 "data": {10551 "n": 11,10552 "chrf": {10553 "mean": 76.37317996735361,10554 "ci_low": 76.37317996735361,10555 "ci_high": 76.37317996735361,10556 "n_items": 11,10557 "n_groups": 110558 },10559 "edit_sim": {10560 "mean": 0.7764467212124699,10561 "ci_low": 0.7764467212124699,10562 "ci_high": 0.7764467212124699,10563 "n_items": 11,10564 "n_groups": 110565 },10566 "rougeL": {10567 "mean": 0.7950318456430914,10568 "ci_low": 0.7950318456430914,10569 "ci_high": 0.7950318456430914,10570 "n_items": 11,10571 "n_groups": 110572 },10573 "exact_match": {10574 "mean": 0.0,10575 "ci_low": 0.0,10576 "ci_high": 0.0,10577 "n_items": 11,10578 "n_groups": 110579 },10580 "number_recall": {10581 "mean": 1.0,10582 "ci_low": 1.0,10583 "ci_high": 1.0,10584 "n_items": 11,10585 "n_groups": 110586 },10587 "placeholders_exact": {10588 "mean": 1.0,10589 "ci_low": 1.0,10590 "ci_high": 1.0,10591 "n_items": 11,10592 "n_groups": 110593 }10594 },10595 "introduction": {10596 "n": 574,10597 "chrf": {10598 "mean": 61.970761027607935,10599 "ci_low": 59.0933625951073,10600 "ci_high": 64.03341384941133,10601 "n_items": 574,10602 "n_groups": 2310603 },10604 "edit_sim": {10605 "mean": 0.6340848335626375,10606 "ci_low": 0.6058611711211794,10607 "ci_high": 0.6551578258825127,10608 "n_items": 574,10609 "n_groups": 2310610 },10611 "rougeL": {10612 "mean": 0.6375457566785642,10613 "ci_low": 0.6089926152304114,10614 "ci_high": 0.6590753575810671,10615 "n_items": 574,10616 "n_groups": 2310617 },10618 "exact_match": {10619 "mean": 0.0,10620 "ci_low": 0.0,10621 "ci_high": 0.0,10622 "n_items": 574,10623 "n_groups": 2310624 },10625 "number_recall": {10626 "mean": 0.9985481997677119,10627 "ci_low": 0.9968299986162161,10628 "ci_high": 1.0,10629 "n_items": 574,10630 "n_groups": 2310631 },10632 "placeholders_exact": {10633 "mean": 1.0,10634 "ci_low": 1.0,10635 "ci_high": 1.0,10636 "n_items": 574,10637 "n_groups": 2310638 }10639 },10640 "methods": {10641 "n": 93,10642 "chrf": {10643 "mean": 70.26374673069233,10644 "ci_low": 67.07424001016264,10645 "ci_high": 78.72517788959836,10646 "n_items": 93,10647 "n_groups": 310648 },10649 "edit_sim": {10650 "mean": 0.6953650323692296,10651 "ci_low": 0.6653723114455663,10652 "ci_high": 0.8042343570020508,10653 "n_items": 93,10654 "n_groups": 310655 },10656 "rougeL": {10657 "mean": 0.7153018430873914,10658 "ci_low": 0.67704566486825,10659 "ci_high": 0.8176601518633387,10660 "n_items": 93,10661 "n_groups": 310662 },10663 "exact_match": {10664 "mean": 0.0,10665 "ci_low": 0.0,10666 "ci_high": 0.0,10667 "n_items": 93,10668 "n_groups": 310669 },10670 "number_recall": {10671 "mean": 0.9772401433691758,10672 "ci_low": 0.9721088435374148,10673 "ci_high": 1.0,10674 "n_items": 93,10675 "n_groups": 310676 },10677 "placeholders_exact": {10678 "mean": 1.0,10679 "ci_low": 1.0,10680 "ci_high": 1.0,10681 "n_items": 93,10682 "n_groups": 310683 }10684 },10685 "other": {10686 "n": 163,10687 "chrf": {10688 "mean": 65.2850372362587,10689 "ci_low": 59.90607568387957,10690 "ci_high": 70.10959744785217,10691 "n_items": 163,10692 "n_groups": 910693 },10694 "edit_sim": {10695 "mean": 0.6720843346118832,10696 "ci_low": 0.6416970920798661,10697 "ci_high": 0.699394102682375,10698 "n_items": 163,10699 "n_groups": 910700 },10701 "rougeL": {10702 "mean": 0.6772160033185844,10703 "ci_low": 0.6457368014503001,10704 "ci_high": 0.7063970754451296,10705 "n_items": 163,10706 "n_groups": 910707 },10708 "exact_match": {10709 "mean": 0.0,10710 "ci_low": 0.0,10711 "ci_high": 0.0,10712 "n_items": 163,10713 "n_groups": 910714 },10715 "number_recall": {10716 "mean": 0.983786152497809,10717 "ci_low": 0.94617371495158,10718 "ci_high": 1.0,10719 "n_items": 163,10720 "n_groups": 910721 },10722 "placeholders_exact": {10723 "mean": 1.0,10724 "ci_low": 1.0,10725 "ci_high": 1.0,10726 "n_items": 163,10727 "n_groups": 910728 }10729 },10730 "preface": {10731 "n": 562,10732 "chrf": {10733 "mean": 59.95986765741636,10734 "ci_low": 58.04697231487036,10735 "ci_high": 61.87399222991151,10736 "n_items": 562,10737 "n_groups": 4810738 },10739 "edit_sim": {10740 "mean": 0.6143316403553769,10741 "ci_low": 0.5958174342523462,10742 "ci_high": 0.634110542665919,10743 "n_items": 562,10744 "n_groups": 4810745 },10746 "rougeL": {10747 "mean": 0.616933472105122,10748 "ci_low": 0.5958138286231618,10749 "ci_high": 0.6388177018383558,10750 "n_items": 562,10751 "n_groups": 4810752 },10753 "exact_match": {10754 "mean": 0.0,10755 "ci_low": 0.0,10756 "ci_high": 0.0,10757 "n_items": 562,10758 "n_groups": 4810759 },10760 "number_recall": {10761 "mean": 0.9989620403321472,10762 "ci_low": 0.9965949982520671,10763 "ci_high": 1.0,10764 "n_items": 562,10765 "n_groups": 4810766 },10767 "placeholders_exact": {10768 "mean": 1.0,10769 "ci_low": 1.0,10770 "ci_high": 1.0,10771 "n_items": 562,10772 "n_groups": 4810773 }10774 },10775 "related_work": {10776 "n": 18,10777 "chrf": {10778 "mean": 70.23764572589049,10779 "ci_low": 70.23764572589049,10780 "ci_high": 70.23764572589049,10781 "n_items": 18,10782 "n_groups": 110783 },10784 "edit_sim": {10785 "mean": 0.6996681645456868,10786 "ci_low": 0.6996681645456868,10787 "ci_high": 0.6996681645456868,10788 "n_items": 18,10789 "n_groups": 110790 },10791 "rougeL": {10792 "mean": 0.6875078623722376,10793 "ci_low": 0.6875078623722376,10794 "ci_high": 0.6875078623722376,10795 "n_items": 18,10796 "n_groups": 110797 },10798 "exact_match": {10799 "mean": 0.0,10800 "ci_low": 0.0,10801 "ci_high": 0.0,10802 "n_items": 18,10803 "n_groups": 110804 },10805 "number_recall": {10806 "mean": 1.0,10807 "ci_low": 1.0,10808 "ci_high": 1.0,10809 "n_items": 18,10810 "n_groups": 110811 },10812 "placeholders_exact": {10813 "mean": 1.0,10814 "ci_low": 1.0,10815 "ci_high": 1.0,10816 "n_items": 18,10817 "n_groups": 110818 }10819 },10820 "results": {10821 "n": 158,10822 "chrf": {10823 "mean": 70.28374987224966,10824 "ci_low": 67.8699840830289,10825 "ci_high": 75.44754205875121,10826 "n_items": 158,10827 "n_groups": 310828 },10829 "edit_sim": {10830 "mean": 0.6912002143447653,10831 "ci_low": 0.6704300318446522,10832 "ci_high": 0.7106113940520952,10833 "n_items": 158,10834 "n_groups": 310835 },10836 "rougeL": {10837 "mean": 0.6937986340009847,10838 "ci_low": 0.6792669421904756,10839 "ci_high": 0.728787858823155,10840 "n_items": 158,10841 "n_groups": 310842 },10843 "exact_match": {10844 "mean": 0.0,10845 "ci_low": 0.0,10846 "ci_high": 0.0,10847 "n_items": 158,10848 "n_groups": 310849 },10850 "number_recall": {10851 "mean": 0.958509142053446,10852 "ci_low": 0.920995670995671,10853 "ci_high": 1.0,10854 "n_items": 158,10855 "n_groups": 310856 },10857 "placeholders_exact": {10858 "mean": 0.9683544303797469,10859 "ci_low": 0.935064935064935,10860 "ci_high": 1.0,10861 "n_items": 158,10862 "n_groups": 310863 }10864 },10865 "theory": {10866 "n": 36,10867 "chrf": {10868 "mean": 74.53040090854375,10869 "ci_low": 70.01270986397519,10870 "ci_high": 75.43393911745747,10871 "n_items": 36,10872 "n_groups": 210873 },10874 "edit_sim": {10875 "mean": 0.7525259357275043,10876 "ci_low": 0.7447664345722599,10877 "ci_high": 0.754077835958553,10878 "n_items": 36,10879 "n_groups": 210880 },10881 "rougeL": {10882 "mean": 0.7463660229849087,10883 "ci_low": 0.6952620284676576,10884 "ci_high": 0.756586821888359,10885 "n_items": 36,10886 "n_groups": 210887 },10888 "exact_match": {10889 "mean": 0.0,10890 "ci_low": 0.0,10891 "ci_high": 0.0,10892 "n_items": 36,10893 "n_groups": 210894 },10895 "number_recall": {10896 "mean": 1.0,10897 "ci_low": 1.0,10898 "ci_high": 1.0,10899 "n_items": 36,10900 "n_groups": 210901 },10902 "placeholders_exact": {10903 "mean": 1.0,10904 "ci_low": 1.0,10905 "ci_high": 1.0,10906 "n_items": 36,10907 "n_groups": 210908 }10909 }10910 }10911 },10912 "htr-m3tokenonly-tiny-s2": {10913 "overall": {10914 "n": 2574,10915 "chrf": {10916 "mean": 63.42508237714038,10917 "ci_low": 61.33898985541974,10918 "ci_high": 65.25425122356796,10919 "n_items": 2574,10920 "n_groups": 9210921 },10922 "edit_sim": {10923 "mean": 0.6444224364119798,10924 "ci_low": 0.6273035190890708,10925 "ci_high": 0.6597618788214299,10926 "n_items": 2574,10927 "n_groups": 9210928 },10929 "rougeL": {10930 "mean": 0.6499995059016356,10931 "ci_low": 0.632253564273307,10932 "ci_high": 0.6659311355521197,10933 "n_items": 2574,10934 "n_groups": 9210935 },10936 "exact_match": {10937 "mean": 0.0,10938 "ci_low": 0.0,10939 "ci_high": 0.0,10940 "n_items": 2574,10941 "n_groups": 9210942 },10943 "number_recall": {10944 "mean": 0.9956478706478707,10945 "ci_low": 0.9933010260065985,10946 "ci_high": 0.997978740770407,10947 "n_items": 2574,10948 "n_groups": 9210949 },10950 "placeholders_exact": {10951 "mean": 0.9988344988344988,10952 "ci_low": 0.9962546036529722,10953 "ci_high": 1.0,10954 "n_items": 2574,10955 "n_groups": 9210956 }10957 },10958 "by_variant": {10959 "A": {10960 "n": 436,10961 "chrf": {10962 "mean": 62.530804137303214,10963 "ci_low": 60.308093281675134,10964 "ci_high": 64.33782605178652,10965 "n_items": 436,10966 "n_groups": 9110967 },10968 "edit_sim": {10969 "mean": 0.6340777982456933,10970 "ci_low": 0.6155034238107815,10971 "ci_high": 0.6491229953387477,10972 "n_items": 436,10973 "n_groups": 9110974 },10975 "rougeL": {10976 "mean": 0.6385990629369737,10977 "ci_low": 0.6185865760220947,10978 "ci_high": 0.6545008952224058,10979 "n_items": 436,10980 "n_groups": 9110981 },10982 "exact_match": {10983 "mean": 0.0,10984 "ci_low": 0.0,10985 "ci_high": 0.0,10986 "n_items": 436,10987 "n_groups": 9110988 },10989 "number_recall": {10990 "mean": 0.9921035386631717,10991 "ci_low": 0.9859526015876197,10992 "ci_high": 0.9972793926883299,10993 "n_items": 436,10994 "n_groups": 9110995 },10996 "placeholders_exact": {10997 "mean": 0.9954128440366973,10998 "ci_low": 0.9860772638034819,10999 "ci_high": 1.0,11000 "n_items": 436,11001 "n_groups": 9111002 }11003 },11004 "B": {11005 "n": 416,11006 "chrf": {11007 "mean": 68.58180221392853,11008 "ci_low": 66.13486118896638,11009 "ci_high": 70.81839652782382,11010 "n_items": 416,11011 "n_groups": 9011012 },11013 "edit_sim": {11014 "mean": 0.6989840193888954,11015 "ci_low": 0.6765623101999918,11016 "ci_high": 0.7202457745614037,11017 "n_items": 416,11018 "n_groups": 9011019 },11020 "rougeL": {11021 "mean": 0.7063673621418872,11022 "ci_low": 0.6833918270670327,11023 "ci_high": 0.7274659331521287,11024 "n_items": 416,11025 "n_groups": 9011026 },11027 "exact_match": {11028 "mean": 0.0,11029 "ci_low": 0.0,11030 "ci_high": 0.0,11031 "n_items": 416,11032 "n_groups": 9011033 },11034 "number_recall": {11035 "mean": 0.9974759615384616,11036 "ci_low": 0.9953571235729712,11037 "ci_high": 0.9995338789009498,11038 "n_items": 416,11039 "n_groups": 9011040 },11041 "placeholders_exact": {11042 "mean": 1.0,11043 "ci_low": 1.0,11044 "ci_high": 1.0,11045 "n_items": 416,11046 "n_groups": 9011047 }11048 },11049 "C": {11050 "n": 438,11051 "chrf": {11052 "mean": 68.45089669079792,11053 "ci_low": 66.6112977794155,11054 "ci_high": 70.29768506053281,11055 "n_items": 438,11056 "n_groups": 9111057 },11058 "edit_sim": {11059 "mean": 0.70792333420863,11060 "ci_low": 0.6913307504918991,11061 "ci_high": 0.7242194251022916,11062 "n_items": 438,11063 "n_groups": 9111064 },11065 "rougeL": {11066 "mean": 0.7244890092136315,11067 "ci_low": 0.7071038383184302,11068 "ci_high": 0.7415793050913935,11069 "n_items": 438,11070 "n_groups": 9111071 },11072 "exact_match": {11073 "mean": 0.0,11074 "ci_low": 0.0,11075 "ci_high": 0.0,11076 "n_items": 438,11077 "n_groups": 9111078 },11079 "number_recall": {11080 "mean": 0.9956240487062404,11081 "ci_low": 0.991804242243727,11082 "ci_high": 0.9989849844990291,11083 "n_items": 438,11084 "n_groups": 9111085 },11086 "placeholders_exact": {11087 "mean": 1.0,11088 "ci_low": 1.0,11089 "ci_high": 1.0,11090 "n_items": 438,11091 "n_groups": 9111092 }11093 },11094 "D": {11095 "n": 431,11096 "chrf": {11097 "mean": 62.95441128576343,11098 "ci_low": 60.55743339707538,11099 "ci_high": 64.93843818567785,11100 "n_items": 431,11101 "n_groups": 9011102 },11103 "edit_sim": {11104 "mean": 0.6450434545644893,11105 "ci_low": 0.6245628436214103,11106 "ci_high": 0.6610953189381943,11107 "n_items": 431,11108 "n_groups": 9011109 },11110 "rougeL": {11111 "mean": 0.6475862676109364,11112 "ci_low": 0.626727567101416,11113 "ci_high": 0.6643432585241333,11114 "n_items": 431,11115 "n_groups": 9011116 },11117 "exact_match": {11118 "mean": 0.0,11119 "ci_low": 0.0,11120 "ci_high": 0.0,11121 "n_items": 431,11122 "n_groups": 9011123 },11124 "number_recall": {11125 "mean": 0.9950502706883217,11126 "ci_low": 0.9896252990514965,11127 "ci_high": 0.9989317042606517,11128 "n_items": 431,11129 "n_groups": 9011130 },11131 "placeholders_exact": {11132 "mean": 0.9976798143851509,11133 "ci_low": 0.9922176461670625,11134 "ci_high": 1.0,11135 "n_items": 431,11136 "n_groups": 9011137 }11138 },11139 "E": {11140 "n": 853,11141 "chrf": {11142 "mean": 59.02445216783974,11143 "ci_low": 56.87409723266566,11144 "ci_high": 60.95997687813207,11145 "n_items": 853,11146 "n_groups": 9111147 },11148 "edit_sim": {11149 "mean": 0.5901804571194116,11150 "ci_low": 0.5739833831189195,11151 "ci_high": 0.6058104191355802,11152 "n_items": 853,11153 "n_groups": 9111154 },11155 "rougeL": {11156 "mean": 0.5913069715397192,11157 "ci_low": 0.5739547824055667,11158 "ci_high": 0.608104646044822,11159 "n_items": 853,11160 "n_groups": 9111161 },11162 "exact_match": {11163 "mean": 0.0,11164 "ci_low": 0.0,11165 "ci_high": 0.0,11166 "n_items": 853,11167 "n_groups": 9111168 },11169 "number_recall": {11170 "mean": 0.9968821526265841,11171 "ci_low": 0.9941138793237163,11172 "ci_high": 0.9994694064944668,11173 "n_items": 853,11174 "n_groups": 9111175 },11176 "placeholders_exact": {11177 "mean": 1.0,11178 "ci_low": 1.0,11179 "ci_high": 1.0,11180 "n_items": 853,11181 "n_groups": 9111182 }11183 }11184 },11185 "by_discipline": {11186 "biomedicine": {11187 "n": 438,11188 "chrf": {11189 "mean": 63.83236421095725,11190 "ci_low": 57.709266993831996,11191 "ci_high": 68.55241873796118,11192 "n_items": 438,11193 "n_groups": 2211194 },11195 "edit_sim": {11196 "mean": 0.6443178352000897,11197 "ci_low": 0.5915658755067933,11198 "ci_high": 0.6856997638077635,11199 "n_items": 438,11200 "n_groups": 2211201 },11202 "rougeL": {11203 "mean": 0.6450234906463694,11204 "ci_low": 0.5888436213769135,11205 "ci_high": 0.687068093376276,11206 "n_items": 438,11207 "n_groups": 2211208 },11209 "exact_match": {11210 "mean": 0.0,11211 "ci_low": 0.0,11212 "ci_high": 0.0,11213 "n_items": 438,11214 "n_groups": 2211215 },11216 "number_recall": {11217 "mean": 0.9915688193085453,11218 "ci_low": 0.9842573120414913,11219 "ci_high": 1.0,11220 "n_items": 438,11221 "n_groups": 2211222 },11223 "placeholders_exact": {11224 "mean": 0.9931506849315068,11225 "ci_low": 0.985172981878089,11226 "ci_high": 1.0,11227 "n_items": 438,11228 "n_groups": 2211229 }11230 },11231 "chemistry": {11232 "n": 183,11233 "chrf": {11234 "mean": 65.10961700561303,11235 "ci_low": 65.10961700561303,11236 "ci_high": 65.10961700561303,11237 "n_items": 183,11238 "n_groups": 111239 },11240 "edit_sim": {11241 "mean": 0.6518281183123898,11242 "ci_low": 0.6518281183123898,11243 "ci_high": 0.6518281183123898,11244 "n_items": 183,11245 "n_groups": 111246 },11247 "rougeL": {11248 "mean": 0.6608452388371402,11249 "ci_low": 0.6608452388371402,11250 "ci_high": 0.6608452388371402,11251 "n_items": 183,11252 "n_groups": 111253 },11254 "exact_match": {11255 "mean": 0.0,11256 "ci_low": 0.0,11257 "ci_high": 0.0,11258 "n_items": 183,11259 "n_groups": 111260 },11261 "number_recall": {11262 "mean": 0.9936247723132968,11263 "ci_low": 0.9936247723132968,11264 "ci_high": 0.9936247723132968,11265 "n_items": 183,11266 "n_groups": 111267 },11268 "placeholders_exact": {11269 "mean": 1.0,11270 "ci_low": 1.0,11271 "ci_high": 1.0,11272 "n_items": 183,11273 "n_groups": 111274 }11275 },11276 "earth_sciences": {11277 "n": 101,11278 "chrf": {11279 "mean": 61.66435956162898,11280 "ci_low": 61.66435956162898,11281 "ci_high": 61.66435956162898,11282 "n_items": 101,11283 "n_groups": 111284 },11285 "edit_sim": {11286 "mean": 0.6118765337794102,11287 "ci_low": 0.6118765337794102,11288 "ci_high": 0.6118765337794102,11289 "n_items": 101,11290 "n_groups": 111291 },11292 "rougeL": {11293 "mean": 0.6235483305862741,11294 "ci_low": 0.6235483305862741,11295 "ci_high": 0.6235483305862741,11296 "n_items": 101,11297 "n_groups": 111298 },11299 "exact_match": {11300 "mean": 0.0,11301 "ci_low": 0.0,11302 "ci_high": 0.0,11303 "n_items": 101,11304 "n_groups": 111305 },11306 "number_recall": {11307 "mean": 0.9851485148514851,11308 "ci_low": 0.9851485148514851,11309 "ci_high": 0.9851485148514851,11310 "n_items": 101,11311 "n_groups": 111312 },11313 "placeholders_exact": {11314 "mean": 1.0,11315 "ci_low": 1.0,11316 "ci_high": 1.0,11317 "n_items": 101,11318 "n_groups": 111319 }11320 },11321 "economics": {11322 "n": 569,11323 "chrf": {11324 "mean": 68.04840812676977,11325 "ci_low": 62.99469086118773,11326 "ci_high": 71.41381840403905,11327 "n_items": 569,11328 "n_groups": 811329 },11330 "edit_sim": {11331 "mean": 0.6788470324404268,11332 "ci_low": 0.6391493920725397,11333 "ci_high": 0.7080798485631659,11334 "n_items": 569,11335 "n_groups": 811336 },11337 "rougeL": {11338 "mean": 0.6855382238216066,11339 "ci_low": 0.6435226914477156,11340 "ci_high": 0.7175250842875173,11341 "n_items": 569,11342 "n_groups": 811343 },11344 "exact_match": {11345 "mean": 0.0,11346 "ci_low": 0.0,11347 "ci_high": 0.0,11348 "n_items": 569,11349 "n_groups": 811350 },11351 "number_recall": {11352 "mean": 0.9943886517700228,11353 "ci_low": 0.992765200586458,11354 "ci_high": 0.9986263736263737,11355 "n_items": 569,11356 "n_groups": 811357 },11358 "placeholders_exact": {11359 "mean": 1.0,11360 "ci_low": 1.0,11361 "ci_high": 1.0,11362 "n_items": 569,11363 "n_groups": 811364 }11365 },11366 "engineering": {11367 "n": 167,11368 "chrf": {11369 "mean": 60.34666162054735,11370 "ci_low": 56.6681642643415,11371 "ci_high": 61.733055842682994,11372 "n_items": 167,11373 "n_groups": 811374 },11375 "edit_sim": {11376 "mean": 0.605373809474376,11377 "ci_low": 0.5799882261218768,11378 "ci_high": 0.6181254580912291,11379 "n_items": 167,11380 "n_groups": 811381 },11382 "rougeL": {11383 "mean": 0.61725308625913,11384 "ci_low": 0.5811817140484695,11385 "ci_high": 0.634051644256811,11386 "n_items": 167,11387 "n_groups": 811388 },11389 "exact_match": {11390 "mean": 0.0,11391 "ci_low": 0.0,11392 "ci_high": 0.0,11393 "n_items": 167,11394 "n_groups": 811395 },11396 "number_recall": {11397 "mean": 0.9916167664670659,11398 "ci_low": 0.9769230769230769,11399 "ci_high": 1.0,11400 "n_items": 167,11401 "n_groups": 811402 },11403 "placeholders_exact": {11404 "mean": 1.0,11405 "ci_low": 1.0,11406 "ci_high": 1.0,11407 "n_items": 167,11408 "n_groups": 811409 }11410 },11411 "finance": {11412 "n": 75,11413 "chrf": {11414 "mean": 58.026231801534934,11415 "ci_low": 57.880526061990274,11416 "ci_high": 58.661092523836565,11417 "n_items": 75,11418 "n_groups": 211419 },11420 "edit_sim": {11421 "mean": 0.5940698289636553,11422 "ci_low": 0.5939034073190748,11423 "ci_high": 0.5947949518436136,11424 "n_items": 75,11425 "n_groups": 211426 },11427 "rougeL": {11428 "mean": 0.5963928572178044,11429 "ci_low": 0.5930600702726705,11430 "ci_high": 0.5971577591396383,11431 "n_items": 75,11432 "n_groups": 211433 },11434 "exact_match": {11435 "mean": 0.0,11436 "ci_low": 0.0,11437 "ci_high": 0.0,11438 "n_items": 75,11439 "n_groups": 211440 },11441 "number_recall": {11442 "mean": 1.0,11443 "ci_low": 1.0,11444 "ci_high": 1.0,11445 "n_items": 75,11446 "n_groups": 211447 },11448 "placeholders_exact": {11449 "mean": 1.0,11450 "ci_low": 1.0,11451 "ci_high": 1.0,11452 "n_items": 75,11453 "n_groups": 211454 }11455 },11456 "general_reference": {11457 "n": 256,11458 "chrf": {11459 "mean": 62.45534155361559,11460 "ci_low": 59.39293574030444,11461 "ci_high": 64.76319507856958,11462 "n_items": 256,11463 "n_groups": 1211464 },11465 "edit_sim": {11466 "mean": 0.6449321526765244,11467 "ci_low": 0.6048927235359998,11468 "ci_high": 0.6696753481425138,11469 "n_items": 256,11470 "n_groups": 1211471 },11472 "rougeL": {11473 "mean": 0.6490059174338021,11474 "ci_low": 0.6052909254298476,11475 "ci_high": 0.6729177494125403,11476 "n_items": 256,11477 "n_groups": 1211478 },11479 "exact_match": {11480 "mean": 0.0,11481 "ci_low": 0.0,11482 "ci_high": 0.0,11483 "n_items": 256,11484 "n_groups": 1211485 },11486 "number_recall": {11487 "mean": 1.0,11488 "ci_low": 1.0,11489 "ci_high": 1.0,11490 "n_items": 256,11491 "n_groups": 1211492 },11493 "placeholders_exact": {11494 "mean": 1.0,11495 "ci_low": 1.0,11496 "ci_high": 1.0,11497 "n_items": 256,11498 "n_groups": 1211499 }11500 },11501 "humanities": {11502 "n": 253,11503 "chrf": {11504 "mean": 63.1402683084029,11505 "ci_low": 59.79344416682399,11506 "ci_high": 66.71583069534853,11507 "n_items": 253,11508 "n_groups": 911509 },11510 "edit_sim": {11511 "mean": 0.6547168998132621,11512 "ci_low": 0.6235622145527817,11513 "ci_high": 0.6964731994553018,11514 "n_items": 253,11515 "n_groups": 911516 },11517 "rougeL": {11518 "mean": 0.6603083280083369,11519 "ci_low": 0.6299439622123729,11520 "ci_high": 0.6978046188763944,11521 "n_items": 253,11522 "n_groups": 911523 },11524 "exact_match": {11525 "mean": 0.0,11526 "ci_low": 0.0,11527 "ci_high": 0.0,11528 "n_items": 253,11529 "n_groups": 911530 },11531 "number_recall": {11532 "mean": 1.0,11533 "ci_low": 1.0,11534 "ci_high": 1.0,11535 "n_items": 253,11536 "n_groups": 911537 },11538 "placeholders_exact": {11539 "mean": 1.0,11540 "ci_low": 1.0,11541 "ci_high": 1.0,11542 "n_items": 253,11543 "n_groups": 911544 }11545 },11546 "life_sciences": {11547 "n": 233,11548 "chrf": {11549 "mean": 60.76097049769207,11550 "ci_low": 58.18972320917828,11551 "ci_high": 63.717021483104205,11552 "n_items": 233,11553 "n_groups": 811554 },11555 "edit_sim": {11556 "mean": 0.6205494792687524,11557 "ci_low": 0.5983713643713532,11558 "ci_high": 0.6455327887568361,11559 "n_items": 233,11560 "n_groups": 811561 },11562 "rougeL": {11563 "mean": 0.6302974946668842,11564 "ci_low": 0.6057913938235333,11565 "ci_high": 0.6588712987652254,11566 "n_items": 233,11567 "n_groups": 811568 },11569 "exact_match": {11570 "mean": 0.0,11571 "ci_low": 0.0,11572 "ci_high": 0.0,11573 "n_items": 233,11574 "n_groups": 811575 },11576 "number_recall": {11577 "mean": 0.9989270386266095,11578 "ci_low": 0.9965112203868725,11579 "ci_high": 1.0,11580 "n_items": 233,11581 "n_groups": 811582 },11583 "placeholders_exact": {11584 "mean": 1.0,11585 "ci_low": 1.0,11586 "ci_high": 1.0,11587 "n_items": 233,11588 "n_groups": 811589 }11590 },11591 "social_sciences": {11592 "n": 299,11593 "chrf": {11594 "mean": 59.8149188662743,11595 "ci_low": 57.285339680624354,11596 "ci_high": 61.994356858952195,11597 "n_items": 299,11598 "n_groups": 2111599 },11600 "edit_sim": {11601 "mean": 0.6294227549272443,11602 "ci_low": 0.6046063676186323,11603 "ci_high": 0.6521080735683898,11604 "n_items": 299,11605 "n_groups": 2111606 },11607 "rougeL": {11608 "mean": 0.6311724482730409,11609 "ci_low": 0.6032435165196949,11610 "ci_high": 0.6569789481172559,11611 "n_items": 299,11612 "n_groups": 2111613 },11614 "exact_match": {11615 "mean": 0.0,11616 "ci_low": 0.0,11617 "ci_high": 0.0,11618 "n_items": 299,11619 "n_groups": 2111620 },11621 "number_recall": {11622 "mean": 1.0,11623 "ci_low": 1.0,11624 "ci_high": 1.0,11625 "n_items": 299,11626 "n_groups": 2111627 },11628 "placeholders_exact": {11629 "mean": 1.0,11630 "ci_low": 1.0,11631 "ci_high": 1.0,11632 "n_items": 299,11633 "n_groups": 2111634 }11635 }11636 },11637 "by_era": {11638 "1900-1949": {11639 "n": 74,11640 "chrf": {11641 "mean": 64.78861865571997,11642 "ci_low": 62.63979800290357,11643 "ci_high": 70.62422456406122,11644 "n_items": 74,11645 "n_groups": 511646 },11647 "edit_sim": {11648 "mean": 0.6740493272066461,11649 "ci_low": 0.6100788115623055,11650 "ci_high": 0.699969873754421,11651 "n_items": 74,11652 "n_groups": 511653 },11654 "rougeL": {11655 "mean": 0.6647762068981666,11656 "ci_low": 0.5902138074109629,11657 "ci_high": 0.6900604515704083,11658 "n_items": 74,11659 "n_groups": 511660 },11661 "exact_match": {11662 "mean": 0.0,11663 "ci_low": 0.0,11664 "ci_high": 0.0,11665 "n_items": 74,11666 "n_groups": 511667 },11668 "number_recall": {11669 "mean": 0.9891891891891892,11670 "ci_low": 0.92,11671 "ci_high": 1.0,11672 "n_items": 74,11673 "n_groups": 511674 },11675 "placeholders_exact": {11676 "mean": 1.0,11677 "ci_low": 1.0,11678 "ci_high": 1.0,11679 "n_items": 74,11680 "n_groups": 511681 }11682 },11683 "2010-2017": {11684 "n": 527,11685 "chrf": {11686 "mean": 70.75433242366606,11687 "ci_low": 67.09235950775532,11688 "ci_high": 73.35813784114804,11689 "n_items": 527,11690 "n_groups": 411691 },11692 "edit_sim": {11693 "mean": 0.6994812592666357,11694 "ci_low": 0.6659138571348107,11695 "ci_high": 0.7238163791763452,11696 "n_items": 527,11697 "n_groups": 411698 },11699 "rougeL": {11700 "mean": 0.7053248671656992,11701 "ci_low": 0.6667669714951987,11702 "ci_high": 0.733643762470089,11703 "n_items": 527,11704 "n_groups": 411705 },11706 "exact_match": {11707 "mean": 0.0,11708 "ci_low": 0.0,11709 "ci_high": 0.0,11710 "n_items": 527,11711 "n_groups": 411712 },11713 "number_recall": {11714 "mean": 0.9894686907020874,11715 "ci_low": 0.9822580645161291,11716 "ci_high": 0.9946236559139785,11717 "n_items": 527,11718 "n_groups": 411719 },11720 "placeholders_exact": {11721 "mean": 0.9943074003795066,11722 "ci_low": 0.9806451612903225,11723 "ci_high": 1.0,11724 "n_items": 527,11725 "n_groups": 411726 }11727 },11728 "pre1900": {11729 "n": 1973,11730 "chrf": {11731 "mean": 61.416254977680694,11732 "ci_low": 60.040587936645956,11733 "ci_high": 62.65807338155982,11734 "n_items": 1973,11735 "n_groups": 8311736 },11737 "edit_sim": {11738 "mean": 0.6286047022187667,11739 "ci_low": 0.6164049009738919,11740 "ci_high": 0.640629332495752,11741 "n_items": 1973,11742 "n_groups": 8311743 },11744 "rougeL": {11745 "mean": 0.6346675539199302,11746 "ci_low": 0.6213015014034718,11747 "ci_high": 0.6469327113809763,11748 "n_items": 1973,11749 "n_groups": 8311750 },11751 "exact_match": {11752 "mean": 0.0,11753 "ci_low": 0.0,11754 "ci_high": 0.0,11755 "n_items": 1973,11756 "n_groups": 8311757 },11758 "number_recall": {11759 "mean": 0.9975406077281395,11760 "ci_low": 0.995691333893438,11761 "ci_high": 0.9992808480100003,11762 "n_items": 1973,11763 "n_groups": 8311764 },11765 "placeholders_exact": {11766 "mean": 1.0,11767 "ci_low": 1.0,11768 "ci_high": 1.0,11769 "n_items": 1973,11770 "n_groups": 8311771 }11772 }11773 },11774 "by_role": {11775 "abstract": {11776 "n": 36,11777 "chrf": {11778 "mean": 66.12601654203657,11779 "ci_low": 62.124671757491285,11780 "ci_high": 70.46254537722888,11781 "n_items": 36,11782 "n_groups": 611783 },11784 "edit_sim": {11785 "mean": 0.6485866928044609,11786 "ci_low": 0.5994233946586304,11787 "ci_high": 0.7020164914072304,11788 "n_items": 36,11789 "n_groups": 611790 },11791 "rougeL": {11792 "mean": 0.6287432433653445,11793 "ci_low": 0.5745602549773645,11794 "ci_high": 0.6823402051394334,11795 "n_items": 36,11796 "n_groups": 611797 },11798 "exact_match": {11799 "mean": 0.0,11800 "ci_low": 0.0,11801 "ci_high": 0.0,11802 "n_items": 36,11803 "n_groups": 611804 },11805 "number_recall": {11806 "mean": 0.9777777777777779,11807 "ci_low": 0.9333333333333333,11808 "ci_high": 1.0,11809 "n_items": 36,11810 "n_groups": 611811 },11812 "placeholders_exact": {11813 "mean": 1.0,11814 "ci_low": 1.0,11815 "ci_high": 1.0,11816 "n_items": 36,11817 "n_groups": 611818 }11819 },11820 "chapter": {11821 "n": 819,11822 "chrf": {11823 "mean": 62.04619485924869,11824 "ci_low": 60.63089216313005,11825 "ci_high": 63.35698907139593,11826 "n_items": 819,11827 "n_groups": 5211828 },11829 "edit_sim": {11830 "mean": 0.6333203388994125,11831 "ci_low": 0.6187970927546635,11832 "ci_high": 0.6476254268817664,11833 "n_items": 819,11834 "n_groups": 5211835 },11836 "rougeL": {11837 "mean": 0.6416722727399738,11838 "ci_low": 0.6261310458106878,11839 "ci_high": 0.6556423793982311,11840 "n_items": 819,11841 "n_groups": 5211842 },11843 "exact_match": {11844 "mean": 0.0,11845 "ci_low": 0.0,11846 "ci_high": 0.0,11847 "n_items": 819,11848 "n_groups": 5211849 },11850 "number_recall": {11851 "mean": 0.9971713471713473,11852 "ci_low": 0.9947148595580532,11853 "ci_high": 0.9995636998254799,11854 "n_items": 819,11855 "n_groups": 5211856 },11857 "placeholders_exact": {11858 "mean": 1.0,11859 "ci_low": 1.0,11860 "ci_high": 1.0,11861 "n_items": 819,11862 "n_groups": 5211863 }11864 },11865 "conclusion": {11866 "n": 104,11867 "chrf": {11868 "mean": 69.96724274594483,11869 "ci_low": 62.884552974960904,11870 "ci_high": 74.06223312435552,11871 "n_items": 104,11872 "n_groups": 311873 },11874 "edit_sim": {11875 "mean": 0.6888547224150087,11876 "ci_low": 0.6183658974532205,11877 "ci_high": 0.7333225839487811,11878 "n_items": 104,11879 "n_groups": 311880 },11881 "rougeL": {11882 "mean": 0.685818730770942,11883 "ci_low": 0.6075511425249016,11884 "ci_high": 0.7354856988381951,11885 "n_items": 104,11886 "n_groups": 311887 },11888 "exact_match": {11889 "mean": 0.0,11890 "ci_low": 0.0,11891 "ci_high": 0.0,11892 "n_items": 104,11893 "n_groups": 311894 },11895 "number_recall": {11896 "mean": 1.0,11897 "ci_low": 1.0,11898 "ci_high": 1.0,11899 "n_items": 104,11900 "n_groups": 311901 },11902 "placeholders_exact": {11903 "mean": 1.0,11904 "ci_low": 1.0,11905 "ci_high": 1.0,11906 "n_items": 104,11907 "n_groups": 311908 }11909 },11910 "data": {11911 "n": 11,11912 "chrf": {11913 "mean": 77.06266622786335,11914 "ci_low": 77.06266622786335,11915 "ci_high": 77.06266622786335,11916 "n_items": 11,11917 "n_groups": 111918 },11919 "edit_sim": {11920 "mean": 0.7838096341826869,11921 "ci_low": 0.7838096341826869,11922 "ci_high": 0.7838096341826869,11923 "n_items": 11,11924 "n_groups": 111925 },11926 "rougeL": {11927 "mean": 0.7992803297321672,11928 "ci_low": 0.7992803297321672,11929 "ci_high": 0.7992803297321672,11930 "n_items": 11,11931 "n_groups": 111932 },11933 "exact_match": {11934 "mean": 0.0,11935 "ci_low": 0.0,11936 "ci_high": 0.0,11937 "n_items": 11,11938 "n_groups": 111939 },11940 "number_recall": {11941 "mean": 1.0,11942 "ci_low": 1.0,11943 "ci_high": 1.0,11944 "n_items": 11,11945 "n_groups": 111946 },11947 "placeholders_exact": {11948 "mean": 1.0,11949 "ci_low": 1.0,11950 "ci_high": 1.0,11951 "n_items": 11,11952 "n_groups": 111953 }11954 },11955 "introduction": {11956 "n": 574,11957 "chrf": {11958 "mean": 62.183453774433225,11959 "ci_low": 59.24841156554029,11960 "ci_high": 64.2428781543005,11961 "n_items": 574,11962 "n_groups": 2311963 },11964 "edit_sim": {11965 "mean": 0.637477444081373,11966 "ci_low": 0.6094530617308931,11967 "ci_high": 0.6577223381646757,11968 "n_items": 574,11969 "n_groups": 2311970 },11971 "rougeL": {11972 "mean": 0.6410559483176941,11973 "ci_low": 0.6128006203403118,11974 "ci_high": 0.6620430059494873,11975 "n_items": 574,11976 "n_groups": 2311977 },11978 "exact_match": {11979 "mean": 0.0,11980 "ci_low": 0.0,11981 "ci_high": 0.0,11982 "n_items": 574,11983 "n_groups": 2311984 },11985 "number_recall": {11986 "mean": 0.9975734196117472,11987 "ci_low": 0.9925925781520759,11988 "ci_high": 1.0,11989 "n_items": 574,11990 "n_groups": 2311991 },11992 "placeholders_exact": {11993 "mean": 1.0,11994 "ci_low": 1.0,11995 "ci_high": 1.0,11996 "n_items": 574,11997 "n_groups": 2311998 }11999 },12000 "methods": {12001 "n": 93,12002 "chrf": {12003 "mean": 70.83962481661973,12004 "ci_low": 67.74673427028459,12005 "ci_high": 78.0107652865983,12006 "n_items": 93,12007 "n_groups": 312008 },12009 "edit_sim": {12010 "mean": 0.7006054985747661,12011 "ci_low": 0.6738123295137316,12012 "ci_high": 0.7990459642899433,12013 "n_items": 93,12014 "n_groups": 312015 },12016 "rougeL": {12017 "mean": 0.7203563031902656,12018 "ci_low": 0.6861083211895005,12019 "ci_high": 0.8142416771730909,12020 "n_items": 93,12021 "n_groups": 312022 },12023 "exact_match": {12024 "mean": 0.0,12025 "ci_low": 0.0,12026 "ci_high": 0.0,12027 "n_items": 93,12028 "n_groups": 312029 },12030 "number_recall": {12031 "mean": 0.9725806451612904,12032 "ci_low": 0.9583333333333334,12033 "ci_high": 0.983673469387755,12034 "n_items": 93,12035 "n_groups": 312036 },12037 "placeholders_exact": {12038 "mean": 1.0,12039 "ci_low": 1.0,12040 "ci_high": 1.0,12041 "n_items": 93,12042 "n_groups": 312043 }12044 },12045 "other": {12046 "n": 163,12047 "chrf": {12048 "mean": 65.32462081089328,12049 "ci_low": 59.942533253629186,12050 "ci_high": 70.16646919213463,12051 "n_items": 163,12052 "n_groups": 912053 },12054 "edit_sim": {12055 "mean": 0.6706004836834842,12056 "ci_low": 0.637891540717037,12057 "ci_high": 0.6992919510711274,12058 "n_items": 163,12059 "n_groups": 912060 },12061 "rougeL": {12062 "mean": 0.6776563836160551,12063 "ci_low": 0.6456867308000251,12064 "ci_high": 0.7082219385360388,12065 "n_items": 163,12066 "n_groups": 912067 },12068 "exact_match": {12069 "mean": 0.0,12070 "ci_low": 0.0,12071 "ci_high": 0.0,12072 "n_items": 163,12073 "n_groups": 912074 },12075 "number_recall": {12076 "mean": 0.992988606485539,12077 "ci_low": 0.9848484848484849,12078 "ci_high": 0.999275197615981,12079 "n_items": 163,12080 "n_groups": 912081 },12082 "placeholders_exact": {12083 "mean": 1.0,12084 "ci_low": 1.0,12085 "ci_high": 1.0,12086 "n_items": 163,12087 "n_groups": 912088 }12089 },12090 "preface": {12091 "n": 562,12092 "chrf": {12093 "mean": 60.32249661327005,12094 "ci_low": 58.52074335306822,12095 "ci_high": 62.19347377097658,12096 "n_items": 562,12097 "n_groups": 4812098 },12099 "edit_sim": {12100 "mean": 0.6172854471298831,12101 "ci_low": 0.6001273670867374,12102 "ci_high": 0.6358293594916343,12103 "n_items": 562,12104 "n_groups": 4812105 },12106 "rougeL": {12107 "mean": 0.6212763815591538,12108 "ci_low": 0.6015362164665407,12109 "ci_high": 0.6417107189833765,12110 "n_items": 562,12111 "n_groups": 4812112 },12113 "exact_match": {12114 "mean": 0.0,12115 "ci_low": 0.0,12116 "ci_high": 0.0,12117 "n_items": 562,12118 "n_groups": 4812119 },12120 "number_recall": {12121 "mean": 0.998220640569395,12122 "ci_low": 0.994140338337818,12123 "ci_high": 1.0,12124 "n_items": 562,12125 "n_groups": 4812126 },12127 "placeholders_exact": {12128 "mean": 1.0,12129 "ci_low": 1.0,12130 "ci_high": 1.0,12131 "n_items": 562,12132 "n_groups": 4812133 }12134 },12135 "related_work": {12136 "n": 18,12137 "chrf": {12138 "mean": 71.55676369462033,12139 "ci_low": 71.55676369462033,12140 "ci_high": 71.55676369462033,12141 "n_items": 18,12142 "n_groups": 112143 },12144 "edit_sim": {12145 "mean": 0.7089577805535883,12146 "ci_low": 0.7089577805535883,12147 "ci_high": 0.7089577805535883,12148 "n_items": 18,12149 "n_groups": 112150 },12151 "rougeL": {12152 "mean": 0.6884817559113801,12153 "ci_low": 0.6884817559113801,12154 "ci_high": 0.6884817559113801,12155 "n_items": 18,12156 "n_groups": 112157 },12158 "exact_match": {12159 "mean": 0.0,12160 "ci_low": 0.0,12161 "ci_high": 0.0,12162 "n_items": 18,12163 "n_groups": 112164 },12165 "number_recall": {12166 "mean": 1.0,12167 "ci_low": 1.0,12168 "ci_high": 1.0,12169 "n_items": 18,12170 "n_groups": 112171 },12172 "placeholders_exact": {12173 "mean": 1.0,12174 "ci_low": 1.0,12175 "ci_high": 1.0,12176 "n_items": 18,12177 "n_groups": 112178 }12179 },12180 "results": {12181 "n": 158,12182 "chrf": {12183 "mean": 70.49351065960138,12184 "ci_low": 68.36920324045707,12185 "ci_high": 74.8332606198953,12186 "n_items": 158,12187 "n_groups": 312188 },12189 "edit_sim": {12190 "mean": 0.6942220865833498,12191 "ci_low": 0.674041572511331,12192 "ci_high": 0.7136173225634238,12193 "n_items": 158,12194 "n_groups": 312195 },12196 "rougeL": {12197 "mean": 0.7024221856228188,12198 "ci_low": 0.6865311968413312,12199 "ci_high": 0.7308161369361468,12200 "n_items": 158,12201 "n_groups": 312202 },12203 "exact_match": {12204 "mean": 0.0,12205 "ci_low": 0.0,12206 "ci_high": 0.0,12207 "n_items": 158,12208 "n_groups": 312209 },12210 "number_recall": {12211 "mean": 0.9873417721518988,12212 "ci_low": 0.974025974025974,12213 "ci_high": 1.0,12214 "n_items": 158,12215 "n_groups": 312216 },12217 "placeholders_exact": {12218 "mean": 0.9810126582278481,12219 "ci_low": 0.961038961038961,12220 "ci_high": 1.0,12221 "n_items": 158,12222 "n_groups": 312223 }12224 },12225 "theory": {12226 "n": 36,12227 "chrf": {12228 "mean": 74.41580515035247,12229 "ci_low": 66.06397254675633,12230 "ci_high": 76.08617167107171,12231 "n_items": 36,12232 "n_groups": 212233 },12234 "edit_sim": {12235 "mean": 0.7417522663885652,12236 "ci_low": 0.6701246906529602,12237 "ci_high": 0.7560777815356862,12238 "n_items": 36,12239 "n_groups": 212240 },12241 "rougeL": {12242 "mean": 0.7463112221351276,12243 "ci_low": 0.6752886114386379,12244 "ci_high": 0.7605157442744255,12245 "n_items": 36,12246 "n_groups": 212247 },12248 "exact_match": {12249 "mean": 0.0,12250 "ci_low": 0.0,12251 "ci_high": 0.0,12252 "n_items": 36,12253 "n_groups": 212254 },12255 "number_recall": {12256 "mean": 1.0,12257 "ci_low": 1.0,12258 "ci_high": 1.0,12259 "n_items": 36,12260 "n_groups": 212261 },12262 "placeholders_exact": {12263 "mean": 1.0,12264 "ci_low": 1.0,12265 "ci_high": 1.0,12266 "n_items": 36,12267 "n_groups": 212268 }12269 }12270 }12271 },12272 "htr-m3tokenonly-tiny": {12273 "overall": {12274 "n": 2574,12275 "chrf": {12276 "mean": 63.39592691705847,12277 "ci_low": 61.28663419440997,12278 "ci_high": 65.2543359813689,12279 "n_items": 2574,12280 "n_groups": 9212281 },12282 "edit_sim": {12283 "mean": 0.6451352247665855,12284 "ci_low": 0.6275288283141465,12285 "ci_high": 0.6610368124153633,12286 "n_items": 2574,12287 "n_groups": 9212288 },12289 "rougeL": {12290 "mean": 0.6498499855439103,12291 "ci_low": 0.6319218941093556,12292 "ci_high": 0.6659631338163804,12293 "n_items": 2574,12294 "n_groups": 9212295 },12296 "exact_match": {12297 "mean": 0.0,12298 "ci_low": 0.0,12299 "ci_high": 0.0,12300 "n_items": 2574,12301 "n_groups": 9212302 },12303 "number_recall": {12304 "mean": 0.9947146288055378,12305 "ci_low": 0.9890670905099801,12306 "ci_high": 0.9984703346454866,12307 "n_items": 2574,12308 "n_groups": 9212309 },12310 "placeholders_exact": {12311 "mean": 0.9980574980574981,12312 "ci_low": 0.9937576727549539,12313 "ci_high": 1.0,12314 "n_items": 2574,12315 "n_groups": 9212316 }12317 },12318 "by_variant": {12319 "A": {12320 "n": 436,12321 "chrf": {12322 "mean": 62.53439114766993,12323 "ci_low": 60.288730329649475,12324 "ci_high": 64.36677496089588,12325 "n_items": 436,12326 "n_groups": 9112327 },12328 "edit_sim": {12329 "mean": 0.6353253994300287,12330 "ci_low": 0.6160489372862467,12331 "ci_high": 0.6510451779396678,12332 "n_items": 436,12333 "n_groups": 9112334 },12335 "rougeL": {12336 "mean": 0.6385548412796054,12337 "ci_low": 0.6188489050443187,12338 "ci_high": 0.654871380965828,12339 "n_items": 436,12340 "n_groups": 9112341 },12342 "exact_match": {12343 "mean": 0.0,12344 "ci_low": 0.0,12345 "ci_high": 0.0,12346 "n_items": 436,12347 "n_groups": 9112348 },12349 "number_recall": {12350 "mean": 0.992335626911315,12351 "ci_low": 0.9853892550116019,12352 "ci_high": 0.9985100770491124,12353 "n_items": 436,12354 "n_groups": 9112355 },12356 "placeholders_exact": {12357 "mean": 0.9954128440366973,12358 "ci_low": 0.9860772638034819,12359 "ci_high": 1.0,12360 "n_items": 436,12361 "n_groups": 9112362 }12363 },12364 "B": {12365 "n": 416,12366 "chrf": {12367 "mean": 68.50511107629369,12368 "ci_low": 65.94983123452545,12369 "ci_high": 70.85712327697055,12370 "n_items": 416,12371 "n_groups": 9012372 },12373 "edit_sim": {12374 "mean": 0.6987013599177172,12375 "ci_low": 0.6751506671320837,12376 "ci_high": 0.7207675838455384,12377 "n_items": 416,12378 "n_groups": 9012379 },12380 "rougeL": {12381 "mean": 0.7054394066011427,12382 "ci_low": 0.681852332827468,12383 "ci_high": 0.7271904064285997,12384 "n_items": 416,12385 "n_groups": 9012386 },12387 "exact_match": {12388 "mean": 0.0,12389 "ci_low": 0.0,12390 "ci_high": 0.0,12391 "n_items": 416,12392 "n_groups": 9012393 },12394 "number_recall": {12395 "mean": 0.9957532051282052,12396 "ci_low": 0.9887799447174448,12397 "ci_high": 0.9997362166481808,12398 "n_items": 416,12399 "n_groups": 9012400 },12401 "placeholders_exact": {12402 "mean": 0.9975961538461539,12403 "ci_low": 0.992571931065287,12404 "ci_high": 1.0,12405 "n_items": 416,12406 "n_groups": 9012407 }12408 },12409 "C": {12410 "n": 438,12411 "chrf": {12412 "mean": 68.41341357584436,12413 "ci_low": 66.5411572231339,12414 "ci_high": 70.27127002499394,12415 "n_items": 438,12416 "n_groups": 9112417 },12418 "edit_sim": {12419 "mean": 0.7088971673920441,12420 "ci_low": 0.6917103196421268,12421 "ci_high": 0.7256626252772658,12422 "n_items": 438,12423 "n_groups": 9112424 },12425 "rougeL": {12426 "mean": 0.7248132334957487,12427 "ci_low": 0.7073697749297628,12428 "ci_high": 0.7423376525210785,12429 "n_items": 438,12430 "n_groups": 9112431 },12432 "exact_match": {12433 "mean": 0.0,12434 "ci_low": 0.0,12435 "ci_high": 0.0,12436 "n_items": 438,12437 "n_groups": 9112438 },12439 "number_recall": {12440 "mean": 0.9937456759374568,12441 "ci_low": 0.9884870533879747,12442 "ci_high": 0.997980720761424,12443 "n_items": 438,12444 "n_groups": 9112445 },12446 "placeholders_exact": {12447 "mean": 0.997716894977169,12448 "ci_low": 0.9928567166723492,12449 "ci_high": 1.0,12450 "n_items": 438,12451 "n_groups": 9112452 }12453 },12454 "D": {12455 "n": 431,12456 "chrf": {12457 "mean": 62.874949840704865,12458 "ci_low": 60.46769630545699,12459 "ci_high": 64.89624436349483,12460 "n_items": 431,12461 "n_groups": 9012462 },12463 "edit_sim": {12464 "mean": 0.645704738617924,12465 "ci_low": 0.6239440806584471,12466 "ci_high": 0.6626484108079463,12467 "n_items": 431,12468 "n_groups": 9012469 },12470 "rougeL": {12471 "mean": 0.6472276940406856,12472 "ci_low": 0.6255808007259696,12473 "ci_high": 0.665077794491405,12474 "n_items": 431,12475 "n_groups": 9012476 },12477 "exact_match": {12478 "mean": 0.0,12479 "ci_low": 0.0,12480 "ci_high": 0.0,12481 "n_items": 431,12482 "n_groups": 9012483 },12484 "number_recall": {12485 "mean": 0.9948024326794628,12486 "ci_low": 0.9894903017694279,12487 "ci_high": 0.9991511500547646,12488 "n_items": 431,12489 "n_groups": 9012490 },12491 "placeholders_exact": {12492 "mean": 1.0,12493 "ci_low": 1.0,12494 "ci_high": 1.0,12495 "n_items": 431,12496 "n_groups": 9012497 }12498 },12499 "E": {12500 "n": 853,12501 "chrf": {12502 "mean": 59.03143799393036,12503 "ci_low": 56.863125561641546,12504 "ci_high": 60.94076966657143,12505 "n_items": 853,12506 "n_groups": 9112507 },12508 "edit_sim": {12509 "mean": 0.590997335298813,12510 "ci_low": 0.5743334285964464,12511 "ci_high": 0.6071908743132722,12512 "n_items": 853,12513 "n_groups": 9112514 },12515 "rougeL": {12516 "mean": 0.5913456347518975,12517 "ci_low": 0.5736633336224108,12518 "ci_high": 0.6081470467256421,12519 "n_items": 853,12520 "n_groups": 9112521 },12522 "exact_match": {12523 "mean": 0.0,12524 "ci_low": 0.0,12525 "ci_high": 0.0,12526 "n_items": 853,12527 "n_groups": 9112528 },12529 "number_recall": {12530 "mean": 0.9958772958186792,12531 "ci_low": 0.9905997002672776,12532 "ci_high": 0.9994805991040261,12533 "n_items": 853,12534 "n_groups": 9112535 },12536 "placeholders_exact": {12537 "mean": 0.9988276670574443,12538 "ci_low": 0.9962546816479401,12539 "ci_high": 1.0,12540 "n_items": 853,12541 "n_groups": 9112542 }12543 }12544 },12545 "by_discipline": {12546 "biomedicine": {12547 "n": 438,12548 "chrf": {12549 "mean": 63.59703352825369,12550 "ci_low": 57.49659760903298,12551 "ci_high": 68.2984243775448,12552 "n_items": 438,12553 "n_groups": 2212554 },12555 "edit_sim": {12556 "mean": 0.6450736596561579,12557 "ci_low": 0.5893679206426707,12558 "ci_high": 0.6887849848862604,12559 "n_items": 438,12560 "n_groups": 2212561 },12562 "rougeL": {12563 "mean": 0.6436259094064497,12564 "ci_low": 0.5865523448717203,12565 "ci_high": 0.6858748696513864,12566 "n_items": 438,12567 "n_groups": 2212568 },12569 "exact_match": {12570 "mean": 0.0,12571 "ci_low": 0.0,12572 "ci_high": 0.0,12573 "n_items": 438,12574 "n_groups": 2212575 },12576 "number_recall": {12577 "mean": 0.9832952815829527,12578 "ci_low": 0.9651322442379754,12579 "ci_high": 1.0,12580 "n_items": 438,12581 "n_groups": 2212582 },12583 "placeholders_exact": {12584 "mean": 0.9885844748858448,12585 "ci_low": 0.9752883031301482,12586 "ci_high": 1.0,12587 "n_items": 438,12588 "n_groups": 2212589 }12590 },12591 "chemistry": {12592 "n": 183,12593 "chrf": {12594 "mean": 65.18866108316993,12595 "ci_low": 65.18866108316993,12596 "ci_high": 65.18866108316993,12597 "n_items": 183,12598 "n_groups": 112599 },12600 "edit_sim": {12601 "mean": 0.6525843213883675,12602 "ci_low": 0.6525843213883675,12603 "ci_high": 0.6525843213883675,12604 "n_items": 183,12605 "n_groups": 112606 },12607 "rougeL": {12608 "mean": 0.6611062481735207,12609 "ci_low": 0.6611062481735207,12610 "ci_high": 0.6611062481735207,12611 "n_items": 183,12612 "n_groups": 112613 },12614 "exact_match": {12615 "mean": 0.0,12616 "ci_low": 0.0,12617 "ci_high": 0.0,12618 "n_items": 183,12619 "n_groups": 112620 },12621 "number_recall": {12622 "mean": 0.9985096870342771,12623 "ci_low": 0.9985096870342771,12624 "ci_high": 0.9985096870342771,12625 "n_items": 183,12626 "n_groups": 112627 },12628 "placeholders_exact": {12629 "mean": 1.0,12630 "ci_low": 1.0,12631 "ci_high": 1.0,12632 "n_items": 183,12633 "n_groups": 112634 }12635 },12636 "earth_sciences": {12637 "n": 101,12638 "chrf": {12639 "mean": 61.64592506911477,12640 "ci_low": 61.64592506911477,12641 "ci_high": 61.64592506911477,12642 "n_items": 101,12643 "n_groups": 112644 },12645 "edit_sim": {12646 "mean": 0.6115384254674736,12647 "ci_low": 0.6115384254674736,12648 "ci_high": 0.6115384254674736,12649 "n_items": 101,12650 "n_groups": 112651 },12652 "rougeL": {12653 "mean": 0.6276521855606206,12654 "ci_low": 0.6276521855606206,12655 "ci_high": 0.6276521855606206,12656 "n_items": 101,12657 "n_groups": 112658 },12659 "exact_match": {12660 "mean": 0.0,12661 "ci_low": 0.0,12662 "ci_high": 0.0,12663 "n_items": 101,12664 "n_groups": 112665 },12666 "number_recall": {12667 "mean": 0.9876237623762376,12668 "ci_low": 0.9876237623762376,12669 "ci_high": 0.9876237623762376,12670 "n_items": 101,12671 "n_groups": 112672 },12673 "placeholders_exact": {12674 "mean": 1.0,12675 "ci_low": 1.0,12676 "ci_high": 1.0,12677 "n_items": 101,12678 "n_groups": 112679 }12680 },12681 "economics": {12682 "n": 569,12683 "chrf": {12684 "mean": 67.94156357506594,12685 "ci_low": 62.55666270617364,12686 "ci_high": 71.57920217338184,12687 "n_items": 569,12688 "n_groups": 812689 },12690 "edit_sim": {12691 "mean": 0.6790939555533044,12692 "ci_low": 0.6389139976683847,12693 "ci_high": 0.7107398089509138,12694 "n_items": 569,12695 "n_groups": 812696 },12697 "rougeL": {12698 "mean": 0.685044746738933,12699 "ci_low": 0.6437359733035541,12700 "ci_high": 0.720247128065242,12701 "n_items": 569,12702 "n_groups": 812703 },12704 "exact_match": {12705 "mean": 0.0,12706 "ci_low": 0.0,12707 "ci_high": 0.0,12708 "n_items": 569,12709 "n_groups": 812710 },12711 "number_recall": {12712 "mean": 0.9945252170208235,12713 "ci_low": 0.9937657556366126,12714 "ci_high": 0.9973776223776224,12715 "n_items": 569,12716 "n_groups": 812717 },12718 "placeholders_exact": {12719 "mean": 1.0,12720 "ci_low": 1.0,12721 "ci_high": 1.0,12722 "n_items": 569,12723 "n_groups": 812724 }12725 },12726 "engineering": {12727 "n": 167,12728 "chrf": {12729 "mean": 60.14687654087614,12730 "ci_low": 56.547089333093965,12731 "ci_high": 61.661364819327375,12732 "n_items": 167,12733 "n_groups": 812734 },12735 "edit_sim": {12736 "mean": 0.6075871241261758,12737 "ci_low": 0.5819430005959161,12738 "ci_high": 0.6203156984829545,12739 "n_items": 167,12740 "n_groups": 812741 },12742 "rougeL": {12743 "mean": 0.6182406770694479,12744 "ci_low": 0.5843478027402599,12745 "ci_high": 0.6348881119532115,12746 "n_items": 167,12747 "n_groups": 812748 },12749 "exact_match": {12750 "mean": 0.0,12751 "ci_low": 0.0,12752 "ci_high": 0.0,12753 "n_items": 167,12754 "n_groups": 812755 },12756 "number_recall": {12757 "mean": 0.9916167664670659,12758 "ci_low": 0.9769230769230769,12759 "ci_high": 1.0,12760 "n_items": 167,12761 "n_groups": 812762 },12763 "placeholders_exact": {12764 "mean": 1.0,12765 "ci_low": 1.0,12766 "ci_high": 1.0,12767 "n_items": 167,12768 "n_groups": 812769 }12770 },12771 "finance": {12772 "n": 75,12773 "chrf": {12774 "mean": 57.77540457959065,12775 "ci_low": 57.48312521113052,12776 "ci_high": 59.04890754216699,12777 "n_items": 75,12778 "n_groups": 212779 },12780 "edit_sim": {12781 "mean": 0.5899787269868279,12782 "ci_low": 0.5896798748282988,12783 "ci_high": 0.5912808685347049,12784 "n_items": 75,12785 "n_groups": 212786 },12787 "rougeL": {12788 "mean": 0.5913767231820873,12789 "ci_low": 0.591047447782249,12790 "ci_high": 0.5928114231385252,12791 "n_items": 75,12792 "n_groups": 212793 },12794 "exact_match": {12795 "mean": 0.0,12796 "ci_low": 0.0,12797 "ci_high": 0.0,12798 "n_items": 75,12799 "n_groups": 212800 },12801 "number_recall": {12802 "mean": 1.0,12803 "ci_low": 1.0,12804 "ci_high": 1.0,12805 "n_items": 75,12806 "n_groups": 212807 },12808 "placeholders_exact": {12809 "mean": 1.0,12810 "ci_low": 1.0,12811 "ci_high": 1.0,12812 "n_items": 75,12813 "n_groups": 212814 }12815 },12816 "general_reference": {12817 "n": 256,12818 "chrf": {12819 "mean": 62.58221842845609,12820 "ci_low": 59.42938408534183,12821 "ci_high": 64.83354120567026,12822 "n_items": 256,12823 "n_groups": 1212824 },12825 "edit_sim": {12826 "mean": 0.6475598877482497,12827 "ci_low": 0.6106061838398974,12828 "ci_high": 0.6704393693536652,12829 "n_items": 256,12830 "n_groups": 1212831 },12832 "rougeL": {12833 "mean": 0.6505699175476303,12834 "ci_low": 0.6072356465230179,12835 "ci_high": 0.6738350631755146,12836 "n_items": 256,12837 "n_groups": 1212838 },12839 "exact_match": {12840 "mean": 0.0,12841 "ci_low": 0.0,12842 "ci_high": 0.0,12843 "n_items": 256,12844 "n_groups": 1212845 },12846 "number_recall": {12847 "mean": 1.0,12848 "ci_low": 1.0,12849 "ci_high": 1.0,12850 "n_items": 256,12851 "n_groups": 1212852 },12853 "placeholders_exact": {12854 "mean": 1.0,12855 "ci_low": 1.0,12856 "ci_high": 1.0,12857 "n_items": 256,12858 "n_groups": 1212859 }12860 },12861 "humanities": {12862 "n": 253,12863 "chrf": {12864 "mean": 63.4603430729446,12865 "ci_low": 59.90243060022108,12866 "ci_high": 66.97227770937675,12867 "n_items": 253,12868 "n_groups": 912869 },12870 "edit_sim": {12871 "mean": 0.6571139223188734,12872 "ci_low": 0.6246487825949227,12873 "ci_high": 0.6997789725268807,12874 "n_items": 253,12875 "n_groups": 912876 },12877 "rougeL": {12878 "mean": 0.6624147286535443,12879 "ci_low": 0.6305807570633232,12880 "ci_high": 0.7002039811723877,12881 "n_items": 253,12882 "n_groups": 912883 },12884 "exact_match": {12885 "mean": 0.0,12886 "ci_low": 0.0,12887 "ci_high": 0.0,12888 "n_items": 253,12889 "n_groups": 912890 },12891 "number_recall": {12892 "mean": 1.0,12893 "ci_low": 1.0,12894 "ci_high": 1.0,12895 "n_items": 253,12896 "n_groups": 912897 },12898 "placeholders_exact": {12899 "mean": 1.0,12900 "ci_low": 1.0,12901 "ci_high": 1.0,12902 "n_items": 253,12903 "n_groups": 912904 }12905 },12906 "life_sciences": {12907 "n": 233,12908 "chrf": {12909 "mean": 60.92143777935449,12910 "ci_low": 58.424505414000095,12911 "ci_high": 63.75847561439019,12912 "n_items": 233,12913 "n_groups": 812914 },12915 "edit_sim": {12916 "mean": 0.6204571167797299,12917 "ci_low": 0.5979518388334819,12918 "ci_high": 0.6448981529488633,12919 "n_items": 233,12920 "n_groups": 812921 },12922 "rougeL": {12923 "mean": 0.6295143990400515,12924 "ci_low": 0.6036604840783826,12925 "ci_high": 0.6584709638879428,12926 "n_items": 233,12927 "n_groups": 812928 },12929 "exact_match": {12930 "mean": 0.0,12931 "ci_low": 0.0,12932 "ci_high": 0.0,12933 "n_items": 233,12934 "n_groups": 812935 },12936 "number_recall": {12937 "mean": 0.9989270386266095,12938 "ci_low": 0.9965112203868725,12939 "ci_high": 1.0,12940 "n_items": 233,12941 "n_groups": 812942 },12943 "placeholders_exact": {12944 "mean": 1.0,12945 "ci_low": 1.0,12946 "ci_high": 1.0,12947 "n_items": 233,12948 "n_groups": 812949 }12950 },12951 "social_sciences": {12952 "n": 299,12953 "chrf": {12954 "mean": 59.73982833175659,12955 "ci_low": 57.09539128167779,12956 "ci_high": 61.949185424107625,12957 "n_items": 299,12958 "n_groups": 2112959 },12960 "edit_sim": {12961 "mean": 0.6292171138819066,12962 "ci_low": 0.6035156869106488,12963 "ci_high": 0.6516193087979353,12964 "n_items": 299,12965 "n_groups": 2112966 },12967 "rougeL": {12968 "mean": 0.6295211100034918,12969 "ci_low": 0.5992663451741355,12970 "ci_high": 0.6556151218269763,12971 "n_items": 299,12972 "n_groups": 2112973 },12974 "exact_match": {12975 "mean": 0.0,12976 "ci_low": 0.0,12977 "ci_high": 0.0,12978 "n_items": 299,12979 "n_groups": 2112980 },12981 "number_recall": {12982 "mean": 1.0,12983 "ci_low": 1.0,12984 "ci_high": 1.0,12985 "n_items": 299,12986 "n_groups": 2112987 },12988 "placeholders_exact": {12989 "mean": 1.0,12990 "ci_low": 1.0,12991 "ci_high": 1.0,12992 "n_items": 299,12993 "n_groups": 2112994 }12995 }12996 },12997 "by_era": {12998 "1900-1949": {12999 "n": 74,13000 "chrf": {13001 "mean": 64.91503838752075,13002 "ci_low": 62.61439733292821,13003 "ci_high": 71.11901014597038,13004 "n_items": 74,13005 "n_groups": 513006 },13007 "edit_sim": {13008 "mean": 0.6769409047216639,13009 "ci_low": 0.618392155227234,13010 "ci_high": 0.7032870971537231,13011 "n_items": 74,13012 "n_groups": 513013 },13014 "rougeL": {13015 "mean": 0.6685369139221219,13016 "ci_low": 0.5914124491145452,13017 "ci_high": 0.6947867669728025,13018 "n_items": 74,13019 "n_groups": 513020 },13021 "exact_match": {13022 "mean": 0.0,13023 "ci_low": 0.0,13024 "ci_high": 0.0,13025 "n_items": 74,13026 "n_groups": 513027 },13028 "number_recall": {13029 "mean": 0.9945945945945945,13030 "ci_low": 0.9600000000000001,13031 "ci_high": 1.0,13032 "n_items": 74,13033 "n_groups": 513034 },13035 "placeholders_exact": {13036 "mean": 1.0,13037 "ci_low": 1.0,13038 "ci_high": 1.0,13039 "n_items": 74,13040 "n_groups": 513041 }13042 },13043 "2010-2017": {13044 "n": 527,13045 "chrf": {13046 "mean": 70.85244065922016,13047 "ci_low": 67.33087155650038,13048 "ci_high": 73.35641349524496,13049 "n_items": 527,13050 "n_groups": 413051 },13052 "edit_sim": {13053 "mean": 0.7036753879465707,13054 "ci_low": 0.6694243963083705,13055 "ci_high": 0.7302659009752224,13056 "n_items": 527,13057 "n_groups": 413058 },13059 "rougeL": {13060 "mean": 0.7069910826645713,13061 "ci_low": 0.6697614410835365,13062 "ci_high": 0.7361447964224318,13063 "n_items": 527,13064 "n_groups": 413065 },13066 "exact_match": {13067 "mean": 0.0,13068 "ci_low": 0.0,13069 "ci_high": 0.0,13070 "n_items": 527,13071 "n_groups": 413072 },13073 "number_recall": {13074 "mean": 0.9823874417802312,13075 "ci_low": 0.9553763440860216,13076 "ci_high": 0.9955197132616488,13077 "n_items": 527,13078 "n_groups": 413079 },13080 "placeholders_exact": {13081 "mean": 0.9905123339658444,13082 "ci_low": 0.967741935483871,13083 "ci_high": 1.0,13084 "n_items": 527,13085 "n_groups": 413086 }13087 },13088 "pre1900": {13089 "n": 1973,13090 "chrf": {13091 "mean": 61.34727157446676,13092 "ci_low": 59.98207081340954,13093 "ci_high": 62.581250190113344,13094 "n_items": 1973,13095 "n_groups": 8313096 },13097 "edit_sim": {13098 "mean": 0.6283058855306362,13099 "ci_low": 0.6163884703848448,13100 "ci_high": 0.6398646738637221,13101 "n_items": 1973,13102 "n_groups": 8313103 },13104 "rougeL": {13105 "mean": 0.6338863814473183,13106 "ci_low": 0.6206725686718467,13107 "ci_high": 0.646106516552405,13108 "n_items": 1973,13109 "n_groups": 8313110 },13111 "exact_match": {13112 "mean": 0.0,13113 "ci_low": 0.0,13114 "ci_high": 0.0,13115 "n_items": 1973,13116 "n_groups": 8313117 },13118 "number_recall": {13119 "mean": 0.9980117956042944,13120 "ci_low": 0.9962828385566476,13121 "ci_high": 0.999471122613543,13122 "n_items": 1973,13123 "n_groups": 8313124 },13125 "placeholders_exact": {13126 "mean": 1.0,13127 "ci_low": 1.0,13128 "ci_high": 1.0,13129 "n_items": 1973,13130 "n_groups": 8313131 }13132 }13133 },13134 "by_role": {13135 "abstract": {13136 "n": 36,13137 "chrf": {13138 "mean": 66.90591822433723,13139 "ci_low": 62.05336169149258,13140 "ci_high": 71.29375759952917,13141 "n_items": 36,13142 "n_groups": 613143 },13144 "edit_sim": {13145 "mean": 0.6608270179532277,13146 "ci_low": 0.605255349159005,13147 "ci_high": 0.7150184703390015,13148 "n_items": 36,13149 "n_groups": 613150 },13151 "rougeL": {13152 "mean": 0.6361712805244613,13153 "ci_low": 0.5750597224713836,13154 "ci_high": 0.69166774000926,13155 "n_items": 36,13156 "n_groups": 613157 },13158 "exact_match": {13159 "mean": 0.0,13160 "ci_low": 0.0,13161 "ci_high": 0.0,13162 "n_items": 36,13163 "n_groups": 613164 },13165 "number_recall": {13166 "mean": 0.9888888888888889,13167 "ci_low": 0.9666666666666666,13168 "ci_high": 1.0,13169 "n_items": 36,13170 "n_groups": 613171 },13172 "placeholders_exact": {13173 "mean": 1.0,13174 "ci_low": 1.0,13175 "ci_high": 1.0,13176 "n_items": 36,13177 "n_groups": 613178 }13179 },13180 "chapter": {13181 "n": 819,13182 "chrf": {13183 "mean": 62.0438613142437,13184 "ci_low": 60.59340850020779,13185 "ci_high": 63.467815020541295,13186 "n_items": 819,13187 "n_groups": 5213188 },13189 "edit_sim": {13190 "mean": 0.6327926375611702,13191 "ci_low": 0.6179246288688597,13192 "ci_high": 0.6474960693134533,13193 "n_items": 819,13194 "n_groups": 5213195 },13196 "rougeL": {13197 "mean": 0.641297401508407,13198 "ci_low": 0.6251355987366602,13199 "ci_high": 0.6561144065287073,13200 "n_items": 819,13201 "n_groups": 5213202 },13203 "exact_match": {13204 "mean": 0.0,13205 "ci_low": 0.0,13206 "ci_high": 0.0,13207 "n_items": 819,13208 "n_groups": 5213209 },13210 "number_recall": {13211 "mean": 0.9976800976800977,13212 "ci_low": 0.9949421535232591,13213 "ci_high": 1.0,13214 "n_items": 819,13215 "n_groups": 5213216 },13217 "placeholders_exact": {13218 "mean": 1.0,13219 "ci_low": 1.0,13220 "ci_high": 1.0,13221 "n_items": 819,13222 "n_groups": 5213223 }13224 },13225 "conclusion": {13226 "n": 104,13227 "chrf": {13228 "mean": 69.79011596725829,13229 "ci_low": 63.2538208718719,13230 "ci_high": 73.52829626077639,13231 "n_items": 104,13232 "n_groups": 313233 },13234 "edit_sim": {13235 "mean": 0.68741604423433,13236 "ci_low": 0.6208587375243435,13237 "ci_high": 0.7417767721790616,13238 "n_items": 104,13239 "n_groups": 313240 },13241 "rougeL": {13242 "mean": 0.6863983625738708,13243 "ci_low": 0.6130570401042006,13244 "ci_high": 0.7321905223935764,13245 "n_items": 104,13246 "n_groups": 313247 },13248 "exact_match": {13249 "mean": 0.0,13250 "ci_low": 0.0,13251 "ci_high": 0.0,13252 "n_items": 104,13253 "n_groups": 313254 },13255 "number_recall": {13256 "mean": 0.9982517482517482,13257 "ci_low": 0.9967532467532466,13258 "ci_high": 1.0,13259 "n_items": 104,13260 "n_groups": 313261 },13262 "placeholders_exact": {13263 "mean": 1.0,13264 "ci_low": 1.0,13265 "ci_high": 1.0,13266 "n_items": 104,13267 "n_groups": 313268 }13269 },13270 "data": {13271 "n": 11,13272 "chrf": {13273 "mean": 77.20431853223647,13274 "ci_low": 77.20431853223647,13275 "ci_high": 77.20431853223647,13276 "n_items": 11,13277 "n_groups": 113278 },13279 "edit_sim": {13280 "mean": 0.7796955977178641,13281 "ci_low": 0.7796955977178641,13282 "ci_high": 0.7796955977178641,13283 "n_items": 11,13284 "n_groups": 113285 },13286 "rougeL": {13287 "mean": 0.7948033983251501,13288 "ci_low": 0.7948033983251501,13289 "ci_high": 0.7948033983251501,13290 "n_items": 11,13291 "n_groups": 113292 },13293 "exact_match": {13294 "mean": 0.0,13295 "ci_low": 0.0,13296 "ci_high": 0.0,13297 "n_items": 11,13298 "n_groups": 113299 },13300 "number_recall": {13301 "mean": 1.0,13302 "ci_low": 1.0,13303 "ci_high": 1.0,13304 "n_items": 11,13305 "n_groups": 113306 },13307 "placeholders_exact": {13308 "mean": 1.0,13309 "ci_low": 1.0,13310 "ci_high": 1.0,13311 "n_items": 11,13312 "n_groups": 113313 }13314 },13315 "introduction": {13316 "n": 574,13317 "chrf": {13318 "mean": 62.10286996337958,13319 "ci_low": 59.202874082303104,13320 "ci_high": 64.11839245676205,13321 "n_items": 574,13322 "n_groups": 2313323 },13324 "edit_sim": {13325 "mean": 0.6372794455758715,13326 "ci_low": 0.6095634819394444,13327 "ci_high": 0.6571322404176873,13328 "n_items": 574,13329 "n_groups": 2313330 },13331 "rougeL": {13332 "mean": 0.6400627892279285,13333 "ci_low": 0.6120476964472785,13334 "ci_high": 0.6603925975139361,13335 "n_items": 574,13336 "n_groups": 2313337 },13338 "exact_match": {13339 "mean": 0.0,13340 "ci_low": 0.0,13341 "ci_high": 0.0,13342 "n_items": 574,13343 "n_groups": 2313344 },13345 "number_recall": {13346 "mean": 0.9982182451694647,13347 "ci_low": 0.9954869424845258,13348 "ci_high": 1.0,13349 "n_items": 574,13350 "n_groups": 2313351 },13352 "placeholders_exact": {13353 "mean": 1.0,13354 "ci_low": 1.0,13355 "ci_high": 1.0,13356 "n_items": 574,13357 "n_groups": 2313358 }13359 },13360 "methods": {13361 "n": 93,13362 "chrf": {13363 "mean": 71.51696856833297,13364 "ci_low": 67.57604907243716,13365 "ci_high": 78.68574287166223,13366 "n_items": 93,13367 "n_groups": 313368 },13369 "edit_sim": {13370 "mean": 0.7061017045893103,13371 "ci_low": 0.6672149383795313,13372 "ci_high": 0.8122436909146247,13373 "n_items": 93,13374 "n_groups": 313375 },13376 "rougeL": {13377 "mean": 0.7298183963574137,13378 "ci_low": 0.6889487973536079,13379 "ci_high": 0.8233435380696901,13380 "n_items": 93,13381 "n_groups": 313382 },13383 "exact_match": {13384 "mean": 0.0,13385 "ci_low": 0.0,13386 "ci_high": 0.0,13387 "n_items": 93,13388 "n_groups": 313389 },13390 "number_recall": {13391 "mean": 0.9765232974910395,13392 "ci_low": 0.9652777777777778,13393 "ci_high": 1.0,13394 "n_items": 93,13395 "n_groups": 313396 },13397 "placeholders_exact": {13398 "mean": 1.0,13399 "ci_low": 1.0,13400 "ci_high": 1.0,13401 "n_items": 93,13402 "n_groups": 313403 }13404 },13405 "other": {13406 "n": 163,13407 "chrf": {13408 "mean": 65.34378751891535,13409 "ci_low": 59.89940533103503,13410 "ci_high": 70.34718639461111,13411 "n_items": 163,13412 "n_groups": 913413 },13414 "edit_sim": {13415 "mean": 0.6730193040265203,13416 "ci_low": 0.6391250374991161,13417 "ci_high": 0.7038401718634573,13418 "n_items": 163,13419 "n_groups": 913420 },13421 "rougeL": {13422 "mean": 0.6795260968125119,13423 "ci_low": 0.6473549234742612,13424 "ci_high": 0.7102764888753419,13425 "n_items": 163,13426 "n_groups": 913427 },13428 "exact_match": {13429 "mean": 0.0,13430 "ci_low": 0.0,13431 "ci_high": 0.0,13432 "n_items": 163,13433 "n_groups": 913434 },13435 "number_recall": {13436 "mean": 1.0,13437 "ci_low": 1.0,13438 "ci_high": 1.0,13439 "n_items": 163,13440 "n_groups": 913441 },13442 "placeholders_exact": {13443 "mean": 1.0,13444 "ci_low": 1.0,13445 "ci_high": 1.0,13446 "n_items": 163,13447 "n_groups": 913448 }13449 },13450 "preface": {13451 "n": 562,13452 "chrf": {13453 "mean": 60.1714549897661,13454 "ci_low": 58.288827891270365,13455 "ci_high": 62.069040295793066,13456 "n_items": 562,13457 "n_groups": 4813458 },13459 "edit_sim": {13460 "mean": 0.6172359105550317,13461 "ci_low": 0.5990847727021255,13462 "ci_high": 0.6363681024959597,13463 "n_items": 562,13464 "n_groups": 4813465 },13466 "rougeL": {13467 "mean": 0.620087501757143,13468 "ci_low": 0.5999802025389984,13469 "ci_high": 0.6412670182522809,13470 "n_items": 562,13471 "n_groups": 4813472 },13473 "exact_match": {13474 "mean": 0.0,13475 "ci_low": 0.0,13476 "ci_high": 0.0,13477 "n_items": 562,13478 "n_groups": 4813479 },13480 "number_recall": {13481 "mean": 0.998220640569395,13482 "ci_low": 0.994140338337818,13483 "ci_high": 1.0,13484 "n_items": 562,13485 "n_groups": 4813486 },13487 "placeholders_exact": {13488 "mean": 1.0,13489 "ci_low": 1.0,13490 "ci_high": 1.0,13491 "n_items": 562,13492 "n_groups": 4813493 }13494 },13495 "related_work": {13496 "n": 18,13497 "chrf": {13498 "mean": 71.15014790707491,13499 "ci_low": 71.15014790707491,13500 "ci_high": 71.15014790707491,13501 "n_items": 18,13502 "n_groups": 113503 },13504 "edit_sim": {13505 "mean": 0.7103014947973771,13506 "ci_low": 0.7103014947973771,13507 "ci_high": 0.7103014947973771,13508 "n_items": 18,13509 "n_groups": 113510 },13511 "rougeL": {13512 "mean": 0.6936643424357295,13513 "ci_low": 0.6936643424357295,13514 "ci_high": 0.6936643424357295,13515 "n_items": 18,13516 "n_groups": 113517 },13518 "exact_match": {13519 "mean": 0.0,13520 "ci_low": 0.0,13521 "ci_high": 0.0,13522 "n_items": 18,13523 "n_groups": 113524 },13525 "number_recall": {13526 "mean": 1.0,13527 "ci_low": 1.0,13528 "ci_high": 1.0,13529 "n_items": 18,13530 "n_groups": 113531 },13532 "placeholders_exact": {13533 "mean": 1.0,13534 "ci_low": 1.0,13535 "ci_high": 1.0,13536 "n_items": 18,13537 "n_groups": 113538 }13539 },13540 "results": {13541 "n": 158,13542 "chrf": {13543 "mean": 70.31796207224802,13544 "ci_low": 68.26232823520115,13545 "ci_high": 76.74098812307047,13546 "n_items": 158,13547 "n_groups": 313548 },13549 "edit_sim": {13550 "mean": 0.6997276621393516,13551 "ci_low": 0.6765498205319835,13552 "ci_high": 0.7208354678404033,13553 "n_items": 158,13554 "n_groups": 313555 },13556 "rougeL": {13557 "mean": 0.6992409043139632,13558 "ci_low": 0.6843855782327402,13559 "ci_high": 0.7320163730784243,13560 "n_items": 158,13561 "n_groups": 313562 },13563 "exact_match": {13564 "mean": 0.0,13565 "ci_low": 0.0,13566 "ci_high": 0.0,13567 "n_items": 158,13568 "n_groups": 313569 },13570 "number_recall": {13571 "mean": 0.9562236286919832,13572 "ci_low": 0.9101731601731602,13573 "ci_high": 1.0,13574 "n_items": 158,13575 "n_groups": 313576 },13577 "placeholders_exact": {13578 "mean": 0.9683544303797469,13579 "ci_low": 0.935064935064935,13580 "ci_high": 1.0,13581 "n_items": 158,13582 "n_groups": 313583 }13584 },13585 "theory": {13586 "n": 36,13587 "chrf": {13588 "mean": 74.85276867244939,13589 "ci_low": 70.04815038534133,13590 "ci_high": 75.81369232987099,13591 "n_items": 36,13592 "n_groups": 213593 },13594 "edit_sim": {13595 "mean": 0.7518394295842393,13596 "ci_low": 0.7470277368959731,13597 "ci_high": 0.7528017681218928,13598 "n_items": 36,13599 "n_groups": 213600 },13601 "rougeL": {13602 "mean": 0.7492709743062923,13603 "ci_low": 0.7096303313159201,13604 "ci_high": 0.7571991029043666,13605 "n_items": 36,13606 "n_groups": 213607 },13608 "exact_match": {13609 "mean": 0.0,13610 "ci_low": 0.0,13611 "ci_high": 0.0,13612 "n_items": 36,13613 "n_groups": 213614 },13615 "number_recall": {13616 "mean": 1.0,13617 "ci_low": 1.0,13618 "ci_high": 1.0,13619 "n_items": 36,13620 "n_groups": 213621 },13622 "placeholders_exact": {13623 "mean": 1.0,13624 "ci_low": 1.0,13625 "ci_high": 1.0,13626 "n_items": 36,13627 "n_groups": 213628 }13629 }13630 }13631 }13632 },13633 "paired_vs_baseline": {13634 "B1_generic_paraphrase": {13635 "chrf": {13636 "mean": -2.049183602571818,13637 "ci_low": -2.3583841064553948,13638 "ci_high": -1.7042799520280805,13639 "n_items": 2574,13640 "n_groups": 92,13641 "p_value_two_sided": 0.0,13642 "p_holm": 0.0,13643 "significant_holm_0_05": true13644 },13645 "edit_sim": {13646 "mean": -0.11533603975618428,13647 "ci_low": -0.12009547196336103,13648 "ci_high": -0.10940698101445706,13649 "n_items": 2574,13650 "n_groups": 92,13651 "p_value_two_sided": 0.0,13652 "p_holm": 0.0,13653 "significant_holm_0_05": true13654 },13655 "rougeL": {13656 "mean": -0.08340639803823041,13657 "ci_low": -0.08707456474208088,13658 "ci_high": -0.07868402187457925,13659 "n_items": 2574,13660 "n_groups": 92,13661 "p_value_two_sided": 0.0,13662 "p_holm": 0.0,13663 "significant_holm_0_05": true13664 },13665 "exact_match": {13666 "mean": 0.0,13667 "ci_low": 0.0,13668 "ci_high": 0.0,13669 "n_items": 2574,13670 "n_groups": 92,13671 "p_value_two_sided": 0.0,13672 "p_holm": 0.0,13673 "significant_holm_0_05": true13674 },13675 "number_recall": {13676 "mean": 0.0,13677 "ci_low": 0.0,13678 "ci_high": 0.0,13679 "n_items": 2574,13680 "n_groups": 92,13681 "p_value_two_sided": 0.0,13682 "p_holm": 0.0,13683 "significant_holm_0_05": true13684 },13685 "placeholders_exact": {13686 "mean": 0.0,13687 "ci_low": 0.0,13688 "ci_high": 0.0,13689 "n_items": 2574,13690 "n_groups": 92,13691 "p_value_two_sided": 0.0,13692 "p_holm": 0.0,13693 "significant_holm_0_05": true13694 }13695 },13696 "htr-m1-small": {13697 "chrf": {13698 "mean": -0.6664519284211142,13699 "ci_low": -0.8764461724697357,13700 "ci_high": -0.4106696788689526,13701 "n_items": 2574,13702 "n_groups": 92,13703 "p_value_two_sided": 0.0,13704 "p_holm": 0.0,13705 "significant_holm_0_05": true13706 },13707 "edit_sim": {13708 "mean": -0.008523536389156091,13709 "ci_low": -0.010850058661468057,13710 "ci_high": -0.006070124236866434,13711 "n_items": 2574,13712 "n_groups": 92,13713 "p_value_two_sided": 0.0,13714 "p_holm": 0.0,13715 "significant_holm_0_05": true13716 },13717 "rougeL": {13718 "mean": -0.008699139157313284,13719 "ci_low": -0.01156396046091473,13720 "ci_high": -0.0055209038542248885,13721 "n_items": 2574,13722 "n_groups": 92,13723 "p_value_two_sided": 0.0,13724 "p_holm": 0.0,13725 "significant_holm_0_05": true13726 },13727 "exact_match": {13728 "mean": 0.0,13729 "ci_low": 0.0,13730 "ci_high": 0.0,13731 "n_items": 2574,13732 "n_groups": 92,13733 "p_value_two_sided": 0.0,13734 "p_holm": 0.0,13735 "significant_holm_0_05": true13736 },13737 "number_recall": {13738 "mean": -0.007553263235081417,13739 "ci_low": -0.015824692073772236,13740 "ci_high": -0.0018518416037246448,13741 "n_items": 2574,13742 "n_groups": 92,13743 "p_value_two_sided": 0.0,13744 "p_holm": 0.0,13745 "significant_holm_0_05": true13746 },13747 "placeholders_exact": {13748 "mean": -0.000777000777000777,13749 "ci_low": -0.0022916124601972242,13750 "ci_high": 0.0,13751 "n_items": 2574,13752 "n_groups": 92,13753 "p_value_two_sided": 0.0,13754 "p_holm": 0.0,13755 "significant_holm_0_05": true13756 }13757 },13758 "htr-m1-tiny-s2": {13759 "chrf": {13760 "mean": -0.544137046510172,13761 "ci_low": -0.74663491944965,13762 "ci_high": -0.29631643328527413,13763 "n_items": 2574,13764 "n_groups": 92,13765 "p_value_two_sided": 0.0,13766 "p_holm": 0.0,13767 "significant_holm_0_05": true13768 },13769 "edit_sim": {13770 "mean": -0.004508578605877275,13771 "ci_low": -0.006504164057890178,13772 "ci_high": -0.002156845970230519,13773 "n_items": 2574,13774 "n_groups": 92,13775 "p_value_two_sided": 0.00019999999999997797,13776 "p_holm": 0.00039999999999995595,13777 "significant_holm_0_05": true13778 },13779 "rougeL": {13780 "mean": -0.004870325848088242,13781 "ci_low": -0.007324377292854278,13782 "ci_high": -0.0019718677501155504,13783 "n_items": 2574,13784 "n_groups": 92,13785 "p_value_two_sided": 0.0016000000000000458,13786 "p_holm": 0.0016000000000000458,13787 "significant_holm_0_05": true13788 },13789 "exact_match": {13790 "mean": 0.0,13791 "ci_low": 0.0,13792 "ci_high": 0.0,13793 "n_items": 2574,13794 "n_groups": 92,13795 "p_value_two_sided": 0.0,13796 "p_holm": 0.0,13797 "significant_holm_0_05": true13798 },13799 "number_recall": {13800 "mean": -0.005566221096524127,13801 "ci_low": -0.011255273074782263,13802 "ci_high": -0.0012363139431608864,13803 "n_items": 2574,13804 "n_groups": 92,13805 "p_value_two_sided": 0.0,13806 "p_holm": 0.0,13807 "significant_holm_0_05": true13808 },13809 "placeholders_exact": {13810 "mean": -0.003108003108003108,13811 "ci_low": -0.00749079269405538,13812 "ci_high": 0.0,13813 "n_items": 2574,13814 "n_groups": 92,13815 "p_value_two_sided": 0.0,13816 "p_holm": 0.0,13817 "significant_holm_0_05": true13818 }13819 },13820 "htr-m1-tiny-s3": {13821 "chrf": {13822 "mean": -0.524895982019787,13823 "ci_low": -0.7495249940289449,13824 "ci_high": -0.2754729945577563,13825 "n_items": 2574,13826 "n_groups": 92,13827 "p_value_two_sided": 0.0,13828 "p_holm": 0.0,13829 "significant_holm_0_05": true13830 },13831 "edit_sim": {13832 "mean": -0.005351581137430553,13833 "ci_low": -0.008103153487234878,13834 "ci_high": -0.002515423685548783,13835 "n_items": 2574,13836 "n_groups": 92,13837 "p_value_two_sided": 0.00019999999999997797,13838 "p_holm": 0.00039999999999995595,13839 "significant_holm_0_05": true13840 },13841 "rougeL": {13842 "mean": -0.005862726966937231,13843 "ci_low": -0.008834145233288588,13844 "ci_high": -0.0025924503210220827,13845 "n_items": 2574,13846 "n_groups": 92,13847 "p_value_two_sided": 0.0005999999999999339,13848 "p_holm": 0.0005999999999999339,13849 "significant_holm_0_05": true13850 },13851 "exact_match": {13852 "mean": 0.0,13853 "ci_low": 0.0,13854 "ci_high": 0.0,13855 "n_items": 2574,13856 "n_groups": 92,13857 "p_value_two_sided": 0.0,13858 "p_holm": 0.0,13859 "significant_holm_0_05": true13860 },13861 "number_recall": {13862 "mean": -0.00621045621045621,13863 "ci_low": -0.01177021379139706,13864 "ci_high": -0.0018506905332562544,13865 "n_items": 2574,13866 "n_groups": 92,13867 "p_value_two_sided": 0.0,13868 "p_holm": 0.0,13869 "significant_holm_0_05": true13870 },13871 "placeholders_exact": {13872 "mean": -0.000777000777000777,13873 "ci_low": -0.00249693089801846,13874 "ci_high": 0.0,13875 "n_items": 2574,13876 "n_groups": 92,13877 "p_value_two_sided": 0.0,13878 "p_holm": 0.0,13879 "significant_holm_0_05": true13880 }13881 },13882 "htr-m1-tiny": {13883 "chrf": {13884 "mean": -0.540960568624686,13885 "ci_low": -0.7561635444955563,13886 "ci_high": -0.2800163765428109,13887 "n_items": 2574,13888 "n_groups": 92,13889 "p_value_two_sided": 0.0,13890 "p_holm": 0.0,13891 "significant_holm_0_05": true13892 },13893 "edit_sim": {13894 "mean": -0.0050168070419813705,13895 "ci_low": -0.007400857767747239,13896 "ci_high": -0.0024355093224154786,13897 "n_items": 2574,13898 "n_groups": 92,13899 "p_value_two_sided": 0.00039999999999995595,13900 "p_holm": 0.0007999999999999119,13901 "significant_holm_0_05": true13902 },13903 "rougeL": {13904 "mean": -0.005542625790928096,13905 "ci_low": -0.008680772425387572,13906 "ci_high": -0.0021180415756388957,13907 "n_items": 2574,13908 "n_groups": 92,13909 "p_value_two_sided": 0.0020000000000000018,13910 "p_holm": 0.0020000000000000018,13911 "significant_holm_0_05": true13912 },13913 "exact_match": {13914 "mean": 0.0,13915 "ci_low": 0.0,13916 "ci_high": 0.0,13917 "n_items": 2574,13918 "n_groups": 92,13919 "p_value_two_sided": 0.0,13920 "p_holm": 0.0,13921 "significant_holm_0_05": true13922 },13923 "number_recall": {13924 "mean": -0.007293674339128885,13925 "ci_low": -0.015386291248166869,13926 "ci_high": -0.0017086285318832636,13927 "n_items": 2574,13928 "n_groups": 92,13929 "p_value_two_sided": 0.0,13930 "p_holm": 0.0,13931 "significant_holm_0_05": true13932 },13933 "placeholders_exact": {13934 "mean": -0.000777000777000777,13935 "ci_low": -0.00249693089801846,13936 "ci_high": 0.0,13937 "n_items": 2574,13938 "n_groups": 92,13939 "p_value_two_sided": 0.0,13940 "p_holm": 0.0,13941 "significant_holm_0_05": true13942 }13943 },13944 "htr-m2-tiny": {13945 "chrf": {13946 "mean": -0.7353035328672429,13947 "ci_low": -0.9616917261417697,13948 "ci_high": -0.48739719695176803,13949 "n_items": 2574,13950 "n_groups": 92,13951 "p_value_two_sided": 0.0,13952 "p_holm": 0.0,13953 "significant_holm_0_05": true13954 },13955 "edit_sim": {13956 "mean": -0.007323187715084649,13957 "ci_low": -0.009435242263762167,13958 "ci_high": -0.004992550735476229,13959 "n_items": 2574,13960 "n_groups": 92,13961 "p_value_two_sided": 0.0,13962 "p_holm": 0.0,13963 "significant_holm_0_05": true13964 },13965 "rougeL": {13966 "mean": -0.00726355036270569,13967 "ci_low": -0.009926879603959864,13968 "ci_high": -0.004432278973408253,13969 "n_items": 2574,13970 "n_groups": 92,13971 "p_value_two_sided": 0.0,13972 "p_holm": 0.0,13973 "significant_holm_0_05": true13974 },13975 "exact_match": {13976 "mean": 0.0,13977 "ci_low": 0.0,13978 "ci_high": 0.0,13979 "n_items": 2574,13980 "n_groups": 92,13981 "p_value_two_sided": 0.0,13982 "p_holm": 0.0,13983 "significant_holm_0_05": true13984 },13985 "number_recall": {13986 "mean": -0.007742930470203197,13987 "ci_low": -0.01460148414089497,13988 "ci_high": -0.0024306558791426726,13989 "n_items": 2574,13990 "n_groups": 92,13991 "p_value_two_sided": 0.0,13992 "p_holm": 0.0,13993 "significant_holm_0_05": true13994 },13995 "placeholders_exact": {13996 "mean": -0.003108003108003108,13997 "ci_low": -0.00998772359207384,13998 "ci_high": 0.0,13999 "n_items": 2574,14000 "n_groups": 92,14001 "p_value_two_sided": 0.0,14002 "p_holm": 0.0,14003 "significant_holm_0_05": true14004 }14005 },14006 "htr-m3light-tiny": {14007 "chrf": {14008 "mean": -0.8567801220363638,14009 "ci_low": -1.092717506836713,14010 "ci_high": -0.5760839743005866,14011 "n_items": 2574,14012 "n_groups": 92,14013 "p_value_two_sided": 0.0,14014 "p_holm": 0.0,14015 "significant_holm_0_05": true14016 },14017 "edit_sim": {14018 "mean": -0.007659832945990915,14019 "ci_low": -0.009898617349406006,14020 "ci_high": -0.00505272223726933,14021 "n_items": 2574,14022 "n_groups": 92,14023 "p_value_two_sided": 0.0,14024 "p_holm": 0.0,14025 "significant_holm_0_05": true14026 },14027 "rougeL": {14028 "mean": -0.008087657174644776,14029 "ci_low": -0.010868757328757491,14030 "ci_high": -0.004827358177697533,14031 "n_items": 2574,14032 "n_groups": 92,14033 "p_value_two_sided": 0.0,14034 "p_holm": 0.0,14035 "significant_holm_0_05": true14036 },14037 "exact_match": {14038 "mean": 0.0,14039 "ci_low": 0.0,14040 "ci_high": 0.0,14041 "n_items": 2574,14042 "n_groups": 92,14043 "p_value_two_sided": 0.0,14044 "p_holm": 0.0,14045 "significant_holm_0_05": true14046 },14047 "number_recall": {14048 "mean": -0.006933820948972464,14049 "ci_low": -0.014055993182286303,14050 "ci_high": -0.0018330936135702454,14051 "n_items": 2574,14052 "n_groups": 92,14053 "p_value_two_sided": 0.0,14054 "p_holm": 0.0,14055 "significant_holm_0_05": true14056 },14057 "placeholders_exact": {14058 "mean": -0.0019425019425019425,14059 "ci_low": -0.006242327245046149,14060 "ci_high": 0.0,14061 "n_items": 2574,14062 "n_groups": 92,14063 "p_value_two_sided": 0.0,14064 "p_holm": 0.0,14065 "significant_holm_0_05": true14066 }14067 },14068 "htr-m3tokenonly-tiny-s2": {14069 "chrf": {14070 "mean": -0.5743647052487758,14071 "ci_low": -0.7950967932530932,14072 "ci_high": -0.33152013293887056,14073 "n_items": 2574,14074 "n_groups": 92,14075 "p_value_two_sided": 0.0,14076 "p_holm": 0.0,14077 "significant_holm_0_05": true14078 },14079 "edit_sim": {14080 "mean": -0.004394917592792422,14081 "ci_low": -0.006520381888638949,14082 "ci_high": -0.0021376604014309015,14083 "n_items": 2574,14084 "n_groups": 92,14085 "p_value_two_sided": 0.0,14086 "p_holm": 0.0,14087 "significant_holm_0_05": true14088 },14089 "rougeL": {14090 "mean": -0.0039000179916843444,14091 "ci_low": -0.006343726013971196,14092 "ci_high": -0.0012077727816190303,14093 "n_items": 2574,14094 "n_groups": 92,14095 "p_value_two_sided": 0.0027999999999999137,14096 "p_holm": 0.0027999999999999137,14097 "significant_holm_0_05": true14098 },14099 "exact_match": {14100 "mean": 0.0,14101 "ci_low": 0.0,14102 "ci_high": 0.0,14103 "n_items": 2574,14104 "n_groups": 92,14105 "p_value_two_sided": 0.0,14106 "p_holm": 0.0,14107 "significant_holm_0_05": true14108 },14109 "number_recall": {14110 "mean": -0.004352129352129352,14111 "ci_low": -0.006698973993401311,14112 "ci_high": -0.0020212592295929875,14113 "n_items": 2574,14114 "n_groups": 92,14115 "p_value_two_sided": 0.0,14116 "p_holm": 0.0,14117 "significant_holm_0_05": true14118 },14119 "placeholders_exact": {14120 "mean": -0.0011655011655011655,14121 "ci_low": -0.00374539634702769,14122 "ci_high": 0.0,14123 "n_items": 2574,14124 "n_groups": 92,14125 "p_value_two_sided": 0.0,14126 "p_holm": 0.0,14127 "significant_holm_0_05": true14128 }14129 },14130 "htr-m3tokenonly-tiny": {14131 "chrf": {14132 "mean": -0.6035201653306697,14133 "ci_low": -0.8285005165655734,14134 "ci_high": -0.34949764319136284,14135 "n_items": 2574,14136 "n_groups": 92,14137 "p_value_two_sided": 0.0,14138 "p_holm": 0.0,14139 "significant_holm_0_05": true14140 },14141 "edit_sim": {14142 "mean": -0.0036821292381866337,14143 "ci_low": -0.005815310008418785,14144 "ci_high": -0.0013077848110516664,14145 "n_items": 2574,14146 "n_groups": 92,14147 "p_value_two_sided": 0.0027999999999999137,14148 "p_holm": 0.005199999999999871,14149 "significant_holm_0_05": true14150 },14151 "rougeL": {14152 "mean": -0.004049538349409643,14153 "ci_low": -0.0064797426285457,14154 "ci_high": -0.001442097191324777,14155 "n_items": 2574,14156 "n_groups": 92,14157 "p_value_two_sided": 0.0025999999999999357,14158 "p_holm": 0.005199999999999871,14159 "significant_holm_0_05": true14160 },14161 "exact_match": {14162 "mean": 0.0,14163 "ci_low": 0.0,14164 "ci_high": 0.0,14165 "n_items": 2574,14166 "n_groups": 92,14167 "p_value_two_sided": 0.0,14168 "p_holm": 0.0,14169 "significant_holm_0_05": true14170 },14171 "number_recall": {14172 "mean": -0.005285371194462104,14173 "ci_low": -0.010932909490020116,14174 "ci_high": -0.0015296653545135014,14175 "n_items": 2574,14176 "n_groups": 92,14177 "p_value_two_sided": 0.0,14178 "p_holm": 0.0,14179 "significant_holm_0_05": true14180 },14181 "placeholders_exact": {14182 "mean": -0.0019425019425019425,14183 "ci_low": -0.006242327245046149,14184 "ci_high": 0.0,14185 "n_items": 2574,14186 "n_groups": 92,14187 "p_value_two_sided": 0.0,14188 "p_holm": 0.0,14189 "significant_holm_0_05": true14190 }14191 }14192 },14193 "stylometry": {14194 "rewrite_vs_original": {14195 "W1_mean_sent_len": 0.31705454382951365,14196 "W1_sd_sent_len": 0.35094636373292604,14197 "W1_ttr": 0.4931949167369863,14198 "W1_mtld": 0.6297369695117688,14199 "W1_mean_word_len": 0.388178662084076,14200 "W1_long_word_rate": 0.0887166637518352,14201 "W1_comma_rate": 0.09067437793331645,14202 "W1_semicolon_rate": 0.3532355422274874,14203 "W1_paren_rate": 0.042248943250355574,14204 "W1_discourse_rate": 0.10644299593960693,14205 "W1_passive_rate": 0.18272920876615986,14206 "W1_nominal_rate": 0.09361865010220287,14207 "W1_first_person_rate": 0.07314137128128478,14208 "W1_subord_rate": 0.05896159521464746,14209 "W1_hedge_rate": 0.15303159611258849,14210 "W1_negation_rate": 0.04570600072267616,14211 "W1_digit_rate": 0.02360204873352831,14212 "W1_flesch": 0.12366877588313005,14213 "W1_mean": 0.2008271792118938914214 },14215 "feature_means": {14216 "original": {14217 "mean_sent_len": 32.363997090580064,14218 "sd_sent_len": 13.296246536739343,14219 "ttr": 0.6363786333503925,14220 "mtld": 72.59407584890894,14221 "mean_word_len": 4.833813103826393,14222 "long_word_rate": 0.07357781248050553,14223 "comma_rate": 0.06867829707994569,14224 "semicolon_rate": 0.005302089774100454,14225 "paren_rate": 0.004651561158502537,14226 "discourse_rate": 0.00797032870681199,14227 "passive_rate": 0.4588957605319073,14228 "nominal_rate": 0.047775970477142916,14229 "first_person_rate": 0.012069992865698613,14230 "subord_rate": 0.03900787849169267,14231 "hedge_rate": 0.006803025452433354,14232 "negation_rate": 0.010569537251963947,14233 "digit_rate": 0.0044634930362821975,14234 "flesch": 34.86940745573128514235 },14236 "rewrite": {14237 "mean_sent_len": 29.064392616020996,14238 "sd_sent_len": 10.626925328034936,14239 "ttr": 0.6791289389902321,14240 "mtld": 90.65471367342826,14241 "mean_word_len": 4.9895424020299055,14242 "long_word_rate": 0.07632929542542134,14243 "comma_rate": 0.0704550786404526,14244 "semicolon_rate": 0.0033058845904534975,14245 "paren_rate": 0.004546773927836971,14246 "discourse_rate": 0.008892475632350653,14247 "passive_rate": 0.3880534541622229,14248 "nominal_rate": 0.0452773984664956,14249 "first_person_rate": 0.011579878275023167,14250 "subord_rate": 0.0397706922592206,14251 "hedge_rate": 0.008143131076581328,14252 "negation_rate": 0.010603972509980202,14253 "digit_rate": 0.0044179887037361105,14254 "flesch": 34.3099702704760414255 }14256 },14257 "feature_sds": {14258 "original": {14259 "mean_sent_len": 12.647099840960085,14260 "sd_sent_len": 8.511111295840472,14261 "ttr": 0.08539045868913513,14262 "mtld": 24.60204605471886,14263 "mean_word_len": 0.40990605438044203,14264 "long_word_rate": 0.03727905743470549,14265 "comma_rate": 0.029019323143779387,14266 "semicolon_rate": 0.007989622690177339,14267 "paren_rate": 0.009817407685487568,14268 "discourse_rate": 0.008386755407873836,14269 "passive_rate": 0.4345477790290478,14270 "nominal_rate": 0.02874499226894197,14271 "first_person_rate": 0.018264096921983042,14272 "subord_rate": 0.01891059395849629,14273 "hedge_rate": 0.008466145199853437,14274 "negation_rate": 0.010201742945958029,14275 "digit_rate": 0.009744036952254759,14276 "flesch": 17.55169390768025314277 },14278 "rewrite": {14279 "mean_sent_len": 9.22698787694779,14280 "sd_sent_len": 5.983819996123602,14281 "ttr": 0.08326273860651343,14282 "mtld": 29.97594643284111,14283 "mean_word_len": 0.4069462995906438,14284 "long_word_rate": 0.036908088834052596,14285 "comma_rate": 0.026941452242009653,14286 "semicolon_rate": 0.010664100746251091,14287 "paren_rate": 0.010235198422820982,14288 "discourse_rate": 0.009191522301011121,14289 "passive_rate": 0.35940162279261967,14290 "nominal_rate": 0.02770133416621583,14291 "first_person_rate": 0.019403342525799536,14292 "subord_rate": 0.018675841270295875,14293 "hedge_rate": 0.009359094222911436,14294 "negation_rate": 0.01077700225680703,14295 "digit_rate": 0.009773702993426803,14296 "flesch": 15.45617600709551514297 }14298 },14299 "B0_identity": {14300 "vs_original": {14301 "W1_mean_sent_len": 0.31705454382951365,14302 "W1_sd_sent_len": 0.35094636373292604,14303 "W1_ttr": 0.4931949167369863,14304 "W1_mtld": 0.6297369695117688,14305 "W1_mean_word_len": 0.388178662084076,14306 "W1_long_word_rate": 0.0887166637518352,14307 "W1_comma_rate": 0.09067437793331645,14308 "W1_semicolon_rate": 0.3532355422274874,14309 "W1_paren_rate": 0.042248943250355574,14310 "W1_discourse_rate": 0.10644299593960693,14311 "W1_passive_rate": 0.18272920876615986,14312 "W1_nominal_rate": 0.09361865010220287,14313 "W1_first_person_rate": 0.07314137128128478,14314 "W1_subord_rate": 0.05896159521464746,14315 "W1_hedge_rate": 0.15303159611258849,14316 "W1_negation_rate": 0.04570600072267616,14317 "W1_digit_rate": 0.02360204873352831,14318 "W1_flesch": 0.12366877588313005,14319 "W1_mean": 0.2008271792118938914320 },14321 "feature_means": {14322 "mean_sent_len": 29.064392616020996,14323 "sd_sent_len": 10.626925328034936,14324 "ttr": 0.6791289389902321,14325 "mtld": 90.65471367342826,14326 "mean_word_len": 4.9895424020299055,14327 "long_word_rate": 0.07632929542542134,14328 "comma_rate": 0.0704550786404526,14329 "semicolon_rate": 0.0033058845904534975,14330 "paren_rate": 0.004546773927836971,14331 "discourse_rate": 0.008892475632350653,14332 "passive_rate": 0.3880534541622229,14333 "nominal_rate": 0.0452773984664956,14334 "first_person_rate": 0.011579878275023167,14335 "subord_rate": 0.0397706922592206,14336 "hedge_rate": 0.008143131076581328,14337 "negation_rate": 0.010603972509980202,14338 "digit_rate": 0.0044179887037361105,14339 "flesch": 34.3099702704760414340 },14341 "probe": {14342 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14343 "probe_acc_heldout": 0.6893203883495146,14344 "eval_mean_p_original": 0.41015487975889775,14345 "eval_frac_classified_original": 0.308469308469308514346 }14347 },14348 "B1_generic_paraphrase": {14349 "vs_original": {14350 "W1_mean_sent_len": 0.38916969579357136,14351 "W1_sd_sent_len": 0.23629716688870034,14352 "W1_ttr": 0.4684778848496878,14353 "W1_mtld": 0.605607411752503,14354 "W1_mean_word_len": 0.519844406325261,14355 "W1_long_word_rate": 0.2332736511682087,14356 "W1_comma_rate": 0.08618582060993601,14357 "W1_semicolon_rate": 0.3545089490942641,14358 "W1_paren_rate": 0.041321710432597726,14359 "W1_discourse_rate": 0.10270384907915305,14360 "W1_passive_rate": 0.15910817494458707,14361 "W1_nominal_rate": 0.06153293947944262,14362 "W1_first_person_rate": 0.06839473979337764,14363 "W1_subord_rate": 0.050681352329049585,14364 "W1_hedge_rate": 0.04080139343039356,14365 "W1_negation_rate": 0.04619365486909494,14366 "W1_digit_rate": 0.024823143734631258,14367 "W1_flesch": 0.6023208057543303,14368 "W1_mean": 0.2272914861293772214369 },14370 "feature_means": {14371 "mean_sent_len": 36.62549258894393,14372 "sd_sent_len": 14.338422076166562,14373 "ttr": 0.6769604039437596,14374 "mtld": 89.97287978589449,14375 "mean_word_len": 5.045652770667571,14376 "long_word_rate": 0.08188585475845127,14377 "comma_rate": 0.07020879646989224,14378 "semicolon_rate": 0.0032950681170817223,14379 "paren_rate": 0.004532376697739831,14380 "discourse_rate": 0.007091119194544618,14381 "passive_rate": 0.507623056730078,14382 "nominal_rate": 0.046185591104896756,14383 "first_person_rate": 0.011584424520352427,14384 "subord_rate": 0.03938271181711672,14385 "hedge_rate": 0.0068245956628749495,14386 "negation_rate": 0.010559073686792394,14387 "digit_rate": 0.004362180533327296,14388 "flesch": 24.942207687201614389 },14390 "probe": {14391 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14392 "probe_acc_heldout": 0.6893203883495146,14393 "eval_mean_p_original": 0.46892420916394123,14394 "eval_frac_classified_original": 0.430846930846930814395 }14396 },14397 "htr-m1-small": {14398 "vs_original": {14399 "W1_mean_sent_len": 0.3013043876159192,14400 "W1_sd_sent_len": 0.3379980497878468,14401 "W1_ttr": 0.22016264343036973,14402 "W1_mtld": 0.19205369732435046,14403 "W1_mean_word_len": 0.07113327455216582,14404 "W1_long_word_rate": 0.05456292646603041,14405 "W1_comma_rate": 0.03853808923572514,14406 "W1_semicolon_rate": 0.38120310300181687,14407 "W1_paren_rate": 0.04069351471561346,14408 "W1_discourse_rate": 0.09059400984831861,14409 "W1_passive_rate": 0.08621686900566157,14410 "W1_nominal_rate": 0.11580099153018,14411 "W1_first_person_rate": 0.06873797879976061,14412 "W1_subord_rate": 0.06532648231245942,14413 "W1_hedge_rate": 0.09180167120956582,14414 "W1_negation_rate": 0.07106289969685747,14415 "W1_digit_rate": 0.02735060612362635,14416 "W1_flesch": 0.19539996153520828,14417 "W1_mean": 0.1361078420106375514418 },14419 "feature_means": {14420 "mean_sent_len": 29.210371441329013,14421 "sd_sent_len": 10.715890997632693,14422 "ttr": 0.6552783297956845,14423 "mtld": 77.9629999659503,14424 "mean_word_len": 4.853331742125417,14425 "long_word_rate": 0.07213203856696959,14426 "comma_rate": 0.06891056357793367,14427 "semicolon_rate": 0.003081729828121073,14428 "paren_rate": 0.0045826790401706525,14429 "discourse_rate": 0.00874704570282098,14430 "passive_rate": 0.4393028167195171,14431 "nominal_rate": 0.044683016920250826,14432 "first_person_rate": 0.011522585243629764,14433 "subord_rate": 0.039739091307140144,14434 "hedge_rate": 0.007561433331974434,14435 "negation_rate": 0.011211101048325478,14436 "digit_rate": 0.0044916010312599335,14437 "flesch": 37.7324911342487314438 },14439 "probe": {14440 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14441 "probe_acc_heldout": 0.6893203883495146,14442 "eval_mean_p_original": 0.5082543215454757,14443 "eval_frac_classified_original": 0.516705516705516714444 }14445 },14446 "htr-m1-tiny-s2": {14447 "vs_original": {14448 "W1_mean_sent_len": 0.31633556160137194,14449 "W1_sd_sent_len": 0.3452408573531074,14450 "W1_ttr": 0.25342694428895,14451 "W1_mtld": 0.22800975747594948,14452 "W1_mean_word_len": 0.07432967046595673,14453 "W1_long_word_rate": 0.0559616667230497,14454 "W1_comma_rate": 0.06456262109245954,14455 "W1_semicolon_rate": 0.42772017381467076,14456 "W1_paren_rate": 0.03894397007074324,14457 "W1_discourse_rate": 0.04777234612967312,14458 "W1_passive_rate": 0.07742460201223358,14459 "W1_nominal_rate": 0.11352156889141196,14460 "W1_first_person_rate": 0.0687012720274541,14461 "W1_subord_rate": 0.04741319670150855,14462 "W1_hedge_rate": 0.10092038213896479,14463 "W1_negation_rate": 0.08916334104076232,14464 "W1_digit_rate": 0.023385783815732995,14465 "W1_flesch": 0.19386399728781942,14466 "W1_mean": 0.142594317385101114467 },14468 "feature_means": {14469 "mean_sent_len": 29.086220241425732,14470 "sd_sent_len": 10.679467573978684,14471 "ttr": 0.6581511239977191,14472 "mtld": 78.9906713969026,14473 "mean_word_len": 4.85588685274342,14474 "long_word_rate": 0.07200378295675298,14475 "comma_rate": 0.0701943295082083,14476 "semicolon_rate": 0.002618074579409703,14477 "paren_rate": 0.004610051430033592,14478 "discourse_rate": 0.008166376367239854,14479 "passive_rate": 0.44415713773659776,14480 "nominal_rate": 0.04476431166923176,14481 "first_person_rate": 0.01152696301835424,14482 "subord_rate": 0.038535054351009825,14483 "hedge_rate": 0.007634136137799233,14484 "negation_rate": 0.011426598692355808,14485 "digit_rate": 0.004484886804658255,14486 "flesch": 37.719163064911414487 },14488 "probe": {14489 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14490 "probe_acc_heldout": 0.6893203883495146,14491 "eval_mean_p_original": 0.5027406606881971,14492 "eval_frac_classified_original": 0.517871017871017914493 }14494 },14495 "htr-m1-tiny-s3": {14496 "vs_original": {14497 "W1_mean_sent_len": 0.30185148302730064,14498 "W1_sd_sent_len": 0.33884117347544235,14499 "W1_ttr": 0.21035717575424517,14500 "W1_mtld": 0.19072629012472986,14501 "W1_mean_word_len": 0.05717939946385625,14502 "W1_long_word_rate": 0.056614577028187056,14503 "W1_comma_rate": 0.07649591902772154,14504 "W1_semicolon_rate": 0.42677518759542105,14505 "W1_paren_rate": 0.039596936911383364,14506 "W1_discourse_rate": 0.05148364305868854,14507 "W1_passive_rate": 0.07755031827168751,14508 "W1_nominal_rate": 0.12000977816275928,14509 "W1_first_person_rate": 0.06475299236774473,14510 "W1_subord_rate": 0.04052162265610049,14511 "W1_hedge_rate": 0.08758669137095276,14512 "W1_negation_rate": 0.09121179576031029,14513 "W1_digit_rate": 0.024746600561626073,14514 "W1_flesch": 0.20129636211296248,14515 "W1_mean": 0.1365332192628399814516 },14517 "feature_means": {14518 "mean_sent_len": 29.19157188907805,14519 "sd_sent_len": 10.72047104442717,14520 "ttr": 0.6545139178366499,14521 "mtld": 77.87973930126057,14522 "mean_word_len": 4.844337700048474,14523 "long_word_rate": 0.07181682547221464,14524 "comma_rate": 0.07071968557248767,14525 "semicolon_rate": 0.0025849345880342247,14526 "paren_rate": 0.004564492781414784,14527 "discourse_rate": 0.008318115672825007,14528 "passive_rate": 0.45285756173936675,14529 "nominal_rate": 0.04460547085387053,14530 "first_person_rate": 0.011491979771047246,14531 "subord_rate": 0.03899689890585511,14532 "hedge_rate": 0.007541661968459187,14533 "negation_rate": 0.01147596923957895,14534 "digit_rate": 0.004481095795205537,14535 "flesch": 37.8655594430624714536 },14537 "probe": {14538 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14539 "probe_acc_heldout": 0.6893203883495146,14540 "eval_mean_p_original": 0.5113454329475815,14541 "eval_frac_classified_original": 0.528360528360528414542 }14543 },14544 "htr-m1-tiny": {14545 "vs_original": {14546 "W1_mean_sent_len": 0.30430663044743317,14547 "W1_sd_sent_len": 0.3371699245774121,14548 "W1_ttr": 0.21926398775574368,14549 "W1_mtld": 0.19281451998024873,14550 "W1_mean_word_len": 0.05586840418181476,14551 "W1_long_word_rate": 0.060908649933118876,14552 "W1_comma_rate": 0.10586278391918706,14553 "W1_semicolon_rate": 0.45391251853490544,14554 "W1_paren_rate": 0.03786913128876686,14555 "W1_discourse_rate": 0.03878270324723189,14556 "W1_passive_rate": 0.08387999986090985,14557 "W1_nominal_rate": 0.12033269067337969,14558 "W1_first_person_rate": 0.06741783136244373,14559 "W1_subord_rate": 0.04635429296849079,14560 "W1_hedge_rate": 0.08447214192993581,14561 "W1_negation_rate": 0.07307811611150326,14562 "W1_digit_rate": 0.023526045313381577,14563 "W1_flesch": 0.2052462572194921,14564 "W1_mean": 0.1395037016280777414565 },14566 "feature_means": {14567 "mean_sent_len": 29.206272386580093,14568 "sd_sent_len": 10.742542116998123,14569 "ttr": 0.6552389533041619,14570 "mtld": 77.97782772649697,14571 "mean_word_len": 4.8442334902811,14572 "long_word_rate": 0.07158082243772149,14573 "comma_rate": 0.07162641818779764,14574 "semicolon_rate": 0.002374540688870884,14575 "paren_rate": 0.004549348452974755,14576 "discourse_rate": 0.008121915360560224,14577 "passive_rate": 0.4464534428301054,14578 "nominal_rate": 0.04458508241336692,14579 "first_person_rate": 0.011476447319837688,14580 "subord_rate": 0.03872942348617556,14581 "hedge_rate": 0.007492457172082932,14582 "negation_rate": 0.011207321078970489,14583 "digit_rate": 0.004469006578304174,14584 "flesch": 37.8982576343845714585 },14586 "probe": {14587 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14588 "probe_acc_heldout": 0.6893203883495146,14589 "eval_mean_p_original": 0.5093232693419081,14590 "eval_frac_classified_original": 0.531080031080031114591 }14592 },14593 "htr-m2-tiny": {14594 "vs_original": {14595 "W1_mean_sent_len": 0.30164387215624716,14596 "W1_sd_sent_len": 0.34279663371198277,14597 "W1_ttr": 0.1925685171058671,14598 "W1_mtld": 0.14956919139532532,14599 "W1_mean_word_len": 0.054405008743843464,14600 "W1_long_word_rate": 0.07997163424322262,14601 "W1_comma_rate": 0.0765170106663005,14602 "W1_semicolon_rate": 0.37996988196191106,14603 "W1_paren_rate": 0.04303098309696555,14604 "W1_discourse_rate": 0.059483755179707165,14605 "W1_passive_rate": 0.07537873540024731,14606 "W1_nominal_rate": 0.12358378731814759,14607 "W1_first_person_rate": 0.0720508184777812,14608 "W1_subord_rate": 0.044717272208562454,14609 "W1_hedge_rate": 0.08422723778490779,14610 "W1_negation_rate": 0.08706018951151225,14611 "W1_digit_rate": 0.025609000911799448,14612 "W1_flesch": 0.23688091732049232,14613 "W1_mean": 0.1349702470663790614614 },14615 "feature_means": {14616 "mean_sent_len": 29.217651386354284,14617 "sd_sent_len": 10.689888264223129,14618 "ttr": 0.6529145194764263,14619 "mtld": 76.71972286885935,14620 "mean_word_len": 4.825607438617277,14621 "long_word_rate": 0.0708646696307006,14622 "comma_rate": 0.07068067484936943,14623 "semicolon_rate": 0.0031216921457473167,14624 "paren_rate": 0.004541514833243233,14625 "discourse_rate": 0.007867905605554228,14626 "passive_rate": 0.45915448425989314,14627 "nominal_rate": 0.04444838727036797,14628 "first_person_rate": 0.011619937921388985,14629 "subord_rate": 0.03880871190682487,14630 "hedge_rate": 0.007487797782427206,14631 "negation_rate": 0.011385526287048272,14632 "digit_rate": 0.00446404684803254,14633 "flesch": 38.4727701279132914634 },14635 "probe": {14636 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14637 "probe_acc_heldout": 0.6893203883495146,14638 "eval_mean_p_original": 0.5228382898899125,14639 "eval_frac_classified_original": 0.559440559440559514640 }14641 },14642 "htr-m3light-tiny": {14643 "vs_original": {14644 "W1_mean_sent_len": 0.30225976312653047,14645 "W1_sd_sent_len": 0.34089918199880953,14646 "W1_ttr": 0.17902895298743315,14647 "W1_mtld": 0.12629214021801152,14648 "W1_mean_word_len": 0.06849694237948457,14649 "W1_long_word_rate": 0.08111564985372305,14650 "W1_comma_rate": 0.1132551358977359,14651 "W1_semicolon_rate": 0.4000169353606362,14652 "W1_paren_rate": 0.04096958710387595,14653 "W1_discourse_rate": 0.054252092716891645,14654 "W1_passive_rate": 0.07794072330270314,14655 "W1_nominal_rate": 0.13686459866919964,14656 "W1_first_person_rate": 0.07070260177823207,14657 "W1_subord_rate": 0.053276336135049236,14658 "W1_hedge_rate": 0.09017582229913557,14659 "W1_negation_rate": 0.06668320052217579,14660 "W1_digit_rate": 0.025939353848576194,14661 "W1_flesch": 0.24613392920185026,14662 "W1_mean": 0.1374612748555585414663 },14664 "feature_means": {14665 "mean_sent_len": 29.198112384376692,14666 "sd_sent_len": 10.69141234581495,14667 "ttr": 0.6517748352491508,14668 "mtld": 76.0715930744529,14669 "mean_word_len": 4.817794986689276,14670 "long_word_rate": 0.0708180320218685,14671 "comma_rate": 0.07179897559948331,14672 "semicolon_rate": 0.0029416286625746765,14673 "paren_rate": 0.004532702092859857,14674 "discourse_rate": 0.008082209278141173,14675 "passive_rate": 0.4615906953060642,14676 "nominal_rate": 0.044026837775173015,14677 "first_person_rate": 0.011652519146818988,14678 "subord_rate": 0.038329666403816395,14679 "hedge_rate": 0.00754711360221443,14680 "negation_rate": 0.011167041035897367,14681 "digit_rate": 0.004514546918401259,14682 "flesch": 38.6589445529217514683 },14684 "probe": {14685 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14686 "probe_acc_heldout": 0.6893203883495146,14687 "eval_mean_p_original": 0.5261776557241575,14688 "eval_frac_classified_original": 0.56798756798756814689 }14690 },14691 "htr-m3tokenonly-tiny-s2": {14692 "vs_original": {14693 "W1_mean_sent_len": 0.31401782735779366,14694 "W1_sd_sent_len": 0.3461515120188921,14695 "W1_ttr": 0.2650273068907825,14696 "W1_mtld": 0.2539728048248621,14697 "W1_mean_word_len": 0.07209810683486445,14698 "W1_long_word_rate": 0.0565297841428816,14699 "W1_comma_rate": 0.05796127768430398,14700 "W1_semicolon_rate": 0.33462151102228416,14701 "W1_paren_rate": 0.04095327362017392,14702 "W1_discourse_rate": 0.0622062379258104,14703 "W1_passive_rate": 0.06933505126825686,14704 "W1_nominal_rate": 0.13147141359303924,14705 "W1_first_person_rate": 0.06492687839884412,14706 "W1_subord_rate": 0.057981727690326744,14707 "W1_hedge_rate": 0.0991932924440558,14708 "W1_negation_rate": 0.07996686813701713,14709 "W1_digit_rate": 0.025647386613349383,14710 "W1_flesch": 0.19493835051975603,14711 "W1_mean": 0.1403889228326274714712 },14713 "feature_means": {14714 "mean_sent_len": 29.0919948458749,14715 "sd_sent_len": 10.654527821800622,14716 "ttr": 0.6593005028347221,14717 "mtld": 79.74810438409409,14718 "mean_word_len": 4.855626051147027,14719 "long_word_rate": 0.07196616385037487,14720 "comma_rate": 0.06996313605672247,14721 "semicolon_rate": 0.0034682047442890314,14722 "paren_rate": 0.004564853013559889,14723 "discourse_rate": 0.0082278104006121,14724 "passive_rate": 0.45205916704081844,14725 "nominal_rate": 0.04422363730005329,14726 "first_person_rate": 0.011664516377411435,14727 "subord_rate": 0.0381802948767621,14728 "hedge_rate": 0.007648059812132582,14729 "negation_rate": 0.011257148174813606,14730 "digit_rate": 0.004503404538196692,14731 "flesch": 37.7359494153006414732 },14733 "probe": {14734 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14735 "probe_acc_heldout": 0.6893203883495146,14736 "eval_mean_p_original": 0.5011829136592061,14737 "eval_frac_classified_original": 0.517871017871017914738 }14739 },14740 "htr-m3tokenonly-tiny": {14741 "vs_original": {14742 "W1_mean_sent_len": 0.32287117475741467,14743 "W1_sd_sent_len": 0.3567274159009958,14744 "W1_ttr": 0.2856058559909407,14745 "W1_mtld": 0.27137654648660176,14746 "W1_mean_word_len": 0.08689417016339077,14747 "W1_long_word_rate": 0.05324642509079446,14748 "W1_comma_rate": 0.0653716139093598,14749 "W1_semicolon_rate": 0.39292151970364114,14750 "W1_paren_rate": 0.04439003121220262,14751 "W1_discourse_rate": 0.0638948842015203,14752 "W1_passive_rate": 0.08589869973548446,14753 "W1_nominal_rate": 0.12198706678768288,14754 "W1_first_person_rate": 0.06762262230673591,14755 "W1_subord_rate": 0.041108288580439536,14756 "W1_hedge_rate": 0.08175188015950637,14757 "W1_negation_rate": 0.0904958537289968,14758 "W1_digit_rate": 0.023844025481192424,14759 "W1_flesch": 0.19263315111367324,14760 "W1_mean": 0.1471467347394763114761 },14762 "feature_means": {14763 "mean_sent_len": 28.97335256684441,14764 "sd_sent_len": 10.582108511929462,14765 "ttr": 0.6610786371204179,14766 "mtld": 80.29725602406592,14767 "mean_word_len": 4.8626168848492695,14768 "long_word_rate": 0.07208023746895131,14769 "comma_rate": 0.07027342101994241,14770 "semicolon_rate": 0.002917582039140102,14771 "paren_rate": 0.004559867392886465,14772 "discourse_rate": 0.008267901392974234,14773 "passive_rate": 0.4306543117706227,14774 "nominal_rate": 0.04450914852419556,14775 "first_person_rate": 0.011531425503316612,14776 "subord_rate": 0.03892268892416564,14777 "hedge_rate": 0.0074868612530391695,14778 "negation_rate": 0.011415076892492132,14779 "digit_rate": 0.004480862024444506,14780 "flesch": 37.66527514755444614781 },14782 "probe": {14783 "probe_auc_orig_vs_rewrite": 0.7370499100071392,14784 "probe_acc_heldout": 0.6893203883495146,14785 "eval_mean_p_original": 0.49271771542161863,14786 "eval_frac_classified_original": 0.4883449883449883514787 }14788 }14789 },14790 "confirmatory": {14791 "preregistration_frozen": true,14792 "n_boot": 1000014793 }14794}