Repository Public Research preview
1{2 "created_at": "2026-11-10T17:20:47Z",3 "git": {4 "commit": "883ce93e2f627cf3d42040460687c511ef436337",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": 266,31 "systems": {32 "B0_identity": {33 "overall": {34 "n": 266,35 "chrf": {36 "mean": 80.31804439593354,37 "ci_low": 79.11528314066213,38 "ci_high": 81.70958308277454,39 "n_items": 266,40 "n_groups": 5541 },42 "edit_sim": {43 "mean": 0.7836377372276923,44 "ci_low": 0.7716056059550513,45 "ci_high": 0.7956444532206056,46 "n_items": 266,47 "n_groups": 5548 },49 "rougeL": {50 "mean": 0.8025524046351549,51 "ci_low": 0.7907201719897177,52 "ci_high": 0.8166829411150309,53 "n_items": 266,54 "n_groups": 5555 },56 "exact_match": {57 "mean": 0.0,58 "ci_low": 0.0,59 "ci_high": 0.0,60 "n_items": 266,61 "n_groups": 5562 },63 "number_recall": {64 "mean": 1.0,65 "ci_low": 1.0,66 "ci_high": 1.0,67 "n_items": 266,68 "n_groups": 5569 },70 "placeholders_exact": {71 "mean": 1.0,72 "ci_low": 1.0,73 "ci_high": 1.0,74 "n_items": 266,75 "n_groups": 5576 }77 },78 "by_variant": {79 "H1": {80 "n": 128,81 "chrf": {82 "mean": 78.727127756947,83 "ci_low": 77.49025127709176,84 "ci_high": 80.19265015807015,85 "n_items": 128,86 "n_groups": 5087 },88 "edit_sim": {89 "mean": 0.749381523939677,90 "ci_low": 0.7332499102633466,91 "ci_high": 0.7641672829526498,92 "n_items": 128,93 "n_groups": 5094 },95 "rougeL": {96 "mean": 0.7757615494501704,97 "ci_low": 0.7622833448469268,98 "ci_high": 0.7906982286309417,99 "n_items": 128,100 "n_groups": 50101 },102 "exact_match": {103 "mean": 0.0,104 "ci_low": 0.0,105 "ci_high": 0.0,106 "n_items": 128,107 "n_groups": 50108 },109 "number_recall": {110 "mean": 1.0,111 "ci_low": 1.0,112 "ci_high": 1.0,113 "n_items": 128,114 "n_groups": 50115 },116 "placeholders_exact": {117 "mean": 1.0,118 "ci_low": 1.0,119 "ci_high": 1.0,120 "n_items": 128,121 "n_groups": 50122 }123 },124 "H2": {125 "n": 138,126 "chrf": {127 "mean": 81.79367722050074,128 "ci_low": 80.56715601939317,129 "ci_high": 83.16149480371993,130 "n_items": 138,131 "n_groups": 53132 },133 "edit_sim": {134 "mean": 0.8154116162194744,135 "ci_low": 0.803044634419047,136 "ci_high": 0.8281632205086704,137 "n_items": 138,138 "n_groups": 53139 },140 "rougeL": {141 "mean": 0.8274018935023868,142 "ci_low": 0.8141996868699847,143 "ci_high": 0.8423373522498734,144 "n_items": 138,145 "n_groups": 53146 },147 "exact_match": {148 "mean": 0.0,149 "ci_low": 0.0,150 "ci_high": 0.0,151 "n_items": 138,152 "n_groups": 53153 },154 "number_recall": {155 "mean": 1.0,156 "ci_low": 1.0,157 "ci_high": 1.0,158 "n_items": 138,159 "n_groups": 53160 },161 "placeholders_exact": {162 "mean": 1.0,163 "ci_low": 1.0,164 "ci_high": 1.0,165 "n_items": 138,166 "n_groups": 53167 }168 }169 },170 "by_discipline": {171 "biomedicine": {172 "n": 57,173 "chrf": {174 "mean": 80.64350848543496,175 "ci_low": 78.55899324690924,176 "ci_high": 82.57637370898476,177 "n_items": 57,178 "n_groups": 26179 },180 "edit_sim": {181 "mean": 0.7845067741202865,182 "ci_low": 0.7635893067777685,183 "ci_high": 0.8053235751915107,184 "n_items": 57,185 "n_groups": 26186 },187 "rougeL": {188 "mean": 0.80597193961719,189 "ci_low": 0.786541290109451,190 "ci_high": 0.8233412723063528,191 "n_items": 57,192 "n_groups": 26193 },194 "exact_match": {195 "mean": 0.0,196 "ci_low": 0.0,197 "ci_high": 0.0,198 "n_items": 57,199 "n_groups": 26200 },201 "number_recall": {202 "mean": 1.0,203 "ci_low": 1.0,204 "ci_high": 1.0,205 "n_items": 57,206 "n_groups": 26207 },208 "placeholders_exact": {209 "mean": 1.0,210 "ci_low": 1.0,211 "ci_high": 1.0,212 "n_items": 57,213 "n_groups": 26214 }215 },216 "computer_science": {217 "n": 30,218 "chrf": {219 "mean": 79.11282443681444,220 "ci_low": 76.0656626775851,221 "ci_high": 85.20714795527309,222 "n_items": 30,223 "n_groups": 2224 },225 "edit_sim": {226 "mean": 0.7957560238493924,227 "ci_low": 0.7803916960339391,228 "ci_high": 0.8264846794802996,229 "n_items": 30,230 "n_groups": 2231 },232 "rougeL": {233 "mean": 0.8027352965297111,234 "ci_low": 0.7715193608755697,235 "ci_high": 0.8651671678379935,236 "n_items": 30,237 "n_groups": 2238 },239 "exact_match": {240 "mean": 0.0,241 "ci_low": 0.0,242 "ci_high": 0.0,243 "n_items": 30,244 "n_groups": 2245 },246 "number_recall": {247 "mean": 1.0,248 "ci_low": 1.0,249 "ci_high": 1.0,250 "n_items": 30,251 "n_groups": 2252 },253 "placeholders_exact": {254 "mean": 1.0,255 "ci_low": 1.0,256 "ci_high": 1.0,257 "n_items": 30,258 "n_groups": 2259 }260 },261 "earth_sciences": {262 "n": 32,263 "chrf": {264 "mean": 79.15005272122849,265 "ci_low": 74.9063044946763,266 "ci_high": 81.98447361565582,267 "n_items": 32,268 "n_groups": 3269 },270 "edit_sim": {271 "mean": 0.7508988031642799,272 "ci_low": 0.729536692063084,273 "ci_high": 0.7641347171601056,274 "n_items": 32,275 "n_groups": 3276 },277 "rougeL": {278 "mean": 0.78001684122484,279 "ci_low": 0.7464267726113513,280 "ci_high": 0.803195073783586,281 "n_items": 32,282 "n_groups": 3283 },284 "exact_match": {285 "mean": 0.0,286 "ci_low": 0.0,287 "ci_high": 0.0,288 "n_items": 32,289 "n_groups": 3290 },291 "number_recall": {292 "mean": 1.0,293 "ci_low": 1.0,294 "ci_high": 1.0,295 "n_items": 32,296 "n_groups": 3297 },298 "placeholders_exact": {299 "mean": 1.0,300 "ci_low": 1.0,301 "ci_high": 1.0,302 "n_items": 32,303 "n_groups": 3304 }305 },306 "economics": {307 "n": 30,308 "chrf": {309 "mean": 78.7226961176012,310 "ci_low": 78.7226961176012,311 "ci_high": 78.7226961176012,312 "n_items": 30,313 "n_groups": 1314 },315 "edit_sim": {316 "mean": 0.791740741073034,317 "ci_low": 0.791740741073034,318 "ci_high": 0.791740741073034,319 "n_items": 30,320 "n_groups": 1321 },322 "rougeL": {323 "mean": 0.7851716513586875,324 "ci_low": 0.7851716513586875,325 "ci_high": 0.7851716513586875,326 "n_items": 30,327 "n_groups": 1328 },329 "exact_match": {330 "mean": 0.0,331 "ci_low": 0.0,332 "ci_high": 0.0,333 "n_items": 30,334 "n_groups": 1335 },336 "number_recall": {337 "mean": 1.0,338 "ci_low": 1.0,339 "ci_high": 1.0,340 "n_items": 30,341 "n_groups": 1342 },343 "placeholders_exact": {344 "mean": 1.0,345 "ci_low": 1.0,346 "ci_high": 1.0,347 "n_items": 30,348 "n_groups": 1349 }350 },351 "engineering": {352 "n": 6,353 "chrf": {354 "mean": 82.42895427470594,355 "ci_low": 82.42895427470594,356 "ci_high": 82.42895427470594,357 "n_items": 6,358 "n_groups": 1359 },360 "edit_sim": {361 "mean": 0.7862135141395434,362 "ci_low": 0.7862135141395434,363 "ci_high": 0.7862135141395434,364 "n_items": 6,365 "n_groups": 1366 },367 "rougeL": {368 "mean": 0.7891288350995262,369 "ci_low": 0.7891288350995262,370 "ci_high": 0.7891288350995262,371 "n_items": 6,372 "n_groups": 1373 },374 "exact_match": {375 "mean": 0.0,376 "ci_low": 0.0,377 "ci_high": 0.0,378 "n_items": 6,379 "n_groups": 1380 },381 "number_recall": {382 "mean": 1.0,383 "ci_low": 1.0,384 "ci_high": 1.0,385 "n_items": 6,386 "n_groups": 1387 },388 "placeholders_exact": {389 "mean": 1.0,390 "ci_low": 1.0,391 "ci_high": 1.0,392 "n_items": 6,393 "n_groups": 1394 }395 },396 "life_sciences": {397 "n": 49,398 "chrf": {399 "mean": 81.71900817273567,400 "ci_low": 79.88524360070795,401 "ci_high": 83.6999877441269,402 "n_items": 49,403 "n_groups": 16404 },405 "edit_sim": {406 "mean": 0.7970636695518315,407 "ci_low": 0.7780612722860379,408 "ci_high": 0.817258521071411,409 "n_items": 49,410 "n_groups": 16411 },412 "rougeL": {413 "mean": 0.8230162333226454,414 "ci_low": 0.8064525289160438,415 "ci_high": 0.8413041697807002,416 "n_items": 49,417 "n_groups": 16418 },419 "exact_match": {420 "mean": 0.0,421 "ci_low": 0.0,422 "ci_high": 0.0,423 "n_items": 49,424 "n_groups": 16425 },426 "number_recall": {427 "mean": 1.0,428 "ci_low": 1.0,429 "ci_high": 1.0,430 "n_items": 49,431 "n_groups": 16432 },433 "placeholders_exact": {434 "mean": 1.0,435 "ci_low": 1.0,436 "ci_high": 1.0,437 "n_items": 49,438 "n_groups": 16439 }440 },441 "social_sciences": {442 "n": 38,443 "chrf": {444 "mean": 82.33350419195449,445 "ci_low": 76.41597186727252,446 "ci_high": 84.90814186259651,447 "n_items": 38,448 "n_groups": 4449 },450 "edit_sim": {451 "mean": 0.8087632478923349,452 "ci_low": 0.7697099638124423,453 "ci_high": 0.8367251491733773,454 "n_items": 38,455 "n_groups": 4456 },457 "rougeL": {458 "mean": 0.8268725017331687,459 "ci_low": 0.7550622400634474,460 "ci_high": 0.8521228309995911,461 "n_items": 38,462 "n_groups": 4463 },464 "exact_match": {465 "mean": 0.0,466 "ci_low": 0.0,467 "ci_high": 0.0,468 "n_items": 38,469 "n_groups": 4470 },471 "number_recall": {472 "mean": 1.0,473 "ci_low": 1.0,474 "ci_high": 1.0,475 "n_items": 38,476 "n_groups": 4477 },478 "placeholders_exact": {479 "mean": 1.0,480 "ci_low": 1.0,481 "ci_high": 1.0,482 "n_items": 38,483 "n_groups": 4484 }485 },486 "statistics": {487 "n": 24,488 "chrf": {489 "mean": 78.02392652209136,490 "ci_low": 77.87500119011926,491 "ci_high": 78.32177718603556,492 "n_items": 24,493 "n_groups": 2494 },495 "edit_sim": {496 "mean": 0.732111792333095,497 "ci_low": 0.7130247777973883,498 "ci_high": 0.7416552996009484,499 "n_items": 24,500 "n_groups": 2501 },502 "rougeL": {503 "mean": 0.7690445087357216,504 "ci_low": 0.7670030154412741,505 "ci_high": 0.7731274953246166,506 "n_items": 24,507 "n_groups": 2508 },509 "exact_match": {510 "mean": 0.0,511 "ci_low": 0.0,512 "ci_high": 0.0,513 "n_items": 24,514 "n_groups": 2515 },516 "number_recall": {517 "mean": 1.0,518 "ci_low": 1.0,519 "ci_high": 1.0,520 "n_items": 24,521 "n_groups": 2522 },523 "placeholders_exact": {524 "mean": 1.0,525 "ci_low": 1.0,526 "ci_high": 1.0,527 "n_items": 24,528 "n_groups": 2529 }530 }531 },532 "by_era": {533 "1980-1999": {534 "n": 2,535 "chrf": {536 "mean": 82.41337960853802,537 "ci_low": 78.44719843396761,538 "ci_high": 86.37956078310843,539 "n_items": 2,540 "n_groups": 2541 },542 "edit_sim": {543 "mean": 0.8329328762713027,544 "ci_low": 0.8215835140997831,545 "ci_high": 0.8442822384428224,546 "n_items": 2,547 "n_groups": 2548 },549 "rougeL": {550 "mean": 0.8406899443013715,551 "ci_low": 0.833922261484099,552 "ci_high": 0.8474576271186439,553 "n_items": 2,554 "n_groups": 2555 },556 "exact_match": {557 "mean": 0.0,558 "ci_low": 0.0,559 "ci_high": 0.0,560 "n_items": 2,561 "n_groups": 2562 },563 "number_recall": {564 "mean": 1.0,565 "ci_low": 1.0,566 "ci_high": 1.0,567 "n_items": 2,568 "n_groups": 2569 },570 "placeholders_exact": {571 "mean": 1.0,572 "ci_low": 1.0,573 "ci_high": 1.0,574 "n_items": 2,575 "n_groups": 2576 }577 },578 "2000-2009": {579 "n": 30,580 "chrf": {581 "mean": 80.81608664110105,582 "ci_low": 78.98026750995969,583 "ci_high": 83.6280770544585,584 "n_items": 30,585 "n_groups": 7586 },587 "edit_sim": {588 "mean": 0.7780534082277536,589 "ci_low": 0.7448834489916596,590 "ci_high": 0.8254739535608765,591 "n_items": 30,592 "n_groups": 7593 },594 "rougeL": {595 "mean": 0.806724310456499,596 "ci_low": 0.7852536028415021,597 "ci_high": 0.8465269377562444,598 "n_items": 30,599 "n_groups": 7600 },601 "exact_match": {602 "mean": 0.0,603 "ci_low": 0.0,604 "ci_high": 0.0,605 "n_items": 30,606 "n_groups": 7607 },608 "number_recall": {609 "mean": 1.0,610 "ci_low": 1.0,611 "ci_high": 1.0,612 "n_items": 30,613 "n_groups": 7614 },615 "placeholders_exact": {616 "mean": 1.0,617 "ci_low": 1.0,618 "ci_high": 1.0,619 "n_items": 30,620 "n_groups": 7621 }622 },623 "2010-2017": {624 "n": 234,625 "chrf": {626 "mean": 80.2362839780693,627 "ci_low": 78.80865716001372,628 "ci_high": 81.74089773406546,629 "n_items": 234,630 "n_groups": 46631 },632 "edit_sim": {633 "mean": 0.7839323508683371,634 "ci_low": 0.7708400813591778,635 "ci_high": 0.796561055144828,636 "n_items": 234,637 "n_groups": 46638 },639 "rougeL": {640 "mean": 0.8016915830369805,641 "ci_low": 0.7876591405377054,642 "ci_high": 0.8168671402100529,643 "n_items": 234,644 "n_groups": 46645 },646 "exact_match": {647 "mean": 0.0,648 "ci_low": 0.0,649 "ci_high": 0.0,650 "n_items": 234,651 "n_groups": 46652 },653 "number_recall": {654 "mean": 1.0,655 "ci_low": 1.0,656 "ci_high": 1.0,657 "n_items": 234,658 "n_groups": 46659 },660 "placeholders_exact": {661 "mean": 1.0,662 "ci_low": 1.0,663 "ci_high": 1.0,664 "n_items": 234,665 "n_groups": 46666 }667 }668 },669 "by_role": {670 "abstract": {671 "n": 28,672 "chrf": {673 "mean": 84.05389256868962,674 "ci_low": 81.70448252683306,675 "ci_high": 86.26340535039317,676 "n_items": 28,677 "n_groups": 15678 },679 "edit_sim": {680 "mean": 0.8217033778927691,681 "ci_low": 0.7874341684335896,682 "ci_high": 0.8563878448611631,683 "n_items": 28,684 "n_groups": 15685 },686 "rougeL": {687 "mean": 0.8344491404003642,688 "ci_low": 0.8008194808182392,689 "ci_high": 0.8678343580768961,690 "n_items": 28,691 "n_groups": 15692 },693 "exact_match": {694 "mean": 0.0,695 "ci_low": 0.0,696 "ci_high": 0.0,697 "n_items": 28,698 "n_groups": 15699 },700 "number_recall": {701 "mean": 1.0,702 "ci_low": 1.0,703 "ci_high": 1.0,704 "n_items": 28,705 "n_groups": 15706 },707 "placeholders_exact": {708 "mean": 1.0,709 "ci_low": 1.0,710 "ci_high": 1.0,711 "n_items": 28,712 "n_groups": 15713 }714 },715 "background": {716 "n": 16,717 "chrf": {718 "mean": 81.24928526514356,719 "ci_low": 76.00106644883027,720 "ci_high": 85.66831814815465,721 "n_items": 16,722 "n_groups": 7723 },724 "edit_sim": {725 "mean": 0.7899211102557473,726 "ci_low": 0.7377227056316705,727 "ci_high": 0.8326864081645722,728 "n_items": 16,729 "n_groups": 7730 },731 "rougeL": {732 "mean": 0.8184827695940686,733 "ci_low": 0.7761455720713449,734 "ci_high": 0.8526856505448923,735 "n_items": 16,736 "n_groups": 7737 },738 "exact_match": {739 "mean": 0.0,740 "ci_low": 0.0,741 "ci_high": 0.0,742 "n_items": 16,743 "n_groups": 7744 },745 "number_recall": {746 "mean": 1.0,747 "ci_low": 1.0,748 "ci_high": 1.0,749 "n_items": 16,750 "n_groups": 7751 },752 "placeholders_exact": {753 "mean": 1.0,754 "ci_low": 1.0,755 "ci_high": 1.0,756 "n_items": 16,757 "n_groups": 7758 }759 },760 "conclusion": {761 "n": 17,762 "chrf": {763 "mean": 78.89421921353198,764 "ci_low": 75.28865728660307,765 "ci_high": 82.27388488036102,766 "n_items": 17,767 "n_groups": 9768 },769 "edit_sim": {770 "mean": 0.7631367746406635,771 "ci_low": 0.7301941332974745,772 "ci_high": 0.7909544008979003,773 "n_items": 17,774 "n_groups": 9775 },776 "rougeL": {777 "mean": 0.780694140855345,778 "ci_low": 0.7484111274555051,779 "ci_high": 0.8116336062737028,780 "n_items": 17,781 "n_groups": 9782 },783 "exact_match": {784 "mean": 0.0,785 "ci_low": 0.0,786 "ci_high": 0.0,787 "n_items": 17,788 "n_groups": 9789 },790 "number_recall": {791 "mean": 1.0,792 "ci_low": 1.0,793 "ci_high": 1.0,794 "n_items": 17,795 "n_groups": 9796 },797 "placeholders_exact": {798 "mean": 1.0,799 "ci_low": 1.0,800 "ci_high": 1.0,801 "n_items": 17,802 "n_groups": 9803 }804 },805 "data": {806 "n": 25,807 "chrf": {808 "mean": 80.8948222028621,809 "ci_low": 77.11839233689868,810 "ci_high": 84.46087615187382,811 "n_items": 25,812 "n_groups": 10813 },814 "edit_sim": {815 "mean": 0.7629296270148483,816 "ci_low": 0.7373446390593601,817 "ci_high": 0.7952345938445297,818 "n_items": 25,819 "n_groups": 10820 },821 "rougeL": {822 "mean": 0.7929363538754521,823 "ci_low": 0.75486795118461,824 "ci_high": 0.8293064966079455,825 "n_items": 25,826 "n_groups": 10827 },828 "exact_match": {829 "mean": 0.0,830 "ci_low": 0.0,831 "ci_high": 0.0,832 "n_items": 25,833 "n_groups": 10834 },835 "number_recall": {836 "mean": 1.0,837 "ci_low": 1.0,838 "ci_high": 1.0,839 "n_items": 25,840 "n_groups": 10841 },842 "placeholders_exact": {843 "mean": 1.0,844 "ci_low": 1.0,845 "ci_high": 1.0,846 "n_items": 25,847 "n_groups": 10848 }849 },850 "discussion": {851 "n": 34,852 "chrf": {853 "mean": 80.4111742290417,854 "ci_low": 77.56871743755876,855 "ci_high": 82.5280609525651,856 "n_items": 34,857 "n_groups": 14858 },859 "edit_sim": {860 "mean": 0.7852466476858705,861 "ci_low": 0.7622131623980205,862 "ci_high": 0.808510861963164,863 "n_items": 34,864 "n_groups": 14865 },866 "rougeL": {867 "mean": 0.8007832279948224,868 "ci_low": 0.7639868857501393,869 "ci_high": 0.82918147369946,870 "n_items": 34,871 "n_groups": 14872 },873 "exact_match": {874 "mean": 0.0,875 "ci_low": 0.0,876 "ci_high": 0.0,877 "n_items": 34,878 "n_groups": 14879 },880 "number_recall": {881 "mean": 1.0,882 "ci_low": 1.0,883 "ci_high": 1.0,884 "n_items": 34,885 "n_groups": 14886 },887 "placeholders_exact": {888 "mean": 1.0,889 "ci_low": 1.0,890 "ci_high": 1.0,891 "n_items": 34,892 "n_groups": 14893 }894 },895 "introduction": {896 "n": 31,897 "chrf": {898 "mean": 78.97189245341035,899 "ci_low": 76.71440657252232,900 "ci_high": 81.51376996347966,901 "n_items": 31,902 "n_groups": 13903 },904 "edit_sim": {905 "mean": 0.7643025805871334,906 "ci_low": 0.7197425851539277,907 "ci_high": 0.8027307677013716,908 "n_items": 31,909 "n_groups": 13910 },911 "rougeL": {912 "mean": 0.7790040662653562,913 "ci_low": 0.7465304087143725,914 "ci_high": 0.8101175318017297,915 "n_items": 31,916 "n_groups": 13917 },918 "exact_match": {919 "mean": 0.0,920 "ci_low": 0.0,921 "ci_high": 0.0,922 "n_items": 31,923 "n_groups": 13924 },925 "number_recall": {926 "mean": 1.0,927 "ci_low": 1.0,928 "ci_high": 1.0,929 "n_items": 31,930 "n_groups": 13931 },932 "placeholders_exact": {933 "mean": 1.0,934 "ci_low": 1.0,935 "ci_high": 1.0,936 "n_items": 31,937 "n_groups": 13938 }939 },940 "limitations": {941 "n": 14,942 "chrf": {943 "mean": 80.87691593295744,944 "ci_low": 80.0139068652156,945 "ci_high": 81.6785911832181,946 "n_items": 14,947 "n_groups": 4948 },949 "edit_sim": {950 "mean": 0.8052638298336493,951 "ci_low": 0.7761332648992643,952 "ci_high": 0.8256957559395313,953 "n_items": 14,954 "n_groups": 4955 },956 "rougeL": {957 "mean": 0.8192202643563569,958 "ci_low": 0.7948200639416184,959 "ci_high": 0.8331162001423364,960 "n_items": 14,961 "n_groups": 4962 },963 "exact_match": {964 "mean": 0.0,965 "ci_low": 0.0,966 "ci_high": 0.0,967 "n_items": 14,968 "n_groups": 4969 },970 "number_recall": {971 "mean": 1.0,972 "ci_low": 1.0,973 "ci_high": 1.0,974 "n_items": 14,975 "n_groups": 4976 },977 "placeholders_exact": {978 "mean": 1.0,979 "ci_low": 1.0,980 "ci_high": 1.0,981 "n_items": 14,982 "n_groups": 4983 }984 },985 "methods": {986 "n": 32,987 "chrf": {988 "mean": 80.34731931670102,989 "ci_low": 77.71062470295959,990 "ci_high": 82.96029390165484,991 "n_items": 32,992 "n_groups": 12993 },994 "edit_sim": {995 "mean": 0.7974426502648211,996 "ci_low": 0.7777677991829182,997 "ci_high": 0.8164316668548032,998 "n_items": 32,999 "n_groups": 121000 },1001 "rougeL": {1002 "mean": 0.8161707827028571,1003 "ci_low": 0.79542681206505,1004 "ci_high": 0.8391124779014244,1005 "n_items": 32,1006 "n_groups": 121007 },1008 "exact_match": {1009 "mean": 0.0,1010 "ci_low": 0.0,1011 "ci_high": 0.0,1012 "n_items": 32,1013 "n_groups": 121014 },1015 "number_recall": {1016 "mean": 1.0,1017 "ci_low": 1.0,1018 "ci_high": 1.0,1019 "n_items": 32,1020 "n_groups": 121021 },1022 "placeholders_exact": {1023 "mean": 1.0,1024 "ci_low": 1.0,1025 "ci_high": 1.0,1026 "n_items": 32,1027 "n_groups": 121028 }1029 },1030 "other": {1031 "n": 22,1032 "chrf": {1033 "mean": 79.105821832827,1034 "ci_low": 73.64655955254288,1035 "ci_high": 83.20772435073955,1036 "n_items": 22,1037 "n_groups": 81038 },1039 "edit_sim": {1040 "mean": 0.7830436336472076,1041 "ci_low": 0.7346900118584614,1042 "ci_high": 0.8219853733976262,1043 "n_items": 22,1044 "n_groups": 81045 },1046 "rougeL": {1047 "mean": 0.7879633290057615,1048 "ci_low": 0.7297930962992475,1049 "ci_high": 0.8327230449816243,1050 "n_items": 22,1051 "n_groups": 81052 },1053 "exact_match": {1054 "mean": 0.0,1055 "ci_low": 0.0,1056 "ci_high": 0.0,1057 "n_items": 22,1058 "n_groups": 81059 },1060 "number_recall": {1061 "mean": 1.0,1062 "ci_low": 1.0,1063 "ci_high": 1.0,1064 "n_items": 22,1065 "n_groups": 81066 },1067 "placeholders_exact": {1068 "mean": 1.0,1069 "ci_low": 1.0,1070 "ci_high": 1.0,1071 "n_items": 22,1072 "n_groups": 81073 }1074 },1075 "related_work": {1076 "n": 2,1077 "chrf": {1078 "mean": 82.84466015485417,1079 "ci_low": 82.84466015485417,1080 "ci_high": 82.84466015485417,1081 "n_items": 2,1082 "n_groups": 11083 },1084 "edit_sim": {1085 "mean": 0.8124664159054271,1086 "ci_low": 0.8124664159054271,1087 "ci_high": 0.8124664159054271,1088 "n_items": 2,1089 "n_groups": 11090 },1091 "rougeL": {1092 "mean": 0.8354964115769326,1093 "ci_low": 0.8354964115769326,1094 "ci_high": 0.8354964115769326,1095 "n_items": 2,1096 "n_groups": 11097 },1098 "exact_match": {1099 "mean": 0.0,1100 "ci_low": 0.0,1101 "ci_high": 0.0,1102 "n_items": 2,1103 "n_groups": 11104 },1105 "number_recall": {1106 "mean": 1.0,1107 "ci_low": 1.0,1108 "ci_high": 1.0,1109 "n_items": 2,1110 "n_groups": 11111 },1112 "placeholders_exact": {1113 "mean": 1.0,1114 "ci_low": 1.0,1115 "ci_high": 1.0,1116 "n_items": 2,1117 "n_groups": 11118 }1119 },1120 "results": {1121 "n": 26,1122 "chrf": {1123 "mean": 77.92782304710794,1124 "ci_low": 75.11723608407041,1125 "ci_high": 81.23883099080281,1126 "n_items": 26,1127 "n_groups": 101128 },1129 "edit_sim": {1130 "mean": 0.7526278221190071,1131 "ci_low": 0.7180843345271481,1132 "ci_high": 0.7916356070548689,1133 "n_items": 26,1134 "n_groups": 101135 },1136 "rougeL": {1137 "mean": 0.7908058121216082,1138 "ci_low": 0.7639712378710721,1139 "ci_high": 0.8225779362010247,1140 "n_items": 26,1141 "n_groups": 101142 },1143 "exact_match": {1144 "mean": 0.0,1145 "ci_low": 0.0,1146 "ci_high": 0.0,1147 "n_items": 26,1148 "n_groups": 101149 },1150 "number_recall": {1151 "mean": 1.0,1152 "ci_low": 1.0,1153 "ci_high": 1.0,1154 "n_items": 26,1155 "n_groups": 101156 },1157 "placeholders_exact": {1158 "mean": 1.0,1159 "ci_low": 1.0,1160 "ci_high": 1.0,1161 "n_items": 26,1162 "n_groups": 101163 }1164 },1165 "theory": {1166 "n": 19,1167 "chrf": {1168 "mean": 80.52050213449657,1169 "ci_low": 78.32455536703446,1170 "ci_high": 83.87855667880214,1171 "n_items": 19,1172 "n_groups": 61173 },1174 "edit_sim": {1175 "mean": 0.7974104905476012,1176 "ci_low": 0.778049993861382,1177 "ci_high": 0.8233088762509583,1178 "n_items": 19,1179 "n_groups": 61180 },1181 "rougeL": {1182 "mean": 0.8102099166755715,1183 "ci_low": 0.7932618748735198,1184 "ci_high": 0.8391015165554253,1185 "n_items": 19,1186 "n_groups": 61187 },1188 "exact_match": {1189 "mean": 0.0,1190 "ci_low": 0.0,1191 "ci_high": 0.0,1192 "n_items": 19,1193 "n_groups": 61194 },1195 "number_recall": {1196 "mean": 1.0,1197 "ci_low": 1.0,1198 "ci_high": 1.0,1199 "n_items": 19,1200 "n_groups": 61201 },1202 "placeholders_exact": {1203 "mean": 1.0,1204 "ci_low": 1.0,1205 "ci_high": 1.0,1206 "n_items": 19,1207 "n_groups": 61208 }1209 }1210 }1211 },1212 "B1_generic_paraphrase": {1213 "overall": {1214 "n": 266,1215 "chrf": {1216 "mean": 75.81664942220753,1217 "ci_low": 74.53941531860455,1218 "ci_high": 77.26274234446144,1219 "n_items": 266,1220 "n_groups": 551221 },1222 "edit_sim": {1223 "mean": 0.6597983463665537,1224 "ci_low": 0.64298338471694,1225 "ci_high": 0.6772371316010104,1226 "n_items": 266,1227 "n_groups": 551228 },1229 "rougeL": {1230 "mean": 0.7077172434857506,1231 "ci_low": 0.6926717007410924,1232 "ci_high": 0.7253956024184841,1233 "n_items": 266,1234 "n_groups": 551235 },1236 "exact_match": {1237 "mean": 0.0,1238 "ci_low": 0.0,1239 "ci_high": 0.0,1240 "n_items": 266,1241 "n_groups": 551242 },1243 "number_recall": {1244 "mean": 0.9981203007518797,1245 "ci_low": 0.9946996466431095,1246 "ci_high": 1.0,1247 "n_items": 266,1248 "n_groups": 551249 },1250 "placeholders_exact": {1251 "mean": 1.0,1252 "ci_low": 1.0,1253 "ci_high": 1.0,1254 "n_items": 266,1255 "n_groups": 551256 }1257 },1258 "by_variant": {1259 "H1": {1260 "n": 128,1261 "chrf": {1262 "mean": 74.59560683520908,1263 "ci_low": 73.32796969678664,1264 "ci_high": 76.07110356431582,1265 "n_items": 128,1266 "n_groups": 501267 },1268 "edit_sim": {1269 "mean": 0.6502052199565931,1270 "ci_low": 0.632504475716416,1271 "ci_high": 0.6684403469741025,1272 "n_items": 128,1273 "n_groups": 501274 },1275 "rougeL": {1276 "mean": 0.6969612985797227,1277 "ci_low": 0.681572523000353,1278 "ci_high": 0.7146378426108396,1279 "n_items": 128,1280 "n_groups": 501281 },1282 "exact_match": {1283 "mean": 0.0,1284 "ci_low": 0.0,1285 "ci_high": 0.0,1286 "n_items": 128,1287 "n_groups": 501288 },1289 "number_recall": {1290 "mean": 0.998046875,1291 "ci_low": 0.9946231724297981,1292 "ci_high": 1.0,1293 "n_items": 128,1294 "n_groups": 501295 },1296 "placeholders_exact": {1297 "mean": 1.0,1298 "ci_low": 1.0,1299 "ci_high": 1.0,1300 "n_items": 128,1301 "n_groups": 501302 }1303 },1304 "H2": {1305 "n": 138,1306 "chrf": {1307 "mean": 76.94921066232203,1308 "ci_low": 75.60478837907257,1309 "ci_high": 78.45815511474169,1310 "n_items": 138,1311 "n_groups": 531312 },1313 "edit_sim": {1314 "mean": 0.6686963186888358,1315 "ci_low": 0.6468416576772527,1316 "ci_high": 0.6902081410724802,1317 "n_items": 138,1318 "n_groups": 531319 },1320 "rougeL": {1321 "mean": 0.7176937720942402,1322 "ci_low": 0.6997250956589932,1323 "ci_high": 0.7369647319168826,1324 "n_items": 138,1325 "n_groups": 531326 },1327 "exact_match": {1328 "mean": 0.0,1329 "ci_low": 0.0,1330 "ci_high": 0.0,1331 "n_items": 138,1332 "n_groups": 531333 },1334 "number_recall": {1335 "mean": 0.9981884057971014,1336 "ci_low": 0.9948630136986302,1337 "ci_high": 1.0,1338 "n_items": 138,1339 "n_groups": 531340 },1341 "placeholders_exact": {1342 "mean": 1.0,1343 "ci_low": 1.0,1344 "ci_high": 1.0,1345 "n_items": 138,1346 "n_groups": 531347 }1348 }1349 },1350 "by_discipline": {1351 "biomedicine": {1352 "n": 57,1353 "chrf": {1354 "mean": 75.96460631642735,1355 "ci_low": 73.7182834321063,1356 "ci_high": 78.08341327286844,1357 "n_items": 57,1358 "n_groups": 261359 },1360 "edit_sim": {1361 "mean": 0.6742065278336427,1362 "ci_low": 0.6470579764306079,1363 "ci_high": 0.7021404192872299,1364 "n_items": 57,1365 "n_groups": 261366 },1367 "rougeL": {1368 "mean": 0.718404478133936,1369 "ci_low": 0.6957807036645464,1370 "ci_high": 0.7413924591781628,1371 "n_items": 57,1372 "n_groups": 261373 },1374 "exact_match": {1375 "mean": 0.0,1376 "ci_low": 0.0,1377 "ci_high": 0.0,1378 "n_items": 57,1379 "n_groups": 261380 },1381 "number_recall": {1382 "mean": 1.0,1383 "ci_low": 1.0,1384 "ci_high": 1.0,1385 "n_items": 57,1386 "n_groups": 261387 },1388 "placeholders_exact": {1389 "mean": 1.0,1390 "ci_low": 1.0,1391 "ci_high": 1.0,1392 "n_items": 57,1393 "n_groups": 261394 }1395 },1396 "computer_science": {1397 "n": 30,1398 "chrf": {1399 "mean": 75.15747039613186,1400 "ci_low": 71.4150231657296,1401 "ci_high": 82.64236485693638,1402 "n_items": 30,1403 "n_groups": 21404 },1405 "edit_sim": {1406 "mean": 0.6892881097678173,1407 "ci_low": 0.6723153136969728,1408 "ci_high": 0.7232337019095063,1409 "n_items": 30,1410 "n_groups": 21411 },1412 "rougeL": {1413 "mean": 0.7150374216484089,1414 "ci_low": 0.6756999518051924,1415 "ci_high": 0.7937123613348419,1416 "n_items": 30,1417 "n_groups": 21418 },1419 "exact_match": {1420 "mean": 0.0,1421 "ci_low": 0.0,1422 "ci_high": 0.0,1423 "n_items": 30,1424 "n_groups": 21425 },1426 "number_recall": {1427 "mean": 1.0,1428 "ci_low": 1.0,1429 "ci_high": 1.0,1430 "n_items": 30,1431 "n_groups": 21432 },1433 "placeholders_exact": {1434 "mean": 1.0,1435 "ci_low": 1.0,1436 "ci_high": 1.0,1437 "n_items": 30,1438 "n_groups": 21439 }1440 },1441 "earth_sciences": {1442 "n": 32,1443 "chrf": {1444 "mean": 74.41990769623033,1445 "ci_low": 71.73887806131867,1446 "ci_high": 76.15901511826065,1447 "n_items": 32,1448 "n_groups": 31449 },1450 "edit_sim": {1451 "mean": 0.5903003617812468,1452 "ci_low": 0.5726704072669151,1453 "ci_high": 0.6081418601132288,1454 "n_items": 32,1455 "n_groups": 31456 },1457 "rougeL": {1458 "mean": 0.6589247433122991,1459 "ci_low": 0.6302714307828111,1460 "ci_high": 0.6760862803882739,1461 "n_items": 32,1462 "n_groups": 31463 },1464 "exact_match": {1465 "mean": 0.0,1466 "ci_low": 0.0,1467 "ci_high": 0.0,1468 "n_items": 32,1469 "n_groups": 31470 },1471 "number_recall": {1472 "mean": 1.0,1473 "ci_low": 1.0,1474 "ci_high": 1.0,1475 "n_items": 32,1476 "n_groups": 31477 },1478 "placeholders_exact": {1479 "mean": 1.0,1480 "ci_low": 1.0,1481 "ci_high": 1.0,1482 "n_items": 32,1483 "n_groups": 31484 }1485 },1486 "economics": {1487 "n": 30,1488 "chrf": {1489 "mean": 74.6132931824005,1490 "ci_low": 74.6132931824005,1491 "ci_high": 74.6132931824005,1492 "n_items": 30,1493 "n_groups": 11494 },1495 "edit_sim": {1496 "mean": 0.6616230620600508,1497 "ci_low": 0.6616230620600508,1498 "ci_high": 0.6616230620600508,1499 "n_items": 30,1500 "n_groups": 11501 },1502 "rougeL": {1503 "mean": 0.6928020207192311,1504 "ci_low": 0.6928020207192311,1505 "ci_high": 0.6928020207192311,1506 "n_items": 30,1507 "n_groups": 11508 },1509 "exact_match": {1510 "mean": 0.0,1511 "ci_low": 0.0,1512 "ci_high": 0.0,1513 "n_items": 30,1514 "n_groups": 11515 },1516 "number_recall": {1517 "mean": 0.9833333333333333,1518 "ci_low": 0.9833333333333333,1519 "ci_high": 0.9833333333333333,1520 "n_items": 30,1521 "n_groups": 11522 },1523 "placeholders_exact": {1524 "mean": 1.0,1525 "ci_low": 1.0,1526 "ci_high": 1.0,1527 "n_items": 30,1528 "n_groups": 11529 }1530 },1531 "engineering": {1532 "n": 6,1533 "chrf": {1534 "mean": 80.89626602895409,1535 "ci_low": 80.89626602895409,1536 "ci_high": 80.89626602895409,1537 "n_items": 6,1538 "n_groups": 11539 },1540 "edit_sim": {1541 "mean": 0.7464090910542239,1542 "ci_low": 0.7464090910542239,1543 "ci_high": 0.7464090910542239,1544 "n_items": 6,1545 "n_groups": 11546 },1547 "rougeL": {1548 "mean": 0.754500163769817,1549 "ci_low": 0.754500163769817,1550 "ci_high": 0.754500163769817,1551 "n_items": 6,1552 "n_groups": 11553 },1554 "exact_match": {1555 "mean": 0.0,1556 "ci_low": 0.0,1557 "ci_high": 0.0,1558 "n_items": 6,1559 "n_groups": 11560 },1561 "number_recall": {1562 "mean": 1.0,1563 "ci_low": 1.0,1564 "ci_high": 1.0,1565 "n_items": 6,1566 "n_groups": 11567 },1568 "placeholders_exact": {1569 "mean": 1.0,1570 "ci_low": 1.0,1571 "ci_high": 1.0,1572 "n_items": 6,1573 "n_groups": 11574 }1575 },1576 "life_sciences": {1577 "n": 49,1578 "chrf": {1579 "mean": 76.8018194821647,1580 "ci_low": 75.085665212553,1581 "ci_high": 78.66716884059886,1582 "n_items": 49,1583 "n_groups": 161584 },1585 "edit_sim": {1586 "mean": 0.6625582234437213,1587 "ci_low": 0.6369918664728104,1588 "ci_high": 0.6890073113434391,1589 "n_items": 49,1590 "n_groups": 161591 },1592 "rougeL": {1593 "mean": 0.719277423787011,1594 "ci_low": 0.7000183171098757,1595 "ci_high": 0.7425054706566013,1596 "n_items": 49,1597 "n_groups": 161598 },1599 "exact_match": {1600 "mean": 0.0,1601 "ci_low": 0.0,1602 "ci_high": 0.0,1603 "n_items": 49,1604 "n_groups": 161605 },1606 "number_recall": {1607 "mean": 1.0,1608 "ci_low": 1.0,1609 "ci_high": 1.0,1610 "n_items": 49,1611 "n_groups": 161612 },1613 "placeholders_exact": {1614 "mean": 1.0,1615 "ci_low": 1.0,1616 "ci_high": 1.0,1617 "n_items": 49,1618 "n_groups": 161619 }1620 },1621 "social_sciences": {1622 "n": 38,1623 "chrf": {1624 "mean": 78.06288774359065,1625 "ci_low": 72.85030249852312,1626 "ci_high": 80.67801584685029,1627 "n_items": 38,1628 "n_groups": 41629 },1630 "edit_sim": {1631 "mean": 0.6898682524945269,1632 "ci_low": 0.665154787985927,1633 "ci_high": 0.7219615303955724,1634 "n_items": 38,1635 "n_groups": 41636 },1637 "rougeL": {1638 "mean": 0.7404788933341823,1639 "ci_low": 0.6843548918968363,1640 "ci_high": 0.7643784644153361,1641 "n_items": 38,1642 "n_groups": 41643 },1644 "exact_match": {1645 "mean": 0.0,1646 "ci_low": 0.0,1647 "ci_high": 0.0,1648 "n_items": 38,1649 "n_groups": 41650 },1651 "number_recall": {1652 "mean": 1.0,1653 "ci_low": 1.0,1654 "ci_high": 1.0,1655 "n_items": 38,1656 "n_groups": 41657 },1658 "placeholders_exact": {1659 "mean": 1.0,1660 "ci_low": 1.0,1661 "ci_high": 1.0,1662 "n_items": 38,1663 "n_groups": 41664 }1665 },1666 "statistics": {1667 "n": 24,1668 "chrf": {1669 "mean": 72.81790614913592,1670 "ci_low": 71.63786314670088,1671 "ci_high": 75.177992154006,1672 "n_items": 24,1673 "n_groups": 21674 },1675 "edit_sim": {1676 "mean": 0.6042016760537486,1677 "ci_low": 0.5980922437019562,1678 "ci_high": 0.6164205407573333,1679 "n_items": 24,1680 "n_groups": 21681 },1682 "rougeL": {1683 "mean": 0.6697151567362981,1684 "ci_low": 0.651915728262979,1685 "ci_high": 0.7053140136829361,1686 "n_items": 24,1687 "n_groups": 21688 },1689 "exact_match": {1690 "mean": 0.0,1691 "ci_low": 0.0,1692 "ci_high": 0.0,1693 "n_items": 24,1694 "n_groups": 21695 },1696 "number_recall": {1697 "mean": 1.0,1698 "ci_low": 1.0,1699 "ci_high": 1.0,1700 "n_items": 24,1701 "n_groups": 21702 },1703 "placeholders_exact": {1704 "mean": 1.0,1705 "ci_low": 1.0,1706 "ci_high": 1.0,1707 "n_items": 24,1708 "n_groups": 21709 }1710 }1711 },1712 "by_era": {1713 "1980-1999": {1714 "n": 2,1715 "chrf": {1716 "mean": 79.76413714338017,1717 "ci_low": 76.4774946128078,1718 "ci_high": 83.05077967395253,1719 "n_items": 2,1720 "n_groups": 21721 },1722 "edit_sim": {1723 "mean": 0.7625535423543217,1724 "ci_low": 0.70515574650913,1725 "ci_high": 0.8199513381995134,1726 "n_items": 2,1727 "n_groups": 21728 },1729 "rougeL": {1730 "mean": 0.7869257950530035,1731 "ci_low": 0.773851590106007,1732 "ci_high": 0.7999999999999999,1733 "n_items": 2,1734 "n_groups": 21735 },1736 "exact_match": {1737 "mean": 0.0,1738 "ci_low": 0.0,1739 "ci_high": 0.0,1740 "n_items": 2,1741 "n_groups": 21742 },1743 "number_recall": {1744 "mean": 1.0,1745 "ci_low": 1.0,1746 "ci_high": 1.0,1747 "n_items": 2,1748 "n_groups": 21749 },1750 "placeholders_exact": {1751 "mean": 1.0,1752 "ci_low": 1.0,1753 "ci_high": 1.0,1754 "n_items": 2,1755 "n_groups": 21756 }1757 },1758 "2000-2009": {1759 "n": 30,1760 "chrf": {1761 "mean": 77.51990923858808,1762 "ci_low": 75.40494418118487,1763 "ci_high": 80.36828008381427,1764 "n_items": 30,1765 "n_groups": 71766 },1767 "edit_sim": {1768 "mean": 0.67572605137773,1769 "ci_low": 0.6240997590729389,1770 "ci_high": 0.7404260170325827,1771 "n_items": 30,1772 "n_groups": 71773 },1774 "rougeL": {1775 "mean": 0.7372751762365594,1776 "ci_low": 0.7100864642059639,1777 "ci_high": 0.78013985077075,1778 "n_items": 30,1779 "n_groups": 71780 },1781 "exact_match": {1782 "mean": 0.0,1783 "ci_low": 0.0,1784 "ci_high": 0.0,1785 "n_items": 30,1786 "n_groups": 71787 },1788 "number_recall": {1789 "mean": 1.0,1790 "ci_low": 1.0,1791 "ci_high": 1.0,1792 "n_items": 30,1793 "n_groups": 71794 },1795 "placeholders_exact": {1796 "mean": 1.0,1797 "ci_low": 1.0,1798 "ci_high": 1.0,1799 "n_items": 30,1800 "n_groups": 71801 }1802 },1803 "2010-2017": {1804 "n": 234,1805 "chrf": {1806 "mean": 75.56454356778974,1807 "ci_low": 74.1043548672098,1808 "ci_high": 77.0976559440423,1809 "n_items": 234,1810 "n_groups": 461811 },1812 "edit_sim": {1813 "mean": 0.6568780833652254,1814 "ci_low": 0.6385367512759528,1815 "ci_high": 0.674951169350377,1816 "n_items": 234,1817 "n_groups": 461818 },1819 "rougeL": {1820 "mean": 0.7032507687607131,1821 "ci_low": 0.6862208573844346,1822 "ci_high": 0.7216728101399663,1823 "n_items": 234,1824 "n_groups": 461825 },1826 "exact_match": {1827 "mean": 0.0,1828 "ci_low": 0.0,1829 "ci_high": 0.0,1830 "n_items": 234,1831 "n_groups": 461832 },1833 "number_recall": {1834 "mean": 0.9978632478632479,1835 "ci_low": 0.9941634241245136,1836 "ci_high": 1.0,1837 "n_items": 234,1838 "n_groups": 461839 },1840 "placeholders_exact": {1841 "mean": 1.0,1842 "ci_low": 1.0,1843 "ci_high": 1.0,1844 "n_items": 234,1845 "n_groups": 461846 }1847 }1848 },1849 "by_role": {1850 "abstract": {1851 "n": 28,1852 "chrf": {1853 "mean": 80.3392737859676,1854 "ci_low": 77.92669097193848,1855 "ci_high": 82.64876147842735,1856 "n_items": 28,1857 "n_groups": 151858 },1859 "edit_sim": {1860 "mean": 0.7283799661925754,1861 "ci_low": 0.6700273865595159,1862 "ci_high": 0.7845098280635807,1863 "n_items": 28,1864 "n_groups": 151865 },1866 "rougeL": {1867 "mean": 0.7589315691794164,1868 "ci_low": 0.7080432259456908,1869 "ci_high": 0.8073344962456329,1870 "n_items": 28,1871 "n_groups": 151872 },1873 "exact_match": {1874 "mean": 0.0,1875 "ci_low": 0.0,1876 "ci_high": 0.0,1877 "n_items": 28,1878 "n_groups": 151879 },1880 "number_recall": {1881 "mean": 1.0,1882 "ci_low": 1.0,1883 "ci_high": 1.0,1884 "n_items": 28,1885 "n_groups": 151886 },1887 "placeholders_exact": {1888 "mean": 1.0,1889 "ci_low": 1.0,1890 "ci_high": 1.0,1891 "n_items": 28,1892 "n_groups": 151893 }1894 },1895 "background": {1896 "n": 16,1897 "chrf": {1898 "mean": 75.88610646234454,1899 "ci_low": 70.99834773508942,1900 "ci_high": 80.22361254720252,1901 "n_items": 16,1902 "n_groups": 71903 },1904 "edit_sim": {1905 "mean": 0.6595179000058995,1906 "ci_low": 0.5959534814293618,1907 "ci_high": 0.7176802123031656,1908 "n_items": 16,1909 "n_groups": 71910 },1911 "rougeL": {1912 "mean": 0.714383750850948,1913 "ci_low": 0.6621099172941902,1914 "ci_high": 0.7541057670743742,1915 "n_items": 16,1916 "n_groups": 71917 },1918 "exact_match": {1919 "mean": 0.0,1920 "ci_low": 0.0,1921 "ci_high": 0.0,1922 "n_items": 16,1923 "n_groups": 71924 },1925 "number_recall": {1926 "mean": 1.0,1927 "ci_low": 1.0,1928 "ci_high": 1.0,1929 "n_items": 16,1930 "n_groups": 71931 },1932 "placeholders_exact": {1933 "mean": 1.0,1934 "ci_low": 1.0,1935 "ci_high": 1.0,1936 "n_items": 16,1937 "n_groups": 71938 }1939 },1940 "conclusion": {1941 "n": 17,1942 "chrf": {1943 "mean": 73.48316419716413,1944 "ci_low": 70.59243994393881,1945 "ci_high": 76.3726330990842,1946 "n_items": 17,1947 "n_groups": 91948 },1949 "edit_sim": {1950 "mean": 0.6009367910653952,1951 "ci_low": 0.568952166054523,1952 "ci_high": 0.6400904229127276,1953 "n_items": 17,1954 "n_groups": 91955 },1956 "rougeL": {1957 "mean": 0.6512338805542024,1958 "ci_low": 0.6236517287372979,1959 "ci_high": 0.678506960338075,1960 "n_items": 17,1961 "n_groups": 91962 },1963 "exact_match": {1964 "mean": 0.0,1965 "ci_low": 0.0,1966 "ci_high": 0.0,1967 "n_items": 17,1968 "n_groups": 91969 },1970 "number_recall": {1971 "mean": 1.0,1972 "ci_low": 1.0,1973 "ci_high": 1.0,1974 "n_items": 17,1975 "n_groups": 91976 },1977 "placeholders_exact": {1978 "mean": 1.0,1979 "ci_low": 1.0,1980 "ci_high": 1.0,1981 "n_items": 17,1982 "n_groups": 91983 }1984 },1985 "data": {1986 "n": 25,1987 "chrf": {1988 "mean": 76.42767877759162,1989 "ci_low": 72.8530368542859,1990 "ci_high": 80.14021785962944,1991 "n_items": 25,1992 "n_groups": 101993 },1994 "edit_sim": {1995 "mean": 0.6264117530233893,1996 "ci_low": 0.6000995281962478,1997 "ci_high": 0.6615740238880137,1998 "n_items": 25,1999 "n_groups": 102000 },2001 "rougeL": {2002 "mean": 0.6903434527378544,2003 "ci_low": 0.6469380089248509,2004 "ci_high": 0.7330142520038528,2005 "n_items": 25,2006 "n_groups": 102007 },2008 "exact_match": {2009 "mean": 0.0,2010 "ci_low": 0.0,2011 "ci_high": 0.0,2012 "n_items": 25,2013 "n_groups": 102014 },2015 "number_recall": {2016 "mean": 0.98,2017 "ci_low": 0.9444444444444444,2018 "ci_high": 1.0,2019 "n_items": 25,2020 "n_groups": 102021 },2022 "placeholders_exact": {2023 "mean": 1.0,2024 "ci_low": 1.0,2025 "ci_high": 1.0,2026 "n_items": 25,2027 "n_groups": 102028 }2029 },2030 "discussion": {2031 "n": 34,2032 "chrf": {2033 "mean": 74.90225119125213,2034 "ci_low": 72.00617322036693,2035 "ci_high": 77.65571360034605,2036 "n_items": 34,2037 "n_groups": 142038 },2039 "edit_sim": {2040 "mean": 0.6550993716489827,2041 "ci_low": 0.6293976069489862,2042 "ci_high": 0.6874840204027335,2043 "n_items": 34,2044 "n_groups": 142045 },2046 "rougeL": {2047 "mean": 0.7006037149254828,2048 "ci_low": 0.6649589954053267,2049 "ci_high": 0.7340322165982375,2050 "n_items": 34,2051 "n_groups": 142052 },2053 "exact_match": {2054 "mean": 0.0,2055 "ci_low": 0.0,2056 "ci_high": 0.0,2057 "n_items": 34,2058 "n_groups": 142059 },2060 "number_recall": {2061 "mean": 1.0,2062 "ci_low": 1.0,2063 "ci_high": 1.0,2064 "n_items": 34,2065 "n_groups": 142066 },2067 "placeholders_exact": {2068 "mean": 1.0,2069 "ci_low": 1.0,2070 "ci_high": 1.0,2071 "n_items": 34,2072 "n_groups": 142073 }2074 },2075 "introduction": {2076 "n": 31,2077 "chrf": {2078 "mean": 74.75992371545141,2079 "ci_low": 72.3493555815991,2080 "ci_high": 77.33594928515681,2081 "n_items": 31,2082 "n_groups": 132083 },2084 "edit_sim": {2085 "mean": 0.654506360632274,2086 "ci_low": 0.618336527801246,2087 "ci_high": 0.688151898023704,2088 "n_items": 31,2089 "n_groups": 132090 },2091 "rougeL": {2092 "mean": 0.6928814163081249,2093 "ci_low": 0.6638925847325701,2094 "ci_high": 0.7239163798385517,2095 "n_items": 31,2096 "n_groups": 132097 },2098 "exact_match": {2099 "mean": 0.0,2100 "ci_low": 0.0,2101 "ci_high": 0.0,2102 "n_items": 31,2103 "n_groups": 132104 },2105 "number_recall": {2106 "mean": 1.0,2107 "ci_low": 1.0,2108 "ci_high": 1.0,2109 "n_items": 31,2110 "n_groups": 132111 },2112 "placeholders_exact": {2113 "mean": 1.0,2114 "ci_low": 1.0,2115 "ci_high": 1.0,2116 "n_items": 31,2117 "n_groups": 132118 }2119 },2120 "limitations": {2121 "n": 14,2122 "chrf": {2123 "mean": 74.9307766644446,2124 "ci_low": 73.81522166452254,2125 "ci_high": 76.17294953559815,2126 "n_items": 14,2127 "n_groups": 42128 },2129 "edit_sim": {2130 "mean": 0.6782773554495456,2131 "ci_low": 0.6432713355549206,2132 "ci_high": 0.7093052333980768,2133 "n_items": 14,2134 "n_groups": 42135 },2136 "rougeL": {2137 "mean": 0.716129531167799,2138 "ci_low": 0.686596327488699,2139 "ci_high": 0.7382794339271236,2140 "n_items": 14,2141 "n_groups": 42142 },2143 "exact_match": {2144 "mean": 0.0,2145 "ci_low": 0.0,2146 "ci_high": 0.0,2147 "n_items": 14,2148 "n_groups": 42149 },2150 "number_recall": {2151 "mean": 1.0,2152 "ci_low": 1.0,2153 "ci_high": 1.0,2154 "n_items": 14,2155 "n_groups": 42156 },2157 "placeholders_exact": {2158 "mean": 1.0,2159 "ci_low": 1.0,2160 "ci_high": 1.0,2161 "n_items": 14,2162 "n_groups": 42163 }2164 },2165 "methods": {2166 "n": 32,2167 "chrf": {2168 "mean": 76.47084834704117,2169 "ci_low": 73.51123316569733,2170 "ci_high": 79.72782031032752,2171 "n_items": 32,2172 "n_groups": 122173 },2174 "edit_sim": {2175 "mean": 0.6400927652501046,2176 "ci_low": 0.6061693380610459,2177 "ci_high": 0.6731360915438129,2178 "n_items": 32,2179 "n_groups": 122180 },2181 "rougeL": {2182 "mean": 0.7065079328421682,2183 "ci_low": 0.680061402350211,2184 "ci_high": 0.73657708961726,2185 "n_items": 32,2186 "n_groups": 122187 },2188 "exact_match": {2189 "mean": 0.0,2190 "ci_low": 0.0,2191 "ci_high": 0.0,2192 "n_items": 32,2193 "n_groups": 122194 },2195 "number_recall": {2196 "mean": 1.0,2197 "ci_low": 1.0,2198 "ci_high": 1.0,2199 "n_items": 32,2200 "n_groups": 122201 },2202 "placeholders_exact": {2203 "mean": 1.0,2204 "ci_low": 1.0,2205 "ci_high": 1.0,2206 "n_items": 32,2207 "n_groups": 122208 }2209 },2210 "other": {2211 "n": 22,2212 "chrf": {2213 "mean": 75.9988057478938,2214 "ci_low": 70.82046175888887,2215 "ci_high": 79.58048713622493,2216 "n_items": 22,2217 "n_groups": 82218 },2219 "edit_sim": {2220 "mean": 0.6979065549768552,2221 "ci_low": 0.6516391708861701,2222 "ci_high": 0.7413223146395511,2223 "n_items": 22,2224 "n_groups": 82225 },2226 "rougeL": {2227 "mean": 0.7223760740054563,2228 "ci_low": 0.6713384175334799,2229 "ci_high": 0.7652328828390587,2230 "n_items": 22,2231 "n_groups": 82232 },2233 "exact_match": {2234 "mean": 0.0,2235 "ci_low": 0.0,2236 "ci_high": 0.0,2237 "n_items": 22,2238 "n_groups": 82239 },2240 "number_recall": {2241 "mean": 1.0,2242 "ci_low": 1.0,2243 "ci_high": 1.0,2244 "n_items": 22,2245 "n_groups": 82246 },2247 "placeholders_exact": {2248 "mean": 1.0,2249 "ci_low": 1.0,2250 "ci_high": 1.0,2251 "n_items": 22,2252 "n_groups": 82253 }2254 },2255 "related_work": {2256 "n": 2,2257 "chrf": {2258 "mean": 77.75472212738029,2259 "ci_low": 77.75472212738029,2260 "ci_high": 77.75472212738029,2261 "n_items": 2,2262 "n_groups": 12263 },2264 "edit_sim": {2265 "mean": 0.7137273087897871,2266 "ci_low": 0.7137273087897871,2267 "ci_high": 0.7137273087897871,2268 "n_items": 2,2269 "n_groups": 12270 },2271 "rougeL": {2272 "mean": 0.7566916030296902,2273 "ci_low": 0.7566916030296902,2274 "ci_high": 0.7566916030296902,2275 "n_items": 2,2276 "n_groups": 12277 },2278 "exact_match": {2279 "mean": 0.0,2280 "ci_low": 0.0,2281 "ci_high": 0.0,2282 "n_items": 2,2283 "n_groups": 12284 },2285 "number_recall": {2286 "mean": 1.0,2287 "ci_low": 1.0,2288 "ci_high": 1.0,2289 "n_items": 2,2290 "n_groups": 12291 },2292 "placeholders_exact": {2293 "mean": 1.0,2294 "ci_low": 1.0,2295 "ci_high": 1.0,2296 "n_items": 2,2297 "n_groups": 12298 }2299 },2300 "results": {2301 "n": 26,2302 "chrf": {2303 "mean": 73.68035971241359,2304 "ci_low": 70.18317802825395,2305 "ci_high": 77.90290198261222,2306 "n_items": 26,2307 "n_groups": 102308 },2309 "edit_sim": {2310 "mean": 0.6268936384581613,2311 "ci_low": 0.571136513633538,2312 "ci_high": 0.6828629603697858,2313 "n_items": 26,2314 "n_groups": 102315 },2316 "rougeL": {2317 "mean": 0.6958224597941425,2318 "ci_low": 0.6502981139348409,2319 "ci_high": 0.7427332181887777,2320 "n_items": 26,2321 "n_groups": 102322 },2323 "exact_match": {2324 "mean": 0.0,2325 "ci_low": 0.0,2326 "ci_high": 0.0,2327 "n_items": 26,2328 "n_groups": 102329 },2330 "number_recall": {2331 "mean": 1.0,2332 "ci_low": 1.0,2333 "ci_high": 1.0,2334 "n_items": 26,2335 "n_groups": 102336 },2337 "placeholders_exact": {2338 "mean": 1.0,2339 "ci_low": 1.0,2340 "ci_high": 1.0,2341 "n_items": 26,2342 "n_groups": 102343 }2344 },2345 "theory": {2346 "n": 19,2347 "chrf": {2348 "mean": 75.79688930477523,2349 "ci_low": 72.9749239182561,2350 "ci_high": 78.97488847640821,2351 "n_items": 19,2352 "n_groups": 62353 },2354 "edit_sim": {2355 "mean": 0.6874028789144653,2356 "ci_low": 0.6667370652650401,2357 "ci_high": 0.7157525033539471,2358 "n_items": 19,2359 "n_groups": 62360 },2361 "rougeL": {2362 "mean": 0.7269495915557392,2363 "ci_low": 0.7136300623948133,2364 "ci_high": 0.7427780924027299,2365 "n_items": 19,2366 "n_groups": 62367 },2368 "exact_match": {2369 "mean": 0.0,2370 "ci_low": 0.0,2371 "ci_high": 0.0,2372 "n_items": 19,2373 "n_groups": 62374 },2375 "number_recall": {2376 "mean": 1.0,2377 "ci_low": 1.0,2378 "ci_high": 1.0,2379 "n_items": 19,2380 "n_groups": 62381 },2382 "placeholders_exact": {2383 "mean": 1.0,2384 "ci_low": 1.0,2385 "ci_high": 1.0,2386 "n_items": 19,2387 "n_groups": 62388 }2389 }2390 }2391 },2392 "htr-m1-small": {2393 "overall": {2394 "n": 266,2395 "chrf": {2396 "mean": 77.78809330166145,2397 "ci_low": 76.6515981141297,2398 "ci_high": 79.14559344625664,2399 "n_items": 266,2400 "n_groups": 552401 },2402 "edit_sim": {2403 "mean": 0.7562392297711924,2404 "ci_low": 0.7438937227543623,2405 "ci_high": 0.7695969046282024,2406 "n_items": 266,2407 "n_groups": 552408 },2409 "rougeL": {2410 "mean": 0.7710661250315312,2411 "ci_low": 0.759041572050746,2412 "ci_high": 0.7858947903715623,2413 "n_items": 266,2414 "n_groups": 552415 },2416 "exact_match": {2417 "mean": 0.0,2418 "ci_low": 0.0,2419 "ci_high": 0.0,2420 "n_items": 266,2421 "n_groups": 552422 },2423 "number_recall": {2424 "mean": 0.9922870681180931,2425 "ci_low": 0.9840241325205993,2426 "ci_high": 0.9978626912687157,2427 "n_items": 266,2428 "n_groups": 552429 },2430 "placeholders_exact": {2431 "mean": 1.0,2432 "ci_low": 1.0,2433 "ci_high": 1.0,2434 "n_items": 266,2435 "n_groups": 552436 }2437 },2438 "by_variant": {2439 "H1": {2440 "n": 128,2441 "chrf": {2442 "mean": 76.95096096791431,2443 "ci_low": 75.8046222311392,2444 "ci_high": 78.34559526824344,2445 "n_items": 128,2446 "n_groups": 502447 },2448 "edit_sim": {2449 "mean": 0.7284653900391919,2450 "ci_low": 0.7126363060794721,2451 "ci_high": 0.7436540170606459,2452 "n_items": 128,2453 "n_groups": 502454 },2455 "rougeL": {2456 "mean": 0.7503526014321291,2457 "ci_low": 0.7377523916503402,2458 "ci_high": 0.7642024271928974,2459 "n_items": 128,2460 "n_groups": 502461 },2462 "exact_match": {2463 "mean": 0.0,2464 "ci_low": 0.0,2465 "ci_high": 0.0,2466 "n_items": 128,2467 "n_groups": 502468 },2469 "number_recall": {2470 "mean": 0.9935892244177607,2471 "ci_low": 0.9864883719248392,2472 "ci_high": 0.9983068885448916,2473 "n_items": 128,2474 "n_groups": 502475 },2476 "placeholders_exact": {2477 "mean": 1.0,2478 "ci_low": 1.0,2479 "ci_high": 1.0,2480 "n_items": 128,2481 "n_groups": 502482 }2483 },2484 "H2": {2485 "n": 138,2486 "chrf": {2487 "mean": 78.5645638720936,2488 "ci_low": 77.36940409693943,2489 "ci_high": 80.01965709046037,2490 "n_items": 138,2491 "n_groups": 532492 },2493 "edit_sim": {2494 "mean": 0.7820004724211641,2495 "ci_low": 0.7692895422956795,2496 "ci_high": 0.7963709562071285,2497 "n_items": 138,2498 "n_groups": 532499 },2500 "rougeL": {2501 "mean": 0.7902786686599618,2502 "ci_low": 0.7762855786742703,2503 "ci_high": 0.8070350255164728,2504 "n_items": 138,2505 "n_groups": 532506 },2507 "exact_match": {2508 "mean": 0.0,2509 "ci_low": 0.0,2510 "ci_high": 0.0,2511 "n_items": 138,2512 "n_groups": 532513 },2514 "number_recall": {2515 "mean": 0.9910792709705752,2516 "ci_low": 0.9781844310763161,2517 "ci_high": 0.999233475312292,2518 "n_items": 138,2519 "n_groups": 532520 },2521 "placeholders_exact": {2522 "mean": 1.0,2523 "ci_low": 1.0,2524 "ci_high": 1.0,2525 "n_items": 138,2526 "n_groups": 532527 }2528 }2529 },2530 "by_discipline": {2531 "biomedicine": {2532 "n": 57,2533 "chrf": {2534 "mean": 77.70888958211218,2535 "ci_low": 75.66902807478823,2536 "ci_high": 79.69122601195346,2537 "n_items": 57,2538 "n_groups": 262539 },2540 "edit_sim": {2541 "mean": 0.7529440328193386,2542 "ci_low": 0.7296095128481118,2543 "ci_high": 0.7762638418083964,2544 "n_items": 57,2545 "n_groups": 262546 },2547 "rougeL": {2548 "mean": 0.7687518652849713,2549 "ci_low": 0.748839132955311,2550 "ci_high": 0.7881433998106787,2551 "n_items": 57,2552 "n_groups": 262553 },2554 "exact_match": {2555 "mean": 0.0,2556 "ci_low": 0.0,2557 "ci_high": 0.0,2558 "n_items": 57,2559 "n_groups": 262560 },2561 "number_recall": {2562 "mean": 0.9932799835846928,2563 "ci_low": 0.9837957588005963,2564 "ci_high": 1.0,2565 "n_items": 57,2566 "n_groups": 262567 },2568 "placeholders_exact": {2569 "mean": 1.0,2570 "ci_low": 1.0,2571 "ci_high": 1.0,2572 "n_items": 57,2573 "n_groups": 262574 }2575 },2576 "computer_science": {2577 "n": 30,2578 "chrf": {2579 "mean": 76.02455508779559,2580 "ci_low": 74.56926987505219,2581 "ci_high": 78.9351255132824,2582 "n_items": 30,2583 "n_groups": 22584 },2585 "edit_sim": {2586 "mean": 0.7658228288277251,2587 "ci_low": 0.7641335019631162,2588 "ci_high": 0.7666674922600296,2589 "n_items": 30,2590 "n_groups": 22591 },2592 "rougeL": {2593 "mean": 0.7655129274201918,2594 "ci_low": 0.7540768363134203,2595 "ci_high": 0.7883851096337351,2596 "n_items": 30,2597 "n_groups": 22598 },2599 "exact_match": {2600 "mean": 0.0,2601 "ci_low": 0.0,2602 "ci_high": 0.0,2603 "n_items": 30,2604 "n_groups": 22605 },2606 "number_recall": {2607 "mean": 0.9948717948717949,2608 "ci_low": 0.9846153846153847,2609 "ci_high": 1.0,2610 "n_items": 30,2611 "n_groups": 22612 },2613 "placeholders_exact": {2614 "mean": 1.0,2615 "ci_low": 1.0,2616 "ci_high": 1.0,2617 "n_items": 30,2618 "n_groups": 22619 }2620 },2621 "earth_sciences": {2622 "n": 32,2623 "chrf": {2624 "mean": 76.488991254173,2625 "ci_low": 73.64973552666666,2626 "ci_high": 78.2993292816473,2627 "n_items": 32,2628 "n_groups": 32629 },2630 "edit_sim": {2631 "mean": 0.7196665741904842,2632 "ci_low": 0.6963218746248238,2633 "ci_high": 0.7309045860241825,2634 "n_items": 32,2635 "n_groups": 32636 },2637 "rougeL": {2638 "mean": 0.7473213408260988,2639 "ci_low": 0.7181987229763126,2640 "ci_high": 0.7690897053974987,2641 "n_items": 32,2642 "n_groups": 32643 },2644 "exact_match": {2645 "mean": 0.0,2646 "ci_low": 0.0,2647 "ci_high": 0.0,2648 "n_items": 32,2649 "n_groups": 32650 },2651 "number_recall": {2652 "mean": 0.9983552631578947,2653 "ci_low": 0.9964912280701753,2654 "ci_high": 1.0,2655 "n_items": 32,2656 "n_groups": 32657 },2658 "placeholders_exact": {2659 "mean": 1.0,2660 "ci_low": 1.0,2661 "ci_high": 1.0,2662 "n_items": 32,2663 "n_groups": 32664 }2665 },2666 "economics": {2667 "n": 30,2668 "chrf": {2669 "mean": 75.47537060464713,2670 "ci_low": 75.47537060464713,2671 "ci_high": 75.47537060464713,2672 "n_items": 30,2673 "n_groups": 12674 },2675 "edit_sim": {2676 "mean": 0.7435158481626737,2677 "ci_low": 0.7435158481626737,2678 "ci_high": 0.7435158481626737,2679 "n_items": 30,2680 "n_groups": 12681 },2682 "rougeL": {2683 "mean": 0.7447296886742298,2684 "ci_low": 0.7447296886742298,2685 "ci_high": 0.7447296886742298,2686 "n_items": 30,2687 "n_groups": 12688 },2689 "exact_match": {2690 "mean": 0.0,2691 "ci_low": 0.0,2692 "ci_high": 0.0,2693 "n_items": 30,2694 "n_groups": 12695 },2696 "number_recall": {2697 "mean": 1.0,2698 "ci_low": 1.0,2699 "ci_high": 1.0,2700 "n_items": 30,2701 "n_groups": 12702 },2703 "placeholders_exact": {2704 "mean": 1.0,2705 "ci_low": 1.0,2706 "ci_high": 1.0,2707 "n_items": 30,2708 "n_groups": 12709 }2710 },2711 "engineering": {2712 "n": 6,2713 "chrf": {2714 "mean": 79.65528440961079,2715 "ci_low": 79.65528440961079,2716 "ci_high": 79.65528440961079,2717 "n_items": 6,2718 "n_groups": 12719 },2720 "edit_sim": {2721 "mean": 0.7556925756358422,2722 "ci_low": 0.7556925756358422,2723 "ci_high": 0.7556925756358422,2724 "n_items": 6,2725 "n_groups": 12726 },2727 "rougeL": {2728 "mean": 0.7538673956099499,2729 "ci_low": 0.7538673956099499,2730 "ci_high": 0.7538673956099499,2731 "n_items": 6,2732 "n_groups": 12733 },2734 "exact_match": {2735 "mean": 0.0,2736 "ci_low": 0.0,2737 "ci_high": 0.0,2738 "n_items": 6,2739 "n_groups": 12740 },2741 "number_recall": {2742 "mean": 1.0,2743 "ci_low": 1.0,2744 "ci_high": 1.0,2745 "n_items": 6,2746 "n_groups": 12747 },2748 "placeholders_exact": {2749 "mean": 1.0,2750 "ci_low": 1.0,2751 "ci_high": 1.0,2752 "n_items": 6,2753 "n_groups": 12754 }2755 },2756 "life_sciences": {2757 "n": 49,2758 "chrf": {2759 "mean": 79.52902721983419,2760 "ci_low": 77.73237672036183,2761 "ci_high": 81.57894077397202,2762 "n_items": 49,2763 "n_groups": 162764 },2765 "edit_sim": {2766 "mean": 0.7778741624101884,2767 "ci_low": 0.7579331623665587,2768 "ci_high": 0.8004809077390794,2769 "n_items": 49,2770 "n_groups": 162771 },2772 "rougeL": {2773 "mean": 0.798318938212888,2774 "ci_low": 0.7792434841843597,2775 "ci_high": 0.8201570371265321,2776 "n_items": 49,2777 "n_groups": 162778 },2779 "exact_match": {2780 "mean": 0.0,2781 "ci_low": 0.0,2782 "ci_high": 0.0,2783 "n_items": 49,2784 "n_groups": 162785 },2786 "number_recall": {2787 "mean": 0.9837662337662337,2788 "ci_low": 0.9554919410946198,2789 "ci_high": 1.0,2790 "n_items": 49,2791 "n_groups": 162792 },2793 "placeholders_exact": {2794 "mean": 1.0,2795 "ci_low": 1.0,2796 "ci_high": 1.0,2797 "n_items": 49,2798 "n_groups": 162799 }2800 },2801 "social_sciences": {2802 "n": 38,2803 "chrf": {2804 "mean": 80.81322733598621,2805 "ci_low": 74.27319617659451,2806 "ci_high": 83.3618280149652,2807 "n_items": 38,2808 "n_groups": 42809 },2810 "edit_sim": {2811 "mean": 0.7919917726753546,2812 "ci_low": 0.7511628865037951,2813 "ci_high": 0.8124286058054565,2814 "n_items": 38,2815 "n_groups": 42816 },2817 "rougeL": {2818 "mean": 0.8051953544459122,2819 "ci_low": 0.7303262257449203,2820 "ci_high": 0.8297659015928833,2821 "n_items": 38,2822 "n_groups": 42823 },2824 "exact_match": {2825 "mean": 0.0,2826 "ci_low": 0.0,2827 "ci_high": 0.0,2828 "n_items": 38,2829 "n_groups": 42830 },2831 "number_recall": {2832 "mean": 0.982456140350877,2833 "ci_low": 0.9259259259259258,2834 "ci_high": 1.0,2835 "n_items": 38,2836 "n_groups": 42837 },2838 "placeholders_exact": {2839 "mean": 1.0,2840 "ci_low": 1.0,2841 "ci_high": 1.0,2842 "n_items": 38,2843 "n_groups": 42844 }2845 },2846 "statistics": {2847 "n": 24,2848 "chrf": {2849 "mean": 75.99266425657171,2850 "ci_low": 74.77649573674888,2851 "ci_high": 76.60074851648314,2852 "n_items": 24,2853 "n_groups": 22854 },2855 "edit_sim": {2856 "mean": 0.7161107412937374,2857 "ci_low": 0.6840764494431025,2858 "ci_high": 0.7321278872190548,2859 "n_items": 24,2860 "n_groups": 22861 },2862 "rougeL": {2863 "mean": 0.7427048222016754,2864 "ci_low": 0.723528759204098,2865 "ci_high": 0.7522928537004641,2866 "n_items": 24,2867 "n_groups": 22868 },2869 "exact_match": {2870 "mean": 0.0,2871 "ci_low": 0.0,2872 "ci_high": 0.0,2873 "n_items": 24,2874 "n_groups": 22875 },2876 "number_recall": {2877 "mean": 1.0,2878 "ci_low": 1.0,2879 "ci_high": 1.0,2880 "n_items": 24,2881 "n_groups": 22882 },2883 "placeholders_exact": {2884 "mean": 1.0,2885 "ci_low": 1.0,2886 "ci_high": 1.0,2887 "n_items": 24,2888 "n_groups": 22889 }2890 }2891 },2892 "by_era": {2893 "1980-1999": {2894 "n": 2,2895 "chrf": {2896 "mean": 77.42998132788014,2897 "ci_low": 77.11844920237209,2898 "ci_high": 77.74151345338821,2899 "n_items": 2,2900 "n_groups": 22901 },2902 "edit_sim": {2903 "mean": 0.7864488496920372,2904 "ci_low": 0.7407809110629067,2905 "ci_high": 0.8321167883211679,2906 "n_items": 2,2907 "n_groups": 22908 },2909 "rougeL": {2910 "mean": 0.7977904448492684,2911 "ci_low": 0.7552447552447553,2912 "ci_high": 0.8403361344537815,2913 "n_items": 2,2914 "n_groups": 22915 },2916 "exact_match": {2917 "mean": 0.0,2918 "ci_low": 0.0,2919 "ci_high": 0.0,2920 "n_items": 2,2921 "n_groups": 22922 },2923 "number_recall": {2924 "mean": 1.0,2925 "ci_low": 1.0,2926 "ci_high": 1.0,2927 "n_items": 2,2928 "n_groups": 22929 },2930 "placeholders_exact": {2931 "mean": 1.0,2932 "ci_low": 1.0,2933 "ci_high": 1.0,2934 "n_items": 2,2935 "n_groups": 22936 }2937 },2938 "2000-2009": {2939 "n": 30,2940 "chrf": {2941 "mean": 78.2420418319754,2942 "ci_low": 75.87299184973251,2943 "ci_high": 81.76322132343839,2944 "n_items": 30,2945 "n_groups": 72946 },2947 "edit_sim": {2948 "mean": 0.7571578121728968,2949 "ci_low": 0.7181968618489049,2950 "ci_high": 0.813734479774441,2951 "n_items": 30,2952 "n_groups": 72953 },2954 "rougeL": {2955 "mean": 0.7718605739830376,2956 "ci_low": 0.7424248527821908,2957 "ci_high": 0.8232631606272761,2958 "n_items": 30,2959 "n_groups": 72960 },2961 "exact_match": {2962 "mean": 0.0,2963 "ci_low": 0.0,2964 "ci_high": 0.0,2965 "n_items": 30,2966 "n_groups": 72967 },2968 "number_recall": {2969 "mean": 1.0,2970 "ci_low": 1.0,2971 "ci_high": 1.0,2972 "n_items": 30,2973 "n_groups": 72974 },2975 "placeholders_exact": {2976 "mean": 1.0,2977 "ci_low": 1.0,2978 "ci_high": 1.0,2979 "n_items": 30,2980 "n_groups": 72981 }2982 },2983 "2010-2017": {2984 "n": 234,2985 "chrf": {2986 "mean": 77.73295555823472,2987 "ci_low": 76.44044200104923,2988 "ci_high": 79.25675595085659,2989 "n_items": 234,2990 "n_groups": 462991 },2992 "edit_sim": {2993 "mean": 0.7558632609169497,2994 "ci_low": 0.7428222571652848,2995 "ci_high": 0.7698262982284051,2996 "n_items": 234,2997 "n_groups": 462998 },2999 "rougeL": {3000 "mean": 0.7707358596119556,3001 "ci_low": 0.756844042642896,3002 "ci_high": 0.7867896838766973,3003 "n_items": 234,3004 "n_groups": 463005 },3006 "exact_match": {3007 "mean": 0.0,3008 "ci_low": 0.0,3009 "ci_high": 0.0,3010 "n_items": 234,3011 "n_groups": 463012 },3013 "number_recall": {3014 "mean": 0.9912323082026185,3015 "ci_low": 0.9813600896833237,3016 "ci_high": 0.9975613110547966,3017 "n_items": 234,3018 "n_groups": 463019 },3020 "placeholders_exact": {3021 "mean": 1.0,3022 "ci_low": 1.0,3023 "ci_high": 1.0,3024 "n_items": 234,3025 "n_groups": 463026 }3027 }3028 },3029 "by_role": {3030 "abstract": {3031 "n": 28,3032 "chrf": {3033 "mean": 81.21288821238235,3034 "ci_low": 78.69164471919905,3035 "ci_high": 84.01163660705204,3036 "n_items": 28,3037 "n_groups": 153038 },3039 "edit_sim": {3040 "mean": 0.7950550546039178,3041 "ci_low": 0.7573759679664045,3042 "ci_high": 0.8361208241179829,3043 "n_items": 28,3044 "n_groups": 153045 },3046 "rougeL": {3047 "mean": 0.8001568552858086,3048 "ci_low": 0.7645825072680045,3049 "ci_high": 0.8399871622112401,3050 "n_items": 28,3051 "n_groups": 153052 },3053 "exact_match": {3054 "mean": 0.0,3055 "ci_low": 0.0,3056 "ci_high": 0.0,3057 "n_items": 28,3058 "n_groups": 153059 },3060 "number_recall": {3061 "mean": 1.0,3062 "ci_low": 1.0,3063 "ci_high": 1.0,3064 "n_items": 28,3065 "n_groups": 153066 },3067 "placeholders_exact": {3068 "mean": 1.0,3069 "ci_low": 1.0,3070 "ci_high": 1.0,3071 "n_items": 28,3072 "n_groups": 153073 }3074 },3075 "background": {3076 "n": 16,3077 "chrf": {3078 "mean": 79.0058060164921,3079 "ci_low": 72.75489915449224,3080 "ci_high": 84.23432400169074,3081 "n_items": 16,3082 "n_groups": 73083 },3084 "edit_sim": {3085 "mean": 0.7734439866831266,3086 "ci_low": 0.7172189216095264,3087 "ci_high": 0.8201926667231876,3088 "n_items": 16,3089 "n_groups": 73090 },3091 "rougeL": {3092 "mean": 0.7941113335696232,3093 "ci_low": 0.7447106292061664,3094 "ci_high": 0.8337456811261552,3095 "n_items": 16,3096 "n_groups": 73097 },3098 "exact_match": {3099 "mean": 0.0,3100 "ci_low": 0.0,3101 "ci_high": 0.0,3102 "n_items": 16,3103 "n_groups": 73104 },3105 "number_recall": {3106 "mean": 1.0,3107 "ci_low": 1.0,3108 "ci_high": 1.0,3109 "n_items": 16,3110 "n_groups": 73111 },3112 "placeholders_exact": {3113 "mean": 1.0,3114 "ci_low": 1.0,3115 "ci_high": 1.0,3116 "n_items": 16,3117 "n_groups": 73118 }3119 },3120 "conclusion": {3121 "n": 17,3122 "chrf": {3123 "mean": 77.85024144878643,3124 "ci_low": 74.25721059354359,3125 "ci_high": 81.34943335669135,3126 "n_items": 17,3127 "n_groups": 93128 },3129 "edit_sim": {3130 "mean": 0.7513427750176699,3131 "ci_low": 0.7168979882509604,3132 "ci_high": 0.7805872796391629,3133 "n_items": 17,3134 "n_groups": 93135 },3136 "rougeL": {3137 "mean": 0.769423717062051,3138 "ci_low": 0.7389098454592767,3139 "ci_high": 0.7989067836332714,3140 "n_items": 17,3141 "n_groups": 93142 },3143 "exact_match": {3144 "mean": 0.0,3145 "ci_low": 0.0,3146 "ci_high": 0.0,3147 "n_items": 17,3148 "n_groups": 93149 },3150 "number_recall": {3151 "mean": 1.0,3152 "ci_low": 1.0,3153 "ci_high": 1.0,3154 "n_items": 17,3155 "n_groups": 93156 },3157 "placeholders_exact": {3158 "mean": 1.0,3159 "ci_low": 1.0,3160 "ci_high": 1.0,3161 "n_items": 17,3162 "n_groups": 93163 }3164 },3165 "data": {3166 "n": 25,3167 "chrf": {3168 "mean": 78.73562653513724,3169 "ci_low": 75.75477938018693,3170 "ci_high": 81.79869510649438,3171 "n_items": 25,3172 "n_groups": 103173 },3174 "edit_sim": {3175 "mean": 0.7423087728773686,3176 "ci_low": 0.7211269227389298,3177 "ci_high": 0.7693924492112646,3178 "n_items": 25,3179 "n_groups": 103180 },3181 "rougeL": {3182 "mean": 0.7700472699128198,3183 "ci_low": 0.7403928257738871,3184 "ci_high": 0.7994472804438242,3185 "n_items": 25,3186 "n_groups": 103187 },3188 "exact_match": {3189 "mean": 0.0,3190 "ci_low": 0.0,3191 "ci_high": 0.0,3192 "n_items": 25,3193 "n_groups": 103194 },3195 "number_recall": {3196 "mean": 0.9817408906882591,3197 "ci_low": 0.9548011363636364,3198 "ci_high": 0.9983047795441683,3199 "n_items": 25,3200 "n_groups": 103201 },3202 "placeholders_exact": {3203 "mean": 1.0,3204 "ci_low": 1.0,3205 "ci_high": 1.0,3206 "n_items": 25,3207 "n_groups": 103208 }3209 },3210 "discussion": {3211 "n": 34,3212 "chrf": {3213 "mean": 77.29151230297136,3214 "ci_low": 74.90283057964294,3215 "ci_high": 79.3074940964158,3216 "n_items": 34,3217 "n_groups": 143218 },3219 "edit_sim": {3220 "mean": 0.7503201145821197,3221 "ci_low": 0.7331196024911596,3222 "ci_high": 0.7695276181527679,3223 "n_items": 34,3224 "n_groups": 143225 },3226 "rougeL": {3227 "mean": 0.7642726881685323,3228 "ci_low": 0.7328199816200321,3229 "ci_high": 0.7905058178355655,3230 "n_items": 34,3231 "n_groups": 143232 },3233 "exact_match": {3234 "mean": 0.0,3235 "ci_low": 0.0,3236 "ci_high": 0.0,3237 "n_items": 34,3238 "n_groups": 143239 },3240 "number_recall": {3241 "mean": 0.980392156862745,3242 "ci_low": 0.9393939393939394,3243 "ci_high": 1.0,3244 "n_items": 34,3245 "n_groups": 143246 },3247 "placeholders_exact": {3248 "mean": 1.0,3249 "ci_low": 1.0,3250 "ci_high": 1.0,3251 "n_items": 34,3252 "n_groups": 143253 }3254 },3255 "introduction": {3256 "n": 31,3257 "chrf": {3258 "mean": 76.72638724990698,3259 "ci_low": 74.18226764665816,3260 "ci_high": 79.25910299744527,3261 "n_items": 31,3262 "n_groups": 133263 },3264 "edit_sim": {3265 "mean": 0.7388766314128037,3266 "ci_low": 0.6961916877961074,3267 "ci_high": 0.7795114355424373,3268 "n_items": 31,3269 "n_groups": 133270 },3271 "rougeL": {3272 "mean": 0.7507089830965311,3273 "ci_low": 0.7152907101135298,3274 "ci_high": 0.784739900953047,3275 "n_items": 31,3276 "n_groups": 133277 },3278 "exact_match": {3279 "mean": 0.0,3280 "ci_low": 0.0,3281 "ci_high": 0.0,3282 "n_items": 31,3283 "n_groups": 133284 },3285 "number_recall": {3286 "mean": 0.996415770609319,3287 "ci_low": 0.9880952380952381,3288 "ci_high": 1.0,3289 "n_items": 31,3290 "n_groups": 133291 },3292 "placeholders_exact": {3293 "mean": 1.0,3294 "ci_low": 1.0,3295 "ci_high": 1.0,3296 "n_items": 31,3297 "n_groups": 133298 }3299 },3300 "limitations": {3301 "n": 14,3302 "chrf": {3303 "mean": 79.12340476691227,3304 "ci_low": 77.03144447666992,3305 "ci_high": 80.60807053174545,3306 "n_items": 14,3307 "n_groups": 43308 },3309 "edit_sim": {3310 "mean": 0.787454889456403,3311 "ci_low": 0.7555654187774168,3312 "ci_high": 0.8104603327702303,3313 "n_items": 14,3314 "n_groups": 43315 },3316 "rougeL": {3317 "mean": 0.7950694735571374,3318 "ci_low": 0.7559917812315919,3319 "ci_high": 0.8160798801470927,3320 "n_items": 14,3321 "n_groups": 43322 },3323 "exact_match": {3324 "mean": 0.0,3325 "ci_low": 0.0,3326 "ci_high": 0.0,3327 "n_items": 14,3328 "n_groups": 43329 },3330 "number_recall": {3331 "mean": 1.0,3332 "ci_low": 1.0,3333 "ci_high": 1.0,3334 "n_items": 14,3335 "n_groups": 43336 },3337 "placeholders_exact": {3338 "mean": 1.0,3339 "ci_low": 1.0,3340 "ci_high": 1.0,3341 "n_items": 14,3342 "n_groups": 43343 }3344 },3345 "methods": {3346 "n": 32,3347 "chrf": {3348 "mean": 77.63461700409688,3349 "ci_low": 75.15168583293199,3350 "ci_high": 80.31294764315973,3351 "n_items": 32,3352 "n_groups": 123353 },3354 "edit_sim": {3355 "mean": 0.7757180073846157,3356 "ci_low": 0.747514758201167,3357 "ci_high": 0.7990636005202916,3358 "n_items": 32,3359 "n_groups": 123360 },3361 "rougeL": {3362 "mean": 0.7849077986687792,3363 "ci_low": 0.7637631237028374,3364 "ci_high": 0.8074856798165965,3365 "n_items": 32,3366 "n_groups": 123367 },3368 "exact_match": {3369 "mean": 0.0,3370 "ci_low": 0.0,3371 "ci_high": 0.0,3372 "n_items": 32,3373 "n_groups": 123374 },3375 "number_recall": {3376 "mean": 1.0,3377 "ci_low": 1.0,3378 "ci_high": 1.0,3379 "n_items": 32,3380 "n_groups": 123381 },3382 "placeholders_exact": {3383 "mean": 1.0,3384 "ci_low": 1.0,3385 "ci_high": 1.0,3386 "n_items": 32,3387 "n_groups": 123388 }3389 },3390 "other": {3391 "n": 22,3392 "chrf": {3393 "mean": 76.75379645927192,3394 "ci_low": 72.22721760848634,3395 "ci_high": 80.2539222656961,3396 "n_items": 22,3397 "n_groups": 83398 },3399 "edit_sim": {3400 "mean": 0.7537820161421674,3401 "ci_low": 0.7090394042224732,3402 "ci_high": 0.7913403366265179,3403 "n_items": 22,3404 "n_groups": 83405 },3406 "rougeL": {3407 "mean": 0.7591846195877416,3408 "ci_low": 0.704455769411876,3409 "ci_high": 0.8043871590595235,3410 "n_items": 22,3411 "n_groups": 83412 },3413 "exact_match": {3414 "mean": 0.0,3415 "ci_low": 0.0,3416 "ci_high": 0.0,3417 "n_items": 22,3418 "n_groups": 83419 },3420 "number_recall": {3421 "mean": 1.0,3422 "ci_low": 1.0,3423 "ci_high": 1.0,3424 "n_items": 22,3425 "n_groups": 83426 },3427 "placeholders_exact": {3428 "mean": 1.0,3429 "ci_low": 1.0,3430 "ci_high": 1.0,3431 "n_items": 22,3432 "n_groups": 83433 }3434 },3435 "related_work": {3436 "n": 2,3437 "chrf": {3438 "mean": 81.51092292717243,3439 "ci_low": 81.51092292717243,3440 "ci_high": 81.51092292717243,3441 "n_items": 2,3442 "n_groups": 13443 },3444 "edit_sim": {3445 "mean": 0.793390650188071,3446 "ci_low": 0.793390650188071,3447 "ci_high": 0.793390650188071,3448 "n_items": 2,3449 "n_groups": 13450 },3451 "rougeL": {3452 "mean": 0.8017543859649123,3453 "ci_low": 0.8017543859649123,3454 "ci_high": 0.8017543859649123,3455 "n_items": 2,3456 "n_groups": 13457 },3458 "exact_match": {3459 "mean": 0.0,3460 "ci_low": 0.0,3461 "ci_high": 0.0,3462 "n_items": 2,3463 "n_groups": 13464 },3465 "number_recall": {3466 "mean": 1.0,3467 "ci_low": 1.0,3468 "ci_high": 1.0,3469 "n_items": 2,3470 "n_groups": 13471 },3472 "placeholders_exact": {3473 "mean": 1.0,3474 "ci_low": 1.0,3475 "ci_high": 1.0,3476 "n_items": 2,3477 "n_groups": 13478 }3479 },3480 "results": {3481 "n": 26,3482 "chrf": {3483 "mean": 74.02956332924978,3484 "ci_low": 72.26797644043235,3485 "ci_high": 75.94256498331373,3486 "n_items": 26,3487 "n_groups": 103488 },3489 "edit_sim": {3490 "mean": 0.6972113636752937,3491 "ci_low": 0.6742277679201677,3492 "ci_high": 0.7228220415817965,3493 "n_items": 26,3494 "n_groups": 103495 },3496 "rougeL": {3497 "mean": 0.7331267631699702,3498 "ci_low": 0.7167880830964122,3499 "ci_high": 0.7528231376357588,3500 "n_items": 26,3501 "n_groups": 103502 },3503 "exact_match": {3504 "mean": 0.0,3505 "ci_low": 0.0,3506 "ci_high": 0.0,3507 "n_items": 26,3508 "n_groups": 103509 },3510 "number_recall": {3511 "mean": 0.9895411605937922,3512 "ci_low": 0.9703947368421053,3513 "ci_high": 1.0,3514 "n_items": 26,3515 "n_groups": 103516 },3517 "placeholders_exact": {3518 "mean": 1.0,3519 "ci_low": 1.0,3520 "ci_high": 1.0,3521 "n_items": 26,3522 "n_groups": 103523 }3524 },3525 "theory": {3526 "n": 19,3527 "chrf": {3528 "mean": 78.25765450467009,3529 "ci_low": 76.1050037220139,3530 "ci_high": 81.39228088314724,3531 "n_items": 19,3532 "n_groups": 63533 },3534 "edit_sim": {3535 "mean": 0.7700820019323732,3536 "ci_low": 0.747805917574946,3537 "ci_high": 0.8027410174380069,3538 "n_items": 19,3539 "n_groups": 63540 },3541 "rougeL": {3542 "mean": 0.7784154067996043,3543 "ci_low": 0.7573185374373147,3544 "ci_high": 0.8054812216733925,3545 "n_items": 19,3546 "n_groups": 63547 },3548 "exact_match": {3549 "mean": 0.0,3550 "ci_low": 0.0,3551 "ci_high": 0.0,3552 "n_items": 19,3553 "n_groups": 63554 },3555 "number_recall": {3556 "mean": 0.9712918660287081,3557 "ci_low": 0.9037433155080213,3558 "ci_high": 1.0,3559 "n_items": 19,3560 "n_groups": 63561 },3562 "placeholders_exact": {3563 "mean": 1.0,3564 "ci_low": 1.0,3565 "ci_high": 1.0,3566 "n_items": 19,3567 "n_groups": 63568 }3569 }3570 }3571 },3572 "htr-m1-tiny-s3": {3573 "overall": {3574 "n": 266,3575 "chrf": {3576 "mean": 77.93582005998915,3577 "ci_low": 76.86242619717079,3578 "ci_high": 79.2111798259343,3579 "n_items": 266,3580 "n_groups": 553581 },3582 "edit_sim": {3583 "mean": 0.7590499016424608,3584 "ci_low": 0.7479103361104839,3585 "ci_high": 0.7710320973453065,3586 "n_items": 266,3587 "n_groups": 553588 },3589 "rougeL": {3590 "mean": 0.7733710313879627,3591 "ci_low": 0.7626494075577126,3592 "ci_high": 0.7867312922882932,3593 "n_items": 266,3594 "n_groups": 553595 },3596 "exact_match": {3597 "mean": 0.0,3598 "ci_low": 0.0,3599 "ci_high": 0.0,3600 "n_items": 266,3601 "n_groups": 553602 },3603 "number_recall": {3604 "mean": 0.9982345074351407,3605 "ci_low": 0.9960396009825936,3606 "ci_high": 0.999653301238886,3607 "n_items": 266,3608 "n_groups": 553609 },3610 "placeholders_exact": {3611 "mean": 0.9924812030075187,3612 "ci_low": 0.9727272727272728,3613 "ci_high": 1.0,3614 "n_items": 266,3615 "n_groups": 553616 }3617 },3618 "by_variant": {3619 "H1": {3620 "n": 128,3621 "chrf": {3622 "mean": 77.00857982829379,3623 "ci_low": 75.84404679951886,3624 "ci_high": 78.30333375286271,3625 "n_items": 128,3626 "n_groups": 503627 },3628 "edit_sim": {3629 "mean": 0.7287803581916116,3630 "ci_low": 0.7129577125723365,3631 "ci_high": 0.743631095692596,3632 "n_items": 128,3633 "n_groups": 503634 },3635 "rougeL": {3636 "mean": 0.7515270037496664,3637 "ci_low": 0.7392209794181591,3638 "ci_high": 0.7645964853681281,3639 "n_items": 128,3640 "n_groups": 503641 },3642 "exact_match": {3643 "mean": 0.0,3644 "ci_low": 0.0,3645 "ci_high": 0.0,3646 "n_items": 128,3647 "n_groups": 503648 },3649 "number_recall": {3650 "mean": 0.9988785885167464,3651 "ci_low": 0.9967466161853498,3652 "ci_high": 1.0,3653 "n_items": 128,3654 "n_groups": 503655 },3656 "placeholders_exact": {3657 "mean": 0.9921875,3658 "ci_low": 0.9724706931702345,3659 "ci_high": 1.0,3660 "n_items": 128,3661 "n_groups": 503662 }3663 },3664 "H2": {3665 "n": 138,3666 "chrf": {3667 "mean": 78.79586897054716,3668 "ci_low": 77.6296826764641,3669 "ci_high": 80.22963029483742,3670 "n_items": 138,3671 "n_groups": 533672 },3673 "edit_sim": {3674 "mean": 0.7871259999157123,3675 "ci_low": 0.7749377364189144,3676 "ci_high": 0.8014130340113192,3677 "n_items": 138,3678 "n_groups": 533679 },3680 "rougeL": {3681 "mean": 0.7936321584727594,3682 "ci_low": 0.7807992876089599,3683 "ci_high": 0.8090455615743624,3684 "n_items": 138,3685 "n_groups": 533686 },3687 "exact_match": {3688 "mean": 0.0,3689 "ci_low": 0.0,3690 "ci_high": 0.0,3691 "n_items": 138,3692 "n_groups": 533693 },3694 "number_recall": {3695 "mean": 0.99763709889568,3696 "ci_low": 0.9945342061240524,3697 "ci_high": 0.9996214231622221,3698 "n_items": 138,3699 "n_groups": 533700 },3701 "placeholders_exact": {3702 "mean": 0.9927536231884058,3703 "ci_low": 0.9748414460123672,3704 "ci_high": 1.0,3705 "n_items": 138,3706 "n_groups": 533707 }3708 }3709 },3710 "by_discipline": {3711 "biomedicine": {3712 "n": 57,3713 "chrf": {3714 "mean": 78.06452447652354,3715 "ci_low": 76.1312616003016,3716 "ci_high": 79.93965871186185,3717 "n_items": 57,3718 "n_groups": 263719 },3720 "edit_sim": {3721 "mean": 0.7590854920756335,3722 "ci_low": 0.736091962277231,3723 "ci_high": 0.7819685718533147,3724 "n_items": 57,3725 "n_groups": 263726 },3727 "rougeL": {3728 "mean": 0.7739634224814232,3729 "ci_low": 0.7547001697714424,3730 "ci_high": 0.7922071186801141,3731 "n_items": 57,3732 "n_groups": 263733 },3734 "exact_match": {3735 "mean": 0.0,3736 "ci_low": 0.0,3737 "ci_high": 0.0,3738 "n_items": 57,3739 "n_groups": 263740 },3741 "number_recall": {3742 "mean": 0.9971273212270442,3743 "ci_low": 0.9916724844535806,3744 "ci_high": 1.0,3745 "n_items": 57,3746 "n_groups": 263747 },3748 "placeholders_exact": {3749 "mean": 1.0,3750 "ci_low": 1.0,3751 "ci_high": 1.0,3752 "n_items": 57,3753 "n_groups": 263754 }3755 },3756 "computer_science": {3757 "n": 30,3758 "chrf": {3759 "mean": 75.80686926335359,3760 "ci_low": 74.36197167552498,3761 "ci_high": 78.69666443901087,3762 "n_items": 30,3763 "n_groups": 23764 },3765 "edit_sim": {3766 "mean": 0.7659851720186932,3767 "ci_low": 0.7650521335914696,3768 "ci_high": 0.7678512488731402,3769 "n_items": 30,3770 "n_groups": 23771 },3772 "rougeL": {3773 "mean": 0.7614920453471523,3774 "ci_low": 0.7520017005556083,3775 "ci_high": 0.7804727349302407,3776 "n_items": 30,3777 "n_groups": 23778 },3779 "exact_match": {3780 "mean": 0.0,3781 "ci_low": 0.0,3782 "ci_high": 0.0,3783 "n_items": 30,3784 "n_groups": 23785 },3786 "number_recall": {3787 "mean": 0.9976190476190477,3788 "ci_low": 0.9928571428571429,3789 "ci_high": 1.0,3790 "n_items": 30,3791 "n_groups": 23792 },3793 "placeholders_exact": {3794 "mean": 1.0,3795 "ci_low": 1.0,3796 "ci_high": 1.0,3797 "n_items": 30,3798 "n_groups": 23799 }3800 },3801 "earth_sciences": {3802 "n": 32,3803 "chrf": {3804 "mean": 76.72080944645442,3805 "ci_low": 74.33852253152666,3806 "ci_high": 78.18367905918473,3807 "n_items": 32,3808 "n_groups": 33809 },3810 "edit_sim": {3811 "mean": 0.7264008943796616,3812 "ci_low": 0.715911335302727,3813 "ci_high": 0.7342175507675642,3814 "n_items": 32,3815 "n_groups": 33816 },3817 "rougeL": {3818 "mean": 0.7522796099377557,3819 "ci_low": 0.7393024026527608,3820 "ci_high": 0.764332072573009,3821 "n_items": 32,3822 "n_groups": 33823 },3824 "exact_match": {3825 "mean": 0.0,3826 "ci_low": 0.0,3827 "ci_high": 0.0,3828 "n_items": 32,3829 "n_groups": 33830 },3831 "number_recall": {3832 "mean": 0.9983552631578947,3833 "ci_low": 0.9964912280701753,3834 "ci_high": 1.0,3835 "n_items": 32,3836 "n_groups": 33837 },3838 "placeholders_exact": {3839 "mean": 1.0,3840 "ci_low": 1.0,3841 "ci_high": 1.0,3842 "n_items": 32,3843 "n_groups": 33844 }3845 },3846 "economics": {3847 "n": 30,3848 "chrf": {3849 "mean": 76.53374162119346,3850 "ci_low": 76.53374162119346,3851 "ci_high": 76.53374162119346,3852 "n_items": 30,3853 "n_groups": 13854 },3855 "edit_sim": {3856 "mean": 0.7525924405317052,3857 "ci_low": 0.7525924405317052,3858 "ci_high": 0.7525924405317052,3859 "n_items": 30,3860 "n_groups": 13861 },3862 "rougeL": {3863 "mean": 0.7570708068135225,3864 "ci_low": 0.7570708068135225,3865 "ci_high": 0.7570708068135225,3866 "n_items": 30,3867 "n_groups": 13868 },3869 "exact_match": {3870 "mean": 0.0,3871 "ci_low": 0.0,3872 "ci_high": 0.0,3873 "n_items": 30,3874 "n_groups": 13875 },3876 "number_recall": {3877 "mean": 1.0,3878 "ci_low": 1.0,3879 "ci_high": 1.0,3880 "n_items": 30,3881 "n_groups": 13882 },3883 "placeholders_exact": {3884 "mean": 1.0,3885 "ci_low": 1.0,3886 "ci_high": 1.0,3887 "n_items": 30,3888 "n_groups": 13889 }3890 },3891 "engineering": {3892 "n": 6,3893 "chrf": {3894 "mean": 80.29831115816386,3895 "ci_low": 80.29831115816386,3896 "ci_high": 80.29831115816386,3897 "n_items": 6,3898 "n_groups": 13899 },3900 "edit_sim": {3901 "mean": 0.7594261318427106,3902 "ci_low": 0.7594261318427106,3903 "ci_high": 0.7594261318427106,3904 "n_items": 6,3905 "n_groups": 13906 },3907 "rougeL": {3908 "mean": 0.7658483039988532,3909 "ci_low": 0.7658483039988532,3910 "ci_high": 0.7658483039988532,3911 "n_items": 6,3912 "n_groups": 13913 },3914 "exact_match": {3915 "mean": 0.0,3916 "ci_low": 0.0,3917 "ci_high": 0.0,3918 "n_items": 6,3919 "n_groups": 13920 },3921 "number_recall": {3922 "mean": 1.0,3923 "ci_low": 1.0,3924 "ci_high": 1.0,3925 "n_items": 6,3926 "n_groups": 13927 },3928 "placeholders_exact": {3929 "mean": 1.0,3930 "ci_low": 1.0,3931 "ci_high": 1.0,3932 "n_items": 6,3933 "n_groups": 13934 }3935 },3936 "life_sciences": {3937 "n": 49,3938 "chrf": {3939 "mean": 79.41591442658493,3940 "ci_low": 77.56958223747426,3941 "ci_high": 81.63040784519762,3942 "n_items": 49,3943 "n_groups": 163944 },3945 "edit_sim": {3946 "mean": 0.7753272830002546,3947 "ci_low": 0.7534257778757545,3948 "ci_high": 0.7997328926660372,3949 "n_items": 49,3950 "n_groups": 163951 },3952 "rougeL": {3953 "mean": 0.7956903697733758,3954 "ci_low": 0.7743052149800245,3955 "ci_high": 0.8193026140624871,3956 "n_items": 49,3957 "n_groups": 163958 },3959 "exact_match": {3960 "mean": 0.0,3961 "ci_low": 0.0,3962 "ci_high": 0.0,3963 "n_items": 49,3964 "n_groups": 163965 },3966 "number_recall": {3967 "mean": 0.9962894248608535,3968 "ci_low": 0.9875997435166713,3969 "ci_high": 1.0,3970 "n_items": 49,3971 "n_groups": 163972 },3973 "placeholders_exact": {3974 "mean": 0.9591836734693877,3975 "ci_low": 0.8749335106382978,3976 "ci_high": 1.0,3977 "n_items": 49,3978 "n_groups": 163979 }3980 },3981 "social_sciences": {3982 "n": 38,3983 "chrf": {3984 "mean": 80.4546529789877,3985 "ci_low": 73.7491245316446,3986 "ci_high": 83.13780735526402,3987 "n_items": 38,3988 "n_groups": 43989 },3990 "edit_sim": {3991 "mean": 0.7893004041265004,3992 "ci_low": 0.7519722732728862,3993 "ci_high": 0.807409140651215,3994 "n_items": 38,3995 "n_groups": 43996 },3997 "rougeL": {3998 "mean": 0.8031416436998493,3999 "ci_low": 0.728643680130585,4000 "ci_high": 0.8276518129979268,4001 "n_items": 38,4002 "n_groups": 44003 },4004 "exact_match": {4005 "mean": 0.0,4006 "ci_low": 0.0,4007 "ci_high": 0.0,4008 "n_items": 38,4009 "n_groups": 44010 },4011 "number_recall": {4012 "mean": 1.0,4013 "ci_low": 1.0,4014 "ci_high": 1.0,4015 "n_items": 38,4016 "n_groups": 44017 },4018 "placeholders_exact": {4019 "mean": 1.0,4020 "ci_low": 1.0,4021 "ci_high": 1.0,4022 "n_items": 38,4023 "n_groups": 44024 }4025 },4026 "statistics": {4027 "n": 24,4028 "chrf": {4029 "mean": 76.06331353829758,4030 "ci_low": 74.91007250126928,4031 "ci_high": 76.63993405681174,4032 "n_items": 24,4033 "n_groups": 24034 },4035 "edit_sim": {4036 "mean": 0.7206764490436085,4037 "ci_low": 0.6894397713756035,4038 "ci_high": 0.7362947878776109,4039 "n_items": 24,4040 "n_groups": 24041 },4042 "rougeL": {4043 "mean": 0.7444852408935724,4044 "ci_low": 0.7275474297388662,4045 "ci_high": 0.7529541464709255,4046 "n_items": 24,4047 "n_groups": 24048 },4049 "exact_match": {4050 "mean": 0.0,4051 "ci_low": 0.0,4052 "ci_high": 0.0,4053 "n_items": 24,4054 "n_groups": 24055 },4056 "number_recall": {4057 "mean": 1.0,4058 "ci_low": 1.0,4059 "ci_high": 1.0,4060 "n_items": 24,4061 "n_groups": 24062 },4063 "placeholders_exact": {4064 "mean": 1.0,4065 "ci_low": 1.0,4066 "ci_high": 1.0,4067 "n_items": 24,4068 "n_groups": 24069 }4070 }4071 },4072 "by_era": {4073 "1980-1999": {4074 "n": 2,4075 "chrf": {4076 "mean": 78.7175411234671,4077 "ci_low": 78.08158322251515,4078 "ci_high": 79.35349902441905,4079 "n_items": 2,4080 "n_groups": 24081 },4082 "edit_sim": {4083 "mean": 0.7943440628614734,4084 "ci_low": 0.7322404371584699,4085 "ci_high": 0.856447688564477,4086 "n_items": 2,4087 "n_groups": 24088 },4089 "rougeL": {4090 "mean": 0.8044455544455544,4091 "ci_low": 0.7517482517482518,4092 "ci_high": 0.8571428571428571,4093 "n_items": 2,4094 "n_groups": 24095 },4096 "exact_match": {4097 "mean": 0.0,4098 "ci_low": 0.0,4099 "ci_high": 0.0,4100 "n_items": 2,4101 "n_groups": 24102 },4103 "number_recall": {4104 "mean": 1.0,4105 "ci_low": 1.0,4106 "ci_high": 1.0,4107 "n_items": 2,4108 "n_groups": 24109 },4110 "placeholders_exact": {4111 "mean": 1.0,4112 "ci_low": 1.0,4113 "ci_high": 1.0,4114 "n_items": 2,4115 "n_groups": 24116 }4117 },4118 "2000-2009": {4119 "n": 30,4120 "chrf": {4121 "mean": 78.3640548034125,4122 "ci_low": 76.17763615766057,4123 "ci_high": 81.692105838577,4124 "n_items": 30,4125 "n_groups": 74126 },4127 "edit_sim": {4128 "mean": 0.7578815440510354,4129 "ci_low": 0.721955743389531,4130 "ci_high": 0.8095803849341876,4131 "n_items": 30,4132 "n_groups": 74133 },4134 "rougeL": {4135 "mean": 0.7733855577065316,4136 "ci_low": 0.7467589562638658,4137 "ci_high": 0.8193249441084896,4138 "n_items": 30,4139 "n_groups": 74140 },4141 "exact_match": {4142 "mean": 0.0,4143 "ci_low": 0.0,4144 "ci_high": 0.0,4145 "n_items": 30,4146 "n_groups": 74147 },4148 "number_recall": {4149 "mean": 1.0,4150 "ci_low": 1.0,4151 "ci_high": 1.0,4152 "n_items": 30,4153 "n_groups": 74154 },4155 "placeholders_exact": {4156 "mean": 1.0,4157 "ci_low": 1.0,4158 "ci_high": 1.0,4159 "n_items": 30,4160 "n_groups": 74161 }4162 },4163 "2010-2017": {4164 "n": 234,4165 "chrf": {4166 "mean": 77.87423679319573,4167 "ci_low": 76.6614116520166,4168 "ci_high": 79.30457524054871,4169 "n_items": 234,4170 "n_groups": 464171 },4172 "edit_sim": {4173 "mean": 0.7588980315796605,4174 "ci_low": 0.7473052938328265,4175 "ci_high": 0.7716501709974173,4176 "n_items": 234,4177 "n_groups": 464178 },4179 "rougeL": {4180 "mean": 0.7731035748252608,4181 "ci_low": 0.7611018816850997,4182 "ci_high": 0.7878297978703942,4183 "n_items": 234,4184 "n_groups": 464185 },4186 "exact_match": {4187 "mean": 0.0,4188 "ci_low": 0.0,4189 "ci_high": 0.0,4190 "n_items": 234,4191 "n_groups": 464192 },4193 "number_recall": {4194 "mean": 0.9979930725544761,4195 "ci_low": 0.9953654046387465,4196 "ci_high": 0.9995936034442227,4197 "n_items": 234,4198 "n_groups": 464199 },4200 "placeholders_exact": {4201 "mean": 0.9914529914529915,4202 "ci_low": 0.9688654917219807,4203 "ci_high": 1.0,4204 "n_items": 234,4205 "n_groups": 464206 }4207 }4208 },4209 "by_role": {4210 "abstract": {4211 "n": 28,4212 "chrf": {4213 "mean": 81.7713234426466,4214 "ci_low": 79.76822193984884,4215 "ci_high": 84.10083207947208,4216 "n_items": 28,4217 "n_groups": 154218 },4219 "edit_sim": {4220 "mean": 0.8018223528195624,4221 "ci_low": 0.7690334723548444,4222 "ci_high": 0.8386126967246813,4223 "n_items": 28,4224 "n_groups": 154225 },4226 "rougeL": {4227 "mean": 0.8066141232931568,4228 "ci_low": 0.7782718406046386,4229 "ci_high": 0.8415152766024974,4230 "n_items": 28,4231 "n_groups": 154232 },4233 "exact_match": {4234 "mean": 0.0,4235 "ci_low": 0.0,4236 "ci_high": 0.0,4237 "n_items": 28,4238 "n_groups": 154239 },4240 "number_recall": {4241 "mean": 1.0,4242 "ci_low": 1.0,4243 "ci_high": 1.0,4244 "n_items": 28,4245 "n_groups": 154246 },4247 "placeholders_exact": {4248 "mean": 1.0,4249 "ci_low": 1.0,4250 "ci_high": 1.0,4251 "n_items": 28,4252 "n_groups": 154253 }4254 },4255 "background": {4256 "n": 16,4257 "chrf": {4258 "mean": 79.69496689499017,4259 "ci_low": 73.88172608369187,4260 "ci_high": 84.67713564419087,4261 "n_items": 16,4262 "n_groups": 74263 },4264 "edit_sim": {4265 "mean": 0.7760421897331028,4266 "ci_low": 0.7198568619594196,4267 "ci_high": 0.8224700133967472,4268 "n_items": 16,4269 "n_groups": 74270 },4271 "rougeL": {4272 "mean": 0.801598998763693,4273 "ci_low": 0.7518546759652979,4274 "ci_high": 0.8430348976083359,4275 "n_items": 16,4276 "n_groups": 74277 },4278 "exact_match": {4279 "mean": 0.0,4280 "ci_low": 0.0,4281 "ci_high": 0.0,4282 "n_items": 16,4283 "n_groups": 74284 },4285 "number_recall": {4286 "mean": 1.0,4287 "ci_low": 1.0,4288 "ci_high": 1.0,4289 "n_items": 16,4290 "n_groups": 74291 },4292 "placeholders_exact": {4293 "mean": 1.0,4294 "ci_low": 1.0,4295 "ci_high": 1.0,4296 "n_items": 16,4297 "n_groups": 74298 }4299 },4300 "conclusion": {4301 "n": 17,4302 "chrf": {4303 "mean": 76.83165180996288,4304 "ci_low": 73.06144263362768,4305 "ci_high": 80.2675332965508,4306 "n_items": 17,4307 "n_groups": 94308 },4309 "edit_sim": {4310 "mean": 0.7453636660488147,4311 "ci_low": 0.7105492405314293,4312 "ci_high": 0.771109094695691,4313 "n_items": 17,4314 "n_groups": 94315 },4316 "rougeL": {4317 "mean": 0.7584982468940625,4318 "ci_low": 0.7279600966650368,4319 "ci_high": 0.7861791223330059,4320 "n_items": 17,4321 "n_groups": 94322 },4323 "exact_match": {4324 "mean": 0.0,4325 "ci_low": 0.0,4326 "ci_high": 0.0,4327 "n_items": 17,4328 "n_groups": 94329 },4330 "number_recall": {4331 "mean": 1.0,4332 "ci_low": 1.0,4333 "ci_high": 1.0,4334 "n_items": 17,4335 "n_groups": 94336 },4337 "placeholders_exact": {4338 "mean": 1.0,4339 "ci_low": 1.0,4340 "ci_high": 1.0,4341 "n_items": 17,4342 "n_groups": 94343 }4344 },4345 "data": {4346 "n": 25,4347 "chrf": {4348 "mean": 78.83899823617173,4349 "ci_low": 75.97058785340839,4350 "ci_high": 81.68342274782265,4351 "n_items": 25,4352 "n_groups": 104353 },4354 "edit_sim": {4355 "mean": 0.7445184755330956,4356 "ci_low": 0.7191949376988857,4357 "ci_high": 0.7762976310885004,4358 "n_items": 25,4359 "n_groups": 104360 },4361 "rougeL": {4362 "mean": 0.7717337373896435,4363 "ci_low": 0.7398336860949203,4364 "ci_high": 0.8032461985705723,4365 "n_items": 25,4366 "n_groups": 104367 },4368 "exact_match": {4369 "mean": 0.0,4370 "ci_low": 0.0,4371 "ci_high": 0.0,4372 "n_items": 25,4373 "n_groups": 104374 },4375 "number_recall": {4376 "mean": 0.9978947368421052,4377 "ci_low": 0.993684210526316,4378 "ci_high": 1.0,4379 "n_items": 25,4380 "n_groups": 104381 },4382 "placeholders_exact": {4383 "mean": 1.0,4384 "ci_low": 1.0,4385 "ci_high": 1.0,4386 "n_items": 25,4387 "n_groups": 104388 }4389 },4390 "discussion": {4391 "n": 34,4392 "chrf": {4393 "mean": 78.23577208231622,4394 "ci_low": 75.72539787163072,4395 "ci_high": 80.14561800403875,4396 "n_items": 34,4397 "n_groups": 144398 },4399 "edit_sim": {4400 "mean": 0.7623627000488347,4401 "ci_low": 0.7454807461816747,4402 "ci_high": 0.780093203314177,4403 "n_items": 34,4404 "n_groups": 144405 },4406 "rougeL": {4407 "mean": 0.7739895108214367,4408 "ci_low": 0.7426314113063651,4409 "ci_high": 0.7997593604934189,4410 "n_items": 34,4411 "n_groups": 144412 },4413 "exact_match": {4414 "mean": 0.0,4415 "ci_low": 0.0,4416 "ci_high": 0.0,4417 "n_items": 34,4418 "n_groups": 144419 },4420 "number_recall": {4421 "mean": 1.0,4422 "ci_low": 1.0,4423 "ci_high": 1.0,4424 "n_items": 34,4425 "n_groups": 144426 },4427 "placeholders_exact": {4428 "mean": 1.0,4429 "ci_low": 1.0,4430 "ci_high": 1.0,4431 "n_items": 34,4432 "n_groups": 144433 }4434 },4435 "introduction": {4436 "n": 31,4437 "chrf": {4438 "mean": 76.76847062511123,4439 "ci_low": 74.97600344412596,4440 "ci_high": 78.58145241861651,4441 "n_items": 31,4442 "n_groups": 134443 },4444 "edit_sim": {4445 "mean": 0.7395798034630172,4446 "ci_low": 0.6999013324929751,4447 "ci_high": 0.771942692150138,4448 "n_items": 31,4449 "n_groups": 134450 },4451 "rougeL": {4452 "mean": 0.7520311547851809,4453 "ci_low": 0.7233081116470939,4454 "ci_high": 0.7761832745062035,4455 "n_items": 31,4456 "n_groups": 134457 },4458 "exact_match": {4459 "mean": 0.0,4460 "ci_low": 0.0,4461 "ci_high": 0.0,4462 "n_items": 31,4463 "n_groups": 134464 },4465 "number_recall": {4466 "mean": 0.996415770609319,4467 "ci_low": 0.9880952380952381,4468 "ci_high": 1.0,4469 "n_items": 31,4470 "n_groups": 134471 },4472 "placeholders_exact": {4473 "mean": 1.0,4474 "ci_low": 1.0,4475 "ci_high": 1.0,4476 "n_items": 31,4477 "n_groups": 134478 }4479 },4480 "limitations": {4481 "n": 14,4482 "chrf": {4483 "mean": 78.52083690694478,4484 "ci_low": 75.66616181824301,4485 "ci_high": 79.63563340961721,4486 "n_items": 14,4487 "n_groups": 44488 },4489 "edit_sim": {4490 "mean": 0.7874571141510801,4491 "ci_low": 0.7432507712596729,4492 "ci_high": 0.8066320551615611,4493 "n_items": 14,4494 "n_groups": 44495 },4496 "rougeL": {4497 "mean": 0.7923540716406494,4498 "ci_low": 0.7489196840910873,4499 "ci_high": 0.8083145929150433,4500 "n_items": 14,4501 "n_groups": 44502 },4503 "exact_match": {4504 "mean": 0.0,4505 "ci_low": 0.0,4506 "ci_high": 0.0,4507 "n_items": 14,4508 "n_groups": 44509 },4510 "number_recall": {4511 "mean": 1.0,4512 "ci_low": 1.0,4513 "ci_high": 1.0,4514 "n_items": 14,4515 "n_groups": 44516 },4517 "placeholders_exact": {4518 "mean": 1.0,4519 "ci_low": 1.0,4520 "ci_high": 1.0,4521 "n_items": 14,4522 "n_groups": 44523 }4524 },4525 "methods": {4526 "n": 32,4527 "chrf": {4528 "mean": 77.18314701061001,4529 "ci_low": 74.9465300404139,4530 "ci_high": 79.80713446793462,4531 "n_items": 32,4532 "n_groups": 124533 },4534 "edit_sim": {4535 "mean": 0.7661338987790012,4536 "ci_low": 0.7373045870534136,4537 "ci_high": 0.7900586219286184,4538 "n_items": 32,4539 "n_groups": 124540 },4541 "rougeL": {4542 "mean": 0.7764027324211766,4543 "ci_low": 0.7545631942930492,4544 "ci_high": 0.7994905858827267,4545 "n_items": 32,4546 "n_groups": 124547 },4548 "exact_match": {4549 "mean": 0.0,4550 "ci_low": 0.0,4551 "ci_high": 0.0,4552 "n_items": 32,4553 "n_groups": 124554 },4555 "number_recall": {4556 "mean": 1.0,4557 "ci_low": 1.0,4558 "ci_high": 1.0,4559 "n_items": 32,4560 "n_groups": 124561 },4562 "placeholders_exact": {4563 "mean": 1.0,4564 "ci_low": 1.0,4565 "ci_high": 1.0,4566 "n_items": 32,4567 "n_groups": 124568 }4569 },4570 "other": {4571 "n": 22,4572 "chrf": {4573 "mean": 77.91838071463734,4574 "ci_low": 72.88396308270107,4575 "ci_high": 81.78550089509162,4576 "n_items": 22,4577 "n_groups": 84578 },4579 "edit_sim": {4580 "mean": 0.7658326655487276,4581 "ci_low": 0.71565315810556,4582 "ci_high": 0.8102835673019896,4583 "n_items": 22,4584 "n_groups": 84585 },4586 "rougeL": {4587 "mean": 0.7702712618328174,4588 "ci_low": 0.715029338193421,4589 "ci_high": 0.8160635796806599,4590 "n_items": 22,4591 "n_groups": 84592 },4593 "exact_match": {4594 "mean": 0.0,4595 "ci_low": 0.0,4596 "ci_high": 0.0,4597 "n_items": 22,4598 "n_groups": 84599 },4600 "number_recall": {4601 "mean": 1.0,4602 "ci_low": 1.0,4603 "ci_high": 1.0,4604 "n_items": 22,4605 "n_groups": 84606 },4607 "placeholders_exact": {4608 "mean": 0.9090909090909091,4609 "ci_low": 0.7391304347826086,4610 "ci_high": 1.0,4611 "n_items": 22,4612 "n_groups": 84613 }4614 },4615 "related_work": {4616 "n": 2,4617 "chrf": {4618 "mean": 81.29801024319144,4619 "ci_low": 81.29801024319144,4620 "ci_high": 81.29801024319144,4621 "n_items": 2,4622 "n_groups": 14623 },4624 "edit_sim": {4625 "mean": 0.7934773419308615,4626 "ci_low": 0.7934773419308615,4627 "ci_high": 0.7934773419308615,4628 "n_items": 2,4629 "n_groups": 14630 },4631 "rougeL": {4632 "mean": 0.8022504456327986,4633 "ci_low": 0.8022504456327986,4634 "ci_high": 0.8022504456327986,4635 "n_items": 2,4636 "n_groups": 14637 },4638 "exact_match": {4639 "mean": 0.0,4640 "ci_low": 0.0,4641 "ci_high": 0.0,4642 "n_items": 2,4643 "n_groups": 14644 },4645 "number_recall": {4646 "mean": 1.0,4647 "ci_low": 1.0,4648 "ci_high": 1.0,4649 "n_items": 2,4650 "n_groups": 14651 },4652 "placeholders_exact": {4653 "mean": 1.0,4654 "ci_low": 1.0,4655 "ci_high": 1.0,4656 "n_items": 2,4657 "n_groups": 14658 }4659 },4660 "results": {4661 "n": 26,4662 "chrf": {4663 "mean": 74.6207383735661,4664 "ci_low": 72.79399392337578,4665 "ci_high": 76.50424058711734,4666 "n_items": 26,4667 "n_groups": 104668 },4669 "edit_sim": {4670 "mean": 0.7138293215928245,4671 "ci_low": 0.6916776623296937,4672 "ci_high": 0.7413015506875632,4673 "n_items": 26,4674 "n_groups": 104675 },4676 "rougeL": {4677 "mean": 0.7466340542030225,4678 "ci_low": 0.7324301953311887,4679 "ci_high": 0.7672096016549971,4680 "n_items": 26,4681 "n_groups": 104682 },4683 "exact_match": {4684 "mean": 0.0,4685 "ci_low": 0.0,4686 "ci_high": 0.0,4687 "n_items": 26,4688 "n_groups": 104689 },4690 "number_recall": {4691 "mean": 0.9952284557547716,4692 "ci_low": 0.9881648565859092,4693 "ci_high": 1.0,4694 "n_items": 26,4695 "n_groups": 104696 },4697 "placeholders_exact": {4698 "mean": 1.0,4699 "ci_low": 1.0,4700 "ci_high": 1.0,4701 "n_items": 26,4702 "n_groups": 104703 }4704 },4705 "theory": {4706 "n": 19,4707 "chrf": {4708 "mean": 77.00882723339126,4709 "ci_low": 74.71273603859521,4710 "ci_high": 81.24101154493367,4711 "n_items": 19,4712 "n_groups": 64713 },4714 "edit_sim": {4715 "mean": 0.7564527871397742,4716 "ci_low": 0.722854264402543,4717 "ci_high": 0.8004688917343827,4718 "n_items": 19,4719 "n_groups": 64720 },4721 "rougeL": {4722 "mean": 0.7678259798551634,4723 "ci_low": 0.7417032584224371,4724 "ci_high": 0.80416982004459,4725 "n_items": 19,4726 "n_groups": 64727 },4728 "exact_match": {4729 "mean": 0.0,4730 "ci_low": 0.0,4731 "ci_high": 0.0,4732 "n_items": 19,4733 "n_groups": 64734 },4735 "number_recall": {4736 "mean": 0.9904306220095694,4737 "ci_low": 0.9679144385026737,4738 "ci_high": 1.0,4739 "n_items": 19,4740 "n_groups": 64741 },4742 "placeholders_exact": {4743 "mean": 1.0,4744 "ci_low": 1.0,4745 "ci_high": 1.0,4746 "n_items": 19,4747 "n_groups": 64748 }4749 }4750 }4751 },4752 "htr-m1-tiny": {4753 "overall": {4754 "n": 266,4755 "chrf": {4756 "mean": 77.90140007792925,4757 "ci_low": 76.86094494697039,4758 "ci_high": 79.12586504584982,4759 "n_items": 266,4760 "n_groups": 554761 },4762 "edit_sim": {4763 "mean": 0.7586232132134015,4764 "ci_low": 0.7477221318604461,4765 "ci_high": 0.7699773558772802,4766 "n_items": 266,4767 "n_groups": 554768 },4769 "rougeL": {4770 "mean": 0.7731304567689509,4771 "ci_low": 0.7623853726889251,4772 "ci_high": 0.7860435453519817,4773 "n_items": 266,4774 "n_groups": 554775 },4776 "exact_match": {4777 "mean": 0.0,4778 "ci_low": 0.0,4779 "ci_high": 0.0,4780 "n_items": 266,4781 "n_groups": 554782 },4783 "number_recall": {4784 "mean": 0.9940950016434782,4785 "ci_low": 0.987200094757932,4786 "ci_high": 0.9984389750777309,4787 "n_items": 266,4788 "n_groups": 554789 },4790 "placeholders_exact": {4791 "mean": 0.9887218045112782,4792 "ci_low": 0.9683257918552036,4793 "ci_high": 1.0,4794 "n_items": 266,4795 "n_groups": 554796 }4797 },4798 "by_variant": {4799 "H1": {4800 "n": 128,4801 "chrf": {4802 "mean": 76.98311239772104,4803 "ci_low": 75.85092306532079,4804 "ci_high": 78.2297611456916,4805 "n_items": 128,4806 "n_groups": 504807 },4808 "edit_sim": {4809 "mean": 0.7282085179134675,4810 "ci_low": 0.7132407067524311,4811 "ci_high": 0.7419684723741865,4812 "n_items": 128,4813 "n_groups": 504814 },4815 "rougeL": {4816 "mean": 0.7513589836708282,4817 "ci_low": 0.7393725767199318,4818 "ci_high": 0.7636820650779211,4819 "n_items": 128,4820 "n_groups": 504821 },4822 "exact_match": {4823 "mean": 0.0,4824 "ci_low": 0.0,4825 "ci_high": 0.0,4826 "n_items": 128,4827 "n_groups": 504828 },4829 "number_recall": {4830 "mean": 0.9946237983964135,4831 "ci_low": 0.9885978103962862,4832 "ci_high": 0.998630270501215,4833 "n_items": 128,4834 "n_groups": 504835 },4836 "placeholders_exact": {4837 "mean": 0.984375,4838 "ci_low": 0.9591794914687186,4839 "ci_high": 1.0,4840 "n_items": 128,4841 "n_groups": 504842 }4843 },4844 "H2": {4845 "n": 138,4846 "chrf": {4847 "mean": 78.75314517261513,4848 "ci_low": 77.6796271190011,4849 "ci_high": 80.06914635054548,4850 "n_items": 138,4851 "n_groups": 534852 },4853 "edit_sim": {4854 "mean": 0.7868339450858041,4855 "ci_low": 0.7756968626326403,4856 "ci_high": 0.799879038164397,4857 "n_items": 138,4858 "n_groups": 534859 },4860 "rougeL": {4861 "mean": 0.7933242868889487,4862 "ci_low": 0.7813261806268111,4863 "ci_high": 0.8081211877734377,4864 "n_items": 138,4865 "n_groups": 534866 },4867 "exact_match": {4868 "mean": 0.0,4869 "ci_low": 0.0,4870 "ci_high": 0.0,4871 "n_items": 138,4872 "n_groups": 534873 },4874 "number_recall": {4875 "mean": 0.9936045234958278,4876 "ci_low": 0.9833987493677091,4877 "ci_high": 0.9991387937583367,4878 "n_items": 138,4879 "n_groups": 534880 },4881 "placeholders_exact": {4882 "mean": 0.9927536231884058,4883 "ci_low": 0.9748414460123672,4884 "ci_high": 1.0,4885 "n_items": 138,4886 "n_groups": 534887 }4888 }4889 },4890 "by_discipline": {4891 "biomedicine": {4892 "n": 57,4893 "chrf": {4894 "mean": 78.01274299063849,4895 "ci_low": 76.03553366177199,4896 "ci_high": 79.83767827677175,4897 "n_items": 57,4898 "n_groups": 264899 },4900 "edit_sim": {4901 "mean": 0.758317361790059,4902 "ci_low": 0.7356560986007521,4903 "ci_high": 0.7798445062624514,4904 "n_items": 57,4905 "n_groups": 264906 },4907 "rougeL": {4908 "mean": 0.7737203697041448,4909 "ci_low": 0.7546320975402638,4910 "ci_high": 0.7917801303840204,4911 "n_items": 57,4912 "n_groups": 264913 },4914 "exact_match": {4915 "mean": 0.0,4916 "ci_low": 0.0,4917 "ci_high": 0.0,4918 "n_items": 57,4919 "n_groups": 264920 },4921 "number_recall": {4922 "mean": 0.9928696009028419,4923 "ci_low": 0.9801269555655521,4924 "ci_high": 1.0,4925 "n_items": 57,4926 "n_groups": 264927 },4928 "placeholders_exact": {4929 "mean": 1.0,4930 "ci_low": 1.0,4931 "ci_high": 1.0,4932 "n_items": 57,4933 "n_groups": 264934 }4935 },4936 "computer_science": {4937 "n": 30,4938 "chrf": {4939 "mean": 76.50350785201357,4940 "ci_low": 75.03693266293833,4941 "ci_high": 79.43665823016401,4942 "n_items": 30,4943 "n_groups": 24944 },4945 "edit_sim": {4946 "mean": 0.767958077466585,4947 "ci_low": 0.7672588444607762,4948 "ci_high": 0.7693565434782027,4949 "n_items": 30,4950 "n_groups": 24951 },4952 "rougeL": {4953 "mean": 0.7668587163491488,4954 "ci_low": 0.7546934301461505,4955 "ci_high": 0.7911892887551455,4956 "n_items": 30,4957 "n_groups": 24958 },4959 "exact_match": {4960 "mean": 0.0,4961 "ci_low": 0.0,4962 "ci_high": 0.0,4963 "n_items": 30,4964 "n_groups": 24965 },4966 "number_recall": {4967 "mean": 1.0,4968 "ci_low": 1.0,4969 "ci_high": 1.0,4970 "n_items": 30,4971 "n_groups": 24972 },4973 "placeholders_exact": {4974 "mean": 1.0,4975 "ci_low": 1.0,4976 "ci_high": 1.0,4977 "n_items": 30,4978 "n_groups": 24979 }4980 },4981 "earth_sciences": {4982 "n": 32,4983 "chrf": {4984 "mean": 76.8431587310058,4985 "ci_low": 74.00784352294129,4986 "ci_high": 78.70206735569121,4987 "n_items": 32,4988 "n_groups": 34989 },4990 "edit_sim": {4991 "mean": 0.7295719206856222,4992 "ci_low": 0.7113806769244633,4993 "ci_high": 0.7392586614929513,4994 "n_items": 32,4995 "n_groups": 34996 },4997 "rougeL": {4998 "mean": 0.7513633022608933,4999 "ci_low": 0.7288309164440744,5000 "ci_high": 0.7662401874521156,5001 "n_items": 32,5002 "n_groups": 35003 },5004 "exact_match": {5005 "mean": 0.0,5006 "ci_low": 0.0,5007 "ci_high": 0.0,5008 "n_items": 32,5009 "n_groups": 35010 },5011 "number_recall": {5012 "mean": 0.9951388888888889,5013 "ci_low": 0.9896296296296296,5014 "ci_high": 1.0,5015 "n_items": 32,5016 "n_groups": 35017 },5018 "placeholders_exact": {5019 "mean": 0.96875,5020 "ci_low": 0.9333333333333333,5021 "ci_high": 1.0,5022 "n_items": 32,5023 "n_groups": 35024 }5025 },5026 "economics": {5027 "n": 30,5028 "chrf": {5029 "mean": 76.62319072329026,5030 "ci_low": 76.62319072329026,5031 "ci_high": 76.62319072329026,5032 "n_items": 30,5033 "n_groups": 15034 },5035 "edit_sim": {5036 "mean": 0.7521854172210661,5037 "ci_low": 0.7521854172210661,5038 "ci_high": 0.7521854172210661,5039 "n_items": 30,5040 "n_groups": 15041 },5042 "rougeL": {5043 "mean": 0.761059246648942,5044 "ci_low": 0.761059246648942,5045 "ci_high": 0.761059246648942,5046 "n_items": 30,5047 "n_groups": 15048 },5049 "exact_match": {5050 "mean": 0.0,5051 "ci_low": 0.0,5052 "ci_high": 0.0,5053 "n_items": 30,5054 "n_groups": 15055 },5056 "number_recall": {5057 "mean": 1.0,5058 "ci_low": 1.0,5059 "ci_high": 1.0,5060 "n_items": 30,5061 "n_groups": 15062 },5063 "placeholders_exact": {5064 "mean": 1.0,5065 "ci_low": 1.0,5066 "ci_high": 1.0,5067 "n_items": 30,5068 "n_groups": 15069 }5070 },5071 "engineering": {5072 "n": 6,5073 "chrf": {5074 "mean": 79.65192360056905,5075 "ci_low": 79.65192360056905,5076 "ci_high": 79.65192360056905,5077 "n_items": 6,5078 "n_groups": 15079 },5080 "edit_sim": {5081 "mean": 0.7651623394421759,5082 "ci_low": 0.7651623394421759,5083 "ci_high": 0.7651623394421759,5084 "n_items": 6,5085 "n_groups": 15086 },5087 "rougeL": {5088 "mean": 0.759574894767899,5089 "ci_low": 0.759574894767899,5090 "ci_high": 0.759574894767899,5091 "n_items": 6,5092 "n_groups": 15093 },5094 "exact_match": {5095 "mean": 0.0,5096 "ci_low": 0.0,5097 "ci_high": 0.0,5098 "n_items": 6,5099 "n_groups": 15100 },5101 "number_recall": {5102 "mean": 1.0,5103 "ci_low": 1.0,5104 "ci_high": 1.0,5105 "n_items": 6,5106 "n_groups": 15107 },5108 "placeholders_exact": {5109 "mean": 1.0,5110 "ci_low": 1.0,5111 "ci_high": 1.0,5112 "n_items": 6,5113 "n_groups": 15114 }5115 },5116 "life_sciences": {5117 "n": 49,5118 "chrf": {5119 "mean": 79.00253745881089,5120 "ci_low": 77.27286628017292,5121 "ci_high": 81.13537247350197,5122 "n_items": 49,5123 "n_groups": 165124 },5125 "edit_sim": {5126 "mean": 0.7748850450538101,5127 "ci_low": 0.7566388130363996,5128 "ci_high": 0.7962130217058967,5129 "n_items": 49,5130 "n_groups": 165131 },5132 "rougeL": {5133 "mean": 0.795088190127251,5134 "ci_low": 0.7756002688324894,5135 "ci_high": 0.8180007059718638,5136 "n_items": 49,5137 "n_groups": 165138 },5139 "exact_match": {5140 "mean": 0.0,5141 "ci_low": 0.0,5142 "ci_high": 0.0,5143 "n_items": 49,5144 "n_groups": 165145 },5146 "number_recall": {5147 "mean": 0.9794134436991581,5148 "ci_low": 0.9494034090909091,5149 "ci_high": 1.0,5150 "n_items": 49,5151 "n_groups": 165152 },5153 "placeholders_exact": {5154 "mean": 0.9591836734693877,5155 "ci_low": 0.8749335106382978,5156 "ci_high": 1.0,5157 "n_items": 49,5158 "n_groups": 165159 }5160 },5161 "social_sciences": {5162 "n": 38,5163 "chrf": {5164 "mean": 80.2523647612724,5165 "ci_low": 73.78375779502286,5166 "ci_high": 83.06143838965409,5167 "n_items": 38,5168 "n_groups": 45169 },5170 "edit_sim": {5171 "mean": 0.7852238871425049,5172 "ci_low": 0.7509193839159972,5173 "ci_high": 0.8120157101131038,5174 "n_items": 38,5175 "n_groups": 45176 },5177 "rougeL": {5178 "mean": 0.7996931539884163,5179 "ci_low": 0.7204518740338067,5180 "ci_high": 0.8276579814246976,5181 "n_items": 38,5182 "n_groups": 45183 },5184 "exact_match": {5185 "mean": 0.0,5186 "ci_low": 0.0,5187 "ci_high": 0.0,5188 "n_items": 38,5189 "n_groups": 45190 },5191 "number_recall": {5192 "mean": 1.0,5193 "ci_low": 1.0,5194 "ci_high": 1.0,5195 "n_items": 38,5196 "n_groups": 45197 },5198 "placeholders_exact": {5199 "mean": 1.0,5200 "ci_low": 1.0,5201 "ci_high": 1.0,5202 "n_items": 38,5203 "n_groups": 45204 }5205 },5206 "statistics": {5207 "n": 24,5208 "chrf": {5209 "mean": 75.98492898324962,5210 "ci_low": 74.57806159440939,5211 "ci_high": 76.68836267766974,5212 "n_items": 24,5213 "n_groups": 25214 },5215 "edit_sim": {5216 "mean": 0.7175095764357112,5217 "ci_low": 0.6849812478342115,5218 "ci_high": 0.7337737407364611,5219 "n_items": 24,5220 "n_groups": 25221 },5222 "rougeL": {5223 "mean": 0.7401818886962858,5224 "ci_low": 0.7198919843580688,5225 "ci_high": 0.7503268408653943,5226 "n_items": 24,5227 "n_groups": 25228 },5229 "exact_match": {5230 "mean": 0.0,5231 "ci_low": 0.0,5232 "ci_high": 0.0,5233 "n_items": 24,5234 "n_groups": 25235 },5236 "number_recall": {5237 "mean": 1.0,5238 "ci_low": 1.0,5239 "ci_high": 1.0,5240 "n_items": 24,5241 "n_groups": 25242 },5243 "placeholders_exact": {5244 "mean": 1.0,5245 "ci_low": 1.0,5246 "ci_high": 1.0,5247 "n_items": 24,5248 "n_groups": 25249 }5250 }5251 },5252 "by_era": {5253 "1980-1999": {5254 "n": 2,5255 "chrf": {5256 "mean": 78.18708710311213,5257 "ci_low": 77.82775035052292,5258 "ci_high": 78.54642385570133,5259 "n_items": 2,5260 "n_groups": 25261 },5262 "edit_sim": {5263 "mean": 0.7943457713536719,5264 "ci_low": 0.7468423942888522,5265 "ci_high": 0.8418491484184915,5266 "n_items": 2,5267 "n_groups": 25268 },5269 "rougeL": {5270 "mean": 0.7989675516224188,5271 "ci_low": 0.7646017699115044,5272 "ci_high": 0.8333333333333334,5273 "n_items": 2,5274 "n_groups": 25275 },5276 "exact_match": {5277 "mean": 0.0,5278 "ci_low": 0.0,5279 "ci_high": 0.0,5280 "n_items": 2,5281 "n_groups": 25282 },5283 "number_recall": {5284 "mean": 1.0,5285 "ci_low": 1.0,5286 "ci_high": 1.0,5287 "n_items": 2,5288 "n_groups": 25289 },5290 "placeholders_exact": {5291 "mean": 1.0,5292 "ci_low": 1.0,5293 "ci_high": 1.0,5294 "n_items": 2,5295 "n_groups": 25296 }5297 },5298 "2000-2009": {5299 "n": 30,5300 "chrf": {5301 "mean": 77.69338930965837,5302 "ci_low": 75.56308873218116,5303 "ci_high": 81.00882746185835,5304 "n_items": 30,5305 "n_groups": 75306 },5307 "edit_sim": {5308 "mean": 0.7526420062409235,5309 "ci_low": 0.7174432465084609,5310 "ci_high": 0.8053834289137388,5311 "n_items": 30,5312 "n_groups": 75313 },5314 "rougeL": {5315 "mean": 0.7672424577693312,5316 "ci_low": 0.7402107416946191,5317 "ci_high": 0.8150994760684224,5318 "n_items": 30,5319 "n_groups": 75320 },5321 "exact_match": {5322 "mean": 0.0,5323 "ci_low": 0.0,5324 "ci_high": 0.0,5325 "n_items": 30,5326 "n_groups": 75327 },5328 "number_recall": {5329 "mean": 1.0,5330 "ci_low": 1.0,5331 "ci_high": 1.0,5332 "n_items": 30,5333 "n_groups": 75334 },5335 "placeholders_exact": {5336 "mean": 1.0,5337 "ci_low": 1.0,5338 "ci_high": 1.0,5339 "n_items": 30,5340 "n_groups": 75341 }5342 },5343 "2010-2017": {5344 "n": 234,5345 "chrf": {5346 "mean": 77.92562635569747,5347 "ci_low": 76.73646218108244,5348 "ci_high": 79.30365426297668,5349 "n_items": 234,5350 "n_groups": 465351 },5352 "edit_sim": {5353 "mean": 0.7590847136103837,5354 "ci_low": 0.7480662505280736,5355 "ci_high": 0.770993420274652,5356 "n_items": 234,5357 "n_groups": 465358 },5359 "rougeL": {5360 "mean": 0.7736644985650263,5361 "ci_low": 0.7614802167819091,5362 "ci_high": 0.7875714902923093,5363 "n_items": 234,5364 "n_groups": 465365 },5366 "exact_match": {5367 "mean": 0.0,5368 "ci_low": 0.0,5369 "ci_high": 0.0,5370 "n_items": 234,5371 "n_groups": 465372 },5373 "number_recall": {5374 "mean": 0.9932874805007058,5375 "ci_low": 0.9855936590034793,5376 "ci_high": 0.9983432001153856,5377 "n_items": 234,5378 "n_groups": 465379 },5380 "placeholders_exact": {5381 "mean": 0.9871794871794872,5382 "ci_low": 0.9644917582417583,5383 "ci_high": 1.0,5384 "n_items": 234,5385 "n_groups": 465386 }5387 }5388 },5389 "by_role": {5390 "abstract": {5391 "n": 28,5392 "chrf": {5393 "mean": 81.58463684699836,5394 "ci_low": 79.45146178813407,5395 "ci_high": 84.05629788686069,5396 "n_items": 28,5397 "n_groups": 155398 },5399 "edit_sim": {5400 "mean": 0.8017671921308098,5401 "ci_low": 0.7693784721244629,5402 "ci_high": 0.8390751707766848,5403 "n_items": 28,5404 "n_groups": 155405 },5406 "rougeL": {5407 "mean": 0.806102424790301,5408 "ci_low": 0.7762184039734867,5409 "ci_high": 0.8418213735107276,5410 "n_items": 28,5411 "n_groups": 155412 },5413 "exact_match": {5414 "mean": 0.0,5415 "ci_low": 0.0,5416 "ci_high": 0.0,5417 "n_items": 28,5418 "n_groups": 155419 },5420 "number_recall": {5421 "mean": 1.0,5422 "ci_low": 1.0,5423 "ci_high": 1.0,5424 "n_items": 28,5425 "n_groups": 155426 },5427 "placeholders_exact": {5428 "mean": 1.0,5429 "ci_low": 1.0,5430 "ci_high": 1.0,5431 "n_items": 28,5432 "n_groups": 155433 }5434 },5435 "background": {5436 "n": 16,5437 "chrf": {5438 "mean": 79.32151470717898,5439 "ci_low": 73.19271985619795,5440 "ci_high": 84.68723216532578,5441 "n_items": 16,5442 "n_groups": 75443 },5444 "edit_sim": {5445 "mean": 0.7724673756097298,5446 "ci_low": 0.7180684775415892,5447 "ci_high": 0.8184476131179487,5448 "n_items": 16,5449 "n_groups": 75450 },5451 "rougeL": {5452 "mean": 0.7993148495286996,5453 "ci_low": 0.7478474904406465,5454 "ci_high": 0.8411150260280842,5455 "n_items": 16,5456 "n_groups": 75457 },5458 "exact_match": {5459 "mean": 0.0,5460 "ci_low": 0.0,5461 "ci_high": 0.0,5462 "n_items": 16,5463 "n_groups": 75464 },5465 "number_recall": {5466 "mean": 0.9965277777777778,5467 "ci_low": 0.9895833333333334,5468 "ci_high": 1.0,5469 "n_items": 16,5470 "n_groups": 75471 },5472 "placeholders_exact": {5473 "mean": 0.9375,5474 "ci_low": 0.8125,5475 "ci_high": 1.0,5476 "n_items": 16,5477 "n_groups": 75478 }5479 },5480 "conclusion": {5481 "n": 17,5482 "chrf": {5483 "mean": 77.70360170473144,5484 "ci_low": 73.87723629246976,5485 "ci_high": 81.39377611092924,5486 "n_items": 17,5487 "n_groups": 95488 },5489 "edit_sim": {5490 "mean": 0.7490641903339591,5491 "ci_low": 0.7116999031210882,5492 "ci_high": 0.7780991346480733,5493 "n_items": 17,5494 "n_groups": 95495 },5496 "rougeL": {5497 "mean": 0.7659107639262747,5498 "ci_low": 0.7333117340904662,5499 "ci_high": 0.795562438638937,5500 "n_items": 17,5501 "n_groups": 95502 },5503 "exact_match": {5504 "mean": 0.0,5505 "ci_low": 0.0,5506 "ci_high": 0.0,5507 "n_items": 17,5508 "n_groups": 95509 },5510 "number_recall": {5511 "mean": 0.9705882352941176,5512 "ci_low": 0.9,5513 "ci_high": 1.0,5514 "n_items": 17,5515 "n_groups": 95516 },5517 "placeholders_exact": {5518 "mean": 1.0,5519 "ci_low": 1.0,5520 "ci_high": 1.0,5521 "n_items": 17,5522 "n_groups": 95523 }5524 },5525 "data": {5526 "n": 25,5527 "chrf": {5528 "mean": 78.45031530618803,5529 "ci_low": 75.7498445780898,5530 "ci_high": 81.2855404003231,5531 "n_items": 25,5532 "n_groups": 105533 },5534 "edit_sim": {5535 "mean": 0.7365370259055176,5536 "ci_low": 0.7136160471033753,5537 "ci_high": 0.7658621574944039,5538 "n_items": 25,5539 "n_groups": 105540 },5541 "rougeL": {5542 "mean": 0.7664498431736915,5543 "ci_low": 0.7388381119448394,5544 "ci_high": 0.7938095433173276,5545 "n_items": 25,5546 "n_groups": 105547 },5548 "exact_match": {5549 "mean": 0.0,5550 "ci_low": 0.0,5551 "ci_high": 0.0,5552 "n_items": 25,5553 "n_groups": 105554 },5555 "number_recall": {5556 "mean": 0.99,5557 "ci_low": 0.9659090909090909,5558 "ci_high": 1.0,5559 "n_items": 25,5560 "n_groups": 105561 },5562 "placeholders_exact": {5563 "mean": 1.0,5564 "ci_low": 1.0,5565 "ci_high": 1.0,5566 "n_items": 25,5567 "n_groups": 105568 }5569 },5570 "discussion": {5571 "n": 34,5572 "chrf": {5573 "mean": 78.31377106202991,5574 "ci_low": 75.97027124135198,5575 "ci_high": 80.07610954896829,5576 "n_items": 34,5577 "n_groups": 145578 },5579 "edit_sim": {5580 "mean": 0.7640324702267175,5581 "ci_low": 0.7451054595461067,5582 "ci_high": 0.7836685289754926,5583 "n_items": 34,5584 "n_groups": 145585 },5586 "rougeL": {5587 "mean": 0.7739997445208048,5588 "ci_low": 0.7417783531180979,5589 "ci_high": 0.8007926673833542,5590 "n_items": 34,5591 "n_groups": 145592 },5593 "exact_match": {5594 "mean": 0.0,5595 "ci_low": 0.0,5596 "ci_high": 0.0,5597 "n_items": 34,5598 "n_groups": 145599 },5600 "number_recall": {5601 "mean": 1.0,5602 "ci_low": 1.0,5603 "ci_high": 1.0,5604 "n_items": 34,5605 "n_groups": 145606 },5607 "placeholders_exact": {5608 "mean": 1.0,5609 "ci_low": 1.0,5610 "ci_high": 1.0,5611 "n_items": 34,5612 "n_groups": 145613 }5614 },5615 "introduction": {5616 "n": 31,5617 "chrf": {5618 "mean": 76.75165889789967,5619 "ci_low": 74.74384204495531,5620 "ci_high": 78.70091064377671,5621 "n_items": 31,5622 "n_groups": 135623 },5624 "edit_sim": {5625 "mean": 0.740784754610963,5626 "ci_low": 0.7004342901311196,5627 "ci_high": 0.7739635345110699,5628 "n_items": 31,5629 "n_groups": 135630 },5631 "rougeL": {5632 "mean": 0.7531670492691469,5633 "ci_low": 0.7224226425924625,5634 "ci_high": 0.7785916629153331,5635 "n_items": 31,5636 "n_groups": 135637 },5638 "exact_match": {5639 "mean": 0.0,5640 "ci_low": 0.0,5641 "ci_high": 0.0,5642 "n_items": 31,5643 "n_groups": 135644 },5645 "number_recall": {5646 "mean": 0.992831541218638,5647 "ci_low": 0.9761904761904763,5648 "ci_high": 1.0,5649 "n_items": 31,5650 "n_groups": 135651 },5652 "placeholders_exact": {5653 "mean": 1.0,5654 "ci_low": 1.0,5655 "ci_high": 1.0,5656 "n_items": 31,5657 "n_groups": 135658 }5659 },5660 "limitations": {5661 "n": 14,5662 "chrf": {5663 "mean": 78.02869645711702,5664 "ci_low": 76.16102612772957,5665 "ci_high": 79.39403000830451,5666 "n_items": 14,5667 "n_groups": 45668 },5669 "edit_sim": {5670 "mean": 0.7841617032180912,5671 "ci_low": 0.7471498718229299,5672 "ci_high": 0.8037233823373611,5673 "n_items": 14,5674 "n_groups": 45675 },5676 "rougeL": {5677 "mean": 0.7894418698283567,5678 "ci_low": 0.7533128397097636,5679 "ci_high": 0.8076832222177265,5680 "n_items": 14,5681 "n_groups": 45682 },5683 "exact_match": {5684 "mean": 0.0,5685 "ci_low": 0.0,5686 "ci_high": 0.0,5687 "n_items": 14,5688 "n_groups": 45689 },5690 "number_recall": {5691 "mean": 1.0,5692 "ci_low": 1.0,5693 "ci_high": 1.0,5694 "n_items": 14,5695 "n_groups": 45696 },5697 "placeholders_exact": {5698 "mean": 1.0,5699 "ci_low": 1.0,5700 "ci_high": 1.0,5701 "n_items": 14,5702 "n_groups": 45703 }5704 },5705 "methods": {5706 "n": 32,5707 "chrf": {5708 "mean": 77.09081741049312,5709 "ci_low": 74.7167894242305,5710 "ci_high": 79.83422404488596,5711 "n_items": 32,5712 "n_groups": 125713 },5714 "edit_sim": {5715 "mean": 0.7656260666661026,5716 "ci_low": 0.7393229719142882,5717 "ci_high": 0.7894186093184815,5718 "n_items": 32,5719 "n_groups": 125720 },5721 "rougeL": {5722 "mean": 0.7745230661627887,5723 "ci_low": 0.7492568397406371,5724 "ci_high": 0.7991645385861421,5725 "n_items": 32,5726 "n_groups": 125727 },5728 "exact_match": {5729 "mean": 0.0,5730 "ci_low": 0.0,5731 "ci_high": 0.0,5732 "n_items": 32,5733 "n_groups": 125734 },5735 "number_recall": {5736 "mean": 0.996875,5737 "ci_low": 0.9880000000000001,5738 "ci_high": 1.0,5739 "n_items": 32,5740 "n_groups": 125741 },5742 "placeholders_exact": {5743 "mean": 1.0,5744 "ci_low": 1.0,5745 "ci_high": 1.0,5746 "n_items": 32,5747 "n_groups": 125748 }5749 },5750 "other": {5751 "n": 22,5752 "chrf": {5753 "mean": 77.14920207763129,5754 "ci_low": 72.3580596461611,5755 "ci_high": 80.60944578836325,5756 "n_items": 22,5757 "n_groups": 85758 },5759 "edit_sim": {5760 "mean": 0.7640429896727187,5761 "ci_low": 0.7242054039357451,5762 "ci_high": 0.7973592442198887,5763 "n_items": 22,5764 "n_groups": 85765 },5766 "rougeL": {5767 "mean": 0.7663458318601006,5768 "ci_low": 0.711170412996619,5769 "ci_high": 0.8086083924044055,5770 "n_items": 22,5771 "n_groups": 85772 },5773 "exact_match": {5774 "mean": 0.0,5775 "ci_low": 0.0,5776 "ci_high": 0.0,5777 "n_items": 22,5778 "n_groups": 85779 },5780 "number_recall": {5781 "mean": 1.0,5782 "ci_low": 1.0,5783 "ci_high": 1.0,5784 "n_items": 22,5785 "n_groups": 85786 },5787 "placeholders_exact": {5788 "mean": 0.9090909090909091,5789 "ci_low": 0.7391304347826086,5790 "ci_high": 1.0,5791 "n_items": 22,5792 "n_groups": 85793 }5794 },5795 "related_work": {5796 "n": 2,5797 "chrf": {5798 "mean": 80.83120932666284,5799 "ci_low": 80.83120932666284,5800 "ci_high": 80.83120932666284,5801 "n_items": 2,5802 "n_groups": 15803 },5804 "edit_sim": {5805 "mean": 0.7855991402471789,5806 "ci_low": 0.7855991402471789,5807 "ci_high": 0.7855991402471789,5808 "n_items": 2,5809 "n_groups": 15810 },5811 "rougeL": {5812 "mean": 0.7965317598825452,5813 "ci_low": 0.7965317598825452,5814 "ci_high": 0.7965317598825452,5815 "n_items": 2,5816 "n_groups": 15817 },5818 "exact_match": {5819 "mean": 0.0,5820 "ci_low": 0.0,5821 "ci_high": 0.0,5822 "n_items": 2,5823 "n_groups": 15824 },5825 "number_recall": {5826 "mean": 1.0,5827 "ci_low": 1.0,5828 "ci_high": 1.0,5829 "n_items": 2,5830 "n_groups": 15831 },5832 "placeholders_exact": {5833 "mean": 1.0,5834 "ci_low": 1.0,5835 "ci_high": 1.0,5836 "n_items": 2,5837 "n_groups": 15838 }5839 },5840 "results": {5841 "n": 26,5842 "chrf": {5843 "mean": 74.91258177732134,5844 "ci_low": 72.75555577396574,5845 "ci_high": 76.9483035429204,5846 "n_items": 26,5847 "n_groups": 105848 },5849 "edit_sim": {5850 "mean": 0.7099411278611535,5851 "ci_low": 0.6808161077996214,5852 "ci_high": 0.7413656059620509,5853 "n_items": 26,5854 "n_groups": 105855 },5856 "rougeL": {5857 "mean": 0.7452749914582062,5858 "ci_low": 0.7248061187897961,5859 "ci_high": 0.7696492955559414,5860 "n_items": 26,5861 "n_groups": 105862 },5863 "exact_match": {5864 "mean": 0.0,5865 "ci_low": 0.0,5866 "ci_high": 0.0,5867 "n_items": 26,5868 "n_groups": 105869 },5870 "number_recall": {5871 "mean": 0.9929149797570851,5872 "ci_low": 0.9736842105263157,5873 "ci_high": 1.0,5874 "n_items": 26,5875 "n_groups": 105876 },5877 "placeholders_exact": {5878 "mean": 1.0,5879 "ci_low": 1.0,5880 "ci_high": 1.0,5881 "n_items": 26,5882 "n_groups": 105883 }5884 },5885 "theory": {5886 "n": 19,5887 "chrf": {5888 "mean": 77.79419484275456,5889 "ci_low": 75.58829499077946,5890 "ci_high": 81.80166599703732,5891 "n_items": 19,5892 "n_groups": 65893 },5894 "edit_sim": {5895 "mean": 0.767313458175276,5896 "ci_low": 0.7409079624339768,5897 "ci_high": 0.8071386713831441,5898 "n_items": 19,5899 "n_groups": 65900 },5901 "rougeL": {5902 "mean": 0.7779026954424493,5903 "ci_low": 0.7544662724847861,5904 "ci_high": 0.8087953889003164,5905 "n_items": 19,5906 "n_groups": 65907 },5908 "exact_match": {5909 "mean": 0.0,5910 "ci_low": 0.0,5911 "ci_high": 0.0,5912 "n_items": 19,5913 "n_groups": 65914 },5915 "number_recall": {5916 "mean": 0.9863820390136181,5917 "ci_low": 0.9543397778691896,5918 "ci_high": 1.0,5919 "n_items": 19,5920 "n_groups": 65921 },5922 "placeholders_exact": {5923 "mean": 1.0,5924 "ci_low": 1.0,5925 "ci_high": 1.0,5926 "n_items": 19,5927 "n_groups": 65928 }5929 }5930 }5931 },5932 "htr-m3tokenonly-tiny": {5933 "overall": {5934 "n": 266,5935 "chrf": {5936 "mean": 78.20772184625075,5937 "ci_low": 77.07942407712858,5938 "ci_high": 79.48525402270614,5939 "n_items": 266,5940 "n_groups": 555941 },5942 "edit_sim": {5943 "mean": 0.7624995299438965,5944 "ci_low": 0.7510669325340873,5945 "ci_high": 0.7741730011087418,5946 "n_items": 266,5947 "n_groups": 555948 },5949 "rougeL": {5950 "mean": 0.7780823589801187,5951 "ci_low": 0.7667535856306757,5952 "ci_high": 0.7916060330090658,5953 "n_items": 266,5954 "n_groups": 555955 },5956 "exact_match": {5957 "mean": 0.0,5958 "ci_low": 0.0,5959 "ci_high": 0.0,5960 "n_items": 266,5961 "n_groups": 555962 },5963 "number_recall": {5964 "mean": 0.9901563546597185,5965 "ci_low": 0.9791645217880741,5966 "ci_high": 0.9976497368882353,5967 "n_items": 266,5968 "n_groups": 555969 },5970 "placeholders_exact": {5971 "mean": 0.9887218045112782,5972 "ci_low": 0.9741689464308436,5973 "ci_high": 1.0,5974 "n_items": 266,5975 "n_groups": 555976 }5977 },5978 "by_variant": {5979 "H1": {5980 "n": 128,5981 "chrf": {5982 "mean": 77.15895692190438,5983 "ci_low": 75.97347732151215,5984 "ci_high": 78.4465031418871,5985 "n_items": 128,5986 "n_groups": 505987 },5988 "edit_sim": {5989 "mean": 0.730480101135348,5990 "ci_low": 0.7146557845992558,5991 "ci_high": 0.7448768936887209,5992 "n_items": 128,5993 "n_groups": 505994 },5995 "rougeL": {5996 "mean": 0.754035075200844,5997 "ci_low": 0.7414288194881523,5998 "ci_high": 0.7672289750713038,5999 "n_items": 128,6000 "n_groups": 506001 },6002 "exact_match": {6003 "mean": 0.0,6004 "ci_low": 0.0,6005 "ci_high": 0.0,6006 "n_items": 128,6007 "n_groups": 506008 },6009 "number_recall": {6010 "mean": 0.988412481843814,6011 "ci_low": 0.9686386054310782,6012 "ci_high": 0.9984673418690007,6013 "n_items": 128,6014 "n_groups": 506015 },6016 "placeholders_exact": {6017 "mean": 0.984375,6018 "ci_low": 0.96,6019 "ci_high": 1.0,6020 "n_items": 128,6021 "n_groups": 506022 }6023 },6024 "H2": {6025 "n": 138,6026 "chrf": {6027 "mean": 79.18048931231114,6028 "ci_low": 77.97946289928171,6029 "ci_high": 80.5286479759278,6030 "n_items": 138,6031 "n_groups": 536032 },6033 "edit_sim": {6034 "mean": 0.7921987102880572,6035 "ci_low": 0.7800119427765888,6036 "ci_high": 0.8047244996944546,6037 "n_items": 138,6038 "n_groups": 536039 },6040 "rougeL": {6041 "mean": 0.8003870859637936,6042 "ci_low": 0.7870041328821824,6043 "ci_high": 0.815328461470322,6044 "n_items": 138,6045 "n_groups": 536046 },6047 "exact_match": {6048 "mean": 0.0,6049 "ci_low": 0.0,6050 "ci_high": 0.0,6051 "n_items": 138,6052 "n_groups": 536053 },6054 "number_recall": {6055 "mean": 0.9917738598802671,6056 "ci_low": 0.9798553709362533,6057 "ci_high": 0.9992428313902554,6058 "n_items": 138,6059 "n_groups": 536060 },6061 "placeholders_exact": {6062 "mean": 0.9927536231884058,6063 "ci_low": 0.9748414460123672,6064 "ci_high": 1.0,6065 "n_items": 138,6066 "n_groups": 536067 }6068 }6069 },6070 "by_discipline": {6071 "biomedicine": {6072 "n": 57,6073 "chrf": {6074 "mean": 78.38508369907984,6075 "ci_low": 76.4359512470774,6076 "ci_high": 80.25812733749278,6077 "n_items": 57,6078 "n_groups": 266079 },6080 "edit_sim": {6081 "mean": 0.7616464518797423,6082 "ci_low": 0.7403866811837072,6083 "ci_high": 0.7823230552850485,6084 "n_items": 57,6085 "n_groups": 266086 },6087 "rougeL": {6088 "mean": 0.7782056841192566,6089 "ci_low": 0.7589404564112523,6090 "ci_high": 0.7966098448660813,6091 "n_items": 57,6092 "n_groups": 266093 },6094 "exact_match": {6095 "mean": 0.0,6096 "ci_low": 0.0,6097 "ci_high": 0.0,6098 "n_items": 57,6099 "n_groups": 266100 },6101 "number_recall": {6102 "mean": 0.9951061865189289,6103 "ci_low": 0.9881578947368421,6104 "ci_high": 1.0,6105 "n_items": 57,6106 "n_groups": 266107 },6108 "placeholders_exact": {6109 "mean": 0.9824561403508771,6110 "ci_low": 0.9482758620689655,6111 "ci_high": 1.0,6112 "n_items": 57,6113 "n_groups": 266114 }6115 },6116 "computer_science": {6117 "n": 30,6118 "chrf": {6119 "mean": 76.18777436681785,6120 "ci_low": 74.41483942510628,6121 "ci_high": 79.73364425024103,6122 "n_items": 30,6123 "n_groups": 26124 },6125 "edit_sim": {6126 "mean": 0.7693701855621614,6127 "ci_low": 0.7632360769891692,6128 "ci_high": 0.7816384027081456,6129 "n_items": 30,6130 "n_groups": 26131 },6132 "rougeL": {6133 "mean": 0.7677440643637016,6134 "ci_low": 0.7526004575099818,6135 "ci_high": 0.7980312780711413,6136 "n_items": 30,6137 "n_groups": 26138 },6139 "exact_match": {6140 "mean": 0.0,6141 "ci_low": 0.0,6142 "ci_high": 0.0,6143 "n_items": 30,6144 "n_groups": 26145 },6146 "number_recall": {6147 "mean": 0.9988095238095238,6148 "ci_low": 0.9964285714285716,6149 "ci_high": 1.0,6150 "n_items": 30,6151 "n_groups": 26152 },6153 "placeholders_exact": {6154 "mean": 1.0,6155 "ci_low": 1.0,6156 "ci_high": 1.0,6157 "n_items": 30,6158 "n_groups": 26159 }6160 },6161 "earth_sciences": {6162 "n": 32,6163 "chrf": {6164 "mean": 75.98762044402575,6165 "ci_low": 73.26884268124996,6166 "ci_high": 77.26132275015094,6167 "n_items": 32,6168 "n_groups": 36169 },6170 "edit_sim": {6171 "mean": 0.7248910218066942,6172 "ci_low": 0.7076212742480905,6173 "ci_high": 0.7448895813774081,6174 "n_items": 32,6175 "n_groups": 36176 },6177 "rougeL": {6178 "mean": 0.7456085719632363,6179 "ci_low": 0.7269731958513745,6180 "ci_high": 0.7543682548834846,6181 "n_items": 32,6182 "n_groups": 36183 },6184 "exact_match": {6185 "mean": 0.0,6186 "ci_low": 0.0,6187 "ci_high": 0.0,6188 "n_items": 32,6189 "n_groups": 36190 },6191 "number_recall": {6192 "mean": 0.9623355263157896,6193 "ci_low": 0.8571428571428571,6194 "ci_high": 1.0,6195 "n_items": 32,6196 "n_groups": 36197 },6198 "placeholders_exact": {6199 "mean": 0.96875,6200 "ci_low": 0.9333333333333333,6201 "ci_high": 1.0,6202 "n_items": 32,6203 "n_groups": 36204 }6205 },6206 "economics": {6207 "n": 30,6208 "chrf": {6209 "mean": 77.44862531685743,6210 "ci_low": 77.44862531685743,6211 "ci_high": 77.44862531685743,6212 "n_items": 30,6213 "n_groups": 16214 },6215 "edit_sim": {6216 "mean": 0.7644897350154738,6217 "ci_low": 0.7644897350154738,6218 "ci_high": 0.7644897350154738,6219 "n_items": 30,6220 "n_groups": 16221 },6222 "rougeL": {6223 "mean": 0.7666202493231505,6224 "ci_low": 0.7666202493231505,6225 "ci_high": 0.7666202493231505,6226 "n_items": 30,6227 "n_groups": 16228 },6229 "exact_match": {6230 "mean": 0.0,6231 "ci_low": 0.0,6232 "ci_high": 0.0,6233 "n_items": 30,6234 "n_groups": 16235 },6236 "number_recall": {6237 "mean": 1.0,6238 "ci_low": 1.0,6239 "ci_high": 1.0,6240 "n_items": 30,6241 "n_groups": 16242 },6243 "placeholders_exact": {6244 "mean": 1.0,6245 "ci_low": 1.0,6246 "ci_high": 1.0,6247 "n_items": 30,6248 "n_groups": 16249 }6250 },6251 "engineering": {6252 "n": 6,6253 "chrf": {6254 "mean": 80.19011819178355,6255 "ci_low": 80.19011819178355,6256 "ci_high": 80.19011819178355,6257 "n_items": 6,6258 "n_groups": 16259 },6260 "edit_sim": {6261 "mean": 0.7667715761262928,6262 "ci_low": 0.7667715761262928,6263 "ci_high": 0.7667715761262928,6264 "n_items": 6,6265 "n_groups": 16266 },6267 "rougeL": {6268 "mean": 0.7686950108265599,6269 "ci_low": 0.7686950108265599,6270 "ci_high": 0.7686950108265599,6271 "n_items": 6,6272 "n_groups": 16273 },6274 "exact_match": {6275 "mean": 0.0,6276 "ci_low": 0.0,6277 "ci_high": 0.0,6278 "n_items": 6,6279 "n_groups": 16280 },6281 "number_recall": {6282 "mean": 1.0,6283 "ci_low": 1.0,6284 "ci_high": 1.0,6285 "n_items": 6,6286 "n_groups": 16287 },6288 "placeholders_exact": {6289 "mean": 1.0,6290 "ci_low": 1.0,6291 "ci_high": 1.0,6292 "n_items": 6,6293 "n_groups": 16294 }6295 },6296 "life_sciences": {6297 "n": 49,6298 "chrf": {6299 "mean": 79.63143172843891,6300 "ci_low": 77.72649421790368,6301 "ci_high": 81.85070319213003,6302 "n_items": 49,6303 "n_groups": 166304 },6305 "edit_sim": {6306 "mean": 0.7781938164614555,6307 "ci_low": 0.7569505903994709,6308 "ci_high": 0.8023153036698417,6309 "n_items": 49,6310 "n_groups": 166311 },6312 "rougeL": {6313 "mean": 0.8007052676143037,6314 "ci_low": 0.7797466178853653,6315 "ci_high": 0.8239317595281571,6316 "n_items": 49,6317 "n_groups": 166318 },6319 "exact_match": {6320 "mean": 0.0,6321 "ci_low": 0.0,6322 "ci_high": 0.0,6323 "n_items": 49,6324 "n_groups": 166325 },6326 "number_recall": {6327 "mean": 0.9911873840445269,6328 "ci_low": 0.9788574500288296,6329 "ci_high": 1.0,6330 "n_items": 49,6331 "n_groups": 166332 },6333 "placeholders_exact": {6334 "mean": 0.9795918367346939,6335 "ci_low": 0.9374667553191489,6336 "ci_high": 1.0,6337 "n_items": 49,6338 "n_groups": 166339 }6340 },6341 "social_sciences": {6342 "n": 38,6343 "chrf": {6344 "mean": 80.97841668356739,6345 "ci_low": 74.49423802007907,6346 "ci_high": 83.43261873645817,6347 "n_items": 38,6348 "n_groups": 46349 },6350 "edit_sim": {6351 "mean": 0.7915245266836717,6352 "ci_low": 0.755445556709388,6353 "ci_high": 0.8127659626285357,6354 "n_items": 38,6355 "n_groups": 46356 },6357 "rougeL": {6358 "mean": 0.810062165433057,6359 "ci_low": 0.7390643906898066,6360 "ci_high": 0.8330462910353025,6361 "n_items": 38,6362 "n_groups": 46363 },6364 "exact_match": {6365 "mean": 0.0,6366 "ci_low": 0.0,6367 "ci_high": 0.0,6368 "n_items": 38,6369 "n_groups": 46370 },6371 "number_recall": {6372 "mean": 0.982456140350877,6373 "ci_low": 0.9259259259259258,6374 "ci_high": 1.0,6375 "n_items": 38,6376 "n_groups": 46377 },6378 "placeholders_exact": {6379 "mean": 1.0,6380 "ci_low": 1.0,6381 "ci_high": 1.0,6382 "n_items": 38,6383 "n_groups": 46384 }6385 },6386 "statistics": {6387 "n": 24,6388 "chrf": {6389 "mean": 76.43115407151221,6390 "ci_low": 75.7995573679924,6391 "ci_high": 76.7469524232721,6392 "n_items": 24,6393 "n_groups": 26394 },6395 "edit_sim": {6396 "mean": 0.7245274339766358,6397 "ci_low": 0.695716960461917,6398 "ci_high": 0.7389326707339952,6399 "n_items": 24,6400 "n_groups": 26401 },6402 "rougeL": {6403 "mean": 0.753862054832017,6404 "ci_low": 0.7435793912120158,6405 "ci_high": 0.7590033866420174,6406 "n_items": 24,6407 "n_groups": 26408 },6409 "exact_match": {6410 "mean": 0.0,6411 "ci_low": 0.0,6412 "ci_high": 0.0,6413 "n_items": 24,6414 "n_groups": 26415 },6416 "number_recall": {6417 "mean": 1.0,6418 "ci_low": 1.0,6419 "ci_high": 1.0,6420 "n_items": 24,6421 "n_groups": 26422 },6423 "placeholders_exact": {6424 "mean": 1.0,6425 "ci_low": 1.0,6426 "ci_high": 1.0,6427 "n_items": 24,6428 "n_groups": 26429 }6430 }6431 },6432 "by_era": {6433 "1980-1999": {6434 "n": 2,6435 "chrf": {6436 "mean": 78.20252020513925,6437 "ci_low": 77.74151345338821,6438 "ci_high": 78.66352695689028,6439 "n_items": 2,6440 "n_groups": 26441 },6442 "edit_sim": {6443 "mean": 0.791195907911959,6444 "ci_low": 0.7502750275027503,6445 "ci_high": 0.8321167883211679,6446 "n_items": 2,6447 "n_groups": 26448 },6449 "rougeL": {6450 "mean": 0.7993567797489367,6451 "ci_low": 0.7583774250440918,6452 "ci_high": 0.8403361344537815,6453 "n_items": 2,6454 "n_groups": 26455 },6456 "exact_match": {6457 "mean": 0.0,6458 "ci_low": 0.0,6459 "ci_high": 0.0,6460 "n_items": 2,6461 "n_groups": 26462 },6463 "number_recall": {6464 "mean": 1.0,6465 "ci_low": 1.0,6466 "ci_high": 1.0,6467 "n_items": 2,6468 "n_groups": 26469 },6470 "placeholders_exact": {6471 "mean": 1.0,6472 "ci_low": 1.0,6473 "ci_high": 1.0,6474 "n_items": 2,6475 "n_groups": 26476 }6477 },6478 "2000-2009": {6479 "n": 30,6480 "chrf": {6481 "mean": 79.00726946166425,6482 "ci_low": 76.84455052463758,6483 "ci_high": 82.46515414182633,6484 "n_items": 30,6485 "n_groups": 76486 },6487 "edit_sim": {6488 "mean": 0.7632919276423945,6489 "ci_low": 0.7280620266276404,6490 "ci_high": 0.815416165477945,6491 "n_items": 30,6492 "n_groups": 76493 },6494 "rougeL": {6495 "mean": 0.7834852348516892,6496 "ci_low": 0.7578867842140653,6497 "ci_high": 0.8292860993675693,6498 "n_items": 30,6499 "n_groups": 76500 },6501 "exact_match": {6502 "mean": 0.0,6503 "ci_low": 0.0,6504 "ci_high": 0.0,6505 "n_items": 30,6506 "n_groups": 76507 },6508 "number_recall": {6509 "mean": 1.0,6510 "ci_low": 1.0,6511 "ci_high": 1.0,6512 "n_items": 30,6513 "n_groups": 76514 },6515 "placeholders_exact": {6516 "mean": 1.0,6517 "ci_low": 1.0,6518 "ci_high": 1.0,6519 "n_items": 30,6520 "n_groups": 76521 }6522 },6523 "2010-2017": {6524 "n": 234,6525 "chrf": {6526 "mean": 78.10526020018158,6527 "ci_low": 76.83510673950866,6528 "ci_high": 79.56173346700605,6529 "n_items": 234,6530 "n_groups": 466531 },6532 "edit_sim": {6533 "mean": 0.7621526723076099,6534 "ci_low": 0.749980363547748,6535 "ci_high": 0.7745049456719371,6536 "n_items": 234,6537 "n_groups": 466538 },6539 "rougeL": {6540 "mean": 0.7772078499301839,6541 "ci_low": 0.7643311815870039,6542 "ci_high": 0.7922381741934788,6543 "n_items": 234,6544 "n_groups": 466545 },6546 "exact_match": {6547 "mean": 0.0,6548 "ci_low": 0.0,6549 "ci_high": 0.0,6550 "n_items": 234,6551 "n_groups": 466552 },6553 "number_recall": {6554 "mean": 0.9888102151260046,6555 "ci_low": 0.9760278790123414,6556 "ci_high": 0.9973161723301288,6557 "n_items": 234,6558 "n_groups": 466559 },6560 "placeholders_exact": {6561 "mean": 0.9871794871794872,6562 "ci_low": 0.9702970297029703,6563 "ci_high": 1.0,6564 "n_items": 234,6565 "n_groups": 466566 }6567 }6568 },6569 "by_role": {6570 "abstract": {6571 "n": 28,6572 "chrf": {6573 "mean": 81.9748578301765,6574 "ci_low": 79.75656795770658,6575 "ci_high": 84.411677597848,6576 "n_items": 28,6577 "n_groups": 156578 },6579 "edit_sim": {6580 "mean": 0.8027425415612974,6581 "ci_low": 0.7674683850888584,6582 "ci_high": 0.8417038909793619,6583 "n_items": 28,6584 "n_groups": 156585 },6586 "rougeL": {6587 "mean": 0.8120500575322919,6588 "ci_low": 0.779938078968308,6589 "ci_high": 0.8485572120542878,6590 "n_items": 28,6591 "n_groups": 156592 },6593 "exact_match": {6594 "mean": 0.0,6595 "ci_low": 0.0,6596 "ci_high": 0.0,6597 "n_items": 28,6598 "n_groups": 156599 },6600 "number_recall": {6601 "mean": 1.0,6602 "ci_low": 1.0,6603 "ci_high": 1.0,6604 "n_items": 28,6605 "n_groups": 156606 },6607 "placeholders_exact": {6608 "mean": 1.0,6609 "ci_low": 1.0,6610 "ci_high": 1.0,6611 "n_items": 28,6612 "n_groups": 156613 }6614 },6615 "background": {6616 "n": 16,6617 "chrf": {6618 "mean": 79.50164614740693,6619 "ci_low": 73.03627879426479,6620 "ci_high": 85.03063606133685,6621 "n_items": 16,6622 "n_groups": 76623 },6624 "edit_sim": {6625 "mean": 0.7747468522874117,6626 "ci_low": 0.7097756135280301,6627 "ci_high": 0.8276466692120424,6628 "n_items": 16,6629 "n_groups": 76630 },6631 "rougeL": {6632 "mean": 0.798494620844939,6633 "ci_low": 0.7351679433881229,6634 "ci_high": 0.8477376292888947,6635 "n_items": 16,6636 "n_groups": 76637 },6638 "exact_match": {6639 "mean": 0.0,6640 "ci_low": 0.0,6641 "ci_high": 0.0,6642 "n_items": 16,6643 "n_groups": 76644 },6645 "number_recall": {6646 "mean": 1.0,6647 "ci_low": 1.0,6648 "ci_high": 1.0,6649 "n_items": 16,6650 "n_groups": 76651 },6652 "placeholders_exact": {6653 "mean": 0.9375,6654 "ci_low": 0.8125,6655 "ci_high": 1.0,6656 "n_items": 16,6657 "n_groups": 76658 }6659 },6660 "conclusion": {6661 "n": 17,6662 "chrf": {6663 "mean": 77.9238294158188,6664 "ci_low": 74.40057507136814,6665 "ci_high": 81.2628770939843,6666 "n_items": 17,6667 "n_groups": 96668 },6669 "edit_sim": {6670 "mean": 0.754928412370503,6671 "ci_low": 0.7193549495713212,6672 "ci_high": 0.7844326416503561,6673 "n_items": 17,6674 "n_groups": 96675 },6676 "rougeL": {6677 "mean": 0.7676439067561087,6678 "ci_low": 0.7353860769710796,6679 "ci_high": 0.7971262249039532,6680 "n_items": 17,6681 "n_groups": 96682 },6683 "exact_match": {6684 "mean": 0.0,6685 "ci_low": 0.0,6686 "ci_high": 0.0,6687 "n_items": 17,6688 "n_groups": 96689 },6690 "number_recall": {6691 "mean": 1.0,6692 "ci_low": 1.0,6693 "ci_high": 1.0,6694 "n_items": 17,6695 "n_groups": 96696 },6697 "placeholders_exact": {6698 "mean": 1.0,6699 "ci_low": 1.0,6700 "ci_high": 1.0,6701 "n_items": 17,6702 "n_groups": 96703 }6704 },6705 "data": {6706 "n": 25,6707 "chrf": {6708 "mean": 78.4258889801437,6709 "ci_low": 74.95646347891929,6710 "ci_high": 81.68389257952634,6711 "n_items": 25,6712 "n_groups": 106713 },6714 "edit_sim": {6715 "mean": 0.7354610503443477,6716 "ci_low": 0.7107153210584216,6717 "ci_high": 0.7646091551796934,6718 "n_items": 25,6719 "n_groups": 106720 },6721 "rougeL": {6722 "mean": 0.76867569909095,6723 "ci_low": 0.7345131708806789,6724 "ci_high": 0.801730947847885,6725 "n_items": 25,6726 "n_groups": 106727 },6728 "exact_match": {6729 "mean": 0.0,6730 "ci_low": 0.0,6731 "ci_high": 0.0,6732 "n_items": 25,6733 "n_groups": 106734 },6735 "number_recall": {6736 "mean": 0.9777894736842105,6737 "ci_low": 0.9475972540045766,6738 "ci_high": 1.0,6739 "n_items": 25,6740 "n_groups": 106741 },6742 "placeholders_exact": {6743 "mean": 0.96,6744 "ci_low": 0.8636363636363636,6745 "ci_high": 1.0,6746 "n_items": 25,6747 "n_groups": 106748 }6749 },6750 "discussion": {6751 "n": 34,6752 "chrf": {6753 "mean": 77.7142431797297,6754 "ci_low": 75.47961996705713,6755 "ci_high": 79.68407603591088,6756 "n_items": 34,6757 "n_groups": 146758 },6759 "edit_sim": {6760 "mean": 0.7571746977657434,6761 "ci_low": 0.7364861841419501,6762 "ci_high": 0.7782112129516079,6763 "n_items": 34,6764 "n_groups": 146765 },6766 "rougeL": {6767 "mean": 0.7685827198236632,6768 "ci_low": 0.7350916921809213,6769 "ci_high": 0.7976133449712076,6770 "n_items": 34,6771 "n_groups": 146772 },6773 "exact_match": {6774 "mean": 0.0,6775 "ci_low": 0.0,6776 "ci_high": 0.0,6777 "n_items": 34,6778 "n_groups": 146779 },6780 "number_recall": {6781 "mean": 0.980392156862745,6782 "ci_low": 0.9393939393939394,6783 "ci_high": 1.0,6784 "n_items": 34,6785 "n_groups": 146786 },6787 "placeholders_exact": {6788 "mean": 1.0,6789 "ci_low": 1.0,6790 "ci_high": 1.0,6791 "n_items": 34,6792 "n_groups": 146793 }6794 },6795 "introduction": {6796 "n": 31,6797 "chrf": {6798 "mean": 76.91503781639875,6799 "ci_low": 74.97034470965005,6800 "ci_high": 78.82568103864675,6801 "n_items": 31,6802 "n_groups": 136803 },6804 "edit_sim": {6805 "mean": 0.7430750422833537,6806 "ci_low": 0.7016090633596672,6807 "ci_high": 0.779155858573269,6808 "n_items": 31,6809 "n_groups": 136810 },6811 "rougeL": {6812 "mean": 0.7530533122673323,6813 "ci_low": 0.721139172267973,6814 "ci_high": 0.7806763086557978,6815 "n_items": 31,6816 "n_groups": 136817 },6818 "exact_match": {6819 "mean": 0.0,6820 "ci_low": 0.0,6821 "ci_high": 0.0,6822 "n_items": 31,6823 "n_groups": 136824 },6825 "number_recall": {6826 "mean": 1.0,6827 "ci_low": 1.0,6828 "ci_high": 1.0,6829 "n_items": 31,6830 "n_groups": 136831 },6832 "placeholders_exact": {6833 "mean": 1.0,6834 "ci_low": 1.0,6835 "ci_high": 1.0,6836 "n_items": 31,6837 "n_groups": 136838 }6839 },6840 "limitations": {6841 "n": 14,6842 "chrf": {6843 "mean": 78.46426559680337,6844 "ci_low": 76.20063344323957,6845 "ci_high": 80.00699825977361,6846 "n_items": 14,6847 "n_groups": 46848 },6849 "edit_sim": {6850 "mean": 0.785973450763908,6851 "ci_low": 0.7435618039948058,6852 "ci_high": 0.8060569988469146,6853 "n_items": 14,6854 "n_groups": 46855 },6856 "rougeL": {6857 "mean": 0.7940366216738959,6858 "ci_low": 0.7495420019426785,6859 "ci_high": 0.8163077986574058,6860 "n_items": 14,6861 "n_groups": 46862 },6863 "exact_match": {6864 "mean": 0.0,6865 "ci_low": 0.0,6866 "ci_high": 0.0,6867 "n_items": 14,6868 "n_groups": 46869 },6870 "number_recall": {6871 "mean": 1.0,6872 "ci_low": 1.0,6873 "ci_high": 1.0,6874 "n_items": 14,6875 "n_groups": 46876 },6877 "placeholders_exact": {6878 "mean": 1.0,6879 "ci_low": 1.0,6880 "ci_high": 1.0,6881 "n_items": 14,6882 "n_groups": 46883 }6884 },6885 "methods": {6886 "n": 32,6887 "chrf": {6888 "mean": 78.39817672300512,6889 "ci_low": 75.95604795576496,6890 "ci_high": 81.01636956741382,6891 "n_items": 32,6892 "n_groups": 126893 },6894 "edit_sim": {6895 "mean": 0.7781938834427704,6896 "ci_low": 0.7567522185252176,6897 "ci_high": 0.7979844458478046,6898 "n_items": 32,6899 "n_groups": 126900 },6901 "rougeL": {6902 "mean": 0.7929917346097934,6903 "ci_low": 0.774759764112927,6904 "ci_high": 0.8136072829931067,6905 "n_items": 32,6906 "n_groups": 126907 },6908 "exact_match": {6909 "mean": 0.0,6910 "ci_low": 0.0,6911 "ci_high": 0.0,6912 "n_items": 32,6913 "n_groups": 126914 },6915 "number_recall": {6916 "mean": 0.996875,6917 "ci_low": 0.9880000000000001,6918 "ci_high": 1.0,6919 "n_items": 32,6920 "n_groups": 126921 },6922 "placeholders_exact": {6923 "mean": 1.0,6924 "ci_low": 1.0,6925 "ci_high": 1.0,6926 "n_items": 32,6927 "n_groups": 126928 }6929 },6930 "other": {6931 "n": 22,6932 "chrf": {6933 "mean": 77.95923490391293,6934 "ci_low": 72.85120517714782,6935 "ci_high": 81.87299952845024,6936 "n_items": 22,6937 "n_groups": 86938 },6939 "edit_sim": {6940 "mean": 0.7754122639884184,6941 "ci_low": 0.7301497603984957,6942 "ci_high": 0.8139309704072896,6943 "n_items": 22,6944 "n_groups": 86945 },6946 "rougeL": {6947 "mean": 0.7772134667514412,6948 "ci_low": 0.7218816146023659,6949 "ci_high": 0.8212982380213001,6950 "n_items": 22,6951 "n_groups": 86952 },6953 "exact_match": {6954 "mean": 0.0,6955 "ci_low": 0.0,6956 "ci_high": 0.0,6957 "n_items": 22,6958 "n_groups": 86959 },6960 "number_recall": {6961 "mean": 0.9545454545454546,6962 "ci_low": 0.8571428571428571,6963 "ci_high": 1.0,6964 "n_items": 22,6965 "n_groups": 86966 },6967 "placeholders_exact": {6968 "mean": 0.9545454545454546,6969 "ci_low": 0.8695652173913043,6970 "ci_high": 1.0,6971 "n_items": 22,6972 "n_groups": 86973 }6974 },6975 "related_work": {6976 "n": 2,6977 "chrf": {6978 "mean": 82.10739373370156,6979 "ci_low": 82.10739373370156,6980 "ci_high": 82.10739373370156,6981 "n_items": 2,6982 "n_groups": 16983 },6984 "edit_sim": {6985 "mean": 0.7964142985740474,6986 "ci_low": 0.7964142985740474,6987 "ci_high": 0.7964142985740474,6988 "n_items": 2,6989 "n_groups": 16990 },6991 "rougeL": {6992 "mean": 0.8114273380407635,6993 "ci_low": 0.8114273380407635,6994 "ci_high": 0.8114273380407635,6995 "n_items": 2,6996 "n_groups": 16997 },6998 "exact_match": {6999 "mean": 0.0,7000 "ci_low": 0.0,7001 "ci_high": 0.0,7002 "n_items": 2,7003 "n_groups": 17004 },7005 "number_recall": {7006 "mean": 1.0,7007 "ci_low": 1.0,7008 "ci_high": 1.0,7009 "n_items": 2,7010 "n_groups": 17011 },7012 "placeholders_exact": {7013 "mean": 1.0,7014 "ci_low": 1.0,7015 "ci_high": 1.0,7016 "n_items": 2,7017 "n_groups": 17018 }7019 },7020 "results": {7021 "n": 26,7022 "chrf": {7023 "mean": 74.8132300886417,7024 "ci_low": 72.52123467884053,7025 "ci_high": 77.09174866776662,7026 "n_items": 26,7027 "n_groups": 107028 },7029 "edit_sim": {7030 "mean": 0.7193812551599503,7031 "ci_low": 0.6934869691550787,7032 "ci_high": 0.7492190266558467,7033 "n_items": 26,7034 "n_groups": 107035 },7036 "rougeL": {7037 "mean": 0.7530223535124213,7038 "ci_low": 0.734526283727928,7039 "ci_high": 0.7756670249796163,7040 "n_items": 26,7041 "n_groups": 107042 },7043 "exact_match": {7044 "mean": 0.0,7045 "ci_low": 0.0,7046 "ci_high": 0.0,7047 "n_items": 26,7048 "n_groups": 107049 },7050 "number_recall": {7051 "mean": 0.9955899363794101,7052 "ci_low": 0.9870211242391694,7053 "ci_high": 1.0,7054 "n_items": 26,7055 "n_groups": 107056 },7057 "placeholders_exact": {7058 "mean": 1.0,7059 "ci_low": 1.0,7060 "ci_high": 1.0,7061 "n_items": 26,7062 "n_groups": 107063 }7064 },7065 "theory": {7066 "n": 19,7067 "chrf": {7068 "mean": 78.5381882819988,7069 "ci_low": 75.86510555403827,7070 "ci_high": 81.70930508383618,7071 "n_items": 19,7072 "n_groups": 67073 },7074 "edit_sim": {7075 "mean": 0.7732060653220884,7076 "ci_low": 0.7452256012963445,7077 "ci_high": 0.8051786716632011,7078 "n_items": 19,7079 "n_groups": 67080 },7081 "rougeL": {7082 "mean": 0.7853109237360424,7083 "ci_low": 0.7574862416870752,7084 "ci_high": 0.8145983367237599,7085 "n_items": 19,7086 "n_groups": 67087 },7088 "exact_match": {7089 "mean": 0.0,7090 "ci_low": 0.0,7091 "ci_high": 0.0,7092 "n_items": 19,7093 "n_groups": 67094 },7095 "number_recall": {7096 "mean": 0.9904306220095694,7097 "ci_low": 0.9679144385026737,7098 "ci_high": 1.0,7099 "n_items": 19,7100 "n_groups": 67101 },7102 "placeholders_exact": {7103 "mean": 1.0,7104 "ci_low": 1.0,7105 "ci_high": 1.0,7106 "n_items": 19,7107 "n_groups": 67108 }7109 }7110 }7111 }7112 },7113 "paired_vs_baseline": {7114 "B1_generic_paraphrase": {7115 "chrf": {7116 "mean": -4.5013949737260095,7117 "ci_low": -4.996827460422494,7118 "ci_high": -4.013435519701374,7119 "n_items": 266,7120 "n_groups": 55,7121 "p_value_two_sided": 0.0,7122 "p_holm": 0.0,7123 "significant_holm_0_05": true7124 },7125 "edit_sim": {7126 "mean": -0.12383939086113854,7127 "ci_low": -0.13439545819599694,7128 "ci_high": -0.11214217802247013,7129 "n_items": 266,7130 "n_groups": 55,7131 "p_value_two_sided": 0.0,7132 "p_holm": 0.0,7133 "significant_holm_0_05": true7134 },7135 "rougeL": {7136 "mean": -0.09483516114940423,7137 "ci_low": -0.10266567769739524,7138 "ci_high": -0.08667428112753275,7139 "n_items": 266,7140 "n_groups": 55,7141 "p_value_two_sided": 0.0,7142 "p_holm": 0.0,7143 "significant_holm_0_05": true7144 },7145 "exact_match": {7146 "mean": 0.0,7147 "ci_low": 0.0,7148 "ci_high": 0.0,7149 "n_items": 266,7150 "n_groups": 55,7151 "p_value_two_sided": 0.0,7152 "p_holm": 0.0,7153 "significant_holm_0_05": true7154 },7155 "number_recall": {7156 "mean": -0.0018796992481203006,7157 "ci_low": -0.00530035335689046,7158 "ci_high": 0.0,7159 "n_items": 266,7160 "n_groups": 55,7161 "p_value_two_sided": 0.0,7162 "p_holm": 0.0,7163 "significant_holm_0_05": true7164 },7165 "placeholders_exact": {7166 "mean": 0.0,7167 "ci_low": 0.0,7168 "ci_high": 0.0,7169 "n_items": 266,7170 "n_groups": 55,7171 "p_value_two_sided": 0.0,7172 "p_holm": 0.0,7173 "significant_holm_0_05": true7174 }7175 },7176 "htr-m1-small": {7177 "chrf": {7178 "mean": -2.529951094272078,7179 "ci_low": -3.0681791002567422,7180 "ci_high": -2.006876875783361,7181 "n_items": 266,7182 "n_groups": 55,7183 "p_value_two_sided": 0.0,7184 "p_holm": 0.0,7185 "significant_holm_0_05": true7186 },7187 "edit_sim": {7188 "mean": -0.027398507456499615,7189 "ci_low": -0.03429942771978724,7190 "ci_high": -0.020501809667541126,7191 "n_items": 266,7192 "n_groups": 55,7193 "p_value_two_sided": 0.0,7194 "p_holm": 0.0,7195 "significant_holm_0_05": true7196 },7197 "rougeL": {7198 "mean": -0.031486279603623775,7199 "ci_low": -0.03765800004233175,7200 "ci_high": -0.025506708186048513,7201 "n_items": 266,7202 "n_groups": 55,7203 "p_value_two_sided": 0.0,7204 "p_holm": 0.0,7205 "significant_holm_0_05": true7206 },7207 "exact_match": {7208 "mean": 0.0,7209 "ci_low": 0.0,7210 "ci_high": 0.0,7211 "n_items": 266,7212 "n_groups": 55,7213 "p_value_two_sided": 0.0,7214 "p_holm": 0.0,7215 "significant_holm_0_05": true7216 },7217 "number_recall": {7218 "mean": -0.007712931881906951,7219 "ci_low": -0.015975867479400815,7220 "ci_high": -0.0021373087312841527,7221 "n_items": 266,7222 "n_groups": 55,7223 "p_value_two_sided": 0.0,7224 "p_holm": 0.0,7225 "significant_holm_0_05": true7226 },7227 "placeholders_exact": {7228 "mean": 0.0,7229 "ci_low": 0.0,7230 "ci_high": 0.0,7231 "n_items": 266,7232 "n_groups": 55,7233 "p_value_two_sided": 0.0,7234 "p_holm": 0.0,7235 "significant_holm_0_05": true7236 }7237 },7238 "htr-m1-tiny-s3": {7239 "chrf": {7240 "mean": -2.382224335944388,7241 "ci_low": -2.9318300785269207,7242 "ci_high": -1.9165096992026147,7243 "n_items": 266,7244 "n_groups": 55,7245 "p_value_two_sided": 0.0,7246 "p_holm": 0.0,7247 "significant_holm_0_05": true7248 },7249 "edit_sim": {7250 "mean": -0.024587835585231334,7251 "ci_low": -0.030327831611370572,7252 "ci_high": -0.018645474030694137,7253 "n_items": 266,7254 "n_groups": 55,7255 "p_value_two_sided": 0.0,7256 "p_holm": 0.0,7257 "significant_holm_0_05": true7258 },7259 "rougeL": {7260 "mean": -0.029181373247192034,7261 "ci_low": -0.03615285634476727,7262 "ci_high": -0.023316574895902154,7263 "n_items": 266,7264 "n_groups": 55,7265 "p_value_two_sided": 0.0,7266 "p_holm": 0.0,7267 "significant_holm_0_05": true7268 },7269 "exact_match": {7270 "mean": 0.0,7271 "ci_low": 0.0,7272 "ci_high": 0.0,7273 "n_items": 266,7274 "n_groups": 55,7275 "p_value_two_sided": 0.0,7276 "p_holm": 0.0,7277 "significant_holm_0_05": true7278 },7279 "number_recall": {7280 "mean": -0.0017654925648594036,7281 "ci_low": -0.003960399017406527,7282 "ci_high": -0.0003466987611141267,7283 "n_items": 266,7284 "n_groups": 55,7285 "p_value_two_sided": 0.0,7286 "p_holm": 0.0,7287 "significant_holm_0_05": true7288 },7289 "placeholders_exact": {7290 "mean": -0.007518796992481203,7291 "ci_low": -0.02727272727272727,7292 "ci_high": 0.0,7293 "n_items": 266,7294 "n_groups": 55,7295 "p_value_two_sided": 0.0,7296 "p_holm": 0.0,7297 "significant_holm_0_05": true7298 }7299 },7300 "htr-m1-tiny": {7301 "chrf": {7302 "mean": -2.416644318004276,7303 "ci_low": -2.957070945974038,7304 "ci_high": -1.9663985091579659,7305 "n_items": 266,7306 "n_groups": 55,7307 "p_value_two_sided": 0.0,7308 "p_holm": 0.0,7309 "significant_holm_0_05": true7310 },7311 "edit_sim": {7312 "mean": -0.025014524014290607,7313 "ci_low": -0.030435594439243378,7314 "ci_high": -0.019521081490123403,7315 "n_items": 266,7316 "n_groups": 55,7317 "p_value_two_sided": 0.0,7318 "p_holm": 0.0,7319 "significant_holm_0_05": true7320 },7321 "rougeL": {7322 "mean": -0.029421947866203915,7323 "ci_low": -0.03575962576023468,7324 "ci_high": -0.024294817998437454,7325 "n_items": 266,7326 "n_groups": 55,7327 "p_value_two_sided": 0.0,7328 "p_holm": 0.0,7329 "significant_holm_0_05": true7330 },7331 "exact_match": {7332 "mean": 0.0,7333 "ci_low": 0.0,7334 "ci_high": 0.0,7335 "n_items": 266,7336 "n_groups": 55,7337 "p_value_two_sided": 0.0,7338 "p_holm": 0.0,7339 "significant_holm_0_05": true7340 },7341 "number_recall": {7342 "mean": -0.005904998356521903,7343 "ci_low": -0.012799905242067972,7344 "ci_high": -0.0015610249222689425,7345 "n_items": 266,7346 "n_groups": 55,7347 "p_value_two_sided": 0.0,7348 "p_holm": 0.0,7349 "significant_holm_0_05": true7350 },7351 "placeholders_exact": {7352 "mean": -0.011278195488721804,7353 "ci_low": -0.03167420814479638,7354 "ci_high": 0.0,7355 "n_items": 266,7356 "n_groups": 55,7357 "p_value_two_sided": 0.0,7358 "p_holm": 0.0,7359 "significant_holm_0_05": true7360 }7361 },7362 "htr-m3tokenonly-tiny": {7363 "chrf": {7364 "mean": -2.110322549682802,7365 "ci_low": -2.716435335401481,7366 "ci_high": -1.6385450163749125,7367 "n_items": 266,7368 "n_groups": 55,7369 "p_value_two_sided": 0.0,7370 "p_holm": 0.0,7371 "significant_holm_0_05": true7372 },7373 "edit_sim": {7374 "mean": -0.02113820728379573,7375 "ci_low": -0.025700903271292902,7376 "ci_high": -0.01645368069905364,7377 "n_items": 266,7378 "n_groups": 55,7379 "p_value_two_sided": 0.0,7380 "p_holm": 0.0,7381 "significant_holm_0_05": true7382 },7383 "rougeL": {7384 "mean": -0.024470045655036125,7385 "ci_low": -0.03080604436761355,7386 "ci_high": -0.019272404297875537,7387 "n_items": 266,7388 "n_groups": 55,7389 "p_value_two_sided": 0.0,7390 "p_holm": 0.0,7391 "significant_holm_0_05": true7392 },7393 "exact_match": {7394 "mean": 0.0,7395 "ci_low": 0.0,7396 "ci_high": 0.0,7397 "n_items": 266,7398 "n_groups": 55,7399 "p_value_two_sided": 0.0,7400 "p_holm": 0.0,7401 "significant_holm_0_05": true7402 },7403 "number_recall": {7404 "mean": -0.009843645340281669,7405 "ci_low": -0.020835478211925742,7406 "ci_high": -0.0023502631117646882,7407 "n_items": 266,7408 "n_groups": 55,7409 "p_value_two_sided": 0.0,7410 "p_holm": 0.0,7411 "significant_holm_0_05": true7412 },7413 "placeholders_exact": {7414 "mean": -0.011278195488721804,7415 "ci_low": -0.02583105356915638,7416 "ci_high": 0.0,7417 "n_items": 266,7418 "n_groups": 55,7419 "p_value_two_sided": 0.0,7420 "p_holm": 0.0,7421 "significant_holm_0_05": true7422 }7423 }7424 },7425 "stylometry": {7426 "rewrite_vs_original": {7427 "W1_mean_sent_len": 0.6941610112829211,7428 "W1_sd_sent_len": 0.4226860781487078,7429 "W1_ttr": 0.26359475679320193,7430 "W1_mtld": 0.327148878456198,7431 "W1_mean_word_len": 0.1995211888325041,7432 "W1_long_word_rate": 0.06689144680772958,7433 "W1_comma_rate": 0.14344364362727552,7434 "W1_semicolon_rate": 0.053999181008536144,7435 "W1_paren_rate": 0.03550883492135679,7436 "W1_discourse_rate": 0.0814483055978516,7437 "W1_passive_rate": 0.4034286071396181,7438 "W1_nominal_rate": 0.09491443881949037,7439 "W1_first_person_rate": 0.031580344732597763,7440 "W1_subord_rate": 0.11627477810151862,7441 "W1_hedge_rate": 0.1002823007199489,7442 "W1_negation_rate": 0.06758703931706646,7443 "W1_digit_rate": 0.02921509558705879,7444 "W1_flesch": 0.2794896686537671,7445 "W1_mean": 0.189509755474852717446 },7447 "feature_means": {7448 "original": {7449 "mean_sent_len": 25.763494035204562,7450 "sd_sent_len": 8.593922121267807,7451 "ttr": 0.6346011226299271,7452 "mtld": 73.4060804373873,7453 "mean_word_len": 5.583882931276622,7454 "long_word_rate": 0.12672923411155548,7455 "comma_rate": 0.049056681424854025,7456 "semicolon_rate": 0.002064010637397045,7457 "paren_rate": 0.016483552466246974,7458 "discourse_rate": 0.010895743586077661,7459 "passive_rate": 0.4373657149033087,7460 "nominal_rate": 0.06637127737240098,7461 "first_person_rate": 0.002681863232537511,7462 "subord_rate": 0.02593423503541845,7463 "hedge_rate": 0.007460546357769086,7464 "negation_rate": 0.005367175669786099,7465 "digit_rate": 0.009286034399433363,7466 "flesch": 16.541407712945177467 },7468 "rewrite": {7469 "mean_sent_len": 20.597123637112002,7470 "sd_sent_len": 6.8521933053078445,7471 "ttr": 0.6608422832474243,7472 "mtld": 81.90482180763928,7473 "mean_word_len": 5.667746247948301,7474 "long_word_rate": 0.12671141886437254,7475 "comma_rate": 0.053043535063464285,7476 "semicolon_rate": 0.0018590833482987714,7477 "paren_rate": 0.016231004674493565,7478 "discourse_rate": 0.010495459915617535,7479 "passive_rate": 0.30711378081472895,7480 "nominal_rate": 0.0637939140567542,7481 "first_person_rate": 0.002870498114420158,7482 "subord_rate": 0.024159766846723458,7483 "hedge_rate": 0.00835860697288513,7484 "negation_rate": 0.0059095566977552345,7485 "digit_rate": 0.00968287636190551,7486 "flesch": 20.208676718875297487 }7488 },7489 "feature_sds": {7490 "original": {7491 "mean_sent_len": 6.788436906608183,7492 "sd_sent_len": 4.4584881906648555,7493 "ttr": 0.09695545108909728,7494 "mtld": 23.499201290688873,7495 "mean_word_len": 0.4181889439137438,7496 "long_word_rate": 0.04164394878119979,7497 "comma_rate": 0.0285640095144132,7498 "semicolon_rate": 0.005841695104277365,7499 "paren_rate": 0.01933176164003878,7500 "discourse_rate": 0.010337400491332438,7501 "passive_rate": 0.3417987438319573,7502 "nominal_rate": 0.030359960442961232,7503 "first_person_rate": 0.006671884565179193,7504 "subord_rate": 0.01629064378944434,7505 "hedge_rate": 0.009150870051588392,7506 "negation_rate": 0.007670188020079333,7507 "digit_rate": 0.015169338856323735,7508 "flesch": 12.6597356685175087509 },7510 "rewrite": {7511 "mean_sent_len": 7.148624408237891,7512 "sd_sent_len": 3.665049075243387,7513 "ttr": 0.1009554912117962,7514 "mtld": 28.564116305603893,7515 "mean_word_len": 0.44618939129482277,7516 "long_word_rate": 0.04360193360405262,7517 "comma_rate": 0.028986489710861492,7518 "semicolon_rate": 0.005442891048901435,7519 "paren_rate": 0.019392353929639665,7520 "discourse_rate": 0.01052188104861703,7521 "passive_rate": 0.2881566346143049,7522 "nominal_rate": 0.030185482550593046,7523 "first_person_rate": 0.007248234961597203,7524 "subord_rate": 0.01656326260165493,7525 "hedge_rate": 0.010519269232222463,7526 "negation_rate": 0.008693235891292816,7527 "digit_rate": 0.015550048601400359,7528 "flesch": 14.9638724311939877529 }7530 },7531 "B0_identity": {7532 "vs_original": {7533 "W1_mean_sent_len": 0.6941610112829211,7534 "W1_sd_sent_len": 0.4226860781487078,7535 "W1_ttr": 0.26359475679320193,7536 "W1_mtld": 0.327148878456198,7537 "W1_mean_word_len": 0.1995211888325041,7538 "W1_long_word_rate": 0.06689144680772958,7539 "W1_comma_rate": 0.14344364362727552,7540 "W1_semicolon_rate": 0.053999181008536144,7541 "W1_paren_rate": 0.03550883492135679,7542 "W1_discourse_rate": 0.0814483055978516,7543 "W1_passive_rate": 0.4034286071396181,7544 "W1_nominal_rate": 0.09491443881949037,7545 "W1_first_person_rate": 0.031580344732597763,7546 "W1_subord_rate": 0.11627477810151862,7547 "W1_hedge_rate": 0.1002823007199489,7548 "W1_negation_rate": 0.06758703931706646,7549 "W1_digit_rate": 0.02921509558705879,7550 "W1_flesch": 0.2794896686537671,7551 "W1_mean": 0.189509755474852717552 },7553 "feature_means": {7554 "mean_sent_len": 20.597123637112002,7555 "sd_sent_len": 6.8521933053078445,7556 "ttr": 0.6608422832474243,7557 "mtld": 81.90482180763928,7558 "mean_word_len": 5.667746247948301,7559 "long_word_rate": 0.12671141886437254,7560 "comma_rate": 0.053043535063464285,7561 "semicolon_rate": 0.0018590833482987714,7562 "paren_rate": 0.016231004674493565,7563 "discourse_rate": 0.010495459915617535,7564 "passive_rate": 0.30711378081472895,7565 "nominal_rate": 0.0637939140567542,7566 "first_person_rate": 0.002870498114420158,7567 "subord_rate": 0.024159766846723458,7568 "hedge_rate": 0.00835860697288513,7569 "negation_rate": 0.0059095566977552345,7570 "digit_rate": 0.00968287636190551,7571 "flesch": 20.208676718875297572 },7573 "probe": {7574 "probe_auc_orig_vs_rewrite": 0.77515625,7575 "probe_acc_heldout": 0.7,7576 "eval_mean_p_original": 0.4194833707289496,7577 "eval_frac_classified_original": 0.319548872180451147578 }7579 },7580 "B1_generic_paraphrase": {7581 "vs_original": {7582 "W1_mean_sent_len": 0.517575276911922,7583 "W1_sd_sent_len": 0.23174943656245608,7584 "W1_ttr": 0.24776334975085773,7585 "W1_mtld": 0.3254806455225975,7586 "W1_mean_word_len": 0.46457892347682694,7587 "W1_long_word_rate": 0.3385030839470359,7588 "W1_comma_rate": 0.1339187223906379,7589 "W1_semicolon_rate": 0.054788018298675696,7590 "W1_paren_rate": 0.03615173209235798,7591 "W1_discourse_rate": 0.16620652506505543,7592 "W1_passive_rate": 0.29457950883488665,7593 "W1_nominal_rate": 0.12107637833903157,7594 "W1_first_person_rate": 0.04940770017616064,7595 "W1_subord_rate": 0.14565423242332612,7596 "W1_hedge_rate": 0.16926174721159779,7597 "W1_negation_rate": 0.06467969518980309,7598 "W1_digit_rate": 0.021918252685900134,7599 "W1_flesch": 0.31153296604037445,7600 "W1_mean": 0.205268121939972437601 },7602 "feature_means": {7603 "mean_sent_len": 23.39415645906646,7604 "sd_sent_len": 8.816707509579748,7605 "ttr": 0.6592607982278013,7606 "mtld": 81.79417907395292,7607 "mean_word_len": 5.785404451999962,7608 "long_word_rate": 0.14101618955353878,7609 "comma_rate": 0.05280650224706781,7610 "semicolon_rate": 0.0018546978219354038,7611 "paren_rate": 0.016146700825190506,7612 "discourse_rate": 0.0093574002140031,7613 "passive_rate": 0.3662053430454699,7614 "nominal_rate": 0.06978389220478652,7615 "first_person_rate": 0.003024516807616718,7616 "subord_rate": 0.023607829542202717,7617 "hedge_rate": 0.005894636158761804,7618 "negation_rate": 0.005884273889727881,7619 "digit_rate": 0.009498224941525694,7620 "flesch": 13.767359795751737621 },7622 "probe": {7623 "probe_auc_orig_vs_rewrite": 0.77515625,7624 "probe_acc_heldout": 0.7,7625 "eval_mean_p_original": 0.4906690657170406,7626 "eval_frac_classified_original": 0.4624060150375947627 }7628 },7629 "htr-m1-small": {7630 "vs_original": {7631 "W1_mean_sent_len": 0.6782151535947981,7632 "W1_sd_sent_len": 0.3475490705717477,7633 "W1_ttr": 0.17761275426225398,7634 "W1_mtld": 0.17977537494789195,7635 "W1_mean_word_len": 0.07186146677530585,7636 "W1_long_word_rate": 0.09312025609310856,7637 "W1_comma_rate": 0.08185416901841117,7638 "W1_semicolon_rate": 0.1171157330520923,7639 "W1_paren_rate": 0.036962261131735966,7640 "W1_discourse_rate": 0.06904240766354193,7641 "W1_passive_rate": 0.2503375829685212,7642 "W1_nominal_rate": 0.10223612583245155,7643 "W1_first_person_rate": 0.07359212758138944,7644 "W1_subord_rate": 0.09089793982134595,7645 "W1_hedge_rate": 0.11166287206643936,7646 "W1_negation_rate": 0.07000500205501964,7647 "W1_digit_rate": 0.03234942405345992,7648 "W1_flesch": 0.38278313447791207,7649 "W1_mean": 0.16483182533152377650 },7651 "feature_means": {7652 "mean_sent_len": 20.726663435762006,7653 "sd_sent_len": 7.187251431854847,7654 "ttr": 0.6523189403066488,7655 "mtld": 77.72283890070949,7656 "mean_word_len": 5.598534376075689,7657 "long_word_rate": 0.12403641402574743,7658 "comma_rate": 0.050604794851740444,7659 "semicolon_rate": 0.0014456086299411558,7660 "paren_rate": 0.01598655650170799,7661 "discourse_rate": 0.010425367999538606,7662 "passive_rate": 0.35756027741930385,7663 "nominal_rate": 0.06373635649072382,7664 "first_person_rate": 0.003204145405203744,7665 "subord_rate": 0.02448789350558883,7666 "hedge_rate": 0.008556846229892822,7667 "negation_rate": 0.0059117635798705895,7668 "digit_rate": 0.009695612974301302,7669 "flesch": 21.884953960120057670 },7671 "probe": {7672 "probe_auc_orig_vs_rewrite": 0.77515625,7673 "probe_acc_heldout": 0.7,7674 "eval_mean_p_original": 0.4624135895562007,7675 "eval_frac_classified_original": 0.387218045112781967676 }7677 },7678 "htr-m1-tiny-s3": {7679 "vs_original": {7680 "W1_mean_sent_len": 0.6615603453829707,7681 "W1_sd_sent_len": 0.36111775209268104,7682 "W1_ttr": 0.17678179964567442,7683 "W1_mtld": 0.201164377381675,7684 "W1_mean_word_len": 0.07185464697621667,7685 "W1_long_word_rate": 0.09165025825399385,7686 "W1_comma_rate": 0.09211893808497186,7687 "W1_semicolon_rate": 0.12504109396464247,7688 "W1_paren_rate": 0.03764827766600856,7689 "W1_discourse_rate": 0.07726908272939137,7690 "W1_passive_rate": 0.24543285413222524,7691 "W1_nominal_rate": 0.11217706717454681,7692 "W1_first_person_rate": 0.08370681646150997,7693 "W1_subord_rate": 0.12336154285242594,7694 "W1_hedge_rate": 0.09254330854411531,7695 "W1_negation_rate": 0.07215350153860725,7696 "W1_digit_rate": 0.03290999518619712,7697 "W1_flesch": 0.37437065146027737,7698 "W1_mean": 0.16849235052934067699 },7700 "feature_means": {7701 "mean_sent_len": 20.845915435727054,7702 "sd_sent_len": 7.114689788614027,7703 "ttr": 0.652101919047646,7704 "mtld": 78.24968104404677,7705 "mean_word_len": 5.593576142779523,7706 "long_word_rate": 0.1239425235435953,7707 "comma_rate": 0.05076697141080882,7708 "semicolon_rate": 0.001411850569720733,7709 "paren_rate": 0.016131971118734212,7710 "discourse_rate": 0.010625342181319726,7711 "passive_rate": 0.3585213835095168,7712 "nominal_rate": 0.06316519746999405,7713 "first_person_rate": 0.003273376919220911,7714 "subord_rate": 0.024005406119664254,7715 "hedge_rate": 0.008224890588029932,7716 "negation_rate": 0.005950583084205191,7717 "digit_rate": 0.009638223973196388,7718 "flesch": 21.735756786521077719 },7720 "probe": {7721 "probe_auc_orig_vs_rewrite": 0.77515625,7722 "probe_acc_heldout": 0.7,7723 "eval_mean_p_original": 0.46562865510155554,7724 "eval_frac_classified_original": 0.387218045112781967725 }7726 },7727 "htr-m1-tiny": {7728 "vs_original": {7729 "W1_mean_sent_len": 0.656403503786121,7730 "W1_sd_sent_len": 0.3703236081735663,7731 "W1_ttr": 0.1797851818232851,7732 "W1_mtld": 0.21579118383715376,7733 "W1_mean_word_len": 0.0717160695109788,7734 "W1_long_word_rate": 0.0936232525751419,7735 "W1_comma_rate": 0.12196990459547032,7736 "W1_semicolon_rate": 0.1512281533565232,7737 "W1_paren_rate": 0.03732819394179555,7738 "W1_discourse_rate": 0.08452030106333888,7739 "W1_passive_rate": 0.24021713416372192,7740 "W1_nominal_rate": 0.12658613535372953,7741 "W1_first_person_rate": 0.09894797648056917,7742 "W1_subord_rate": 0.14519448991115824,7743 "W1_hedge_rate": 0.055784124659612064,7744 "W1_negation_rate": 0.06288016716818258,7745 "W1_digit_rate": 0.026842236883625588,7746 "W1_flesch": 0.37494729071164895,7747 "W1_mean": 0.173004939333090167748 },7749 "feature_means": {7750 "mean_sent_len": 20.878453544972352,7751 "sd_sent_len": 7.0774212817519295,7752 "ttr": 0.6524813612244227,7753 "mtld": 78.8238044178395,7754 "mean_word_len": 5.590228696749892,7755 "long_word_rate": 0.12384942117234525,7756 "comma_rate": 0.05183118479816092,7757 "semicolon_rate": 0.0012452528561069456,7758 "paren_rate": 0.016171127695003912,7759 "discourse_rate": 0.010395689342497906,7760 "passive_rate": 0.3597822135944242,7761 "nominal_rate": 0.06287655922392302,7762 "first_person_rate": 0.0033784780546970913,7763 "subord_rate": 0.023680792158407054,7764 "hedge_rate": 0.007846400381538972,7765 "negation_rate": 0.005859450003442213,7766 "digit_rate": 0.009610353681810554,7767 "flesch": 21.788542830576887768 },7769 "probe": {7770 "probe_auc_orig_vs_rewrite": 0.77515625,7771 "probe_acc_heldout": 0.7,7772 "eval_mean_p_original": 0.4653924376683523,7773 "eval_frac_classified_original": 0.409774436090225577774 }7775 },7776 "htr-m3tokenonly-tiny": {7777 "vs_original": {7778 "W1_mean_sent_len": 0.6566533653402262,7779 "W1_sd_sent_len": 0.3856436393368803,7780 "W1_ttr": 0.21759266993101042,7781 "W1_mtld": 0.2415863246265341,7782 "W1_mean_word_len": 0.09692202150136119,7783 "W1_long_word_rate": 0.08057072831085885,7784 "W1_comma_rate": 0.06977845242928968,7785 "W1_semicolon_rate": 0.135628788480267,7786 "W1_paren_rate": 0.036934258597271195,7787 "W1_discourse_rate": 0.07853754672740179,7788 "W1_passive_rate": 0.2759178549611446,7789 "W1_nominal_rate": 0.11584674435833764,7790 "W1_first_person_rate": 0.06652731267503728,7791 "W1_subord_rate": 0.11216153360361143,7792 "W1_hedge_rate": 0.07179401802635149,7793 "W1_negation_rate": 0.06603270184563344,7794 "W1_digit_rate": 0.031888356888786606,7795 "W1_flesch": 0.3370983247805182,7796 "W1_mean": 0.170950813467806727797 },7798 "feature_means": {7799 "mean_sent_len": 20.88816655800916,7800 "sd_sent_len": 7.056898083602478,7801 "ttr": 0.6562442603354398,7802 "mtld": 79.63898591232436,7803 "mean_word_len": 5.615210111466186,7804 "long_word_rate": 0.12468914787205215,7805 "comma_rate": 0.05041308880672688,7806 "semicolon_rate": 0.0013313340183434231,7807 "paren_rate": 0.01615316884368819,7808 "discourse_rate": 0.010863950620187943,7809 "passive_rate": 0.3481093656782156,7810 "nominal_rate": 0.06314709805858065,7811 "first_person_rate": 0.003139544935186081,7812 "subord_rate": 0.024133784036175287,7813 "hedge_rate": 0.0079168473612529,7814 "negation_rate": 0.005896440922789977,7815 "digit_rate": 0.00967290111009055,7816 "flesch": 21.202127435767817817 },7818 "probe": {7819 "probe_auc_orig_vs_rewrite": 0.77515625,7820 "probe_acc_heldout": 0.7,7821 "eval_mean_p_original": 0.46120038839306904,7822 "eval_frac_classified_original": 0.413533834586466147823 }7824 }7825 },7826 "confirmatory": {7827 "preregistration_frozen": true,7828 "n_boot": 100007829 }7830}