Repository Public Research preview
1{2 "created_at": "2026-11-10T00:45:30Z",3 "git": {4 "commit": "c777c34462ba0599fd259992424636251da582d5",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": 502,31 "systems": {32 "B0_identity": {33 "overall": {34 "n": 502,35 "chrf": {36 "mean": 71.23937783602265,37 "ci_low": 69.69231510865107,38 "ci_high": 72.65316852745619,39 "n_items": 502,40 "n_groups": 3941 },42 "edit_sim": {43 "mean": 0.6664540763041797,44 "ci_low": 0.6446656326574934,45 "ci_high": 0.685653554307791,46 "n_items": 502,47 "n_groups": 3948 },49 "rougeL": {50 "mean": 0.689762389206981,51 "ci_low": 0.6702253423571827,52 "ci_high": 0.7078250400940606,53 "n_items": 502,54 "n_groups": 3955 },56 "exact_match": {57 "mean": 0.0,58 "ci_low": 0.0,59 "ci_high": 0.0,60 "n_items": 502,61 "n_groups": 3962 },63 "number_recall": {64 "mean": 1.0,65 "ci_low": 1.0,66 "ci_high": 1.0,67 "n_items": 502,68 "n_groups": 3969 },70 "placeholders_exact": {71 "mean": 1.0,72 "ci_low": 1.0,73 "ci_high": 1.0,74 "n_items": 502,75 "n_groups": 3976 }77 },78 "by_variant": {79 "A": {80 "n": 83,81 "chrf": {82 "mean": 68.9107985434573,83 "ci_low": 67.25114571753734,84 "ci_high": 70.54292514680496,85 "n_items": 83,86 "n_groups": 3687 },88 "edit_sim": {89 "mean": 0.6247169202534111,90 "ci_low": 0.5999340663324213,91 "ci_high": 0.6460411501228405,92 "n_items": 83,93 "n_groups": 3694 },95 "rougeL": {96 "mean": 0.6487263771936375,97 "ci_low": 0.6264159328459006,98 "ci_high": 0.6692508200024451,99 "n_items": 83,100 "n_groups": 36101 },102 "exact_match": {103 "mean": 0.0,104 "ci_low": 0.0,105 "ci_high": 0.0,106 "n_items": 83,107 "n_groups": 36108 },109 "number_recall": {110 "mean": 1.0,111 "ci_low": 1.0,112 "ci_high": 1.0,113 "n_items": 83,114 "n_groups": 36115 },116 "placeholders_exact": {117 "mean": 1.0,118 "ci_low": 1.0,119 "ci_high": 1.0,120 "n_items": 83,121 "n_groups": 36122 }123 },124 "B": {125 "n": 83,126 "chrf": {127 "mean": 79.032156101057,128 "ci_low": 77.24720769900043,129 "ci_high": 80.69539229905163,130 "n_items": 83,131 "n_groups": 37132 },133 "edit_sim": {134 "mean": 0.7673482308403631,135 "ci_low": 0.7399335755509158,136 "ci_high": 0.7930462238086002,137 "n_items": 83,138 "n_groups": 37139 },140 "rougeL": {141 "mean": 0.7897929928972692,142 "ci_low": 0.7645123110541671,143 "ci_high": 0.8129055973912531,144 "n_items": 83,145 "n_groups": 37146 },147 "exact_match": {148 "mean": 0.0,149 "ci_low": 0.0,150 "ci_high": 0.0,151 "n_items": 83,152 "n_groups": 37153 },154 "number_recall": {155 "mean": 1.0,156 "ci_low": 1.0,157 "ci_high": 1.0,158 "n_items": 83,159 "n_groups": 37160 },161 "placeholders_exact": {162 "mean": 1.0,163 "ci_low": 1.0,164 "ci_high": 1.0,165 "n_items": 83,166 "n_groups": 37167 }168 },169 "C": {170 "n": 84,171 "chrf": {172 "mean": 74.55188592895387,173 "ci_low": 72.96481590008713,174 "ci_high": 76.2154624222726,175 "n_items": 84,176 "n_groups": 38177 },178 "edit_sim": {179 "mean": 0.7374783537866176,180 "ci_low": 0.7113612504216417,181 "ci_high": 0.7613319277592546,182 "n_items": 84,183 "n_groups": 38184 },185 "rougeL": {186 "mean": 0.7688164671180863,187 "ci_low": 0.7466086246105067,188 "ci_high": 0.7880720402712103,189 "n_items": 84,190 "n_groups": 38191 },192 "exact_match": {193 "mean": 0.0,194 "ci_low": 0.0,195 "ci_high": 0.0,196 "n_items": 84,197 "n_groups": 38198 },199 "number_recall": {200 "mean": 1.0,201 "ci_low": 1.0,202 "ci_high": 1.0,203 "n_items": 84,204 "n_groups": 38205 },206 "placeholders_exact": {207 "mean": 1.0,208 "ci_low": 1.0,209 "ci_high": 1.0,210 "n_items": 84,211 "n_groups": 38212 }213 },214 "D": {215 "n": 85,216 "chrf": {217 "mean": 67.49171977861238,218 "ci_low": 65.66197623783536,219 "ci_high": 69.31338037618508,220 "n_items": 85,221 "n_groups": 37222 },223 "edit_sim": {224 "mean": 0.6050263283744549,225 "ci_low": 0.5818262298858048,226 "ci_high": 0.6270962333723196,227 "n_items": 85,228 "n_groups": 37229 },230 "rougeL": {231 "mean": 0.6270250163646537,232 "ci_low": 0.604046789358639,233 "ci_high": 0.6496134915198688,234 "n_items": 85,235 "n_groups": 37236 },237 "exact_match": {238 "mean": 0.0,239 "ci_low": 0.0,240 "ci_high": 0.0,241 "n_items": 85,242 "n_groups": 37243 },244 "number_recall": {245 "mean": 1.0,246 "ci_low": 1.0,247 "ci_high": 1.0,248 "n_items": 85,249 "n_groups": 37250 },251 "placeholders_exact": {252 "mean": 1.0,253 "ci_low": 1.0,254 "ci_high": 1.0,255 "n_items": 85,256 "n_groups": 37257 }258 },259 "E": {260 "n": 167,261 "chrf": {262 "mean": 68.76495711960781,263 "ci_low": 67.10252665724664,264 "ci_high": 70.36754544025631,265 "n_items": 167,266 "n_groups": 38267 },268 "edit_sim": {269 "mean": 0.6325935277485656,270 "ci_low": 0.6124074256005445,271 "ci_high": 0.6535805121808616,272 "n_items": 167,273 "n_groups": 38274 },275 "rougeL": {276 "mean": 0.652610191829008,277 "ci_low": 0.632857635694573,278 "ci_high": 0.6729838123518029,279 "n_items": 167,280 "n_groups": 38281 },282 "exact_match": {283 "mean": 0.0,284 "ci_low": 0.0,285 "ci_high": 0.0,286 "n_items": 167,287 "n_groups": 38288 },289 "number_recall": {290 "mean": 1.0,291 "ci_low": 1.0,292 "ci_high": 1.0,293 "n_items": 167,294 "n_groups": 38295 },296 "placeholders_exact": {297 "mean": 1.0,298 "ci_low": 1.0,299 "ci_high": 1.0,300 "n_items": 167,301 "n_groups": 38302 }303 }304 },305 "by_discipline": {306 "biomedicine": {307 "n": 184,308 "chrf": {309 "mean": 72.4420780776866,310 "ci_low": 69.65394388519677,311 "ci_high": 74.50962590914234,312 "n_items": 184,313 "n_groups": 19314 },315 "edit_sim": {316 "mean": 0.6814521410632746,317 "ci_low": 0.6542993114324067,318 "ci_high": 0.7021794542233118,319 "n_items": 184,320 "n_groups": 19321 },322 "rougeL": {323 "mean": 0.7072868247634702,324 "ci_low": 0.6715962021697993,325 "ci_high": 0.7295248298947277,326 "n_items": 184,327 "n_groups": 19328 },329 "exact_match": {330 "mean": 0.0,331 "ci_low": 0.0,332 "ci_high": 0.0,333 "n_items": 184,334 "n_groups": 19335 },336 "number_recall": {337 "mean": 1.0,338 "ci_low": 1.0,339 "ci_high": 1.0,340 "n_items": 184,341 "n_groups": 19342 },343 "placeholders_exact": {344 "mean": 1.0,345 "ci_low": 1.0,346 "ci_high": 1.0,347 "n_items": 184,348 "n_groups": 19349 }350 },351 "computer_science": {352 "n": 53,353 "chrf": {354 "mean": 67.1016292020675,355 "ci_low": 63.32544785482342,356 "ci_high": 71.10042137396198,357 "n_items": 53,358 "n_groups": 3359 },360 "edit_sim": {361 "mean": 0.6424254585874279,362 "ci_low": 0.6098401690231675,363 "ci_high": 0.6990899731611595,364 "n_items": 53,365 "n_groups": 3366 },367 "rougeL": {368 "mean": 0.6477225780633263,369 "ci_low": 0.6120831599301225,370 "ci_high": 0.6892538035199753,371 "n_items": 53,372 "n_groups": 3373 },374 "exact_match": {375 "mean": 0.0,376 "ci_low": 0.0,377 "ci_high": 0.0,378 "n_items": 53,379 "n_groups": 3380 },381 "number_recall": {382 "mean": 1.0,383 "ci_low": 1.0,384 "ci_high": 1.0,385 "n_items": 53,386 "n_groups": 3387 },388 "placeholders_exact": {389 "mean": 1.0,390 "ci_low": 1.0,391 "ci_high": 1.0,392 "n_items": 53,393 "n_groups": 3394 }395 },396 "earth_sciences": {397 "n": 22,398 "chrf": {399 "mean": 73.79666729681833,400 "ci_low": 73.79666729681833,401 "ci_high": 73.79666729681833,402 "n_items": 22,403 "n_groups": 1404 },405 "edit_sim": {406 "mean": 0.6885175353745011,407 "ci_low": 0.6885175353745011,408 "ci_high": 0.6885175353745011,409 "n_items": 22,410 "n_groups": 1411 },412 "rougeL": {413 "mean": 0.7227206126650174,414 "ci_low": 0.7227206126650174,415 "ci_high": 0.7227206126650174,416 "n_items": 22,417 "n_groups": 1418 },419 "exact_match": {420 "mean": 0.0,421 "ci_low": 0.0,422 "ci_high": 0.0,423 "n_items": 22,424 "n_groups": 1425 },426 "number_recall": {427 "mean": 1.0,428 "ci_low": 1.0,429 "ci_high": 1.0,430 "n_items": 22,431 "n_groups": 1432 },433 "placeholders_exact": {434 "mean": 1.0,435 "ci_low": 1.0,436 "ci_high": 1.0,437 "n_items": 22,438 "n_groups": 1439 }440 },441 "engineering": {442 "n": 45,443 "chrf": {444 "mean": 68.23760768399778,445 "ci_low": 68.03949881334208,446 "ci_high": 69.52531534325972,447 "n_items": 45,448 "n_groups": 2449 },450 "edit_sim": {451 "mean": 0.5621710523204569,452 "ci_low": 0.5612896029073148,453 "ci_high": 0.562306659922479,454 "n_items": 45,455 "n_groups": 2456 },457 "rougeL": {458 "mean": 0.6193663025992324,459 "ci_low": 0.6118165022835942,460 "ci_high": 0.6205278103401,461 "n_items": 45,462 "n_groups": 2463 },464 "exact_match": {465 "mean": 0.0,466 "ci_low": 0.0,467 "ci_high": 0.0,468 "n_items": 45,469 "n_groups": 2470 },471 "number_recall": {472 "mean": 1.0,473 "ci_low": 1.0,474 "ci_high": 1.0,475 "n_items": 45,476 "n_groups": 2477 },478 "placeholders_exact": {479 "mean": 1.0,480 "ci_low": 1.0,481 "ci_high": 1.0,482 "n_items": 45,483 "n_groups": 2484 }485 },486 "life_sciences": {487 "n": 144,488 "chrf": {489 "mean": 71.74953174323284,490 "ci_low": 69.19046543380087,491 "ci_high": 74.74658905751316,492 "n_items": 144,493 "n_groups": 13494 },495 "edit_sim": {496 "mean": 0.6903761377717228,497 "ci_low": 0.6672404992900409,498 "ci_high": 0.718182907568068,499 "n_items": 144,500 "n_groups": 13501 },502 "rougeL": {503 "mean": 0.701906841983478,504 "ci_low": 0.677270682809856,505 "ci_high": 0.7284315057702586,506 "n_items": 144,507 "n_groups": 13508 },509 "exact_match": {510 "mean": 0.0,511 "ci_low": 0.0,512 "ci_high": 0.0,513 "n_items": 144,514 "n_groups": 13515 },516 "number_recall": {517 "mean": 1.0,518 "ci_low": 1.0,519 "ci_high": 1.0,520 "n_items": 144,521 "n_groups": 13522 },523 "placeholders_exact": {524 "mean": 1.0,525 "ci_low": 1.0,526 "ci_high": 1.0,527 "n_items": 144,528 "n_groups": 13529 }530 },531 "mathematics": {532 "n": 54,533 "chrf": {534 "mean": 71.30161782118573,535 "ci_low": 71.30161782118573,536 "ci_high": 71.30161782118573,537 "n_items": 54,538 "n_groups": 1539 },540 "edit_sim": {541 "mean": 0.6530547420765628,542 "ci_low": 0.6530547420765628,543 "ci_high": 0.6530547420765628,544 "n_items": 54,545 "n_groups": 1546 },547 "rougeL": {548 "mean": 0.6841615675343137,549 "ci_low": 0.6841615675343137,550 "ci_high": 0.6841615675343137,551 "n_items": 54,552 "n_groups": 1553 },554 "exact_match": {555 "mean": 0.0,556 "ci_low": 0.0,557 "ci_high": 0.0,558 "n_items": 54,559 "n_groups": 1560 },561 "number_recall": {562 "mean": 1.0,563 "ci_low": 1.0,564 "ci_high": 1.0,565 "n_items": 54,566 "n_groups": 1567 },568 "placeholders_exact": {569 "mean": 1.0,570 "ci_low": 1.0,571 "ci_high": 1.0,572 "n_items": 54,573 "n_groups": 1574 }575 }576 },577 "by_era": {578 "1980-1999": {579 "n": 16,580 "chrf": {581 "mean": 76.53469556553756,582 "ci_low": 68.75273822368474,583 "ci_high": 79.12868134615516,584 "n_items": 16,585 "n_groups": 2586 },587 "edit_sim": {588 "mean": 0.7105890717070038,589 "ci_low": 0.6418485674132676,590 "ci_high": 0.7335025731382491,591 "n_items": 16,592 "n_groups": 2593 },594 "rougeL": {595 "mean": 0.7434990480209428,596 "ci_low": 0.6703459464919619,597 "ci_high": 0.7678834151972698,598 "n_items": 16,599 "n_groups": 2600 },601 "exact_match": {602 "mean": 0.0,603 "ci_low": 0.0,604 "ci_high": 0.0,605 "n_items": 16,606 "n_groups": 2607 },608 "number_recall": {609 "mean": 1.0,610 "ci_low": 1.0,611 "ci_high": 1.0,612 "n_items": 16,613 "n_groups": 2614 },615 "placeholders_exact": {616 "mean": 1.0,617 "ci_low": 1.0,618 "ci_high": 1.0,619 "n_items": 16,620 "n_groups": 2621 }622 },623 "2000-2009": {624 "n": 70,625 "chrf": {626 "mean": 72.45477499424156,627 "ci_low": 65.77032192832114,628 "ci_high": 73.08144246917159,629 "n_items": 70,630 "n_groups": 2631 },632 "edit_sim": {633 "mean": 0.6800615142137126,634 "ci_low": 0.6113922818035633,635 "ci_high": 0.686499254752164,636 "n_items": 70,637 "n_groups": 2638 },639 "rougeL": {640 "mean": 0.7127318327999563,641 "ci_low": 0.6252591424068187,642 "ci_high": 0.7209323975243132,643 "n_items": 70,644 "n_groups": 2645 },646 "exact_match": {647 "mean": 0.0,648 "ci_low": 0.0,649 "ci_high": 0.0,650 "n_items": 70,651 "n_groups": 2652 },653 "number_recall": {654 "mean": 1.0,655 "ci_low": 1.0,656 "ci_high": 1.0,657 "n_items": 70,658 "n_groups": 2659 },660 "placeholders_exact": {661 "mean": 1.0,662 "ci_low": 1.0,663 "ci_high": 1.0,664 "n_items": 70,665 "n_groups": 2666 }667 },668 "2010-2017": {669 "n": 416,670 "chrf": {671 "mean": 70.83119782461026,672 "ci_low": 69.20665698290502,673 "ci_high": 72.44835803242813,674 "n_items": 416,675 "n_groups": 35676 },677 "edit_sim": {678 "mean": 0.6624668633712171,679 "ci_low": 0.6401976234822544,680 "ci_high": 0.686154247947939,681 "n_items": 416,682 "n_groups": 35683 },684 "rougeL": {685 "mean": 0.6838305440326258,686 "ci_low": 0.6647430086304852,687 "ci_high": 0.7043191152394412,688 "n_items": 416,689 "n_groups": 35690 },691 "exact_match": {692 "mean": 0.0,693 "ci_low": 0.0,694 "ci_high": 0.0,695 "n_items": 416,696 "n_groups": 35697 },698 "number_recall": {699 "mean": 1.0,700 "ci_low": 1.0,701 "ci_high": 1.0,702 "n_items": 416,703 "n_groups": 35704 },705 "placeholders_exact": {706 "mean": 1.0,707 "ci_low": 1.0,708 "ci_high": 1.0,709 "n_items": 416,710 "n_groups": 35711 }712 }713 },714 "by_role": {715 "abstract": {716 "n": 63,717 "chrf": {718 "mean": 72.50800472934515,719 "ci_low": 70.1366090728497,720 "ci_high": 75.39388501665668,721 "n_items": 63,722 "n_groups": 9723 },724 "edit_sim": {725 "mean": 0.6794247432965996,726 "ci_low": 0.6480390236181733,727 "ci_high": 0.7038125464639546,728 "n_items": 63,729 "n_groups": 9730 },731 "rougeL": {732 "mean": 0.7040402872766465,733 "ci_low": 0.6714091216592436,734 "ci_high": 0.7336710555864084,735 "n_items": 63,736 "n_groups": 9737 },738 "exact_match": {739 "mean": 0.0,740 "ci_low": 0.0,741 "ci_high": 0.0,742 "n_items": 63,743 "n_groups": 9744 },745 "number_recall": {746 "mean": 1.0,747 "ci_low": 1.0,748 "ci_high": 1.0,749 "n_items": 63,750 "n_groups": 9751 },752 "placeholders_exact": {753 "mean": 1.0,754 "ci_low": 1.0,755 "ci_high": 1.0,756 "n_items": 63,757 "n_groups": 9758 }759 },760 "background": {761 "n": 22,762 "chrf": {763 "mean": 71.06509343012831,764 "ci_low": 64.97141998646227,765 "ci_high": 77.15876687379435,766 "n_items": 22,767 "n_groups": 4768 },769 "edit_sim": {770 "mean": 0.6587641108419198,771 "ci_low": 0.5849656059376194,772 "ci_high": 0.7325626157462204,773 "n_items": 22,774 "n_groups": 4775 },776 "rougeL": {777 "mean": 0.6793767804221361,778 "ci_low": 0.6185573282691166,779 "ci_high": 0.7401962325751559,780 "n_items": 22,781 "n_groups": 4782 },783 "exact_match": {784 "mean": 0.0,785 "ci_low": 0.0,786 "ci_high": 0.0,787 "n_items": 22,788 "n_groups": 4789 },790 "number_recall": {791 "mean": 1.0,792 "ci_low": 1.0,793 "ci_high": 1.0,794 "n_items": 22,795 "n_groups": 4796 },797 "placeholders_exact": {798 "mean": 1.0,799 "ci_low": 1.0,800 "ci_high": 1.0,801 "n_items": 22,802 "n_groups": 4803 }804 },805 "conclusion": {806 "n": 60,807 "chrf": {808 "mean": 67.12469791564295,809 "ci_low": 63.49519904767281,810 "ci_high": 71.13716911631873,811 "n_items": 60,812 "n_groups": 9813 },814 "edit_sim": {815 "mean": 0.6190243583358187,816 "ci_low": 0.5834103415903529,817 "ci_high": 0.6596010978840353,818 "n_items": 60,819 "n_groups": 9820 },821 "rougeL": {822 "mean": 0.6446193679889368,823 "ci_low": 0.6136770850269723,824 "ci_high": 0.681882390662704,825 "n_items": 60,826 "n_groups": 9827 },828 "exact_match": {829 "mean": 0.0,830 "ci_low": 0.0,831 "ci_high": 0.0,832 "n_items": 60,833 "n_groups": 9834 },835 "number_recall": {836 "mean": 1.0,837 "ci_low": 1.0,838 "ci_high": 1.0,839 "n_items": 60,840 "n_groups": 9841 },842 "placeholders_exact": {843 "mean": 1.0,844 "ci_low": 1.0,845 "ci_high": 1.0,846 "n_items": 60,847 "n_groups": 9848 }849 },850 "data": {851 "n": 33,852 "chrf": {853 "mean": 74.14360652121479,854 "ci_low": 69.43507542422063,855 "ci_high": 77.25654347791803,856 "n_items": 33,857 "n_groups": 5858 },859 "edit_sim": {860 "mean": 0.647008801796061,861 "ci_low": 0.5970703452604852,862 "ci_high": 0.6737201540891958,863 "n_items": 33,864 "n_groups": 5865 },866 "rougeL": {867 "mean": 0.7021431476216692,868 "ci_low": 0.6458351194583515,869 "ci_high": 0.7436789354339403,870 "n_items": 33,871 "n_groups": 5872 },873 "exact_match": {874 "mean": 0.0,875 "ci_low": 0.0,876 "ci_high": 0.0,877 "n_items": 33,878 "n_groups": 5879 },880 "number_recall": {881 "mean": 1.0,882 "ci_low": 1.0,883 "ci_high": 1.0,884 "n_items": 33,885 "n_groups": 5886 },887 "placeholders_exact": {888 "mean": 1.0,889 "ci_low": 1.0,890 "ci_high": 1.0,891 "n_items": 33,892 "n_groups": 5893 }894 },895 "discussion": {896 "n": 60,897 "chrf": {898 "mean": 69.3304390116742,899 "ci_low": 66.82968401956781,900 "ci_high": 71.51070885276089,901 "n_items": 60,902 "n_groups": 7903 },904 "edit_sim": {905 "mean": 0.6705317268995572,906 "ci_low": 0.6375776348401072,907 "ci_high": 0.7128781739312059,908 "n_items": 60,909 "n_groups": 7910 },911 "rougeL": {912 "mean": 0.6662314028041307,913 "ci_low": 0.6361486083465432,914 "ci_high": 0.7014521610234185,915 "n_items": 60,916 "n_groups": 7917 },918 "exact_match": {919 "mean": 0.0,920 "ci_low": 0.0,921 "ci_high": 0.0,922 "n_items": 60,923 "n_groups": 7924 },925 "number_recall": {926 "mean": 1.0,927 "ci_low": 1.0,928 "ci_high": 1.0,929 "n_items": 60,930 "n_groups": 7931 },932 "placeholders_exact": {933 "mean": 1.0,934 "ci_low": 1.0,935 "ci_high": 1.0,936 "n_items": 60,937 "n_groups": 7938 }939 },940 "introduction": {941 "n": 56,942 "chrf": {943 "mean": 69.79620638311606,944 "ci_low": 67.57993695285768,945 "ci_high": 72.38297315594704,946 "n_items": 56,947 "n_groups": 9948 },949 "edit_sim": {950 "mean": 0.6527494739524976,951 "ci_low": 0.609773471652292,952 "ci_high": 0.6928527952886531,953 "n_items": 56,954 "n_groups": 9955 },956 "rougeL": {957 "mean": 0.6702027355599444,958 "ci_low": 0.6385690647523419,959 "ci_high": 0.7029346494989263,960 "n_items": 56,961 "n_groups": 9962 },963 "exact_match": {964 "mean": 0.0,965 "ci_low": 0.0,966 "ci_high": 0.0,967 "n_items": 56,968 "n_groups": 9969 },970 "number_recall": {971 "mean": 1.0,972 "ci_low": 1.0,973 "ci_high": 1.0,974 "n_items": 56,975 "n_groups": 9976 },977 "placeholders_exact": {978 "mean": 1.0,979 "ci_low": 1.0,980 "ci_high": 1.0,981 "n_items": 56,982 "n_groups": 9983 }984 },985 "limitations": {986 "n": 12,987 "chrf": {988 "mean": 67.58867261770651,989 "ci_low": 67.51507845011241,990 "ci_high": 67.66226678530062,991 "n_items": 12,992 "n_groups": 2993 },994 "edit_sim": {995 "mean": 0.6180924670994487,996 "ci_low": 0.5740828939289379,997 "ci_high": 0.6621020402699591,998 "n_items": 12,999 "n_groups": 21000 },1001 "rougeL": {1002 "mean": 0.6590679633539022,1003 "ci_low": 0.6170681628635761,1004 "ci_high": 0.7010677638442283,1005 "n_items": 12,1006 "n_groups": 21007 },1008 "exact_match": {1009 "mean": 0.0,1010 "ci_low": 0.0,1011 "ci_high": 0.0,1012 "n_items": 12,1013 "n_groups": 21014 },1015 "number_recall": {1016 "mean": 1.0,1017 "ci_low": 1.0,1018 "ci_high": 1.0,1019 "n_items": 12,1020 "n_groups": 21021 },1022 "placeholders_exact": {1023 "mean": 1.0,1024 "ci_low": 1.0,1025 "ci_high": 1.0,1026 "n_items": 12,1027 "n_groups": 21028 }1029 },1030 "methods": {1031 "n": 69,1032 "chrf": {1033 "mean": 73.86391944052264,1034 "ci_low": 70.17347783026452,1035 "ci_high": 77.13478296733658,1036 "n_items": 69,1037 "n_groups": 111038 },1039 "edit_sim": {1040 "mean": 0.6940625375374952,1041 "ci_low": 0.6526431332950627,1042 "ci_high": 0.7325620151323582,1043 "n_items": 69,1044 "n_groups": 111045 },1046 "rougeL": {1047 "mean": 0.7278835869635425,1048 "ci_low": 0.6852424947207937,1049 "ci_high": 0.7662232624227634,1050 "n_items": 69,1051 "n_groups": 111052 },1053 "exact_match": {1054 "mean": 0.0,1055 "ci_low": 0.0,1056 "ci_high": 0.0,1057 "n_items": 69,1058 "n_groups": 111059 },1060 "number_recall": {1061 "mean": 1.0,1062 "ci_low": 1.0,1063 "ci_high": 1.0,1064 "n_items": 69,1065 "n_groups": 111066 },1067 "placeholders_exact": {1068 "mean": 1.0,1069 "ci_low": 1.0,1070 "ci_high": 1.0,1071 "n_items": 69,1072 "n_groups": 111073 }1074 },1075 "other": {1076 "n": 32,1077 "chrf": {1078 "mean": 77.94837613196489,1079 "ci_low": 75.15562051435919,1080 "ci_high": 80.98180243728342,1081 "n_items": 32,1082 "n_groups": 51083 },1084 "edit_sim": {1085 "mean": 0.7205898867666445,1086 "ci_low": 0.6821683732671255,1087 "ci_high": 0.7768109892121111,1088 "n_items": 32,1089 "n_groups": 51090 },1091 "rougeL": {1092 "mean": 0.7453892862476221,1093 "ci_low": 0.7102994028921933,1094 "ci_high": 0.7895859766946772,1095 "n_items": 32,1096 "n_groups": 51097 },1098 "exact_match": {1099 "mean": 0.0,1100 "ci_low": 0.0,1101 "ci_high": 0.0,1102 "n_items": 32,1103 "n_groups": 51104 },1105 "number_recall": {1106 "mean": 1.0,1107 "ci_low": 1.0,1108 "ci_high": 1.0,1109 "n_items": 32,1110 "n_groups": 51111 },1112 "placeholders_exact": {1113 "mean": 1.0,1114 "ci_low": 1.0,1115 "ci_high": 1.0,1116 "n_items": 32,1117 "n_groups": 51118 }1119 },1120 "related_work": {1121 "n": 6,1122 "chrf": {1123 "mean": 74.90034152742608,1124 "ci_low": 74.90034152742608,1125 "ci_high": 74.90034152742608,1126 "n_items": 6,1127 "n_groups": 11128 },1129 "edit_sim": {1130 "mean": 0.7644345555888461,1131 "ci_low": 0.7644345555888461,1132 "ci_high": 0.7644345555888461,1133 "n_items": 6,1134 "n_groups": 11135 },1136 "rougeL": {1137 "mean": 0.7822450515000217,1138 "ci_low": 0.7822450515000217,1139 "ci_high": 0.7822450515000217,1140 "n_items": 6,1141 "n_groups": 11142 },1143 "exact_match": {1144 "mean": 0.0,1145 "ci_low": 0.0,1146 "ci_high": 0.0,1147 "n_items": 6,1148 "n_groups": 11149 },1150 "number_recall": {1151 "mean": 1.0,1152 "ci_low": 1.0,1153 "ci_high": 1.0,1154 "n_items": 6,1155 "n_groups": 11156 },1157 "placeholders_exact": {1158 "mean": 1.0,1159 "ci_low": 1.0,1160 "ci_high": 1.0,1161 "n_items": 6,1162 "n_groups": 11163 }1164 },1165 "results": {1166 "n": 62,1167 "chrf": {1168 "mean": 69.55675231721033,1169 "ci_low": 66.31712109026962,1170 "ci_high": 72.4953129256282,1171 "n_items": 62,1172 "n_groups": 81173 },1174 "edit_sim": {1175 "mean": 0.646478978135782,1176 "ci_low": 0.6074848517816466,1177 "ci_high": 0.6859764650268937,1178 "n_items": 62,1179 "n_groups": 81180 },1181 "rougeL": {1182 "mean": 0.673630306392738,1183 "ci_low": 0.629348386967102,1184 "ci_high": 0.7131591249556015,1185 "n_items": 62,1186 "n_groups": 81187 },1188 "exact_match": {1189 "mean": 0.0,1190 "ci_low": 0.0,1191 "ci_high": 0.0,1192 "n_items": 62,1193 "n_groups": 81194 },1195 "number_recall": {1196 "mean": 1.0,1197 "ci_low": 1.0,1198 "ci_high": 1.0,1199 "n_items": 62,1200 "n_groups": 81201 },1202 "placeholders_exact": {1203 "mean": 1.0,1204 "ci_low": 1.0,1205 "ci_high": 1.0,1206 "n_items": 62,1207 "n_groups": 81208 }1209 },1210 "theory": {1211 "n": 27,1212 "chrf": {1213 "mean": 71.26493667093234,1214 "ci_low": 68.68218252408576,1215 "ci_high": 75.80166910110874,1216 "n_items": 27,1217 "n_groups": 41218 },1219 "edit_sim": {1220 "mean": 0.7018572545923376,1221 "ci_low": 0.6765913328496294,1222 "ci_high": 0.7587985573717205,1223 "n_items": 27,1224 "n_groups": 41225 },1226 "rougeL": {1227 "mean": 0.7097399732491702,1228 "ci_low": 0.6709765189399954,1229 "ci_high": 0.7650183460250818,1230 "n_items": 27,1231 "n_groups": 41232 },1233 "exact_match": {1234 "mean": 0.0,1235 "ci_low": 0.0,1236 "ci_high": 0.0,1237 "n_items": 27,1238 "n_groups": 41239 },1240 "number_recall": {1241 "mean": 1.0,1242 "ci_low": 1.0,1243 "ci_high": 1.0,1244 "n_items": 27,1245 "n_groups": 41246 },1247 "placeholders_exact": {1248 "mean": 1.0,1249 "ci_low": 1.0,1250 "ci_high": 1.0,1251 "n_items": 27,1252 "n_groups": 41253 }1254 }1255 }1256 },1257 "B1_generic_paraphrase": {1258 "overall": {1259 "n": 502,1260 "chrf": {1261 "mean": 68.41496364055496,1262 "ci_low": 66.89613357695933,1263 "ci_high": 69.99220930031775,1264 "n_items": 502,1265 "n_groups": 391266 },1267 "edit_sim": {1268 "mean": 0.5610653524519996,1269 "ci_low": 0.5449377084892308,1270 "ci_high": 0.5790777572852239,1271 "n_items": 502,1272 "n_groups": 391273 },1274 "rougeL": {1275 "mean": 0.611930573837605,1276 "ci_low": 0.5930902863620554,1277 "ci_high": 0.6322312429768826,1278 "n_items": 502,1279 "n_groups": 391280 },1281 "exact_match": {1282 "mean": 0.0,1283 "ci_low": 0.0,1284 "ci_high": 0.0,1285 "n_items": 502,1286 "n_groups": 391287 },1288 "number_recall": {1289 "mean": 1.0,1290 "ci_low": 1.0,1291 "ci_high": 1.0,1292 "n_items": 502,1293 "n_groups": 391294 },1295 "placeholders_exact": {1296 "mean": 1.0,1297 "ci_low": 1.0,1298 "ci_high": 1.0,1299 "n_items": 502,1300 "n_groups": 391301 }1302 },1303 "by_variant": {1304 "A": {1305 "n": 83,1306 "chrf": {1307 "mean": 66.62891098315664,1308 "ci_low": 64.98846665868173,1309 "ci_high": 68.32399956859184,1310 "n_items": 83,1311 "n_groups": 361312 },1313 "edit_sim": {1314 "mean": 0.5213047295696933,1315 "ci_low": 0.5007951510593024,1316 "ci_high": 0.5465331534530121,1317 "n_items": 83,1318 "n_groups": 361319 },1320 "rougeL": {1321 "mean": 0.5755838238071158,1322 "ci_low": 0.5519459843105253,1323 "ci_high": 0.5982277905146144,1324 "n_items": 83,1325 "n_groups": 361326 },1327 "exact_match": {1328 "mean": 0.0,1329 "ci_low": 0.0,1330 "ci_high": 0.0,1331 "n_items": 83,1332 "n_groups": 361333 },1334 "number_recall": {1335 "mean": 1.0,1336 "ci_low": 1.0,1337 "ci_high": 1.0,1338 "n_items": 83,1339 "n_groups": 361340 },1341 "placeholders_exact": {1342 "mean": 1.0,1343 "ci_low": 1.0,1344 "ci_high": 1.0,1345 "n_items": 83,1346 "n_groups": 361347 }1348 },1349 "B": {1350 "n": 83,1351 "chrf": {1352 "mean": 74.46485021822518,1353 "ci_low": 72.48484273310405,1354 "ci_high": 76.43768164450897,1355 "n_items": 83,1356 "n_groups": 371357 },1358 "edit_sim": {1359 "mean": 0.6231977456534893,1360 "ci_low": 0.6007951521191784,1361 "ci_high": 0.648778963231297,1362 "n_items": 83,1363 "n_groups": 371364 },1365 "rougeL": {1366 "mean": 0.6838430471901602,1367 "ci_low": 0.6591657200712578,1368 "ci_high": 0.7089500524886799,1369 "n_items": 83,1370 "n_groups": 371371 },1372 "exact_match": {1373 "mean": 0.0,1374 "ci_low": 0.0,1375 "ci_high": 0.0,1376 "n_items": 83,1377 "n_groups": 371378 },1379 "number_recall": {1380 "mean": 1.0,1381 "ci_low": 1.0,1382 "ci_high": 1.0,1383 "n_items": 83,1384 "n_groups": 371385 },1386 "placeholders_exact": {1387 "mean": 1.0,1388 "ci_low": 1.0,1389 "ci_high": 1.0,1390 "n_items": 83,1391 "n_groups": 371392 }1393 },1394 "C": {1395 "n": 84,1396 "chrf": {1397 "mean": 70.87948383858354,1398 "ci_low": 69.17992352046014,1399 "ci_high": 72.81035646129664,1400 "n_items": 84,1401 "n_groups": 381402 },1403 "edit_sim": {1404 "mean": 0.6364483980456039,1405 "ci_low": 0.6120799140760054,1406 "ci_high": 0.6632514752862443,1407 "n_items": 84,1408 "n_groups": 381409 },1410 "rougeL": {1411 "mean": 0.6839548079956678,1412 "ci_low": 0.6607162242742968,1413 "ci_high": 0.7086705182842311,1414 "n_items": 84,1415 "n_groups": 381416 },1417 "exact_match": {1418 "mean": 0.0,1419 "ci_low": 0.0,1420 "ci_high": 0.0,1421 "n_items": 84,1422 "n_groups": 381423 },1424 "number_recall": {1425 "mean": 1.0,1426 "ci_low": 1.0,1427 "ci_high": 1.0,1428 "n_items": 84,1429 "n_groups": 381430 },1431 "placeholders_exact": {1432 "mean": 1.0,1433 "ci_low": 1.0,1434 "ci_high": 1.0,1435 "n_items": 84,1436 "n_groups": 381437 }1438 },1439 "D": {1440 "n": 85,1441 "chrf": {1442 "mean": 65.4678771032133,1443 "ci_low": 63.77250861549224,1444 "ci_high": 67.22071310972167,1445 "n_items": 85,1446 "n_groups": 371447 },1448 "edit_sim": {1449 "mean": 0.5212264718802007,1450 "ci_low": 0.5008419311560566,1451 "ci_high": 0.5456043760455651,1452 "n_items": 85,1453 "n_groups": 371454 },1455 "rougeL": {1456 "mean": 0.5677359066590383,1457 "ci_low": 0.5445182864142464,1458 "ci_high": 0.5903869919269626,1459 "n_items": 85,1460 "n_groups": 371461 },1462 "exact_match": {1463 "mean": 0.0,1464 "ci_low": 0.0,1465 "ci_high": 0.0,1466 "n_items": 85,1467 "n_groups": 371468 },1469 "number_recall": {1470 "mean": 1.0,1471 "ci_low": 1.0,1472 "ci_high": 1.0,1473 "n_items": 85,1474 "n_groups": 371475 },1476 "placeholders_exact": {1477 "mean": 1.0,1478 "ci_low": 1.0,1479 "ci_high": 1.0,1480 "n_items": 85,1481 "n_groups": 371482 }1483 },1484 "E": {1485 "n": 167,1486 "chrf": {1487 "mean": 66.55618785407037,1488 "ci_low": 64.86656922543445,1489 "ci_high": 68.35755529924558,1490 "n_items": 167,1491 "n_groups": 381492 },1493 "edit_sim": {1494 "mean": 0.5323065026451008,1495 "ci_low": 0.5149282395041979,1496 "ci_high": 0.5499390471932212,1497 "n_items": 167,1498 "n_groups": 381499 },1500 "rougeL": {1501 "mean": 0.5805207295571821,1502 "ci_low": 0.5582366530338828,1503 "ci_high": 0.6014050232995725,1504 "n_items": 167,1505 "n_groups": 381506 },1507 "exact_match": {1508 "mean": 0.0,1509 "ci_low": 0.0,1510 "ci_high": 0.0,1511 "n_items": 167,1512 "n_groups": 381513 },1514 "number_recall": {1515 "mean": 1.0,1516 "ci_low": 1.0,1517 "ci_high": 1.0,1518 "n_items": 167,1519 "n_groups": 381520 },1521 "placeholders_exact": {1522 "mean": 1.0,1523 "ci_low": 1.0,1524 "ci_high": 1.0,1525 "n_items": 167,1526 "n_groups": 381527 }1528 }1529 },1530 "by_discipline": {1531 "biomedicine": {1532 "n": 184,1533 "chrf": {1534 "mean": 69.55811875605362,1535 "ci_low": 66.72176819715405,1536 "ci_high": 71.54726214280008,1537 "n_items": 184,1538 "n_groups": 191539 },1540 "edit_sim": {1541 "mean": 0.5733583390326791,1542 "ci_low": 0.5564335968415356,1543 "ci_high": 0.5964589313532669,1544 "n_items": 184,1545 "n_groups": 191546 },1547 "rougeL": {1548 "mean": 0.6302691678701969,1549 "ci_low": 0.5982787620358284,1550 "ci_high": 0.6535471260577799,1551 "n_items": 184,1552 "n_groups": 191553 },1554 "exact_match": {1555 "mean": 0.0,1556 "ci_low": 0.0,1557 "ci_high": 0.0,1558 "n_items": 184,1559 "n_groups": 191560 },1561 "number_recall": {1562 "mean": 1.0,1563 "ci_low": 1.0,1564 "ci_high": 1.0,1565 "n_items": 184,1566 "n_groups": 191567 },1568 "placeholders_exact": {1569 "mean": 1.0,1570 "ci_low": 1.0,1571 "ci_high": 1.0,1572 "n_items": 184,1573 "n_groups": 191574 }1575 },1576 "computer_science": {1577 "n": 53,1578 "chrf": {1579 "mean": 63.99075882233407,1580 "ci_low": 60.523596574797644,1581 "ci_high": 67.49527537073324,1582 "n_items": 53,1583 "n_groups": 31584 },1585 "edit_sim": {1586 "mean": 0.5151038952075662,1587 "ci_low": 0.4948253403107151,1588 "ci_high": 0.5691037974353317,1589 "n_items": 53,1590 "n_groups": 31591 },1592 "rougeL": {1593 "mean": 0.550292498941781,1594 "ci_low": 0.5237480855889659,1595 "ci_high": 0.6225605352197426,1596 "n_items": 53,1597 "n_groups": 31598 },1599 "exact_match": {1600 "mean": 0.0,1601 "ci_low": 0.0,1602 "ci_high": 0.0,1603 "n_items": 53,1604 "n_groups": 31605 },1606 "number_recall": {1607 "mean": 1.0,1608 "ci_low": 1.0,1609 "ci_high": 1.0,1610 "n_items": 53,1611 "n_groups": 31612 },1613 "placeholders_exact": {1614 "mean": 1.0,1615 "ci_low": 1.0,1616 "ci_high": 1.0,1617 "n_items": 53,1618 "n_groups": 31619 }1620 },1621 "earth_sciences": {1622 "n": 22,1623 "chrf": {1624 "mean": 71.13370699332951,1625 "ci_low": 71.13370699332951,1626 "ci_high": 71.13370699332951,1627 "n_items": 22,1628 "n_groups": 11629 },1630 "edit_sim": {1631 "mean": 0.5698303788619592,1632 "ci_low": 0.5698303788619592,1633 "ci_high": 0.5698303788619592,1634 "n_items": 22,1635 "n_groups": 11636 },1637 "rougeL": {1638 "mean": 0.6284606960502809,1639 "ci_low": 0.6284606960502809,1640 "ci_high": 0.6284606960502809,1641 "n_items": 22,1642 "n_groups": 11643 },1644 "exact_match": {1645 "mean": 0.0,1646 "ci_low": 0.0,1647 "ci_high": 0.0,1648 "n_items": 22,1649 "n_groups": 11650 },1651 "number_recall": {1652 "mean": 1.0,1653 "ci_low": 1.0,1654 "ci_high": 1.0,1655 "n_items": 22,1656 "n_groups": 11657 },1658 "placeholders_exact": {1659 "mean": 1.0,1660 "ci_low": 1.0,1661 "ci_high": 1.0,1662 "n_items": 22,1663 "n_groups": 11664 }1665 },1666 "engineering": {1667 "n": 45,1668 "chrf": {1669 "mean": 66.00603233138307,1670 "ci_low": 65.71788228073791,1671 "ci_high": 67.87900766057658,1672 "n_items": 45,1673 "n_groups": 21674 },1675 "edit_sim": {1676 "mean": 0.5050068411440728,1677 "ci_low": 0.5006608378080585,1678 "ci_high": 0.5332558628281662,1679 "n_items": 45,1680 "n_groups": 21681 },1682 "rougeL": {1683 "mean": 0.5684143969063395,1684 "ci_low": 0.565869725004619,1685 "ci_high": 0.5849547642675231,1686 "n_items": 45,1687 "n_groups": 21688 },1689 "exact_match": {1690 "mean": 0.0,1691 "ci_low": 0.0,1692 "ci_high": 0.0,1693 "n_items": 45,1694 "n_groups": 21695 },1696 "number_recall": {1697 "mean": 1.0,1698 "ci_low": 1.0,1699 "ci_high": 1.0,1700 "n_items": 45,1701 "n_groups": 21702 },1703 "placeholders_exact": {1704 "mean": 1.0,1705 "ci_low": 1.0,1706 "ci_high": 1.0,1707 "n_items": 45,1708 "n_groups": 21709 }1710 },1711 "life_sciences": {1712 "n": 144,1713 "chrf": {1714 "mean": 69.71647251134767,1715 "ci_low": 66.81412138891113,1716 "ci_high": 72.9197571258011,1717 "n_items": 144,1718 "n_groups": 131719 },1720 "edit_sim": {1721 "mean": 0.5835593277739309,1722 "ci_low": 0.5488492893335379,1723 "ci_high": 0.6132755735497472,1724 "n_items": 144,1725 "n_groups": 131726 },1727 "rougeL": {1728 "mean": 0.6261329191268302,1729 "ci_low": 0.5885128299489978,1730 "ci_high": 0.6635997818131015,1731 "n_items": 144,1732 "n_groups": 131733 },1734 "exact_match": {1735 "mean": 0.0,1736 "ci_low": 0.0,1737 "ci_high": 0.0,1738 "n_items": 144,1739 "n_groups": 131740 },1741 "number_recall": {1742 "mean": 1.0,1743 "ci_low": 1.0,1744 "ci_high": 1.0,1745 "n_items": 144,1746 "n_groups": 131747 },1748 "placeholders_exact": {1749 "mean": 1.0,1750 "ci_low": 1.0,1751 "ci_high": 1.0,1752 "n_items": 144,1753 "n_groups": 131754 }1755 },1756 "mathematics": {1757 "n": 54,1758 "chrf": {1759 "mean": 66.2911597863235,1760 "ci_low": 66.2911597863235,1761 "ci_high": 66.2911597863235,1762 "n_items": 54,1763 "n_groups": 11764 },1765 "edit_sim": {1766 "mean": 0.5474490132777297,1767 "ci_low": 0.5474490132777297,1768 "ci_high": 0.5474490132777297,1769 "n_items": 54,1770 "n_groups": 11771 },1772 "rougeL": {1773 "mean": 0.6015962075239264,1774 "ci_low": 0.6015962075239264,1775 "ci_high": 0.6015962075239264,1776 "n_items": 54,1777 "n_groups": 11778 },1779 "exact_match": {1780 "mean": 0.0,1781 "ci_low": 0.0,1782 "ci_high": 0.0,1783 "n_items": 54,1784 "n_groups": 11785 },1786 "number_recall": {1787 "mean": 1.0,1788 "ci_low": 1.0,1789 "ci_high": 1.0,1790 "n_items": 54,1791 "n_groups": 11792 },1793 "placeholders_exact": {1794 "mean": 1.0,1795 "ci_low": 1.0,1796 "ci_high": 1.0,1797 "n_items": 54,1798 "n_groups": 11799 }1800 }1801 },1802 "by_era": {1803 "1980-1999": {1804 "n": 16,1805 "chrf": {1806 "mean": 74.4831008660397,1807 "ci_low": 68.10448653022137,1808 "ci_high": 76.60930564464581,1809 "n_items": 16,1810 "n_groups": 21811 },1812 "edit_sim": {1813 "mean": 0.6258569172517547,1814 "ci_low": 0.5619422650219379,1815 "ci_high": 0.6471618013283603,1816 "n_items": 16,1817 "n_groups": 21818 },1819 "rougeL": {1820 "mean": 0.6837339309903148,1821 "ci_low": 0.6195279128857556,1822 "ci_high": 0.7051359370251679,1823 "n_items": 16,1824 "n_groups": 21825 },1826 "exact_match": {1827 "mean": 0.0,1828 "ci_low": 0.0,1829 "ci_high": 0.0,1830 "n_items": 16,1831 "n_groups": 21832 },1833 "number_recall": {1834 "mean": 1.0,1835 "ci_low": 1.0,1836 "ci_high": 1.0,1837 "n_items": 16,1838 "n_groups": 21839 },1840 "placeholders_exact": {1841 "mean": 1.0,1842 "ci_low": 1.0,1843 "ci_high": 1.0,1844 "n_items": 16,1845 "n_groups": 21846 }1847 },1848 "2000-2009": {1849 "n": 70,1850 "chrf": {1851 "mean": 69.7511720091413,1852 "ci_low": 62.85207539594276,1853 "ci_high": 70.39796231662865,1854 "n_items": 70,1855 "n_groups": 21856 },1857 "edit_sim": {1858 "mean": 0.5648510726364605,1859 "ci_low": 0.5637856418986429,1860 "ci_high": 0.5762156671731808,1861 "n_items": 70,1862 "n_groups": 21863 },1864 "rougeL": {1865 "mean": 0.6343833984597328,1866 "ci_low": 0.579129225583514,1867 "ci_high": 0.6395634771668781,1868 "n_items": 70,1869 "n_groups": 21870 },1871 "exact_match": {1872 "mean": 0.0,1873 "ci_low": 0.0,1874 "ci_high": 0.0,1875 "n_items": 70,1876 "n_groups": 21877 },1878 "number_recall": {1879 "mean": 1.0,1880 "ci_low": 1.0,1881 "ci_high": 1.0,1882 "n_items": 70,1883 "n_groups": 21884 },1885 "placeholders_exact": {1886 "mean": 1.0,1887 "ci_low": 1.0,1888 "ci_high": 1.0,1889 "n_items": 70,1890 "n_groups": 21891 }1892 },1893 "2010-2017": {1894 "n": 416,1895 "chrf": {1896 "mean": 67.95673099293766,1897 "ci_low": 66.41247640625778,1898 "ci_high": 69.78101316991065,1899 "n_items": 416,1900 "n_groups": 351901 },1902 "edit_sim": {1903 "mean": 0.5579363489671239,1904 "ci_low": 0.5402325934388691,1905 "ci_high": 0.5795079737158443,1906 "n_items": 416,1907 "n_groups": 351908 },1909 "rougeL": {1910 "mean": 0.6053907867270465,1911 "ci_low": 0.5853731490018689,1912 "ci_high": 0.6273880870113338,1913 "n_items": 416,1914 "n_groups": 351915 },1916 "exact_match": {1917 "mean": 0.0,1918 "ci_low": 0.0,1919 "ci_high": 0.0,1920 "n_items": 416,1921 "n_groups": 351922 },1923 "number_recall": {1924 "mean": 1.0,1925 "ci_low": 1.0,1926 "ci_high": 1.0,1927 "n_items": 416,1928 "n_groups": 351929 },1930 "placeholders_exact": {1931 "mean": 1.0,1932 "ci_low": 1.0,1933 "ci_high": 1.0,1934 "n_items": 416,1935 "n_groups": 351936 }1937 }1938 },1939 "by_role": {1940 "abstract": {1941 "n": 63,1942 "chrf": {1943 "mean": 68.99589124709463,1944 "ci_low": 67.21122335715242,1945 "ci_high": 71.53828467707339,1946 "n_items": 63,1947 "n_groups": 91948 },1949 "edit_sim": {1950 "mean": 0.5688909941154892,1951 "ci_low": 0.536541904383497,1952 "ci_high": 0.5940848732838352,1953 "n_items": 63,1954 "n_groups": 91955 },1956 "rougeL": {1957 "mean": 0.6276534004255929,1958 "ci_low": 0.587816189310633,1959 "ci_high": 0.6594244542046435,1960 "n_items": 63,1961 "n_groups": 91962 },1963 "exact_match": {1964 "mean": 0.0,1965 "ci_low": 0.0,1966 "ci_high": 0.0,1967 "n_items": 63,1968 "n_groups": 91969 },1970 "number_recall": {1971 "mean": 1.0,1972 "ci_low": 1.0,1973 "ci_high": 1.0,1974 "n_items": 63,1975 "n_groups": 91976 },1977 "placeholders_exact": {1978 "mean": 1.0,1979 "ci_low": 1.0,1980 "ci_high": 1.0,1981 "n_items": 63,1982 "n_groups": 91983 }1984 },1985 "background": {1986 "n": 22,1987 "chrf": {1988 "mean": 69.1272102583559,1989 "ci_low": 63.29616179895101,1990 "ci_high": 74.95825871776083,1991 "n_items": 22,1992 "n_groups": 41993 },1994 "edit_sim": {1995 "mean": 0.6047318606508599,1996 "ci_low": 0.5438018245248809,1997 "ci_high": 0.6656618967768391,1998 "n_items": 22,1999 "n_groups": 42000 },2001 "rougeL": {2002 "mean": 0.6375869858093672,2003 "ci_low": 0.5784404149005471,2004 "ci_high": 0.6967335567181874,2005 "n_items": 22,2006 "n_groups": 42007 },2008 "exact_match": {2009 "mean": 0.0,2010 "ci_low": 0.0,2011 "ci_high": 0.0,2012 "n_items": 22,2013 "n_groups": 42014 },2015 "number_recall": {2016 "mean": 1.0,2017 "ci_low": 1.0,2018 "ci_high": 1.0,2019 "n_items": 22,2020 "n_groups": 42021 },2022 "placeholders_exact": {2023 "mean": 1.0,2024 "ci_low": 1.0,2025 "ci_high": 1.0,2026 "n_items": 22,2027 "n_groups": 42028 }2029 },2030 "conclusion": {2031 "n": 60,2032 "chrf": {2033 "mean": 64.7327836698532,2034 "ci_low": 61.43778054901944,2035 "ci_high": 68.44320932837974,2036 "n_items": 60,2037 "n_groups": 92038 },2039 "edit_sim": {2040 "mean": 0.5354600602323661,2041 "ci_low": 0.5017101270370798,2042 "ci_high": 0.5712975561668697,2043 "n_items": 60,2044 "n_groups": 92045 },2046 "rougeL": {2047 "mean": 0.5802515714209402,2048 "ci_low": 0.5539809878213815,2049 "ci_high": 0.6126535784563463,2050 "n_items": 60,2051 "n_groups": 92052 },2053 "exact_match": {2054 "mean": 0.0,2055 "ci_low": 0.0,2056 "ci_high": 0.0,2057 "n_items": 60,2058 "n_groups": 92059 },2060 "number_recall": {2061 "mean": 1.0,2062 "ci_low": 1.0,2063 "ci_high": 1.0,2064 "n_items": 60,2065 "n_groups": 92066 },2067 "placeholders_exact": {2068 "mean": 1.0,2069 "ci_low": 1.0,2070 "ci_high": 1.0,2071 "n_items": 60,2072 "n_groups": 92073 }2074 },2075 "data": {2076 "n": 33,2077 "chrf": {2078 "mean": 72.00668367532082,2079 "ci_low": 67.45264254432394,2080 "ci_high": 75.73710786840466,2081 "n_items": 33,2082 "n_groups": 52083 },2084 "edit_sim": {2085 "mean": 0.5892450331339368,2086 "ci_low": 0.5498267969224073,2087 "ci_high": 0.6220935633102116,2088 "n_items": 33,2089 "n_groups": 52090 },2091 "rougeL": {2092 "mean": 0.6634347731602546,2093 "ci_low": 0.607064907546156,2094 "ci_high": 0.7117451843440367,2095 "n_items": 33,2096 "n_groups": 52097 },2098 "exact_match": {2099 "mean": 0.0,2100 "ci_low": 0.0,2101 "ci_high": 0.0,2102 "n_items": 33,2103 "n_groups": 52104 },2105 "number_recall": {2106 "mean": 1.0,2107 "ci_low": 1.0,2108 "ci_high": 1.0,2109 "n_items": 33,2110 "n_groups": 52111 },2112 "placeholders_exact": {2113 "mean": 1.0,2114 "ci_low": 1.0,2115 "ci_high": 1.0,2116 "n_items": 33,2117 "n_groups": 52118 }2119 },2120 "discussion": {2121 "n": 60,2122 "chrf": {2123 "mean": 65.22450967183414,2124 "ci_low": 63.08413233519539,2125 "ci_high": 67.01450915210013,2126 "n_items": 60,2127 "n_groups": 72128 },2129 "edit_sim": {2130 "mean": 0.538932415930476,2131 "ci_low": 0.5059555901709601,2132 "ci_high": 0.5814326444707776,2133 "n_items": 60,2134 "n_groups": 72135 },2136 "rougeL": {2137 "mean": 0.5673813529566215,2138 "ci_low": 0.5375355143605095,2139 "ci_high": 0.5983043873307661,2140 "n_items": 60,2141 "n_groups": 72142 },2143 "exact_match": {2144 "mean": 0.0,2145 "ci_low": 0.0,2146 "ci_high": 0.0,2147 "n_items": 60,2148 "n_groups": 72149 },2150 "number_recall": {2151 "mean": 1.0,2152 "ci_low": 1.0,2153 "ci_high": 1.0,2154 "n_items": 60,2155 "n_groups": 72156 },2157 "placeholders_exact": {2158 "mean": 1.0,2159 "ci_low": 1.0,2160 "ci_high": 1.0,2161 "n_items": 60,2162 "n_groups": 72163 }2164 },2165 "introduction": {2166 "n": 56,2167 "chrf": {2168 "mean": 67.18246757817609,2169 "ci_low": 65.03762856788411,2170 "ci_high": 69.58773138098087,2171 "n_items": 56,2172 "n_groups": 92173 },2174 "edit_sim": {2175 "mean": 0.5391186797874457,2176 "ci_low": 0.5165800996876023,2177 "ci_high": 0.5660015361246413,2178 "n_items": 56,2179 "n_groups": 92180 },2181 "rougeL": {2182 "mean": 0.58522280976924,2183 "ci_low": 0.5653601625759967,2184 "ci_high": 0.6077419995446028,2185 "n_items": 56,2186 "n_groups": 92187 },2188 "exact_match": {2189 "mean": 0.0,2190 "ci_low": 0.0,2191 "ci_high": 0.0,2192 "n_items": 56,2193 "n_groups": 92194 },2195 "number_recall": {2196 "mean": 1.0,2197 "ci_low": 1.0,2198 "ci_high": 1.0,2199 "n_items": 56,2200 "n_groups": 92201 },2202 "placeholders_exact": {2203 "mean": 1.0,2204 "ci_low": 1.0,2205 "ci_high": 1.0,2206 "n_items": 56,2207 "n_groups": 92208 }2209 },2210 "limitations": {2211 "n": 12,2212 "chrf": {2213 "mean": 62.90710820532765,2214 "ci_low": 62.47589668641524,2215 "ci_high": 63.33831972424006,2216 "n_items": 12,2217 "n_groups": 22218 },2219 "edit_sim": {2220 "mean": 0.5186641133940276,2221 "ci_low": 0.49868391456451927,2222 "ci_high": 0.5386443122235359,2223 "n_items": 12,2224 "n_groups": 22225 },2226 "rougeL": {2227 "mean": 0.5642058440270518,2228 "ci_low": 0.5549081392428828,2229 "ci_high": 0.573503548811221,2230 "n_items": 12,2231 "n_groups": 22232 },2233 "exact_match": {2234 "mean": 0.0,2235 "ci_low": 0.0,2236 "ci_high": 0.0,2237 "n_items": 12,2238 "n_groups": 22239 },2240 "number_recall": {2241 "mean": 1.0,2242 "ci_low": 1.0,2243 "ci_high": 1.0,2244 "n_items": 12,2245 "n_groups": 22246 },2247 "placeholders_exact": {2248 "mean": 1.0,2249 "ci_low": 1.0,2250 "ci_high": 1.0,2251 "n_items": 12,2252 "n_groups": 22253 }2254 },2255 "methods": {2256 "n": 69,2257 "chrf": {2258 "mean": 71.53691042793893,2259 "ci_low": 67.59048054965476,2260 "ci_high": 75.38903308729738,2261 "n_items": 69,2262 "n_groups": 112263 },2264 "edit_sim": {2265 "mean": 0.5962452166089098,2266 "ci_low": 0.554992933777329,2267 "ci_high": 0.6451926249069851,2268 "n_items": 69,2269 "n_groups": 112270 },2271 "rougeL": {2272 "mean": 0.654191974190857,2273 "ci_low": 0.601382778396698,2274 "ci_high": 0.7063338535257487,2275 "n_items": 69,2276 "n_groups": 112277 },2278 "exact_match": {2279 "mean": 0.0,2280 "ci_low": 0.0,2281 "ci_high": 0.0,2282 "n_items": 69,2283 "n_groups": 112284 },2285 "number_recall": {2286 "mean": 1.0,2287 "ci_low": 1.0,2288 "ci_high": 1.0,2289 "n_items": 69,2290 "n_groups": 112291 },2292 "placeholders_exact": {2293 "mean": 1.0,2294 "ci_low": 1.0,2295 "ci_high": 1.0,2296 "n_items": 69,2297 "n_groups": 112298 }2299 },2300 "other": {2301 "n": 32,2302 "chrf": {2303 "mean": 75.57511180963655,2304 "ci_low": 71.2945271204087,2305 "ci_high": 79.4709192420226,2306 "n_items": 32,2307 "n_groups": 52308 },2309 "edit_sim": {2310 "mean": 0.576949721271589,2311 "ci_low": 0.5327236980561744,2312 "ci_high": 0.6229230224775087,2313 "n_items": 32,2314 "n_groups": 52315 },2316 "rougeL": {2317 "mean": 0.6492314487447789,2318 "ci_low": 0.5889023907208442,2319 "ci_high": 0.7010623779871381,2320 "n_items": 32,2321 "n_groups": 52322 },2323 "exact_match": {2324 "mean": 0.0,2325 "ci_low": 0.0,2326 "ci_high": 0.0,2327 "n_items": 32,2328 "n_groups": 52329 },2330 "number_recall": {2331 "mean": 1.0,2332 "ci_low": 1.0,2333 "ci_high": 1.0,2334 "n_items": 32,2335 "n_groups": 52336 },2337 "placeholders_exact": {2338 "mean": 1.0,2339 "ci_low": 1.0,2340 "ci_high": 1.0,2341 "n_items": 32,2342 "n_groups": 52343 }2344 },2345 "related_work": {2346 "n": 6,2347 "chrf": {2348 "mean": 72.84593201110854,2349 "ci_low": 72.84593201110854,2350 "ci_high": 72.84593201110854,2351 "n_items": 6,2352 "n_groups": 12353 },2354 "edit_sim": {2355 "mean": 0.6771611111463544,2356 "ci_low": 0.6771611111463544,2357 "ci_high": 0.6771611111463544,2358 "n_items": 6,2359 "n_groups": 12360 },2361 "rougeL": {2362 "mean": 0.7252386739976376,2363 "ci_low": 0.7252386739976376,2364 "ci_high": 0.7252386739976376,2365 "n_items": 6,2366 "n_groups": 12367 },2368 "exact_match": {2369 "mean": 0.0,2370 "ci_low": 0.0,2371 "ci_high": 0.0,2372 "n_items": 6,2373 "n_groups": 12374 },2375 "number_recall": {2376 "mean": 1.0,2377 "ci_low": 1.0,2378 "ci_high": 1.0,2379 "n_items": 6,2380 "n_groups": 12381 },2382 "placeholders_exact": {2383 "mean": 1.0,2384 "ci_low": 1.0,2385 "ci_high": 1.0,2386 "n_items": 6,2387 "n_groups": 12388 }2389 },2390 "results": {2391 "n": 62,2392 "chrf": {2393 "mean": 66.44544476443677,2394 "ci_low": 63.38340030626309,2395 "ci_high": 69.6442978673028,2396 "n_items": 62,2397 "n_groups": 82398 },2399 "edit_sim": {2400 "mean": 0.5179112266140106,2401 "ci_low": 0.483249733583908,2402 "ci_high": 0.5552097626741724,2403 "n_items": 62,2404 "n_groups": 82405 },2406 "rougeL": {2407 "mean": 0.5798254953743093,2408 "ci_low": 0.540225996406992,2409 "ci_high": 0.6243959880924234,2410 "n_items": 62,2411 "n_groups": 82412 },2413 "exact_match": {2414 "mean": 0.0,2415 "ci_low": 0.0,2416 "ci_high": 0.0,2417 "n_items": 62,2418 "n_groups": 82419 },2420 "number_recall": {2421 "mean": 1.0,2422 "ci_low": 1.0,2423 "ci_high": 1.0,2424 "n_items": 62,2425 "n_groups": 82426 },2427 "placeholders_exact": {2428 "mean": 1.0,2429 "ci_low": 1.0,2430 "ci_high": 1.0,2431 "n_items": 62,2432 "n_groups": 82433 }2434 },2435 "theory": {2436 "n": 27,2437 "chrf": {2438 "mean": 69.43950976967757,2439 "ci_low": 67.27890236074487,2440 "ci_high": 74.09555882155192,2441 "n_items": 27,2442 "n_groups": 42443 },2444 "edit_sim": {2445 "mean": 0.6077981308015153,2446 "ci_low": 0.5503962942365649,2447 "ci_high": 0.6692852221112914,2448 "n_items": 27,2449 "n_groups": 42450 },2451 "rougeL": {2452 "mean": 0.6337234949377781,2453 "ci_low": 0.5573176222058711,2454 "ci_high": 0.708161971443909,2455 "n_items": 27,2456 "n_groups": 42457 },2458 "exact_match": {2459 "mean": 0.0,2460 "ci_low": 0.0,2461 "ci_high": 0.0,2462 "n_items": 27,2463 "n_groups": 42464 },2465 "number_recall": {2466 "mean": 1.0,2467 "ci_low": 1.0,2468 "ci_high": 1.0,2469 "n_items": 27,2470 "n_groups": 42471 },2472 "placeholders_exact": {2473 "mean": 1.0,2474 "ci_low": 1.0,2475 "ci_high": 1.0,2476 "n_items": 27,2477 "n_groups": 42478 }2479 }2480 }2481 },2482 "B2_t5-small": {2483 "overall": {2484 "n": 502,2485 "chrf": {2486 "mean": 68.84869127039843,2487 "ci_low": 67.66116434333608,2488 "ci_high": 69.94403713118699,2489 "n_items": 502,2490 "n_groups": 392491 },2492 "edit_sim": {2493 "mean": 0.6384676336752433,2494 "ci_low": 0.6205640844108342,2495 "ci_high": 0.6571890686078552,2496 "n_items": 502,2497 "n_groups": 392498 },2499 "rougeL": {2500 "mean": 0.6710300417541715,2501 "ci_low": 0.6535888213131146,2502 "ci_high": 0.687249014416098,2503 "n_items": 502,2504 "n_groups": 392505 },2506 "exact_match": {2507 "mean": 0.0,2508 "ci_low": 0.0,2509 "ci_high": 0.0,2510 "n_items": 502,2511 "n_groups": 392512 },2513 "number_recall": {2514 "mean": 0.9448681705725623,2515 "ci_low": 0.918843434547651,2516 "ci_high": 0.9692864074480885,2517 "n_items": 502,2518 "n_groups": 392519 },2520 "placeholders_exact": {2521 "mean": 0.6912350597609562,2522 "ci_low": 0.5846795699528408,2523 "ci_high": 0.7865244752199285,2524 "n_items": 502,2525 "n_groups": 392526 }2527 },2528 "by_variant": {2529 "A": {2530 "n": 83,2531 "chrf": {2532 "mean": 67.98318573107532,2533 "ci_low": 66.69174280082973,2534 "ci_high": 69.26296102665752,2535 "n_items": 83,2536 "n_groups": 362537 },2538 "edit_sim": {2539 "mean": 0.6178477743511694,2540 "ci_low": 0.5950226364815355,2541 "ci_high": 0.6411703127995071,2542 "n_items": 83,2543 "n_groups": 362544 },2545 "rougeL": {2546 "mean": 0.6495108886670681,2547 "ci_low": 0.6282922978075788,2548 "ci_high": 0.668678477577094,2549 "n_items": 83,2550 "n_groups": 362551 },2552 "exact_match": {2553 "mean": 0.0,2554 "ci_low": 0.0,2555 "ci_high": 0.0,2556 "n_items": 83,2557 "n_groups": 362558 },2559 "number_recall": {2560 "mean": 0.9435118031230388,2561 "ci_low": 0.9107814722863407,2562 "ci_high": 0.974025298157506,2563 "n_items": 83,2564 "n_groups": 362565 },2566 "placeholders_exact": {2567 "mean": 0.6987951807228916,2568 "ci_low": 0.5890209508460919,2569 "ci_high": 0.7954545454545454,2570 "n_items": 83,2571 "n_groups": 362572 }2573 },2574 "B": {2575 "n": 83,2576 "chrf": {2577 "mean": 73.31058068524277,2578 "ci_low": 71.8518368644048,2579 "ci_high": 74.65374776397742,2580 "n_items": 83,2581 "n_groups": 372582 },2583 "edit_sim": {2584 "mean": 0.7023233772419402,2585 "ci_low": 0.6789924725534436,2586 "ci_high": 0.7272004612375648,2587 "n_items": 83,2588 "n_groups": 372589 },2590 "rougeL": {2591 "mean": 0.7329190876494731,2592 "ci_low": 0.7118811882091722,2593 "ci_high": 0.7532590426322497,2594 "n_items": 83,2595 "n_groups": 372596 },2597 "exact_match": {2598 "mean": 0.0,2599 "ci_low": 0.0,2600 "ci_high": 0.0,2601 "n_items": 83,2602 "n_groups": 372603 },2604 "number_recall": {2605 "mean": 0.9361197546081269,2606 "ci_low": 0.9024673200222543,2607 "ci_high": 0.9696938892119188,2608 "n_items": 83,2609 "n_groups": 372610 },2611 "placeholders_exact": {2612 "mean": 0.7108433734939759,2613 "ci_low": 0.6049310938845823,2614 "ci_high": 0.8026315789473685,2615 "n_items": 83,2616 "n_groups": 372617 }2618 },2619 "C": {2620 "n": 84,2621 "chrf": {2622 "mean": 70.33405792789534,2623 "ci_low": 69.24118167415475,2624 "ci_high": 71.44892213138883,2625 "n_items": 84,2626 "n_groups": 382627 },2628 "edit_sim": {2629 "mean": 0.6845538386596853,2630 "ci_low": 0.661906768949646,2631 "ci_high": 0.7063412017780726,2632 "n_items": 84,2633 "n_groups": 382634 },2635 "rougeL": {2636 "mean": 0.7195516704834948,2637 "ci_low": 0.7012939807144101,2638 "ci_high": 0.7363466292677431,2639 "n_items": 84,2640 "n_groups": 382641 },2642 "exact_match": {2643 "mean": 0.0,2644 "ci_low": 0.0,2645 "ci_high": 0.0,2646 "n_items": 84,2647 "n_groups": 382648 },2649 "number_recall": {2650 "mean": 0.9601494284010895,2651 "ci_low": 0.9282442330137481,2652 "ci_high": 0.9873745316633249,2653 "n_items": 84,2654 "n_groups": 382655 },2656 "placeholders_exact": {2657 "mean": 0.6785714285714286,2658 "ci_low": 0.5769230769230769,2659 "ci_high": 0.7792207792207793,2660 "n_items": 84,2661 "n_groups": 382662 }2663 },2664 "D": {2665 "n": 85,2666 "chrf": {2667 "mean": 66.89419219890566,2668 "ci_low": 65.33299880451007,2669 "ci_high": 68.46367918357788,2670 "n_items": 85,2671 "n_groups": 372672 },2673 "edit_sim": {2674 "mean": 0.597316112374439,2675 "ci_low": 0.5755000044454562,2676 "ci_high": 0.6202724251039127,2677 "n_items": 85,2678 "n_groups": 372679 },2680 "rougeL": {2681 "mean": 0.6330556827001014,2682 "ci_low": 0.6138239315785531,2683 "ci_high": 0.653089206442082,2684 "n_items": 85,2685 "n_groups": 372686 },2687 "exact_match": {2688 "mean": 0.0,2689 "ci_low": 0.0,2690 "ci_high": 0.0,2691 "n_items": 85,2692 "n_groups": 372693 },2694 "number_recall": {2695 "mean": 0.9479871047251349,2696 "ci_low": 0.9224099681814791,2697 "ci_high": 0.9731215475404337,2698 "n_items": 85,2699 "n_groups": 372700 },2701 "placeholders_exact": {2702 "mean": 0.6705882352941176,2703 "ci_low": 0.5595063025210084,2704 "ci_high": 0.7681203605514315,2705 "n_items": 85,2706 "n_groups": 372707 }2708 },2709 "E": {2710 "n": 167,2711 "chrf": {2712 "mean": 67.30894133134984,2713 "ci_low": 66.04680638649934,2714 "ci_high": 68.50532509972109,2715 "n_items": 167,2716 "n_groups": 382717 },2718 "edit_sim": {2719 "mean": 0.6147434402604981,2720 "ci_low": 0.597411297005053,2721 "ci_high": 0.6337943592833476,2722 "n_items": 167,2723 "n_groups": 382724 },2725 "rougeL": {2726 "mean": 0.6458881411748446,2727 "ci_low": 0.6278829117088456,2728 "ci_high": 0.6634248382769834,2729 "n_items": 167,2730 "n_groups": 382731 },2732 "exact_match": {2733 "mean": 0.0,2734 "ci_low": 0.0,2735 "ci_high": 0.0,2736 "n_items": 167,2737 "n_groups": 382738 },2739 "number_recall": {2740 "mean": 0.9406164457988717,2741 "ci_low": 0.9153174491291493,2742 "ci_high": 0.9654471007438198,2743 "n_items": 167,2744 "n_groups": 382745 },2746 "placeholders_exact": {2747 "mean": 0.6946107784431138,2748 "ci_low": 0.585705574912892,2749 "ci_high": 0.7902126099706744,2750 "n_items": 167,2751 "n_groups": 382752 }2753 }2754 },2755 "by_discipline": {2756 "biomedicine": {2757 "n": 184,2758 "chrf": {2759 "mean": 69.31797191979842,2760 "ci_low": 67.11263516120505,2761 "ci_high": 70.48695676325372,2762 "n_items": 184,2763 "n_groups": 192764 },2765 "edit_sim": {2766 "mean": 0.6461918424152698,2767 "ci_low": 0.6261631210782476,2768 "ci_high": 0.6721212487704998,2769 "n_items": 184,2770 "n_groups": 192771 },2772 "rougeL": {2773 "mean": 0.6814753478310017,2774 "ci_low": 0.6564317246181692,2775 "ci_high": 0.6980019038989655,2776 "n_items": 184,2777 "n_groups": 192778 },2779 "exact_match": {2780 "mean": 0.0,2781 "ci_low": 0.0,2782 "ci_high": 0.0,2783 "n_items": 184,2784 "n_groups": 192785 },2786 "number_recall": {2787 "mean": 0.9571493929026791,2788 "ci_low": 0.8915117578297468,2789 "ci_high": 0.9961038961038962,2790 "n_items": 184,2791 "n_groups": 192792 },2793 "placeholders_exact": {2794 "mean": 0.6521739130434783,2795 "ci_low": 0.42990268015756544,2796 "ci_high": 0.7786275184582655,2797 "n_items": 184,2798 "n_groups": 192799 }2800 },2801 "computer_science": {2802 "n": 53,2803 "chrf": {2804 "mean": 66.71642494904157,2805 "ci_low": 64.14526007095762,2806 "ci_high": 69.92935728081719,2807 "n_items": 53,2808 "n_groups": 32809 },2810 "edit_sim": {2811 "mean": 0.6306459139332519,2812 "ci_low": 0.6090374988909681,2813 "ci_high": 0.654661657837377,2814 "n_items": 53,2815 "n_groups": 32816 },2817 "rougeL": {2818 "mean": 0.6508402523835498,2819 "ci_low": 0.6088729553019402,2820 "ci_high": 0.685094785151113,2821 "n_items": 53,2822 "n_groups": 32823 },2824 "exact_match": {2825 "mean": 0.0,2826 "ci_low": 0.0,2827 "ci_high": 0.0,2828 "n_items": 53,2829 "n_groups": 32830 },2831 "number_recall": {2832 "mean": 0.8930817610062892,2833 "ci_low": 0.8260869565217391,2834 "ci_high": 0.9583333333333334,2835 "n_items": 53,2836 "n_groups": 32837 },2838 "placeholders_exact": {2839 "mean": 0.8867924528301887,2840 "ci_low": 0.75,2841 "ci_high": 1.0,2842 "n_items": 53,2843 "n_groups": 32844 }2845 },2846 "earth_sciences": {2847 "n": 22,2848 "chrf": {2849 "mean": 73.26212355763131,2850 "ci_low": 73.26212355763131,2851 "ci_high": 73.26212355763131,2852 "n_items": 22,2853 "n_groups": 12854 },2855 "edit_sim": {2856 "mean": 0.6783428947867072,2857 "ci_low": 0.6783428947867072,2858 "ci_high": 0.6783428947867072,2859 "n_items": 22,2860 "n_groups": 12861 },2862 "rougeL": {2863 "mean": 0.7223120252991394,2864 "ci_low": 0.7223120252991394,2865 "ci_high": 0.7223120252991394,2866 "n_items": 22,2867 "n_groups": 12868 },2869 "exact_match": {2870 "mean": 0.0,2871 "ci_low": 0.0,2872 "ci_high": 0.0,2873 "n_items": 22,2874 "n_groups": 12875 },2876 "number_recall": {2877 "mean": 0.9545454545454546,2878 "ci_low": 0.9545454545454546,2879 "ci_high": 0.9545454545454546,2880 "n_items": 22,2881 "n_groups": 12882 },2883 "placeholders_exact": {2884 "mean": 0.6363636363636364,2885 "ci_low": 0.6363636363636364,2886 "ci_high": 0.6363636363636364,2887 "n_items": 22,2888 "n_groups": 12889 }2890 },2891 "engineering": {2892 "n": 45,2893 "chrf": {2894 "mean": 65.51898317469568,2895 "ci_low": 65.14209631148071,2896 "ci_high": 67.96874778559294,2897 "n_items": 45,2898 "n_groups": 22899 },2900 "edit_sim": {2901 "mean": 0.5494086718720823,2902 "ci_low": 0.5424918163120709,2903 "ci_high": 0.5943682330121566,2904 "n_items": 45,2905 "n_groups": 22906 },2907 "rougeL": {2908 "mean": 0.6010134593473906,2909 "ci_low": 0.5925660571281129,2910 "ci_high": 0.6559215737726959,2911 "n_items": 45,2912 "n_groups": 22913 },2914 "exact_match": {2915 "mean": 0.0,2916 "ci_low": 0.0,2917 "ci_high": 0.0,2918 "n_items": 45,2919 "n_groups": 22920 },2921 "number_recall": {2922 "mean": 0.9620370370370371,2923 "ci_low": 0.9444444444444445,2924 "ci_high": 0.9647435897435898,2925 "n_items": 45,2926 "n_groups": 22927 },2928 "placeholders_exact": {2929 "mean": 0.5333333333333333,2930 "ci_low": 0.46153846153846156,2931 "ci_high": 1.0,2932 "n_items": 45,2933 "n_groups": 22934 }2935 },2936 "life_sciences": {2937 "n": 144,2938 "chrf": {2939 "mean": 69.22450159285926,2940 "ci_low": 67.70697224117633,2941 "ci_high": 71.54131366974036,2942 "n_items": 144,2943 "n_groups": 132944 },2945 "edit_sim": {2946 "mean": 0.6538168537550614,2947 "ci_low": 0.6314093232391641,2948 "ci_high": 0.6919656316272309,2949 "n_items": 144,2950 "n_groups": 132951 },2952 "rougeL": {2953 "mean": 0.6797363994911884,2954 "ci_low": 0.6596424592225952,2955 "ci_high": 0.7094324350665436,2956 "n_items": 144,2957 "n_groups": 132958 },2959 "exact_match": {2960 "mean": 0.0,2961 "ci_low": 0.0,2962 "ci_high": 0.0,2963 "n_items": 144,2964 "n_groups": 132965 },2966 "number_recall": {2967 "mean": 0.958829365079365,2968 "ci_low": 0.9223723282068521,2969 "ci_high": 0.9919354838709677,2970 "n_items": 144,2971 "n_groups": 132972 },2973 "placeholders_exact": {2974 "mean": 0.6666666666666666,2975 "ci_low": 0.4817980437284235,2976 "ci_high": 0.9213728591687574,2977 "n_items": 144,2978 "n_groups": 132979 }2980 },2981 "mathematics": {2982 "n": 54,2983 "chrf": {2984 "mean": 69.31697169809208,2985 "ci_low": 69.31697169809208,2986 "ci_high": 69.31697169809208,2987 "n_items": 54,2988 "n_groups": 12989 },2990 "edit_sim": {2991 "mean": 0.6368640518855568,2992 "ci_low": 0.6368640518855568,2993 "ci_high": 0.6368640518855568,2994 "n_items": 54,2995 "n_groups": 12996 },2997 "rougeL": {2998 "mean": 0.6694920709151281,2999 "ci_low": 0.6694920709151281,3000 "ci_high": 0.6694920709151281,3001 "n_items": 54,3002 "n_groups": 13003 },3004 "exact_match": {3005 "mean": 0.0,3006 "ci_low": 0.0,3007 "ci_high": 0.0,3008 "n_items": 54,3009 "n_groups": 13010 },3011 "number_recall": {3012 "mean": 0.89836860670194,3013 "ci_low": 0.89836860670194,3014 "ci_high": 0.89836860670194,3015 "n_items": 54,3016 "n_groups": 13017 },3018 "placeholders_exact": {3019 "mean": 0.8518518518518519,3020 "ci_low": 0.8518518518518519,3021 "ci_high": 0.8518518518518519,3022 "n_items": 54,3023 "n_groups": 13024 }3025 }3026 },3027 "by_era": {3028 "1980-1999": {3029 "n": 16,3030 "chrf": {3031 "mean": 70.91154332247825,3032 "ci_low": 67.10003424301172,3033 "ci_high": 72.18204634896709,3034 "n_items": 16,3035 "n_groups": 23036 },3037 "edit_sim": {3038 "mean": 0.6657283973056335,3039 "ci_low": 0.6247688275511325,3040 "ci_high": 0.6793815872238005,3041 "n_items": 16,3042 "n_groups": 23043 },3044 "rougeL": {3045 "mean": 0.7098664160203574,3046 "ci_low": 0.6641552173246086,3047 "ci_high": 0.7251034822522735,3048 "n_items": 16,3049 "n_groups": 23050 },3051 "exact_match": {3052 "mean": 0.0,3053 "ci_low": 0.0,3054 "ci_high": 0.0,3055 "n_items": 16,3056 "n_groups": 23057 },3058 "number_recall": {3059 "mean": 0.9821428571428572,3060 "ci_low": 0.9761904761904763,3061 "ci_high": 1.0,3062 "n_items": 16,3063 "n_groups": 23064 },3065 "placeholders_exact": {3066 "mean": 0.625,3067 "ci_low": 0.5,3068 "ci_high": 1.0,3069 "n_items": 16,3070 "n_groups": 23071 }3072 },3073 "2000-2009": {3074 "n": 70,3075 "chrf": {3076 "mean": 69.93885121597579,3077 "ci_low": 65.59562830410216,3078 "ci_high": 70.34602836396394,3079 "n_items": 70,3080 "n_groups": 23081 },3082 "edit_sim": {3083 "mean": 0.631332678794729,3084 "ci_low": 0.5707434052757794,3085 "ci_high": 0.6370129231871305,3086 "n_items": 70,3087 "n_groups": 23088 },3089 "rougeL": {3090 "mean": 0.6822433304921326,3091 "ci_low": 0.6187534897862957,3092 "ci_high": 0.6881955030583047,3093 "n_items": 70,3094 "n_groups": 23095 },3096 "exact_match": {3097 "mean": 0.0,3098 "ci_low": 0.0,3099 "ci_high": 0.0,3100 "n_items": 70,3101 "n_groups": 23102 },3103 "number_recall": {3104 "mean": 0.9674695103266532,3105 "ci_low": 0.9644197769197769,3106 "ci_high": 1.0,3107 "n_items": 70,3108 "n_groups": 23109 },3110 "placeholders_exact": {3111 "mean": 0.8285714285714286,3112 "ci_low": 0.8125,3113 "ci_high": 1.0,3114 "n_items": 70,3115 "n_groups": 23116 }3117 },3118 "2010-2017": {3119 "n": 416,3120 "chrf": {3121 "mean": 68.58591043139917,3122 "ci_low": 67.37121270385508,3123 "ci_high": 69.8596313466302,3124 "n_items": 416,3125 "n_groups": 353126 },3127 "edit_sim": {3128 "mean": 0.6386197361356994,3129 "ci_low": 0.6170997505921862,3130 "ci_high": 0.6605293205805717,3131 "n_items": 416,3132 "n_groups": 353133 },3134 "rougeL": {3135 "mean": 0.667649483581296,3136 "ci_low": 0.6495119730443278,3137 "ci_high": 0.6869778601084262,3138 "n_items": 416,3139 "n_groups": 353140 },3141 "exact_match": {3142 "mean": 0.0,3143 "ci_low": 0.0,3144 "ci_high": 0.0,3145 "n_items": 416,3146 "n_groups": 353147 },3148 "number_recall": {3149 "mean": 0.9396314187266223,3150 "ci_low": 0.9089139767806422,3151 "ci_high": 0.9676848571075741,3152 "n_items": 416,3153 "n_groups": 353154 },3155 "placeholders_exact": {3156 "mean": 0.6706730769230769,3157 "ci_low": 0.5566953508846667,3158 "ci_high": 0.7819711466809741,3159 "n_items": 416,3160 "n_groups": 353161 }3162 }3163 },3164 "by_role": {3165 "abstract": {3166 "n": 63,3167 "chrf": {3168 "mean": 70.02868370723843,3169 "ci_low": 67.96908066550209,3170 "ci_high": 72.06767893375712,3171 "n_items": 63,3172 "n_groups": 93173 },3174 "edit_sim": {3175 "mean": 0.6475979635479585,3176 "ci_low": 0.6147737898387473,3177 "ci_high": 0.6803305419172674,3178 "n_items": 63,3179 "n_groups": 93180 },3181 "rougeL": {3182 "mean": 0.6809860912960237,3183 "ci_low": 0.6506750756742123,3184 "ci_high": 0.7065091326319418,3185 "n_items": 63,3186 "n_groups": 93187 },3188 "exact_match": {3189 "mean": 0.0,3190 "ci_low": 0.0,3191 "ci_high": 0.0,3192 "n_items": 63,3193 "n_groups": 93194 },3195 "number_recall": {3196 "mean": 0.8867460317460316,3197 "ci_low": 0.7825287356321838,3198 "ci_high": 0.9981343283582089,3199 "n_items": 63,3200 "n_groups": 93201 },3202 "placeholders_exact": {3203 "mean": 0.9047619047619048,3204 "ci_low": 0.6896551724137931,3205 "ci_high": 1.0,3206 "n_items": 63,3207 "n_groups": 93208 }3209 },3210 "background": {3211 "n": 22,3212 "chrf": {3213 "mean": 62.656485978795416,3214 "ci_low": 55.49719559226832,3215 "ci_high": 70.30735707287307,3216 "n_items": 22,3217 "n_groups": 43218 },3219 "edit_sim": {3220 "mean": 0.5639307240712715,3221 "ci_low": 0.48321091224871243,3222 "ci_high": 0.6530408436687904,3223 "n_items": 22,3224 "n_groups": 43225 },3226 "rougeL": {3227 "mean": 0.6040828574416105,3228 "ci_low": 0.5540079624012754,3229 "ci_high": 0.6627436840154615,3230 "n_items": 22,3231 "n_groups": 43232 },3233 "exact_match": {3234 "mean": 0.0,3235 "ci_low": 0.0,3236 "ci_high": 0.0,3237 "n_items": 22,3238 "n_groups": 43239 },3240 "number_recall": {3241 "mean": 0.8874458874458875,3242 "ci_low": 0.7204968944099378,3243 "ci_high": 1.0,3244 "n_items": 22,3245 "n_groups": 43246 },3247 "placeholders_exact": {3248 "mean": 0.22727272727272727,3249 "ci_low": 0.0,3250 "ci_high": 0.7142857142857143,3251 "n_items": 22,3252 "n_groups": 43253 }3254 },3255 "conclusion": {3256 "n": 60,3257 "chrf": {3258 "mean": 66.30075618626606,3259 "ci_low": 63.493381004454285,3260 "ci_high": 69.3793377926901,3261 "n_items": 60,3262 "n_groups": 93263 },3264 "edit_sim": {3265 "mean": 0.5994362020461839,3266 "ci_low": 0.5639947020749013,3267 "ci_high": 0.6345318294665634,3268 "n_items": 60,3269 "n_groups": 93270 },3271 "rougeL": {3272 "mean": 0.6383496737991544,3273 "ci_low": 0.6086338744417098,3274 "ci_high": 0.6669585605526095,3275 "n_items": 60,3276 "n_groups": 93277 },3278 "exact_match": {3279 "mean": 0.0,3280 "ci_low": 0.0,3281 "ci_high": 0.0,3282 "n_items": 60,3283 "n_groups": 93284 },3285 "number_recall": {3286 "mean": 0.98,3287 "ci_low": 0.9407407407407407,3288 "ci_high": 1.0,3289 "n_items": 60,3290 "n_groups": 93291 },3292 "placeholders_exact": {3293 "mean": 0.8833333333333333,3294 "ci_low": 0.6481481481481481,3295 "ci_high": 1.0,3296 "n_items": 60,3297 "n_groups": 93298 }3299 },3300 "data": {3301 "n": 33,3302 "chrf": {3303 "mean": 73.42328451377784,3304 "ci_low": 69.56278027250741,3305 "ci_high": 76.64037138150323,3306 "n_items": 33,3307 "n_groups": 53308 },3309 "edit_sim": {3310 "mean": 0.6533629762643594,3311 "ci_low": 0.6175489035792705,3312 "ci_high": 0.6781543658356503,3313 "n_items": 33,3314 "n_groups": 53315 },3316 "rougeL": {3317 "mean": 0.7156281910613946,3318 "ci_low": 0.6752321871728009,3319 "ci_high": 0.7461182027084253,3320 "n_items": 33,3321 "n_groups": 53322 },3323 "exact_match": {3324 "mean": 0.0,3325 "ci_low": 0.0,3326 "ci_high": 0.0,3327 "n_items": 33,3328 "n_groups": 53329 },3330 "number_recall": {3331 "mean": 0.9898989898989901,3332 "ci_low": 0.9666666666666667,3333 "ci_high": 1.0,3334 "n_items": 33,3335 "n_groups": 53336 },3337 "placeholders_exact": {3338 "mean": 0.6666666666666666,3339 "ci_low": 0.23255813953488372,3340 "ci_high": 1.0,3341 "n_items": 33,3342 "n_groups": 53343 }3344 },3345 "discussion": {3346 "n": 60,3347 "chrf": {3348 "mean": 67.63397341876718,3349 "ci_low": 65.0456643085456,3350 "ci_high": 70.98339437192914,3351 "n_items": 60,3352 "n_groups": 73353 },3354 "edit_sim": {3355 "mean": 0.6310373523444311,3356 "ci_low": 0.5842006734685932,3357 "ci_high": 0.6986364340985626,3358 "n_items": 60,3359 "n_groups": 73360 },3361 "rougeL": {3362 "mean": 0.6451899311589921,3363 "ci_low": 0.6128979360282077,3364 "ci_high": 0.6910614798063214,3365 "n_items": 60,3366 "n_groups": 73367 },3368 "exact_match": {3369 "mean": 0.0,3370 "ci_low": 0.0,3371 "ci_high": 0.0,3372 "n_items": 60,3373 "n_groups": 73374 },3375 "number_recall": {3376 "mean": 0.9884259259259259,3377 "ci_low": 0.9760101010101011,3378 "ci_high": 1.0,3379 "n_items": 60,3380 "n_groups": 73381 },3382 "placeholders_exact": {3383 "mean": 0.6,3384 "ci_low": 0.3333333333333333,3385 "ci_high": 0.8753472222222203,3386 "n_items": 60,3387 "n_groups": 73388 }3389 },3390 "introduction": {3391 "n": 56,3392 "chrf": {3393 "mean": 67.87659733813874,3394 "ci_low": 64.67396576525545,3395 "ci_high": 71.31161278433927,3396 "n_items": 56,3397 "n_groups": 93398 },3399 "edit_sim": {3400 "mean": 0.6288946972734722,3401 "ci_low": 0.5722277380542782,3402 "ci_high": 0.6832068672686982,3403 "n_items": 56,3404 "n_groups": 93405 },3406 "rougeL": {3407 "mean": 0.6392634521863242,3408 "ci_low": 0.5918796371509364,3409 "ci_high": 0.6897831514458022,3410 "n_items": 56,3411 "n_groups": 93412 },3413 "exact_match": {3414 "mean": 0.0,3415 "ci_low": 0.0,3416 "ci_high": 0.0,3417 "n_items": 56,3418 "n_groups": 93419 },3420 "number_recall": {3421 "mean": 0.9788961038961038,3422 "ci_low": 0.9487179487179487,3423 "ci_high": 0.9974025974025973,3424 "n_items": 56,3425 "n_groups": 93426 },3427 "placeholders_exact": {3428 "mean": 0.375,3429 "ci_low": 0.10714285714285714,3430 "ci_high": 0.7194192377495456,3431 "n_items": 56,3432 "n_groups": 93433 }3434 },3435 "limitations": {3436 "n": 12,3437 "chrf": {3438 "mean": 67.21042089553475,3439 "ci_low": 66.53751205521174,3440 "ci_high": 67.88332973585777,3441 "n_items": 12,3442 "n_groups": 23443 },3444 "edit_sim": {3445 "mean": 0.6112741828596869,3446 "ci_low": 0.567618788254585,3447 "ci_high": 0.6549295774647886,3448 "n_items": 12,3449 "n_groups": 23450 },3451 "rougeL": {3452 "mean": 0.6502005589020848,3453 "ci_low": 0.6323191428454585,3454 "ci_high": 0.6680819749587109,3455 "n_items": 12,3456 "n_groups": 23457 },3458 "exact_match": {3459 "mean": 0.0,3460 "ci_low": 0.0,3461 "ci_high": 0.0,3462 "n_items": 12,3463 "n_groups": 23464 },3465 "number_recall": {3466 "mean": 1.0,3467 "ci_low": 1.0,3468 "ci_high": 1.0,3469 "n_items": 12,3470 "n_groups": 23471 },3472 "placeholders_exact": {3473 "mean": 1.0,3474 "ci_low": 1.0,3475 "ci_high": 1.0,3476 "n_items": 12,3477 "n_groups": 23478 }3479 },3480 "methods": {3481 "n": 69,3482 "chrf": {3483 "mean": 71.76592706986926,3484 "ci_low": 69.06616752983292,3485 "ci_high": 74.46660950816009,3486 "n_items": 69,3487 "n_groups": 113488 },3489 "edit_sim": {3490 "mean": 0.6850513813891714,3491 "ci_low": 0.6510808584449106,3492 "ci_high": 0.7147955870602689,3493 "n_items": 69,3494 "n_groups": 113495 },3496 "rougeL": {3497 "mean": 0.722823235662198,3498 "ci_low": 0.6864871709124435,3499 "ci_high": 0.7578633214039718,3500 "n_items": 69,3501 "n_groups": 113502 },3503 "exact_match": {3504 "mean": 0.0,3505 "ci_low": 0.0,3506 "ci_high": 0.0,3507 "n_items": 69,3508 "n_groups": 113509 },3510 "number_recall": {3511 "mean": 0.9676501035196686,3512 "ci_low": 0.9386638904573688,3513 "ci_high": 0.9936476865985894,3514 "n_items": 69,3515 "n_groups": 113516 },3517 "placeholders_exact": {3518 "mean": 0.5797101449275363,3519 "ci_low": 0.260829307568438,3520 "ci_high": 0.8607682841068917,3521 "n_items": 69,3522 "n_groups": 113523 }3524 },3525 "other": {3526 "n": 32,3527 "chrf": {3528 "mean": 71.2915586481511,3529 "ci_low": 63.461574261218814,3530 "ci_high": 75.66100719162036,3531 "n_items": 32,3532 "n_groups": 53533 },3534 "edit_sim": {3535 "mean": 0.6536981210238975,3536 "ci_low": 0.5773997728225111,3537 "ci_high": 0.7158847154519954,3538 "n_items": 32,3539 "n_groups": 53540 },3541 "rougeL": {3542 "mean": 0.7002858407236372,3543 "ci_low": 0.6408843117556967,3544 "ci_high": 0.7448163812454396,3545 "n_items": 32,3546 "n_groups": 53547 },3548 "exact_match": {3549 "mean": 0.0,3550 "ci_low": 0.0,3551 "ci_high": 0.0,3552 "n_items": 32,3553 "n_groups": 53554 },3555 "number_recall": {3556 "mean": 0.9246651785714286,3557 "ci_low": 0.7362637362637364,3558 "ci_high": 1.0,3559 "n_items": 32,3560 "n_groups": 53561 },3562 "placeholders_exact": {3563 "mean": 0.5625,3564 "ci_low": 0.21428571428571427,3565 "ci_high": 0.9230769230769231,3566 "n_items": 32,3567 "n_groups": 53568 }3569 },3570 "related_work": {3571 "n": 6,3572 "chrf": {3573 "mean": 68.82956989269978,3574 "ci_low": 68.82956989269978,3575 "ci_high": 68.82956989269978,3576 "n_items": 6,3577 "n_groups": 13578 },3579 "edit_sim": {3580 "mean": 0.7701242618412515,3581 "ci_low": 0.7701242618412515,3582 "ci_high": 0.7701242618412515,3583 "n_items": 6,3584 "n_groups": 13585 },3586 "rougeL": {3587 "mean": 0.7871458557991686,3588 "ci_low": 0.7871458557991686,3589 "ci_high": 0.7871458557991686,3590 "n_items": 6,3591 "n_groups": 13592 },3593 "exact_match": {3594 "mean": 0.0,3595 "ci_low": 0.0,3596 "ci_high": 0.0,3597 "n_items": 6,3598 "n_groups": 13599 },3600 "number_recall": {3601 "mean": 1.0,3602 "ci_low": 1.0,3603 "ci_high": 1.0,3604 "n_items": 6,3605 "n_groups": 13606 },3607 "placeholders_exact": {3608 "mean": 1.0,3609 "ci_low": 1.0,3610 "ci_high": 1.0,3611 "n_items": 6,3612 "n_groups": 13613 }3614 },3615 "results": {3616 "n": 62,3617 "chrf": {3618 "mean": 67.78617377582606,3619 "ci_low": 65.58315819925956,3620 "ci_high": 69.93547562604662,3621 "n_items": 62,3622 "n_groups": 83623 },3624 "edit_sim": {3625 "mean": 0.6236777968973451,3626 "ci_low": 0.5892646366584524,3627 "ci_high": 0.6699085342216045,3628 "n_items": 62,3629 "n_groups": 83630 },3631 "rougeL": {3632 "mean": 0.6566756893758796,3633 "ci_low": 0.6285105771958721,3634 "ci_high": 0.6827781373094045,3635 "n_items": 62,3636 "n_groups": 83637 },3638 "exact_match": {3639 "mean": 0.0,3640 "ci_low": 0.0,3641 "ci_high": 0.0,3642 "n_items": 62,3643 "n_groups": 83644 },3645 "number_recall": {3646 "mean": 0.8438838474097289,3647 "ci_low": 0.7544698396061041,3648 "ci_high": 0.9404201436459502,3649 "n_items": 62,3650 "n_groups": 83651 },3652 "placeholders_exact": {3653 "mean": 1.0,3654 "ci_low": 1.0,3655 "ci_high": 1.0,3656 "n_items": 62,3657 "n_groups": 83658 }3659 },3660 "theory": {3661 "n": 27,3662 "chrf": {3663 "mean": 68.74916843305243,3664 "ci_low": 66.05339348602972,3665 "ci_high": 70.75575488569558,3666 "n_items": 27,3667 "n_groups": 43668 },3669 "edit_sim": {3670 "mean": 0.6624876141774403,3671 "ci_low": 0.6313329323275937,3672 "ci_high": 0.6874113596573177,3673 "n_items": 27,3674 "n_groups": 43675 },3676 "rougeL": {3677 "mean": 0.6931536916113927,3678 "ci_low": 0.6745693123199379,3679 "ci_high": 0.7080211950445565,3680 "n_items": 27,3681 "n_groups": 43682 },3683 "exact_match": {3684 "mean": 0.0,3685 "ci_low": 0.0,3686 "ci_high": 0.0,3687 "n_items": 27,3688 "n_groups": 43689 },3690 "number_recall": {3691 "mean": 0.9876543209876544,3692 "ci_low": 0.9583333333333334,3693 "ci_high": 1.0,3694 "n_items": 27,3695 "n_groups": 43696 },3697 "placeholders_exact": {3698 "mean": 0.5555555555555556,3699 "ci_low": 0.0,3700 "ci_high": 1.0,3701 "n_items": 27,3702 "n_groups": 43703 }3704 }3705 }3706 },3707 "htr-denoise-only": {3708 "overall": {3709 "n": 502,3710 "chrf": {3711 "mean": 58.05924231768958,3712 "ci_low": 55.20797272552014,3713 "ci_high": 60.86882506412343,3714 "n_items": 502,3715 "n_groups": 393716 },3717 "edit_sim": {3718 "mean": 0.45613712210440965,3719 "ci_low": 0.42092173711272096,3720 "ci_high": 0.4906026386198624,3721 "n_items": 502,3722 "n_groups": 393723 },3724 "rougeL": {3725 "mean": 0.4934257114990783,3726 "ci_low": 0.45890367233336526,3727 "ci_high": 0.5261225678841001,3728 "n_items": 502,3729 "n_groups": 393730 },3731 "exact_match": {3732 "mean": 0.0,3733 "ci_low": 0.0,3734 "ci_high": 0.0,3735 "n_items": 502,3736 "n_groups": 393737 },3738 "number_recall": {3739 "mean": 0.8560837534672427,3740 "ci_low": 0.8057124463068436,3741 "ci_high": 0.9019730253396027,3742 "n_items": 502,3743 "n_groups": 393744 },3745 "placeholders_exact": {3746 "mean": 0.7410358565737052,3747 "ci_low": 0.6494339799676292,3748 "ci_high": 0.823835210853452,3749 "n_items": 502,3750 "n_groups": 393751 }3752 },3753 "by_variant": {3754 "A": {3755 "n": 83,3756 "chrf": {3757 "mean": 55.85151002965664,3758 "ci_low": 51.527617155351315,3759 "ci_high": 59.54159610145542,3760 "n_items": 83,3761 "n_groups": 363762 },3763 "edit_sim": {3764 "mean": 0.42405460039227816,3765 "ci_low": 0.38338381129619836,3766 "ci_high": 0.4606063038405454,3767 "n_items": 83,3768 "n_groups": 363769 },3770 "rougeL": {3771 "mean": 0.45132118724209996,3772 "ci_low": 0.40689227450295323,3773 "ci_high": 0.4903791040401542,3774 "n_items": 83,3775 "n_groups": 363776 },3777 "exact_match": {3778 "mean": 0.0,3779 "ci_low": 0.0,3780 "ci_high": 0.0,3781 "n_items": 83,3782 "n_groups": 363783 },3784 "number_recall": {3785 "mean": 0.8595717190610719,3786 "ci_low": 0.793968425135672,3787 "ci_high": 0.9163236190521356,3788 "n_items": 83,3789 "n_groups": 363790 },3791 "placeholders_exact": {3792 "mean": 0.7590361445783133,3793 "ci_low": 0.6533333333333333,3794 "ci_high": 0.8480025316455696,3795 "n_items": 83,3796 "n_groups": 363797 }3798 },3799 "B": {3800 "n": 83,3801 "chrf": {3802 "mean": 62.13530483886448,3803 "ci_low": 57.440523148044065,3804 "ci_high": 66.75173504622784,3805 "n_items": 83,3806 "n_groups": 373807 },3808 "edit_sim": {3809 "mean": 0.49090295928322736,3810 "ci_low": 0.43846126280135855,3811 "ci_high": 0.5451886477848253,3812 "n_items": 83,3813 "n_groups": 373814 },3815 "rougeL": {3816 "mean": 0.5511995859079996,3817 "ci_low": 0.49952324012716415,3818 "ci_high": 0.6045863975433549,3819 "n_items": 83,3820 "n_groups": 373821 },3822 "exact_match": {3823 "mean": 0.0,3824 "ci_low": 0.0,3825 "ci_high": 0.0,3826 "n_items": 83,3827 "n_groups": 373828 },3829 "number_recall": {3830 "mean": 0.846062707325666,3831 "ci_low": 0.783718037707422,3832 "ci_high": 0.9145192132852171,3833 "n_items": 83,3834 "n_groups": 373835 },3836 "placeholders_exact": {3837 "mean": 0.6987951807228916,3838 "ci_low": 0.585705574912892,3839 "ci_high": 0.8095238095238095,3840 "n_items": 83,3841 "n_groups": 373842 }3843 },3844 "C": {3845 "n": 84,3846 "chrf": {3847 "mean": 62.02547512292482,3848 "ci_low": 57.87967753217883,3849 "ci_high": 65.34019381256721,3850 "n_items": 84,3851 "n_groups": 383852 },3853 "edit_sim": {3854 "mean": 0.5194922960285734,3855 "ci_low": 0.4654038587215197,3856 "ci_high": 0.5665518615902133,3857 "n_items": 84,3858 "n_groups": 383859 },3860 "rougeL": {3861 "mean": 0.571886483641955,3862 "ci_low": 0.5242802036672467,3863 "ci_high": 0.6149787516723372,3864 "n_items": 84,3865 "n_groups": 383866 },3867 "exact_match": {3868 "mean": 0.0,3869 "ci_low": 0.0,3870 "ci_high": 0.0,3871 "n_items": 84,3872 "n_groups": 383873 },3874 "number_recall": {3875 "mean": 0.8573806631738525,3876 "ci_low": 0.8015531258972151,3877 "ci_high": 0.9110139097873605,3878 "n_items": 84,3879 "n_groups": 383880 },3881 "placeholders_exact": {3882 "mean": 0.7738095238095238,3883 "ci_low": 0.658528866934239,3884 "ci_high": 0.8718085106382978,3885 "n_items": 84,3886 "n_groups": 383887 }3888 },3889 "D": {3890 "n": 85,3891 "chrf": {3892 "mean": 54.521852348347494,3893 "ci_low": 50.800458327367906,3894 "ci_high": 57.84688394122645,3895 "n_items": 85,3896 "n_groups": 373897 },3898 "edit_sim": {3899 "mean": 0.4186623429323334,3900 "ci_low": 0.3803732642029223,3901 "ci_high": 0.45411905081526177,3902 "n_items": 85,3903 "n_groups": 373904 },3905 "rougeL": {3906 "mean": 0.45043778217295516,3907 "ci_low": 0.4099900551572536,3908 "ci_high": 0.48933297175503515,3909 "n_items": 85,3910 "n_groups": 373911 },3912 "exact_match": {3913 "mean": 0.0,3914 "ci_low": 0.0,3915 "ci_high": 0.0,3916 "n_items": 85,3917 "n_groups": 373918 },3919 "number_recall": {3920 "mean": 0.8629634053457582,3921 "ci_low": 0.79139783039912,3922 "ci_high": 0.9267942457345119,3923 "n_items": 85,3924 "n_groups": 373925 },3926 "placeholders_exact": {3927 "mean": 0.7647058823529411,3928 "ci_low": 0.6477105614973262,3929 "ci_high": 0.8815982972136222,3930 "n_items": 85,3931 "n_groups": 373932 }3933 },3934 "E": {3935 "n": 167,3936 "chrf": {3937 "mean": 56.936147601543084,3938 "ci_low": 54.23036080643975,3939 "ci_high": 59.310708116079894,3940 "n_items": 167,3941 "n_groups": 383942 },3943 "edit_sim": {3944 "mean": 0.4420102145371149,3945 "ci_low": 0.4099104519616285,3946 "ci_high": 0.47374476195577786,3947 "n_items": 167,3948 "n_groups": 383949 },3950 "rougeL": {3951 "mean": 0.4680527358709802,3952 "ci_low": 0.43717952249576364,3953 "ci_high": 0.49587096949584625,3954 "n_items": 167,3955 "n_groups": 383956 },3957 "exact_match": {3958 "mean": 0.0,3959 "ci_low": 0.0,3960 "ci_high": 0.0,3961 "n_items": 167,3962 "n_groups": 383963 },3964 "number_recall": {3965 "mean": 0.8551767765836141,3966 "ci_low": 0.7967943308941823,3967 "ci_high": 0.9064610734343942,3968 "n_items": 167,3969 "n_groups": 383970 },3971 "placeholders_exact": {3972 "mean": 0.7245508982035929,3973 "ci_low": 0.6275745178258328,3974 "ci_high": 0.8121633287292818,3975 "n_items": 167,3976 "n_groups": 383977 }3978 }3979 },3980 "by_discipline": {3981 "biomedicine": {3982 "n": 184,3983 "chrf": {3984 "mean": 61.847068450438776,3985 "ci_low": 55.99517101381644,3986 "ci_high": 64.53728016402778,3987 "n_items": 184,3988 "n_groups": 193989 },3990 "edit_sim": {3991 "mean": 0.5163237800734375,3992 "ci_low": 0.45462005012386053,3993 "ci_high": 0.5471827753100195,3994 "n_items": 184,3995 "n_groups": 193996 },3997 "rougeL": {3998 "mean": 0.5457572772848402,3999 "ci_low": 0.4863381596888729,4000 "ci_high": 0.5746822491987249,4001 "n_items": 184,4002 "n_groups": 194003 },4004 "exact_match": {4005 "mean": 0.0,4006 "ci_low": 0.0,4007 "ci_high": 0.0,4008 "n_items": 184,4009 "n_groups": 194010 },4011 "number_recall": {4012 "mean": 0.8880201679740354,4013 "ci_low": 0.7965463823309661,4014 "ci_high": 0.9403826240501307,4015 "n_items": 184,4016 "n_groups": 194017 },4018 "placeholders_exact": {4019 "mean": 0.7010869565217391,4020 "ci_low": 0.5891408268733851,4021 "ci_high": 0.795047752621385,4022 "n_items": 184,4023 "n_groups": 194024 }4025 },4026 "computer_science": {4027 "n": 53,4028 "chrf": {4029 "mean": 52.871013098328106,4030 "ci_low": 47.245241472829,4031 "ci_high": 53.934445153829465,4032 "n_items": 53,4033 "n_groups": 34034 },4035 "edit_sim": {4036 "mean": 0.43071918911544416,4037 "ci_low": 0.3395120684192908,4038 "ci_high": 0.47423601843567575,4039 "n_items": 53,4040 "n_groups": 34041 },4042 "rougeL": {4043 "mean": 0.4503881203948692,4044 "ci_low": 0.36859738291621985,4045 "ci_high": 0.48176739360196386,4046 "n_items": 53,4047 "n_groups": 34048 },4049 "exact_match": {4050 "mean": 0.0,4051 "ci_low": 0.0,4052 "ci_high": 0.0,4053 "n_items": 53,4054 "n_groups": 34055 },4056 "number_recall": {4057 "mean": 0.7987421383647799,4058 "ci_low": 0.27777777777777773,4059 "ci_high": 0.9637681159420292,4060 "n_items": 53,4061 "n_groups": 34062 },4063 "placeholders_exact": {4064 "mean": 1.0,4065 "ci_low": 1.0,4066 "ci_high": 1.0,4067 "n_items": 53,4068 "n_groups": 34069 }4070 },4071 "earth_sciences": {4072 "n": 22,4073 "chrf": {4074 "mean": 59.12392718815517,4075 "ci_low": 59.12392718815517,4076 "ci_high": 59.12392718815517,4077 "n_items": 22,4078 "n_groups": 14079 },4080 "edit_sim": {4081 "mean": 0.43093946472854516,4082 "ci_low": 0.43093946472854516,4083 "ci_high": 0.43093946472854516,4084 "n_items": 22,4085 "n_groups": 14086 },4087 "rougeL": {4088 "mean": 0.5310341273068881,4089 "ci_low": 0.5310341273068881,4090 "ci_high": 0.5310341273068881,4091 "n_items": 22,4092 "n_groups": 14093 },4094 "exact_match": {4095 "mean": 0.0,4096 "ci_low": 0.0,4097 "ci_high": 0.0,4098 "n_items": 22,4099 "n_groups": 14100 },4101 "number_recall": {4102 "mean": 0.8545454545454546,4103 "ci_low": 0.8545454545454546,4104 "ci_high": 0.8545454545454546,4105 "n_items": 22,4106 "n_groups": 14107 },4108 "placeholders_exact": {4109 "mean": 0.9090909090909091,4110 "ci_low": 0.9090909090909091,4111 "ci_high": 0.9090909090909091,4112 "n_items": 22,4113 "n_groups": 14114 }4115 },4116 "engineering": {4117 "n": 45,4118 "chrf": {4119 "mean": 51.4643226984462,4120 "ci_low": 49.889226038452506,4121 "ci_high": 61.70245098840527,4122 "n_items": 45,4123 "n_groups": 24124 },4125 "edit_sim": {4126 "mean": 0.36207437031484474,4127 "ci_low": 0.35077862814482497,4128 "ci_high": 0.43549669441997363,4129 "n_items": 45,4130 "n_groups": 24131 },4132 "rougeL": {4133 "mean": 0.40137648564763273,4134 "ci_low": 0.38723330689013036,4135 "ci_high": 0.4933071475713979,4136 "n_items": 45,4137 "n_groups": 24138 },4139 "exact_match": {4140 "mean": 0.0,4141 "ci_low": 0.0,4142 "ci_high": 0.0,4143 "n_items": 45,4144 "n_groups": 24145 },4146 "number_recall": {4147 "mean": 0.7052469135802469,4148 "ci_low": 0.6826923076923077,4149 "ci_high": 0.851851851851852,4150 "n_items": 45,4151 "n_groups": 24152 },4153 "placeholders_exact": {4154 "mean": 0.7111111111111111,4155 "ci_low": 0.6666666666666666,4156 "ci_high": 1.0,4157 "n_items": 45,4158 "n_groups": 24159 }4160 },4161 "life_sciences": {4162 "n": 144,4163 "chrf": {4164 "mean": 56.99385907640525,4165 "ci_low": 52.22486088493287,4166 "ci_high": 61.41291313451449,4167 "n_items": 144,4168 "n_groups": 134169 },4170 "edit_sim": {4171 "mean": 0.41952075377558073,4172 "ci_low": 0.3741409395154935,4173 "ci_high": 0.4569430982333457,4174 "n_items": 144,4175 "n_groups": 134176 },4177 "rougeL": {4178 "mean": 0.4602329131771737,4179 "ci_low": 0.4148494263255043,4180 "ci_high": 0.5014293629003042,4181 "n_items": 144,4182 "n_groups": 134183 },4184 "exact_match": {4185 "mean": 0.0,4186 "ci_low": 0.0,4187 "ci_high": 0.0,4188 "n_items": 144,4189 "n_groups": 134190 },4191 "number_recall": {4192 "mean": 0.9029072971781306,4193 "ci_low": 0.8341564939430107,4194 "ci_high": 0.9549003623188407,4195 "n_items": 144,4196 "n_groups": 134197 },4198 "placeholders_exact": {4199 "mean": 0.625,4200 "ci_low": 0.4666666666666667,4201 "ci_high": 0.8272805642633229,4202 "n_items": 144,4203 "n_groups": 134204 }4205 },4206 "mathematics": {4207 "n": 54,4208 "chrf": {4209 "mean": 58.1477542188185,4210 "ci_low": 58.1477542188185,4211 "ci_high": 58.1477542188185,4212 "n_items": 54,4213 "n_groups": 14214 },4215 "edit_sim": {4216 "mean": 0.46229887607227704,4217 "ci_low": 0.46229887607227704,4218 "ci_high": 0.46229887607227704,4219 "n_items": 54,4220 "n_groups": 14221 },4222 "rougeL": {4223 "mean": 0.5072512151627899,4224 "ci_low": 0.5072512151627899,4225 "ci_high": 0.5072512151627899,4226 "n_items": 54,4227 "n_groups": 14228 },4229 "exact_match": {4230 "mean": 0.0,4231 "ci_low": 0.0,4232 "ci_high": 0.0,4233 "n_items": 54,4234 "n_groups": 14235 },4236 "number_recall": {4237 "mean": 0.805004409171076,4238 "ci_low": 0.805004409171076,4239 "ci_high": 0.805004409171076,4240 "n_items": 54,4241 "n_groups": 14242 },4243 "placeholders_exact": {4244 "mean": 0.8888888888888888,4245 "ci_low": 0.8888888888888888,4246 "ci_high": 0.8888888888888888,4247 "n_items": 54,4248 "n_groups": 14249 }4250 }4251 },4252 "by_era": {4253 "1980-1999": {4254 "n": 16,4255 "chrf": {4256 "mean": 65.37316318932487,4257 "ci_low": 63.48855568987571,4258 "ci_high": 66.00136568914125,4259 "n_items": 16,4260 "n_groups": 24261 },4262 "edit_sim": {4263 "mean": 0.5278867738426428,4264 "ci_low": 0.48856978283101177,4265 "ci_high": 0.5409924375131864,4266 "n_items": 16,4267 "n_groups": 24268 },4269 "rougeL": {4270 "mean": 0.5706510128946682,4271 "ci_low": 0.5141624356562157,4272 "ci_high": 0.589480538640819,4273 "n_items": 16,4274 "n_groups": 24275 },4276 "exact_match": {4277 "mean": 0.0,4278 "ci_low": 0.0,4279 "ci_high": 0.0,4280 "n_items": 16,4281 "n_groups": 24282 },4283 "number_recall": {4284 "mean": 0.9073660714285714,4285 "ci_low": 0.8869047619047619,4286 "ci_high": 0.96875,4287 "n_items": 16,4288 "n_groups": 24289 },4290 "placeholders_exact": {4291 "mean": 0.8125,4292 "ci_low": 0.75,4293 "ci_high": 1.0,4294 "n_items": 16,4295 "n_groups": 24296 }4297 },4298 "2000-2009": {4299 "n": 70,4300 "chrf": {4301 "mean": 62.839059226984354,4302 "ci_low": 34.222989351861884,4303 "ci_high": 65.5218157777771,4304 "n_items": 70,4305 "n_groups": 24306 },4307 "edit_sim": {4308 "mean": 0.5417920378084812,4309 "ci_low": 0.328537170263789,4310 "ci_high": 0.5617846816407961,4311 "n_items": 70,4312 "n_groups": 24313 },4314 "rougeL": {4315 "mean": 0.5692876342778694,4316 "ci_low": 0.3436673570418229,4317 "ci_high": 0.5904395352687488,4318 "n_items": 70,4319 "n_groups": 24320 },4321 "exact_match": {4322 "mean": 0.0,4323 "ci_low": 0.0,4324 "ci_high": 0.0,4325 "n_items": 70,4326 "n_groups": 24327 },4328 "number_recall": {4329 "mean": 0.9453649567935283,4330 "ci_low": 0.9402429214929215,4331 "ci_high": 1.0,4332 "n_items": 70,4333 "n_groups": 24334 },4335 "placeholders_exact": {4336 "mean": 0.7285714285714285,4337 "ci_low": 0.703125,4338 "ci_high": 1.0,4339 "n_items": 70,4340 "n_groups": 24341 }4342 },4343 "2010-2017": {4344 "n": 416,4345 "chrf": {4346 "mean": 56.97364155423574,4347 "ci_low": 54.61673466759405,4348 "ci_high": 59.543457368445345,4349 "n_items": 416,4350 "n_groups": 354351 },4352 "edit_sim": {4353 "mean": 0.43896443333735025,4354 "ci_low": 0.4127171638254301,4355 "ci_high": 0.466369463658887,4356 "n_items": 416,4357 "n_groups": 354358 },4359 "rougeL": {4360 "mean": 0.47769028020858606,4361 "ci_low": 0.4501952094389262,4362 "ci_high": 0.5057254196496171,4363 "n_items": 416,4364 "n_groups": 354365 },4366 "exact_match": {4367 "mean": 0.0,4368 "ci_low": 0.0,4369 "ci_high": 0.0,4370 "n_items": 416,4371 "n_groups": 354372 },4373 "number_recall": {4374 "mean": 0.839088077216711,4375 "ci_low": 0.7910826235535174,4376 "ci_high": 0.8922422731563594,4377 "n_items": 416,4378 "n_groups": 354379 },4380 "placeholders_exact": {4381 "mean": 0.7403846153846154,4382 "ci_low": 0.6302547653958944,4383 "ci_high": 0.8359622933123988,4384 "n_items": 416,4385 "n_groups": 354386 }4387 }4388 },4389 "by_role": {4390 "abstract": {4391 "n": 63,4392 "chrf": {4393 "mean": 57.3585856113318,4394 "ci_low": 48.237197625603386,4395 "ci_high": 63.81415478658498,4396 "n_items": 63,4397 "n_groups": 94398 },4399 "edit_sim": {4400 "mean": 0.4383573868785074,4401 "ci_low": 0.36561669293084476,4402 "ci_high": 0.48729581423120905,4403 "n_items": 63,4404 "n_groups": 94405 },4406 "rougeL": {4407 "mean": 0.47361684692467637,4408 "ci_low": 0.39780818828657666,4409 "ci_high": 0.5282335249943553,4410 "n_items": 63,4411 "n_groups": 94412 },4413 "exact_match": {4414 "mean": 0.0,4415 "ci_low": 0.0,4416 "ci_high": 0.0,4417 "n_items": 63,4418 "n_groups": 94419 },4420 "number_recall": {4421 "mean": 0.8292592592592594,4422 "ci_low": 0.7314207427536231,4423 "ci_high": 0.9325919191919192,4424 "n_items": 63,4425 "n_groups": 94426 },4427 "placeholders_exact": {4428 "mean": 1.0,4429 "ci_low": 1.0,4430 "ci_high": 1.0,4431 "n_items": 63,4432 "n_groups": 94433 }4434 },4435 "background": {4436 "n": 22,4437 "chrf": {4438 "mean": 60.95443814029067,4439 "ci_low": 56.42596500855756,4440 "ci_high": 65.48291127202377,4441 "n_items": 22,4442 "n_groups": 44443 },4444 "edit_sim": {4445 "mean": 0.41649812469590697,4446 "ci_low": 0.3179076819377543,4447 "ci_high": 0.503856596534757,4448 "n_items": 22,4449 "n_groups": 44450 },4451 "rougeL": {4452 "mean": 0.46723363495629244,4453 "ci_low": 0.38675499074943676,4454 "ci_high": 0.5215470604338471,4455 "n_items": 22,4456 "n_groups": 44457 },4458 "exact_match": {4459 "mean": 0.0,4460 "ci_low": 0.0,4461 "ci_high": 0.0,4462 "n_items": 22,4463 "n_groups": 44464 },4465 "number_recall": {4466 "mean": 0.8755411255411256,4467 "ci_low": 0.7585034013605443,4468 "ci_high": 0.9710144927536232,4469 "n_items": 22,4470 "n_groups": 44471 },4472 "placeholders_exact": {4473 "mean": 0.45454545454545453,4474 "ci_low": 0.125,4475 "ci_high": 0.85,4476 "n_items": 22,4477 "n_groups": 44478 }4479 },4480 "conclusion": {4481 "n": 60,4482 "chrf": {4483 "mean": 55.294814008306325,4484 "ci_low": 48.33548453894617,4485 "ci_high": 61.40520764479529,4486 "n_items": 60,4487 "n_groups": 94488 },4489 "edit_sim": {4490 "mean": 0.48962805450182517,4491 "ci_low": 0.41600743814263524,4492 "ci_high": 0.551160362393205,4493 "n_items": 60,4494 "n_groups": 94495 },4496 "rougeL": {4497 "mean": 0.5142924037016526,4498 "ci_low": 0.4440098268687277,4499 "ci_high": 0.5713107044869327,4500 "n_items": 60,4501 "n_groups": 94502 },4503 "exact_match": {4504 "mean": 0.0,4505 "ci_low": 0.0,4506 "ci_high": 0.0,4507 "n_items": 60,4508 "n_groups": 94509 },4510 "number_recall": {4511 "mean": 0.8833333333333333,4512 "ci_low": 0.75,4513 "ci_high": 1.0,4514 "n_items": 60,4515 "n_groups": 94516 },4517 "placeholders_exact": {4518 "mean": 0.8666666666666667,4519 "ci_low": 0.6296296296296297,4520 "ci_high": 1.0,4521 "n_items": 60,4522 "n_groups": 94523 }4524 },4525 "data": {4526 "n": 33,4527 "chrf": {4528 "mean": 62.258816386493244,4529 "ci_low": 55.35766060645533,4530 "ci_high": 66.47730207612084,4531 "n_items": 33,4532 "n_groups": 54533 },4534 "edit_sim": {4535 "mean": 0.49321571484434035,4536 "ci_low": 0.4537168661007316,4537 "ci_high": 0.5416713666356746,4538 "n_items": 33,4539 "n_groups": 54540 },4541 "rougeL": {4542 "mean": 0.5412747629172093,4543 "ci_low": 0.5083297459157795,4544 "ci_high": 0.5761457587161467,4545 "n_items": 33,4546 "n_groups": 54547 },4548 "exact_match": {4549 "mean": 0.0,4550 "ci_low": 0.0,4551 "ci_high": 0.0,4552 "n_items": 33,4553 "n_groups": 54554 },4555 "number_recall": {4556 "mean": 0.7888047138047138,4557 "ci_low": 0.5259259259259259,4558 "ci_high": 0.89375,4559 "n_items": 33,4560 "n_groups": 54561 },4562 "placeholders_exact": {4563 "mean": 0.7272727272727273,4564 "ci_low": 0.4888888888888889,4565 "ci_high": 1.0,4566 "n_items": 33,4567 "n_groups": 54568 }4569 },4570 "discussion": {4571 "n": 60,4572 "chrf": {4573 "mean": 53.236581422952966,4574 "ci_low": 44.717599878662455,4575 "ci_high": 62.82505127265362,4576 "n_items": 60,4577 "n_groups": 74578 },4579 "edit_sim": {4580 "mean": 0.4024765305829328,4581 "ci_low": 0.30508568540071995,4582 "ci_high": 0.5214062456003927,4583 "n_items": 60,4584 "n_groups": 74585 },4586 "rougeL": {4587 "mean": 0.4196897704674513,4588 "ci_low": 0.3277252541939618,4589 "ci_high": 0.5346681737511982,4590 "n_items": 60,4591 "n_groups": 74592 },4593 "exact_match": {4594 "mean": 0.0,4595 "ci_low": 0.0,4596 "ci_high": 0.0,4597 "n_items": 60,4598 "n_groups": 74599 },4600 "number_recall": {4601 "mean": 0.8458333333333333,4602 "ci_low": 0.645703125,4603 "ci_high": 1.0,4604 "n_items": 60,4605 "n_groups": 74606 },4607 "placeholders_exact": {4608 "mean": 0.45,4609 "ci_low": 0.22727272727272727,4610 "ci_high": 0.6666666666666666,4611 "n_items": 60,4612 "n_groups": 74613 }4614 },4615 "introduction": {4616 "n": 56,4617 "chrf": {4618 "mean": 58.746726301956755,4619 "ci_low": 54.336300096992126,4620 "ci_high": 63.78234137400099,4621 "n_items": 56,4622 "n_groups": 94623 },4624 "edit_sim": {4625 "mean": 0.4427366897570644,4626 "ci_low": 0.37763010349944265,4627 "ci_high": 0.5240920750233107,4628 "n_items": 56,4629 "n_groups": 94630 },4631 "rougeL": {4632 "mean": 0.46362590637116113,4633 "ci_low": 0.4014942231875557,4634 "ci_high": 0.5411569166172194,4635 "n_items": 56,4636 "n_groups": 94637 },4638 "exact_match": {4639 "mean": 0.0,4640 "ci_low": 0.0,4641 "ci_high": 0.0,4642 "n_items": 56,4643 "n_groups": 94644 },4645 "number_recall": {4646 "mean": 0.8625541125541126,4647 "ci_low": 0.7129186602870813,4648 "ci_high": 0.9928698752228164,4649 "n_items": 56,4650 "n_groups": 94651 },4652 "placeholders_exact": {4653 "mean": 0.6607142857142857,4654 "ci_low": 0.43283582089552236,4655 "ci_high": 0.9166666666666666,4656 "n_items": 56,4657 "n_groups": 94658 }4659 },4660 "limitations": {4661 "n": 12,4662 "chrf": {4663 "mean": 49.51637730271353,4664 "ci_low": 36.161953621053044,4665 "ci_high": 62.87080098437403,4666 "n_items": 12,4667 "n_groups": 24668 },4669 "edit_sim": {4670 "mean": 0.368964986759399,4671 "ci_low": 0.32321700369645573,4672 "ci_high": 0.41471296982234235,4673 "n_items": 12,4674 "n_groups": 24675 },4676 "rougeL": {4677 "mean": 0.45380432922808067,4678 "ci_low": 0.370142579614543,4679 "ci_high": 0.5374660788416185,4680 "n_items": 12,4681 "n_groups": 24682 },4683 "exact_match": {4684 "mean": 0.0,4685 "ci_low": 0.0,4686 "ci_high": 0.0,4687 "n_items": 12,4688 "n_groups": 24689 },4690 "number_recall": {4691 "mean": 1.0,4692 "ci_low": 1.0,4693 "ci_high": 1.0,4694 "n_items": 12,4695 "n_groups": 24696 },4697 "placeholders_exact": {4698 "mean": 1.0,4699 "ci_low": 1.0,4700 "ci_high": 1.0,4701 "n_items": 12,4702 "n_groups": 24703 }4704 },4705 "methods": {4706 "n": 69,4707 "chrf": {4708 "mean": 63.01926227065401,4709 "ci_low": 57.388002006186674,4710 "ci_high": 67.87833649634294,4711 "n_items": 69,4712 "n_groups": 114713 },4714 "edit_sim": {4715 "mean": 0.4957814667793402,4716 "ci_low": 0.4099171352346952,4717 "ci_high": 0.5832970095536479,4718 "n_items": 69,4719 "n_groups": 114720 },4721 "rougeL": {4722 "mean": 0.5588822605872231,4723 "ci_low": 0.4836650410414121,4724 "ci_high": 0.6273572872614841,4725 "n_items": 69,4726 "n_groups": 114727 },4728 "exact_match": {4729 "mean": 0.0,4730 "ci_low": 0.0,4731 "ci_high": 0.0,4732 "n_items": 69,4733 "n_groups": 114734 },4735 "number_recall": {4736 "mean": 0.8903554175293306,4737 "ci_low": 0.7986173396915585,4738 "ci_high": 0.9731481481481481,4739 "n_items": 69,4740 "n_groups": 114741 },4742 "placeholders_exact": {4743 "mean": 0.7971014492753623,4744 "ci_low": 0.6712283705839942,4745 "ci_high": 0.9166666666666666,4746 "n_items": 69,4747 "n_groups": 114748 }4749 },4750 "other": {4751 "n": 32,4752 "chrf": {4753 "mean": 65.09994965403749,4754 "ci_low": 58.14635515465798,4755 "ci_high": 69.09095948281214,4756 "n_items": 32,4757 "n_groups": 54758 },4759 "edit_sim": {4760 "mean": 0.5124724589451337,4761 "ci_low": 0.44465820025169706,4762 "ci_high": 0.5551153712074196,4763 "n_items": 32,4764 "n_groups": 54765 },4766 "rougeL": {4767 "mean": 0.5539848017713089,4768 "ci_low": 0.47438048955069206,4769 "ci_high": 0.6017025868576388,4770 "n_items": 32,4771 "n_groups": 54772 },4773 "exact_match": {4774 "mean": 0.0,4775 "ci_low": 0.0,4776 "ci_high": 0.0,4777 "n_items": 32,4778 "n_groups": 54779 },4780 "number_recall": {4781 "mean": 0.9317336309523809,4782 "ci_low": 0.8241758241758242,4783 "ci_high": 1.0,4784 "n_items": 32,4785 "n_groups": 54786 },4787 "placeholders_exact": {4788 "mean": 0.53125,4789 "ci_low": 0.38235294117647056,4790 "ci_high": 0.7666666666666667,4791 "n_items": 32,4792 "n_groups": 54793 }4794 },4795 "related_work": {4796 "n": 6,4797 "chrf": {4798 "mean": 57.569754197146516,4799 "ci_low": 57.569754197146516,4800 "ci_high": 57.569754197146516,4801 "n_items": 6,4802 "n_groups": 14803 },4804 "edit_sim": {4805 "mean": 0.3309330813867883,4806 "ci_low": 0.3309330813867883,4807 "ci_high": 0.3309330813867883,4808 "n_items": 6,4809 "n_groups": 14810 },4811 "rougeL": {4812 "mean": 0.3460045598583071,4813 "ci_low": 0.3460045598583071,4814 "ci_high": 0.3460045598583071,4815 "n_items": 6,4816 "n_groups": 14817 },4818 "exact_match": {4819 "mean": 0.0,4820 "ci_low": 0.0,4821 "ci_high": 0.0,4822 "n_items": 6,4823 "n_groups": 14824 },4825 "number_recall": {4826 "mean": 0.7592592592592592,4827 "ci_low": 0.7592592592592592,4828 "ci_high": 0.7592592592592592,4829 "n_items": 6,4830 "n_groups": 14831 },4832 "placeholders_exact": {4833 "mean": 0.6666666666666666,4834 "ci_low": 0.6666666666666666,4835 "ci_high": 0.6666666666666666,4836 "n_items": 6,4837 "n_groups": 14838 }4839 },4840 "results": {4841 "n": 62,4842 "chrf": {4843 "mean": 56.576409589222266,4844 "ci_low": 49.21162291533534,4845 "ci_high": 60.95868252221671,4846 "n_items": 62,4847 "n_groups": 84848 },4849 "edit_sim": {4850 "mean": 0.4595888654101964,4851 "ci_low": 0.4134756889806548,4852 "ci_high": 0.49898464481639265,4853 "n_items": 62,4854 "n_groups": 84855 },4856 "rougeL": {4857 "mean": 0.4922339586173349,4858 "ci_low": 0.44406907162646947,4859 "ci_high": 0.5297607256571454,4860 "n_items": 62,4861 "n_groups": 84862 },4863 "exact_match": {4864 "mean": 0.0,4865 "ci_low": 0.0,4866 "ci_high": 0.0,4867 "n_items": 62,4868 "n_groups": 84869 },4870 "number_recall": {4871 "mean": 0.853471294947289,4872 "ci_low": 0.7638615534050189,4873 "ci_high": 0.9304586563307493,4874 "n_items": 62,4875 "n_groups": 84876 },4877 "placeholders_exact": {4878 "mean": 0.9193548387096774,4879 "ci_low": 0.7272727272727273,4880 "ci_high": 1.0,4881 "n_items": 62,4882 "n_groups": 84883 }4884 },4885 "theory": {4886 "n": 27,4887 "chrf": {4888 "mean": 53.92703105144125,4889 "ci_low": 43.75537099709515,4890 "ci_high": 61.990168709453734,4891 "n_items": 27,4892 "n_groups": 44893 },4894 "edit_sim": {4895 "mean": 0.44777722146403665,4896 "ci_low": 0.3475776026373178,4897 "ci_high": 0.5279369165254119,4898 "n_items": 27,4899 "n_groups": 44900 },4901 "rougeL": {4902 "mean": 0.49585492898827005,4903 "ci_low": 0.4000348794142381,4904 "ci_high": 0.5725109686474957,4905 "n_items": 27,4906 "n_groups": 44907 },4908 "exact_match": {4909 "mean": 0.0,4910 "ci_low": 0.0,4911 "ci_high": 0.0,4912 "n_items": 27,4913 "n_groups": 44914 },4915 "number_recall": {4916 "mean": 0.720164609053498,4917 "ci_low": 0.4732510288065843,4918 "ci_high": 0.9176954732510288,4919 "n_items": 27,4920 "n_groups": 44921 },4922 "placeholders_exact": {4923 "mean": 0.5185185185185185,4924 "ci_low": 0.0,4925 "ci_high": 0.9333333333333333,4926 "n_items": 27,4927 "n_groups": 44928 }4929 }4930 }4931 },4932 "htr-m1-tiny-denoiseinit": {4933 "overall": {4934 "n": 502,4935 "chrf": {4936 "mean": 63.60454762148763,4937 "ci_low": 62.19762877862158,4938 "ci_high": 64.86102963432451,4939 "n_items": 502,4940 "n_groups": 394941 },4942 "edit_sim": {4943 "mean": 0.5776924761933073,4944 "ci_low": 0.5582109483057954,4945 "ci_high": 0.5954648466565631,4946 "n_items": 502,4947 "n_groups": 394948 },4949 "rougeL": {4950 "mean": 0.5995742519798042,4951 "ci_low": 0.5794807343450454,4952 "ci_high": 0.6168672039368986,4953 "n_items": 502,4954 "n_groups": 394955 },4956 "exact_match": {4957 "mean": 0.0,4958 "ci_low": 0.0,4959 "ci_high": 0.0,4960 "n_items": 502,4961 "n_groups": 394962 },4963 "number_recall": {4964 "mean": 0.9308203953694086,4965 "ci_low": 0.9119695304708855,4966 "ci_high": 0.9503206874669801,4967 "n_items": 502,4968 "n_groups": 394969 },4970 "placeholders_exact": {4971 "mean": 0.8844621513944223,4972 "ci_low": 0.830338414080929,4973 "ci_high": 0.9380970149253731,4974 "n_items": 502,4975 "n_groups": 394976 }4977 },4978 "by_variant": {4979 "A": {4980 "n": 83,4981 "chrf": {4982 "mean": 62.944904021806465,4983 "ci_low": 61.3641201883548,4984 "ci_high": 64.21131324038282,4985 "n_items": 83,4986 "n_groups": 364987 },4988 "edit_sim": {4989 "mean": 0.5559386937596604,4990 "ci_low": 0.5315886090984615,4991 "ci_high": 0.5778344026916119,4992 "n_items": 83,4993 "n_groups": 364994 },4995 "rougeL": {4996 "mean": 0.5776932974761121,4997 "ci_low": 0.5529375849996585,4998 "ci_high": 0.5970328087222647,4999 "n_items": 83,5000 "n_groups": 365001 },5002 "exact_match": {5003 "mean": 0.0,5004 "ci_low": 0.0,5005 "ci_high": 0.0,5006 "n_items": 83,5007 "n_groups": 365008 },5009 "number_recall": {5010 "mean": 0.937573276336235,5011 "ci_low": 0.9160960666860118,5012 "ci_high": 0.9598105691712245,5013 "n_items": 83,5014 "n_groups": 365015 },5016 "placeholders_exact": {5017 "mean": 0.8433734939759037,5018 "ci_low": 0.7654289493575207,5019 "ci_high": 0.9255417651694247,5020 "n_items": 83,5021 "n_groups": 365022 }5023 },5024 "B": {5025 "n": 83,5026 "chrf": {5027 "mean": 69.13009038124349,5028 "ci_low": 67.67919547517856,5029 "ci_high": 70.58014433772856,5030 "n_items": 83,5031 "n_groups": 375032 },5033 "edit_sim": {5034 "mean": 0.659862344431267,5035 "ci_low": 0.6361670447147234,5036 "ci_high": 0.6849985900853893,5037 "n_items": 83,5038 "n_groups": 375039 },5040 "rougeL": {5041 "mean": 0.6805072429158392,5042 "ci_low": 0.6589141169677569,5043 "ci_high": 0.7016813031851892,5044 "n_items": 83,5045 "n_groups": 375046 },5047 "exact_match": {5048 "mean": 0.0,5049 "ci_low": 0.0,5050 "ci_high": 0.0,5051 "n_items": 83,5052 "n_groups": 375053 },5054 "number_recall": {5055 "mean": 0.9490690229825841,5056 "ci_low": 0.9129175427698649,5057 "ci_high": 0.978992428216139,5058 "n_items": 83,5059 "n_groups": 375060 },5061 "placeholders_exact": {5062 "mean": 0.927710843373494,5063 "ci_low": 0.8723267866884888,5064 "ci_high": 0.9802076324137268,5065 "n_items": 83,5066 "n_groups": 375067 }5068 },5069 "C": {5070 "n": 84,5071 "chrf": {5072 "mean": 65.18352642017189,5073 "ci_low": 63.22424413209587,5074 "ci_high": 67.1062531800497,5075 "n_items": 84,5076 "n_groups": 385077 },5078 "edit_sim": {5079 "mean": 0.6277699348887597,5080 "ci_low": 0.6013379614273958,5081 "ci_high": 0.652733726499173,5082 "n_items": 84,5083 "n_groups": 385084 },5085 "rougeL": {5086 "mean": 0.656131264830551,5087 "ci_low": 0.6325194874501527,5088 "ci_high": 0.6775098407588013,5089 "n_items": 84,5090 "n_groups": 385091 },5092 "exact_match": {5093 "mean": 0.0,5094 "ci_low": 0.0,5095 "ci_high": 0.0,5096 "n_items": 84,5097 "n_groups": 385098 },5099 "number_recall": {5100 "mean": 0.9303901236417847,5101 "ci_low": 0.8885538803820053,5102 "ci_high": 0.9660715087827276,5103 "n_items": 84,5104 "n_groups": 385105 },5106 "placeholders_exact": {5107 "mean": 0.9285714285714286,5108 "ci_low": 0.8846052631578947,5109 "ci_high": 0.976204318936877,5110 "n_items": 84,5111 "n_groups": 385112 }5113 },5114 "D": {5115 "n": 85,5116 "chrf": {5117 "mean": 60.866875138896106,5118 "ci_low": 59.109869885361924,5119 "ci_high": 62.402198236335394,5120 "n_items": 85,5121 "n_groups": 375122 },5123 "edit_sim": {5124 "mean": 0.5285839418295691,5125 "ci_low": 0.503288870289911,5126 "ci_high": 0.551197450741539,5127 "n_items": 85,5128 "n_groups": 375129 },5130 "rougeL": {5131 "mean": 0.5495706893497612,5132 "ci_low": 0.5227620655443871,5133 "ci_high": 0.573187998039554,5134 "n_items": 85,5135 "n_groups": 375136 },5137 "exact_match": {5138 "mean": 0.0,5139 "ci_low": 0.0,5140 "ci_high": 0.0,5141 "n_items": 85,5142 "n_groups": 375143 },5144 "number_recall": {5145 "mean": 0.9066063878916136,5146 "ci_low": 0.8649450833287778,5147 "ci_high": 0.9479665312206431,5148 "n_items": 85,5149 "n_groups": 375150 },5151 "placeholders_exact": {5152 "mean": 0.8588235294117647,5153 "ci_low": 0.776310879811469,5154 "ci_high": 0.925,5155 "n_items": 85,5156 "n_groups": 375157 }5158 },5159 "E": {5160 "n": 167,5161 "chrf": {5162 "mean": 61.78537583492838,5163 "ci_low": 59.81440206781933,5164 "ci_high": 63.42727388582314,5165 "n_items": 167,5166 "n_groups": 385167 },5168 "edit_sim": {5169 "mean": 0.5474720197187073,5170 "ci_low": 0.5265352093199283,5171 "ci_high": 0.568349351469219,5172 "n_items": 167,5173 "n_groups": 385174 },5175 "rougeL": {5176 "mean": 0.567228112579843,5177 "ci_low": 0.5463465868633086,5178 "ci_high": 0.5867225394900981,5179 "n_items": 167,5180 "n_groups": 385181 },5182 "exact_match": {5183 "mean": 0.0,5184 "ci_low": 0.0,5185 "ci_high": 0.0,5186 "n_items": 167,5187 "n_groups": 385188 },5189 "number_recall": {5190 "mean": 0.93093541482206,5191 "ci_low": 0.9023090259438702,5192 "ci_high": 0.9574882562663406,5193 "n_items": 167,5194 "n_groups": 385195 },5196 "placeholders_exact": {5197 "mean": 0.874251497005988,5198 "ci_low": 0.8029084437235289,5199 "ci_high": 0.9423168789808917,5200 "n_items": 167,5201 "n_groups": 385202 }5203 }5204 },5205 "by_discipline": {5206 "biomedicine": {5207 "n": 184,5208 "chrf": {5209 "mean": 64.40894809593456,5210 "ci_low": 62.22928869353284,5211 "ci_high": 65.78476999572715,5212 "n_items": 184,5213 "n_groups": 195214 },5215 "edit_sim": {5216 "mean": 0.5843317798478694,5217 "ci_low": 0.5636041497707389,5218 "ci_high": 0.6020763427802991,5219 "n_items": 184,5220 "n_groups": 195221 },5222 "rougeL": {5223 "mean": 0.6092858651201103,5224 "ci_low": 0.5799864295566395,5225 "ci_high": 0.6238744819288842,5226 "n_items": 184,5227 "n_groups": 195228 },5229 "exact_match": {5230 "mean": 0.0,5231 "ci_low": 0.0,5232 "ci_high": 0.0,5233 "n_items": 184,5234 "n_groups": 195235 },5236 "number_recall": {5237 "mean": 0.9177683987662502,5238 "ci_low": 0.8726989462669059,5239 "ci_high": 0.9610806397306398,5240 "n_items": 184,5241 "n_groups": 195242 },5243 "placeholders_exact": {5244 "mean": 0.8478260869565217,5245 "ci_low": 0.7839974576271187,5246 "ci_high": 0.9435483870967742,5247 "n_items": 184,5248 "n_groups": 195249 }5250 },5251 "computer_science": {5252 "n": 53,5253 "chrf": {5254 "mean": 60.0787834189732,5255 "ci_low": 56.36918316836446,5256 "ci_high": 64.68239666535634,5257 "n_items": 53,5258 "n_groups": 35259 },5260 "edit_sim": {5261 "mean": 0.5595688424343689,5262 "ci_low": 0.5360813003562476,5263 "ci_high": 0.6649498952315932,5264 "n_items": 53,5265 "n_groups": 35266 },5267 "rougeL": {5268 "mean": 0.5776024766530546,5269 "ci_low": 0.5530581419327719,5270 "ci_high": 0.6713801076431577,5271 "n_items": 53,5272 "n_groups": 35273 },5274 "exact_match": {5275 "mean": 0.0,5276 "ci_low": 0.0,5277 "ci_high": 0.0,5278 "n_items": 53,5279 "n_groups": 35280 },5281 "number_recall": {5282 "mean": 0.9339622641509434,5283 "ci_low": 0.8958333333333334,5284 "ci_high": 1.0,5285 "n_items": 53,5286 "n_groups": 35287 },5288 "placeholders_exact": {5289 "mean": 1.0,5290 "ci_low": 1.0,5291 "ci_high": 1.0,5292 "n_items": 53,5293 "n_groups": 35294 }5295 },5296 "earth_sciences": {5297 "n": 22,5298 "chrf": {5299 "mean": 68.01877374669442,5300 "ci_low": 68.01877374669442,5301 "ci_high": 68.01877374669442,5302 "n_items": 22,5303 "n_groups": 15304 },5305 "edit_sim": {5306 "mean": 0.6394944373020675,5307 "ci_low": 0.6394944373020675,5308 "ci_high": 0.6394944373020675,5309 "n_items": 22,5310 "n_groups": 15311 },5312 "rougeL": {5313 "mean": 0.6680454285105145,5314 "ci_low": 0.6680454285105145,5315 "ci_high": 0.6680454285105145,5316 "n_items": 22,5317 "n_groups": 15318 },5319 "exact_match": {5320 "mean": 0.0,5321 "ci_low": 0.0,5322 "ci_high": 0.0,5323 "n_items": 22,5324 "n_groups": 15325 },5326 "number_recall": {5327 "mean": 0.9082644628099174,5328 "ci_low": 0.9082644628099174,5329 "ci_high": 0.9082644628099174,5330 "n_items": 22,5331 "n_groups": 15332 },5333 "placeholders_exact": {5334 "mean": 1.0,5335 "ci_low": 1.0,5336 "ci_high": 1.0,5337 "n_items": 22,5338 "n_groups": 15339 }5340 },5341 "engineering": {5342 "n": 45,5343 "chrf": {5344 "mean": 60.634187681765724,5345 "ci_low": 60.26668146736538,5346 "ci_high": 63.02297807536814,5347 "n_items": 45,5348 "n_groups": 25349 },5350 "edit_sim": {5351 "mean": 0.49368319588829174,5352 "ci_low": 0.49142010519853657,5353 "ci_high": 0.5083932853717027,5354 "n_items": 45,5355 "n_groups": 25356 },5357 "rougeL": {5358 "mean": 0.5276374574808196,5359 "ci_low": 0.523414619894315,5360 "ci_high": 0.5550859017930981,5361 "n_items": 45,5362 "n_groups": 25363 },5364 "exact_match": {5365 "mean": 0.0,5366 "ci_low": 0.0,5367 "ci_high": 0.0,5368 "n_items": 45,5369 "n_groups": 25370 },5371 "number_recall": {5372 "mean": 0.9237654320987654,5373 "ci_low": 0.9074074074074076,5374 "ci_high": 0.9262820512820513,5375 "n_items": 45,5376 "n_groups": 25377 },5378 "placeholders_exact": {5379 "mean": 0.9333333333333333,5380 "ci_low": 0.9230769230769231,5381 "ci_high": 1.0,5382 "n_items": 45,5383 "n_groups": 25384 }5385 },5386 "life_sciences": {5387 "n": 144,5388 "chrf": {5389 "mean": 63.44634608529006,5390 "ci_low": 60.99289214816774,5391 "ci_high": 65.52295142423753,5392 "n_items": 144,5393 "n_groups": 135394 },5395 "edit_sim": {5396 "mean": 0.5845637468585313,5397 "ci_low": 0.554453652168234,5398 "ci_high": 0.6133633198444963,5399 "n_items": 144,5400 "n_groups": 135401 },5402 "rougeL": {5403 "mean": 0.6012414092148768,5404 "ci_low": 0.5683476193833785,5405 "ci_high": 0.6253739746531763,5406 "n_items": 144,5407 "n_groups": 135408 },5409 "exact_match": {5410 "mean": 0.0,5411 "ci_low": 0.0,5412 "ci_high": 0.0,5413 "n_items": 144,5414 "n_groups": 135415 },5416 "number_recall": {5417 "mean": 0.9551366843033509,5418 "ci_low": 0.9151740515131287,5419 "ci_high": 0.9834071231798505,5420 "n_items": 144,5421 "n_groups": 135422 },5423 "placeholders_exact": {5424 "mean": 0.8263888888888888,5425 "ci_low": 0.734175385966196,5426 "ci_high": 0.9313836898395722,5427 "n_items": 144,5428 "n_groups": 135429 }5430 },5431 "mathematics": {5432 "n": 54,5433 "chrf": {5434 "mean": 65.42288205075462,5435 "ci_low": 65.42288205075462,5436 "ci_high": 65.42288205075462,5437 "n_items": 54,5438 "n_groups": 15439 },5440 "edit_sim": {5441 "mean": 0.5993634430511782,5442 "ci_low": 0.5993634430511782,5443 "ci_high": 0.5993634430511782,5444 "n_items": 54,5445 "n_groups": 15446 },5447 "rougeL": {5448 "mean": 0.6156536316359085,5449 "ci_low": 0.6156536316359085,5450 "ci_high": 0.6156536316359085,5451 "n_items": 54,5452 "n_groups": 15453 },5454 "exact_match": {5455 "mean": 0.0,5456 "ci_low": 0.0,5457 "ci_high": 0.0,5458 "n_items": 54,5459 "n_groups": 15460 },5461 "number_recall": {5462 "mean": 0.9224353321575544,5463 "ci_low": 0.9224353321575544,5464 "ci_high": 0.9224353321575544,5465 "n_items": 54,5466 "n_groups": 15467 },5468 "placeholders_exact": {5469 "mean": 0.9629629629629629,5470 "ci_low": 0.9629629629629629,5471 "ci_high": 0.9629629629629629,5472 "n_items": 54,5473 "n_groups": 15474 }5475 }5476 },5477 "by_era": {5478 "1980-1999": {5479 "n": 16,5480 "chrf": {5481 "mean": 64.60411919396859,5482 "ci_low": 55.4625302088827,5483 "ci_high": 67.65131552233055,5484 "n_items": 16,5485 "n_groups": 25486 },5487 "edit_sim": {5488 "mean": 0.5734555133848177,5489 "ci_low": 0.5477864106986279,5490 "ci_high": 0.582011880946881,5491 "n_items": 16,5492 "n_groups": 25493 },5494 "rougeL": {5495 "mean": 0.6072153755790399,5496 "ci_low": 0.5527710528645629,5497 "ci_high": 0.6253634831505323,5498 "n_items": 16,5499 "n_groups": 25500 },5501 "exact_match": {5502 "mean": 0.0,5503 "ci_low": 0.0,5504 "ci_high": 0.0,5505 "n_items": 16,5506 "n_groups": 25507 },5508 "number_recall": {5509 "mean": 0.9464285714285714,5510 "ci_low": 0.875,5511 "ci_high": 0.9702380952380952,5512 "n_items": 16,5513 "n_groups": 25514 },5515 "placeholders_exact": {5516 "mean": 1.0,5517 "ci_low": 1.0,5518 "ci_high": 1.0,5519 "n_items": 16,5520 "n_groups": 25521 }5522 },5523 "2000-2009": {5524 "n": 70,5525 "chrf": {5526 "mean": 64.15266319820014,5527 "ci_low": 54.15159266107181,5528 "ci_high": 65.09026356105592,5529 "n_items": 70,5530 "n_groups": 25531 },5532 "edit_sim": {5533 "mean": 0.5803548742929352,5534 "ci_low": 0.5041798598446282,5535 "ci_high": 0.5874962818974641,5536 "n_items": 70,5537 "n_groups": 25538 },5539 "rougeL": {5540 "mean": 0.6120650867978075,5541 "ci_low": 0.47883449071942746,5542 "ci_high": 0.6245554551801555,5543 "n_items": 70,5544 "n_groups": 25545 },5546 "exact_match": {5547 "mean": 0.0,5548 "ci_low": 0.0,5549 "ci_high": 0.0,5550 "n_items": 70,5551 "n_groups": 25552 },5553 "number_recall": {5554 "mean": 0.9242310167310167,5555 "ci_low": 0.9171276745495496,5556 "ci_high": 1.0,5557 "n_items": 70,5558 "n_groups": 25559 },5560 "placeholders_exact": {5561 "mean": 0.8,5562 "ci_low": 0.78125,5563 "ci_high": 1.0,5564 "n_items": 70,5565 "n_groups": 25566 }5567 },5568 "2010-2017": {5569 "n": 416,5570 "chrf": {5571 "mean": 63.47387157454155,5572 "ci_low": 61.88580007836362,5573 "ci_high": 64.93630996819996,5574 "n_items": 416,5575 "n_groups": 355576 },5577 "edit_sim": {5578 "mean": 0.5774074366211003,5579 "ci_low": 0.5547383943651548,5580 "ci_high": 0.5999019076514243,5581 "n_items": 416,5582 "n_groups": 355583 },5584 "rougeL": {5585 "mean": 0.5971785394441118,5586 "ci_low": 0.5764448891976729,5587 "ci_high": 0.6171234018616155,5588 "n_items": 416,5589 "n_groups": 355590 },5591 "exact_match": {5592 "mean": 0.0,5593 "ci_low": 0.0,5594 "ci_high": 0.0,5595 "n_items": 416,5596 "n_groups": 355597 },5598 "number_recall": {5599 "mean": 0.9313288705803241,5600 "ci_low": 0.9092597449320252,5601 "ci_high": 0.9541258019437696,5602 "n_items": 416,5603 "n_groups": 355604 },5605 "placeholders_exact": {5606 "mean": 0.8942307692307693,5607 "ci_low": 0.8321596004891969,5608 "ci_high": 0.9443404777137983,5609 "n_items": 416,5610 "n_groups": 355611 }5612 }5613 },5614 "by_role": {5615 "abstract": {5616 "n": 63,5617 "chrf": {5618 "mean": 63.72790824799047,5619 "ci_low": 60.52455526437607,5620 "ci_high": 66.23515986717462,5621 "n_items": 63,5622 "n_groups": 95623 },5624 "edit_sim": {5625 "mean": 0.5795642521515618,5626 "ci_low": 0.5270688232568439,5627 "ci_high": 0.6229346075440922,5628 "n_items": 63,5629 "n_groups": 95630 },5631 "rougeL": {5632 "mean": 0.5956788644648706,5633 "ci_low": 0.5335568959685676,5634 "ci_high": 0.6396692085677752,5635 "n_items": 63,5636 "n_groups": 95637 },5638 "exact_match": {5639 "mean": 0.0,5640 "ci_low": 0.0,5641 "ci_high": 0.0,5642 "n_items": 63,5643 "n_groups": 95644 },5645 "number_recall": {5646 "mean": 0.926384479717813,5647 "ci_low": 0.8772514619883041,5648 "ci_high": 0.9742424242424241,5649 "n_items": 63,5650 "n_groups": 95651 },5652 "placeholders_exact": {5653 "mean": 1.0,5654 "ci_low": 1.0,5655 "ci_high": 1.0,5656 "n_items": 63,5657 "n_groups": 95658 }5659 },5660 "background": {5661 "n": 22,5662 "chrf": {5663 "mean": 63.17758450065653,5664 "ci_low": 56.99585616676862,5665 "ci_high": 70.79098134997645,5666 "n_items": 22,5667 "n_groups": 45668 },5669 "edit_sim": {5670 "mean": 0.5600728114590905,5671 "ci_low": 0.498374141029053,5672 "ci_high": 0.6499019533381096,5673 "n_items": 22,5674 "n_groups": 45675 },5676 "rougeL": {5677 "mean": 0.5901581351409434,5678 "ci_low": 0.5316738664064361,5679 "ci_high": 0.660103387398078,5680 "n_items": 22,5681 "n_groups": 45682 },5683 "exact_match": {5684 "mean": 0.0,5685 "ci_low": 0.0,5686 "ci_high": 0.0,5687 "n_items": 22,5688 "n_groups": 45689 },5690 "number_recall": {5691 "mean": 0.8966450216450217,5692 "ci_low": 0.8614718614718615,5693 "ci_high": 0.9384057971014493,5694 "n_items": 22,5695 "n_groups": 45696 },5697 "placeholders_exact": {5698 "mean": 0.6363636363636364,5699 "ci_low": 0.20833333333333334,5700 "ci_high": 0.95,5701 "n_items": 22,5702 "n_groups": 45703 }5704 },5705 "conclusion": {5706 "n": 60,5707 "chrf": {5708 "mean": 60.05368796438645,5709 "ci_low": 57.37875003051526,5710 "ci_high": 63.2705302727833,5711 "n_items": 60,5712 "n_groups": 95713 },5714 "edit_sim": {5715 "mean": 0.5403305815701108,5716 "ci_low": 0.5124844754018948,5717 "ci_high": 0.5695456303792531,5718 "n_items": 60,5719 "n_groups": 95720 },5721 "rougeL": {5722 "mean": 0.5635858673995935,5723 "ci_low": 0.528107802583432,5724 "ci_high": 0.5991755006476016,5725 "n_items": 60,5726 "n_groups": 95727 },5728 "exact_match": {5729 "mean": 0.0,5730 "ci_low": 0.0,5731 "ci_high": 0.0,5732 "n_items": 60,5733 "n_groups": 95734 },5735 "number_recall": {5736 "mean": 0.9733333333333334,5737 "ci_low": 0.9433333333333332,5738 "ci_high": 1.0,5739 "n_items": 60,5740 "n_groups": 95741 },5742 "placeholders_exact": {5743 "mean": 0.8666666666666667,5744 "ci_low": 0.6296296296296297,5745 "ci_high": 1.0,5746 "n_items": 60,5747 "n_groups": 95748 }5749 },5750 "data": {5751 "n": 33,5752 "chrf": {5753 "mean": 67.07868465192519,5754 "ci_low": 62.85396584412625,5755 "ci_high": 70.09082962666237,5756 "n_items": 33,5757 "n_groups": 55758 },5759 "edit_sim": {5760 "mean": 0.5743489163812424,5761 "ci_low": 0.5368378018382304,5762 "ci_high": 0.6170332236125863,5763 "n_items": 33,5764 "n_groups": 55765 },5766 "rougeL": {5767 "mean": 0.6200420462878301,5768 "ci_low": 0.5808320564620972,5769 "ci_high": 0.648851681189832,5770 "n_items": 33,5771 "n_groups": 55772 },5773 "exact_match": {5774 "mean": 0.0,5775 "ci_low": 0.0,5776 "ci_high": 0.0,5777 "n_items": 33,5778 "n_groups": 55779 },5780 "number_recall": {5781 "mean": 0.8895622895622896,5782 "ci_low": 0.8037037037037037,5783 "ci_high": 0.9416666666666667,5784 "n_items": 33,5785 "n_groups": 55786 },5787 "placeholders_exact": {5788 "mean": 0.8787878787878788,5789 "ci_low": 0.7209302325581395,5790 "ci_high": 1.0,5791 "n_items": 33,5792 "n_groups": 55793 }5794 },5795 "discussion": {5796 "n": 60,5797 "chrf": {5798 "mean": 62.713283782709475,5799 "ci_low": 60.94699399223962,5800 "ci_high": 64.23840325190913,5801 "n_items": 60,5802 "n_groups": 75803 },5804 "edit_sim": {5805 "mean": 0.5879481213694281,5806 "ci_low": 0.5503840398404767,5807 "ci_high": 0.6338597765714796,5808 "n_items": 60,5809 "n_groups": 75810 },5811 "rougeL": {5812 "mean": 0.588184672679247,5813 "ci_low": 0.5532345109056624,5814 "ci_high": 0.6290678151033815,5815 "n_items": 60,5816 "n_groups": 75817 },5818 "exact_match": {5819 "mean": 0.0,5820 "ci_low": 0.0,5821 "ci_high": 0.0,5822 "n_items": 60,5823 "n_groups": 75824 },5825 "number_recall": {5826 "mean": 0.9458333333333334,5827 "ci_low": 0.9027777777777778,5828 "ci_high": 0.9861111111111112,5829 "n_items": 60,5830 "n_groups": 75831 },5832 "placeholders_exact": {5833 "mean": 0.7666666666666667,5834 "ci_low": 0.6,5835 "ci_high": 0.8888888888888888,5836 "n_items": 60,5837 "n_groups": 75838 }5839 },5840 "introduction": {5841 "n": 56,5842 "chrf": {5843 "mean": 64.35464403468632,5844 "ci_low": 61.287707144781855,5845 "ci_high": 67.32515174849843,5846 "n_items": 56,5847 "n_groups": 95848 },5849 "edit_sim": {5850 "mean": 0.5925785305159288,5851 "ci_low": 0.5389589334229783,5852 "ci_high": 0.6459684766740563,5853 "n_items": 56,5854 "n_groups": 95855 },5856 "rougeL": {5857 "mean": 0.5985942231849452,5858 "ci_low": 0.551413235556016,5859 "ci_high": 0.6445897113196594,5860 "n_items": 56,5861 "n_groups": 95862 },5863 "exact_match": {5864 "mean": 0.0,5865 "ci_low": 0.0,5866 "ci_high": 0.0,5867 "n_items": 56,5868 "n_groups": 95869 },5870 "number_recall": {5871 "mean": 0.9269480519480519,5872 "ci_low": 0.8455693363240532,5873 "ci_high": 1.0,5874 "n_items": 56,5875 "n_groups": 95876 },5877 "placeholders_exact": {5878 "mean": 0.8392857142857143,5879 "ci_low": 0.717391304347826,5880 "ci_high": 0.9583545918367347,5881 "n_items": 56,5882 "n_groups": 95883 }5884 },5885 "limitations": {5886 "n": 12,5887 "chrf": {5888 "mean": 59.17481131450242,5889 "ci_low": 56.542562118558756,5890 "ci_high": 61.807060510446085,5891 "n_items": 12,5892 "n_groups": 25893 },5894 "edit_sim": {5895 "mean": 0.5366561430931808,5896 "ci_low": 0.5052371688154694,5897 "ci_high": 0.568075117370892,5898 "n_items": 12,5899 "n_groups": 25900 },5901 "rougeL": {5902 "mean": 0.5731511252079322,5903 "ci_low": 0.55189026465094,5904 "ci_high": 0.5944119857649245,5905 "n_items": 12,5906 "n_groups": 25907 },5908 "exact_match": {5909 "mean": 0.0,5910 "ci_low": 0.0,5911 "ci_high": 0.0,5912 "n_items": 12,5913 "n_groups": 25914 },5915 "number_recall": {5916 "mean": 1.0,5917 "ci_low": 1.0,5918 "ci_high": 1.0,5919 "n_items": 12,5920 "n_groups": 25921 },5922 "placeholders_exact": {5923 "mean": 1.0,5924 "ci_low": 1.0,5925 "ci_high": 1.0,5926 "n_items": 12,5927 "n_groups": 25928 }5929 },5930 "methods": {5931 "n": 69,5932 "chrf": {5933 "mean": 66.50750481066868,5934 "ci_low": 63.3617079559867,5935 "ci_high": 69.28076252509751,5936 "n_items": 69,5937 "n_groups": 115938 },5939 "edit_sim": {5940 "mean": 0.6133696238625139,5941 "ci_low": 0.5744896814151598,5942 "ci_high": 0.6505433703214472,5943 "n_items": 69,5944 "n_groups": 115945 },5946 "rougeL": {5947 "mean": 0.6416693366820773,5948 "ci_low": 0.6060668445210158,5949 "ci_high": 0.6748218895139884,5950 "n_items": 69,5951 "n_groups": 115952 },5953 "exact_match": {5954 "mean": 0.0,5955 "ci_low": 0.0,5956 "ci_high": 0.0,5957 "n_items": 69,5958 "n_groups": 115959 },5960 "number_recall": {5961 "mean": 0.9228731413514022,5962 "ci_low": 0.8790297583679937,5963 "ci_high": 0.9621713350209113,5964 "n_items": 69,5965 "n_groups": 115966 },5967 "placeholders_exact": {5968 "mean": 0.9420289855072463,5969 "ci_low": 0.8709326788218794,5970 "ci_high": 1.0,5971 "n_items": 69,5972 "n_groups": 115973 }5974 },5975 "other": {5976 "n": 32,5977 "chrf": {5978 "mean": 66.65485366564093,5979 "ci_low": 62.022440374142526,5980 "ci_high": 70.59415324358925,5981 "n_items": 32,5982 "n_groups": 55983 },5984 "edit_sim": {5985 "mean": 0.582484352188299,5986 "ci_low": 0.5120052672572712,5987 "ci_high": 0.6582567919312743,5988 "n_items": 32,5989 "n_groups": 55990 },5991 "rougeL": {5992 "mean": 0.6127330270330108,5993 "ci_low": 0.5586975517423018,5994 "ci_high": 0.6602341132923805,5995 "n_items": 32,5996 "n_groups": 55997 },5998 "exact_match": {5999 "mean": 0.0,6000 "ci_low": 0.0,6001 "ci_high": 0.0,6002 "n_items": 32,6003 "n_groups": 56004 },6005 "number_recall": {6006 "mean": 0.9291294642857142,6007 "ci_low": 0.8021978021978022,6008 "ci_high": 1.0,6009 "n_items": 32,6010 "n_groups": 56011 },6012 "placeholders_exact": {6013 "mean": 0.75,6014 "ci_low": 0.5789473684210527,6015 "ci_high": 1.0,6016 "n_items": 32,6017 "n_groups": 56018 }6019 },6020 "related_work": {6021 "n": 6,6022 "chrf": {6023 "mean": 64.07785469461898,6024 "ci_low": 64.07785469461898,6025 "ci_high": 64.07785469461898,6026 "n_items": 6,6027 "n_groups": 16028 },6029 "edit_sim": {6030 "mean": 0.5772739736343329,6031 "ci_low": 0.5772739736343329,6032 "ci_high": 0.5772739736343329,6033 "n_items": 6,6034 "n_groups": 16035 },6036 "rougeL": {6037 "mean": 0.6175461267127934,6038 "ci_low": 0.6175461267127934,6039 "ci_high": 0.6175461267127934,6040 "n_items": 6,6041 "n_groups": 16042 },6043 "exact_match": {6044 "mean": 0.0,6045 "ci_low": 0.0,6046 "ci_high": 0.0,6047 "n_items": 6,6048 "n_groups": 16049 },6050 "number_recall": {6051 "mean": 0.7962962962962963,6052 "ci_low": 0.7962962962962963,6053 "ci_high": 0.7962962962962963,6054 "n_items": 6,6055 "n_groups": 16056 },6057 "placeholders_exact": {6058 "mean": 1.0,6059 "ci_low": 1.0,6060 "ci_high": 1.0,6061 "n_items": 6,6062 "n_groups": 16063 }6064 },6065 "results": {6066 "n": 62,6067 "chrf": {6068 "mean": 60.84394754599197,6069 "ci_low": 59.29420870768561,6070 "ci_high": 62.47357474630703,6071 "n_items": 62,6072 "n_groups": 86073 },6074 "edit_sim": {6075 "mean": 0.5445845734570305,6076 "ci_low": 0.5261842840685801,6077 "ci_high": 0.5677852543054435,6078 "n_items": 62,6079 "n_groups": 86080 },6081 "rougeL": {6082 "mean": 0.5715691885715276,6083 "ci_low": 0.5521660537800104,6084 "ci_high": 0.5931537248468381,6085 "n_items": 62,6086 "n_groups": 86087 },6088 "exact_match": {6089 "mean": 0.0,6090 "ci_low": 0.0,6091 "ci_high": 0.0,6092 "n_items": 62,6093 "n_groups": 86094 },6095 "number_recall": {6096 "mean": 0.901837826734676,6097 "ci_low": 0.8368767416339572,6098 "ci_high": 0.9635680346700084,6099 "n_items": 62,6100 "n_groups": 86101 },6102 "placeholders_exact": {6103 "mean": 1.0,6104 "ci_low": 1.0,6105 "ci_high": 1.0,6106 "n_items": 62,6107 "n_groups": 86108 }6109 },6110 "theory": {6111 "n": 27,6112 "chrf": {6113 "mean": 64.90296674212351,6114 "ci_low": 62.3007085698723,6115 "ci_high": 69.3743552620003,6116 "n_items": 27,6117 "n_groups": 46118 },6119 "edit_sim": {6120 "mean": 0.6186323983610172,6121 "ci_low": 0.5859554185791912,6122 "ci_high": 0.6677441546853276,6123 "n_items": 27,6124 "n_groups": 46125 },6126 "rougeL": {6127 "mean": 0.6475225769837789,6128 "ci_low": 0.6064013292408277,6129 "ci_high": 0.708733331526404,6130 "n_items": 27,6131 "n_groups": 46132 },6133 "exact_match": {6134 "mean": 0.0,6135 "ci_low": 0.0,6136 "ci_high": 0.0,6137 "n_items": 27,6138 "n_groups": 46139 },6140 "number_recall": {6141 "mean": 0.9876543209876544,6142 "ci_low": 0.9722222222222223,6143 "ci_high": 1.0,6144 "n_items": 27,6145 "n_groups": 46146 },6147 "placeholders_exact": {6148 "mean": 0.8888888888888888,6149 "ci_low": 0.75,6150 "ci_high": 1.0,6151 "n_items": 27,6152 "n_groups": 46153 }6154 }6155 }6156 },6157 "htr-m1-tiny-mediumdenoiseinit": {6158 "overall": {6159 "n": 502,6160 "chrf": {6161 "mean": 67.91266616829115,6162 "ci_low": 66.43276778140203,6163 "ci_high": 69.37757106654759,6164 "n_items": 502,6165 "n_groups": 396166 },6167 "edit_sim": {6168 "mean": 0.6302612626817108,6169 "ci_low": 0.6106876458449003,6170 "ci_high": 0.6485583083383845,6171 "n_items": 502,6172 "n_groups": 396173 },6174 "rougeL": {6175 "mean": 0.6559729339890068,6176 "ci_low": 0.6372967353200685,6177 "ci_high": 0.6743518549830609,6178 "n_items": 502,6179 "n_groups": 396180 },6181 "exact_match": {6182 "mean": 0.0,6183 "ci_low": 0.0,6184 "ci_high": 0.0,6185 "n_items": 502,6186 "n_groups": 396187 },6188 "number_recall": {6189 "mean": 0.9621081813140324,6190 "ci_low": 0.9423374212861456,6191 "ci_high": 0.976138284563272,6192 "n_items": 502,6193 "n_groups": 396194 },6195 "placeholders_exact": {6196 "mean": 0.9322709163346613,6197 "ci_low": 0.8919888367209478,6198 "ci_high": 0.9771936818127324,6199 "n_items": 502,6200 "n_groups": 396201 }6202 },6203 "by_variant": {6204 "A": {6205 "n": 83,6206 "chrf": {6207 "mean": 65.88020290094545,6208 "ci_low": 63.4977783291073,6209 "ci_high": 67.8496167141609,6210 "n_items": 83,6211 "n_groups": 366212 },6213 "edit_sim": {6214 "mean": 0.5935828296495945,6215 "ci_low": 0.5665207394268249,6216 "ci_high": 0.6164037639652495,6217 "n_items": 83,6218 "n_groups": 366219 },6220 "rougeL": {6221 "mean": 0.6192020111200073,6222 "ci_low": 0.594749080369981,6223 "ci_high": 0.6420202243328735,6224 "n_items": 83,6225 "n_groups": 366226 },6227 "exact_match": {6228 "mean": 0.0,6229 "ci_low": 0.0,6230 "ci_high": 0.0,6231 "n_items": 83,6232 "n_groups": 366233 },6234 "number_recall": {6235 "mean": 0.9591285807081547,6236 "ci_low": 0.9161410913220231,6237 "ci_high": 0.9878014792241984,6238 "n_items": 83,6239 "n_groups": 366240 },6241 "placeholders_exact": {6242 "mean": 0.9156626506024096,6243 "ci_low": 0.8648481815148482,6244 "ci_high": 0.969234693877551,6245 "n_items": 83,6246 "n_groups": 366247 }6248 },6249 "B": {6250 "n": 83,6251 "chrf": {6252 "mean": 72.97589012108112,6253 "ci_low": 71.23870380843346,6254 "ci_high": 74.60549423721032,6255 "n_items": 83,6256 "n_groups": 376257 },6258 "edit_sim": {6259 "mean": 0.7035569945883273,6260 "ci_low": 0.6786497150616573,6261 "ci_high": 0.7294869778773267,6262 "n_items": 83,6263 "n_groups": 376264 },6265 "rougeL": {6266 "mean": 0.7270977470256711,6267 "ci_low": 0.7013165614061085,6268 "ci_high": 0.751486769776823,6269 "n_items": 83,6270 "n_groups": 376271 },6272 "exact_match": {6273 "mean": 0.0,6274 "ci_low": 0.0,6275 "ci_high": 0.0,6276 "n_items": 83,6277 "n_groups": 376278 },6279 "number_recall": {6280 "mean": 0.952592908523141,6281 "ci_low": 0.915553858648704,6282 "ci_high": 0.9773364903092626,6283 "n_items": 83,6284 "n_groups": 376285 },6286 "placeholders_exact": {6287 "mean": 0.9397590361445783,6288 "ci_low": 0.8888888888888888,6289 "ci_high": 1.0,6290 "n_items": 83,6291 "n_groups": 376292 }6293 },6294 "C": {6295 "n": 84,6296 "chrf": {6297 "mean": 70.32106333665963,6298 "ci_low": 68.68443140498069,6299 "ci_high": 71.94063397254745,6300 "n_items": 84,6301 "n_groups": 386302 },6303 "edit_sim": {6304 "mean": 0.6888315508538388,6305 "ci_low": 0.6636668021477494,6306 "ci_high": 0.7115393710847655,6307 "n_items": 84,6308 "n_groups": 386309 },6310 "rougeL": {6311 "mean": 0.7208246936568122,6312 "ci_low": 0.6983467057136389,6313 "ci_high": 0.7417116526253483,6314 "n_items": 84,6315 "n_groups": 386316 },6317 "exact_match": {6318 "mean": 0.0,6319 "ci_low": 0.0,6320 "ci_high": 0.0,6321 "n_items": 84,6322 "n_groups": 386323 },6324 "number_recall": {6325 "mean": 0.9794939817012077,6326 "ci_low": 0.959009128323227,6327 "ci_high": 0.9931162025793978,6328 "n_items": 84,6329 "n_groups": 386330 },6331 "placeholders_exact": {6332 "mean": 0.9166666666666666,6333 "ci_low": 0.8546969696969696,6334 "ci_high": 0.9807783018867924,6335 "n_items": 84,6336 "n_groups": 386337 }6338 },6339 "D": {6340 "n": 85,6341 "chrf": {6342 "mean": 65.26265469317656,6343 "ci_low": 63.514482614022214,6344 "ci_high": 66.94407129704715,6345 "n_items": 85,6346 "n_groups": 376347 },6348 "edit_sim": {6349 "mean": 0.5828272495651694,6350 "ci_low": 0.5614560312765797,6351 "ci_high": 0.6035499376876804,6352 "n_items": 85,6353 "n_groups": 376354 },6355 "rougeL": {6356 "mean": 0.6065662546813195,6357 "ci_low": 0.5853568194600378,6358 "ci_high": 0.6286303772027991,6359 "n_items": 85,6360 "n_groups": 376361 },6362 "exact_match": {6363 "mean": 0.0,6364 "ci_low": 0.0,6365 "ci_high": 0.0,6366 "n_items": 85,6367 "n_groups": 376368 },6369 "number_recall": {6370 "mean": 0.948251379579697,6371 "ci_low": 0.9219677889679326,6372 "ci_high": 0.9704963824755491,6373 "n_items": 85,6374 "n_groups": 376375 },6376 "placeholders_exact": {6377 "mean": 0.9411764705882353,6378 "ci_low": 0.8940948029697317,6379 "ci_high": 0.9885057471264368,6380 "n_items": 85,6381 "n_groups": 376382 }6383 },6384 "E": {6385 "n": 167,6386 "chrf": {6387 "mean": 66.54375884104515,6388 "ci_low": 65.02264178970047,6389 "ci_high": 68.15332578852198,6390 "n_items": 167,6391 "n_groups": 386392 },6393 "edit_sim": {6394 "mean": 0.6067448022138292,6395 "ci_low": 0.588083859282693,6396 "ci_high": 0.6269893627367364,6397 "n_items": 167,6398 "n_groups": 386399 },6400 "rougeL": {6401 "mean": 0.6314259103072195,6402 "ci_low": 0.6124448052943172,6403 "ci_high": 0.6515832580835188,6404 "n_items": 167,6405 "n_groups": 386406 },6407 "exact_match": {6408 "mean": 0.0,6409 "ci_low": 0.0,6410 "ci_high": 0.0,6411 "n_items": 167,6412 "n_groups": 386413 },6414 "number_recall": {6415 "mean": 0.9666261178818621,6416 "ci_low": 0.9464102452526871,6417 "ci_high": 0.984003500686782,6418 "n_items": 167,6419 "n_groups": 386420 },6421 "placeholders_exact": {6422 "mean": 0.9401197604790419,6423 "ci_low": 0.9,6424 "ci_high": 0.9855098529871755,6425 "n_items": 167,6426 "n_groups": 386427 }6428 }6429 },6430 "by_discipline": {6431 "biomedicine": {6432 "n": 184,6433 "chrf": {6434 "mean": 69.08493427540893,6435 "ci_low": 66.40425349054426,6436 "ci_high": 70.93445392515862,6437 "n_items": 184,6438 "n_groups": 196439 },6440 "edit_sim": {6441 "mean": 0.646226026360822,6442 "ci_low": 0.6228612627906367,6443 "ci_high": 0.666416313170997,6444 "n_items": 184,6445 "n_groups": 196446 },6447 "rougeL": {6448 "mean": 0.674174170522928,6449 "ci_low": 0.6425896778165939,6450 "ci_high": 0.694434966127727,6451 "n_items": 184,6452 "n_groups": 196453 },6454 "exact_match": {6455 "mean": 0.0,6456 "ci_low": 0.0,6457 "ci_high": 0.0,6458 "n_items": 184,6459 "n_groups": 196460 },6461 "number_recall": {6462 "mean": 0.9598706730708754,6463 "ci_low": 0.9344570212155009,6464 "ci_high": 0.9788186190979487,6465 "n_items": 184,6466 "n_groups": 196467 },6468 "placeholders_exact": {6469 "mean": 0.907608695652174,6470 "ci_low": 0.8576251871167125,6471 "ci_high": 0.9846183206106871,6472 "n_items": 184,6473 "n_groups": 196474 }6475 },6476 "computer_science": {6477 "n": 53,6478 "chrf": {6479 "mean": 63.45921510740352,6480 "ci_low": 60.04326828179546,6481 "ci_high": 66.96462131997859,6482 "n_items": 53,6483 "n_groups": 36484 },6485 "edit_sim": {6486 "mean": 0.606194783809727,6487 "ci_low": 0.5710905102916427,6488 "ci_high": 0.6586572228506369,6489 "n_items": 53,6490 "n_groups": 36491 },6492 "rougeL": {6493 "mean": 0.6136659221261314,6494 "ci_low": 0.5849176250040806,6495 "ci_high": 0.6550500871370253,6496 "n_items": 53,6497 "n_groups": 36498 },6499 "exact_match": {6500 "mean": 0.0,6501 "ci_low": 0.0,6502 "ci_high": 0.0,6503 "n_items": 53,6504 "n_groups": 36505 },6506 "number_recall": {6507 "mean": 0.9465408805031446,6508 "ci_low": 0.8333333333333333,6509 "ci_high": 0.9855072463768116,6510 "n_items": 53,6511 "n_groups": 36512 },6513 "placeholders_exact": {6514 "mean": 1.0,6515 "ci_low": 1.0,6516 "ci_high": 1.0,6517 "n_items": 53,6518 "n_groups": 36519 }6520 },6521 "earth_sciences": {6522 "n": 22,6523 "chrf": {6524 "mean": 71.95618483486705,6525 "ci_low": 71.95618483486705,6526 "ci_high": 71.95618483486705,6527 "n_items": 22,6528 "n_groups": 16529 },6530 "edit_sim": {6531 "mean": 0.6596697978992637,6532 "ci_low": 0.6596697978992637,6533 "ci_high": 0.6596697978992637,6534 "n_items": 22,6535 "n_groups": 16536 },6537 "rougeL": {6538 "mean": 0.7031080758504492,6539 "ci_low": 0.7031080758504492,6540 "ci_high": 0.7031080758504492,6541 "n_items": 22,6542 "n_groups": 16543 },6544 "exact_match": {6545 "mean": 0.0,6546 "ci_low": 0.0,6547 "ci_high": 0.0,6548 "n_items": 22,6549 "n_groups": 16550 },6551 "number_recall": {6552 "mean": 1.0,6553 "ci_low": 1.0,6554 "ci_high": 1.0,6555 "n_items": 22,6556 "n_groups": 16557 },6558 "placeholders_exact": {6559 "mean": 1.0,6560 "ci_low": 1.0,6561 "ci_high": 1.0,6562 "n_items": 22,6563 "n_groups": 16564 }6565 },6566 "engineering": {6567 "n": 45,6568 "chrf": {6569 "mean": 65.26301813538232,6570 "ci_low": 64.91662493173422,6571 "ci_high": 67.51457395909496,6572 "n_items": 45,6573 "n_groups": 26574 },6575 "edit_sim": {6576 "mean": 0.5355276563235445,6577 "ci_low": 0.5352839367544386,6578 "ci_high": 0.537111833522732,6579 "n_items": 45,6580 "n_groups": 26581 },6582 "rougeL": {6583 "mean": 0.587014532981246,6584 "ci_low": 0.5862872846626923,6585 "ci_high": 0.5917416470518458,6586 "n_items": 45,6587 "n_groups": 26588 },6589 "exact_match": {6590 "mean": 0.0,6591 "ci_low": 0.0,6592 "ci_high": 0.0,6593 "n_items": 45,6594 "n_groups": 26595 },6596 "number_recall": {6597 "mean": 0.9680555555555556,6598 "ci_low": 0.9631410256410257,6599 "ci_high": 1.0,6600 "n_items": 45,6601 "n_groups": 26602 },6603 "placeholders_exact": {6604 "mean": 0.8444444444444444,6605 "ci_low": 0.8205128205128205,6606 "ci_high": 1.0,6607 "n_items": 45,6608 "n_groups": 26609 }6610 },6611 "life_sciences": {6612 "n": 144,6613 "chrf": {6614 "mean": 68.48067785838936,6615 "ci_low": 65.94582476490291,6616 "ci_high": 71.235666232649,6617 "n_items": 144,6618 "n_groups": 136619 },6620 "edit_sim": {6621 "mean": 0.6493916631163201,6622 "ci_low": 0.6312250402022156,6623 "ci_high": 0.6721823667138445,6624 "n_items": 144,6625 "n_groups": 136626 },6627 "rougeL": {6628 "mean": 0.6680732828184641,6629 "ci_low": 0.6434708253530282,6630 "ci_high": 0.6945373574148775,6631 "n_items": 144,6632 "n_groups": 136633 },6634 "exact_match": {6635 "mean": 0.0,6636 "ci_low": 0.0,6637 "ci_high": 0.0,6638 "n_items": 144,6639 "n_groups": 136640 },6641 "number_recall": {6642 "mean": 0.9560736331569664,6643 "ci_low": 0.8973976061893298,6644 "ci_high": 0.9903568443259164,6645 "n_items": 144,6646 "n_groups": 136647 },6648 "placeholders_exact": {6649 "mean": 0.9305555555555556,6650 "ci_low": 0.8717948717948718,6651 "ci_high": 1.0,6652 "n_items": 144,6653 "n_groups": 136654 }6655 },6656 "mathematics": {6657 "n": 54,6658 "chrf": {6659 "mean": 67.33523361198483,6660 "ci_low": 67.33523361198483,6661 "ci_high": 67.33523361198483,6662 "n_items": 54,6663 "n_groups": 16664 },6665 "edit_sim": {6666 "mean": 0.6154326277188642,6667 "ci_low": 0.6154326277188642,6668 "ci_high": 0.6154326277188642,6669 "n_items": 54,6670 "n_groups": 16671 },6672 "rougeL": {6673 "mean": 0.6414719858306086,6674 "ci_low": 0.6414719858306086,6675 "ci_high": 0.6414719858306086,6676 "n_items": 54,6677 "n_groups": 16678 },6679 "exact_match": {6680 "mean": 0.0,6681 "ci_low": 0.0,6682 "ci_high": 0.0,6683 "n_items": 54,6684 "n_groups": 16685 },6686 "number_recall": {6687 "mean": 0.9807098765432097,6688 "ci_low": 0.9807098765432097,6689 "ci_high": 0.9807098765432097,6690 "n_items": 54,6691 "n_groups": 16692 },6693 "placeholders_exact": {6694 "mean": 1.0,6695 "ci_low": 1.0,6696 "ci_high": 1.0,6697 "n_items": 54,6698 "n_groups": 16699 }6700 }6701 },6702 "by_era": {6703 "1980-1999": {6704 "n": 16,6705 "chrf": {6706 "mean": 71.89150566005401,6707 "ci_low": 62.36595674105207,6708 "ci_high": 75.06668863305465,6709 "n_items": 16,6710 "n_groups": 26711 },6712 "edit_sim": {6713 "mean": 0.6692486746824184,6714 "ci_low": 0.5878953771289538,6715 "ci_high": 0.6963664405335731,6716 "n_items": 16,6717 "n_groups": 26718 },6719 "rougeL": {6720 "mean": 0.697159995310223,6721 "ci_low": 0.6058644826999978,6722 "ci_high": 0.7275918328469647,6723 "n_items": 16,6724 "n_groups": 26725 },6726 "exact_match": {6727 "mean": 0.0,6728 "ci_low": 0.0,6729 "ci_high": 0.0,6730 "n_items": 16,6731 "n_groups": 26732 },6733 "number_recall": {6734 "mean": 0.9866071428571429,6735 "ci_low": 0.9821428571428572,6736 "ci_high": 1.0,6737 "n_items": 16,6738 "n_groups": 26739 },6740 "placeholders_exact": {6741 "mean": 1.0,6742 "ci_low": 1.0,6743 "ci_high": 1.0,6744 "n_items": 16,6745 "n_groups": 26746 }6747 },6748 "2000-2009": {6749 "n": 70,6750 "chrf": {6751 "mean": 69.05586457691146,6752 "ci_low": 63.92551268386097,6753 "ci_high": 69.53683506688498,6754 "n_items": 70,6755 "n_groups": 26756 },6757 "edit_sim": {6758 "mean": 0.6396515286982312,6759 "ci_low": 0.5782374100719424,6760 "ci_high": 0.6454091023194457,6761 "n_items": 70,6762 "n_groups": 26763 },6764 "rougeL": {6765 "mean": 0.6779950311035592,6766 "ci_low": 0.6080551445179364,6767 "ci_high": 0.6845518954709611,6768 "n_items": 70,6769 "n_groups": 26770 },6771 "exact_match": {6772 "mean": 0.0,6773 "ci_low": 0.0,6774 "ci_high": 0.0,6775 "n_items": 70,6776 "n_groups": 26777 },6778 "number_recall": {6779 "mean": 0.9699099099099099,6780 "ci_low": 0.9670889639639639,6781 "ci_high": 1.0,6782 "n_items": 70,6783 "n_groups": 26784 },6785 "placeholders_exact": {6786 "mean": 0.8285714285714286,6787 "ci_low": 0.8125,6788 "ci_high": 1.0,6789 "n_items": 70,6790 "n_groups": 26791 }6792 },6793 "2010-2017": {6794 "n": 416,6795 "chrf": {6796 "mean": 67.56726876331128,6797 "ci_low": 65.99674220466835,6798 "ci_high": 69.21085899224632,6799 "n_items": 416,6800 "n_groups": 356801 },6802 "edit_sim": {6803 "mean": 0.6271816539962114,6804 "ci_low": 0.6065382694896541,6805 "ci_high": 0.6498731672190722,6806 "n_items": 416,6807 "n_groups": 356808 },6809 "rougeL": {6810 "mean": 0.6506831749044921,6811 "ci_low": 0.6320120869483514,6812 "ci_high": 0.6723812980044337,6813 "n_items": 416,6814 "n_groups": 356815 },6816 "exact_match": {6817 "mean": 0.0,6818 "ci_low": 0.0,6819 "ci_high": 0.0,6820 "n_items": 416,6821 "n_groups": 356822 },6823 "number_recall": {6824 "mean": 0.9598531226928757,6825 "ci_low": 0.9359439624349289,6826 "ci_high": 0.9768844464847732,6827 "n_items": 416,6828 "n_groups": 356829 },6830 "placeholders_exact": {6831 "mean": 0.9471153846153846,6832 "ci_low": 0.9072975038206826,6833 "ci_high": 0.9844979184610967,6834 "n_items": 416,6835 "n_groups": 356836 }6837 }6838 },6839 "by_role": {6840 "abstract": {6841 "n": 63,6842 "chrf": {6843 "mean": 68.81245617526537,6844 "ci_low": 67.17353396079736,6845 "ci_high": 70.29362574290975,6846 "n_items": 63,6847 "n_groups": 96848 },6849 "edit_sim": {6850 "mean": 0.6356542989865452,6851 "ci_low": 0.6047750348296203,6852 "ci_high": 0.6598346262448734,6853 "n_items": 63,6854 "n_groups": 96855 },6856 "rougeL": {6857 "mean": 0.6664317042337193,6858 "ci_low": 0.6332260873255517,6859 "ci_high": 0.6941238712555045,6860 "n_items": 63,6861 "n_groups": 96862 },6863 "exact_match": {6864 "mean": 0.0,6865 "ci_low": 0.0,6866 "ci_high": 0.0,6867 "n_items": 63,6868 "n_groups": 96869 },6870 "number_recall": {6871 "mean": 0.9741269841269842,6872 "ci_low": 0.9393333333333335,6873 "ci_high": 1.0,6874 "n_items": 63,6875 "n_groups": 96876 },6877 "placeholders_exact": {6878 "mean": 1.0,6879 "ci_low": 1.0,6880 "ci_high": 1.0,6881 "n_items": 63,6882 "n_groups": 96883 }6884 },6885 "background": {6886 "n": 22,6887 "chrf": {6888 "mean": 70.40919681696901,6889 "ci_low": 65.58542516536743,6890 "ci_high": 75.23296846857058,6891 "n_items": 22,6892 "n_groups": 46893 },6894 "edit_sim": {6895 "mean": 0.6322395567583718,6896 "ci_low": 0.5811010797165491,6897 "ci_high": 0.6833780338001945,6898 "n_items": 22,6899 "n_groups": 46900 },6901 "rougeL": {6902 "mean": 0.6566909208845556,6903 "ci_low": 0.6055488397564543,6904 "ci_high": 0.7078330020126571,6905 "n_items": 22,6906 "n_groups": 46907 },6908 "exact_match": {6909 "mean": 0.0,6910 "ci_low": 0.0,6911 "ci_high": 0.0,6912 "n_items": 22,6913 "n_groups": 46914 },6915 "number_recall": {6916 "mean": 0.9085497835497836,6917 "ci_low": 0.8863636363636364,6918 "ci_high": 0.9307359307359309,6919 "n_items": 22,6920 "n_groups": 46921 },6922 "placeholders_exact": {6923 "mean": 0.8636363636363636,6924 "ci_low": 0.6086956521739131,6925 "ci_high": 1.0,6926 "n_items": 22,6927 "n_groups": 46928 }6929 },6930 "conclusion": {6931 "n": 60,6932 "chrf": {6933 "mean": 63.717911594740194,6934 "ci_low": 60.098526350601695,6935 "ci_high": 67.56759707176839,6936 "n_items": 60,6937 "n_groups": 96938 },6939 "edit_sim": {6940 "mean": 0.5823756871462075,6941 "ci_low": 0.5487579422238235,6942 "ci_high": 0.6178793207175192,6943 "n_items": 60,6944 "n_groups": 96945 },6946 "rougeL": {6947 "mean": 0.6109049717797156,6948 "ci_low": 0.580580300636186,6949 "ci_high": 0.6435597598415779,6950 "n_items": 60,6951 "n_groups": 96952 },6953 "exact_match": {6954 "mean": 0.0,6955 "ci_low": 0.0,6956 "ci_high": 0.0,6957 "n_items": 60,6958 "n_groups": 96959 },6960 "number_recall": {6961 "mean": 0.9833333333333333,6962 "ci_low": 0.9583333333333334,6963 "ci_high": 1.0,6964 "n_items": 60,6965 "n_groups": 96966 },6967 "placeholders_exact": {6968 "mean": 0.9,6969 "ci_low": 0.6666666666666666,6970 "ci_high": 1.0,6971 "n_items": 60,6972 "n_groups": 96973 }6974 },6975 "data": {6976 "n": 33,6977 "chrf": {6978 "mean": 71.23378123818136,6979 "ci_low": 65.70062001547748,6980 "ci_high": 75.03002890935035,6981 "n_items": 33,6982 "n_groups": 56983 },6984 "edit_sim": {6985 "mean": 0.6126394848089909,6986 "ci_low": 0.5661321630907079,6987 "ci_high": 0.6491681070339662,6988 "n_items": 33,6989 "n_groups": 56990 },6991 "rougeL": {6992 "mean": 0.666513949856515,6993 "ci_low": 0.6056359569470667,6994 "ci_high": 0.710511774063004,6995 "n_items": 33,6996 "n_groups": 56997 },6998 "exact_match": {6999 "mean": 0.0,7000 "ci_low": 0.0,7001 "ci_high": 0.0,7002 "n_items": 33,7003 "n_groups": 57004 },7005 "number_recall": {7006 "mean": 0.9577441077441077,7007 "ci_low": 0.9173015873015873,7008 "ci_high": 0.9923076923076923,7009 "n_items": 33,7010 "n_groups": 57011 },7012 "placeholders_exact": {7013 "mean": 0.9696969696969697,7014 "ci_low": 0.9302325581395349,7015 "ci_high": 1.0,7016 "n_items": 33,7017 "n_groups": 57018 }7019 },7020 "discussion": {7021 "n": 60,7022 "chrf": {7023 "mean": 66.08186120827627,7024 "ci_low": 63.6804032559537,7025 "ci_high": 68.21008341262568,7026 "n_items": 60,7027 "n_groups": 77028 },7029 "edit_sim": {7030 "mean": 0.6357685594614126,7031 "ci_low": 0.604101016088021,7032 "ci_high": 0.6746874310254011,7033 "n_items": 60,7034 "n_groups": 77035 },7036 "rougeL": {7037 "mean": 0.6350047805687153,7038 "ci_low": 0.5958568825211238,7039 "ci_high": 0.6779097407714938,7040 "n_items": 60,7041 "n_groups": 77042 },7043 "exact_match": {7044 "mean": 0.0,7045 "ci_low": 0.0,7046 "ci_high": 0.0,7047 "n_items": 60,7048 "n_groups": 77049 },7050 "number_recall": {7051 "mean": 0.9444444444444444,7052 "ci_low": 0.8271604938271605,7053 "ci_high": 1.0,7054 "n_items": 60,7055 "n_groups": 77056 },7057 "placeholders_exact": {7058 "mean": 0.8833333333333333,7059 "ci_low": 0.7291666666666666,7060 "ci_high": 1.0,7061 "n_items": 60,7062 "n_groups": 77063 }7064 },7065 "introduction": {7066 "n": 56,7067 "chrf": {7068 "mean": 66.39173500868758,7069 "ci_low": 63.285776657724405,7070 "ci_high": 69.97805043934879,7071 "n_items": 56,7072 "n_groups": 97073 },7074 "edit_sim": {7075 "mean": 0.6237058330211515,7076 "ci_low": 0.5751951341169275,7077 "ci_high": 0.6717129385126871,7078 "n_items": 56,7079 "n_groups": 97080 },7081 "rougeL": {7082 "mean": 0.641085169917592,7083 "ci_low": 0.5994344390628505,7084 "ci_high": 0.6838511851093025,7085 "n_items": 56,7086 "n_groups": 97087 },7088 "exact_match": {7089 "mean": 0.0,7090 "ci_low": 0.0,7091 "ci_high": 0.0,7092 "n_items": 56,7093 "n_groups": 97094 },7095 "number_recall": {7096 "mean": 0.9464285714285714,7097 "ci_low": 0.9,7098 "ci_high": 0.9833333333333333,7099 "n_items": 56,7100 "n_groups": 97101 },7102 "placeholders_exact": {7103 "mean": 0.9107142857142857,7104 "ci_low": 0.8059701492537313,7105 "ci_high": 1.0,7106 "n_items": 56,7107 "n_groups": 97108 }7109 },7110 "limitations": {7111 "n": 12,7112 "chrf": {7113 "mean": 64.73717889068958,7114 "ci_low": 64.54126637320557,7115 "ci_high": 64.93309140817358,7116 "n_items": 12,7117 "n_groups": 27118 },7119 "edit_sim": {7120 "mean": 0.5838755058278225,7121 "ci_low": 0.558204845771451,7122 "ci_high": 0.6095461658841942,7123 "n_items": 12,7124 "n_groups": 27125 },7126 "rougeL": {7127 "mean": 0.6278290024575325,7128 "ci_low": 0.5992791858271255,7129 "ci_high": 0.6563788190879394,7130 "n_items": 12,7131 "n_groups": 27132 },7133 "exact_match": {7134 "mean": 0.0,7135 "ci_low": 0.0,7136 "ci_high": 0.0,7137 "n_items": 12,7138 "n_groups": 27139 },7140 "number_recall": {7141 "mean": 1.0,7142 "ci_low": 1.0,7143 "ci_high": 1.0,7144 "n_items": 12,7145 "n_groups": 27146 },7147 "placeholders_exact": {7148 "mean": 1.0,7149 "ci_low": 1.0,7150 "ci_high": 1.0,7151 "n_items": 12,7152 "n_groups": 27153 }7154 },7155 "methods": {7156 "n": 69,7157 "chrf": {7158 "mean": 70.67551687548591,7159 "ci_low": 67.17552094793321,7160 "ci_high": 73.64238239191785,7161 "n_items": 69,7162 "n_groups": 117163 },7164 "edit_sim": {7165 "mean": 0.6602593647378732,7166 "ci_low": 0.6211148510398505,7167 "ci_high": 0.6952773384047424,7168 "n_items": 69,7169 "n_groups": 117170 },7171 "rougeL": {7172 "mean": 0.6968593411597133,7173 "ci_low": 0.6541871935900071,7174 "ci_high": 0.7339932253500001,7175 "n_items": 69,7176 "n_groups": 117177 },7178 "exact_match": {7179 "mean": 0.0,7180 "ci_low": 0.0,7181 "ci_high": 0.0,7182 "n_items": 69,7183 "n_groups": 117184 },7185 "number_recall": {7186 "mean": 0.9688146997929605,7187 "ci_low": 0.9409602272727272,7188 "ci_high": 0.9885284980430528,7189 "n_items": 69,7190 "n_groups": 117191 },7192 "placeholders_exact": {7193 "mean": 0.927536231884058,7194 "ci_low": 0.8441558441558441,7195 "ci_high": 1.0,7196 "n_items": 69,7197 "n_groups": 117198 }7199 },7200 "other": {7201 "n": 32,7202 "chrf": {7203 "mean": 74.30423298427299,7204 "ci_low": 71.20441056589085,7205 "ci_high": 75.77767257113607,7206 "n_items": 32,7207 "n_groups": 57208 },7209 "edit_sim": {7210 "mean": 0.6797656319658786,7211 "ci_low": 0.643580745826137,7212 "ci_high": 0.7209822167385058,7213 "n_items": 32,7214 "n_groups": 57215 },7216 "rougeL": {7217 "mean": 0.7053126722116594,7218 "ci_low": 0.6763087557983866,7219 "ci_high": 0.7285452772064395,7220 "n_items": 32,7221 "n_groups": 57222 },7223 "exact_match": {7224 "mean": 0.0,7225 "ci_low": 0.0,7226 "ci_high": 0.0,7227 "n_items": 32,7228 "n_groups": 57229 },7230 "number_recall": {7231 "mean": 0.9624255952380952,7232 "ci_low": 0.8901098901098903,7233 "ci_high": 1.0,7234 "n_items": 32,7235 "n_groups": 57236 },7237 "placeholders_exact": {7238 "mean": 0.8125,7239 "ci_low": 0.5909090909090909,7240 "ci_high": 1.0,7241 "n_items": 32,7242 "n_groups": 57243 }7244 },7245 "related_work": {7246 "n": 6,7247 "chrf": {7248 "mean": 65.40055099444285,7249 "ci_low": 65.40055099444285,7250 "ci_high": 65.40055099444285,7251 "n_items": 6,7252 "n_groups": 17253 },7254 "edit_sim": {7255 "mean": 0.6402274094095107,7256 "ci_low": 0.6402274094095107,7257 "ci_high": 0.6402274094095107,7258 "n_items": 6,7259 "n_groups": 17260 },7261 "rougeL": {7262 "mean": 0.643932968701952,7263 "ci_low": 0.643932968701952,7264 "ci_high": 0.643932968701952,7265 "n_items": 6,7266 "n_groups": 17267 },7268 "exact_match": {7269 "mean": 0.0,7270 "ci_low": 0.0,7271 "ci_high": 0.0,7272 "n_items": 6,7273 "n_groups": 17274 },7275 "number_recall": {7276 "mean": 0.8148148148148148,7277 "ci_low": 0.8148148148148148,7278 "ci_high": 0.8148148148148148,7279 "n_items": 6,7280 "n_groups": 17281 },7282 "placeholders_exact": {7283 "mean": 1.0,7284 "ci_low": 1.0,7285 "ci_high": 1.0,7286 "n_items": 6,7287 "n_groups": 17288 }7289 },7290 "results": {7291 "n": 62,7292 "chrf": {7293 "mean": 66.0436154089488,7294 "ci_low": 63.39136843201341,7295 "ci_high": 68.87539529401715,7296 "n_items": 62,7297 "n_groups": 87298 },7299 "edit_sim": {7300 "mean": 0.6151747509670296,7301 "ci_low": 0.5757491712272339,7302 "ci_high": 0.6659128638953996,7303 "n_items": 62,7304 "n_groups": 87305 },7306 "rougeL": {7307 "mean": 0.6413923176721632,7308 "ci_low": 0.6055703943781261,7309 "ci_high": 0.6853774345062031,7310 "n_items": 62,7311 "n_groups": 87312 },7313 "exact_match": {7314 "mean": 0.0,7315 "ci_low": 0.0,7316 "ci_high": 0.0,7317 "n_items": 62,7318 "n_groups": 87319 },7320 "number_recall": {7321 "mean": 0.9647301183403959,7322 "ci_low": 0.9333432534013929,7323 "ci_high": 0.9921014601710774,7324 "n_items": 62,7325 "n_groups": 87326 },7327 "placeholders_exact": {7328 "mean": 1.0,7329 "ci_low": 1.0,7330 "ci_high": 1.0,7331 "n_items": 62,7332 "n_groups": 87333 }7334 },7335 "theory": {7336 "n": 27,7337 "chrf": {7338 "mean": 67.89012259350463,7339 "ci_low": 65.77607861762628,7340 "ci_high": 70.95082279956245,7341 "n_items": 27,7342 "n_groups": 47343 },7344 "edit_sim": {7345 "mean": 0.6630843281805846,7346 "ci_low": 0.64058952332651,7347 "ci_high": 0.7097108818243356,7348 "n_items": 27,7349 "n_groups": 47350 },7351 "rougeL": {7352 "mean": 0.6814270609841219,7353 "ci_low": 0.6515981111257806,7354 "ci_high": 0.7422004327053475,7355 "n_items": 27,7356 "n_groups": 47357 },7358 "exact_match": {7359 "mean": 0.0,7360 "ci_low": 0.0,7361 "ci_high": 0.0,7362 "n_items": 27,7363 "n_groups": 47364 },7365 "number_recall": {7366 "mean": 1.0,7367 "ci_low": 1.0,7368 "ci_high": 1.0,7369 "n_items": 27,7370 "n_groups": 47371 },7372 "placeholders_exact": {7373 "mean": 0.9629629629629629,7374 "ci_low": 0.875,7375 "ci_high": 1.0,7376 "n_items": 27,7377 "n_groups": 47378 }7379 }7380 }7381 },7382 "htr-m1-tiny": {7383 "overall": {7384 "n": 502,7385 "chrf": {7386 "mean": 32.864094484172995,7387 "ci_low": 30.870800305133606,7388 "ci_high": 34.473730140988856,7389 "n_items": 502,7390 "n_groups": 397391 },7392 "edit_sim": {7393 "mean": 0.28731875598492707,7394 "ci_low": 0.2744869891662172,7395 "ci_high": 0.29880440437265043,7396 "n_items": 502,7397 "n_groups": 397398 },7399 "rougeL": {7400 "mean": 0.24058493025470046,7401 "ci_low": 0.22446976437933516,7402 "ci_high": 0.25466659481138487,7403 "n_items": 502,7404 "n_groups": 397405 },7406 "exact_match": {7407 "mean": 0.0,7408 "ci_low": 0.0,7409 "ci_high": 0.0,7410 "n_items": 502,7411 "n_groups": 397412 },7413 "number_recall": {7414 "mean": 0.5709301266883728,7415 "ci_low": 0.503361217704839,7416 "ci_high": 0.6591184588142488,7417 "n_items": 502,7418 "n_groups": 397419 },7420 "placeholders_exact": {7421 "mean": 0.6334661354581673,7422 "ci_low": 0.5052100628930818,7423 "ci_high": 0.7420883637297714,7424 "n_items": 502,7425 "n_groups": 397426 }7427 },7428 "by_variant": {7429 "A": {7430 "n": 83,7431 "chrf": {7432 "mean": 33.07156769458874,7433 "ci_low": 30.99392287051379,7434 "ci_high": 35.10804366335277,7435 "n_items": 83,7436 "n_groups": 367437 },7438 "edit_sim": {7439 "mean": 0.28848045415154605,7440 "ci_low": 0.27266181395025335,7441 "ci_high": 0.3052922785904164,7442 "n_items": 83,7443 "n_groups": 367444 },7445 "rougeL": {7446 "mean": 0.23939745672798293,7447 "ci_low": 0.2241723086656753,7448 "ci_high": 0.2533685927615092,7449 "n_items": 83,7450 "n_groups": 367451 },7452 "exact_match": {7453 "mean": 0.0,7454 "ci_low": 0.0,7455 "ci_high": 0.0,7456 "n_items": 83,7457 "n_groups": 367458 },7459 "number_recall": {7460 "mean": 0.5659756962607901,7461 "ci_low": 0.48014426460616244,7462 "ci_high": 0.6746024150556522,7463 "n_items": 83,7464 "n_groups": 367465 },7466 "placeholders_exact": {7467 "mean": 0.6385542168674698,7468 "ci_low": 0.49114249037227214,7469 "ci_high": 0.7572815533980582,7470 "n_items": 83,7471 "n_groups": 367472 }7473 },7474 "B": {7475 "n": 83,7476 "chrf": {7477 "mean": 35.587733164299,7478 "ci_low": 32.80264503448966,7479 "ci_high": 38.00100757597856,7480 "n_items": 83,7481 "n_groups": 377482 },7483 "edit_sim": {7484 "mean": 0.3045754251703215,7485 "ci_low": 0.28658737640703247,7486 "ci_high": 0.3205690544819298,7487 "n_items": 83,7488 "n_groups": 377489 },7490 "rougeL": {7491 "mean": 0.2665775936134248,7492 "ci_low": 0.24348790901196257,7493 "ci_high": 0.2853935366033134,7494 "n_items": 83,7495 "n_groups": 377496 },7497 "exact_match": {7498 "mean": 0.0,7499 "ci_low": 0.0,7500 "ci_high": 0.0,7501 "n_items": 83,7502 "n_groups": 377503 },7504 "number_recall": {7505 "mean": 0.6241798738457467,7506 "ci_low": 0.5471901643512324,7507 "ci_high": 0.7179712327896615,7508 "n_items": 83,7509 "n_groups": 377510 },7511 "placeholders_exact": {7512 "mean": 0.6626506024096386,7513 "ci_low": 0.5416666666666666,7514 "ci_high": 0.7669936161723633,7515 "n_items": 83,7516 "n_groups": 377517 }7518 },7519 "C": {7520 "n": 84,7521 "chrf": {7522 "mean": 32.12946843199234,7523 "ci_low": 29.489218364795704,7524 "ci_high": 35.188168391675724,7525 "n_items": 84,7526 "n_groups": 387527 },7528 "edit_sim": {7529 "mean": 0.28618697816162086,7530 "ci_low": 0.26923887636888205,7531 "ci_high": 0.30373938326817856,7532 "n_items": 84,7533 "n_groups": 387534 },7535 "rougeL": {7536 "mean": 0.24373330037921864,7537 "ci_low": 0.22176161624574733,7538 "ci_high": 0.26739218323837965,7539 "n_items": 84,7540 "n_groups": 387541 },7542 "exact_match": {7543 "mean": 0.0,7544 "ci_low": 0.0,7545 "ci_high": 0.0,7546 "n_items": 84,7547 "n_groups": 387548 },7549 "number_recall": {7550 "mean": 0.5767274797341242,7551 "ci_low": 0.504395585649328,7552 "ci_high": 0.6726102063672621,7553 "n_items": 84,7554 "n_groups": 387555 },7556 "placeholders_exact": {7557 "mean": 0.6071428571428571,7558 "ci_low": 0.48749198717948716,7559 "ci_high": 0.7230851063829786,7560 "n_items": 84,7561 "n_groups": 387562 }7563 },7564 "D": {7565 "n": 85,7566 "chrf": {7567 "mean": 31.21511784364206,7568 "ci_low": 27.996201075157813,7569 "ci_high": 33.56245778430242,7570 "n_items": 85,7571 "n_groups": 377572 },7573 "edit_sim": {7574 "mean": 0.27582559482167923,7575 "ci_low": 0.2548001537509841,7576 "ci_high": 0.2931588025174646,7577 "n_items": 85,7578 "n_groups": 377579 },7580 "rougeL": {7581 "mean": 0.22556056063641466,7582 "ci_low": 0.2050512505406832,7583 "ci_high": 0.24320361810678484,7584 "n_items": 85,7585 "n_groups": 377586 },7587 "exact_match": {7588 "mean": 0.0,7589 "ci_low": 0.0,7590 "ci_high": 0.0,7591 "n_items": 85,7592 "n_groups": 377593 },7594 "number_recall": {7595 "mean": 0.5666088042934828,7596 "ci_low": 0.49022111396650975,7597 "ci_high": 0.6523832714046355,7598 "n_items": 85,7599 "n_groups": 377600 },7601 "placeholders_exact": {7602 "mean": 0.6235294117647059,7603 "ci_low": 0.4925254678986022,7604 "ci_high": 0.7397513952308471,7605 "n_items": 85,7606 "n_groups": 377607 }7608 },7609 "E": {7610 "n": 167,7611 "chrf": {7612 "mean": 32.61612631598939,7613 "ci_low": 30.10743309145161,7614 "ci_high": 34.644551009086726,7615 "n_items": 167,7616 "n_groups": 387617 },7618 "edit_sim": {7619 "mean": 0.2845838071574819,7620 "ci_low": 0.2697432470694847,7621 "ci_high": 0.2967213335324346,7622 "n_items": 167,7623 "n_groups": 387624 },7625 "rougeL": {7626 "mean": 0.23432012529085733,7627 "ci_low": 0.2162238058296304,7628 "ci_high": 0.25005948921657134,7629 "n_items": 167,7630 "n_groups": 387631 },7632 "exact_match": {7633 "mean": 0.0,7634 "ci_low": 0.0,7635 "ci_high": 0.0,7636 "n_items": 167,7637 "n_groups": 387638 },7639 "number_recall": {7640 "mean": 0.5462105066832821,7641 "ci_low": 0.4624736862416503,7642 "ci_high": 0.6417299573419757,7643 "n_items": 167,7644 "n_groups": 387645 },7646 "placeholders_exact": {7647 "mean": 0.6347305389221557,7648 "ci_low": 0.5129401154401154,7649 "ci_high": 0.7425149700598802,7650 "n_items": 167,7651 "n_groups": 387652 }7653 }7654 },7655 "by_discipline": {7656 "biomedicine": {7657 "n": 184,7658 "chrf": {7659 "mean": 32.49953699426334,7660 "ci_low": 29.494974946163453,7661 "ci_high": 34.55440486832658,7662 "n_items": 184,7663 "n_groups": 197664 },7665 "edit_sim": {7666 "mean": 0.28203930320465603,7667 "ci_low": 0.26532004004843784,7668 "ci_high": 0.3026708119713607,7669 "n_items": 184,7670 "n_groups": 197671 },7672 "rougeL": {7673 "mean": 0.24471458019223913,7674 "ci_low": 0.22332815309097814,7675 "ci_high": 0.26113935977724106,7676 "n_items": 184,7677 "n_groups": 197678 },7679 "exact_match": {7680 "mean": 0.0,7681 "ci_low": 0.0,7682 "ci_high": 0.0,7683 "n_items": 184,7684 "n_groups": 197685 },7686 "number_recall": {7687 "mean": 0.5104636077632791,7688 "ci_low": 0.419842708022189,7689 "ci_high": 0.6555374692874691,7690 "n_items": 184,7691 "n_groups": 197692 },7693 "placeholders_exact": {7694 "mean": 0.6141304347826086,7695 "ci_low": 0.3539788972089857,7696 "ci_high": 0.7574136840440671,7697 "n_items": 184,7698 "n_groups": 197699 }7700 },7701 "computer_science": {7702 "n": 53,7703 "chrf": {7704 "mean": 36.315953338513104,7705 "ci_low": 24.75976651907004,7706 "ci_high": 40.63257013943116,7707 "n_items": 53,7708 "n_groups": 37709 },7710 "edit_sim": {7711 "mean": 0.30319672034770073,7712 "ci_low": 0.24062991683776508,7713 "ci_high": 0.3277722823119609,7714 "n_items": 53,7715 "n_groups": 37716 },7717 "rougeL": {7718 "mean": 0.2464538156121319,7719 "ci_low": 0.1802526414025264,7720 "ci_high": 0.2915750877448658,7721 "n_items": 53,7722 "n_groups": 37723 },7724 "exact_match": {7725 "mean": 0.0,7726 "ci_low": 0.0,7727 "ci_high": 0.0,7728 "n_items": 53,7729 "n_groups": 37730 },7731 "number_recall": {7732 "mean": 0.559748427672956,7733 "ci_low": 0.3333333333333333,7734 "ci_high": 0.8115942028985507,7735 "n_items": 53,7736 "n_groups": 37737 },7738 "placeholders_exact": {7739 "mean": 0.8867924528301887,7740 "ci_low": 0.75,7741 "ci_high": 1.0,7742 "n_items": 53,7743 "n_groups": 37744 }7745 },7746 "earth_sciences": {7747 "n": 22,7748 "chrf": {7749 "mean": 31.152131197869895,7750 "ci_low": 31.152131197869895,7751 "ci_high": 31.152131197869895,7752 "n_items": 22,7753 "n_groups": 17754 },7755 "edit_sim": {7756 "mean": 0.2914655019426739,7757 "ci_low": 0.2914655019426739,7758 "ci_high": 0.2914655019426739,7759 "n_items": 22,7760 "n_groups": 17761 },7762 "rougeL": {7763 "mean": 0.23022198548587475,7764 "ci_low": 0.23022198548587475,7765 "ci_high": 0.23022198548587475,7766 "n_items": 22,7767 "n_groups": 17768 },7769 "exact_match": {7770 "mean": 0.0,7771 "ci_low": 0.0,7772 "ci_high": 0.0,7773 "n_items": 22,7774 "n_groups": 17775 },7776 "number_recall": {7777 "mean": 0.6809917355371901,7778 "ci_low": 0.6809917355371901,7779 "ci_high": 0.6809917355371901,7780 "n_items": 22,7781 "n_groups": 17782 },7783 "placeholders_exact": {7784 "mean": 0.5,7785 "ci_low": 0.5,7786 "ci_high": 0.5,7787 "n_items": 22,7788 "n_groups": 17789 }7790 },7791 "engineering": {7792 "n": 45,7793 "chrf": {7794 "mean": 31.150887580969876,7795 "ci_low": 20.8687068092226,7796 "ci_high": 32.732761545854075,7797 "n_items": 45,7798 "n_groups": 27799 },7800 "edit_sim": {7801 "mean": 0.29174248643118716,7802 "ci_low": 0.2240438390548296,7803 "ci_high": 0.3021576629506268,7804 "n_items": 45,7805 "n_groups": 27806 },7807 "rougeL": {7808 "mean": 0.222670279724063,7809 "ci_low": 0.1564842344312726,7810 "ci_high": 0.2328527482306462,7811 "n_items": 45,7812 "n_groups": 27813 },7814 "exact_match": {7815 "mean": 0.0,7816 "ci_low": 0.0,7817 "ci_high": 0.0,7818 "n_items": 45,7819 "n_groups": 27820 },7821 "number_recall": {7822 "mean": 0.49737654320987656,7823 "ci_low": 0.24074074074074073,7824 "ci_high": 0.5368589743589743,7825 "n_items": 45,7826 "n_groups": 27827 },7828 "placeholders_exact": {7829 "mean": 0.6,7830 "ci_low": 0.5384615384615384,7831 "ci_high": 1.0,7832 "n_items": 45,7833 "n_groups": 27834 }7835 },7836 "life_sciences": {7837 "n": 144,7838 "chrf": {7839 "mean": 32.0713958925288,7840 "ci_low": 27.61052312771844,7841 "ci_high": 36.24923139788782,7842 "n_items": 144,7843 "n_groups": 137844 },7845 "edit_sim": {7846 "mean": 0.28371465056836154,7847 "ci_low": 0.25164735282866485,7848 "ci_high": 0.31227653673898875,7849 "n_items": 144,7850 "n_groups": 137851 },7852 "rougeL": {7853 "mean": 0.23475929413118735,7854 "ci_low": 0.19757354271589345,7855 "ci_high": 0.2730330402121034,7856 "n_items": 144,7857 "n_groups": 137858 },7859 "exact_match": {7860 "mean": 0.0,7861 "ci_low": 0.0,7862 "ci_high": 0.0,7863 "n_items": 144,7864 "n_groups": 137865 },7866 "number_recall": {7867 "mean": 0.7022045855379189,7868 "ci_low": 0.5674283377943359,7869 "ci_high": 0.8510740821151155,7870 "n_items": 144,7871 "n_groups": 137872 },7873 "placeholders_exact": {7874 "mean": 0.5138888888888888,7875 "ci_low": 0.33529326759605577,7876 "ci_high": 0.763651145602365,7877 "n_items": 144,7878 "n_groups": 137879 }7880 },7881 "mathematics": {7882 "n": 54,7883 "chrf": {7884 "mean": 34.957356687930826,7885 "ci_low": 34.957356687930826,7886 "ci_high": 34.957356687930826,7887 "n_items": 54,7888 "n_groups": 17889 },7890 "edit_sim": {7891 "mean": 0.2939591652289299,7892 "ci_low": 0.2939591652289299,7893 "ci_high": 0.2939591652289299,7894 "n_items": 54,7895 "n_groups": 17896 },7897 "rougeL": {7898 "mean": 0.25543917373854774,7899 "ci_low": 0.25543917373854774,7900 "ci_high": 0.25543917373854774,7901 "n_items": 54,7902 "n_groups": 17903 },7904 "exact_match": {7905 "mean": 0.0,7906 "ci_low": 0.0,7907 "ci_high": 0.0,7908 "n_items": 54,7909 "n_groups": 17910 },7911 "number_recall": {7912 "mean": 0.4543283362727807,7913 "ci_low": 0.4543283362727807,7914 "ci_high": 0.4543283362727807,7915 "n_items": 54,7916 "n_groups": 17917 },7918 "placeholders_exact": {7919 "mean": 0.8518518518518519,7920 "ci_low": 0.8518518518518519,7921 "ci_high": 0.8518518518518519,7922 "n_items": 54,7923 "n_groups": 17924 }7925 }7926 },7927 "by_era": {7928 "1980-1999": {7929 "n": 16,7930 "chrf": {7931 "mean": 26.694123460189214,7932 "ci_low": 26.210016074204457,7933 "ci_high": 28.146445618143474,7934 "n_items": 16,7935 "n_groups": 27936 },7937 "edit_sim": {7938 "mean": 0.2356963532669673,7939 "ci_low": 0.22527097618530453,7940 "ci_high": 0.26697248451195554,7941 "n_items": 16,7942 "n_groups": 27943 },7944 "rougeL": {7945 "mean": 0.19321748227199315,7946 "ci_low": 0.18750635177193534,7947 "ci_high": 0.21035087377216652,7948 "n_items": 16,7949 "n_groups": 27950 },7951 "exact_match": {7952 "mean": 0.0,7953 "ci_low": 0.0,7954 "ci_high": 0.0,7955 "n_items": 16,7956 "n_groups": 27957 },7958 "number_recall": {7959 "mean": 0.40625,7960 "ci_low": 0.375,7961 "ci_high": 0.4166666666666667,7962 "n_items": 16,7963 "n_groups": 27964 },7965 "placeholders_exact": {7966 "mean": 0.625,7967 "ci_low": 0.5,7968 "ci_high": 1.0,7969 "n_items": 16,7970 "n_groups": 27971 }7972 },7973 "2000-2009": {7974 "n": 70,7975 "chrf": {7976 "mean": 32.296585086664166,7977 "ci_low": 16.62026375663373,7978 "ci_high": 33.7662402113545,7979 "n_items": 70,7980 "n_groups": 27981 },7982 "edit_sim": {7983 "mean": 0.27308885699322777,7984 "ci_low": 0.203537170263789,7985 "ci_high": 0.27960932762411267,7986 "n_items": 70,7987 "n_groups": 27988 },7989 "rougeL": {7990 "mean": 0.2468706747514004,7991 "ci_low": 0.15796046822670343,7992 "ci_high": 0.2552060066130908,7993 "n_items": 70,7994 "n_groups": 27995 },7996 "exact_match": {7997 "mean": 0.0,7998 "ci_low": 0.0,7999 "ci_high": 0.0,8000 "n_items": 70,8001 "n_groups": 28002 },8003 "number_recall": {8004 "mean": 0.5073303916161057,8005 "ci_low": 0.46114261583011584,8006 "ci_high": 1.0,8007 "n_items": 70,8008 "n_groups": 28009 },8010 "placeholders_exact": {8011 "mean": 0.8285714285714286,8012 "ci_low": 0.8125,8013 "ci_high": 1.0,8014 "n_items": 70,8015 "n_groups": 28016 }8017 },8018 "2010-2017": {8019 "n": 416,8020 "chrf": {8021 "mean": 33.196895431791646,8022 "ci_low": 31.038915951997893,8023 "ci_high": 35.162529586396175,8024 "n_items": 416,8025 "n_groups": 358026 },8027 "edit_sim": {8028 "mean": 0.29169868716979797,8029 "ci_low": 0.2770061923544644,8030 "ci_high": 0.3046506495680751,8031 "n_items": 416,8032 "n_groups": 358033 },8034 "rougeL": {8035 "mean": 0.24134905778584062,8036 "ci_low": 0.22477410208945367,8037 "ci_high": 0.2580749413567238,8038 "n_items": 416,8039 "n_groups": 358040 },8041 "exact_match": {8042 "mean": 0.0,8043 "ci_low": 0.0,8044 "ci_high": 0.0,8045 "n_items": 416,8046 "n_groups": 358047 },8048 "number_recall": {8049 "mean": 0.5879658562125859,8050 "ci_low": 0.5113524095264027,8051 "ci_high": 0.6814626857951229,8052 "n_items": 416,8053 "n_groups": 358054 },8055 "placeholders_exact": {8056 "mean": 0.6009615384615384,8057 "ci_low": 0.4633431141942879,8058 "ci_high": 0.7256810551442405,8059 "n_items": 416,8060 "n_groups": 358061 }8062 }8063 },8064 "by_role": {8065 "abstract": {8066 "n": 63,8067 "chrf": {8068 "mean": 32.89476680880338,8069 "ci_low": 28.187055032269203,8070 "ci_high": 36.90106980054331,8071 "n_items": 63,8072 "n_groups": 98073 },8074 "edit_sim": {8075 "mean": 0.2884845051353506,8076 "ci_low": 0.26170740308265666,8077 "ci_high": 0.310302004383093,8078 "n_items": 63,8079 "n_groups": 98080 },8081 "rougeL": {8082 "mean": 0.23665588797925322,8083 "ci_low": 0.1949140919801325,8084 "ci_high": 0.2709805746936378,8085 "n_items": 63,8086 "n_groups": 98087 },8088 "exact_match": {8089 "mean": 0.0,8090 "ci_low": 0.0,8091 "ci_high": 0.0,8092 "n_items": 63,8093 "n_groups": 98094 },8095 "number_recall": {8096 "mean": 0.5279012345679012,8097 "ci_low": 0.3609852461156809,8098 "ci_high": 0.7496296296296298,8099 "n_items": 63,8100 "n_groups": 98101 },8102 "placeholders_exact": {8103 "mean": 0.9047619047619048,8104 "ci_low": 0.6896551724137931,8105 "ci_high": 1.0,8106 "n_items": 63,8107 "n_groups": 98108 }8109 },8110 "background": {8111 "n": 22,8112 "chrf": {8113 "mean": 28.115172559443224,8114 "ci_low": 15.90260344179139,8115 "ci_high": 36.127720620576376,8116 "n_items": 22,8117 "n_groups": 48118 },8119 "edit_sim": {8120 "mean": 0.24447786087690415,8121 "ci_low": 0.1693334641801111,8122 "ci_high": 0.29345162848107254,8123 "n_items": 22,8124 "n_groups": 48125 },8126 "rougeL": {8127 "mean": 0.1865656412572622,8128 "ci_low": 0.11734142451826553,8129 "ci_high": 0.23017224083718396,8130 "n_items": 22,8131 "n_groups": 48132 },8133 "exact_match": {8134 "mean": 0.0,8135 "ci_low": 0.0,8136 "ci_high": 0.0,8137 "n_items": 22,8138 "n_groups": 48139 },8140 "number_recall": {8141 "mean": 0.1883116883116883,8142 "ci_low": 0.08035714285714285,8143 "ci_high": 0.275,8144 "n_items": 22,8145 "n_groups": 48146 },8147 "placeholders_exact": {8148 "mean": 0.22727272727272727,8149 "ci_low": 0.0,8150 "ci_high": 0.7142857142857143,8151 "n_items": 22,8152 "n_groups": 48153 }8154 },8155 "conclusion": {8156 "n": 60,8157 "chrf": {8158 "mean": 27.482620711316166,8159 "ci_low": 21.1820126111011,8160 "ci_high": 33.09429610974568,8161 "n_items": 60,8162 "n_groups": 98163 },8164 "edit_sim": {8165 "mean": 0.2610967398942016,8166 "ci_low": 0.22160753295318844,8167 "ci_high": 0.2956613266446859,8168 "n_items": 60,8169 "n_groups": 98170 },8171 "rougeL": {8172 "mean": 0.2064528078480141,8173 "ci_low": 0.1676405363379482,8174 "ci_high": 0.2424721684284904,8175 "n_items": 60,8176 "n_groups": 98177 },8178 "exact_match": {8179 "mean": 0.0,8180 "ci_low": 0.0,8181 "ci_high": 0.0,8182 "n_items": 60,8183 "n_groups": 98184 },8185 "number_recall": {8186 "mean": 0.7883333333333333,8187 "ci_low": 0.5847222222222221,8188 "ci_high": 0.9777777777777777,8189 "n_items": 60,8190 "n_groups": 98191 },8192 "placeholders_exact": {8193 "mean": 0.8,8194 "ci_low": 0.5454545454545454,8195 "ci_high": 1.0,8196 "n_items": 60,8197 "n_groups": 98198 }8199 },8200 "data": {8201 "n": 33,8202 "chrf": {8203 "mean": 33.19101091408015,8204 "ci_low": 26.45401910930149,8205 "ci_high": 39.86982309449889,8206 "n_items": 33,8207 "n_groups": 58208 },8209 "edit_sim": {8210 "mean": 0.2874815378193248,8211 "ci_low": 0.2549288855505199,8212 "ci_high": 0.32854333594568363,8213 "n_items": 33,8214 "n_groups": 58215 },8216 "rougeL": {8217 "mean": 0.23965550114521328,8218 "ci_low": 0.1994915742678612,8219 "ci_high": 0.28706109921476647,8220 "n_items": 33,8221 "n_groups": 58222 },8223 "exact_match": {8224 "mean": 0.0,8225 "ci_low": 0.0,8226 "ci_high": 0.0,8227 "n_items": 33,8228 "n_groups": 58229 },8230 "number_recall": {8231 "mean": 0.42171717171717177,8232 "ci_low": 0.3246031746031746,8233 "ci_high": 0.4942652329749104,8234 "n_items": 33,8235 "n_groups": 58236 },8237 "placeholders_exact": {8238 "mean": 0.5454545454545454,8239 "ci_low": 0.2222222222222222,8240 "ci_high": 1.0,8241 "n_items": 33,8242 "n_groups": 58243 }8244 },8245 "discussion": {8246 "n": 60,8247 "chrf": {8248 "mean": 37.617082161821365,8249 "ci_low": 34.8099615269077,8250 "ci_high": 40.93136470524232,8251 "n_items": 60,8252 "n_groups": 78253 },8254 "edit_sim": {8255 "mean": 0.3206238603282104,8256 "ci_low": 0.3048072008636808,8257 "ci_high": 0.335328065121999,8258 "n_items": 60,8259 "n_groups": 78260 },8261 "rougeL": {8262 "mean": 0.2644551039758106,8263 "ci_low": 0.23855261647874024,8264 "ci_high": 0.29672142749016833,8265 "n_items": 60,8266 "n_groups": 78267 },8268 "exact_match": {8269 "mean": 0.0,8270 "ci_low": 0.0,8271 "ci_high": 0.0,8272 "n_items": 60,8273 "n_groups": 78274 },8275 "number_recall": {8276 "mean": 0.7486111111111111,8277 "ci_low": 0.5,8278 "ci_high": 1.0,8279 "n_items": 60,8280 "n_groups": 78281 },8282 "placeholders_exact": {8283 "mean": 0.48333333333333334,8284 "ci_low": 0.1875,8285 "ci_high": 0.7777777777777778,8286 "n_items": 60,8287 "n_groups": 78288 }8289 },8290 "introduction": {8291 "n": 56,8292 "chrf": {8293 "mean": 29.360005057701205,8294 "ci_low": 25.480637787789178,8295 "ci_high": 33.21615690067879,8296 "n_items": 56,8297 "n_groups": 98298 },8299 "edit_sim": {8300 "mean": 0.2720429405610013,8301 "ci_low": 0.2412425004349178,8302 "ci_high": 0.2963224373273699,8303 "n_items": 56,8304 "n_groups": 98305 },8306 "rougeL": {8307 "mean": 0.21265103656319514,8308 "ci_low": 0.19072145017398864,8309 "ci_high": 0.23669067227477497,8310 "n_items": 56,8311 "n_groups": 98312 },8313 "exact_match": {8314 "mean": 0.0,8315 "ci_low": 0.0,8316 "ci_high": 0.0,8317 "n_items": 56,8318 "n_groups": 98319 },8320 "number_recall": {8321 "mean": 0.6255411255411255,8322 "ci_low": 0.4216742252456538,8323 "ci_high": 0.846181818181818,8324 "n_items": 56,8325 "n_groups": 98326 },8327 "placeholders_exact": {8328 "mean": 0.35714285714285715,8329 "ci_low": 0.14285714285714285,8330 "ci_high": 0.6862745098039216,8331 "n_items": 56,8332 "n_groups": 98333 }8334 },8335 "limitations": {8336 "n": 12,8337 "chrf": {8338 "mean": 44.224433162546,8339 "ci_low": 43.83240287427196,8340 "ci_high": 44.61646345082002,8341 "n_items": 12,8342 "n_groups": 28343 },8344 "edit_sim": {8345 "mean": 0.36503416941345684,8346 "ci_low": 0.3493860230229366,8347 "ci_high": 0.38068231580397716,8348 "n_items": 12,8349 "n_groups": 28350 },8351 "rougeL": {8352 "mean": 0.3516511587133695,8353 "ci_low": 0.3293809924036886,8354 "ci_high": 0.3739213250230505,8355 "n_items": 12,8356 "n_groups": 28357 },8358 "exact_match": {8359 "mean": 0.0,8360 "ci_low": 0.0,8361 "ci_high": 0.0,8362 "n_items": 12,8363 "n_groups": 28364 },8365 "number_recall": {8366 "mean": 0.6666666666666666,8367 "ci_low": 0.3333333333333333,8368 "ci_high": 1.0,8369 "n_items": 12,8370 "n_groups": 28371 },8372 "placeholders_exact": {8373 "mean": 1.0,8374 "ci_low": 1.0,8375 "ci_high": 1.0,8376 "n_items": 12,8377 "n_groups": 28378 }8379 },8380 "methods": {8381 "n": 69,8382 "chrf": {8383 "mean": 31.819354749704647,8384 "ci_low": 27.04952613799918,8385 "ci_high": 35.65549310077974,8386 "n_items": 69,8387 "n_groups": 118388 },8389 "edit_sim": {8390 "mean": 0.280701964652064,8391 "ci_low": 0.24978982900014116,8392 "ci_high": 0.30736547464006797,8393 "n_items": 69,8394 "n_groups": 118395 },8396 "rougeL": {8397 "mean": 0.23816837305180644,8398 "ci_low": 0.20490590691059507,8399 "ci_high": 0.26537986363912586,8400 "n_items": 69,8401 "n_groups": 118402 },8403 "exact_match": {8404 "mean": 0.0,8405 "ci_low": 0.0,8406 "ci_high": 0.0,8407 "n_items": 69,8408 "n_groups": 118409 },8410 "number_recall": {8411 "mean": 0.39543180249701987,8412 "ci_low": 0.2798903447742733,8413 "ci_high": 0.49652782044263294,8414 "n_items": 69,8415 "n_groups": 118416 },8417 "placeholders_exact": {8418 "mean": 0.5507246376811594,8419 "ci_low": 0.26865671641791045,8420 "ci_high": 0.8125208333333332,8421 "n_items": 69,8422 "n_groups": 118423 }8424 },8425 "other": {8426 "n": 32,8427 "chrf": {8428 "mean": 32.362842915943304,8429 "ci_low": 27.01089322242955,8430 "ci_high": 38.13706853528385,8431 "n_items": 32,8432 "n_groups": 58433 },8434 "edit_sim": {8435 "mean": 0.2649831826247425,8436 "ci_low": 0.23141053164947256,8437 "ci_high": 0.3098925855900993,8438 "n_items": 32,8439 "n_groups": 58440 },8441 "rougeL": {8442 "mean": 0.21484023906524405,8443 "ci_low": 0.17543898014021134,8444 "ci_high": 0.2621613309864527,8445 "n_items": 32,8446 "n_groups": 58447 },8448 "exact_match": {8449 "mean": 0.0,8450 "ci_low": 0.0,8451 "ci_high": 0.0,8452 "n_items": 32,8453 "n_groups": 58454 },8455 "number_recall": {8456 "mean": 0.6116071428571428,8457 "ci_low": 0.42063492063492064,8458 "ci_high": 0.8669047619047606,8459 "n_items": 32,8460 "n_groups": 58461 },8462 "placeholders_exact": {8463 "mean": 0.5,8464 "ci_low": 0.18181818181818182,8465 "ci_high": 0.8181818181818182,8466 "n_items": 32,8467 "n_groups": 58468 }8469 },8470 "related_work": {8471 "n": 6,8472 "chrf": {8473 "mean": 36.04033625593898,8474 "ci_low": 36.04033625593898,8475 "ci_high": 36.04033625593898,8476 "n_items": 6,8477 "n_groups": 18478 },8479 "edit_sim": {8480 "mean": 0.31426202321724706,8481 "ci_low": 0.31426202321724706,8482 "ci_high": 0.31426202321724706,8483 "n_items": 6,8484 "n_groups": 18485 },8486 "rougeL": {8487 "mean": 0.2949699503803547,8488 "ci_low": 0.2949699503803547,8489 "ci_high": 0.2949699503803547,8490 "n_items": 6,8491 "n_groups": 18492 },8493 "exact_match": {8494 "mean": 0.0,8495 "ci_low": 0.0,8496 "ci_high": 0.0,8497 "n_items": 6,8498 "n_groups": 18499 },8500 "number_recall": {8501 "mean": 0.3148148148148148,8502 "ci_low": 0.3148148148148148,8503 "ci_high": 0.3148148148148148,8504 "n_items": 6,8505 "n_groups": 18506 },8507 "placeholders_exact": {8508 "mean": 1.0,8509 "ci_low": 1.0,8510 "ci_high": 1.0,8511 "n_items": 6,8512 "n_groups": 18513 }8514 },8515 "results": {8516 "n": 62,8517 "chrf": {8518 "mean": 34.27299209793996,8519 "ci_low": 30.614708962329342,8520 "ci_high": 37.91513318899014,8521 "n_items": 62,8522 "n_groups": 88523 },8524 "edit_sim": {8525 "mean": 0.2837908708702173,8526 "ci_low": 0.2556424717559754,8527 "ci_high": 0.3123127383723478,8528 "n_items": 62,8529 "n_groups": 88530 },8531 "rougeL": {8532 "mean": 0.25130684640228707,8533 "ci_low": 0.22233764615102258,8534 "ci_high": 0.28003114747588426,8535 "n_items": 62,8536 "n_groups": 88537 },8538 "exact_match": {8539 "mean": 0.0,8540 "ci_low": 0.0,8541 "ci_high": 0.0,8542 "n_items": 62,8543 "n_groups": 88544 },8545 "number_recall": {8546 "mean": 0.5558743088281722,8547 "ci_low": 0.36391663410169806,8548 "ci_high": 0.7739675305478912,8549 "n_items": 62,8550 "n_groups": 88551 },8552 "placeholders_exact": {8553 "mean": 0.967741935483871,8554 "ci_low": 0.8909090909090909,8555 "ci_high": 1.0,8556 "n_items": 62,8557 "n_groups": 88558 }8559 },8560 "theory": {8561 "n": 27,8562 "chrf": {8563 "mean": 39.200679015186836,8564 "ci_low": 32.515465044094896,8565 "ci_high": 44.548850192060385,8566 "n_items": 27,8567 "n_groups": 48568 },8569 "edit_sim": {8570 "mean": 0.3462049532449361,8571 "ci_low": 0.3016710322141039,8572 "ci_high": 0.3862156903758071,8573 "n_items": 27,8574 "n_groups": 48575 },8576 "rougeL": {8577 "mean": 0.3262645247518385,8578 "ci_low": 0.26317893112423224,8579 "ci_high": 0.39052940244699225,8580 "n_items": 27,8581 "n_groups": 48582 },8583 "exact_match": {8584 "mean": 0.0,8585 "ci_low": 0.0,8586 "ci_high": 0.0,8587 "n_items": 27,8588 "n_groups": 48589 },8590 "number_recall": {8591 "mean": 0.6234567901234569,8592 "ci_low": 0.23611111111111113,8593 "ci_high": 0.9166666666666666,8594 "n_items": 27,8595 "n_groups": 48596 },8597 "placeholders_exact": {8598 "mean": 0.3333333333333333,8599 "ci_low": 0.0,8600 "ci_high": 0.75,8601 "n_items": 27,8602 "n_groups": 48603 }8604 }8605 }8606 },8607 "htr-pilot_m1_tiny_denoiseinit_s2": {8608 "overall": {8609 "n": 502,8610 "chrf": {8611 "mean": 64.12217354737793,8612 "ci_low": 62.538592366593605,8613 "ci_high": 65.45416613513201,8614 "n_items": 502,8615 "n_groups": 398616 },8617 "edit_sim": {8618 "mean": 0.5816624787528646,8619 "ci_low": 0.5615344463056009,8620 "ci_high": 0.6004505859528196,8621 "n_items": 502,8622 "n_groups": 398623 },8624 "rougeL": {8625 "mean": 0.6031412886538868,8626 "ci_low": 0.5814478782241497,8627 "ci_high": 0.6220948983515935,8628 "n_items": 502,8629 "n_groups": 398630 },8631 "exact_match": {8632 "mean": 0.0,8633 "ci_low": 0.0,8634 "ci_high": 0.0,8635 "n_items": 502,8636 "n_groups": 398637 },8638 "number_recall": {8639 "mean": 0.9360757585089329,8640 "ci_low": 0.9088239976603834,8641 "ci_high": 0.9593214050991313,8642 "n_items": 502,8643 "n_groups": 398644 },8645 "placeholders_exact": {8646 "mean": 0.8784860557768924,8647 "ci_low": 0.8187001594896332,8648 "ci_high": 0.9356074532085561,8649 "n_items": 502,8650 "n_groups": 398651 }8652 },8653 "by_variant": {8654 "A": {8655 "n": 83,8656 "chrf": {8657 "mean": 62.25242956538081,8658 "ci_low": 59.700690291328435,8659 "ci_high": 64.07511207595272,8660 "n_items": 83,8661 "n_groups": 368662 },8663 "edit_sim": {8664 "mean": 0.5509085859327887,8665 "ci_low": 0.5242354200840532,8666 "ci_high": 0.5739681028704454,8667 "n_items": 83,8668 "n_groups": 368669 },8670 "rougeL": {8671 "mean": 0.5697745384969686,8672 "ci_low": 0.5396700261313306,8673 "ci_high": 0.5940496347549544,8674 "n_items": 83,8675 "n_groups": 368676 },8677 "exact_match": {8678 "mean": 0.0,8679 "ci_low": 0.0,8680 "ci_high": 0.0,8681 "n_items": 83,8682 "n_groups": 368683 },8684 "number_recall": {8685 "mean": 0.9276967545957459,8686 "ci_low": 0.8731947080425451,8687 "ci_high": 0.9650233859168023,8688 "n_items": 83,8689 "n_groups": 368690 },8691 "placeholders_exact": {8692 "mean": 0.8433734939759037,8693 "ci_low": 0.7698944860449285,8694 "ci_high": 0.9178082191780822,8695 "n_items": 83,8696 "n_groups": 368697 }8698 },8699 "B": {8700 "n": 83,8701 "chrf": {8702 "mean": 69.19810179885707,8703 "ci_low": 67.2178227695512,8704 "ci_high": 70.92187993349782,8705 "n_items": 83,8706 "n_groups": 378707 },8708 "edit_sim": {8709 "mean": 0.6529269485387869,8710 "ci_low": 0.6254618834383735,8711 "ci_high": 0.6815334097788466,8712 "n_items": 83,8713 "n_groups": 378714 },8715 "rougeL": {8716 "mean": 0.6739400726632702,8717 "ci_low": 0.6479878925858961,8718 "ci_high": 0.6992765996453177,8719 "n_items": 83,8720 "n_groups": 378721 },8722 "exact_match": {8723 "mean": 0.0,8724 "ci_low": 0.0,8725 "ci_high": 0.0,8726 "n_items": 83,8727 "n_groups": 378728 },8729 "number_recall": {8730 "mean": 0.9330507460606929,8731 "ci_low": 0.8955896276889552,8732 "ci_high": 0.9637630625426233,8733 "n_items": 83,8734 "n_groups": 378735 },8736 "placeholders_exact": {8737 "mean": 0.9156626506024096,8738 "ci_low": 0.8493150684931506,8739 "ci_high": 0.9756242740998837,8740 "n_items": 83,8741 "n_groups": 378742 }8743 },8744 "C": {8745 "n": 84,8746 "chrf": {8747 "mean": 66.53361806380232,8748 "ci_low": 64.56730410031406,8749 "ci_high": 68.1912994765944,8750 "n_items": 84,8751 "n_groups": 388752 },8753 "edit_sim": {8754 "mean": 0.6414324199535831,8755 "ci_low": 0.6138742098948945,8756 "ci_high": 0.6657982029220442,8757 "n_items": 84,8758 "n_groups": 388759 },8760 "rougeL": {8761 "mean": 0.6688023259360523,8762 "ci_low": 0.6450629943076874,8763 "ci_high": 0.6896221219491591,8764 "n_items": 84,8765 "n_groups": 388766 },8767 "exact_match": {8768 "mean": 0.0,8769 "ci_low": 0.0,8770 "ci_high": 0.0,8771 "n_items": 84,8772 "n_groups": 388773 },8774 "number_recall": {8775 "mean": 0.9647288082566322,8776 "ci_low": 0.9400595473880795,8777 "ci_high": 0.9827631757851745,8778 "n_items": 84,8779 "n_groups": 388780 },8781 "placeholders_exact": {8782 "mean": 0.8928571428571429,8783 "ci_low": 0.8202191011235955,8784 "ci_high": 0.9589110986860496,8785 "n_items": 84,8786 "n_groups": 388787 }8788 },8789 "D": {8790 "n": 85,8791 "chrf": {8792 "mean": 60.80531683325782,8793 "ci_low": 58.278597515818966,8794 "ci_high": 62.77201272633212,8795 "n_items": 85,8796 "n_groups": 378797 },8798 "edit_sim": {8799 "mean": 0.5270374809024545,8800 "ci_low": 0.5014029345990912,8801 "ci_high": 0.5508518633640737,8802 "n_items": 85,8803 "n_groups": 378804 },8805 "rougeL": {8806 "mean": 0.5487975145372015,8807 "ci_low": 0.5207188643800233,8808 "ci_high": 0.575458436043547,8809 "n_items": 85,8810 "n_groups": 378811 },8812 "exact_match": {8813 "mean": 0.0,8814 "ci_low": 0.0,8815 "ci_high": 0.0,8816 "n_items": 85,8817 "n_groups": 378818 },8819 "number_recall": {8820 "mean": 0.8847117546330951,8821 "ci_low": 0.8235083484779936,8822 "ci_high": 0.9347788423698232,8823 "n_items": 85,8824 "n_groups": 378825 },8826 "placeholders_exact": {8827 "mean": 0.8823529411764706,8828 "ci_low": 0.8160919540229885,8829 "ci_high": 0.9431977783452502,8830 "n_items": 85,8831 "n_groups": 378832 }8833 },8834 "E": {8835 "n": 167,8836 "chrf": {8837 "mean": 63.00395909799799,8838 "ci_low": 61.611017073223486,8839 "ci_high": 64.31455719454802,8840 "n_items": 167,8841 "n_groups": 388842 },8843 "edit_sim": {8844 "mean": 0.5592676995208838,8845 "ci_low": 0.5412347015049016,8846 "ci_high": 0.5781722159780981,8847 "n_items": 167,8848 "n_groups": 388849 },8850 "rougeL": {8851 "mean": 0.5791702399021609,8852 "ci_low": 0.5594383097200007,8853 "ci_high": 0.5983520592508426,8854 "n_items": 167,8855 "n_groups": 388856 },8857 "exact_match": {8858 "mean": 0.0,8859 "ci_low": 0.0,8860 "ci_high": 0.0,8861 "n_items": 167,8862 "n_groups": 388863 },8864 "number_recall": {8865 "mean": 0.9534746657462854,8866 "ci_low": 0.9322245755369449,8867 "ci_high": 0.9750077120638201,8868 "n_items": 167,8869 "n_groups": 388870 },8871 "placeholders_exact": {8872 "mean": 0.8682634730538922,8873 "ci_low": 0.7894736842105263,8874 "ci_high": 0.9473684210526315,8875 "n_items": 167,8876 "n_groups": 388877 }8878 }8879 },8880 "by_discipline": {8881 "biomedicine": {8882 "n": 184,8883 "chrf": {8884 "mean": 64.34517532279101,8885 "ci_low": 61.29548817799581,8886 "ci_high": 65.88953655148713,8887 "n_items": 184,8888 "n_groups": 198889 },8890 "edit_sim": {8891 "mean": 0.5895455724267366,8892 "ci_low": 0.555919454569626,8893 "ci_high": 0.610229790327301,8894 "n_items": 184,8895 "n_groups": 198896 },8897 "rougeL": {8898 "mean": 0.6126827512892802,8899 "ci_low": 0.5782076643527705,8900 "ci_high": 0.6298752503390775,8901 "n_items": 184,8902 "n_groups": 198903 },8904 "exact_match": {8905 "mean": 0.0,8906 "ci_low": 0.0,8907 "ci_high": 0.0,8908 "n_items": 184,8909 "n_groups": 198910 },8911 "number_recall": {8912 "mean": 0.9169692956320865,8913 "ci_low": 0.8610892050494033,8914 "ci_high": 0.9601206542091232,8915 "n_items": 184,8916 "n_groups": 198917 },8918 "placeholders_exact": {8919 "mean": 0.8641304347826086,8920 "ci_low": 0.8,8921 "ci_high": 0.9600234374999999,8922 "n_items": 184,8923 "n_groups": 198924 }8925 },8926 "computer_science": {8927 "n": 53,8928 "chrf": {8929 "mean": 62.6304017592149,8930 "ci_low": 60.77919113825706,8931 "ci_high": 66.34057697469342,8932 "n_items": 53,8933 "n_groups": 38934 },8935 "edit_sim": {8936 "mean": 0.579185251320851,8937 "ci_low": 0.559659811576524,8938 "ci_high": 0.6876225563316937,8939 "n_items": 53,8940 "n_groups": 38941 },8942 "rougeL": {8943 "mean": 0.5915978807916623,8944 "ci_low": 0.5782045701468136,8945 "ci_high": 0.6954527871553733,8946 "n_items": 53,8947 "n_groups": 38948 },8949 "exact_match": {8950 "mean": 0.0,8951 "ci_low": 0.0,8952 "ci_high": 0.0,8953 "n_items": 53,8954 "n_groups": 38955 },8956 "number_recall": {8957 "mean": 0.9811320754716981,8958 "ci_low": 0.9565217391304348,8959 "ci_high": 1.0,8960 "n_items": 53,8961 "n_groups": 38962 },8963 "placeholders_exact": {8964 "mean": 1.0,8965 "ci_low": 1.0,8966 "ci_high": 1.0,8967 "n_items": 53,8968 "n_groups": 38969 }8970 },8971 "earth_sciences": {8972 "n": 22,8973 "chrf": {8974 "mean": 70.24435847931197,8975 "ci_low": 70.24435847931197,8976 "ci_high": 70.24435847931197,8977 "n_items": 22,8978 "n_groups": 18979 },8980 "edit_sim": {8981 "mean": 0.646755767967938,8982 "ci_low": 0.646755767967938,8983 "ci_high": 0.646755767967938,8984 "n_items": 22,8985 "n_groups": 18986 },8987 "rougeL": {8988 "mean": 0.69123065359199,8989 "ci_low": 0.69123065359199,8990 "ci_high": 0.69123065359199,8991 "n_items": 22,8992 "n_groups": 18993 },8994 "exact_match": {8995 "mean": 0.0,8996 "ci_low": 0.0,8997 "ci_high": 0.0,8998 "n_items": 22,8999 "n_groups": 19000 },9001 "number_recall": {9002 "mean": 0.9570247933884297,9003 "ci_low": 0.9570247933884297,9004 "ci_high": 0.9570247933884297,9005 "n_items": 22,9006 "n_groups": 19007 },9008 "placeholders_exact": {9009 "mean": 1.0,9010 "ci_low": 1.0,9011 "ci_high": 1.0,9012 "n_items": 22,9013 "n_groups": 19014 }9015 },9016 "engineering": {9017 "n": 45,9018 "chrf": {9019 "mean": 62.31578564077828,9020 "ci_low": 61.82750860106604,9021 "ci_high": 65.48958639890765,9022 "n_items": 45,9023 "n_groups": 29024 },9025 "edit_sim": {9026 "mean": 0.5043768268661161,9027 "ci_low": 0.5018754086651409,9028 "ci_high": 0.5206360451724553,9029 "n_items": 45,9030 "n_groups": 29031 },9032 "rougeL": {9033 "mean": 0.531158768207819,9034 "ci_low": 0.5256925527788382,9035 "ci_high": 0.5666891684961951,9036 "n_items": 45,9037 "n_groups": 29038 },9039 "exact_match": {9040 "mean": 0.0,9041 "ci_low": 0.0,9042 "ci_high": 0.0,9043 "n_items": 45,9044 "n_groups": 29045 },9046 "number_recall": {9047 "mean": 0.9794753086419752,9048 "ci_low": 0.9791666666666666,9049 "ci_high": 0.9814814814814815,9050 "n_items": 45,9051 "n_groups": 29052 },9053 "placeholders_exact": {9054 "mean": 0.9111111111111111,9055 "ci_low": 0.8974358974358975,9056 "ci_high": 1.0,9057 "n_items": 45,9058 "n_groups": 29059 }9060 },9061 "life_sciences": {9062 "n": 144,9063 "chrf": {9064 "mean": 63.490628685034885,9065 "ci_low": 59.81189492681026,9066 "ci_high": 66.1406579798303,9067 "n_items": 144,9068 "n_groups": 139069 },9070 "edit_sim": {9071 "mean": 0.5847473788569092,9072 "ci_low": 0.5518855818933798,9073 "ci_high": 0.6183324274175132,9074 "n_items": 144,9075 "n_groups": 139076 },9077 "rougeL": {9078 "mean": 0.6013131415951629,9079 "ci_low": 0.5656324972753383,9080 "ci_high": 0.628487906161812,9081 "n_items": 144,9082 "n_groups": 139083 },9084 "exact_match": {9085 "mean": 0.0,9086 "ci_low": 0.0,9087 "ci_high": 0.0,9088 "n_items": 144,9089 "n_groups": 139090 },9091 "number_recall": {9092 "mean": 0.9282627865961199,9093 "ci_low": 0.8591629219811994,9094 "ci_high": 0.9704457905595815,9095 "n_items": 144,9096 "n_groups": 139097 },9098 "placeholders_exact": {9099 "mean": 0.7916666666666666,9100 "ci_low": 0.6848484848484848,9101 "ci_high": 0.9310759283819626,9102 "n_items": 144,9103 "n_groups": 139104 }9105 },9106 "mathematics": {9107 "n": 54,9108 "chrf": {9109 "mean": 65.52168142827551,9110 "ci_low": 65.52168142827551,9111 "ci_high": 65.52168142827551,9112 "n_items": 54,9113 "n_groups": 19114 },9115 "edit_sim": {9116 "mean": 0.5868917412546036,9117 "ci_low": 0.5868917412546036,9118 "ci_high": 0.5868917412546036,9119 "n_items": 54,9120 "n_groups": 19121 },9122 "rougeL": {9123 "mean": 0.6109315119812299,9124 "ci_low": 0.6109315119812299,9125 "ci_high": 0.6109315119812299,9126 "n_items": 54,9127 "n_groups": 19128 },9129 "exact_match": {9130 "mean": 0.0,9131 "ci_low": 0.0,9132 "ci_high": 0.0,9133 "n_items": 54,9134 "n_groups": 19135 },9136 "number_recall": {9137 "mean": 0.9330908289241622,9138 "ci_low": 0.9330908289241622,9139 "ci_high": 0.9330908289241622,9140 "n_items": 54,9141 "n_groups": 19142 },9143 "placeholders_exact": {9144 "mean": 0.9629629629629629,9145 "ci_low": 0.9629629629629629,9146 "ci_high": 0.9629629629629629,9147 "n_items": 54,9148 "n_groups": 19149 }9150 }9151 },9152 "by_era": {9153 "1980-1999": {9154 "n": 16,9155 "chrf": {9156 "mean": 65.85251166340583,9157 "ci_low": 59.04445511069966,9158 "ci_high": 68.12186384764121,9159 "n_items": 16,9160 "n_groups": 29161 },9162 "edit_sim": {9163 "mean": 0.5495589031901957,9164 "ci_low": 0.5466217321512574,9165 "ci_high": 0.5583704163070107,9166 "n_items": 16,9167 "n_groups": 29168 },9169 "rougeL": {9170 "mean": 0.5827224869143555,9171 "ci_low": 0.5550914094744589,9172 "ci_high": 0.5919328460609875,9173 "n_items": 16,9174 "n_groups": 29175 },9176 "exact_match": {9177 "mean": 0.0,9178 "ci_low": 0.0,9179 "ci_high": 0.0,9180 "n_items": 16,9181 "n_groups": 29182 },9183 "number_recall": {9184 "mean": 0.8895089285714286,9185 "ci_low": 0.84375,9186 "ci_high": 0.9047619047619048,9187 "n_items": 16,9188 "n_groups": 29189 },9190 "placeholders_exact": {9191 "mean": 1.0,9192 "ci_low": 1.0,9193 "ci_high": 1.0,9194 "n_items": 16,9195 "n_groups": 29196 }9197 },9198 "2000-2009": {9199 "n": 70,9200 "chrf": {9201 "mean": 65.50603687453871,9202 "ci_low": 59.99269947386981,9203 "ci_high": 66.0229122558514,9204 "n_items": 70,9205 "n_groups": 29206 },9207 "edit_sim": {9208 "mean": 0.6041332618193045,9209 "ci_low": 0.5812350119904076,9210 "ci_high": 0.6062799727407634,9211 "n_items": 70,9212 "n_groups": 29213 },9214 "rougeL": {9215 "mean": 0.6294637181645435,9216 "ci_low": 0.5335460806613905,9217 "ci_high": 0.6384559966804642,9218 "n_items": 70,9219 "n_groups": 29220 },9221 "exact_match": {9222 "mean": 0.0,9223 "ci_low": 0.0,9224 "ci_high": 0.0,9225 "n_items": 70,9226 "n_groups": 29227 },9228 "number_recall": {9229 "mean": 0.9327307409450266,9230 "ci_low": 0.9264242479086229,9231 "ci_high": 1.0,9232 "n_items": 70,9233 "n_groups": 29234 },9235 "placeholders_exact": {9236 "mean": 0.8142857142857143,9237 "ci_low": 0.796875,9238 "ci_high": 1.0,9239 "n_items": 70,9240 "n_groups": 29241 }9242 },9243 "2010-2017": {9244 "n": 416,9245 "chrf": {9246 "mean": 63.822760463825766,9247 "ci_low": 62.154568169010886,9248 "ci_high": 65.37186994167652,9249 "n_items": 416,9250 "n_groups": 359251 },9252 "edit_sim": {9253 "mean": 0.5791160902777489,9254 "ci_low": 0.5572639766698843,9255 "ci_high": 0.6015846213578083,9256 "n_items": 416,9257 "n_groups": 359258 },9259 "rougeL": {9260 "mean": 0.5994973722165948,9261 "ci_low": 0.577693156928724,9262 "ci_high": 0.6212849326104678,9263 "n_items": 416,9264 "n_groups": 359265 },9266 "exact_match": {9267 "mean": 0.0,9268 "ci_low": 0.0,9269 "ci_high": 0.0,9270 "n_items": 416,9271 "n_groups": 359272 },9273 "number_recall": {9274 "mean": 0.9384296539619942,9275 "ci_low": 0.904271732085239,9276 "ci_high": 0.9637943693908269,9277 "n_items": 416,9278 "n_groups": 359279 },9280 "placeholders_exact": {9281 "mean": 0.8846153846153846,9282 "ci_low": 0.8162278007861855,9283 "ci_high": 0.9438015477038998,9284 "n_items": 416,9285 "n_groups": 359286 }9287 }9288 },9289 "by_role": {9290 "abstract": {9291 "n": 63,9292 "chrf": {9293 "mean": 65.11839585867347,9294 "ci_low": 61.10482953085178,9295 "ci_high": 67.8505324428611,9296 "n_items": 63,9297 "n_groups": 99298 },9299 "edit_sim": {9300 "mean": 0.5925153249695821,9301 "ci_low": 0.5276213839869837,9302 "ci_high": 0.6399519618378211,9303 "n_items": 63,9304 "n_groups": 99305 },9306 "rougeL": {9307 "mean": 0.6098223194718614,9308 "ci_low": 0.5407384182940791,9309 "ci_high": 0.6600931476232775,9310 "n_items": 63,9311 "n_groups": 99312 },9313 "exact_match": {9314 "mean": 0.0,9315 "ci_low": 0.0,9316 "ci_high": 0.0,9317 "n_items": 63,9318 "n_groups": 99319 },9320 "number_recall": {9321 "mean": 0.9434920634920636,9322 "ci_low": 0.8429383928571428,9323 "ci_high": 1.0,9324 "n_items": 63,9325 "n_groups": 99326 },9327 "placeholders_exact": {9328 "mean": 1.0,9329 "ci_low": 1.0,9330 "ci_high": 1.0,9331 "n_items": 63,9332 "n_groups": 99333 }9334 },9335 "background": {9336 "n": 22,9337 "chrf": {9338 "mean": 63.76425391510547,9339 "ci_low": 58.33862586414111,9340 "ci_high": 70.95918395144238,9341 "n_items": 22,9342 "n_groups": 49343 },9344 "edit_sim": {9345 "mean": 0.562073187677602,9346 "ci_low": 0.5014758808520791,9347 "ci_high": 0.6487612313116324,9348 "n_items": 22,9349 "n_groups": 49350 },9351 "rougeL": {9352 "mean": 0.5871284935571919,9353 "ci_low": 0.5289766061409089,9354 "ci_high": 0.6534891186520363,9355 "n_items": 22,9356 "n_groups": 49357 },9358 "exact_match": {9359 "mean": 0.0,9360 "ci_low": 0.0,9361 "ci_high": 0.0,9362 "n_items": 22,9363 "n_groups": 49364 },9365 "number_recall": {9366 "mean": 0.8777056277056278,9367 "ci_low": 0.775,9368 "ci_high": 0.9642857142857143,9369 "n_items": 22,9370 "n_groups": 49371 },9372 "placeholders_exact": {9373 "mean": 0.6363636363636364,9374 "ci_low": 0.20833333333333334,9375 "ci_high": 0.95,9376 "n_items": 22,9377 "n_groups": 49378 }9379 },9380 "conclusion": {9381 "n": 60,9382 "chrf": {9383 "mean": 59.41574104463805,9384 "ci_low": 53.55655733102806,9385 "ci_high": 63.929889101940866,9386 "n_items": 60,9387 "n_groups": 99388 },9389 "edit_sim": {9390 "mean": 0.5343235238746051,9391 "ci_low": 0.47833800216041356,9392 "ci_high": 0.5731998894261486,9393 "n_items": 60,9394 "n_groups": 99395 },9396 "rougeL": {9397 "mean": 0.5576242887957118,9398 "ci_low": 0.5052395457484474,9399 "ci_high": 0.5985871943587855,9400 "n_items": 60,9401 "n_groups": 99402 },9403 "exact_match": {9404 "mean": 0.0,9405 "ci_low": 0.0,9406 "ci_high": 0.0,9407 "n_items": 60,9408 "n_groups": 99409 },9410 "number_recall": {9411 "mean": 0.9866666666666667,9412 "ci_low": 0.9555555555555555,9413 "ci_high": 1.0,9414 "n_items": 60,9415 "n_groups": 99416 },9417 "placeholders_exact": {9418 "mean": 0.8333333333333334,9419 "ci_low": 0.5925925925925926,9420 "ci_high": 1.0,9421 "n_items": 60,9422 "n_groups": 99423 }9424 },9425 "data": {9426 "n": 33,9427 "chrf": {9428 "mean": 66.83383098308444,9429 "ci_low": 62.25406308374134,9430 "ci_high": 69.65001583513532,9431 "n_items": 33,9432 "n_groups": 59433 },9434 "edit_sim": {9435 "mean": 0.5535572924113232,9436 "ci_low": 0.5275088191644894,9437 "ci_high": 0.5829668589803289,9438 "n_items": 33,9439 "n_groups": 59440 },9441 "rougeL": {9442 "mean": 0.6153724331384903,9443 "ci_low": 0.5673253192267455,9444 "ci_high": 0.6513110859887772,9445 "n_items": 33,9446 "n_groups": 59447 },9448 "exact_match": {9449 "mean": 0.0,9450 "ci_low": 0.0,9451 "ci_high": 0.0,9452 "n_items": 33,9453 "n_groups": 59454 },9455 "number_recall": {9456 "mean": 0.9259259259259259,9457 "ci_low": 0.9041666666666667,9458 "ci_high": 0.9525252525252526,9459 "n_items": 33,9460 "n_groups": 59461 },9462 "placeholders_exact": {9463 "mean": 0.7878787878787878,9464 "ci_low": 0.6285714285714286,9465 "ci_high": 1.0,9466 "n_items": 33,9467 "n_groups": 59468 }9469 },9470 "discussion": {9471 "n": 60,9472 "chrf": {9473 "mean": 62.89846261682713,9474 "ci_low": 61.24708695822154,9475 "ci_high": 64.72464557529742,9476 "n_items": 60,9477 "n_groups": 79478 },9479 "edit_sim": {9480 "mean": 0.5906348997792705,9481 "ci_low": 0.5531025879955026,9482 "ci_high": 0.6449105412817737,9483 "n_items": 60,9484 "n_groups": 79485 },9486 "rougeL": {9487 "mean": 0.5902793762501861,9488 "ci_low": 0.5574187157296175,9489 "ci_high": 0.6279231201575918,9490 "n_items": 60,9491 "n_groups": 79492 },9493 "exact_match": {9494 "mean": 0.0,9495 "ci_low": 0.0,9496 "ci_high": 0.0,9497 "n_items": 60,9498 "n_groups": 79499 },9500 "number_recall": {9501 "mean": 0.9055555555555554,9502 "ci_low": 0.7927489177489176,9503 "ci_high": 0.9907407407407409,9504 "n_items": 60,9505 "n_groups": 79506 },9507 "placeholders_exact": {9508 "mean": 0.8666666666666667,9509 "ci_low": 0.7360416666666667,9510 "ci_high": 1.0,9511 "n_items": 60,9512 "n_groups": 79513 }9514 },9515 "introduction": {9516 "n": 56,9517 "chrf": {9518 "mean": 63.410788978465156,9519 "ci_low": 58.31794922113747,9520 "ci_high": 67.86671860414995,9521 "n_items": 56,9522 "n_groups": 99523 },9524 "edit_sim": {9525 "mean": 0.5834716546318143,9526 "ci_low": 0.5208914248945865,9527 "ci_high": 0.6480050473391676,9528 "n_items": 56,9529 "n_groups": 99530 },9531 "rougeL": {9532 "mean": 0.5928596794606752,9533 "ci_low": 0.5330321329466677,9534 "ci_high": 0.6537019835154076,9535 "n_items": 56,9536 "n_groups": 99537 },9538 "exact_match": {9539 "mean": 0.0,9540 "ci_low": 0.0,9541 "ci_high": 0.0,9542 "n_items": 56,9543 "n_groups": 99544 },9545 "number_recall": {9546 "mean": 0.9594155844155845,9547 "ci_low": 0.8719851576994434,9548 "ci_high": 1.0,9549 "n_items": 56,9550 "n_groups": 99551 },9552 "placeholders_exact": {9553 "mean": 0.8392857142857143,9554 "ci_low": 0.6785714285714286,9555 "ci_high": 0.9622641509433962,9556 "n_items": 56,9557 "n_groups": 99558 }9559 },9560 "limitations": {9561 "n": 12,9562 "chrf": {9563 "mean": 62.21164438876741,9564 "ci_low": 61.26066045125939,9565 "ci_high": 63.16262832627543,9566 "n_items": 12,9567 "n_groups": 29568 },9569 "edit_sim": {9570 "mean": 0.5694321102081562,9571 "ci_low": 0.5340128902128694,9572 "ci_high": 0.604851330203443,9573 "n_items": 12,9574 "n_groups": 29575 },9576 "rougeL": {9577 "mean": 0.5961368961326968,9578 "ci_low": 0.5631146891549107,9579 "ci_high": 0.629159103110483,9580 "n_items": 12,9581 "n_groups": 29582 },9583 "exact_match": {9584 "mean": 0.0,9585 "ci_low": 0.0,9586 "ci_high": 0.0,9587 "n_items": 12,9588 "n_groups": 29589 },9590 "number_recall": {9591 "mean": 0.8333333333333334,9592 "ci_low": 0.6666666666666666,9593 "ci_high": 1.0,9594 "n_items": 12,9595 "n_groups": 29596 },9597 "placeholders_exact": {9598 "mean": 1.0,9599 "ci_low": 1.0,9600 "ci_high": 1.0,9601 "n_items": 12,9602 "n_groups": 29603 }9604 },9605 "methods": {9606 "n": 69,9607 "chrf": {9608 "mean": 67.74376567810803,9609 "ci_low": 64.19623487204527,9610 "ci_high": 70.93198589766045,9611 "n_items": 69,9612 "n_groups": 119613 },9614 "edit_sim": {9615 "mean": 0.6172324999001861,9616 "ci_low": 0.5597792769149093,9617 "ci_high": 0.6665339231614827,9618 "n_items": 69,9619 "n_groups": 119620 },9621 "rougeL": {9622 "mean": 0.6461781742398217,9623 "ci_low": 0.5931785184223545,9624 "ci_high": 0.6927423891627913,9625 "n_items": 69,9626 "n_groups": 119627 },9628 "exact_match": {9629 "mean": 0.0,9630 "ci_low": 0.0,9631 "ci_high": 0.0,9632 "n_items": 69,9633 "n_groups": 119634 },9635 "number_recall": {9636 "mean": 0.9557853378505553,9637 "ci_low": 0.9164235412474849,9638 "ci_high": 0.9875668449197861,9639 "n_items": 69,9640 "n_groups": 119641 },9642 "placeholders_exact": {9643 "mean": 0.927536231884058,9644 "ci_low": 0.8529411764705882,9645 "ci_high": 1.0,9646 "n_items": 69,9647 "n_groups": 119648 }9649 },9650 "other": {9651 "n": 32,9652 "chrf": {9653 "mean": 68.13265375128232,9654 "ci_low": 62.11250738252306,9655 "ci_high": 71.7453812025957,9656 "n_items": 32,9657 "n_groups": 59658 },9659 "edit_sim": {9660 "mean": 0.5968070697843888,9661 "ci_low": 0.5227397294393985,9662 "ci_high": 0.6636620509350398,9663 "n_items": 32,9664 "n_groups": 59665 },9666 "rougeL": {9667 "mean": 0.6177561817787275,9668 "ci_low": 0.5460743664343729,9669 "ci_high": 0.6652157466083941,9670 "n_items": 32,9671 "n_groups": 59672 },9673 "exact_match": {9674 "mean": 0.0,9675 "ci_low": 0.0,9676 "ci_high": 0.0,9677 "n_items": 32,9678 "n_groups": 59679 },9680 "number_recall": {9681 "mean": 0.9430803571428572,9682 "ci_low": 0.8351648351648352,9683 "ci_high": 1.0,9684 "n_items": 32,9685 "n_groups": 59686 },9687 "placeholders_exact": {9688 "mean": 0.6875,9689 "ci_low": 0.47058823529411764,9690 "ci_high": 0.9615384615384616,9691 "n_items": 32,9692 "n_groups": 59693 }9694 },9695 "related_work": {9696 "n": 6,9697 "chrf": {9698 "mean": 63.13925172535328,9699 "ci_low": 63.13925172535328,9700 "ci_high": 63.13925172535328,9701 "n_items": 6,9702 "n_groups": 19703 },9704 "edit_sim": {9705 "mean": 0.5709184024257961,9706 "ci_low": 0.5709184024257961,9707 "ci_high": 0.5709184024257961,9708 "n_items": 6,9709 "n_groups": 19710 },9711 "rougeL": {9712 "mean": 0.6425551815852316,9713 "ci_low": 0.6425551815852316,9714 "ci_high": 0.6425551815852316,9715 "n_items": 6,9716 "n_groups": 19717 },9718 "exact_match": {9719 "mean": 0.0,9720 "ci_low": 0.0,9721 "ci_high": 0.0,9722 "n_items": 6,9723 "n_groups": 19724 },9725 "number_recall": {9726 "mean": 0.7777777777777778,9727 "ci_low": 0.7777777777777778,9728 "ci_high": 0.7777777777777778,9729 "n_items": 6,9730 "n_groups": 19731 },9732 "placeholders_exact": {9733 "mean": 1.0,9734 "ci_low": 1.0,9735 "ci_high": 1.0,9736 "n_items": 6,9737 "n_groups": 19738 }9739 },9740 "results": {9741 "n": 62,9742 "chrf": {9743 "mean": 61.62659743091665,9744 "ci_low": 59.66471393990593,9745 "ci_high": 63.46614896727628,9746 "n_items": 62,9747 "n_groups": 89748 },9749 "edit_sim": {9750 "mean": 0.5643096974324938,9751 "ci_low": 0.535450434944105,9752 "ci_high": 0.6015409208466195,9753 "n_items": 62,9754 "n_groups": 89755 },9756 "rougeL": {9757 "mean": 0.582684276047564,9758 "ci_low": 0.5559851128199094,9759 "ci_high": 0.6103728902167151,9760 "n_items": 62,9761 "n_groups": 89762 },9763 "exact_match": {9764 "mean": 0.0,9765 "ci_low": 0.0,9766 "ci_high": 0.0,9767 "n_items": 62,9768 "n_groups": 89769 },9770 "number_recall": {9771 "mean": 0.9031348932793044,9772 "ci_low": 0.848973373320381,9773 "ci_high": 0.9614661654135339,9774 "n_items": 62,9775 "n_groups": 89776 },9777 "placeholders_exact": {9778 "mean": 1.0,9779 "ci_low": 1.0,9780 "ci_high": 1.0,9781 "n_items": 62,9782 "n_groups": 89783 }9784 },9785 "theory": {9786 "n": 27,9787 "chrf": {9788 "mean": 66.21839759505839,9789 "ci_low": 63.11579119385177,9790 "ci_high": 69.29393824958164,9791 "n_items": 27,9792 "n_groups": 49793 },9794 "edit_sim": {9795 "mean": 0.6269783073955089,9796 "ci_low": 0.5685283491776306,9797 "ci_high": 0.6690716586885171,9798 "n_items": 27,9799 "n_groups": 49800 },9801 "rougeL": {9802 "mean": 0.6507315139120057,9803 "ci_low": 0.5994907221443632,9804 "ci_high": 0.7076071121106706,9805 "n_items": 27,9806 "n_groups": 49807 },9808 "exact_match": {9809 "mean": 0.0,9810 "ci_low": 0.0,9811 "ci_high": 0.0,9812 "n_items": 27,9813 "n_groups": 49814 },9815 "number_recall": {9816 "mean": 0.9835390946502058,9817 "ci_low": 0.9703703703703703,9818 "ci_high": 1.0,9819 "n_items": 27,9820 "n_groups": 49821 },9822 "placeholders_exact": {9823 "mean": 0.8518518518518519,9824 "ci_low": 0.5,9825 "ci_high": 1.0,9826 "n_items": 27,9827 "n_groups": 49828 }9829 }9830 }9831 },9832 "htr-pilot_m3light_tiny_denoiseinit": {9833 "overall": {9834 "n": 502,9835 "chrf": {9836 "mean": 63.99858986107077,9837 "ci_low": 62.56214941171215,9838 "ci_high": 65.34551455490106,9839 "n_items": 502,9840 "n_groups": 399841 },9842 "edit_sim": {9843 "mean": 0.5840591409855569,9844 "ci_low": 0.5633406968452398,9845 "ci_high": 0.6045045170737277,9846 "n_items": 502,9847 "n_groups": 399848 },9849 "rougeL": {9850 "mean": 0.6057201785519856,9851 "ci_low": 0.5842194241570446,9852 "ci_high": 0.6248463023185595,9853 "n_items": 502,9854 "n_groups": 399855 },9856 "exact_match": {9857 "mean": 0.0,9858 "ci_low": 0.0,9859 "ci_high": 0.0,9860 "n_items": 502,9861 "n_groups": 399862 },9863 "number_recall": {9864 "mean": 0.9412974652164404,9865 "ci_low": 0.9228100205423516,9866 "ci_high": 0.9641982729847016,9867 "n_items": 502,9868 "n_groups": 399869 },9870 "placeholders_exact": {9871 "mean": 0.8784860557768924,9872 "ci_low": 0.8298247922306571,9873 "ci_high": 0.9306949733434883,9874 "n_items": 502,9875 "n_groups": 399876 }9877 },9878 "by_variant": {9879 "A": {9880 "n": 83,9881 "chrf": {9882 "mean": 62.10599354602174,9883 "ci_low": 60.78587689132302,9884 "ci_high": 63.51589244286736,9885 "n_items": 83,9886 "n_groups": 369887 },9888 "edit_sim": {9889 "mean": 0.5467361921125834,9890 "ci_low": 0.5227220282203768,9891 "ci_high": 0.56944530159431,9892 "n_items": 83,9893 "n_groups": 369894 },9895 "rougeL": {9896 "mean": 0.5685396181716212,9897 "ci_low": 0.543148837094718,9898 "ci_high": 0.5905714921990016,9899 "n_items": 83,9900 "n_groups": 369901 },9902 "exact_match": {9903 "mean": 0.0,9904 "ci_low": 0.0,9905 "ci_high": 0.0,9906 "n_items": 83,9907 "n_groups": 369908 },9909 "number_recall": {9910 "mean": 0.9383347975831864,9911 "ci_low": 0.9060444458050466,9912 "ci_high": 0.9713658136326716,9913 "n_items": 83,9914 "n_groups": 369915 },9916 "placeholders_exact": {9917 "mean": 0.8674698795180723,9918 "ci_low": 0.8099880952380953,9919 "ci_high": 0.9315068493150684,9920 "n_items": 83,9921 "n_groups": 369922 }9923 },9924 "B": {9925 "n": 83,9926 "chrf": {9927 "mean": 69.25968508241579,9928 "ci_low": 67.17753691528782,9929 "ci_high": 71.0960046377064,9930 "n_items": 83,9931 "n_groups": 379932 },9933 "edit_sim": {9934 "mean": 0.6602026947118503,9935 "ci_low": 0.6279728138815308,9936 "ci_high": 0.6927204417905212,9937 "n_items": 83,9938 "n_groups": 379939 },9940 "rougeL": {9941 "mean": 0.6796567252891487,9942 "ci_low": 0.6495054295459058,9943 "ci_high": 0.7077676533343803,9944 "n_items": 83,9945 "n_groups": 379946 },9947 "exact_match": {9948 "mean": 0.0,9949 "ci_low": 0.0,9950 "ci_high": 0.0,9951 "n_items": 83,9952 "n_groups": 379953 },9954 "number_recall": {9955 "mean": 0.9624492667025588,9956 "ci_low": 0.9345129542602826,9957 "ci_high": 0.9872627131901295,9958 "n_items": 83,9959 "n_groups": 379960 },9961 "placeholders_exact": {9962 "mean": 0.8795180722891566,9963 "ci_low": 0.8137213359920239,9964 "ci_high": 0.9466842105263157,9965 "n_items": 83,9966 "n_groups": 379967 }9968 },9969 "C": {9970 "n": 84,9971 "chrf": {9972 "mean": 66.68787150707333,9973 "ci_low": 64.67888201597006,9974 "ci_high": 68.51111350023557,9975 "n_items": 84,9976 "n_groups": 389977 },9978 "edit_sim": {9979 "mean": 0.6425172365897026,9980 "ci_low": 0.6141113480656553,9981 "ci_high": 0.6676089408440484,9982 "n_items": 84,9983 "n_groups": 389984 },9985 "rougeL": {9986 "mean": 0.6722144442586178,9987 "ci_low": 0.6481955075192951,9988 "ci_high": 0.6940111876112707,9989 "n_items": 84,9990 "n_groups": 389991 },9992 "exact_match": {9993 "mean": 0.0,9994 "ci_low": 0.0,9995 "ci_high": 0.0,9996 "n_items": 84,9997 "n_groups": 389998 },9999 "number_recall": {10000 "mean": 0.9535401456975376,10001 "ci_low": 0.9326308530299612,10002 "ci_high": 0.9726524523317986,10003 "n_items": 84,10004 "n_groups": 3810005 },10006 "placeholders_exact": {10007 "mean": 0.8928571428571429,10008 "ci_low": 0.8390804597701149,10009 "ci_high": 0.9489839156001384,10010 "n_items": 84,10011 "n_groups": 3810012 }10013 },10014 "D": {10015 "n": 85,10016 "chrf": {10017 "mean": 61.732462417597624,10018 "ci_low": 59.80376040214844,10019 "ci_high": 63.743218726172344,10020 "n_items": 85,10021 "n_groups": 3710022 },10023 "edit_sim": {10024 "mean": 0.541029827063415,10025 "ci_low": 0.5194737037780102,10026 "ci_high": 0.5637037426268026,10027 "n_items": 85,10028 "n_groups": 3710029 },10030 "rougeL": {10031 "mean": 0.5620604438046575,10032 "ci_low": 0.5364489975165044,10033 "ci_high": 0.5858356201056272,10034 "n_items": 85,10035 "n_groups": 3710036 },10037 "exact_match": {10038 "mean": 0.0,10039 "ci_low": 0.0,10040 "ci_high": 0.0,10041 "n_items": 85,10042 "n_groups": 3710043 },10044 "number_recall": {10045 "mean": 0.91971098282179,10046 "ci_low": 0.8834704864090719,10047 "ci_high": 0.9584660191337517,10048 "n_items": 85,10049 "n_groups": 3710050 },10051 "placeholders_exact": {10052 "mean": 0.8941176470588236,10053 "ci_low": 0.8168870365047428,10054 "ci_high": 0.9541284403669725,10055 "n_items": 85,10056 "n_groups": 3710057 }10058 },10059 "E": {10060 "n": 167,10061 "chrf": {10062 "mean": 62.12515132938476,10063 "ci_low": 60.33322983552885,10064 "ci_high": 63.72617180248547,10065 "n_items": 167,10066 "n_groups": 3810067 },10068 "edit_sim": {10069 "mean": 0.5572621436790197,10070 "ci_low": 0.5364012884124387,10071 "ci_high": 0.5778931305099413,10072 "n_items": 167,10073 "n_groups": 3810074 },10075 "rougeL": {10076 "mean": 0.5762280364355272,10077 "ci_low": 0.5547026460912281,10078 "ci_high": 0.5967528605426814,10079 "n_items": 167,10080 "n_groups": 3810081 },10082 "exact_match": {10083 "mean": 0.0,10084 "ci_low": 0.0,10085 "ci_high": 0.0,10086 "n_items": 167,10087 "n_groups": 3810088 },10089 "number_recall": {10090 "mean": 0.9370864935598259,10091 "ci_low": 0.9148241020774258,10092 "ci_high": 0.9636839886457412,10093 "n_items": 167,10094 "n_groups": 3810095 },10096 "placeholders_exact": {10097 "mean": 0.8682634730538922,10098 "ci_low": 0.8060479797979798,10099 "ci_high": 0.9319842801985659,10100 "n_items": 167,10101 "n_groups": 3810102 }10103 }10104 },10105 "by_discipline": {10106 "biomedicine": {10107 "n": 184,10108 "chrf": {10109 "mean": 65.08852960162399,10110 "ci_low": 63.519159408723766,10111 "ci_high": 66.9586527124082,10112 "n_items": 184,10113 "n_groups": 1910114 },10115 "edit_sim": {10116 "mean": 0.5962965273243758,10117 "ci_low": 0.581201915729345,10118 "ci_high": 0.6175750164147219,10119 "n_items": 184,10120 "n_groups": 1910121 },10122 "rougeL": {10123 "mean": 0.6192171648949089,10124 "ci_low": 0.5971884501696261,10125 "ci_high": 0.6336548943875131,10126 "n_items": 184,10127 "n_groups": 1910128 },10129 "exact_match": {10130 "mean": 0.0,10131 "ci_low": 0.0,10132 "ci_high": 0.0,10133 "n_items": 184,10134 "n_groups": 1910135 },10136 "number_recall": {10137 "mean": 0.9267514820902081,10138 "ci_low": 0.8963066374899624,10139 "ci_high": 0.9716938163558888,10140 "n_items": 184,10141 "n_groups": 1910142 },10143 "placeholders_exact": {10144 "mean": 0.8532608695652174,10145 "ci_low": 0.7692307692307693,10146 "ci_high": 0.9508395029085138,10147 "n_items": 184,10148 "n_groups": 1910149 }10150 },10151 "computer_science": {10152 "n": 53,10153 "chrf": {10154 "mean": 62.015546444863695,10155 "ci_low": 60.43156943609434,10156 "ci_high": 64.59789584688366,10157 "n_items": 53,10158 "n_groups": 310159 },10160 "edit_sim": {10161 "mean": 0.5779123741942488,10162 "ci_low": 0.5655596049813282,10163 "ci_high": 0.6412704044397707,10164 "n_items": 53,10165 "n_groups": 310166 },10167 "rougeL": {10168 "mean": 0.5893275553484509,10169 "ci_low": 0.57923149926173,10170 "ci_high": 0.6671280128099215,10171 "n_items": 53,10172 "n_groups": 310173 },10174 "exact_match": {10175 "mean": 0.0,10176 "ci_low": 0.0,10177 "ci_high": 0.0,10178 "n_items": 53,10179 "n_groups": 310180 },10181 "number_recall": {10182 "mean": 0.9905660377358491,10183 "ci_low": 0.9791666666666666,10184 "ci_high": 1.0,10185 "n_items": 53,10186 "n_groups": 310187 },10188 "placeholders_exact": {10189 "mean": 1.0,10190 "ci_low": 1.0,10191 "ci_high": 1.0,10192 "n_items": 53,10193 "n_groups": 310194 }10195 },10196 "earth_sciences": {10197 "n": 22,10198 "chrf": {10199 "mean": 69.25658636856207,10200 "ci_low": 69.25658636856207,10201 "ci_high": 69.25658636856207,10202 "n_items": 22,10203 "n_groups": 110204 },10205 "edit_sim": {10206 "mean": 0.651917340917171,10207 "ci_low": 0.651917340917171,10208 "ci_high": 0.651917340917171,10209 "n_items": 22,10210 "n_groups": 110211 },10212 "rougeL": {10213 "mean": 0.6884163697853721,10214 "ci_low": 0.6884163697853721,10215 "ci_high": 0.6884163697853721,10216 "n_items": 22,10217 "n_groups": 110218 },10219 "exact_match": {10220 "mean": 0.0,10221 "ci_low": 0.0,10222 "ci_high": 0.0,10223 "n_items": 22,10224 "n_groups": 110225 },10226 "number_recall": {10227 "mean": 0.928099173553719,10228 "ci_low": 0.928099173553719,10229 "ci_high": 0.928099173553719,10230 "n_items": 22,10231 "n_groups": 110232 },10233 "placeholders_exact": {10234 "mean": 1.0,10235 "ci_low": 1.0,10236 "ci_high": 1.0,10237 "n_items": 22,10238 "n_groups": 110239 }10240 },10241 "engineering": {10242 "n": 45,10243 "chrf": {10244 "mean": 60.822310537287954,10245 "ci_low": 60.33025139739848,10246 "ci_high": 64.02069494656956,10247 "n_items": 45,10248 "n_groups": 210249 },10250 "edit_sim": {10251 "mean": 0.4923875099962777,10252 "ci_low": 0.48626647144316265,10253 "ci_high": 0.5321742605915268,10254 "n_items": 45,10255 "n_groups": 210256 },10257 "rougeL": {10258 "mean": 0.5252894940484617,10259 "ci_low": 0.518452120683771,10260 "ci_high": 0.569732420918951,10261 "n_items": 45,10262 "n_groups": 210263 },10264 "exact_match": {10265 "mean": 0.0,10266 "ci_low": 0.0,10267 "ci_high": 0.0,10268 "n_items": 45,10269 "n_groups": 210270 },10271 "number_recall": {10272 "mean": 0.895679012345679,10273 "ci_low": 0.8910256410256411,10274 "ci_high": 0.925925925925926,10275 "n_items": 45,10276 "n_groups": 210277 },10278 "placeholders_exact": {10279 "mean": 0.8,10280 "ci_low": 0.7692307692307693,10281 "ci_high": 1.0,10282 "n_items": 45,10283 "n_groups": 210284 }10285 },10286 "life_sciences": {10287 "n": 144,10288 "chrf": {10289 "mean": 63.457548311327955,10290 "ci_low": 59.590331169744125,10291 "ci_high": 66.23412071781537,10292 "n_items": 144,10293 "n_groups": 1310294 },10295 "edit_sim": {10296 "mean": 0.5891000192951381,10297 "ci_low": 0.5488605913072219,10298 "ci_high": 0.6237626041281389,10299 "n_items": 144,10300 "n_groups": 1310301 },10302 "rougeL": {10303 "mean": 0.6076337688864082,10304 "ci_low": 0.566659809727174,10305 "ci_high": 0.6387670322882264,10306 "n_items": 144,10307 "n_groups": 1310308 },10309 "exact_match": {10310 "mean": 0.0,10311 "ci_low": 0.0,10312 "ci_high": 0.0,10313 "n_items": 144,10314 "n_groups": 1310315 },10316 "number_recall": {10317 "mean": 0.9666391093474426,10318 "ci_low": 0.9356010709251988,10319 "ci_high": 0.9889489552138693,10320 "n_items": 144,10321 "n_groups": 1310322 },10323 "placeholders_exact": {10324 "mean": 0.8680555555555556,10325 "ci_low": 0.7618712273641851,10326 "ci_high": 0.96296977124183,10327 "n_items": 144,10328 "n_groups": 1310329 }10330 },10331 "mathematics": {10332 "n": 54,10333 "chrf": {10334 "mean": 64.17857168265532,10335 "ci_low": 64.17857168265532,10336 "ci_high": 64.17857168265532,10337 "n_items": 54,10338 "n_groups": 110339 },10340 "edit_sim": {10341 "mean": 0.5836990682640577,10342 "ci_low": 0.5836990682640577,10343 "ci_high": 0.5836990682640577,10344 "n_items": 54,10345 "n_groups": 110346 },10347 "rougeL": {10348 "mean": 0.6040511254048871,10349 "ci_low": 0.6040511254048871,10350 "ci_high": 0.6040511254048871,10351 "n_items": 54,10352 "n_groups": 110353 },10354 "exact_match": {10355 "mean": 0.0,10356 "ci_low": 0.0,10357 "ci_high": 0.0,10358 "n_items": 54,10359 "n_groups": 110360 },10361 "number_recall": {10362 "mean": 0.9183201058201057,10363 "ci_low": 0.9183201058201057,10364 "ci_high": 0.9183201058201057,10365 "n_items": 54,10366 "n_groups": 110367 },10368 "placeholders_exact": {10369 "mean": 0.8888888888888888,10370 "ci_low": 0.8888888888888888,10371 "ci_high": 0.8888888888888888,10372 "n_items": 54,10373 "n_groups": 110374 }10375 }10376 },10377 "by_era": {10378 "1980-1999": {10379 "n": 16,10380 "chrf": {10381 "mean": 67.44613884145433,10382 "ci_low": 58.99392151245412,10383 "ci_high": 70.26354461778772,10384 "n_items": 16,10385 "n_groups": 210386 },10387 "edit_sim": {10388 "mean": 0.6194595196389503,10389 "ci_low": 0.5502341890404234,10390 "ci_high": 0.6425346298384592,10391 "n_items": 16,10392 "n_groups": 210393 },10394 "rougeL": {10395 "mean": 0.6229792042526165,10396 "ci_low": 0.536149868262839,10397 "ci_high": 0.651922316249209,10398 "n_items": 16,10399 "n_groups": 210400 },10401 "exact_match": {10402 "mean": 0.0,10403 "ci_low": 0.0,10404 "ci_high": 0.0,10405 "n_items": 16,10406 "n_groups": 210407 },10408 "number_recall": {10409 "mean": 0.9564732142857142,10410 "ci_low": 0.9523809523809524,10411 "ci_high": 0.96875,10412 "n_items": 16,10413 "n_groups": 210414 },10415 "placeholders_exact": {10416 "mean": 1.0,10417 "ci_low": 1.0,10418 "ci_high": 1.0,10419 "n_items": 16,10420 "n_groups": 210421 }10422 },10423 "2000-2009": {10424 "n": 70,10425 "chrf": {10426 "mean": 63.95046814561048,10427 "ci_low": 58.33185562671872,10428 "ci_high": 64.47721306925658,10429 "n_items": 70,10430 "n_groups": 210431 },10432 "edit_sim": {10433 "mean": 0.582673047235574,10434 "ci_low": 0.5487868058086137,10435 "ci_high": 0.5858498823693516,10436 "n_items": 70,10437 "n_groups": 210438 },10439 "rougeL": {10440 "mean": 0.6139946081891187,10441 "ci_low": 0.51199438682316,10442 "ci_high": 0.6235571289421775,10443 "n_items": 70,10444 "n_groups": 210445 },10446 "exact_match": {10447 "mean": 0.0,10448 "ci_low": 0.0,10449 "ci_high": 0.0,10450 "n_items": 70,10451 "n_groups": 210452 },10453 "number_recall": {10454 "mean": 0.9111756143899001,10455 "ci_low": 0.9028483282389532,10456 "ci_high": 1.0,10457 "n_items": 70,10458 "n_groups": 210459 },10460 "placeholders_exact": {10461 "mean": 0.8285714285714286,10462 "ci_low": 0.8125,10463 "ci_high": 1.0,10464 "n_items": 70,10465 "n_groups": 210466 }10467 },10468 "2010-2017": {10469 "n": 416,10470 "chrf": {10471 "mean": 63.8740892274075,10472 "ci_low": 62.32199391881563,10473 "ci_high": 65.45309629895058,10474 "n_items": 416,10475 "n_groups": 3510476 },10477 "edit_sim": {10478 "mean": 0.5829308248895101,10479 "ci_low": 0.5588814378206429,10480 "ci_high": 0.6074227157229025,10481 "n_items": 416,10482 "n_groups": 3510483 },10484 "rougeL": {10485 "mean": 0.6036640379610975,10486 "ci_low": 0.5814715486292278,10487 "ci_high": 0.62691345895094,10488 "n_items": 416,10489 "n_groups": 3510490 },10491 "exact_match": {10492 "mean": 0.0,10493 "ci_low": 0.0,10494 "ci_high": 0.0,10495 "n_items": 416,10496 "n_groups": 3510497 },10498 "number_recall": {10499 "mean": 0.9457823632278575,10500 "ci_low": 0.9238924678612692,10501 "ci_high": 0.968899793172011,10502 "n_items": 416,10503 "n_groups": 3510504 },10505 "placeholders_exact": {10506 "mean": 0.8822115384615384,10507 "ci_low": 0.8206966403162056,10508 "ci_high": 0.9393239257259784,10509 "n_items": 416,10510 "n_groups": 3510511 }10512 }10513 },10514 "by_role": {10515 "abstract": {10516 "n": 63,10517 "chrf": {10518 "mean": 65.41614644678369,10519 "ci_low": 62.46800610291402,10520 "ci_high": 67.61584062329179,10521 "n_items": 63,10522 "n_groups": 910523 },10524 "edit_sim": {10525 "mean": 0.5902942955184581,10526 "ci_low": 0.5347581303393243,10527 "ci_high": 0.6304958850755608,10528 "n_items": 63,10529 "n_groups": 910530 },10531 "rougeL": {10532 "mean": 0.608745082126049,10533 "ci_low": 0.5432014415401976,10534 "ci_high": 0.6548647674134165,10535 "n_items": 63,10536 "n_groups": 910537 },10538 "exact_match": {10539 "mean": 0.0,10540 "ci_low": 0.0,10541 "ci_high": 0.0,10542 "n_items": 63,10543 "n_groups": 910544 },10545 "number_recall": {10546 "mean": 0.9442328042328042,10547 "ci_low": 0.8856080873758037,10548 "ci_high": 0.9831989247311829,10549 "n_items": 63,10550 "n_groups": 910551 },10552 "placeholders_exact": {10553 "mean": 1.0,10554 "ci_low": 1.0,10555 "ci_high": 1.0,10556 "n_items": 63,10557 "n_groups": 910558 }10559 },10560 "background": {10561 "n": 22,10562 "chrf": {10563 "mean": 63.081301100089696,10564 "ci_low": 56.88031234240837,10565 "ci_high": 71.14148782101714,10566 "n_items": 22,10567 "n_groups": 410568 },10569 "edit_sim": {10570 "mean": 0.5563741740846727,10571 "ci_low": 0.4786085500784211,10572 "ci_high": 0.6505329545513573,10573 "n_items": 22,10574 "n_groups": 410575 },10576 "rougeL": {10577 "mean": 0.5884965920150577,10578 "ci_low": 0.5308816806840778,10579 "ci_high": 0.6575529919678973,10580 "n_items": 22,10581 "n_groups": 410582 },10583 "exact_match": {10584 "mean": 0.0,10585 "ci_low": 0.0,10586 "ci_high": 0.0,10587 "n_items": 22,10588 "n_groups": 410589 },10590 "number_recall": {10591 "mean": 0.952922077922078,10592 "ci_low": 0.9166666666666666,10593 "ci_high": 0.9863945578231293,10594 "n_items": 22,10595 "n_groups": 410596 },10597 "placeholders_exact": {10598 "mean": 0.6818181818181818,10599 "ci_low": 0.21739130434782608,10600 "ci_high": 1.0,10601 "n_items": 22,10602 "n_groups": 410603 }10604 },10605 "conclusion": {10606 "n": 60,10607 "chrf": {10608 "mean": 59.12358896678917,10609 "ci_low": 53.272512065476725,10610 "ci_high": 63.703157955932134,10611 "n_items": 60,10612 "n_groups": 910613 },10614 "edit_sim": {10615 "mean": 0.5345341047350338,10616 "ci_low": 0.47744870178320714,10617 "ci_high": 0.576092810424112,10618 "n_items": 60,10619 "n_groups": 910620 },10621 "rougeL": {10622 "mean": 0.5617017095444371,10623 "ci_low": 0.5069933554812032,10624 "ci_high": 0.6046742337769002,10625 "n_items": 60,10626 "n_groups": 910627 },10628 "exact_match": {10629 "mean": 0.0,10630 "ci_low": 0.0,10631 "ci_high": 0.0,10632 "n_items": 60,10633 "n_groups": 910634 },10635 "number_recall": {10636 "mean": 0.9866666666666667,10637 "ci_low": 0.9555555555555555,10638 "ci_high": 1.0,10639 "n_items": 60,10640 "n_groups": 910641 },10642 "placeholders_exact": {10643 "mean": 0.8333333333333334,10644 "ci_low": 0.5925925925925926,10645 "ci_high": 1.0,10646 "n_items": 60,10647 "n_groups": 910648 }10649 },10650 "data": {10651 "n": 33,10652 "chrf": {10653 "mean": 67.07027646278145,10654 "ci_low": 62.04153166213606,10655 "ci_high": 70.65276088714761,10656 "n_items": 33,10657 "n_groups": 510658 },10659 "edit_sim": {10660 "mean": 0.5812831120612135,10661 "ci_low": 0.5344447063494264,10662 "ci_high": 0.625016647980203,10663 "n_items": 33,10664 "n_groups": 510665 },10666 "rougeL": {10667 "mean": 0.630717100381718,10668 "ci_low": 0.5689500780571207,10669 "ci_high": 0.676815156008117,10670 "n_items": 33,10671 "n_groups": 510672 },10673 "exact_match": {10674 "mean": 0.0,10675 "ci_low": 0.0,10676 "ci_high": 0.0,10677 "n_items": 33,10678 "n_groups": 510679 },10680 "number_recall": {10681 "mean": 0.9095117845117845,10682 "ci_low": 0.787962962962963,10683 "ci_high": 0.9602380952380952,10684 "n_items": 33,10685 "n_groups": 510686 },10687 "placeholders_exact": {10688 "mean": 0.9090909090909091,10689 "ci_low": 0.7906976744186046,10690 "ci_high": 1.0,10691 "n_items": 33,10692 "n_groups": 510693 }10694 },10695 "discussion": {10696 "n": 60,10697 "chrf": {10698 "mean": 62.636892295278905,10699 "ci_low": 59.97780321801142,10700 "ci_high": 65.64592028134629,10701 "n_items": 60,10702 "n_groups": 710703 },10704 "edit_sim": {10705 "mean": 0.5992174285567616,10706 "ci_low": 0.5535754102248699,10707 "ci_high": 0.6548621674284043,10708 "n_items": 60,10709 "n_groups": 710710 },10711 "rougeL": {10712 "mean": 0.5924984533984392,10713 "ci_low": 0.549997415245332,10714 "ci_high": 0.6396770370716892,10715 "n_items": 60,10716 "n_groups": 710717 },10718 "exact_match": {10719 "mean": 0.0,10720 "ci_low": 0.0,10721 "ci_high": 0.0,10722 "n_items": 60,10723 "n_groups": 710724 },10725 "number_recall": {10726 "mean": 0.923148148148148,10727 "ci_low": 0.8575498575498575,10728 "ci_high": 0.9848484848484849,10729 "n_items": 60,10730 "n_groups": 710731 },10732 "placeholders_exact": {10733 "mean": 0.8166666666666667,10734 "ci_low": 0.6295940170940171,10735 "ci_high": 0.9833333333333333,10736 "n_items": 60,10737 "n_groups": 710738 }10739 },10740 "introduction": {10741 "n": 56,10742 "chrf": {10743 "mean": 64.65716549408202,10744 "ci_low": 60.5739501415744,10745 "ci_high": 68.60369266054312,10746 "n_items": 56,10747 "n_groups": 910748 },10749 "edit_sim": {10750 "mean": 0.5912634785693466,10751 "ci_low": 0.5312147821255914,10752 "ci_high": 0.6465033313972237,10753 "n_items": 56,10754 "n_groups": 910755 },10756 "rougeL": {10757 "mean": 0.6003584824660386,10758 "ci_low": 0.5423371258659194,10759 "ci_high": 0.6537995750970239,10760 "n_items": 56,10761 "n_groups": 910762 },10763 "exact_match": {10764 "mean": 0.0,10765 "ci_low": 0.0,10766 "ci_high": 0.0,10767 "n_items": 56,10768 "n_groups": 910769 },10770 "number_recall": {10771 "mean": 0.9404761904761906,10772 "ci_low": 0.8615174129353235,10773 "ci_high": 1.0,10774 "n_items": 56,10775 "n_groups": 910776 },10777 "placeholders_exact": {10778 "mean": 0.75,10779 "ci_low": 0.5362318840579711,10780 "ci_high": 0.9622641509433962,10781 "n_items": 56,10782 "n_groups": 910783 }10784 },10785 "limitations": {10786 "n": 12,10787 "chrf": {10788 "mean": 60.278962812081225,10789 "ci_low": 59.57086383396077,10790 "ci_high": 60.98706179020167,10791 "n_items": 12,10792 "n_groups": 210793 },10794 "edit_sim": {10795 "mean": 0.5397388468153839,10796 "ci_low": 0.4962747723996775,10797 "ci_high": 0.5832029212310902,10798 "n_items": 12,10799 "n_groups": 210800 },10801 "rougeL": {10802 "mean": 0.583014917971097,10803 "ci_low": 0.5473013189910921,10804 "ci_high": 0.6187285169511019,10805 "n_items": 12,10806 "n_groups": 210807 },10808 "exact_match": {10809 "mean": 0.0,10810 "ci_low": 0.0,10811 "ci_high": 0.0,10812 "n_items": 12,10813 "n_groups": 210814 },10815 "number_recall": {10816 "mean": 1.0,10817 "ci_low": 1.0,10818 "ci_high": 1.0,10819 "n_items": 12,10820 "n_groups": 210821 },10822 "placeholders_exact": {10823 "mean": 1.0,10824 "ci_low": 1.0,10825 "ci_high": 1.0,10826 "n_items": 12,10827 "n_groups": 210828 }10829 },10830 "methods": {10831 "n": 69,10832 "chrf": {10833 "mean": 67.27846654089997,10834 "ci_low": 64.73743030957358,10835 "ci_high": 69.94025980384275,10836 "n_items": 69,10837 "n_groups": 1110838 },10839 "edit_sim": {10840 "mean": 0.6230607647061648,10841 "ci_low": 0.586397803807734,10842 "ci_high": 0.6569310734252283,10843 "n_items": 69,10844 "n_groups": 1110845 },10846 "rougeL": {10847 "mean": 0.6489017489896198,10848 "ci_low": 0.6127084040302673,10849 "ci_high": 0.6833470312140161,10850 "n_items": 69,10851 "n_groups": 1110852 },10853 "exact_match": {10854 "mean": 0.0,10855 "ci_low": 0.0,10856 "ci_high": 0.0,10857 "n_items": 69,10858 "n_groups": 1110859 },10860 "number_recall": {10861 "mean": 0.9543007716920762,10862 "ci_low": 0.933593084796501,10863 "ci_high": 0.9771447044334975,10864 "n_items": 69,10865 "n_groups": 1110866 },10867 "placeholders_exact": {10868 "mean": 0.9420289855072463,10869 "ci_low": 0.875,10870 "ci_high": 1.0,10871 "n_items": 69,10872 "n_groups": 1110873 }10874 },10875 "other": {10876 "n": 32,10877 "chrf": {10878 "mean": 68.3526338482213,10879 "ci_low": 60.942215733427744,10880 "ci_high": 72.63660315806511,10881 "n_items": 32,10882 "n_groups": 510883 },10884 "edit_sim": {10885 "mean": 0.5939291792624968,10886 "ci_low": 0.49992575398518874,10887 "ci_high": 0.6843972053897232,10888 "n_items": 32,10889 "n_groups": 510890 },10891 "rougeL": {10892 "mean": 0.6222067926078613,10893 "ci_low": 0.5514691321365793,10894 "ci_high": 0.6793946166186581,10895 "n_items": 32,10896 "n_groups": 510897 },10898 "exact_match": {10899 "mean": 0.0,10900 "ci_low": 0.0,10901 "ci_high": 0.0,10902 "n_items": 32,10903 "n_groups": 510904 },10905 "number_recall": {10906 "mean": 0.9375,10907 "ci_low": 0.7857142857142858,10908 "ci_high": 1.0,10909 "n_items": 32,10910 "n_groups": 510911 },10912 "placeholders_exact": {10913 "mean": 0.78125,10914 "ci_low": 0.5909090909090909,10915 "ci_high": 1.0,10916 "n_items": 32,10917 "n_groups": 510918 }10919 },10920 "related_work": {10921 "n": 6,10922 "chrf": {10923 "mean": 64.25497458823419,10924 "ci_low": 64.25497458823419,10925 "ci_high": 64.25497458823419,10926 "n_items": 6,10927 "n_groups": 110928 },10929 "edit_sim": {10930 "mean": 0.5842873179716587,10931 "ci_low": 0.5842873179716587,10932 "ci_high": 0.5842873179716587,10933 "n_items": 6,10934 "n_groups": 110935 },10936 "rougeL": {10937 "mean": 0.6243066673452068,10938 "ci_low": 0.6243066673452068,10939 "ci_high": 0.6243066673452068,10940 "n_items": 6,10941 "n_groups": 110942 },10943 "exact_match": {10944 "mean": 0.0,10945 "ci_low": 0.0,10946 "ci_high": 0.0,10947 "n_items": 6,10948 "n_groups": 110949 },10950 "number_recall": {10951 "mean": 0.7592592592592592,10952 "ci_low": 0.7592592592592592,10953 "ci_high": 0.7592592592592592,10954 "n_items": 6,10955 "n_groups": 110956 },10957 "placeholders_exact": {10958 "mean": 1.0,10959 "ci_low": 1.0,10960 "ci_high": 1.0,10961 "n_items": 6,10962 "n_groups": 110963 }10964 },10965 "results": {10966 "n": 62,10967 "chrf": {10968 "mean": 60.46670034641617,10969 "ci_low": 58.08325634551734,10970 "ci_high": 63.26550145891158,10971 "n_items": 62,10972 "n_groups": 810973 },10974 "edit_sim": {10975 "mean": 0.5542946303224281,10976 "ci_low": 0.5190532188564949,10977 "ci_high": 0.596819500315861,10978 "n_items": 62,10979 "n_groups": 810980 },10981 "rougeL": {10982 "mean": 0.5775224859266075,10983 "ci_low": 0.5466219216521097,10984 "ci_high": 0.6154790635149523,10985 "n_items": 62,10986 "n_groups": 810987 },10988 "exact_match": {10989 "mean": 0.0,10990 "ci_low": 0.0,10991 "ci_high": 0.0,10992 "n_items": 62,10993 "n_groups": 810994 },10995 "number_recall": {10996 "mean": 0.906232253043956,10997 "ci_low": 0.815556052904196,10998 "ci_high": 0.9852040816326532,10999 "n_items": 62,11000 "n_groups": 811001 },11002 "placeholders_exact": {11003 "mean": 1.0,11004 "ci_low": 1.0,11005 "ci_high": 1.0,11006 "n_items": 62,11007 "n_groups": 811008 }11009 },11010 "theory": {11011 "n": 27,11012 "chrf": {11013 "mean": 66.34169244542049,11014 "ci_low": 63.255697465422124,11015 "ci_high": 70.02422656646115,11016 "n_items": 27,11017 "n_groups": 411018 },11019 "edit_sim": {11020 "mean": 0.633516414114162,11021 "ci_low": 0.6033466154914345,11022 "ci_high": 0.672152486836656,11023 "n_items": 27,11024 "n_groups": 411025 },11026 "rougeL": {11027 "mean": 0.6612838569128721,11028 "ci_low": 0.6179017452246344,11029 "ci_high": 0.7219400493605369,11030 "n_items": 27,11031 "n_groups": 411032 },11033 "exact_match": {11034 "mean": 0.0,11035 "ci_low": 0.0,11036 "ci_high": 0.0,11037 "n_items": 27,11038 "n_groups": 411039 },11040 "number_recall": {11041 "mean": 0.9711934156378601,11042 "ci_low": 0.9444444444444443,11043 "ci_high": 1.0,11044 "n_items": 27,11045 "n_groups": 411046 },11047 "placeholders_exact": {11048 "mean": 0.8148148148148148,11049 "ci_low": 0.375,11050 "ci_high": 1.0,11051 "n_items": 27,11052 "n_groups": 411053 }11054 }11055 }11056 },11057 "htr-pilot_m3tokenonly_tiny_denoiseinit": {11058 "overall": {11059 "n": 502,11060 "chrf": {11061 "mean": 64.05827613904006,11062 "ci_low": 62.248400615748245,11063 "ci_high": 65.58520657192028,11064 "n_items": 502,11065 "n_groups": 3911066 },11067 "edit_sim": {11068 "mean": 0.5838102487806074,11069 "ci_low": 0.5609760648865554,11070 "ci_high": 0.604944879666314,11071 "n_items": 502,11072 "n_groups": 3911073 },11074 "rougeL": {11075 "mean": 0.6061122675661809,11076 "ci_low": 0.5823824578641973,11077 "ci_high": 0.6265518784128117,11078 "n_items": 502,11079 "n_groups": 3911080 },11081 "exact_match": {11082 "mean": 0.0,11083 "ci_low": 0.0,11084 "ci_high": 0.0,11085 "n_items": 502,11086 "n_groups": 3911087 },11088 "number_recall": {11089 "mean": 0.9519959226801625,11090 "ci_low": 0.9346470192642594,11091 "ci_high": 0.9703398341508833,11092 "n_items": 502,11093 "n_groups": 3911094 },11095 "placeholders_exact": {11096 "mean": 0.8904382470119522,11097 "ci_low": 0.8496175784288307,11098 "ci_high": 0.9351302671111045,11099 "n_items": 502,11100 "n_groups": 3911101 }11102 },11103 "by_variant": {11104 "A": {11105 "n": 83,11106 "chrf": {11107 "mean": 63.02918920856664,11108 "ci_low": 61.22654793295244,11109 "ci_high": 64.58644757825799,11110 "n_items": 83,11111 "n_groups": 3611112 },11113 "edit_sim": {11114 "mean": 0.5576784003829124,11115 "ci_low": 0.5313442637570404,11116 "ci_high": 0.5788671586551565,11117 "n_items": 83,11118 "n_groups": 3611119 },11120 "rougeL": {11121 "mean": 0.5779309151371874,11122 "ci_low": 0.5486601401783133,11123 "ci_high": 0.5999648879876333,11124 "n_items": 83,11125 "n_groups": 3611126 },11127 "exact_match": {11128 "mean": 0.0,11129 "ci_low": 0.0,11130 "ci_high": 0.0,11131 "n_items": 83,11132 "n_groups": 3611133 },11134 "number_recall": {11135 "mean": 0.9667093211699542,11136 "ci_low": 0.9471190371911998,11137 "ci_high": 0.9825383924361197,11138 "n_items": 83,11139 "n_groups": 3611140 },11141 "placeholders_exact": {11142 "mean": 0.8674698795180723,11143 "ci_low": 0.7921942640692641,11144 "ci_high": 0.9375,11145 "n_items": 83,11146 "n_groups": 3611147 }11148 },11149 "B": {11150 "n": 83,11151 "chrf": {11152 "mean": 69.75732276004912,11153 "ci_low": 67.57130687615297,11154 "ci_high": 71.70303661012036,11155 "n_items": 83,11156 "n_groups": 3711157 },11158 "edit_sim": {11159 "mean": 0.6601672678824636,11160 "ci_low": 0.6273065080629837,11161 "ci_high": 0.6936834033111836,11162 "n_items": 83,11163 "n_groups": 3711164 },11165 "rougeL": {11166 "mean": 0.6826045308176781,11167 "ci_low": 0.6541635065663675,11168 "ci_high": 0.709357344279597,11169 "n_items": 83,11170 "n_groups": 3711171 },11172 "exact_match": {11173 "mean": 0.0,11174 "ci_low": 0.0,11175 "ci_high": 0.0,11176 "n_items": 83,11177 "n_groups": 3711178 },11179 "number_recall": {11180 "mean": 0.9661330882177057,11181 "ci_low": 0.9427011319723834,11182 "ci_high": 0.9882105027543886,11183 "n_items": 83,11184 "n_groups": 3711185 },11186 "placeholders_exact": {11187 "mean": 0.891566265060241,11188 "ci_low": 0.8085033517924802,11189 "ci_high": 0.9710144927536232,11190 "n_items": 83,11191 "n_groups": 3711192 }11193 },11194 "C": {11195 "n": 84,11196 "chrf": {11197 "mean": 65.47019015942618,11198 "ci_low": 62.91754293951048,11199 "ci_high": 67.4789982354406,11200 "n_items": 84,11201 "n_groups": 3811202 },11203 "edit_sim": {11204 "mean": 0.6325052282113448,11205 "ci_low": 0.6023372820438117,11206 "ci_high": 0.6596958372164105,11207 "n_items": 84,11208 "n_groups": 3811209 },11210 "rougeL": {11211 "mean": 0.6631299357007048,11212 "ci_low": 0.6347274868482645,11213 "ci_high": 0.6881335064932195,11214 "n_items": 84,11215 "n_groups": 3811216 },11217 "exact_match": {11218 "mean": 0.0,11219 "ci_low": 0.0,11220 "ci_high": 0.0,11221 "n_items": 84,11222 "n_groups": 3811223 },11224 "number_recall": {11225 "mean": 0.9542631098922627,11226 "ci_low": 0.9289414174263899,11227 "ci_high": 0.9756614387466231,11228 "n_items": 84,11229 "n_groups": 3811230 },11231 "placeholders_exact": {11232 "mean": 0.9047619047619048,11233 "ci_low": 0.8390711902113459,11234 "ci_high": 0.9634146341463414,11235 "n_items": 84,11236 "n_groups": 3811237 }11238 },11239 "D": {11240 "n": 85,11241 "chrf": {11242 "mean": 60.98357000510767,11243 "ci_low": 58.80610281717415,11244 "ci_high": 62.911923699819845,11245 "n_items": 85,11246 "n_groups": 3711247 },11248 "edit_sim": {11249 "mean": 0.5310669231240174,11250 "ci_low": 0.5053365978537255,11251 "ci_high": 0.5552492075497858,11252 "n_items": 85,11253 "n_groups": 3711254 },11255 "rougeL": {11256 "mean": 0.5502812146969529,11257 "ci_low": 0.5217997208957844,11258 "ci_high": 0.5749873211834771,11259 "n_items": 85,11260 "n_groups": 3711261 },11262 "exact_match": {11263 "mean": 0.0,11264 "ci_low": 0.0,11265 "ci_high": 0.0,11266 "n_items": 85,11267 "n_groups": 3711268 },11269 "number_recall": {11270 "mean": 0.9351698648032438,11271 "ci_low": 0.9062374414249413,11272 "ci_high": 0.962217807883199,11273 "n_items": 85,11274 "n_groups": 3711275 },11276 "placeholders_exact": {11277 "mean": 0.8823529411764706,11278 "ci_low": 0.8225716845878137,11279 "ci_high": 0.9459459459459459,11280 "n_items": 85,11281 "n_groups": 3711282 }11283 },11284 "E": {11285 "n": 167,11286 "chrf": {11287 "mean": 62.59206409926375,11288 "ci_low": 60.48771717742431,11289 "ci_high": 64.31832123274545,11290 "n_items": 167,11291 "n_groups": 3811292 },11293 "edit_sim": {11294 "mean": 0.5612001603984684,11295 "ci_low": 0.5393242862060753,11296 "ci_high": 0.5825159175784287,11297 "n_items": 167,11298 "n_groups": 3811299 },11300 "rougeL": {11301 "mean": 0.5818389129093936,11302 "ci_low": 0.5568764134695227,11303 "ci_high": 0.6041312133679161,11304 "n_items": 167,11305 "n_groups": 3811306 },11307 "exact_match": {11308 "mean": 0.0,11309 "ci_low": 0.0,11310 "ci_high": 0.0,11311 "n_items": 167,11312 "n_groups": 3811313 },11314 "number_recall": {11315 "mean": 0.9450807992038321,11316 "ci_low": 0.91745509419519,11317 "ci_high": 0.97249526571898,11318 "n_items": 167,11319 "n_groups": 3811320 },11321 "placeholders_exact": {11322 "mean": 0.8982035928143712,11323 "ci_low": 0.8571428571428571,11324 "ci_high": 0.9461577181208053,11325 "n_items": 167,11326 "n_groups": 3811327 }11328 }11329 },11330 "by_discipline": {11331 "biomedicine": {11332 "n": 184,11333 "chrf": {11334 "mean": 65.57914836588536,11335 "ci_low": 63.47747157613285,11336 "ci_high": 66.93860560512508,11337 "n_items": 184,11338 "n_groups": 1911339 },11340 "edit_sim": {11341 "mean": 0.6028269443581152,11342 "ci_low": 0.5830777357128867,11343 "ci_high": 0.622035154840563,11344 "n_items": 184,11345 "n_groups": 1911346 },11347 "rougeL": {11348 "mean": 0.6267845562173536,11349 "ci_low": 0.5992328926341175,11350 "ci_high": 0.6400178225965747,11351 "n_items": 184,11352 "n_groups": 1911353 },11354 "exact_match": {11355 "mean": 0.0,11356 "ci_low": 0.0,11357 "ci_high": 0.0,11358 "n_items": 184,11359 "n_groups": 1911360 },11361 "number_recall": {11362 "mean": 0.9324322695707932,11363 "ci_low": 0.8918111174163023,11364 "ci_high": 0.9673858676046176,11365 "n_items": 184,11366 "n_groups": 1911367 },11368 "placeholders_exact": {11369 "mean": 0.875,11370 "ci_low": 0.8205105633802816,11371 "ci_high": 0.9603226817042606,11372 "n_items": 184,11373 "n_groups": 1911374 }11375 },11376 "computer_science": {11377 "n": 53,11378 "chrf": {11379 "mean": 60.7066013747546,11380 "ci_low": 57.20973366256136,11381 "ci_high": 65.09673139245248,11382 "n_items": 53,11383 "n_groups": 311384 },11385 "edit_sim": {11386 "mean": 0.5666232488141209,11387 "ci_low": 0.5332708948967925,11388 "ci_high": 0.655102672335693,11389 "n_items": 53,11390 "n_groups": 311391 },11392 "rougeL": {11393 "mean": 0.5805723535196355,11394 "ci_low": 0.5487450967145447,11395 "ci_high": 0.6846795194952298,11396 "n_items": 53,11397 "n_groups": 311398 },11399 "exact_match": {11400 "mean": 0.0,11401 "ci_low": 0.0,11402 "ci_high": 0.0,11403 "n_items": 53,11404 "n_groups": 311405 },11406 "number_recall": {11407 "mean": 0.9811320754716981,11408 "ci_low": 0.9583333333333334,11409 "ci_high": 1.0,11410 "n_items": 53,11411 "n_groups": 311412 },11413 "placeholders_exact": {11414 "mean": 0.9811320754716981,11415 "ci_low": 0.9583333333333334,11416 "ci_high": 1.0,11417 "n_items": 53,11418 "n_groups": 311419 }11420 },11421 "earth_sciences": {11422 "n": 22,11423 "chrf": {11424 "mean": 69.57506481904464,11425 "ci_low": 69.57506481904464,11426 "ci_high": 69.57506481904464,11427 "n_items": 22,11428 "n_groups": 111429 },11430 "edit_sim": {11431 "mean": 0.644423310479911,11432 "ci_low": 0.644423310479911,11433 "ci_high": 0.644423310479911,11434 "n_items": 22,11435 "n_groups": 111436 },11437 "rougeL": {11438 "mean": 0.6755567516391993,11439 "ci_low": 0.6755567516391993,11440 "ci_high": 0.6755567516391993,11441 "n_items": 22,11442 "n_groups": 111443 },11444 "exact_match": {11445 "mean": 0.0,11446 "ci_low": 0.0,11447 "ci_high": 0.0,11448 "n_items": 22,11449 "n_groups": 111450 },11451 "number_recall": {11452 "mean": 0.9785123966942149,11453 "ci_low": 0.9785123966942149,11454 "ci_high": 0.9785123966942149,11455 "n_items": 22,11456 "n_groups": 111457 },11458 "placeholders_exact": {11459 "mean": 0.9545454545454546,11460 "ci_low": 0.9545454545454546,11461 "ci_high": 0.9545454545454546,11462 "n_items": 22,11463 "n_groups": 111464 }11465 },11466 "engineering": {11467 "n": 45,11468 "chrf": {11469 "mean": 61.92709359161393,11470 "ci_low": 61.412170934677796,11471 "ci_high": 65.27409086169882,11472 "n_items": 45,11473 "n_groups": 211474 },11475 "edit_sim": {11476 "mean": 0.4974285035932749,11477 "ci_low": 0.4951225785916145,11478 "ci_high": 0.5124170161040665,11479 "n_items": 45,11480 "n_groups": 211481 },11482 "rougeL": {11483 "mean": 0.5298287098994425,11484 "ci_low": 0.5247185248356389,11485 "ci_high": 0.5630449128141668,11486 "n_items": 45,11487 "n_groups": 211488 },11489 "exact_match": {11490 "mean": 0.0,11491 "ci_low": 0.0,11492 "ci_high": 0.0,11493 "n_items": 45,11494 "n_groups": 211495 },11496 "number_recall": {11497 "mean": 0.9567901234567902,11498 "ci_low": 0.925925925925926,11499 "ci_high": 0.9615384615384616,11500 "n_items": 45,11501 "n_groups": 211502 },11503 "placeholders_exact": {11504 "mean": 0.8444444444444444,11505 "ci_low": 0.8205128205128205,11506 "ci_high": 1.0,11507 "n_items": 45,11508 "n_groups": 211509 }11510 },11511 "life_sciences": {11512 "n": 144,11513 "chrf": {11514 "mean": 62.522152609594286,11515 "ci_low": 58.05225258773552,11516 "ci_high": 65.8159511672335,11517 "n_items": 144,11518 "n_groups": 1311519 },11520 "edit_sim": {11521 "mean": 0.5787505066194537,11522 "ci_low": 0.5326740832627979,11523 "ci_high": 0.6211317132608962,11524 "n_items": 144,11525 "n_groups": 1311526 },11527 "rougeL": {11528 "mean": 0.5972000864111676,11529 "ci_low": 0.5489753564231101,11530 "ci_high": 0.6338075118132425,11531 "n_items": 144,11532 "n_groups": 1311533 },11534 "exact_match": {11535 "mean": 0.0,11536 "ci_low": 0.0,11537 "ci_high": 0.0,11538 "n_items": 144,11539 "n_groups": 1311540 },11541 "number_recall": {11542 "mean": 0.9720679012345678,11543 "ci_low": 0.9425744601271678,11544 "ci_high": 0.9904624947324062,11545 "n_items": 144,11546 "n_groups": 1311547 },11548 "placeholders_exact": {11549 "mean": 0.8611111111111112,11550 "ci_low": 0.789109977324263,11551 "ci_high": 0.9444444444444444,11552 "n_items": 144,11553 "n_groups": 1311554 }11555 },11556 "mathematics": {11557 "n": 54,11558 "chrf": {11559 "mean": 65.79038585537077,11560 "ci_low": 65.79038585537077,11561 "ci_high": 65.79038585537077,11562 "n_items": 54,11563 "n_groups": 111564 },11565 "edit_sim": {11566 "mean": 0.5966645646919732,11567 "ci_low": 0.5966645646919732,11568 "ci_high": 0.5966645646919732,11569 "n_items": 54,11570 "n_groups": 111571 },11572 "rougeL": {11573 "mean": 0.6197835613508071,11574 "ci_low": 0.6197835613508071,11575 "ci_high": 0.6197835613508071,11576 "n_items": 54,11577 "n_groups": 111578 },11579 "exact_match": {11580 "mean": 0.0,11581 "ci_low": 0.0,11582 "ci_high": 0.0,11583 "n_items": 54,11584 "n_groups": 111585 },11586 "number_recall": {11587 "mean": 0.9217372134038799,11588 "ci_low": 0.9217372134038799,11589 "ci_high": 0.9217372134038799,11590 "n_items": 54,11591 "n_groups": 111592 },11593 "placeholders_exact": {11594 "mean": 0.9444444444444444,11595 "ci_low": 0.9444444444444444,11596 "ci_high": 0.9444444444444444,11597 "n_items": 54,11598 "n_groups": 111599 }11600 }11601 },11602 "by_era": {11603 "1980-1999": {11604 "n": 16,11605 "chrf": {11606 "mean": 67.57026267831249,11607 "ci_low": 60.01128746529643,11608 "ci_high": 70.08992108265117,11609 "n_items": 16,11610 "n_groups": 211611 },11612 "edit_sim": {11613 "mean": 0.6336367840054131,11614 "ci_low": 0.583029197080292,11615 "ci_high": 0.6505059796471201,11616 "n_items": 16,11617 "n_groups": 211618 },11619 "rougeL": {11620 "mean": 0.638927474149823,11621 "ci_low": 0.578597398836012,11622 "ci_high": 0.6590374992544267,11623 "n_items": 16,11624 "n_groups": 211625 },11626 "exact_match": {11627 "mean": 0.0,11628 "ci_low": 0.0,11629 "ci_high": 0.0,11630 "n_items": 16,11631 "n_groups": 211632 },11633 "number_recall": {11634 "mean": 0.953125,11635 "ci_low": 0.9375,11636 "ci_high": 0.9583333333333334,11637 "n_items": 16,11638 "n_groups": 211639 },11640 "placeholders_exact": {11641 "mean": 1.0,11642 "ci_low": 1.0,11643 "ci_high": 1.0,11644 "n_items": 16,11645 "n_groups": 211646 }11647 },11648 "2000-2009": {11649 "n": 70,11650 "chrf": {11651 "mean": 65.3432924173741,11652 "ci_low": 56.68968308489543,11653 "ci_high": 66.15456829229396,11654 "n_items": 70,11655 "n_groups": 211656 },11657 "edit_sim": {11658 "mean": 0.5972226389400725,11659 "ci_low": 0.5439215348026443,11660 "ci_high": 0.6022196174529565,11661 "n_items": 70,11662 "n_groups": 211663 },11664 "rougeL": {11665 "mean": 0.6283486668497674,11666 "ci_low": 0.5008485578434644,11667 "ci_high": 0.6403018020691085,11668 "n_items": 70,11669 "n_groups": 211670 },11671 "exact_match": {11672 "mean": 0.0,11673 "ci_low": 0.0,11674 "ci_high": 0.0,11675 "n_items": 70,11676 "n_groups": 211677 },11678 "number_recall": {11679 "mean": 0.9394508794508795,11680 "ci_low": 0.9337743993993994,11681 "ci_high": 1.0,11682 "n_items": 70,11683 "n_groups": 211684 },11685 "placeholders_exact": {11686 "mean": 0.8,11687 "ci_low": 0.78125,11688 "ci_high": 1.0,11689 "n_items": 70,11690 "n_groups": 211691 }11692 },11693 "2010-2017": {11694 "n": 416,11695 "chrf": {11696 "mean": 63.70697103300222,11697 "ci_low": 61.80269575420911,11698 "ci_high": 65.4362905353224,11699 "n_items": 416,11700 "n_groups": 3511701 },11702 "edit_sim": {11703 "mean": 0.5796369510047433,11704 "ci_low": 0.555094196206075,11705 "ci_high": 0.6051856741625878,11706 "n_items": 416,11707 "n_groups": 3511708 },11709 "rougeL": {11710 "mean": 0.6011084424335142,11711 "ci_low": 0.5775897589667284,11712 "ci_high": 0.6244781542959565,11713 "n_items": 416,11714 "n_groups": 3511715 },11716 "exact_match": {11717 "mean": 0.0,11718 "ci_low": 0.0,11719 "ci_high": 0.0,11720 "n_items": 416,11721 "n_groups": 3511722 },11723 "number_recall": {11724 "mean": 0.9540634414035576,11725 "ci_low": 0.9323299623305394,11726 "ci_high": 0.9737122673017017,11727 "n_items": 416,11728 "n_groups": 3511729 },11730 "placeholders_exact": {11731 "mean": 0.9014423076923077,11732 "ci_low": 0.8594113657456985,11733 "ci_high": 0.9415214171793119,11734 "n_items": 416,11735 "n_groups": 3511736 }11737 }11738 },11739 "by_role": {11740 "abstract": {11741 "n": 63,11742 "chrf": {11743 "mean": 63.97990917536261,11744 "ci_low": 58.914143888004006,11745 "ci_high": 67.5776345615631,11746 "n_items": 63,11747 "n_groups": 911748 },11749 "edit_sim": {11750 "mean": 0.575465122838251,11751 "ci_low": 0.5027701527075961,11752 "ci_high": 0.628501678688568,11753 "n_items": 63,11754 "n_groups": 911755 },11756 "rougeL": {11757 "mean": 0.600559062337953,11758 "ci_low": 0.5221156784152607,11759 "ci_high": 0.6570388129169751,11760 "n_items": 63,11761 "n_groups": 911762 },11763 "exact_match": {11764 "mean": 0.0,11765 "ci_low": 0.0,11766 "ci_high": 0.0,11767 "n_items": 63,11768 "n_groups": 911769 },11770 "number_recall": {11771 "mean": 0.9388095238095239,11772 "ci_low": 0.884,11773 "ci_high": 0.984375,11774 "n_items": 63,11775 "n_groups": 911776 },11777 "placeholders_exact": {11778 "mean": 0.9841269841269841,11779 "ci_low": 0.9482758620689655,11780 "ci_high": 1.0,11781 "n_items": 63,11782 "n_groups": 911783 }11784 },11785 "background": {11786 "n": 22,11787 "chrf": {11788 "mean": 63.73906870522657,11789 "ci_low": 57.588622085566044,11790 "ci_high": 71.4293850447106,11791 "n_items": 22,11792 "n_groups": 411793 },11794 "edit_sim": {11795 "mean": 0.5596573147745768,11796 "ci_low": 0.47683089425109976,11797 "ci_high": 0.6503286804495056,11798 "n_items": 22,11799 "n_groups": 411800 },11801 "rougeL": {11802 "mean": 0.5918750090363892,11803 "ci_low": 0.5321392476595752,11804 "ci_high": 0.6604376392677994,11805 "n_items": 22,11806 "n_groups": 411807 },11808 "exact_match": {11809 "mean": 0.0,11810 "ci_low": 0.0,11811 "ci_high": 0.0,11812 "n_items": 22,11813 "n_groups": 411814 },11815 "number_recall": {11816 "mean": 0.9312770562770563,11817 "ci_low": 0.9083333333333332,11818 "ci_high": 0.9508928571428571,11819 "n_items": 22,11820 "n_groups": 411821 },11822 "placeholders_exact": {11823 "mean": 0.6363636363636364,11824 "ci_low": 0.20833333333333334,11825 "ci_high": 0.95,11826 "n_items": 22,11827 "n_groups": 411828 }11829 },11830 "conclusion": {11831 "n": 60,11832 "chrf": {11833 "mean": 57.73478688318453,11834 "ci_low": 51.50068778568037,11835 "ci_high": 62.86959156508576,11836 "n_items": 60,11837 "n_groups": 911838 },11839 "edit_sim": {11840 "mean": 0.5211269985852837,11841 "ci_low": 0.4672835674047592,11842 "ci_high": 0.5648776325206206,11843 "n_items": 60,11844 "n_groups": 911845 },11846 "rougeL": {11847 "mean": 0.548671762216318,11848 "ci_low": 0.4942462932223197,11849 "ci_high": 0.5929768486423617,11850 "n_items": 60,11851 "n_groups": 911852 },11853 "exact_match": {11854 "mean": 0.0,11855 "ci_low": 0.0,11856 "ci_high": 0.0,11857 "n_items": 60,11858 "n_groups": 911859 },11860 "number_recall": {11861 "mean": 0.9933333333333334,11862 "ci_low": 0.9777777777777777,11863 "ci_high": 1.0,11864 "n_items": 60,11865 "n_groups": 911866 },11867 "placeholders_exact": {11868 "mean": 0.8333333333333334,11869 "ci_low": 0.5925925925925926,11870 "ci_high": 1.0,11871 "n_items": 60,11872 "n_groups": 911873 }11874 },11875 "data": {11876 "n": 33,11877 "chrf": {11878 "mean": 67.05989630783267,11879 "ci_low": 63.07188269784385,11880 "ci_high": 69.94038923710013,11881 "n_items": 33,11882 "n_groups": 511883 },11884 "edit_sim": {11885 "mean": 0.5782324152310793,11886 "ci_low": 0.5452552787079212,11887 "ci_high": 0.6146050838899954,11888 "n_items": 33,11889 "n_groups": 511890 },11891 "rougeL": {11892 "mean": 0.6254101630620441,11893 "ci_low": 0.581838942951748,11894 "ci_high": 0.6598715070984231,11895 "n_items": 33,11896 "n_groups": 511897 },11898 "exact_match": {11899 "mean": 0.0,11900 "ci_low": 0.0,11901 "ci_high": 0.0,11902 "n_items": 33,11903 "n_groups": 511904 },11905 "number_recall": {11906 "mean": 0.9372895622895623,11907 "ci_low": 0.8901851851851852,11908 "ci_high": 0.9808139534883721,11909 "n_items": 33,11910 "n_groups": 511911 },11912 "placeholders_exact": {11913 "mean": 1.0,11914 "ci_low": 1.0,11915 "ci_high": 1.0,11916 "n_items": 33,11917 "n_groups": 511918 }11919 },11920 "discussion": {11921 "n": 60,11922 "chrf": {11923 "mean": 63.851388037994774,11924 "ci_low": 61.445399827675864,11925 "ci_high": 66.49747467520966,11926 "n_items": 60,11927 "n_groups": 711928 },11929 "edit_sim": {11930 "mean": 0.6020997459727496,11931 "ci_low": 0.5574727918288438,11932 "ci_high": 0.6588592539897946,11933 "n_items": 60,11934 "n_groups": 711935 },11936 "rougeL": {11937 "mean": 0.6032542226090929,11938 "ci_low": 0.5652625485133973,11939 "ci_high": 0.6474372273182484,11940 "n_items": 60,11941 "n_groups": 711942 },11943 "exact_match": {11944 "mean": 0.0,11945 "ci_low": 0.0,11946 "ci_high": 0.0,11947 "n_items": 60,11948 "n_groups": 711949 },11950 "number_recall": {11951 "mean": 0.950462962962963,11952 "ci_low": 0.9027777777777778,11953 "ci_high": 1.0,11954 "n_items": 60,11955 "n_groups": 711956 },11957 "placeholders_exact": {11958 "mean": 0.8833333333333333,11959 "ci_low": 0.8076923076923077,11960 "ci_high": 0.9666666666666667,11961 "n_items": 60,11962 "n_groups": 711963 }11964 },11965 "introduction": {11966 "n": 56,11967 "chrf": {11968 "mean": 64.7927880060769,11969 "ci_low": 61.454491195954525,11970 "ci_high": 68.25580565019206,11971 "n_items": 56,11972 "n_groups": 911973 },11974 "edit_sim": {11975 "mean": 0.5955625344908532,11976 "ci_low": 0.5420469275450537,11977 "ci_high": 0.6464061733008192,11978 "n_items": 56,11979 "n_groups": 911980 },11981 "rougeL": {11982 "mean": 0.6041609108147471,11983 "ci_low": 0.5530786078775458,11984 "ci_high": 0.6536699938288948,11985 "n_items": 56,11986 "n_groups": 911987 },11988 "exact_match": {11989 "mean": 0.0,11990 "ci_low": 0.0,11991 "ci_high": 0.0,11992 "n_items": 56,11993 "n_groups": 911994 },11995 "number_recall": {11996 "mean": 0.9696969696969697,11997 "ci_low": 0.9424756034925527,11998 "ci_high": 1.0,11999 "n_items": 56,12000 "n_groups": 912001 },12002 "placeholders_exact": {12003 "mean": 0.8571428571428571,12004 "ci_low": 0.7058823529411765,12005 "ci_high": 0.9811320754716981,12006 "n_items": 56,12007 "n_groups": 912008 }12009 },12010 "limitations": {12011 "n": 12,12012 "chrf": {12013 "mean": 63.26380573168243,12014 "ci_low": 62.71020197312587,12015 "ci_high": 63.817409490239015,12016 "n_items": 12,12017 "n_groups": 212018 },12019 "edit_sim": {12020 "mean": 0.5822181085547199,12021 "ci_low": 0.553585930202815,12022 "ci_high": 0.6108502869066249,12023 "n_items": 12,12024 "n_groups": 212025 },12026 "rougeL": {12027 "mean": 0.6089146474010061,12028 "ci_low": 0.5761375483928487,12029 "ci_high": 0.6416917464091634,12030 "n_items": 12,12031 "n_groups": 212032 },12033 "exact_match": {12034 "mean": 0.0,12035 "ci_low": 0.0,12036 "ci_high": 0.0,12037 "n_items": 12,12038 "n_groups": 212039 },12040 "number_recall": {12041 "mean": 1.0,12042 "ci_low": 1.0,12043 "ci_high": 1.0,12044 "n_items": 12,12045 "n_groups": 212046 },12047 "placeholders_exact": {12048 "mean": 1.0,12049 "ci_low": 1.0,12050 "ci_high": 1.0,12051 "n_items": 12,12052 "n_groups": 212053 }12054 },12055 "methods": {12056 "n": 69,12057 "chrf": {12058 "mean": 67.98068881056697,12059 "ci_low": 64.98380131328469,12060 "ci_high": 70.78824341879579,12061 "n_items": 69,12062 "n_groups": 1112063 },12064 "edit_sim": {12065 "mean": 0.6292355127515695,12066 "ci_low": 0.592756790552265,12067 "ci_high": 0.6645972146034127,12068 "n_items": 69,12069 "n_groups": 1112070 },12071 "rougeL": {12072 "mean": 0.6547437485875605,12073 "ci_low": 0.6194408506848759,12074 "ci_high": 0.6878622852992444,12075 "n_items": 69,12076 "n_groups": 1112077 },12078 "exact_match": {12079 "mean": 0.0,12080 "ci_low": 0.0,12081 "ci_high": 0.0,12082 "n_items": 69,12083 "n_groups": 1112084 },12085 "number_recall": {12086 "mean": 0.960540184453228,12087 "ci_low": 0.9420069648093842,12088 "ci_high": 0.9795081967213115,12089 "n_items": 69,12090 "n_groups": 1112091 },12092 "placeholders_exact": {12093 "mean": 0.8840579710144928,12094 "ci_low": 0.7972722722722723,12095 "ci_high": 0.9655318527177089,12096 "n_items": 69,12097 "n_groups": 1112098 }12099 },12100 "other": {12101 "n": 32,12102 "chrf": {12103 "mean": 66.94314806732903,12104 "ci_low": 57.733079854846444,12105 "ci_high": 71.70190651572143,12106 "n_items": 32,12107 "n_groups": 512108 },12109 "edit_sim": {12110 "mean": 0.5954655303982099,12111 "ci_low": 0.492548174461675,12112 "ci_high": 0.6687638130958159,12113 "n_items": 32,12114 "n_groups": 512115 },12116 "rougeL": {12117 "mean": 0.6085983485640443,12118 "ci_low": 0.5030898262053848,12119 "ci_high": 0.6674007402600618,12120 "n_items": 32,12121 "n_groups": 512122 },12123 "exact_match": {12124 "mean": 0.0,12125 "ci_low": 0.0,12126 "ci_high": 0.0,12127 "n_items": 32,12128 "n_groups": 512129 },12130 "number_recall": {12131 "mean": 0.9287574404761905,12132 "ci_low": 0.7802197802197803,12133 "ci_high": 1.0,12134 "n_items": 32,12135 "n_groups": 512136 },12137 "placeholders_exact": {12138 "mean": 0.71875,12139 "ci_low": 0.5294117647058824,12140 "ci_high": 0.9615384615384616,12141 "n_items": 32,12142 "n_groups": 512143 }12144 },12145 "related_work": {12146 "n": 6,12147 "chrf": {12148 "mean": 61.72295195775032,12149 "ci_low": 61.72295195775032,12150 "ci_high": 61.72295195775032,12151 "n_items": 6,12152 "n_groups": 112153 },12154 "edit_sim": {12155 "mean": 0.5766010334371202,12156 "ci_low": 0.5766010334371202,12157 "ci_high": 0.5766010334371202,12158 "n_items": 6,12159 "n_groups": 112160 },12161 "rougeL": {12162 "mean": 0.6611756069623974,12163 "ci_low": 0.6611756069623974,12164 "ci_high": 0.6611756069623974,12165 "n_items": 6,12166 "n_groups": 112167 },12168 "exact_match": {12169 "mean": 0.0,12170 "ci_low": 0.0,12171 "ci_high": 0.0,12172 "n_items": 6,12173 "n_groups": 112174 },12175 "number_recall": {12176 "mean": 0.7777777777777778,12177 "ci_low": 0.7777777777777778,12178 "ci_high": 0.7777777777777778,12179 "n_items": 6,12180 "n_groups": 112181 },12182 "placeholders_exact": {12183 "mean": 1.0,12184 "ci_low": 1.0,12185 "ci_high": 1.0,12186 "n_items": 6,12187 "n_groups": 112188 }12189 },12190 "results": {12191 "n": 62,12192 "chrf": {12193 "mean": 61.98086817673121,12194 "ci_low": 60.315758998468446,12195 "ci_high": 63.423508669020755,12196 "n_items": 62,12197 "n_groups": 812198 },12199 "edit_sim": {12200 "mean": 0.5618544998640282,12201 "ci_low": 0.538382884966219,12202 "ci_high": 0.5928266306789338,12203 "n_items": 62,12204 "n_groups": 812205 },12206 "rougeL": {12207 "mean": 0.5867260084435898,12208 "ci_low": 0.5648788504211671,12209 "ci_high": 0.6094420878229747,12210 "n_items": 62,12211 "n_groups": 812212 },12213 "exact_match": {12214 "mean": 0.0,12215 "ci_low": 0.0,12216 "ci_high": 0.0,12217 "n_items": 62,12218 "n_groups": 812219 },12220 "number_recall": {12221 "mean": 0.9241753609251734,12222 "ci_low": 0.8554095045500505,12223 "ci_high": 0.9827586206896551,12224 "n_items": 62,12225 "n_groups": 812226 },12227 "placeholders_exact": {12228 "mean": 1.0,12229 "ci_low": 1.0,12230 "ci_high": 1.0,12231 "n_items": 62,12232 "n_groups": 812233 }12234 },12235 "theory": {12236 "n": 27,12237 "chrf": {12238 "mean": 66.02045025548362,12239 "ci_low": 63.728003621305106,12240 "ci_high": 69.0338671063182,12241 "n_items": 27,12242 "n_groups": 412243 },12244 "edit_sim": {12245 "mean": 0.6268835210729213,12246 "ci_low": 0.5774686463763968,12247 "ci_high": 0.6562803592459607,12248 "n_items": 27,12249 "n_groups": 412250 },12251 "rougeL": {12252 "mean": 0.648936073157523,12253 "ci_low": 0.6048263580303156,12254 "ci_high": 0.6894206298797907,12255 "n_items": 27,12256 "n_groups": 412257 },12258 "exact_match": {12259 "mean": 0.0,12260 "ci_low": 0.0,12261 "ci_high": 0.0,12262 "n_items": 27,12263 "n_groups": 412264 },12265 "number_recall": {12266 "mean": 0.9794238683127573,12267 "ci_low": 0.9444444444444443,12268 "ci_high": 1.0,12269 "n_items": 27,12270 "n_groups": 412271 },12272 "placeholders_exact": {12273 "mean": 0.8518518518518519,12274 "ci_low": 0.625,12275 "ci_high": 1.0,12276 "n_items": 27,12277 "n_groups": 412278 }12279 }12280 }12281 }12282 },12283 "paired_vs_baseline": {12284 "B1_generic_paraphrase": {12285 "chrf": {12286 "mean": -2.8244141954676913,12287 "ci_low": -3.4674466510792525,12288 "ci_high": -2.2532471091386665,12289 "n_items": 502,12290 "n_groups": 39,12291 "p_value_two_sided": 0.0,12292 "p_holm": 0.0,12293 "significant_holm_0_05": true12294 },12295 "edit_sim": {12296 "mean": -0.10538872385218022,12297 "ci_low": -0.11661678424278955,12298 "ci_high": -0.09387899024193502,12299 "n_items": 502,12300 "n_groups": 39,12301 "p_value_two_sided": 0.0,12302 "p_holm": 0.0,12303 "significant_holm_0_05": true12304 },12305 "rougeL": {12306 "mean": -0.07783181536937597,12307 "ci_low": -0.08559615246789867,12308 "ci_high": -0.0701506718955975,12309 "n_items": 502,12310 "n_groups": 39,12311 "p_value_two_sided": 0.0,12312 "p_holm": 0.0,12313 "significant_holm_0_05": true12314 },12315 "exact_match": {12316 "mean": 0.0,12317 "ci_low": 0.0,12318 "ci_high": 0.0,12319 "n_items": 502,12320 "n_groups": 39,12321 "p_value_two_sided": 0.0,12322 "p_holm": 0.0,12323 "significant_holm_0_05": true12324 },12325 "number_recall": {12326 "mean": 0.0,12327 "ci_low": 0.0,12328 "ci_high": 0.0,12329 "n_items": 502,12330 "n_groups": 39,12331 "p_value_two_sided": 0.0,12332 "p_holm": 0.0,12333 "significant_holm_0_05": true12334 },12335 "placeholders_exact": {12336 "mean": 0.0,12337 "ci_low": 0.0,12338 "ci_high": 0.0,12339 "n_items": 502,12340 "n_groups": 39,12341 "p_value_two_sided": 0.0,12342 "p_holm": 0.0,12343 "significant_holm_0_05": true12344 }12345 },12346 "B2_t5-small": {12347 "chrf": {12348 "mean": -2.3906865656242227,12349 "ci_low": -3.297782897454658,12350 "ci_high": -1.584770264348658,12351 "n_items": 502,12352 "n_groups": 39,12353 "p_value_two_sided": 0.0,12354 "p_holm": 0.0,12355 "significant_holm_0_05": true12356 },12357 "edit_sim": {12358 "mean": -0.027986442628936504,12359 "ci_low": -0.039435500718328964,12360 "ci_high": -0.016551617344356503,12361 "n_items": 502,12362 "n_groups": 39,12363 "p_value_two_sided": 0.0,12364 "p_holm": 0.0,12365 "significant_holm_0_05": true12366 },12367 "rougeL": {12368 "mean": -0.01873234745280931,12369 "ci_low": -0.027761912218407656,12370 "ci_high": -0.009128510007270932,12371 "n_items": 502,12372 "n_groups": 39,12373 "p_value_two_sided": 0.0,12374 "p_holm": 0.0,12375 "significant_holm_0_05": true12376 },12377 "exact_match": {12378 "mean": 0.0,12379 "ci_low": 0.0,12380 "ci_high": 0.0,12381 "n_items": 502,12382 "n_groups": 39,12383 "p_value_two_sided": 0.0,12384 "p_holm": 0.0,12385 "significant_holm_0_05": true12386 },12387 "number_recall": {12388 "mean": -0.0551318294274377,12389 "ci_low": -0.08115656545234898,12390 "ci_high": -0.03071359255191145,12391 "n_items": 502,12392 "n_groups": 39,12393 "p_value_two_sided": 0.0,12394 "p_holm": 0.0,12395 "significant_holm_0_05": true12396 },12397 "placeholders_exact": {12398 "mean": -0.30876494023904383,12399 "ci_low": -0.41532043004715924,12400 "ci_high": -0.21347552478007145,12401 "n_items": 502,12402 "n_groups": 39,12403 "p_value_two_sided": 0.0,12404 "p_holm": 0.0,12405 "significant_holm_0_05": true12406 }12407 },12408 "htr-denoise-only": {12409 "chrf": {12410 "mean": -13.180135518333072,12411 "ci_low": -15.399556949821978,12412 "ci_high": -11.03064687635739,12413 "n_items": 502,12414 "n_groups": 39,12415 "p_value_two_sided": 0.0,12416 "p_holm": 0.0,12417 "significant_holm_0_05": true12418 },12419 "edit_sim": {12420 "mean": -0.21031695419977015,12421 "ci_low": -0.24147303463647574,12422 "ci_high": -0.18186924640988755,12423 "n_items": 502,12424 "n_groups": 39,12425 "p_value_two_sided": 0.0,12426 "p_holm": 0.0,12427 "significant_holm_0_05": true12428 },12429 "rougeL": {12430 "mean": -0.1963366777079025,12431 "ci_low": -0.22338018814188548,12432 "ci_high": -0.17216333866188555,12433 "n_items": 502,12434 "n_groups": 39,12435 "p_value_two_sided": 0.0,12436 "p_holm": 0.0,12437 "significant_holm_0_05": true12438 },12439 "exact_match": {12440 "mean": 0.0,12441 "ci_low": 0.0,12442 "ci_high": 0.0,12443 "n_items": 502,12444 "n_groups": 39,12445 "p_value_two_sided": 0.0,12446 "p_holm": 0.0,12447 "significant_holm_0_05": true12448 },12449 "number_recall": {12450 "mean": -0.14391624653275722,12451 "ci_low": -0.19428755369315645,12452 "ci_high": -0.09802697466039736,12453 "n_items": 502,12454 "n_groups": 39,12455 "p_value_two_sided": 0.0,12456 "p_holm": 0.0,12457 "significant_holm_0_05": true12458 },12459 "placeholders_exact": {12460 "mean": -0.2589641434262948,12461 "ci_low": -0.3505660200323708,12462 "ci_high": -0.17616478914654796,12463 "n_items": 502,12464 "n_groups": 39,12465 "p_value_two_sided": 0.0,12466 "p_holm": 0.0,12467 "significant_holm_0_05": true12468 }12469 },12470 "htr-m1-tiny-denoiseinit": {12471 "chrf": {12472 "mean": -7.634830214535022,12473 "ci_low": -8.644857565291234,12474 "ci_high": -6.707980257083264,12475 "n_items": 502,12476 "n_groups": 39,12477 "p_value_two_sided": 0.0,12478 "p_holm": 0.0,12479 "significant_holm_0_05": true12480 },12481 "edit_sim": {12482 "mean": -0.08876160011087247,12483 "ci_low": -0.10476923077904916,12484 "ci_high": -0.07481147109182354,12485 "n_items": 502,12486 "n_groups": 39,12487 "p_value_two_sided": 0.0,12488 "p_holm": 0.0,12489 "significant_holm_0_05": true12490 },12491 "rougeL": {12492 "mean": -0.09018813722717674,12493 "ci_low": -0.10417561006235836,12494 "ci_high": -0.07779646298924468,12495 "n_items": 502,12496 "n_groups": 39,12497 "p_value_two_sided": 0.0,12498 "p_holm": 0.0,12499 "significant_holm_0_05": true12500 },12501 "exact_match": {12502 "mean": 0.0,12503 "ci_low": 0.0,12504 "ci_high": 0.0,12505 "n_items": 502,12506 "n_groups": 39,12507 "p_value_two_sided": 0.0,12508 "p_holm": 0.0,12509 "significant_holm_0_05": true12510 },12511 "number_recall": {12512 "mean": -0.0691796046305914,12513 "ci_low": -0.08803046952911443,12514 "ci_high": -0.04967931253302001,12515 "n_items": 502,12516 "n_groups": 39,12517 "p_value_two_sided": 0.0,12518 "p_holm": 0.0,12519 "significant_holm_0_05": true12520 },12521 "placeholders_exact": {12522 "mean": -0.11553784860557768,12523 "ci_low": -0.16966158591907093,12524 "ci_high": -0.061902985074626875,12525 "n_items": 502,12526 "n_groups": 39,12527 "p_value_two_sided": 0.0,12528 "p_holm": 0.0,12529 "significant_holm_0_05": true12530 }12531 },12532 "htr-m1-tiny-mediumdenoiseinit": {12533 "chrf": {12534 "mean": -3.326711667731503,12535 "ci_low": -3.8655576015419104,12536 "ci_high": -2.751222099554388,12537 "n_items": 502,12538 "n_groups": 39,12539 "p_value_two_sided": 0.0,12540 "p_holm": 0.0,12541 "significant_holm_0_05": true12542 },12543 "edit_sim": {12544 "mean": -0.036192813622468956,12545 "ci_low": -0.04171714969601055,12546 "ci_high": -0.029972224855885462,12547 "n_items": 502,12548 "n_groups": 39,12549 "p_value_two_sided": 0.0,12550 "p_holm": 0.0,12551 "significant_holm_0_05": true12552 },12553 "rougeL": {12554 "mean": -0.03378945521797417,12555 "ci_low": -0.039280484341445945,12556 "ci_high": -0.027642577631445273,12557 "n_items": 502,12558 "n_groups": 39,12559 "p_value_two_sided": 0.0,12560 "p_holm": 0.0,12561 "significant_holm_0_05": true12562 },12563 "exact_match": {12564 "mean": 0.0,12565 "ci_low": 0.0,12566 "ci_high": 0.0,12567 "n_items": 502,12568 "n_groups": 39,12569 "p_value_two_sided": 0.0,12570 "p_holm": 0.0,12571 "significant_holm_0_05": true12572 },12573 "number_recall": {12574 "mean": -0.037891818685967665,12575 "ci_low": -0.05766257871385439,12576 "ci_high": -0.023861715436728083,12577 "n_items": 502,12578 "n_groups": 39,12579 "p_value_two_sided": 0.0,12580 "p_holm": 0.0,12581 "significant_holm_0_05": true12582 },12583 "placeholders_exact": {12584 "mean": -0.06772908366533864,12585 "ci_low": -0.10801116327905226,12586 "ci_high": -0.022806318187267718,12587 "n_items": 502,12588 "n_groups": 39,12589 "p_value_two_sided": 0.0,12590 "p_holm": 0.0,12591 "significant_holm_0_05": true12592 }12593 },12594 "htr-m1-tiny": {12595 "chrf": {12596 "mean": -38.37528335184966,12597 "ci_low": -41.191817223438605,12598 "ci_high": -35.922351419406354,12599 "n_items": 502,12600 "n_groups": 39,12601 "p_value_two_sided": 0.0,12602 "p_holm": 0.0,12603 "significant_holm_0_05": true12604 },12605 "edit_sim": {12606 "mean": -0.37913532031925273,12607 "ci_low": -0.4065451352067559,12608 "ci_high": -0.352988259600813,12609 "n_items": 502,12610 "n_groups": 39,12611 "p_value_two_sided": 0.0,12612 "p_holm": 0.0,12613 "significant_holm_0_05": true12614 },12615 "rougeL": {12616 "mean": -0.44917745895228045,12617 "ci_low": -0.47565525386421925,12618 "ci_high": -0.42670219059174097,12619 "n_items": 502,12620 "n_groups": 39,12621 "p_value_two_sided": 0.0,12622 "p_holm": 0.0,12623 "significant_holm_0_05": true12624 },12625 "exact_match": {12626 "mean": 0.0,12627 "ci_low": 0.0,12628 "ci_high": 0.0,12629 "n_items": 502,12630 "n_groups": 39,12631 "p_value_two_sided": 0.0,12632 "p_holm": 0.0,12633 "significant_holm_0_05": true12634 },12635 "number_recall": {12636 "mean": -0.4290698733116272,12637 "ci_low": -0.49663878229516095,12638 "ci_high": -0.34088154118575115,12639 "n_items": 502,12640 "n_groups": 39,12641 "p_value_two_sided": 0.0,12642 "p_holm": 0.0,12643 "significant_holm_0_05": true12644 },12645 "placeholders_exact": {12646 "mean": -0.3665338645418327,12647 "ci_low": -0.49478993710691827,12648 "ci_high": -0.2579116362702287,12649 "n_items": 502,12650 "n_groups": 39,12651 "p_value_two_sided": 0.0,12652 "p_holm": 0.0,12653 "significant_holm_0_05": true12654 }12655 },12656 "htr-pilot_m1_tiny_denoiseinit_s2": {12657 "chrf": {12658 "mean": -7.11720428864473,12659 "ci_low": -8.702732500390503,12660 "ci_high": -5.904656609912408,12661 "n_items": 502,12662 "n_groups": 39,12663 "p_value_two_sided": 0.0,12664 "p_holm": 0.0,12665 "significant_holm_0_05": true12666 },12667 "edit_sim": {12668 "mean": -0.08479159755131523,12669 "ci_low": -0.10322400713895813,12670 "ci_high": -0.07008903952499151,12671 "n_items": 502,12672 "n_groups": 39,12673 "p_value_two_sided": 0.0,12674 "p_holm": 0.0,12675 "significant_holm_0_05": true12676 },12677 "rougeL": {12678 "mean": -0.08662110055309405,12679 "ci_low": -0.10322306922441735,12680 "ci_high": -0.07260092069850785,12681 "n_items": 502,12682 "n_groups": 39,12683 "p_value_two_sided": 0.0,12684 "p_holm": 0.0,12685 "significant_holm_0_05": true12686 },12687 "exact_match": {12688 "mean": 0.0,12689 "ci_low": 0.0,12690 "ci_high": 0.0,12691 "n_items": 502,12692 "n_groups": 39,12693 "p_value_two_sided": 0.0,12694 "p_holm": 0.0,12695 "significant_holm_0_05": true12696 },12697 "number_recall": {12698 "mean": -0.06392424149106721,12699 "ci_low": -0.09117600233961673,12700 "ci_high": -0.04067859490086871,12701 "n_items": 502,12702 "n_groups": 39,12703 "p_value_two_sided": 0.0,12704 "p_holm": 0.0,12705 "significant_holm_0_05": true12706 },12707 "placeholders_exact": {12708 "mean": -0.12151394422310757,12709 "ci_low": -0.18129984051036682,12710 "ci_high": -0.06439254679144385,12711 "n_items": 502,12712 "n_groups": 39,12713 "p_value_two_sided": 0.0,12714 "p_holm": 0.0,12715 "significant_holm_0_05": true12716 }12717 },12718 "htr-pilot_m3light_tiny_denoiseinit": {12719 "chrf": {12720 "mean": -7.240787974951889,12721 "ci_low": -8.505808888347106,12722 "ci_high": -6.021093451836009,12723 "n_items": 502,12724 "n_groups": 39,12725 "p_value_two_sided": 0.0,12726 "p_holm": 0.0,12727 "significant_holm_0_05": true12728 },12729 "edit_sim": {12730 "mean": -0.0823949353186229,12731 "ci_low": -0.09748939415696528,12732 "ci_high": -0.06794718206317041,12733 "n_items": 502,12734 "n_groups": 39,12735 "p_value_two_sided": 0.0,12736 "p_holm": 0.0,12737 "significant_holm_0_05": true12738 },12739 "rougeL": {12740 "mean": -0.08404221065499531,12741 "ci_low": -0.09797291996104224,12742 "ci_high": -0.06950751476581761,12743 "n_items": 502,12744 "n_groups": 39,12745 "p_value_two_sided": 0.0,12746 "p_holm": 0.0,12747 "significant_holm_0_05": true12748 },12749 "exact_match": {12750 "mean": 0.0,12751 "ci_low": 0.0,12752 "ci_high": 0.0,12753 "n_items": 502,12754 "n_groups": 39,12755 "p_value_two_sided": 0.0,12756 "p_holm": 0.0,12757 "significant_holm_0_05": true12758 },12759 "number_recall": {12760 "mean": -0.058702534783559523,12761 "ci_low": -0.07718997945764844,12762 "ci_high": -0.035801727015298414,12763 "n_items": 502,12764 "n_groups": 39,12765 "p_value_two_sided": 0.0,12766 "p_holm": 0.0,12767 "significant_holm_0_05": true12768 },12769 "placeholders_exact": {12770 "mean": -0.12151394422310757,12771 "ci_low": -0.1701752077693429,12772 "ci_high": -0.06930502665651182,12773 "n_items": 502,12774 "n_groups": 39,12775 "p_value_two_sided": 0.0,12776 "p_holm": 0.0,12777 "significant_holm_0_05": true12778 }12779 },12780 "htr-pilot_m3tokenonly_tiny_denoiseinit": {12781 "chrf": {12782 "mean": -7.181101696982603,12783 "ci_low": -8.665770066983175,12784 "ci_high": -5.9496998296541594,12785 "n_items": 502,12786 "n_groups": 39,12787 "p_value_two_sided": 0.0,12788 "p_holm": 0.0,12789 "significant_holm_0_05": true12790 },12791 "edit_sim": {12792 "mean": -0.08264382752357248,12793 "ci_low": -0.10031416946097817,12794 "ci_high": -0.06787746905708089,12795 "n_items": 502,12796 "n_groups": 39,12797 "p_value_two_sided": 0.0,12798 "p_holm": 0.0,12799 "significant_holm_0_05": true12800 },12801 "rougeL": {12802 "mean": -0.08365012164080003,12803 "ci_low": -0.10035967928130261,12804 "ci_high": -0.06982966098168285,12805 "n_items": 502,12806 "n_groups": 39,12807 "p_value_two_sided": 0.0,12808 "p_holm": 0.0,12809 "significant_holm_0_05": true12810 },12811 "exact_match": {12812 "mean": 0.0,12813 "ci_low": 0.0,12814 "ci_high": 0.0,12815 "n_items": 502,12816 "n_groups": 39,12817 "p_value_two_sided": 0.0,12818 "p_holm": 0.0,12819 "significant_holm_0_05": true12820 },12821 "number_recall": {12822 "mean": -0.04800407731983754,12823 "ci_low": -0.06535298073574056,12824 "ci_high": -0.029660165849116682,12825 "n_items": 502,12826 "n_groups": 39,12827 "p_value_two_sided": 0.0,12828 "p_holm": 0.0,12829 "significant_holm_0_05": true12830 },12831 "placeholders_exact": {12832 "mean": -0.10956175298804781,12833 "ci_low": -0.1503824215711693,12834 "ci_high": -0.06486973288889557,12835 "n_items": 502,12836 "n_groups": 39,12837 "p_value_two_sided": 0.0,12838 "p_holm": 0.0,12839 "significant_holm_0_05": true12840 }12841 }12842 },12843 "stylometry": {12844 "rewrite_vs_original": {12845 "W1_mean_sent_len": 0.12190902494497877,12846 "W1_sd_sent_len": 0.10779234845106696,12847 "W1_ttr": 0.33383830166537914,12848 "W1_mtld": 0.3720980622008033,12849 "W1_mean_word_len": 0.2904068555168811,12850 "W1_long_word_rate": 0.16407994769190853,12851 "W1_comma_rate": 0.4228329749481948,12852 "W1_semicolon_rate": 0.1013631471388104,12853 "W1_paren_rate": 0.047102518106105454,12854 "W1_discourse_rate": 0.053369009920797815,12855 "W1_passive_rate": 0.09962550057438872,12856 "W1_nominal_rate": 0.09378752317126467,12857 "W1_first_person_rate": 0.16713852148887554,12858 "W1_subord_rate": 0.1605632471115266,12859 "W1_hedge_rate": 0.1528162335842082,12860 "W1_negation_rate": 0.1046727511235617,12861 "W1_digit_rate": 0.023690856974461,12862 "W1_flesch": 0.24528015229171585,12863 "W1_mean": 0.1701314987169404712864 },12865 "feature_means": {12866 "original": {12867 "mean_sent_len": 25.808144267002962,12868 "sd_sent_len": 9.003375488301481,12869 "ttr": 0.6409600884423484,12870 "mtld": 76.86391034420689,12871 "mean_word_len": 5.4300069581386,12872 "long_word_rate": 0.10805147167229831,12873 "comma_rate": 0.05053487967499568,12874 "semicolon_rate": 0.005243209950776467,12875 "paren_rate": 0.024539671087879054,12876 "discourse_rate": 0.007952205790944269,12877 "passive_rate": 0.463981608579687,12878 "nominal_rate": 0.05596235796416312,12879 "first_person_rate": 0.0034229997369521984,12880 "subord_rate": 0.02210284998012766,12881 "hedge_rate": 0.004050329378862597,12882 "negation_rate": 0.004498273018612058,12883 "digit_rate": 0.020137440826277414,12884 "flesch": 22.03355975954511312885 },12886 "rewrite": {12887 "mean_sent_len": 26.103446518653335,12888 "sd_sent_len": 8.68986253632324,12889 "ttr": 0.6737887450245789,12890 "mtld": 87.97996568972378,12891 "mean_word_len": 5.555295064856149,12892 "long_word_rate": 0.11401659674806652,12893 "comma_rate": 0.06370615702093413,12894 "semicolon_rate": 0.004417045470056317,12895 "paren_rate": 0.023775662092649023,12896 "discourse_rate": 0.00783218010328074,12897 "passive_rate": 0.48532132399017774,12898 "nominal_rate": 0.054063263581117904,12899 "first_person_rate": 0.0023591236161748944,12900 "subord_rate": 0.024621436522913896,12901 "hedge_rate": 0.005102610381535896,12902 "negation_rate": 0.004297128571861258,12903 "digit_rate": 0.020173408977794554,12904 "flesch": 18.590854261294112905 }12906 },12907 "feature_sds": {12908 "original": {12909 "mean_sent_len": 6.406481661757472,12910 "sd_sent_len": 4.422761187101167,12911 "ttr": 0.10183743641171336,12912 "mtld": 28.403643435099806,12913 "mean_word_len": 0.4298253767368124,12914 "long_word_rate": 0.038702132650959516,12915 "comma_rate": 0.031221323798232316,12916 "semicolon_rate": 0.015785808595903048,12917 "paren_rate": 0.03342913919176233,12918 "discourse_rate": 0.008396128049719658,12919 "passive_rate": 0.36288359005437787,12920 "nominal_rate": 0.028283870382167457,12921 "first_person_rate": 0.007139529523764533,12922 "subord_rate": 0.014994552291043257,12923 "hedge_rate": 0.006359233540743385,12924 "negation_rate": 0.006213258129032898,12925 "digit_rate": 0.026269321074966864,12926 "flesch": 14.6083138973115312927 },12928 "rewrite": {12929 "mean_sent_len": 5.910085780069904,12930 "sd_sent_len": 4.093252238629246,12931 "ttr": 0.09183012699145253,12932 "mtld": 30.75112540790839,12933 "mean_word_len": 0.440605647404047,12934 "long_word_rate": 0.039077471246336606,12935 "comma_rate": 0.03093064437345577,12936 "semicolon_rate": 0.012381755987629741,12937 "paren_rate": 0.032135724905816926,12938 "discourse_rate": 0.008193912900981603,12939 "passive_rate": 0.37618254412229685,12940 "nominal_rate": 0.02754781179781557,12941 "first_person_rate": 0.005777014628525316,12942 "subord_rate": 0.016533191744477323,12943 "hedge_rate": 0.007574358302067374,12944 "negation_rate": 0.0066505655039707685,12945 "digit_rate": 0.0265911146123269,12946 "flesch": 13.96785576129498812947 }12948 },12949 "B0_identity": {12950 "vs_original": {12951 "W1_mean_sent_len": 0.12190902494497877,12952 "W1_sd_sent_len": 0.10779234845106696,12953 "W1_ttr": 0.33383830166537914,12954 "W1_mtld": 0.3720980622008033,12955 "W1_mean_word_len": 0.2904068555168811,12956 "W1_long_word_rate": 0.16407994769190853,12957 "W1_comma_rate": 0.4228329749481948,12958 "W1_semicolon_rate": 0.1013631471388104,12959 "W1_paren_rate": 0.047102518106105454,12960 "W1_discourse_rate": 0.053369009920797815,12961 "W1_passive_rate": 0.09962550057438872,12962 "W1_nominal_rate": 0.09378752317126467,12963 "W1_first_person_rate": 0.16713852148887554,12964 "W1_subord_rate": 0.1605632471115266,12965 "W1_hedge_rate": 0.1528162335842082,12966 "W1_negation_rate": 0.1046727511235617,12967 "W1_digit_rate": 0.023690856974461,12968 "W1_flesch": 0.24528015229171585,12969 "W1_mean": 0.1701314987169404712970 },12971 "feature_means": {12972 "mean_sent_len": 26.103446518653335,12973 "sd_sent_len": 8.68986253632324,12974 "ttr": 0.6737887450245789,12975 "mtld": 87.97996568972378,12976 "mean_word_len": 5.555295064856149,12977 "long_word_rate": 0.11401659674806652,12978 "comma_rate": 0.06370615702093413,12979 "semicolon_rate": 0.004417045470056317,12980 "paren_rate": 0.023775662092649023,12981 "discourse_rate": 0.00783218010328074,12982 "passive_rate": 0.48532132399017774,12983 "nominal_rate": 0.054063263581117904,12984 "first_person_rate": 0.0023591236161748944,12985 "subord_rate": 0.024621436522913896,12986 "hedge_rate": 0.005102610381535896,12987 "negation_rate": 0.004297128571861258,12988 "digit_rate": 0.020173408977794554,12989 "flesch": 18.590854261294112990 },12991 "probe": {12992 "probe_auc_orig_vs_rewrite": 0.6862727871732923,12993 "probe_acc_heldout": 0.6059602649006622,12994 "eval_mean_p_original": 0.4436535789604957,12995 "eval_frac_classified_original": 0.366533864541832712996 }12997 },12998 "B1_generic_paraphrase": {12999 "vs_original": {13000 "W1_mean_sent_len": 0.679657840532468,13001 "W1_sd_sent_len": 0.6190177554314056,13002 "W1_ttr": 0.30996297485748914,13003 "W1_mtld": 0.3515475229892262,13004 "W1_mean_word_len": 0.4619972930677184,13005 "W1_long_word_rate": 0.36576825350393116,13006 "W1_comma_rate": 0.41446817644915446,13007 "W1_semicolon_rate": 0.10180421375923747,13008 "W1_paren_rate": 0.04774338398570347,13009 "W1_discourse_rate": 0.16371995107592374,13010 "W1_passive_rate": 0.284027816447565,13011 "W1_nominal_rate": 0.12625006488449858,13012 "W1_first_person_rate": 0.14898630354219788,13013 "W1_subord_rate": 0.10948808945534624,13014 "W1_hedge_rate": 0.06281199480514174,13015 "W1_negation_rate": 0.1028223408424557,13016 "W1_digit_rate": 0.024041438728505542,13017 "W1_flesch": 0.681289166048963,13018 "W1_mean": 0.280855810022607313019 },13020 "feature_means": {13021 "mean_sent_len": 29.894512648738406,13022 "sd_sent_len": 11.603145092452813,13023 "ttr": 0.6714648551567352,13024 "mtld": 87.36386637568289,13025 "mean_word_len": 5.631400063055265,13026 "long_word_rate": 0.12218948725505901,13027 "comma_rate": 0.06342962360315076,13028 "semicolon_rate": 0.004406496345567756,13029 "paren_rate": 0.023733244497353055,13030 "discourse_rate": 0.006619184305161049,13031 "passive_rate": 0.5679519215258609,13032 "nominal_rate": 0.05947008754801525,13033 "first_person_rate": 0.0024902406617055995,13034 "subord_rate": 0.02375002775736577,13035 "hedge_rate": 0.004136237510930693,13036 "negation_rate": 0.004268314645494309,13037 "digit_rate": 0.01992214545734172,13038 "flesch": 12.32557834246308413039 },13040 "probe": {13041 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13042 "probe_acc_heldout": 0.6059602649006622,13043 "eval_mean_p_original": 0.4422212119476709,13044 "eval_frac_classified_original": 0.354581673306772913045 }13046 },13047 "B2_t5-small": {13048 "vs_original": {13049 "W1_mean_sent_len": 0.14350882425660125,13050 "W1_sd_sent_len": 0.17290433902835817,13051 "W1_ttr": 0.10721256927124356,13052 "W1_mtld": 0.11822371548823016,13053 "W1_mean_word_len": 0.07066930633101288,13054 "W1_long_word_rate": 0.10575923349389171,13055 "W1_comma_rate": 0.2610403583996712,13056 "W1_semicolon_rate": 0.09882797486280599,13057 "W1_paren_rate": 0.055012637538454284,13058 "W1_discourse_rate": 0.060407935274851346,13059 "W1_passive_rate": 0.1878240126497184,13060 "W1_nominal_rate": 0.10493652139420535,13061 "W1_first_person_rate": 0.14890737388535846,13062 "W1_subord_rate": 0.07921418386961332,13063 "W1_hedge_rate": 0.0825259432731774,13064 "W1_negation_rate": 0.1005005937407785,13065 "W1_digit_rate": 0.0417885017767767,13066 "W1_flesch": 0.0817698850783194,13067 "W1_mean": 0.1122796616451704513068 },13069 "feature_means": {13070 "mean_sent_len": 25.958566790115615,13071 "sd_sent_len": 8.60472699823935,13072 "ttr": 0.6423844617831883,13073 "mtld": 73.79813452347419,13074 "mean_word_len": 5.429800199120557,13075 "long_word_rate": 0.11023799358475453,13076 "comma_rate": 0.058711392803239386,13077 "semicolon_rate": 0.004023940627019275,13078 "paren_rate": 0.02446249531243301,13079 "discourse_rate": 0.008311285196836177,13080 "passive_rate": 0.5298883995597142,13081 "nominal_rate": 0.053536331701048566,13082 "first_person_rate": 0.0024504982826217847,13083 "subord_rate": 0.022886467076021978,13084 "hedge_rate": 0.004585233732198783,13085 "negation_rate": 0.0045997433959496575,13086 "digit_rate": 0.020815269257554,13087 "flesch": 21.4590256214749813088 },13089 "probe": {13090 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13091 "probe_acc_heldout": 0.6059602649006622,13092 "eval_mean_p_original": 0.5404516735953796,13093 "eval_frac_classified_original": 0.611553784860557813094 }13095 },13096 "htr-denoise-only": {13097 "vs_original": {13098 "W1_mean_sent_len": 0.19242209790865453,13099 "W1_sd_sent_len": 0.17271499174353436,13100 "W1_ttr": 0.42404560402425845,13101 "W1_mtld": 0.23014498063140915,13102 "W1_mean_word_len": 0.2783555257291717,13103 "W1_long_word_rate": 0.1840589179265139,13104 "W1_comma_rate": 0.3252509944384211,13105 "W1_semicolon_rate": 0.11048133582946691,13106 "W1_paren_rate": 0.08185983412783011,13107 "W1_discourse_rate": 0.20946619728138502,13108 "W1_passive_rate": 0.13566978637897667,13109 "W1_nominal_rate": 0.21378811660605557,13110 "W1_first_person_rate": 0.2635423752519141,13111 "W1_subord_rate": 0.22148969148006534,13112 "W1_hedge_rate": 0.2838427717506629,13113 "W1_negation_rate": 0.2538380523836624,13114 "W1_digit_rate": 0.07073936058424792,13115 "W1_flesch": 0.20957301706526105,13116 "W1_mean": 0.2145157583967495213117 },13118 "feature_means": {13119 "mean_sent_len": 24.966529027634603,13120 "sd_sent_len": 8.6087176694217,13121 "ttr": 0.6368920111945818,13122 "mtld": 71.10503028513429,13123 "mean_word_len": 5.467991327915724,13124 "long_word_rate": 0.11135540580710122,13125 "comma_rate": 0.059873400807775125,13126 "semicolon_rate": 0.0045210416853296844,13127 "paren_rate": 0.023587110571879528,13128 "discourse_rate": 0.007597050720317571,13129 "passive_rate": 0.49609329360325366,13130 "nominal_rate": 0.05222076487031447,13131 "first_person_rate": 0.0022794455168756588,13132 "subord_rate": 0.024467111413559364,13133 "hedge_rate": 0.005409971282542075,13134 "negation_rate": 0.004568023503802907,13135 "digit_rate": 0.020885352872935727,13136 "flesch": 21.95094347976141313137 },13138 "probe": {13139 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13140 "probe_acc_heldout": 0.6059602649006622,13141 "eval_mean_p_original": 0.5264522408627899,13142 "eval_frac_classified_original": 0.571713147410358613143 }13144 },13145 "htr-m1-tiny-denoiseinit": {13146 "vs_original": {13147 "W1_mean_sent_len": 0.1511205309314669,13148 "W1_sd_sent_len": 0.1117332973356636,13149 "W1_ttr": 0.10801680681690552,13150 "W1_mtld": 0.33910492771715345,13151 "W1_mean_word_len": 0.2469447356606326,13152 "W1_long_word_rate": 0.12822528101657826,13153 "W1_comma_rate": 0.3427573167354112,13154 "W1_semicolon_rate": 0.12384866440310136,13155 "W1_paren_rate": 0.0499499261848629,13156 "W1_discourse_rate": 0.06408784978812483,13157 "W1_passive_rate": 0.2921683397699533,13158 "W1_nominal_rate": 0.09650025792073011,13159 "W1_first_person_rate": 0.07796022600563803,13160 "W1_subord_rate": 0.11411902515823494,13161 "W1_hedge_rate": 0.07928745127451436,13162 "W1_negation_rate": 0.1478307439224504,13163 "W1_digit_rate": 0.034832791932104416,13164 "W1_flesch": 0.1983313661337669,13165 "W1_mean": 0.1503788632615162813166 },13167 "feature_means": {13168 "mean_sent_len": 25.76657263442622,13169 "sd_sent_len": 8.698318029003591,13170 "ttr": 0.638697272424977,13171 "mtld": 66.65116254473983,13172 "mean_word_len": 5.323513034908457,13173 "long_word_rate": 0.10446293747374921,13174 "comma_rate": 0.0607679045538513,13175 "semicolon_rate": 0.0037920430717460394,13176 "paren_rate": 0.023805736543397602,13177 "discourse_rate": 0.007767092772692719,13178 "passive_rate": 0.5718306068654676,13179 "nominal_rate": 0.05396444946482739,13180 "first_person_rate": 0.0030159037453920097,13181 "subord_rate": 0.023836158072563413,13182 "hedge_rate": 0.004216222611638543,13183 "negation_rate": 0.004228984674132187,13184 "digit_rate": 0.020217422540281183,13185 "flesch": 24.81346613511445713186 },13187 "probe": {13188 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13189 "probe_acc_heldout": 0.6059602649006622,13190 "eval_mean_p_original": 0.5532922622418285,13191 "eval_frac_classified_original": 0.667330677290836613192 }13193 },13194 "htr-m1-tiny-mediumdenoiseinit": {13195 "vs_original": {13196 "W1_mean_sent_len": 0.1716962743375337,13197 "W1_sd_sent_len": 0.14579007261451418,13198 "W1_ttr": 0.1103961793295351,13199 "W1_mtld": 0.13302134578514907,13200 "W1_mean_word_len": 0.12778929642311415,13201 "W1_long_word_rate": 0.1186886142778446,13202 "W1_comma_rate": 0.22014687956966622,13203 "W1_semicolon_rate": 0.09485804426207031,13204 "W1_paren_rate": 0.05161893537157036,13205 "W1_discourse_rate": 0.05900783389531671,13206 "W1_passive_rate": 0.37212995156150186,13207 "W1_nominal_rate": 0.12170574218608197,13208 "W1_first_person_rate": 0.15262675160095662,13209 "W1_subord_rate": 0.22184899384344925,13210 "W1_hedge_rate": 0.07942462425452576,13211 "W1_negation_rate": 0.12412320102357624,13212 "W1_digit_rate": 0.036579983495733576,13213 "W1_flesch": 0.12959622144298785,13214 "W1_mean": 0.137280496959729313215 },13216 "feature_means": {13217 "mean_sent_len": 24.961092850201133,13218 "sd_sent_len": 8.590537416116016,13219 "ttr": 0.6455319739512289,13220 "mtld": 73.10608403984747,13221 "mean_word_len": 5.382159235259426,13222 "long_word_rate": 0.1062233005327708,13223 "comma_rate": 0.05593506206459229,13224 "semicolon_rate": 0.00402382981208523,13225 "paren_rate": 0.023680674428123872,13226 "discourse_rate": 0.007769785509961525,13227 "passive_rate": 0.600807674085152,13228 "nominal_rate": 0.05302474823994762,13229 "first_person_rate": 0.0024659135836435776,13230 "subord_rate": 0.02559680860942427,13231 "hedge_rate": 0.004227124973385719,13232 "negation_rate": 0.004384114686741737,13233 "digit_rate": 0.02056065288374733,13234 "flesch": 23.8110968303127713235 },13236 "probe": {13237 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13238 "probe_acc_heldout": 0.6059602649006622,13239 "eval_mean_p_original": 0.5475467003658718,13240 "eval_frac_classified_original": 0.607569721115537913241 }13242 },13243 "htr-m1-tiny": {13244 "vs_original": {13245 "W1_mean_sent_len": 1.2703420529529994,13246 "W1_sd_sent_len": 1.7184546435585595,13247 "W1_ttr": 2.1956663194786556,13248 "W1_mtld": 2.0572416452307145,13249 "W1_mean_word_len": 10.8409432379061,13250 "W1_long_word_rate": 0.8914849277980097,13251 "W1_comma_rate": 0.4021988206853386,13252 "W1_semicolon_rate": 0.2044271217113101,13253 "W1_paren_rate": 0.3794028810523868,13254 "W1_discourse_rate": 0.5204571770012922,13255 "W1_passive_rate": 0.48337756917631736,13256 "W1_nominal_rate": 0.5426283138362586,13257 "W1_first_person_rate": 0.3507021569255897,13258 "W1_subord_rate": 0.6798685505864364,13259 "W1_hedge_rate": 0.3221542776928466,13260 "W1_negation_rate": 0.39502351414004516,13261 "W1_digit_rate": 0.1562034539539809,13262 "W1_flesch": 7.169567686414069,13263 "W1_mean": 1.698896908338939613264 },13265 "feature_means": {13266 "mean_sent_len": 28.31189977298044,13267 "sd_sent_len": 14.960832949117384,13268 "ttr": 0.4369796707531769,13269 "mtld": 14.928789729076978,13270 "mean_word_len": 8.9038947891805,13271 "long_word_rate": 0.10470327332131085,13272 "comma_rate": 0.05224918546115159,13273 "semicolon_rate": 0.002392519589051433,13274 "paren_rate": 0.030562140820874457,13275 "discourse_rate": 0.0050232206566186806,13276 "passive_rate": 0.44506095663964207,13277 "nominal_rate": 0.04981593092905524,13278 "first_person_rate": 0.0048446311679809515,13279 "subord_rate": 0.01498294219198282,13280 "hedge_rate": 0.0029082270408961517,13281 "negation_rate": 0.0032195413162135157,13282 "digit_rate": 0.020104252016553362,13283 "flesch": -27.65229003299792513284 },13285 "probe": {13286 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13287 "probe_acc_heldout": 0.6059602649006622,13288 "eval_mean_p_original": 0.7310646108304102,13289 "eval_frac_classified_original": 0.812749003984063813290 }13291 },13292 "htr-pilot_m1_tiny_denoiseinit_s2": {13293 "vs_original": {13294 "W1_mean_sent_len": 0.1187073322459574,13295 "W1_sd_sent_len": 0.12388312173592084,13296 "W1_ttr": 0.08140429286685022,13297 "W1_mtld": 0.23999156433790061,13298 "W1_mean_word_len": 0.20166807100340958,13299 "W1_long_word_rate": 0.12085246463315961,13300 "W1_comma_rate": 0.34645858462509405,13301 "W1_semicolon_rate": 0.09904795744768267,13302 "W1_paren_rate": 0.054436129458698065,13303 "W1_discourse_rate": 0.06496540255163635,13304 "W1_passive_rate": 0.3674126114379113,13305 "W1_nominal_rate": 0.1109178083447146,13306 "W1_first_person_rate": 0.10127084296725017,13307 "W1_subord_rate": 0.10482231584001052,13308 "W1_hedge_rate": 0.05964804878663293,13309 "W1_negation_rate": 0.13650401361272765,13310 "W1_digit_rate": 0.02714339363857325,13311 "W1_flesch": 0.11877595676502725,13312 "W1_mean": 0.1376616617943976513313 },13314 "feature_means": {13315 "mean_sent_len": 26.164495760111844,13316 "sd_sent_len": 8.83319395807729,13317 "ttr": 0.6431331860640372,13318 "mtld": 69.65623700512634,13319 "mean_word_len": 5.346105931503124,13320 "long_word_rate": 0.10473967797362631,13321 "comma_rate": 0.060849630433653365,13322 "semicolon_rate": 0.0039474509734050344,13323 "paren_rate": 0.023765080295865545,13324 "discourse_rate": 0.008052304397336939,13325 "passive_rate": 0.5999224896591314,13326 "nominal_rate": 0.05371633655541842,13327 "first_person_rate": 0.002826800855690221,13328 "subord_rate": 0.023098515349367296,13329 "hedge_rate": 0.004121976061150119,13330 "negation_rate": 0.004127244581509009,13331 "digit_rate": 0.020003756332517757,13332 "flesch": 23.61551989955034613333 },13334 "probe": {13335 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13336 "probe_acc_heldout": 0.6059602649006622,13337 "eval_mean_p_original": 0.5445402642049988,13338 "eval_frac_classified_original": 0.631474103585657413339 }13340 },13341 "htr-pilot_m3light_tiny_denoiseinit": {13342 "vs_original": {13343 "W1_mean_sent_len": 0.09247005759351105,13344 "W1_sd_sent_len": 0.10345155724278149,13345 "W1_ttr": 0.1215147888567603,13346 "W1_mtld": 0.2186636025723757,13347 "W1_mean_word_len": 0.21562337070911763,13348 "W1_long_word_rate": 0.12680031296217745,13349 "W1_comma_rate": 0.3551418775176367,13350 "W1_semicolon_rate": 0.10971451405061938,13351 "W1_paren_rate": 0.05879968387154649,13352 "W1_discourse_rate": 0.08127544424363822,13353 "W1_passive_rate": 0.4099076432581312,13354 "W1_nominal_rate": 0.14543806712409962,13355 "W1_first_person_rate": 0.13707709686341743,13356 "W1_subord_rate": 0.23840054620334364,13357 "W1_hedge_rate": 0.06679612251092798,13358 "W1_negation_rate": 0.12496130247674377,13359 "W1_digit_rate": 0.029006331515281404,13360 "W1_flesch": 0.15238206290782225,13361 "W1_mean": 0.1548569101377739713362 },13363 "feature_means": {13364 "mean_sent_len": 25.827507966800773,13365 "sd_sent_len": 8.817691926401116,13366 "ttr": 0.6471501719702837,13367 "mtld": 70.2944465343401,13368 "mean_word_len": 5.338466650246886,13369 "long_word_rate": 0.1046153140915385,13370 "comma_rate": 0.06116618154460635,13371 "semicolon_rate": 0.0038137182383753323,13372 "paren_rate": 0.024006755181816088,13373 "discourse_rate": 0.007382378115904174,13374 "passive_rate": 0.6136801224450626,13375 "nominal_rate": 0.052399729444686356,13376 "first_person_rate": 0.002558908342576023,13377 "subord_rate": 0.025869946545720907,13378 "hedge_rate": 0.004376332487651248,13379 "negation_rate": 0.004677500808580317,13380 "digit_rate": 0.02024929888893815,13381 "flesch": 24.19819893789020413382 },13383 "probe": {13384 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13385 "probe_acc_heldout": 0.6059602649006622,13386 "eval_mean_p_original": 0.5263999728821372,13387 "eval_frac_classified_original": 0.583665338645418413388 }13389 },13390 "htr-pilot_m3tokenonly_tiny_denoiseinit": {13391 "vs_original": {13392 "W1_mean_sent_len": 0.11172175958621414,13393 "W1_sd_sent_len": 0.15149910435250427,13394 "W1_ttr": 0.12188723400474032,13395 "W1_mtld": 0.1848973051143551,13396 "W1_mean_word_len": 0.22285252991570673,13397 "W1_long_word_rate": 0.13513324638481886,13398 "W1_comma_rate": 0.3742962717401992,13399 "W1_semicolon_rate": 0.10461888052686259,13400 "W1_paren_rate": 0.04669124471070915,13401 "W1_discourse_rate": 0.10507618076262526,13402 "W1_passive_rate": 0.3793949367801599,13403 "W1_nominal_rate": 0.15905141966004754,13404 "W1_first_person_rate": 0.1516380564776306,13405 "W1_subord_rate": 0.2082904104322992,13406 "W1_hedge_rate": 0.09055462436107459,13407 "W1_negation_rate": 0.10474314125527556,13408 "W1_digit_rate": 0.03605075701711473,13409 "W1_flesch": 0.1739138225997733,13410 "W1_mean": 0.159017273649006213411 },13412 "feature_means": {13413 "mean_sent_len": 25.77230431697563,13414 "sd_sent_len": 8.706066962257044,13415 "ttr": 0.6483662128564884,13416 "mtld": 71.3380670130666,13417 "mean_word_len": 5.335012379955838,13418 "long_word_rate": 0.10460180108451492,13419 "comma_rate": 0.06217010436842354,13420 "semicolon_rate": 0.0038376518326151635,13421 "paren_rate": 0.024197682651775874,13422 "discourse_rate": 0.0072400623270230885,13423 "passive_rate": 0.6031786108977347,13424 "nominal_rate": 0.05193100719408231,13425 "first_person_rate": 0.002503843488122218,13426 "subord_rate": 0.025384069829557925,13427 "hedge_rate": 0.004415530002064558,13428 "negation_rate": 0.0047070197410591435,13429 "digit_rate": 0.020491918874532694,13430 "flesch": 24.51751847461760613431 },13432 "probe": {13433 "probe_auc_orig_vs_rewrite": 0.6862727871732923,13434 "probe_acc_heldout": 0.6059602649006622,13435 "eval_mean_p_original": 0.5225110239541864,13436 "eval_frac_classified_original": 0.591633466135458213437 }13438 }13439 }13440}13441