Repository Public Research preview
1{2 "created_at": "2026-11-10T17:19:41Z",3 "git": {4 "commit": "883ce93e2f627cf3d42040460687c511ef436337",5 "branch": "main",6 "dirty": true7 },8 "libraries": {9 "python": "3.14.4",10 "torch": "2.12.0",11 "numpy": "2.5.4",12 "anthropic": "2.3.0",13 "transformers": "5.8.1",14 "sentencepiece": "0.2.2",15 "lxml": "6.1.3",16 "pyarrow": "24.0.0",17 "sacrebleu": "2.6.0",18 "datasketch": "2.0.0",19 "rapidfuzz": "3.14.6"20 },21 "hardware": {22 "platform": "macOS-27.0-arm64-arm-64bit-Mach-O",23 "machine": "arm64",24 "cpu_count": 18,25 "chip": "Apple M5 Max",26 "ram_gb": 48.0,27 "torch_mps": true,28 "torch_cuda": false29 },30 "n_pairs": 531,31 "systems": {32 "B0_identity": {33 "overall": {34 "n": 531,35 "chrf": {36 "mean": 74.09735850305259,37 "ci_low": 72.9852926930523,38 "ci_high": 75.53591350986837,39 "n_items": 531,40 "n_groups": 5541 },42 "edit_sim": {43 "mean": 0.7296165310393293,44 "ci_low": 0.720503841860743,45 "ci_high": 0.7415973359660197,46 "n_items": 531,47 "n_groups": 5548 },49 "rougeL": {50 "mean": 0.7350224935713351,51 "ci_low": 0.7228677049992028,52 "ci_high": 0.7505789673733297,53 "n_items": 531,54 "n_groups": 5555 },56 "exact_match": {57 "mean": 0.0,58 "ci_low": 0.0,59 "ci_high": 0.0,60 "n_items": 531,61 "n_groups": 5562 },63 "number_recall": {64 "mean": 1.0,65 "ci_low": 1.0,66 "ci_high": 1.0,67 "n_items": 531,68 "n_groups": 5569 },70 "placeholders_exact": {71 "mean": 1.0,72 "ci_low": 1.0,73 "ci_high": 1.0,74 "n_items": 531,75 "n_groups": 5576 }77 },78 "by_variant": {79 "A": {80 "n": 267,81 "chrf": {82 "mean": 68.61885835049287,83 "ci_low": 67.43146317275819,84 "ci_high": 70.14581253748482,85 "n_items": 267,86 "n_groups": 5387 },88 "edit_sim": {89 "mean": 0.6624871917607208,90 "ci_low": 0.6496984206525277,91 "ci_high": 0.6771035785121357,92 "n_items": 267,93 "n_groups": 5394 },95 "rougeL": {96 "mean": 0.6661812260148625,97 "ci_low": 0.6525114017777672,98 "ci_high": 0.6832436278370377,99 "n_items": 267,100 "n_groups": 53101 },102 "exact_match": {103 "mean": 0.0,104 "ci_low": 0.0,105 "ci_high": 0.0,106 "n_items": 267,107 "n_groups": 53108 },109 "number_recall": {110 "mean": 1.0,111 "ci_low": 1.0,112 "ci_high": 1.0,113 "n_items": 267,114 "n_groups": 53115 },116 "placeholders_exact": {117 "mean": 1.0,118 "ci_low": 1.0,119 "ci_high": 1.0,120 "n_items": 267,121 "n_groups": 53122 }123 },124 "B": {125 "n": 264,126 "chrf": {127 "mean": 79.63811433916412,128 "ci_low": 78.36637832310636,129 "ci_high": 81.17474252498255,130 "n_items": 264,131 "n_groups": 54132 },133 "edit_sim": {134 "mean": 0.7975087037188312,135 "ci_low": 0.7862718697488066,136 "ci_high": 0.8103816479097101,137 "n_items": 264,138 "n_groups": 54139 },140 "rougeL": {141 "mean": 0.8046460482591311,142 "ci_low": 0.7906262843904555,143 "ci_high": 0.8215499822250224,144 "n_items": 264,145 "n_groups": 54146 },147 "exact_match": {148 "mean": 0.0,149 "ci_low": 0.0,150 "ci_high": 0.0,151 "n_items": 264,152 "n_groups": 54153 },154 "number_recall": {155 "mean": 1.0,156 "ci_low": 1.0,157 "ci_high": 1.0,158 "n_items": 264,159 "n_groups": 54160 },161 "placeholders_exact": {162 "mean": 1.0,163 "ci_low": 1.0,164 "ci_high": 1.0,165 "n_items": 264,166 "n_groups": 54167 }168 }169 },170 "by_discipline": {171 "biomedicine": {172 "n": 118,173 "chrf": {174 "mean": 76.25897748491485,175 "ci_low": 74.27228287473694,176 "ci_high": 78.065249913662,177 "n_items": 118,178 "n_groups": 26179 },180 "edit_sim": {181 "mean": 0.7429198148536477,182 "ci_low": 0.7221631919535642,183 "ci_high": 0.7610323304238035,184 "n_items": 118,185 "n_groups": 26186 },187 "rougeL": {188 "mean": 0.7547854414395244,189 "ci_low": 0.7346130606174267,190 "ci_high": 0.7734165503988791,191 "n_items": 118,192 "n_groups": 26193 },194 "exact_match": {195 "mean": 0.0,196 "ci_low": 0.0,197 "ci_high": 0.0,198 "n_items": 118,199 "n_groups": 26200 },201 "number_recall": {202 "mean": 1.0,203 "ci_low": 1.0,204 "ci_high": 1.0,205 "n_items": 118,206 "n_groups": 26207 },208 "placeholders_exact": {209 "mean": 1.0,210 "ci_low": 1.0,211 "ci_high": 1.0,212 "n_items": 118,213 "n_groups": 26214 }215 },216 "computer_science": {217 "n": 57,218 "chrf": {219 "mean": 73.62604389860856,220 "ci_low": 71.27570200286345,221 "ci_high": 78.7184513393896,222 "n_items": 57,223 "n_groups": 2224 },225 "edit_sim": {226 "mean": 0.733629098148365,227 "ci_low": 0.7215197616003136,228 "ci_high": 0.7598659940024767,229 "n_items": 57,230 "n_groups": 2231 },232 "rougeL": {233 "mean": 0.7292048456153359,234 "ci_low": 0.7027141037036976,235 "ci_high": 0.7866014530905524,236 "n_items": 57,237 "n_groups": 2238 },239 "exact_match": {240 "mean": 0.0,241 "ci_low": 0.0,242 "ci_high": 0.0,243 "n_items": 57,244 "n_groups": 2245 },246 "number_recall": {247 "mean": 1.0,248 "ci_low": 1.0,249 "ci_high": 1.0,250 "n_items": 57,251 "n_groups": 2252 },253 "placeholders_exact": {254 "mean": 1.0,255 "ci_low": 1.0,256 "ci_high": 1.0,257 "n_items": 57,258 "n_groups": 2259 }260 },261 "earth_sciences": {262 "n": 64,263 "chrf": {264 "mean": 72.19820887343154,265 "ci_low": 70.43195541782559,266 "ci_high": 74.23267715127565,267 "n_items": 64,268 "n_groups": 3269 },270 "edit_sim": {271 "mean": 0.7105519929521058,272 "ci_low": 0.6887541184642032,273 "ci_high": 0.7236146382915184,274 "n_items": 64,275 "n_groups": 3276 },277 "rougeL": {278 "mean": 0.7200757121809718,279 "ci_low": 0.6852621253929488,280 "ci_high": 0.7478257578711085,281 "n_items": 64,282 "n_groups": 3283 },284 "exact_match": {285 "mean": 0.0,286 "ci_low": 0.0,287 "ci_high": 0.0,288 "n_items": 64,289 "n_groups": 3290 },291 "number_recall": {292 "mean": 1.0,293 "ci_low": 1.0,294 "ci_high": 1.0,295 "n_items": 64,296 "n_groups": 3297 },298 "placeholders_exact": {299 "mean": 1.0,300 "ci_low": 1.0,301 "ci_high": 1.0,302 "n_items": 64,303 "n_groups": 3304 }305 },306 "economics": {307 "n": 64,308 "chrf": {309 "mean": 71.9836326236494,310 "ci_low": 71.9836326236494,311 "ci_high": 71.9836326236494,312 "n_items": 64,313 "n_groups": 1314 },315 "edit_sim": {316 "mean": 0.7152493387313763,317 "ci_low": 0.7152493387313763,318 "ci_high": 0.7152493387313763,319 "n_items": 64,320 "n_groups": 1321 },322 "rougeL": {323 "mean": 0.7080753467534434,324 "ci_low": 0.7080753467534434,325 "ci_high": 0.7080753467534434,326 "n_items": 64,327 "n_groups": 1328 },329 "exact_match": {330 "mean": 0.0,331 "ci_low": 0.0,332 "ci_high": 0.0,333 "n_items": 64,334 "n_groups": 1335 },336 "number_recall": {337 "mean": 1.0,338 "ci_low": 1.0,339 "ci_high": 1.0,340 "n_items": 64,341 "n_groups": 1342 },343 "placeholders_exact": {344 "mean": 1.0,345 "ci_low": 1.0,346 "ci_high": 1.0,347 "n_items": 64,348 "n_groups": 1349 }350 },351 "engineering": {352 "n": 11,353 "chrf": {354 "mean": 73.10799868680554,355 "ci_low": 73.10799868680554,356 "ci_high": 73.10799868680554,357 "n_items": 11,358 "n_groups": 1359 },360 "edit_sim": {361 "mean": 0.7226746267894654,362 "ci_low": 0.7226746267894654,363 "ci_high": 0.7226746267894654,364 "n_items": 11,365 "n_groups": 1366 },367 "rougeL": {368 "mean": 0.694940328496901,369 "ci_low": 0.694940328496901,370 "ci_high": 0.694940328496901,371 "n_items": 11,372 "n_groups": 1373 },374 "exact_match": {375 "mean": 0.0,376 "ci_low": 0.0,377 "ci_high": 0.0,378 "n_items": 11,379 "n_groups": 1380 },381 "number_recall": {382 "mean": 1.0,383 "ci_low": 1.0,384 "ci_high": 1.0,385 "n_items": 11,386 "n_groups": 1387 },388 "placeholders_exact": {389 "mean": 1.0,390 "ci_low": 1.0,391 "ci_high": 1.0,392 "n_items": 11,393 "n_groups": 1394 }395 },396 "life_sciences": {397 "n": 95,398 "chrf": {399 "mean": 76.40170932749884,400 "ci_low": 73.72395476412905,401 "ci_high": 79.4528945908895,402 "n_items": 95,403 "n_groups": 16404 },405 "edit_sim": {406 "mean": 0.7537350753883516,407 "ci_low": 0.725762933235402,408 "ci_high": 0.7861348733670778,409 "n_items": 95,410 "n_groups": 16411 },412 "rougeL": {413 "mean": 0.7613015488491759,414 "ci_low": 0.7312890987438148,415 "ci_high": 0.7950064489911026,416 "n_items": 95,417 "n_groups": 16418 },419 "exact_match": {420 "mean": 0.0,421 "ci_low": 0.0,422 "ci_high": 0.0,423 "n_items": 95,424 "n_groups": 16425 },426 "number_recall": {427 "mean": 1.0,428 "ci_low": 1.0,429 "ci_high": 1.0,430 "n_items": 95,431 "n_groups": 16432 },433 "placeholders_exact": {434 "mean": 1.0,435 "ci_low": 1.0,436 "ci_high": 1.0,437 "n_items": 95,438 "n_groups": 16439 }440 },441 "social_sciences": {442 "n": 75,443 "chrf": {444 "mean": 73.20293823701438,445 "ci_low": 67.11523698395015,446 "ci_high": 76.20998946074042,447 "n_items": 75,448 "n_groups": 4449 },450 "edit_sim": {451 "mean": 0.7235731601896878,452 "ci_low": 0.6820601908169195,453 "ci_high": 0.7424369174612734,454 "n_items": 75,455 "n_groups": 4456 },457 "rougeL": {458 "mean": 0.7282656243437794,459 "ci_low": 0.6667100656978142,460 "ci_high": 0.752731498627293,461 "n_items": 75,462 "n_groups": 4463 },464 "exact_match": {465 "mean": 0.0,466 "ci_low": 0.0,467 "ci_high": 0.0,468 "n_items": 75,469 "n_groups": 4470 },471 "number_recall": {472 "mean": 1.0,473 "ci_low": 1.0,474 "ci_high": 1.0,475 "n_items": 75,476 "n_groups": 4477 },478 "placeholders_exact": {479 "mean": 1.0,480 "ci_low": 1.0,481 "ci_high": 1.0,482 "n_items": 75,483 "n_groups": 4484 }485 },486 "statistics": {487 "n": 47,488 "chrf": {489 "mean": 71.70733881752716,490 "ci_low": 71.14529481935185,491 "ci_high": 71.99742604239182,492 "n_items": 47,493 "n_groups": 2494 },495 "edit_sim": {496 "mean": 0.6993926794925472,497 "ci_low": 0.6930919376418176,498 "ci_high": 0.7026446752864722,499 "n_items": 47,500 "n_groups": 2501 },502 "rougeL": {503 "mean": 0.7165533073344088,504 "ci_low": 0.7089264177490493,505 "ci_high": 0.7313304059060428,506 "n_items": 47,507 "n_groups": 2508 },509 "exact_match": {510 "mean": 0.0,511 "ci_low": 0.0,512 "ci_high": 0.0,513 "n_items": 47,514 "n_groups": 2515 },516 "number_recall": {517 "mean": 1.0,518 "ci_low": 1.0,519 "ci_high": 1.0,520 "n_items": 47,521 "n_groups": 2522 },523 "placeholders_exact": {524 "mean": 1.0,525 "ci_low": 1.0,526 "ci_high": 1.0,527 "n_items": 47,528 "n_groups": 2529 }530 }531 },532 "by_era": {533 "1980-1999": {534 "n": 5,535 "chrf": {536 "mean": 79.09654139810681,537 "ci_low": 74.25022563117723,538 "ci_high": 86.3660150485012,539 "n_items": 5,540 "n_groups": 2541 },542 "edit_sim": {543 "mean": 0.8177757720335739,544 "ci_low": 0.7887509598387291,545 "ci_high": 0.8613129903258411,546 "n_items": 5,547 "n_groups": 2548 },549 "rougeL": {550 "mean": 0.8035824409520362,551 "ci_low": 0.7675413489688632,552 "ci_high": 0.8576440789267956,553 "n_items": 5,554 "n_groups": 2555 },556 "exact_match": {557 "mean": 0.0,558 "ci_low": 0.0,559 "ci_high": 0.0,560 "n_items": 5,561 "n_groups": 2562 },563 "number_recall": {564 "mean": 1.0,565 "ci_low": 1.0,566 "ci_high": 1.0,567 "n_items": 5,568 "n_groups": 2569 },570 "placeholders_exact": {571 "mean": 1.0,572 "ci_low": 1.0,573 "ci_high": 1.0,574 "n_items": 5,575 "n_groups": 2576 }577 },578 "2000-2009": {579 "n": 58,580 "chrf": {581 "mean": 73.6400202894656,582 "ci_low": 71.50660777307215,583 "ci_high": 76.8776792344721,584 "n_items": 58,585 "n_groups": 7586 },587 "edit_sim": {588 "mean": 0.7214369025204301,589 "ci_low": 0.7034228177058538,590 "ci_high": 0.7484797478851362,591 "n_items": 58,592 "n_groups": 7593 },594 "rougeL": {595 "mean": 0.7327582570680545,596 "ci_low": 0.7080297311146776,597 "ci_high": 0.7627250088629595,598 "n_items": 58,599 "n_groups": 7600 },601 "exact_match": {602 "mean": 0.0,603 "ci_low": 0.0,604 "ci_high": 0.0,605 "n_items": 58,606 "n_groups": 7607 },608 "number_recall": {609 "mean": 1.0,610 "ci_low": 1.0,611 "ci_high": 1.0,612 "n_items": 58,613 "n_groups": 7614 },615 "placeholders_exact": {616 "mean": 1.0,617 "ci_low": 1.0,618 "ci_high": 1.0,619 "n_items": 58,620 "n_groups": 7621 }622 },623 "2010-2017": {624 "n": 468,625 "chrf": {626 "mean": 74.1006270968833,627 "ci_low": 72.87122228813497,628 "ci_high": 75.64996863253353,629 "n_items": 468,630 "n_groups": 46631 },632 "edit_sim": {633 "mean": 0.7296883734519896,634 "ci_low": 0.7196432514807597,635 "ci_high": 0.7425147236884504,636 "n_items": 468,637 "n_groups": 46638 },639 "rougeL": {640 "mean": 0.7345706260078452,641 "ci_low": 0.7209704169725577,642 "ci_high": 0.751599651598519,643 "n_items": 468,644 "n_groups": 46645 },646 "exact_match": {647 "mean": 0.0,648 "ci_low": 0.0,649 "ci_high": 0.0,650 "n_items": 468,651 "n_groups": 46652 },653 "number_recall": {654 "mean": 1.0,655 "ci_low": 1.0,656 "ci_high": 1.0,657 "n_items": 468,658 "n_groups": 46659 },660 "placeholders_exact": {661 "mean": 1.0,662 "ci_low": 1.0,663 "ci_high": 1.0,664 "n_items": 468,665 "n_groups": 46666 }667 }668 },669 "by_role": {670 "abstract": {671 "n": 55,672 "chrf": {673 "mean": 77.30295278521172,674 "ci_low": 75.03371591437453,675 "ci_high": 79.44480222171971,676 "n_items": 55,677 "n_groups": 15678 },679 "edit_sim": {680 "mean": 0.7655626357210039,681 "ci_low": 0.7453327152927198,682 "ci_high": 0.784263726940902,683 "n_items": 55,684 "n_groups": 15685 },686 "rougeL": {687 "mean": 0.7601432768401742,688 "ci_low": 0.7370746935609966,689 "ci_high": 0.7836772896026495,690 "n_items": 55,691 "n_groups": 15692 },693 "exact_match": {694 "mean": 0.0,695 "ci_low": 0.0,696 "ci_high": 0.0,697 "n_items": 55,698 "n_groups": 15699 },700 "number_recall": {701 "mean": 1.0,702 "ci_low": 1.0,703 "ci_high": 1.0,704 "n_items": 55,705 "n_groups": 15706 },707 "placeholders_exact": {708 "mean": 1.0,709 "ci_low": 1.0,710 "ci_high": 1.0,711 "n_items": 55,712 "n_groups": 15713 }714 },715 "background": {716 "n": 36,717 "chrf": {718 "mean": 74.72977940807455,719 "ci_low": 71.90137847314853,720 "ci_high": 76.96049359513817,721 "n_items": 36,722 "n_groups": 7723 },724 "edit_sim": {725 "mean": 0.7400455031665572,726 "ci_low": 0.7095343349881201,727 "ci_high": 0.7683100630464078,728 "n_items": 36,729 "n_groups": 7730 },731 "rougeL": {732 "mean": 0.7449471720426997,733 "ci_low": 0.7249650960355464,734 "ci_high": 0.7641427265777122,735 "n_items": 36,736 "n_groups": 7737 },738 "exact_match": {739 "mean": 0.0,740 "ci_low": 0.0,741 "ci_high": 0.0,742 "n_items": 36,743 "n_groups": 7744 },745 "number_recall": {746 "mean": 1.0,747 "ci_low": 1.0,748 "ci_high": 1.0,749 "n_items": 36,750 "n_groups": 7751 },752 "placeholders_exact": {753 "mean": 1.0,754 "ci_low": 1.0,755 "ci_high": 1.0,756 "n_items": 36,757 "n_groups": 7758 }759 },760 "conclusion": {761 "n": 36,762 "chrf": {763 "mean": 70.57998215565435,764 "ci_low": 67.78457893419305,765 "ci_high": 73.23661322912169,766 "n_items": 36,767 "n_groups": 9768 },769 "edit_sim": {770 "mean": 0.7044531906740836,771 "ci_low": 0.6729820467628196,772 "ci_high": 0.7408457410625443,773 "n_items": 36,774 "n_groups": 9775 },776 "rougeL": {777 "mean": 0.6924300680664327,778 "ci_low": 0.655218354807707,779 "ci_high": 0.728619142398708,780 "n_items": 36,781 "n_groups": 9782 },783 "exact_match": {784 "mean": 0.0,785 "ci_low": 0.0,786 "ci_high": 0.0,787 "n_items": 36,788 "n_groups": 9789 },790 "number_recall": {791 "mean": 1.0,792 "ci_low": 1.0,793 "ci_high": 1.0,794 "n_items": 36,795 "n_groups": 9796 },797 "placeholders_exact": {798 "mean": 1.0,799 "ci_low": 1.0,800 "ci_high": 1.0,801 "n_items": 36,802 "n_groups": 9803 }804 },805 "data": {806 "n": 41,807 "chrf": {808 "mean": 77.76462553180018,809 "ci_low": 73.39117858798821,810 "ci_high": 81.8565713375424,811 "n_items": 41,812 "n_groups": 10813 },814 "edit_sim": {815 "mean": 0.7406672454569356,816 "ci_low": 0.6975094312646304,817 "ci_high": 0.7943085504235705,818 "n_items": 41,819 "n_groups": 10820 },821 "rougeL": {822 "mean": 0.7649063394458633,823 "ci_low": 0.7178397811444941,824 "ci_high": 0.8155466077205137,825 "n_items": 41,826 "n_groups": 10827 },828 "exact_match": {829 "mean": 0.0,830 "ci_low": 0.0,831 "ci_high": 0.0,832 "n_items": 41,833 "n_groups": 10834 },835 "number_recall": {836 "mean": 1.0,837 "ci_low": 1.0,838 "ci_high": 1.0,839 "n_items": 41,840 "n_groups": 10841 },842 "placeholders_exact": {843 "mean": 1.0,844 "ci_low": 1.0,845 "ci_high": 1.0,846 "n_items": 41,847 "n_groups": 10848 }849 },850 "discussion": {851 "n": 69,852 "chrf": {853 "mean": 74.0393849238493,854 "ci_low": 71.4880196764122,855 "ci_high": 76.28519071601724,856 "n_items": 69,857 "n_groups": 14858 },859 "edit_sim": {860 "mean": 0.733156445257548,861 "ci_low": 0.7049903454760429,862 "ci_high": 0.7589451112068152,863 "n_items": 69,864 "n_groups": 14865 },866 "rougeL": {867 "mean": 0.7365222510480376,868 "ci_low": 0.7024204302759973,869 "ci_high": 0.7680466502186286,870 "n_items": 69,871 "n_groups": 14872 },873 "exact_match": {874 "mean": 0.0,875 "ci_low": 0.0,876 "ci_high": 0.0,877 "n_items": 69,878 "n_groups": 14879 },880 "number_recall": {881 "mean": 1.0,882 "ci_low": 1.0,883 "ci_high": 1.0,884 "n_items": 69,885 "n_groups": 14886 },887 "placeholders_exact": {888 "mean": 1.0,889 "ci_low": 1.0,890 "ci_high": 1.0,891 "n_items": 69,892 "n_groups": 14893 }894 },895 "introduction": {896 "n": 63,897 "chrf": {898 "mean": 72.50054347438893,899 "ci_low": 70.08852974908537,900 "ci_high": 74.99379885767881,901 "n_items": 63,902 "n_groups": 14903 },904 "edit_sim": {905 "mean": 0.7051984684703257,906 "ci_low": 0.6811571542982995,907 "ci_high": 0.7276344491261721,908 "n_items": 63,909 "n_groups": 14910 },911 "rougeL": {912 "mean": 0.7121813870806701,913 "ci_low": 0.6892522663003757,914 "ci_high": 0.735466030884993,915 "n_items": 63,916 "n_groups": 14917 },918 "exact_match": {919 "mean": 0.0,920 "ci_low": 0.0,921 "ci_high": 0.0,922 "n_items": 63,923 "n_groups": 14924 },925 "number_recall": {926 "mean": 1.0,927 "ci_low": 1.0,928 "ci_high": 1.0,929 "n_items": 63,930 "n_groups": 14931 },932 "placeholders_exact": {933 "mean": 1.0,934 "ci_low": 1.0,935 "ci_high": 1.0,936 "n_items": 63,937 "n_groups": 14938 }939 },940 "limitations": {941 "n": 28,942 "chrf": {943 "mean": 73.74971555554949,944 "ci_low": 69.04320542399651,945 "ci_high": 77.15673435613681,946 "n_items": 28,947 "n_groups": 4948 },949 "edit_sim": {950 "mean": 0.7261072571058759,951 "ci_low": 0.6876924714172656,952 "ci_high": 0.7634054697538243,953 "n_items": 28,954 "n_groups": 4955 },956 "rougeL": {957 "mean": 0.729077685323354,958 "ci_low": 0.6762828539872487,959 "ci_high": 0.7770354140152016,960 "n_items": 28,961 "n_groups": 4962 },963 "exact_match": {964 "mean": 0.0,965 "ci_low": 0.0,966 "ci_high": 0.0,967 "n_items": 28,968 "n_groups": 4969 },970 "number_recall": {971 "mean": 1.0,972 "ci_low": 1.0,973 "ci_high": 1.0,974 "n_items": 28,975 "n_groups": 4976 },977 "placeholders_exact": {978 "mean": 1.0,979 "ci_low": 1.0,980 "ci_high": 1.0,981 "n_items": 28,982 "n_groups": 4983 }984 },985 "methods": {986 "n": 67,987 "chrf": {988 "mean": 74.04963189475991,989 "ci_low": 70.74630208190763,990 "ci_high": 77.55394066580905,991 "n_items": 67,992 "n_groups": 12993 },994 "edit_sim": {995 "mean": 0.7379112298497554,996 "ci_low": 0.7163395790460739,997 "ci_high": 0.7657120363885886,998 "n_items": 67,999 "n_groups": 121000 },1001 "rougeL": {1002 "mean": 0.7499792648027648,1003 "ci_low": 0.7178141457052944,1004 "ci_high": 0.7868550492075944,1005 "n_items": 67,1006 "n_groups": 121007 },1008 "exact_match": {1009 "mean": 0.0,1010 "ci_low": 0.0,1011 "ci_high": 0.0,1012 "n_items": 67,1013 "n_groups": 121014 },1015 "number_recall": {1016 "mean": 1.0,1017 "ci_low": 1.0,1018 "ci_high": 1.0,1019 "n_items": 67,1020 "n_groups": 121021 },1022 "placeholders_exact": {1023 "mean": 1.0,1024 "ci_low": 1.0,1025 "ci_high": 1.0,1026 "n_items": 67,1027 "n_groups": 121028 }1029 },1030 "other": {1031 "n": 52,1032 "chrf": {1033 "mean": 72.8504747030755,1034 "ci_low": 68.07290800848621,1035 "ci_high": 78.14248986788414,1036 "n_items": 52,1037 "n_groups": 91038 },1039 "edit_sim": {1040 "mean": 0.7188976345517483,1041 "ci_low": 0.6769053313863567,1042 "ci_high": 0.771600615989724,1043 "n_items": 52,1044 "n_groups": 91045 },1046 "rougeL": {1047 "mean": 0.715422090181229,1048 "ci_low": 0.6623978957371353,1049 "ci_high": 0.7771146468208918,1050 "n_items": 52,1051 "n_groups": 91052 },1053 "exact_match": {1054 "mean": 0.0,1055 "ci_low": 0.0,1056 "ci_high": 0.0,1057 "n_items": 52,1058 "n_groups": 91059 },1060 "number_recall": {1061 "mean": 1.0,1062 "ci_low": 1.0,1063 "ci_high": 1.0,1064 "n_items": 52,1065 "n_groups": 91066 },1067 "placeholders_exact": {1068 "mean": 1.0,1069 "ci_low": 1.0,1070 "ci_high": 1.0,1071 "n_items": 52,1072 "n_groups": 91073 }1074 },1075 "related_work": {1076 "n": 4,1077 "chrf": {1078 "mean": 81.14741453036652,1079 "ci_low": 81.14741453036652,1080 "ci_high": 81.14741453036652,1081 "n_items": 4,1082 "n_groups": 11083 },1084 "edit_sim": {1085 "mean": 0.8045860302425867,1086 "ci_low": 0.8045860302425867,1087 "ci_high": 0.8045860302425867,1088 "n_items": 4,1089 "n_groups": 11090 },1091 "rougeL": {1092 "mean": 0.8245763209693642,1093 "ci_low": 0.8245763209693642,1094 "ci_high": 0.8245763209693642,1095 "n_items": 4,1096 "n_groups": 11097 },1098 "exact_match": {1099 "mean": 0.0,1100 "ci_low": 0.0,1101 "ci_high": 0.0,1102 "n_items": 4,1103 "n_groups": 11104 },1105 "number_recall": {1106 "mean": 1.0,1107 "ci_low": 1.0,1108 "ci_high": 1.0,1109 "n_items": 4,1110 "n_groups": 11111 },1112 "placeholders_exact": {1113 "mean": 1.0,1114 "ci_low": 1.0,1115 "ci_high": 1.0,1116 "n_items": 4,1117 "n_groups": 11118 }1119 },1120 "results": {1121 "n": 46,1122 "chrf": {1123 "mean": 72.89815347781007,1124 "ci_low": 69.90571944803317,1125 "ci_high": 76.09142181504036,1126 "n_items": 46,1127 "n_groups": 91128 },1129 "edit_sim": {1130 "mean": 0.7136007122018055,1131 "ci_low": 0.6806672875453843,1132 "ci_high": 0.7494226025369051,1133 "n_items": 46,1134 "n_groups": 91135 },1136 "rougeL": {1137 "mean": 0.733518916057253,1138 "ci_low": 0.7103121388491207,1139 "ci_high": 0.7603562420965052,1140 "n_items": 46,1141 "n_groups": 91142 },1143 "exact_match": {1144 "mean": 0.0,1145 "ci_low": 0.0,1146 "ci_high": 0.0,1147 "n_items": 46,1148 "n_groups": 91149 },1150 "number_recall": {1151 "mean": 1.0,1152 "ci_low": 1.0,1153 "ci_high": 1.0,1154 "n_items": 46,1155 "n_groups": 91156 },1157 "placeholders_exact": {1158 "mean": 1.0,1159 "ci_low": 1.0,1160 "ci_high": 1.0,1161 "n_items": 46,1162 "n_groups": 91163 }1164 },1165 "theory": {1166 "n": 34,1167 "chrf": {1168 "mean": 73.70103897174033,1169 "ci_low": 70.80158329080012,1170 "ci_high": 78.62927236486057,1171 "n_items": 34,1172 "n_groups": 61173 },1174 "edit_sim": {1175 "mean": 0.7275916253231617,1176 "ci_low": 0.7115111176614389,1177 "ci_high": 0.7605303151327707,1178 "n_items": 34,1179 "n_groups": 61180 },1181 "rougeL": {1182 "mean": 0.7291161925820353,1183 "ci_low": 0.7077134461378256,1184 "ci_high": 0.772892414042223,1185 "n_items": 34,1186 "n_groups": 61187 },1188 "exact_match": {1189 "mean": 0.0,1190 "ci_low": 0.0,1191 "ci_high": 0.0,1192 "n_items": 34,1193 "n_groups": 61194 },1195 "number_recall": {1196 "mean": 1.0,1197 "ci_low": 1.0,1198 "ci_high": 1.0,1199 "n_items": 34,1200 "n_groups": 61201 },1202 "placeholders_exact": {1203 "mean": 1.0,1204 "ci_low": 1.0,1205 "ci_high": 1.0,1206 "n_items": 34,1207 "n_groups": 61208 }1209 }1210 }1211 },1212 "B1_generic_paraphrase": {1213 "overall": {1214 "n": 531,1215 "chrf": {1216 "mean": 70.56352530314159,1217 "ci_low": 69.49132760004149,1218 "ci_high": 71.96779897970004,1219 "n_items": 531,1220 "n_groups": 551221 },1222 "edit_sim": {1223 "mean": 0.5973660036504006,1224 "ci_low": 0.5839967303964118,1225 "ci_high": 0.6114389929250237,1226 "n_items": 531,1227 "n_groups": 551228 },1229 "rougeL": {1230 "mean": 0.6395884775059318,1231 "ci_low": 0.6269384130192818,1232 "ci_high": 0.6554666165020044,1233 "n_items": 531,1234 "n_groups": 551235 },1236 "exact_match": {1237 "mean": 0.0,1238 "ci_low": 0.0,1239 "ci_high": 0.0,1240 "n_items": 531,1241 "n_groups": 551242 },1243 "number_recall": {1244 "mean": 0.9995291902071564,1245 "ci_low": 0.9986956521739131,1246 "ci_high": 1.0,1247 "n_items": 531,1248 "n_groups": 551249 },1250 "placeholders_exact": {1251 "mean": 1.0,1252 "ci_low": 1.0,1253 "ci_high": 1.0,1254 "n_items": 531,1255 "n_groups": 551256 }1257 },1258 "by_variant": {1259 "A": {1260 "n": 267,1261 "chrf": {1262 "mean": 66.103123507829,1263 "ci_low": 65.01446699965983,1264 "ci_high": 67.51285301343083,1265 "n_items": 267,1266 "n_groups": 531267 },1268 "edit_sim": {1269 "mean": 0.5450414218001322,1270 "ci_low": 0.5301044589816083,1271 "ci_high": 0.5596595978549702,1272 "n_items": 267,1273 "n_groups": 531274 },1275 "rougeL": {1276 "mean": 0.5808449074462645,1277 "ci_low": 0.5675290999087786,1278 "ci_high": 0.596920765606263,1279 "n_items": 267,1280 "n_groups": 531281 },1282 "exact_match": {1283 "mean": 0.0,1284 "ci_low": 0.0,1285 "ci_high": 0.0,1286 "n_items": 267,1287 "n_groups": 531288 },1289 "number_recall": {1290 "mean": 1.0,1291 "ci_low": 1.0,1292 "ci_high": 1.0,1293 "n_items": 267,1294 "n_groups": 531295 },1296 "placeholders_exact": {1297 "mean": 1.0,1298 "ci_low": 1.0,1299 "ci_high": 1.0,1300 "n_items": 267,1301 "n_groups": 531302 }1303 },1304 "B": {1305 "n": 264,1306 "chrf": {1307 "mean": 75.07461348249184,1308 "ci_low": 73.83125418913355,1309 "ci_high": 76.50356648465998,1310 "n_items": 264,1311 "n_groups": 541312 },1313 "edit_sim": {1314 "mean": 0.6502851830216951,1315 "ci_low": 0.6326680619290322,1316 "ci_high": 0.6678170713227768,1317 "n_items": 264,1318 "n_groups": 541319 },1320 "rougeL": {1321 "mean": 0.6989995881344592,1322 "ci_low": 0.6833457172754557,1323 "ci_high": 0.7170894689364288,1324 "n_items": 264,1325 "n_groups": 541326 },1327 "exact_match": {1328 "mean": 0.0,1329 "ci_low": 0.0,1330 "ci_high": 0.0,1331 "n_items": 264,1332 "n_groups": 541333 },1334 "number_recall": {1335 "mean": 0.9990530303030303,1336 "ci_low": 0.9974135693831285,1337 "ci_high": 1.0,1338 "n_items": 264,1339 "n_groups": 541340 },1341 "placeholders_exact": {1342 "mean": 1.0,1343 "ci_low": 1.0,1344 "ci_high": 1.0,1345 "n_items": 264,1346 "n_groups": 541347 }1348 }1349 },1350 "by_discipline": {1351 "biomedicine": {1352 "n": 118,1353 "chrf": {1354 "mean": 72.22376936599586,1355 "ci_low": 70.11534019500961,1356 "ci_high": 74.32193376120713,1357 "n_items": 118,1358 "n_groups": 261359 },1360 "edit_sim": {1361 "mean": 0.616698800016931,1362 "ci_low": 0.5965933750088976,1363 "ci_high": 0.6400834228341022,1364 "n_items": 118,1365 "n_groups": 261366 },1367 "rougeL": {1368 "mean": 0.6608963449692341,1369 "ci_low": 0.6389132639921383,1370 "ci_high": 0.6841267195527541,1371 "n_items": 118,1372 "n_groups": 261373 },1374 "exact_match": {1375 "mean": 0.0,1376 "ci_low": 0.0,1377 "ci_high": 0.0,1378 "n_items": 118,1379 "n_groups": 261380 },1381 "number_recall": {1382 "mean": 1.0,1383 "ci_low": 1.0,1384 "ci_high": 1.0,1385 "n_items": 118,1386 "n_groups": 261387 },1388 "placeholders_exact": {1389 "mean": 1.0,1390 "ci_low": 1.0,1391 "ci_high": 1.0,1392 "n_items": 118,1393 "n_groups": 261394 }1395 },1396 "computer_science": {1397 "n": 57,1398 "chrf": {1399 "mean": 70.29360823852089,1400 "ci_low": 67.39112743291669,1401 "ci_high": 76.58231665066332,1402 "n_items": 57,1403 "n_groups": 21404 },1405 "edit_sim": {1406 "mean": 0.621344789864901,1407 "ci_low": 0.6107161165081377,1408 "ci_high": 0.6443735821378883,1409 "n_items": 57,1410 "n_groups": 21411 },1412 "rougeL": {1413 "mean": 0.6465340234684777,1414 "ci_low": 0.6195129723141873,1415 "ci_high": 0.7050796343027734,1416 "n_items": 57,1417 "n_groups": 21418 },1419 "exact_match": {1420 "mean": 0.0,1421 "ci_low": 0.0,1422 "ci_high": 0.0,1423 "n_items": 57,1424 "n_groups": 21425 },1426 "number_recall": {1427 "mean": 1.0,1428 "ci_low": 1.0,1429 "ci_high": 1.0,1430 "n_items": 57,1431 "n_groups": 21432 },1433 "placeholders_exact": {1434 "mean": 1.0,1435 "ci_low": 1.0,1436 "ci_high": 1.0,1437 "n_items": 57,1438 "n_groups": 21439 }1440 },1441 "earth_sciences": {1442 "n": 64,1443 "chrf": {1444 "mean": 68.84034258712867,1445 "ci_low": 67.94910592796298,1446 "ci_high": 69.59610258548531,1447 "n_items": 64,1448 "n_groups": 31449 },1450 "edit_sim": {1451 "mean": 0.5643687306524237,1452 "ci_low": 0.5402589675542293,1453 "ci_high": 0.5973503575072625,1454 "n_items": 64,1455 "n_groups": 31456 },1457 "rougeL": {1458 "mean": 0.6094812441330204,1459 "ci_low": 0.5706557424519617,1460 "ci_high": 0.6316648138157247,1461 "n_items": 64,1462 "n_groups": 31463 },1464 "exact_match": {1465 "mean": 0.0,1466 "ci_low": 0.0,1467 "ci_high": 0.0,1468 "n_items": 64,1469 "n_groups": 31470 },1471 "number_recall": {1472 "mean": 1.0,1473 "ci_low": 1.0,1474 "ci_high": 1.0,1475 "n_items": 64,1476 "n_groups": 31477 },1478 "placeholders_exact": {1479 "mean": 1.0,1480 "ci_low": 1.0,1481 "ci_high": 1.0,1482 "n_items": 64,1483 "n_groups": 31484 }1485 },1486 "economics": {1487 "n": 64,1488 "chrf": {1489 "mean": 69.2031345363479,1490 "ci_low": 69.2031345363479,1491 "ci_high": 69.2031345363479,1492 "n_items": 64,1493 "n_groups": 11494 },1495 "edit_sim": {1496 "mean": 0.5919896476262996,1497 "ci_low": 0.5919896476262996,1498 "ci_high": 0.5919896476262996,1499 "n_items": 64,1500 "n_groups": 11501 },1502 "rougeL": {1503 "mean": 0.6183966551392275,1504 "ci_low": 0.6183966551392275,1505 "ci_high": 0.6183966551392275,1506 "n_items": 64,1507 "n_groups": 11508 },1509 "exact_match": {1510 "mean": 0.0,1511 "ci_low": 0.0,1512 "ci_high": 0.0,1513 "n_items": 64,1514 "n_groups": 11515 },1516 "number_recall": {1517 "mean": 0.99609375,1518 "ci_low": 0.99609375,1519 "ci_high": 0.99609375,1520 "n_items": 64,1521 "n_groups": 11522 },1523 "placeholders_exact": {1524 "mean": 1.0,1525 "ci_low": 1.0,1526 "ci_high": 1.0,1527 "n_items": 64,1528 "n_groups": 11529 }1530 },1531 "engineering": {1532 "n": 11,1533 "chrf": {1534 "mean": 70.99164111910089,1535 "ci_low": 70.99164111910089,1536 "ci_high": 70.99164111910089,1537 "n_items": 11,1538 "n_groups": 11539 },1540 "edit_sim": {1541 "mean": 0.5416409042283713,1542 "ci_low": 0.5416409042283713,1543 "ci_high": 0.5416409042283713,1544 "n_items": 11,1545 "n_groups": 11546 },1547 "rougeL": {1548 "mean": 0.5786421516052488,1549 "ci_low": 0.5786421516052488,1550 "ci_high": 0.5786421516052488,1551 "n_items": 11,1552 "n_groups": 11553 },1554 "exact_match": {1555 "mean": 0.0,1556 "ci_low": 0.0,1557 "ci_high": 0.0,1558 "n_items": 11,1559 "n_groups": 11560 },1561 "number_recall": {1562 "mean": 1.0,1563 "ci_low": 1.0,1564 "ci_high": 1.0,1565 "n_items": 11,1566 "n_groups": 11567 },1568 "placeholders_exact": {1569 "mean": 1.0,1570 "ci_low": 1.0,1571 "ci_high": 1.0,1572 "n_items": 11,1573 "n_groups": 11574 }1575 },1576 "life_sciences": {1577 "n": 95,1578 "chrf": {1579 "mean": 72.38505552969525,1580 "ci_low": 69.91380863958891,1581 "ci_high": 75.13721813033476,1582 "n_items": 95,1583 "n_groups": 161584 },1585 "edit_sim": {1586 "mean": 0.59382633713605,1587 "ci_low": 0.5698357314537508,1588 "ci_high": 0.6191411694557489,1589 "n_items": 95,1590 "n_groups": 161591 },1592 "rougeL": {1593 "mean": 0.6521849300265039,1594 "ci_low": 0.62307533889578,1595 "ci_high": 0.6834214055105949,1596 "n_items": 95,1597 "n_groups": 161598 },1599 "exact_match": {1600 "mean": 0.0,1601 "ci_low": 0.0,1602 "ci_high": 0.0,1603 "n_items": 95,1604 "n_groups": 161605 },1606 "number_recall": {1607 "mean": 1.0,1608 "ci_low": 1.0,1609 "ci_high": 1.0,1610 "n_items": 95,1611 "n_groups": 161612 },1613 "placeholders_exact": {1614 "mean": 1.0,1615 "ci_low": 1.0,1616 "ci_high": 1.0,1617 "n_items": 95,1618 "n_groups": 161619 }1620 },1621 "social_sciences": {1622 "n": 75,1623 "chrf": {1624 "mean": 70.04828098053572,1625 "ci_low": 64.04084764161995,1626 "ci_high": 73.18662378387992,1627 "n_items": 75,1628 "n_groups": 41629 },1630 "edit_sim": {1631 "mean": 0.6200728915971074,1632 "ci_low": 0.5993588260421793,1633 "ci_high": 0.6402418501637478,1634 "n_items": 75,1635 "n_groups": 41636 },1637 "rougeL": {1638 "mean": 0.649954866280109,1639 "ci_low": 0.6100027930193745,1640 "ci_high": 0.6659482390835306,1641 "n_items": 75,1642 "n_groups": 41643 },1644 "exact_match": {1645 "mean": 0.0,1646 "ci_low": 0.0,1647 "ci_high": 0.0,1648 "n_items": 75,1649 "n_groups": 41650 },1651 "number_recall": {1652 "mean": 1.0,1653 "ci_low": 1.0,1654 "ci_high": 1.0,1655 "n_items": 75,1656 "n_groups": 41657 },1658 "placeholders_exact": {1659 "mean": 1.0,1660 "ci_low": 1.0,1661 "ci_high": 1.0,1662 "n_items": 75,1663 "n_groups": 41664 }1665 },1666 "statistics": {1667 "n": 47,1668 "chrf": {1669 "mean": 67.96169242789664,1670 "ci_low": 67.2599829554614,1671 "ci_high": 69.32125453073995,1672 "n_items": 47,1673 "n_groups": 21674 },1675 "edit_sim": {1676 "mean": 0.5559634353193065,1677 "ci_low": 0.5257383377481802,1678 "ci_high": 0.6145245618633639,1679 "n_items": 47,1680 "n_groups": 21681 },1682 "rougeL": {1683 "mean": 0.6197838503610489,1684 "ci_low": 0.5887175265796291,1685 "ci_high": 0.67997485268755,1686 "n_items": 47,1687 "n_groups": 21688 },1689 "exact_match": {1690 "mean": 0.0,1691 "ci_low": 0.0,1692 "ci_high": 0.0,1693 "n_items": 47,1694 "n_groups": 21695 },1696 "number_recall": {1697 "mean": 1.0,1698 "ci_low": 1.0,1699 "ci_high": 1.0,1700 "n_items": 47,1701 "n_groups": 21702 },1703 "placeholders_exact": {1704 "mean": 1.0,1705 "ci_low": 1.0,1706 "ci_high": 1.0,1707 "n_items": 47,1708 "n_groups": 21709 }1710 }1711 },1712 "by_era": {1713 "1980-1999": {1714 "n": 5,1715 "chrf": {1716 "mean": 76.65052077019476,1717 "ci_low": 72.10148433684537,1718 "ci_high": 83.47407542021884,1719 "n_items": 5,1720 "n_groups": 21721 },1722 "edit_sim": {1723 "mean": 0.7268166709980768,1724 "ci_low": 0.7096466768338283,1725 "ci_high": 0.7525716622444496,1726 "n_items": 5,1727 "n_groups": 21728 },1729 "rougeL": {1730 "mean": 0.7404430536063628,1731 "ci_low": 0.7021522657087037,1732 "ci_high": 0.7978792354528514,1733 "n_items": 5,1734 "n_groups": 21735 },1736 "exact_match": {1737 "mean": 0.0,1738 "ci_low": 0.0,1739 "ci_high": 0.0,1740 "n_items": 5,1741 "n_groups": 21742 },1743 "number_recall": {1744 "mean": 1.0,1745 "ci_low": 1.0,1746 "ci_high": 1.0,1747 "n_items": 5,1748 "n_groups": 21749 },1750 "placeholders_exact": {1751 "mean": 1.0,1752 "ci_low": 1.0,1753 "ci_high": 1.0,1754 "n_items": 5,1755 "n_groups": 21756 }1757 },1758 "2000-2009": {1759 "n": 58,1760 "chrf": {1761 "mean": 71.13026663907445,1762 "ci_low": 68.93919842561324,1763 "ci_high": 73.8161105094014,1764 "n_items": 58,1765 "n_groups": 71766 },1767 "edit_sim": {1768 "mean": 0.5756116983849198,1769 "ci_low": 0.5463866125785484,1770 "ci_high": 0.6002391722766497,1771 "n_items": 58,1772 "n_groups": 71773 },1774 "rougeL": {1775 "mean": 0.641702397212755,1776 "ci_low": 0.6000071143754985,1777 "ci_high": 0.6769071322367302,1778 "n_items": 58,1779 "n_groups": 71780 },1781 "exact_match": {1782 "mean": 0.0,1783 "ci_low": 0.0,1784 "ci_high": 0.0,1785 "n_items": 58,1786 "n_groups": 71787 },1788 "number_recall": {1789 "mean": 1.0,1790 "ci_low": 1.0,1791 "ci_high": 1.0,1792 "n_items": 58,1793 "n_groups": 71794 },1795 "placeholders_exact": {1796 "mean": 1.0,1797 "ci_low": 1.0,1798 "ci_high": 1.0,1799 "n_items": 58,1800 "n_groups": 71801 }1802 },1803 "2010-2017": {1804 "n": 468,1805 "chrf": {1806 "mean": 70.42825612617712,1807 "ci_low": 69.21570870034282,1808 "ci_high": 71.9081359490569,1809 "n_items": 468,1810 "n_groups": 461811 },1812 "edit_sim": {1813 "mean": 0.5986790300791605,1814 "ci_low": 0.584275429605747,1815 "ci_high": 0.6149499296719314,1816 "n_items": 468,1817 "n_groups": 461818 },1819 "rougeL": {1820 "mean": 0.6382489898488851,1821 "ci_low": 0.624699214754989,1822 "ci_high": 0.655941405912873,1823 "n_items": 468,1824 "n_groups": 461825 },1826 "exact_match": {1827 "mean": 0.0,1828 "ci_low": 0.0,1829 "ci_high": 0.0,1830 "n_items": 468,1831 "n_groups": 461832 },1833 "number_recall": {1834 "mean": 0.999465811965812,1835 "ci_low": 0.9985740084317766,1836 "ci_high": 1.0,1837 "n_items": 468,1838 "n_groups": 461839 },1840 "placeholders_exact": {1841 "mean": 1.0,1842 "ci_low": 1.0,1843 "ci_high": 1.0,1844 "n_items": 468,1845 "n_groups": 461846 }1847 }1848 },1849 "by_role": {1850 "abstract": {1851 "n": 55,1852 "chrf": {1853 "mean": 74.48646775774434,1854 "ci_low": 72.34059915210216,1855 "ci_high": 76.52950300340113,1856 "n_items": 55,1857 "n_groups": 151858 },1859 "edit_sim": {1860 "mean": 0.6518433630877178,1861 "ci_low": 0.6256946986938194,1862 "ci_high": 0.6815688834229802,1863 "n_items": 55,1864 "n_groups": 151865 },1866 "rougeL": {1867 "mean": 0.6849556318189165,1868 "ci_low": 0.6596996498658187,1869 "ci_high": 0.7104852065523277,1870 "n_items": 55,1871 "n_groups": 151872 },1873 "exact_match": {1874 "mean": 0.0,1875 "ci_low": 0.0,1876 "ci_high": 0.0,1877 "n_items": 55,1878 "n_groups": 151879 },1880 "number_recall": {1881 "mean": 1.0,1882 "ci_low": 1.0,1883 "ci_high": 1.0,1884 "n_items": 55,1885 "n_groups": 151886 },1887 "placeholders_exact": {1888 "mean": 1.0,1889 "ci_low": 1.0,1890 "ci_high": 1.0,1891 "n_items": 55,1892 "n_groups": 151893 }1894 },1895 "background": {1896 "n": 36,1897 "chrf": {1898 "mean": 70.988369992241,1899 "ci_low": 68.0560221855624,1900 "ci_high": 73.20313981541214,1901 "n_items": 36,1902 "n_groups": 71903 },1904 "edit_sim": {1905 "mean": 0.5767428956869465,1906 "ci_low": 0.5488580317419783,1907 "ci_high": 0.6116095827645303,1908 "n_items": 36,1909 "n_groups": 71910 },1911 "rougeL": {1912 "mean": 0.6296143800150641,1913 "ci_low": 0.611758964026275,1914 "ci_high": 0.6499085575156719,1915 "n_items": 36,1916 "n_groups": 71917 },1918 "exact_match": {1919 "mean": 0.0,1920 "ci_low": 0.0,1921 "ci_high": 0.0,1922 "n_items": 36,1923 "n_groups": 71924 },1925 "number_recall": {1926 "mean": 1.0,1927 "ci_low": 1.0,1928 "ci_high": 1.0,1929 "n_items": 36,1930 "n_groups": 71931 },1932 "placeholders_exact": {1933 "mean": 1.0,1934 "ci_low": 1.0,1935 "ci_high": 1.0,1936 "n_items": 36,1937 "n_groups": 71938 }1939 },1940 "conclusion": {1941 "n": 36,1942 "chrf": {1943 "mean": 66.60351410634263,1944 "ci_low": 64.22972730521036,1945 "ci_high": 69.07011756261191,1946 "n_items": 36,1947 "n_groups": 91948 },1949 "edit_sim": {1950 "mean": 0.5511150033851441,1951 "ci_low": 0.5264156652986279,1952 "ci_high": 0.5743076971226369,1953 "n_items": 36,1954 "n_groups": 91955 },1956 "rougeL": {1957 "mean": 0.5819088165813334,1958 "ci_low": 0.5496224920083176,1959 "ci_high": 0.6135800800777379,1960 "n_items": 36,1961 "n_groups": 91962 },1963 "exact_match": {1964 "mean": 0.0,1965 "ci_low": 0.0,1966 "ci_high": 0.0,1967 "n_items": 36,1968 "n_groups": 91969 },1970 "number_recall": {1971 "mean": 1.0,1972 "ci_low": 1.0,1973 "ci_high": 1.0,1974 "n_items": 36,1975 "n_groups": 91976 },1977 "placeholders_exact": {1978 "mean": 1.0,1979 "ci_low": 1.0,1980 "ci_high": 1.0,1981 "n_items": 36,1982 "n_groups": 91983 }1984 },1985 "data": {1986 "n": 41,1987 "chrf": {1988 "mean": 73.84030667933911,1989 "ci_low": 70.24777383695815,1990 "ci_high": 77.76644181145235,1991 "n_items": 41,1992 "n_groups": 101993 },1994 "edit_sim": {1995 "mean": 0.6178267530286464,1996 "ci_low": 0.5801456440461101,1997 "ci_high": 0.6656354751518797,1998 "n_items": 41,1999 "n_groups": 102000 },2001 "rougeL": {2002 "mean": 0.6674457337645245,2003 "ci_low": 0.6239163435129093,2004 "ci_high": 0.7200438099811374,2005 "n_items": 41,2006 "n_groups": 102007 },2008 "exact_match": {2009 "mean": 0.0,2010 "ci_low": 0.0,2011 "ci_high": 0.0,2012 "n_items": 41,2013 "n_groups": 102014 },2015 "number_recall": {2016 "mean": 0.9939024390243902,2017 "ci_low": 0.9840425531914894,2018 "ci_high": 1.0,2019 "n_items": 41,2020 "n_groups": 102021 },2022 "placeholders_exact": {2023 "mean": 1.0,2024 "ci_low": 1.0,2025 "ci_high": 1.0,2026 "n_items": 41,2027 "n_groups": 102028 }2029 },2030 "discussion": {2031 "n": 69,2032 "chrf": {2033 "mean": 70.0583408464894,2034 "ci_low": 67.5716732890305,2035 "ci_high": 72.64674375658424,2036 "n_items": 69,2037 "n_groups": 142038 },2039 "edit_sim": {2040 "mean": 0.5743456838338393,2041 "ci_low": 0.5439435823308689,2042 "ci_high": 0.6068497424089183,2043 "n_items": 69,2044 "n_groups": 142045 },2046 "rougeL": {2047 "mean": 0.6191544748841882,2048 "ci_low": 0.5804216651123117,2049 "ci_high": 0.6591707557019366,2050 "n_items": 69,2051 "n_groups": 142052 },2053 "exact_match": {2054 "mean": 0.0,2055 "ci_low": 0.0,2056 "ci_high": 0.0,2057 "n_items": 69,2058 "n_groups": 142059 },2060 "number_recall": {2061 "mean": 1.0,2062 "ci_low": 1.0,2063 "ci_high": 1.0,2064 "n_items": 69,2065 "n_groups": 142066 },2067 "placeholders_exact": {2068 "mean": 1.0,2069 "ci_low": 1.0,2070 "ci_high": 1.0,2071 "n_items": 69,2072 "n_groups": 142073 }2074 },2075 "introduction": {2076 "n": 63,2077 "chrf": {2078 "mean": 69.3099798691024,2079 "ci_low": 66.98136833914869,2080 "ci_high": 71.84647461756119,2081 "n_items": 63,2082 "n_groups": 142083 },2084 "edit_sim": {2085 "mean": 0.6001218746756973,2086 "ci_low": 0.5699672674341876,2087 "ci_high": 0.6289396524573378,2088 "n_items": 63,2089 "n_groups": 142090 },2091 "rougeL": {2092 "mean": 0.6345320185540141,2093 "ci_low": 0.6115831025577608,2094 "ci_high": 0.656406675961606,2095 "n_items": 63,2096 "n_groups": 142097 },2098 "exact_match": {2099 "mean": 0.0,2100 "ci_low": 0.0,2101 "ci_high": 0.0,2102 "n_items": 63,2103 "n_groups": 142104 },2105 "number_recall": {2106 "mean": 1.0,2107 "ci_low": 1.0,2108 "ci_high": 1.0,2109 "n_items": 63,2110 "n_groups": 142111 },2112 "placeholders_exact": {2113 "mean": 1.0,2114 "ci_low": 1.0,2115 "ci_high": 1.0,2116 "n_items": 63,2117 "n_groups": 142118 }2119 },2120 "limitations": {2121 "n": 28,2122 "chrf": {2123 "mean": 68.59784102209817,2124 "ci_low": 63.77567961268359,2125 "ci_high": 71.97002967995091,2126 "n_items": 28,2127 "n_groups": 42128 },2129 "edit_sim": {2130 "mean": 0.597707085580561,2131 "ci_low": 0.5265604738044514,2132 "ci_high": 0.6678801966367572,2133 "n_items": 28,2134 "n_groups": 42135 },2136 "rougeL": {2137 "mean": 0.6302550485592207,2138 "ci_low": 0.5660781845535234,2139 "ci_high": 0.6953845033268692,2140 "n_items": 28,2141 "n_groups": 42142 },2143 "exact_match": {2144 "mean": 0.0,2145 "ci_low": 0.0,2146 "ci_high": 0.0,2147 "n_items": 28,2148 "n_groups": 42149 },2150 "number_recall": {2151 "mean": 1.0,2152 "ci_low": 1.0,2153 "ci_high": 1.0,2154 "n_items": 28,2155 "n_groups": 42156 },2157 "placeholders_exact": {2158 "mean": 1.0,2159 "ci_low": 1.0,2160 "ci_high": 1.0,2161 "n_items": 28,2162 "n_groups": 42163 }2164 },2165 "methods": {2166 "n": 67,2167 "chrf": {2168 "mean": 71.13527898247175,2169 "ci_low": 67.47759367867012,2170 "ci_high": 74.95327961076526,2171 "n_items": 67,2172 "n_groups": 122173 },2174 "edit_sim": {2175 "mean": 0.5989942129723581,2176 "ci_low": 0.5619371227792744,2177 "ci_high": 0.6423117760300493,2178 "n_items": 67,2179 "n_groups": 122180 },2181 "rougeL": {2182 "mean": 0.656826700372381,2183 "ci_low": 0.6203355971553356,2184 "ci_high": 0.6983938926836459,2185 "n_items": 67,2186 "n_groups": 122187 },2188 "exact_match": {2189 "mean": 0.0,2190 "ci_low": 0.0,2191 "ci_high": 0.0,2192 "n_items": 67,2193 "n_groups": 122194 },2195 "number_recall": {2196 "mean": 1.0,2197 "ci_low": 1.0,2198 "ci_high": 1.0,2199 "n_items": 67,2200 "n_groups": 122201 },2202 "placeholders_exact": {2203 "mean": 1.0,2204 "ci_low": 1.0,2205 "ci_high": 1.0,2206 "n_items": 67,2207 "n_groups": 122208 }2209 },2210 "other": {2211 "n": 52,2212 "chrf": {2213 "mean": 70.00068661850354,2214 "ci_low": 65.523176283178,2215 "ci_high": 74.27270398513089,2216 "n_items": 52,2217 "n_groups": 92218 },2219 "edit_sim": {2220 "mean": 0.5967798833682061,2221 "ci_low": 0.5556570370665155,2222 "ci_high": 0.636878822092237,2223 "n_items": 52,2224 "n_groups": 92225 },2226 "rougeL": {2227 "mean": 0.622695843532042,2228 "ci_low": 0.5773160777742155,2229 "ci_high": 0.6746270637326764,2230 "n_items": 52,2231 "n_groups": 92232 },2233 "exact_match": {2234 "mean": 0.0,2235 "ci_low": 0.0,2236 "ci_high": 0.0,2237 "n_items": 52,2238 "n_groups": 92239 },2240 "number_recall": {2241 "mean": 1.0,2242 "ci_low": 1.0,2243 "ci_high": 1.0,2244 "n_items": 52,2245 "n_groups": 92246 },2247 "placeholders_exact": {2248 "mean": 1.0,2249 "ci_low": 1.0,2250 "ci_high": 1.0,2251 "n_items": 52,2252 "n_groups": 92253 }2254 },2255 "related_work": {2256 "n": 4,2257 "chrf": {2258 "mean": 76.00976818666527,2259 "ci_low": 76.00976818666527,2260 "ci_high": 76.00976818666527,2261 "n_items": 4,2262 "n_groups": 12263 },2264 "edit_sim": {2265 "mean": 0.6385318409871222,2266 "ci_low": 0.6385318409871222,2267 "ci_high": 0.6385318409871222,2268 "n_items": 4,2269 "n_groups": 12270 },2271 "rougeL": {2272 "mean": 0.6953422414038766,2273 "ci_low": 0.6953422414038766,2274 "ci_high": 0.6953422414038766,2275 "n_items": 4,2276 "n_groups": 12277 },2278 "exact_match": {2279 "mean": 0.0,2280 "ci_low": 0.0,2281 "ci_high": 0.0,2282 "n_items": 4,2283 "n_groups": 12284 },2285 "number_recall": {2286 "mean": 1.0,2287 "ci_low": 1.0,2288 "ci_high": 1.0,2289 "n_items": 4,2290 "n_groups": 12291 },2292 "placeholders_exact": {2293 "mean": 1.0,2294 "ci_low": 1.0,2295 "ci_high": 1.0,2296 "n_items": 4,2297 "n_groups": 12298 }2299 },2300 "results": {2301 "n": 46,2302 "chrf": {2303 "mean": 69.01127854774657,2304 "ci_low": 66.3376956649435,2305 "ci_high": 72.13055628698571,2306 "n_items": 46,2307 "n_groups": 92308 },2309 "edit_sim": {2310 "mean": 0.574879016995649,2311 "ci_low": 0.5119354989512994,2312 "ci_high": 0.6328563054087043,2313 "n_items": 46,2314 "n_groups": 92315 },2316 "rougeL": {2317 "mean": 0.6381228492669682,2318 "ci_low": 0.6065481520650006,2319 "ci_high": 0.6791091069760095,2320 "n_items": 46,2321 "n_groups": 92322 },2323 "exact_match": {2324 "mean": 0.0,2325 "ci_low": 0.0,2326 "ci_high": 0.0,2327 "n_items": 46,2328 "n_groups": 92329 },2330 "number_recall": {2331 "mean": 1.0,2332 "ci_low": 1.0,2333 "ci_high": 1.0,2334 "n_items": 46,2335 "n_groups": 92336 },2337 "placeholders_exact": {2338 "mean": 1.0,2339 "ci_low": 1.0,2340 "ci_high": 1.0,2341 "n_items": 46,2342 "n_groups": 92343 }2344 },2345 "theory": {2346 "n": 34,2347 "chrf": {2348 "mean": 70.16955079939912,2349 "ci_low": 66.9845935573836,2350 "ci_high": 74.78348991755236,2351 "n_items": 34,2352 "n_groups": 62353 },2354 "edit_sim": {2355 "mean": 0.6199742556578218,2356 "ci_low": 0.5744623693864036,2357 "ci_high": 0.6514221309256256,2358 "n_items": 34,2359 "n_groups": 62360 },2361 "rougeL": {2362 "mean": 0.6500559272856405,2363 "ci_low": 0.6143415836255652,2364 "ci_high": 0.6873155286857103,2365 "n_items": 34,2366 "n_groups": 62367 },2368 "exact_match": {2369 "mean": 0.0,2370 "ci_low": 0.0,2371 "ci_high": 0.0,2372 "n_items": 34,2373 "n_groups": 62374 },2375 "number_recall": {2376 "mean": 1.0,2377 "ci_low": 1.0,2378 "ci_high": 1.0,2379 "n_items": 34,2380 "n_groups": 62381 },2382 "placeholders_exact": {2383 "mean": 1.0,2384 "ci_low": 1.0,2385 "ci_high": 1.0,2386 "n_items": 34,2387 "n_groups": 62388 }2389 }2390 }2391 },2392 "htr-m1-small": {2393 "overall": {2394 "n": 531,2395 "chrf": {2396 "mean": 73.01451358592071,2397 "ci_low": 71.9888260628548,2398 "ci_high": 74.32835553383504,2399 "n_items": 531,2400 "n_groups": 552401 },2402 "edit_sim": {2403 "mean": 0.7170415494121176,2404 "ci_low": 0.7070255838255219,2405 "ci_high": 0.7296068836110591,2406 "n_items": 531,2407 "n_groups": 552408 },2409 "rougeL": {2410 "mean": 0.7225283118216634,2411 "ci_low": 0.7111293593686384,2412 "ci_high": 0.736958873281438,2413 "n_items": 531,2414 "n_groups": 552415 },2416 "exact_match": {2417 "mean": 0.0,2418 "ci_low": 0.0,2419 "ci_high": 0.0,2420 "n_items": 531,2421 "n_groups": 552422 },2423 "number_recall": {2424 "mean": 0.9928487655888787,2425 "ci_low": 0.9873952430044546,2426 "ci_high": 0.9965057313597073,2427 "n_items": 531,2428 "n_groups": 552429 },2430 "placeholders_exact": {2431 "mean": 0.9943502824858758,2432 "ci_low": 0.9842929365658977,2433 "ci_high": 1.0,2434 "n_items": 531,2435 "n_groups": 552436 }2437 },2438 "by_variant": {2439 "A": {2440 "n": 267,2441 "chrf": {2442 "mean": 69.27262418075142,2443 "ci_low": 68.21503209377708,2444 "ci_high": 70.5799205593968,2445 "n_items": 267,2446 "n_groups": 532447 },2448 "edit_sim": {2449 "mean": 0.6657242639650883,2450 "ci_low": 0.6527078469645096,2451 "ci_high": 0.6810471191381934,2452 "n_items": 267,2453 "n_groups": 532454 },2455 "rougeL": {2456 "mean": 0.6723031339677936,2457 "ci_low": 0.6599920315360627,2458 "ci_high": 0.6871086478063315,2459 "n_items": 267,2460 "n_groups": 532461 },2462 "exact_match": {2463 "mean": 0.0,2464 "ci_low": 0.0,2465 "ci_high": 0.0,2466 "n_items": 267,2467 "n_groups": 532468 },2469 "number_recall": {2470 "mean": 0.9930084272780904,2471 "ci_low": 0.9863833505661382,2472 "ci_high": 0.9975689711612041,2473 "n_items": 267,2474 "n_groups": 532475 },2476 "placeholders_exact": {2477 "mean": 0.9925093632958801,2478 "ci_low": 0.9801572494669509,2479 "ci_high": 1.0,2480 "n_items": 267,2481 "n_groups": 532482 }2483 },2484 "B": {2485 "n": 264,2486 "chrf": {2487 "mean": 76.79892446160325,2488 "ci_low": 75.61070609616903,2489 "ci_high": 78.23024972194064,2490 "n_items": 264,2491 "n_groups": 542492 },2493 "edit_sim": {2494 "mean": 0.768941985830136,2495 "ci_low": 0.7573786918235814,2496 "ci_high": 0.78248152536988,2497 "n_items": 264,2498 "n_groups": 542499 },2500 "rougeL": {2501 "mean": 0.7733242303329634,2502 "ci_low": 0.759849232559269,2503 "ci_high": 0.7896326377447593,2504 "n_items": 264,2505 "n_groups": 542506 },2507 "exact_match": {2508 "mean": 0.0,2509 "ci_low": 0.0,2510 "ci_high": 0.0,2511 "n_items": 264,2512 "n_groups": 542513 },2514 "number_recall": {2515 "mean": 0.9926872895622896,2516 "ci_low": 0.9852696887541201,2517 "ci_high": 0.9974551841948901,2518 "n_items": 264,2519 "n_groups": 542520 },2521 "placeholders_exact": {2522 "mean": 0.9962121212121212,2523 "ci_low": 0.9867826790378543,2524 "ci_high": 1.0,2525 "n_items": 264,2526 "n_groups": 542527 }2528 }2529 },2530 "by_discipline": {2531 "biomedicine": {2532 "n": 118,2533 "chrf": {2534 "mean": 74.58501615059448,2535 "ci_low": 72.9519551720419,2536 "ci_high": 76.08186471971365,2537 "n_items": 118,2538 "n_groups": 262539 },2540 "edit_sim": {2541 "mean": 0.722459281983819,2542 "ci_low": 0.703993633679205,2543 "ci_high": 0.7385504431457502,2544 "n_items": 118,2545 "n_groups": 262546 },2547 "rougeL": {2548 "mean": 0.7307908515206099,2549 "ci_low": 0.7127512362140623,2550 "ci_high": 0.7461082645427688,2551 "n_items": 118,2552 "n_groups": 262553 },2554 "exact_match": {2555 "mean": 0.0,2556 "ci_low": 0.0,2557 "ci_high": 0.0,2558 "n_items": 118,2559 "n_groups": 262560 },2561 "number_recall": {2562 "mean": 0.9884715802088683,2563 "ci_low": 0.9752896893462932,2564 "ci_high": 0.9976754148629148,2565 "n_items": 118,2566 "n_groups": 262567 },2568 "placeholders_exact": {2569 "mean": 0.9830508474576272,2570 "ci_low": 0.9495691496937758,2571 "ci_high": 1.0,2572 "n_items": 118,2573 "n_groups": 262574 }2575 },2576 "computer_science": {2577 "n": 57,2578 "chrf": {2579 "mean": 72.61515930662854,2580 "ci_low": 71.10075110565663,2581 "ci_high": 75.896377075401,2582 "n_items": 57,2583 "n_groups": 22584 },2585 "edit_sim": {2586 "mean": 0.7274789136608865,2587 "ci_low": 0.7194660837863791,2588 "ci_high": 0.744840045055652,2589 "n_items": 57,2590 "n_groups": 22591 },2592 "rougeL": {2593 "mean": 0.7204271616201201,2594 "ci_low": 0.7046525247953968,2595 "ci_high": 0.7546055414070204,2596 "n_items": 57,2597 "n_groups": 22598 },2599 "exact_match": {2600 "mean": 0.0,2601 "ci_low": 0.0,2602 "ci_high": 0.0,2603 "n_items": 57,2604 "n_groups": 22605 },2606 "number_recall": {2607 "mean": 0.9986504723346828,2608 "ci_low": 0.9957264957264957,2609 "ci_high": 1.0,2610 "n_items": 57,2611 "n_groups": 22612 },2613 "placeholders_exact": {2614 "mean": 1.0,2615 "ci_low": 1.0,2616 "ci_high": 1.0,2617 "n_items": 57,2618 "n_groups": 22619 }2620 },2621 "earth_sciences": {2622 "n": 64,2623 "chrf": {2624 "mean": 70.6370129541664,2625 "ci_low": 68.63814880073264,2626 "ci_high": 72.43472042088335,2627 "n_items": 64,2628 "n_groups": 32629 },2630 "edit_sim": {2631 "mean": 0.693403604182923,2632 "ci_low": 0.6719449405937304,2633 "ci_high": 0.7094603323446155,2634 "n_items": 64,2635 "n_groups": 32636 },2637 "rougeL": {2638 "mean": 0.7008411183420007,2639 "ci_low": 0.6655897934826678,2640 "ci_high": 0.7248897181473652,2641 "n_items": 64,2642 "n_groups": 32643 },2644 "exact_match": {2645 "mean": 0.0,2646 "ci_low": 0.0,2647 "ci_high": 0.0,2648 "n_items": 64,2649 "n_groups": 32650 },2651 "number_recall": {2652 "mean": 0.9930555555555556,2653 "ci_low": 0.9791666666666666,2654 "ci_high": 1.0,2655 "n_items": 64,2656 "n_groups": 32657 },2658 "placeholders_exact": {2659 "mean": 1.0,2660 "ci_low": 1.0,2661 "ci_high": 1.0,2662 "n_items": 64,2663 "n_groups": 32664 }2665 },2666 "economics": {2667 "n": 64,2668 "chrf": {2669 "mean": 70.43234343223347,2670 "ci_low": 70.43234343223347,2671 "ci_high": 70.43234343223347,2672 "n_items": 64,2673 "n_groups": 12674 },2675 "edit_sim": {2676 "mean": 0.6876475356307931,2677 "ci_low": 0.6876475356307931,2678 "ci_high": 0.6876475356307931,2679 "n_items": 64,2680 "n_groups": 12681 },2682 "rougeL": {2683 "mean": 0.6905657240653954,2684 "ci_low": 0.6905657240653954,2685 "ci_high": 0.6905657240653954,2686 "n_items": 64,2687 "n_groups": 12688 },2689 "exact_match": {2690 "mean": 0.0,2691 "ci_low": 0.0,2692 "ci_high": 0.0,2693 "n_items": 64,2694 "n_groups": 12695 },2696 "number_recall": {2697 "mean": 0.9973958333333334,2698 "ci_low": 0.9973958333333334,2699 "ci_high": 0.9973958333333334,2700 "n_items": 64,2701 "n_groups": 12702 },2703 "placeholders_exact": {2704 "mean": 1.0,2705 "ci_low": 1.0,2706 "ci_high": 1.0,2707 "n_items": 64,2708 "n_groups": 12709 }2710 },2711 "engineering": {2712 "n": 11,2713 "chrf": {2714 "mean": 72.90372177613371,2715 "ci_low": 72.90372177613371,2716 "ci_high": 72.90372177613371,2717 "n_items": 11,2718 "n_groups": 12719 },2720 "edit_sim": {2721 "mean": 0.7053303503809484,2722 "ci_low": 0.7053303503809484,2723 "ci_high": 0.7053303503809484,2724 "n_items": 11,2725 "n_groups": 12726 },2727 "rougeL": {2728 "mean": 0.6836214744157934,2729 "ci_low": 0.6836214744157934,2730 "ci_high": 0.6836214744157934,2731 "n_items": 11,2732 "n_groups": 12733 },2734 "exact_match": {2735 "mean": 0.0,2736 "ci_low": 0.0,2737 "ci_high": 0.0,2738 "n_items": 11,2739 "n_groups": 12740 },2741 "number_recall": {2742 "mean": 1.0,2743 "ci_low": 1.0,2744 "ci_high": 1.0,2745 "n_items": 11,2746 "n_groups": 12747 },2748 "placeholders_exact": {2749 "mean": 1.0,2750 "ci_low": 1.0,2751 "ci_high": 1.0,2752 "n_items": 11,2753 "n_groups": 12754 }2755 },2756 "life_sciences": {2757 "n": 95,2758 "chrf": {2759 "mean": 75.69363376529883,2760 "ci_low": 73.26252444654585,2761 "ci_high": 78.46557066824828,2762 "n_items": 95,2763 "n_groups": 162764 },2765 "edit_sim": {2766 "mean": 0.7511131217113183,2767 "ci_low": 0.7250276036099382,2768 "ci_high": 0.7818172418182653,2769 "n_items": 95,2770 "n_groups": 162771 },2772 "rougeL": {2773 "mean": 0.7553780090594514,2774 "ci_low": 0.7247227111729351,2775 "ci_high": 0.7900188370771767,2776 "n_items": 95,2777 "n_groups": 162778 },2779 "exact_match": {2780 "mean": 0.0,2781 "ci_low": 0.0,2782 "ci_high": 0.0,2783 "n_items": 95,2784 "n_groups": 162785 },2786 "number_recall": {2787 "mean": 0.9815903394850762,2788 "ci_low": 0.9653657106782106,2789 "ci_high": 0.9952390791027156,2790 "n_items": 95,2791 "n_groups": 162792 },2793 "placeholders_exact": {2794 "mean": 0.9894736842105263,2795 "ci_low": 0.9680851063829787,2796 "ci_high": 1.0,2797 "n_items": 95,2798 "n_groups": 162799 }2800 },2801 "social_sciences": {2802 "n": 75,2803 "chrf": {2804 "mean": 72.51792011351895,2805 "ci_low": 67.22499359184549,2806 "ci_high": 75.37509353834932,2807 "n_items": 75,2808 "n_groups": 42809 },2810 "edit_sim": {2811 "mean": 0.7126913750003041,2812 "ci_low": 0.6867322335959193,2813 "ci_high": 0.7321732000808222,2814 "n_items": 75,2815 "n_groups": 42816 },2817 "rougeL": {2818 "mean": 0.7236386847971922,2819 "ci_low": 0.673242451874913,2820 "ci_high": 0.7473012177293179,2821 "n_items": 75,2822 "n_groups": 42823 },2824 "exact_match": {2825 "mean": 0.0,2826 "ci_low": 0.0,2827 "ci_high": 0.0,2828 "n_items": 75,2829 "n_groups": 42830 },2831 "number_recall": {2832 "mean": 1.0,2833 "ci_low": 1.0,2834 "ci_high": 1.0,2835 "n_items": 75,2836 "n_groups": 42837 },2838 "placeholders_exact": {2839 "mean": 1.0,2840 "ci_low": 1.0,2841 "ci_high": 1.0,2842 "n_items": 75,2843 "n_groups": 42844 }2845 },2846 "statistics": {2847 "n": 47,2848 "chrf": {2849 "mean": 71.71259071045841,2850 "ci_low": 70.03506011117778,2851 "ci_high": 72.57841295524841,2852 "n_items": 47,2853 "n_groups": 22854 },2855 "edit_sim": {2856 "mean": 0.7038098488341913,2857 "ci_low": 0.6921055095970471,2858 "ci_high": 0.7098507981178787,2859 "n_items": 47,2860 "n_groups": 22861 },2862 "rougeL": {2863 "mean": 0.718322947498725,2864 "ci_low": 0.7181896940831521,2865 "ci_high": 0.7185811259913971,2866 "n_items": 47,2867 "n_groups": 22868 },2869 "exact_match": {2870 "mean": 0.0,2871 "ci_low": 0.0,2872 "ci_high": 0.0,2873 "n_items": 47,2874 "n_groups": 22875 },2876 "number_recall": {2877 "mean": 1.0,2878 "ci_low": 1.0,2879 "ci_high": 1.0,2880 "n_items": 47,2881 "n_groups": 22882 },2883 "placeholders_exact": {2884 "mean": 1.0,2885 "ci_low": 1.0,2886 "ci_high": 1.0,2887 "n_items": 47,2888 "n_groups": 22889 }2890 }2891 },2892 "by_era": {2893 "1980-1999": {2894 "n": 5,2895 "chrf": {2896 "mean": 74.31785170904116,2897 "ci_low": 71.97241941947175,2898 "ci_high": 77.83600014339534,2899 "n_items": 5,2900 "n_groups": 22901 },2902 "edit_sim": {2903 "mean": 0.7723019053704588,2904 "ci_low": 0.7640895874988235,2905 "ci_high": 0.7846203821779119,2906 "n_items": 5,2907 "n_groups": 22908 },2909 "rougeL": {2910 "mean": 0.7632981833537615,2911 "ci_low": 0.7488970692773917,2912 "ci_high": 0.7848998544683161,2913 "n_items": 5,2914 "n_groups": 22915 },2916 "exact_match": {2917 "mean": 0.0,2918 "ci_low": 0.0,2919 "ci_high": 0.0,2920 "n_items": 5,2921 "n_groups": 22922 },2923 "number_recall": {2924 "mean": 1.0,2925 "ci_low": 1.0,2926 "ci_high": 1.0,2927 "n_items": 5,2928 "n_groups": 22929 },2930 "placeholders_exact": {2931 "mean": 1.0,2932 "ci_low": 1.0,2933 "ci_high": 1.0,2934 "n_items": 5,2935 "n_groups": 22936 }2937 },2938 "2000-2009": {2939 "n": 58,2940 "chrf": {2941 "mean": 72.42966835532253,2942 "ci_low": 70.28449297457281,2943 "ci_high": 75.57075585507965,2944 "n_items": 58,2945 "n_groups": 72946 },2947 "edit_sim": {2948 "mean": 0.7128282012310688,2949 "ci_low": 0.6922653865083287,2950 "ci_high": 0.742784549650111,2951 "n_items": 58,2952 "n_groups": 72953 },2954 "rougeL": {2955 "mean": 0.717731080307042,2956 "ci_low": 0.6923817444951247,2957 "ci_high": 0.7512119156075319,2958 "n_items": 58,2959 "n_groups": 72960 },2961 "exact_match": {2962 "mean": 0.0,2963 "ci_low": 0.0,2964 "ci_high": 0.0,2965 "n_items": 58,2966 "n_groups": 72967 },2968 "number_recall": {2969 "mean": 0.9942528735632185,2970 "ci_low": 0.9821428571428571,2971 "ci_high": 1.0,2972 "n_items": 58,2973 "n_groups": 72974 },2975 "placeholders_exact": {2976 "mean": 0.9827586206896551,2977 "ci_low": 0.9464285714285714,2978 "ci_high": 1.0,2979 "n_items": 58,2980 "n_groups": 72981 }2982 },2983 "2010-2017": {2984 "n": 468,2985 "chrf": {2986 "mean": 73.07306985249996,2987 "ci_low": 71.92835083003968,2988 "ci_high": 74.53312280576931,2989 "n_items": 468,2990 "n_groups": 462991 },2992 "edit_sim": {2993 "mean": 0.7169733280760261,2994 "ci_low": 0.70573081658125,2995 "ci_high": 0.7306159047217982,2996 "n_items": 468,2997 "n_groups": 462998 },2999 "rougeL": {3000 "mean": 0.7226872649630898,3001 "ci_low": 0.7097238288763907,3002 "ci_high": 0.7382322223619628,3003 "n_items": 468,3004 "n_groups": 463005 },3006 "exact_match": {3007 "mean": 0.0,3008 "ci_low": 0.0,3009 "ci_high": 0.0,3010 "n_items": 468,3011 "n_groups": 463012 },3013 "number_recall": {3014 "mean": 0.9925983501304013,3015 "ci_low": 0.9865113956803685,3016 "ci_high": 0.9965083486154998,3017 "n_items": 468,3018 "n_groups": 463019 },3020 "placeholders_exact": {3021 "mean": 0.9957264957264957,3022 "ci_low": 0.9842929365658977,3023 "ci_high": 1.0,3024 "n_items": 468,3025 "n_groups": 463026 }3027 }3028 },3029 "by_role": {3030 "abstract": {3031 "n": 55,3032 "chrf": {3033 "mean": 75.91632711793007,3034 "ci_low": 73.85147049919057,3035 "ci_high": 77.86514812582686,3036 "n_items": 55,3037 "n_groups": 153038 },3039 "edit_sim": {3040 "mean": 0.7532743187071133,3041 "ci_low": 0.7334032890668607,3042 "ci_high": 0.7720594138166785,3043 "n_items": 55,3044 "n_groups": 153045 },3046 "rougeL": {3047 "mean": 0.7458971721065834,3048 "ci_low": 0.7224081826508878,3049 "ci_high": 0.7707140064717978,3050 "n_items": 55,3051 "n_groups": 153052 },3053 "exact_match": {3054 "mean": 0.0,3055 "ci_low": 0.0,3056 "ci_high": 0.0,3057 "n_items": 55,3058 "n_groups": 153059 },3060 "number_recall": {3061 "mean": 1.0,3062 "ci_low": 1.0,3063 "ci_high": 1.0,3064 "n_items": 55,3065 "n_groups": 153066 },3067 "placeholders_exact": {3068 "mean": 1.0,3069 "ci_low": 1.0,3070 "ci_high": 1.0,3071 "n_items": 55,3072 "n_groups": 153073 }3074 },3075 "background": {3076 "n": 36,3077 "chrf": {3078 "mean": 73.96018888070611,3079 "ci_low": 71.21381498026464,3080 "ci_high": 76.61810248455204,3081 "n_items": 36,3082 "n_groups": 73083 },3084 "edit_sim": {3085 "mean": 0.733616737479577,3086 "ci_low": 0.7023421351101671,3087 "ci_high": 0.7634875480501766,3088 "n_items": 36,3089 "n_groups": 73090 },3091 "rougeL": {3092 "mean": 0.7354494084669532,3093 "ci_low": 0.7126869035205377,3094 "ci_high": 0.7616442149530543,3095 "n_items": 36,3096 "n_groups": 73097 },3098 "exact_match": {3099 "mean": 0.0,3100 "ci_low": 0.0,3101 "ci_high": 0.0,3102 "n_items": 36,3103 "n_groups": 73104 },3105 "number_recall": {3106 "mean": 0.9876543209876544,3107 "ci_low": 0.9705882352941176,3108 "ci_high": 1.0,3109 "n_items": 36,3110 "n_groups": 73111 },3112 "placeholders_exact": {3113 "mean": 0.9722222222222222,3114 "ci_low": 0.9166666666666666,3115 "ci_high": 1.0,3116 "n_items": 36,3117 "n_groups": 73118 }3119 },3120 "conclusion": {3121 "n": 36,3122 "chrf": {3123 "mean": 70.67443296765929,3124 "ci_low": 67.5380710071136,3125 "ci_high": 73.5249636550058,3126 "n_items": 36,3127 "n_groups": 93128 },3129 "edit_sim": {3130 "mean": 0.6986503217913271,3131 "ci_low": 0.6645997797015587,3132 "ci_high": 0.7357618174181111,3133 "n_items": 36,3134 "n_groups": 93135 },3136 "rougeL": {3137 "mean": 0.6961198196246394,3138 "ci_low": 0.6574439989447308,3139 "ci_high": 0.7325869242922736,3140 "n_items": 36,3141 "n_groups": 93142 },3143 "exact_match": {3144 "mean": 0.0,3145 "ci_low": 0.0,3146 "ci_high": 0.0,3147 "n_items": 36,3148 "n_groups": 93149 },3150 "number_recall": {3151 "mean": 0.9861111111111112,3152 "ci_low": 0.9583333333333334,3153 "ci_high": 1.0,3154 "n_items": 36,3155 "n_groups": 93156 },3157 "placeholders_exact": {3158 "mean": 1.0,3159 "ci_low": 1.0,3160 "ci_high": 1.0,3161 "n_items": 36,3162 "n_groups": 93163 }3164 },3165 "data": {3166 "n": 41,3167 "chrf": {3168 "mean": 76.31745606496186,3169 "ci_low": 73.01331395445725,3170 "ci_high": 79.73871992368196,3171 "n_items": 41,3172 "n_groups": 103173 },3174 "edit_sim": {3175 "mean": 0.7292266580762401,3176 "ci_low": 0.6915183784492891,3177 "ci_high": 0.7770559259508043,3178 "n_items": 41,3179 "n_groups": 103180 },3181 "rougeL": {3182 "mean": 0.7496636209294808,3183 "ci_low": 0.7156957842889629,3184 "ci_high": 0.7879852248558342,3185 "n_items": 41,3186 "n_groups": 103187 },3188 "exact_match": {3189 "mean": 0.0,3190 "ci_low": 0.0,3191 "ci_high": 0.0,3192 "n_items": 41,3193 "n_groups": 103194 },3195 "number_recall": {3196 "mean": 0.9859287054409005,3197 "ci_low": 0.9555555555555556,3198 "ci_high": 1.0,3199 "n_items": 41,3200 "n_groups": 103201 },3202 "placeholders_exact": {3203 "mean": 0.9512195121951219,3204 "ci_low": 0.8333333333333334,3205 "ci_high": 1.0,3206 "n_items": 41,3207 "n_groups": 103208 }3209 },3210 "discussion": {3211 "n": 69,3212 "chrf": {3213 "mean": 72.9288538063287,3214 "ci_low": 70.6843986723002,3215 "ci_high": 75.65219980379727,3216 "n_items": 69,3217 "n_groups": 143218 },3219 "edit_sim": {3220 "mean": 0.7207725953602292,3221 "ci_low": 0.6927958957134256,3222 "ci_high": 0.75298844261023,3223 "n_items": 69,3224 "n_groups": 143225 },3226 "rougeL": {3227 "mean": 0.7237442703712798,3228 "ci_low": 0.6924740339287004,3229 "ci_high": 0.7604939779706809,3230 "n_items": 69,3231 "n_groups": 143232 },3233 "exact_match": {3234 "mean": 0.0,3235 "ci_low": 0.0,3236 "ci_high": 0.0,3237 "n_items": 69,3238 "n_groups": 143239 },3240 "number_recall": {3241 "mean": 0.9979296066252589,3242 "ci_low": 0.9927659607073898,3243 "ci_high": 1.0,3244 "n_items": 69,3245 "n_groups": 143246 },3247 "placeholders_exact": {3248 "mean": 1.0,3249 "ci_low": 1.0,3250 "ci_high": 1.0,3251 "n_items": 69,3252 "n_groups": 143253 }3254 },3255 "introduction": {3256 "n": 63,3257 "chrf": {3258 "mean": 72.15826062635298,3259 "ci_low": 69.76768454307995,3260 "ci_high": 74.7147834232155,3261 "n_items": 63,3262 "n_groups": 143263 },3264 "edit_sim": {3265 "mean": 0.700770051246762,3266 "ci_low": 0.677493106157633,3267 "ci_high": 0.7233975302269506,3268 "n_items": 63,3269 "n_groups": 143270 },3271 "rougeL": {3272 "mean": 0.7098144580819752,3273 "ci_low": 0.6896416142189605,3274 "ci_high": 0.7315418226123824,3275 "n_items": 63,3276 "n_groups": 143277 },3278 "exact_match": {3279 "mean": 0.0,3280 "ci_low": 0.0,3281 "ci_high": 0.0,3282 "n_items": 63,3283 "n_groups": 143284 },3285 "number_recall": {3286 "mean": 0.9962522045855379,3287 "ci_low": 0.9902094717668488,3288 "ci_high": 1.0,3289 "n_items": 63,3290 "n_groups": 143291 },3292 "placeholders_exact": {3293 "mean": 1.0,3294 "ci_low": 1.0,3295 "ci_high": 1.0,3296 "n_items": 63,3297 "n_groups": 143298 }3299 },3300 "limitations": {3301 "n": 28,3302 "chrf": {3303 "mean": 73.23811321258312,3304 "ci_low": 69.4452264246932,3305 "ci_high": 76.20119526574571,3306 "n_items": 28,3307 "n_groups": 43308 },3309 "edit_sim": {3310 "mean": 0.717246964743496,3311 "ci_low": 0.6954724716508809,3312 "ci_high": 0.7387049112570757,3313 "n_items": 28,3314 "n_groups": 43315 },3316 "rougeL": {3317 "mean": 0.7194406836340473,3318 "ci_low": 0.6794396891708837,3319 "ci_high": 0.74944142948142,3320 "n_items": 28,3321 "n_groups": 43322 },3323 "exact_match": {3324 "mean": 0.0,3325 "ci_low": 0.0,3326 "ci_high": 0.0,3327 "n_items": 28,3328 "n_groups": 43329 },3330 "number_recall": {3331 "mean": 1.0,3332 "ci_low": 1.0,3333 "ci_high": 1.0,3334 "n_items": 28,3335 "n_groups": 43336 },3337 "placeholders_exact": {3338 "mean": 1.0,3339 "ci_low": 1.0,3340 "ci_high": 1.0,3341 "n_items": 28,3342 "n_groups": 43343 }3344 },3345 "methods": {3346 "n": 67,3347 "chrf": {3348 "mean": 72.47399445816811,3349 "ci_low": 69.74089917121309,3350 "ci_high": 75.40660314060462,3351 "n_items": 67,3352 "n_groups": 123353 },3354 "edit_sim": {3355 "mean": 0.716513901448404,3356 "ci_low": 0.693906110095698,3357 "ci_high": 0.7401382606182368,3358 "n_items": 67,3359 "n_groups": 123360 },3361 "rougeL": {3362 "mean": 0.7288579575851031,3363 "ci_low": 0.7035409261187602,3364 "ci_high": 0.7563167193337433,3365 "n_items": 67,3366 "n_groups": 123367 },3368 "exact_match": {3369 "mean": 0.0,3370 "ci_low": 0.0,3371 "ci_high": 0.0,3372 "n_items": 67,3373 "n_groups": 123374 },3375 "number_recall": {3376 "mean": 0.991180461329715,3377 "ci_low": 0.9734848484848484,3378 "ci_high": 1.0,3379 "n_items": 67,3380 "n_groups": 123381 },3382 "placeholders_exact": {3383 "mean": 1.0,3384 "ci_low": 1.0,3385 "ci_high": 1.0,3386 "n_items": 67,3387 "n_groups": 123388 }3389 },3390 "other": {3391 "n": 52,3392 "chrf": {3393 "mean": 71.82482676794147,3394 "ci_low": 68.07671687151215,3395 "ci_high": 76.0769761054388,3396 "n_items": 52,3397 "n_groups": 93398 },3399 "edit_sim": {3400 "mean": 0.707106837309332,3401 "ci_low": 0.6708945347023293,3402 "ci_high": 0.7545414033879071,3403 "n_items": 52,3404 "n_groups": 93405 },3406 "rougeL": {3407 "mean": 0.7071964982570692,3408 "ci_low": 0.6634566234346598,3409 "ci_high": 0.764686444646759,3410 "n_items": 52,3411 "n_groups": 93412 },3413 "exact_match": {3414 "mean": 0.0,3415 "ci_low": 0.0,3416 "ci_high": 0.0,3417 "n_items": 52,3418 "n_groups": 93419 },3420 "number_recall": {3421 "mean": 0.9897435897435898,3422 "ci_low": 0.9754343520090548,3423 "ci_high": 1.0,3424 "n_items": 52,3425 "n_groups": 93426 },3427 "placeholders_exact": {3428 "mean": 1.0,3429 "ci_low": 1.0,3430 "ci_high": 1.0,3431 "n_items": 52,3432 "n_groups": 93433 }3434 },3435 "related_work": {3436 "n": 4,3437 "chrf": {3438 "mean": 80.6303709211075,3439 "ci_low": 80.6303709211075,3440 "ci_high": 80.6303709211075,3441 "n_items": 4,3442 "n_groups": 13443 },3444 "edit_sim": {3445 "mean": 0.8007621459996452,3446 "ci_low": 0.8007621459996452,3447 "ci_high": 0.8007621459996452,3448 "n_items": 4,3449 "n_groups": 13450 },3451 "rougeL": {3452 "mean": 0.7996966483165651,3453 "ci_low": 0.7996966483165651,3454 "ci_high": 0.7996966483165651,3455 "n_items": 4,3456 "n_groups": 13457 },3458 "exact_match": {3459 "mean": 0.0,3460 "ci_low": 0.0,3461 "ci_high": 0.0,3462 "n_items": 4,3463 "n_groups": 13464 },3465 "number_recall": {3466 "mean": 1.0,3467 "ci_low": 1.0,3468 "ci_high": 1.0,3469 "n_items": 4,3470 "n_groups": 13471 },3472 "placeholders_exact": {3473 "mean": 1.0,3474 "ci_low": 1.0,3475 "ci_high": 1.0,3476 "n_items": 4,3477 "n_groups": 13478 }3479 },3480 "results": {3481 "n": 46,3482 "chrf": {3483 "mean": 70.8910054213943,3484 "ci_low": 68.82921107168154,3485 "ci_high": 72.80639303077038,3486 "n_items": 46,3487 "n_groups": 93488 },3489 "edit_sim": {3490 "mean": 0.6911806315520853,3491 "ci_low": 0.6669690705054361,3492 "ci_high": 0.7189295132307508,3493 "n_items": 46,3494 "n_groups": 93495 },3496 "rougeL": {3497 "mean": 0.709689437438547,3498 "ci_low": 0.6961516348083661,3499 "ci_high": 0.7247193629217838,3500 "n_items": 46,3501 "n_groups": 93502 },3503 "exact_match": {3504 "mean": 0.0,3505 "ci_low": 0.0,3506 "ci_high": 0.0,3507 "n_items": 46,3508 "n_groups": 93509 },3510 "number_recall": {3511 "mean": 0.9891304347826086,3512 "ci_low": 0.9700854700854702,3513 "ci_high": 1.0,3514 "n_items": 46,3515 "n_groups": 93516 },3517 "placeholders_exact": {3518 "mean": 1.0,3519 "ci_low": 1.0,3520 "ci_high": 1.0,3521 "n_items": 46,3522 "n_groups": 93523 }3524 },3525 "theory": {3526 "n": 34,3527 "chrf": {3528 "mean": 72.25181710838572,3529 "ci_low": 69.92214720035376,3530 "ci_high": 76.54530922319827,3531 "n_items": 34,3532 "n_groups": 63533 },3534 "edit_sim": {3535 "mean": 0.7094407705977154,3536 "ci_low": 0.6906727704864998,3537 "ci_high": 0.7430294033556744,3538 "n_items": 34,3539 "n_groups": 63540 },3541 "rougeL": {3542 "mean": 0.7091847647791214,3543 "ci_low": 0.6896313682261355,3544 "ci_high": 0.7446361121429312,3545 "n_items": 34,3546 "n_groups": 63547 },3548 "exact_match": {3549 "mean": 0.0,3550 "ci_low": 0.0,3551 "ci_high": 0.0,3552 "n_items": 34,3553 "n_groups": 63554 },3555 "number_recall": {3556 "mean": 0.9919786096256684,3557 "ci_low": 0.9659090909090908,3558 "ci_high": 1.0,3559 "n_items": 34,3560 "n_groups": 63561 },3562 "placeholders_exact": {3563 "mean": 1.0,3564 "ci_low": 1.0,3565 "ci_high": 1.0,3566 "n_items": 34,3567 "n_groups": 63568 }3569 }3570 }3571 },3572 "htr-m1-tiny-s3": {3573 "overall": {3574 "n": 531,3575 "chrf": {3576 "mean": 73.24617320620672,3577 "ci_low": 72.26414092143095,3578 "ci_high": 74.46466551478325,3579 "n_items": 531,3580 "n_groups": 553581 },3582 "edit_sim": {3583 "mean": 0.7230970938933502,3584 "ci_low": 0.7141026058933048,3585 "ci_high": 0.7343746327888357,3586 "n_items": 531,3587 "n_groups": 553588 },3589 "rougeL": {3590 "mean": 0.7259894778671283,3591 "ci_low": 0.7154919028821826,3592 "ci_high": 0.739170394777393,3593 "n_items": 531,3594 "n_groups": 553595 },3596 "exact_match": {3597 "mean": 0.0,3598 "ci_low": 0.0,3599 "ci_high": 0.0,3600 "n_items": 531,3601 "n_groups": 553602 },3603 "number_recall": {3604 "mean": 0.9909052762085767,3605 "ci_low": 0.9830014026293498,3606 "ci_high": 0.997085630635441,3607 "n_items": 531,3608 "n_groups": 553609 },3610 "placeholders_exact": {3611 "mean": 0.992467043314501,3612 "ci_low": 0.9775268245773864,3613 "ci_high": 1.0,3614 "n_items": 531,3615 "n_groups": 553616 }3617 },3618 "by_variant": {3619 "A": {3620 "n": 267,3621 "chrf": {3622 "mean": 69.67564925229263,3623 "ci_low": 68.68035069359479,3624 "ci_high": 70.82797047396751,3625 "n_items": 267,3626 "n_groups": 533627 },3628 "edit_sim": {3629 "mean": 0.6737675532192922,3630 "ci_low": 0.6623608187169184,3631 "ci_high": 0.6870655964149424,3632 "n_items": 267,3633 "n_groups": 533634 },3635 "rougeL": {3636 "mean": 0.677729001282889,3637 "ci_low": 0.6656546094946639,3638 "ci_high": 0.6917275552099988,3639 "n_items": 267,3640 "n_groups": 533641 },3642 "exact_match": {3643 "mean": 0.0,3644 "ci_low": 0.0,3645 "ci_high": 0.0,3646 "n_items": 267,3647 "n_groups": 533648 },3649 "number_recall": {3650 "mean": 0.9908143425884407,3651 "ci_low": 0.9802530604312382,3652 "ci_high": 0.9978089796373577,3653 "n_items": 267,3654 "n_groups": 533655 },3656 "placeholders_exact": {3657 "mean": 0.9925093632958801,3658 "ci_low": 0.9803889318885448,3659 "ci_high": 1.0,3660 "n_items": 267,3661 "n_groups": 533662 }3663 },3664 "B": {3665 "n": 264,3666 "chrf": {3667 "mean": 76.85727129596076,3668 "ci_low": 75.66475837138302,3669 "ci_high": 78.21878904280216,3670 "n_items": 264,3671 "n_groups": 543672 },3673 "edit_sim": {3674 "mean": 0.7729871975296135,3675 "ci_low": 0.7625051385216299,3676 "ci_high": 0.78594532300246,3677 "n_items": 264,3678 "n_groups": 543679 },3680 "rougeL": {3681 "mean": 0.7747983689580065,3682 "ci_low": 0.7626824009176614,3683 "ci_high": 0.7891184266120643,3684 "n_items": 264,3685 "n_groups": 543686 },3687 "exact_match": {3688 "mean": 0.0,3689 "ci_low": 0.0,3690 "ci_high": 0.0,3691 "n_items": 264,3692 "n_groups": 543693 },3694 "number_recall": {3695 "mean": 0.9909972431653055,3696 "ci_low": 0.9828269868563602,3697 "ci_high": 0.9982640579216274,3698 "n_items": 264,3699 "n_groups": 543700 },3701 "placeholders_exact": {3702 "mean": 0.9924242424242424,3703 "ci_low": 0.9719626168224299,3704 "ci_high": 1.0,3705 "n_items": 264,3706 "n_groups": 543707 }3708 }3709 },3710 "by_discipline": {3711 "biomedicine": {3712 "n": 118,3713 "chrf": {3714 "mean": 74.52932043486099,3715 "ci_low": 72.67116040490754,3716 "ci_high": 76.14581689718268,3717 "n_items": 118,3718 "n_groups": 263719 },3720 "edit_sim": {3721 "mean": 0.7292050510045609,3722 "ci_low": 0.710391610391992,3723 "ci_high": 0.7457206196824608,3724 "n_items": 118,3725 "n_groups": 263726 },3727 "rougeL": {3728 "mean": 0.7352662353358067,3729 "ci_low": 0.7159337234510826,3730 "ci_high": 0.751949201861442,3731 "n_items": 118,3732 "n_groups": 263733 },3734 "exact_match": {3735 "mean": 0.0,3736 "ci_low": 0.0,3737 "ci_high": 0.0,3738 "n_items": 118,3739 "n_groups": 263740 },3741 "number_recall": {3742 "mean": 0.9792036588646758,3743 "ci_low": 0.9463067259343326,3744 "ci_high": 0.9977328726766298,3745 "n_items": 118,3746 "n_groups": 263747 },3748 "placeholders_exact": {3749 "mean": 1.0,3750 "ci_low": 1.0,3751 "ci_high": 1.0,3752 "n_items": 118,3753 "n_groups": 263754 }3755 },3756 "computer_science": {3757 "n": 57,3758 "chrf": {3759 "mean": 72.23753000293323,3760 "ci_low": 71.085084107029,3761 "ci_high": 74.73449611072573,3762 "n_items": 57,3763 "n_groups": 23764 },3765 "edit_sim": {3766 "mean": 0.7250850016533585,3767 "ci_low": 0.7234601351459371,3768 "ci_high": 0.7286055457527716,3769 "n_items": 57,3770 "n_groups": 23771 },3772 "rougeL": {3773 "mean": 0.7161626585586723,3774 "ci_low": 0.7074228362444404,3775 "ci_high": 0.7350989402395091,3776 "n_items": 57,3777 "n_groups": 23778 },3779 "exact_match": {3780 "mean": 0.0,3781 "ci_low": 0.0,3782 "ci_high": 0.0,3783 "n_items": 57,3784 "n_groups": 23785 },3786 "number_recall": {3787 "mean": 0.9980239059186429,3788 "ci_low": 0.9937423687423687,3789 "ci_high": 1.0,3790 "n_items": 57,3791 "n_groups": 23792 },3793 "placeholders_exact": {3794 "mean": 1.0,3795 "ci_low": 1.0,3796 "ci_high": 1.0,3797 "n_items": 57,3798 "n_groups": 23799 }3800 },3801 "earth_sciences": {3802 "n": 64,3803 "chrf": {3804 "mean": 71.23771726046412,3805 "ci_low": 68.54225457725262,3806 "ci_high": 73.44203987972506,3807 "n_items": 64,3808 "n_groups": 33809 },3810 "edit_sim": {3811 "mean": 0.7081124215431105,3812 "ci_low": 0.6780042973882151,3813 "ci_high": 0.7199219370532418,3814 "n_items": 64,3815 "n_groups": 33816 },3817 "rougeL": {3818 "mean": 0.7127111428122836,3819 "ci_low": 0.6718687754154238,3820 "ci_high": 0.7361629259047036,3821 "n_items": 64,3822 "n_groups": 33823 },3824 "exact_match": {3825 "mean": 0.0,3826 "ci_low": 0.0,3827 "ci_high": 0.0,3828 "n_items": 64,3829 "n_groups": 33830 },3831 "number_recall": {3832 "mean": 0.9888523391812866,3833 "ci_low": 0.9753982657793909,3834 "ci_high": 1.0,3835 "n_items": 64,3836 "n_groups": 33837 },3838 "placeholders_exact": {3839 "mean": 1.0,3840 "ci_low": 1.0,3841 "ci_high": 1.0,3842 "n_items": 64,3843 "n_groups": 33844 }3845 },3846 "economics": {3847 "n": 64,3848 "chrf": {3849 "mean": 71.53936263570459,3850 "ci_low": 71.53936263570459,3851 "ci_high": 71.53936263570459,3852 "n_items": 64,3853 "n_groups": 13854 },3855 "edit_sim": {3856 "mean": 0.7008817186445759,3857 "ci_low": 0.7008817186445759,3858 "ci_high": 0.7008817186445759,3859 "n_items": 64,3860 "n_groups": 13861 },3862 "rougeL": {3863 "mean": 0.701504736430343,3864 "ci_low": 0.701504736430343,3865 "ci_high": 0.701504736430343,3866 "n_items": 64,3867 "n_groups": 13868 },3869 "exact_match": {3870 "mean": 0.0,3871 "ci_low": 0.0,3872 "ci_high": 0.0,3873 "n_items": 64,3874 "n_groups": 13875 },3876 "number_recall": {3877 "mean": 0.9817708333333333,3878 "ci_low": 0.9817708333333333,3879 "ci_high": 0.9817708333333333,3880 "n_items": 64,3881 "n_groups": 13882 },3883 "placeholders_exact": {3884 "mean": 1.0,3885 "ci_low": 1.0,3886 "ci_high": 1.0,3887 "n_items": 64,3888 "n_groups": 13889 }3890 },3891 "engineering": {3892 "n": 11,3893 "chrf": {3894 "mean": 73.8078451662965,3895 "ci_low": 73.8078451662965,3896 "ci_high": 73.8078451662965,3897 "n_items": 11,3898 "n_groups": 13899 },3900 "edit_sim": {3901 "mean": 0.7214164359475738,3902 "ci_low": 0.7214164359475738,3903 "ci_high": 0.7214164359475738,3904 "n_items": 11,3905 "n_groups": 13906 },3907 "rougeL": {3908 "mean": 0.6978389983331019,3909 "ci_low": 0.6978389983331019,3910 "ci_high": 0.6978389983331019,3911 "n_items": 11,3912 "n_groups": 13913 },3914 "exact_match": {3915 "mean": 0.0,3916 "ci_low": 0.0,3917 "ci_high": 0.0,3918 "n_items": 11,3919 "n_groups": 13920 },3921 "number_recall": {3922 "mean": 1.0,3923 "ci_low": 1.0,3924 "ci_high": 1.0,3925 "n_items": 11,3926 "n_groups": 13927 },3928 "placeholders_exact": {3929 "mean": 1.0,3930 "ci_low": 1.0,3931 "ci_high": 1.0,3932 "n_items": 11,3933 "n_groups": 13934 }3935 },3936 "life_sciences": {3937 "n": 95,3938 "chrf": {3939 "mean": 75.88638641144645,3940 "ci_low": 73.22612579234465,3941 "ci_high": 78.92869170243789,3942 "n_items": 95,3943 "n_groups": 163944 },3945 "edit_sim": {3946 "mean": 0.7533317572772471,3947 "ci_low": 0.7252272109971194,3948 "ci_high": 0.7846300980570087,3949 "n_items": 95,3950 "n_groups": 163951 },3952 "rougeL": {3953 "mean": 0.7553332980181386,3954 "ci_low": 0.7239910890035001,3955 "ci_high": 0.7897824206601725,3956 "n_items": 95,3957 "n_groups": 163958 },3959 "exact_match": {3960 "mean": 0.0,3961 "ci_low": 0.0,3962 "ci_high": 0.0,3963 "n_items": 95,3964 "n_groups": 163965 },3966 "number_recall": {3967 "mean": 0.9977272727272727,3968 "ci_low": 0.9944316573756432,3969 "ci_high": 1.0,3970 "n_items": 95,3971 "n_groups": 163972 },3973 "placeholders_exact": {3974 "mean": 0.968421052631579,3975 "ci_low": 0.9010714285714286,3976 "ci_high": 1.0,3977 "n_items": 95,3978 "n_groups": 163979 }3980 },3981 "social_sciences": {3982 "n": 75,3983 "chrf": {3984 "mean": 72.48816131861847,3985 "ci_low": 67.24791428617185,3986 "ci_high": 75.08619181410941,3987 "n_items": 75,3988 "n_groups": 43989 },3990 "edit_sim": {3991 "mean": 0.7143343450193503,3992 "ci_low": 0.6764009173360505,3993 "ci_high": 0.7310382243225894,3994 "n_items": 75,3995 "n_groups": 43996 },3997 "rougeL": {3998 "mean": 0.7220728443565679,3999 "ci_low": 0.6682713242414964,4000 "ci_high": 0.7445635935679316,4001 "n_items": 75,4002 "n_groups": 44003 },4004 "exact_match": {4005 "mean": 0.0,4006 "ci_low": 0.0,4007 "ci_high": 0.0,4008 "n_items": 75,4009 "n_groups": 44010 },4011 "number_recall": {4012 "mean": 1.0,4013 "ci_low": 1.0,4014 "ci_high": 1.0,4015 "n_items": 75,4016 "n_groups": 44017 },4018 "placeholders_exact": {4019 "mean": 1.0,4020 "ci_low": 1.0,4021 "ci_high": 1.0,4022 "n_items": 75,4023 "n_groups": 44024 }4025 },4026 "statistics": {4027 "n": 47,4028 "chrf": {4029 "mean": 72.04852623078988,4030 "ci_low": 70.5616606312932,4031 "ci_high": 72.81594073375591,4032 "n_items": 47,4033 "n_groups": 24034 },4035 "edit_sim": {4036 "mean": 0.7092705778588161,4037 "ci_low": 0.7017543676148208,4038 "ci_high": 0.7131499121782976,4039 "n_items": 47,4040 "n_groups": 24041 },4042 "rougeL": {4043 "mean": 0.7195649691131395,4044 "ci_low": 0.7192808841093574,4045 "ci_high": 0.7201153838079671,4046 "n_items": 47,4047 "n_groups": 24048 },4049 "exact_match": {4050 "mean": 0.0,4051 "ci_low": 0.0,4052 "ci_high": 0.0,4053 "n_items": 47,4054 "n_groups": 24055 },4056 "number_recall": {4057 "mean": 0.9964539007092199,4058 "ci_low": 0.9946236559139786,4059 "ci_high": 1.0,4060 "n_items": 47,4061 "n_groups": 24062 },4063 "placeholders_exact": {4064 "mean": 0.9787234042553191,4065 "ci_low": 0.9375,4066 "ci_high": 1.0,4067 "n_items": 47,4068 "n_groups": 24069 }4070 }4071 },4072 "by_era": {4073 "1980-1999": {4074 "n": 5,4075 "chrf": {4076 "mean": 75.78680125933609,4077 "ci_low": 73.66503894966762,4078 "ci_high": 78.96944472383879,4079 "n_items": 5,4080 "n_groups": 24081 },4082 "edit_sim": {4083 "mean": 0.7892609978995382,4084 "ci_low": 0.7867482498332551,4085 "ci_high": 0.7930301199989632,4086 "n_items": 5,4087 "n_groups": 24088 },4089 "rougeL": {4090 "mean": 0.7793642301546324,4091 "ci_low": 0.7754205507339549,4092 "ci_high": 0.7852797492856485,4093 "n_items": 5,4094 "n_groups": 24095 },4096 "exact_match": {4097 "mean": 0.0,4098 "ci_low": 0.0,4099 "ci_high": 0.0,4100 "n_items": 5,4101 "n_groups": 24102 },4103 "number_recall": {4104 "mean": 1.0,4105 "ci_low": 1.0,4106 "ci_high": 1.0,4107 "n_items": 5,4108 "n_groups": 24109 },4110 "placeholders_exact": {4111 "mean": 1.0,4112 "ci_low": 1.0,4113 "ci_high": 1.0,4114 "n_items": 5,4115 "n_groups": 24116 }4117 },4118 "2000-2009": {4119 "n": 58,4120 "chrf": {4121 "mean": 73.00274710761704,4122 "ci_low": 70.46572012272797,4123 "ci_high": 76.30296886615335,4124 "n_items": 58,4125 "n_groups": 74126 },4127 "edit_sim": {4128 "mean": 0.7225466380929827,4129 "ci_low": 0.6983214873058678,4130 "ci_high": 0.7536155486845613,4131 "n_items": 58,4132 "n_groups": 74133 },4134 "rougeL": {4135 "mean": 0.7217389987211364,4136 "ci_low": 0.6901559522956536,4137 "ci_high": 0.7567114927067454,4138 "n_items": 58,4139 "n_groups": 74140 },4141 "exact_match": {4142 "mean": 0.0,4143 "ci_low": 0.0,4144 "ci_high": 0.0,4145 "n_items": 58,4146 "n_groups": 74147 },4148 "number_recall": {4149 "mean": 1.0,4150 "ci_low": 1.0,4151 "ci_high": 1.0,4152 "n_items": 58,4153 "n_groups": 74154 },4155 "placeholders_exact": {4156 "mean": 0.9827586206896551,4157 "ci_low": 0.9599864864864864,4158 "ci_high": 1.0,4159 "n_items": 58,4160 "n_groups": 74161 }4162 },4163 "2010-2017": {4164 "n": 468,4165 "chrf": {4166 "mean": 73.24919793580621,4167 "ci_low": 72.13863955260905,4168 "ci_high": 74.58707715390322,4169 "n_items": 468,4170 "n_groups": 464171 },4172 "edit_sim": {4173 "mean": 0.7224584334582869,4174 "ci_low": 0.7125458639779236,4175 "ci_high": 0.7342693989637702,4176 "n_items": 468,4177 "n_groups": 464178 },4179 "rougeL": {4180 "mean": 0.7259460035701837,4181 "ci_low": 0.714115571335054,4182 "ci_high": 0.7403485188125342,4183 "n_items": 468,4184 "n_groups": 464185 },4186 "exact_match": {4187 "mean": 0.0,4188 "ci_low": 0.0,4189 "ci_high": 0.0,4190 "n_items": 468,4191 "n_groups": 464192 },4193 "number_recall": {4194 "mean": 0.9896809864674238,4195 "ci_low": 0.9805728236454629,4196 "ci_high": 0.9965801859091545,4197 "n_items": 468,4198 "n_groups": 464199 },4200 "placeholders_exact": {4201 "mean": 0.9935897435897436,4202 "ci_low": 0.9762364450730787,4203 "ci_high": 1.0,4204 "n_items": 468,4205 "n_groups": 464206 }4207 }4208 },4209 "by_role": {4210 "abstract": {4211 "n": 55,4212 "chrf": {4213 "mean": 75.91538824602178,4214 "ci_low": 74.08222899262155,4215 "ci_high": 77.80216213061931,4216 "n_items": 55,4217 "n_groups": 154218 },4219 "edit_sim": {4220 "mean": 0.7530297760345976,4221 "ci_low": 0.7339631631930112,4222 "ci_high": 0.771404166438195,4223 "n_items": 55,4224 "n_groups": 154225 },4226 "rougeL": {4227 "mean": 0.741873353714182,4228 "ci_low": 0.7218358325815667,4229 "ci_high": 0.7639908787165651,4230 "n_items": 55,4231 "n_groups": 154232 },4233 "exact_match": {4234 "mean": 0.0,4235 "ci_low": 0.0,4236 "ci_high": 0.0,4237 "n_items": 55,4238 "n_groups": 154239 },4240 "number_recall": {4241 "mean": 1.0,4242 "ci_low": 1.0,4243 "ci_high": 1.0,4244 "n_items": 55,4245 "n_groups": 154246 },4247 "placeholders_exact": {4248 "mean": 0.9818181818181818,4249 "ci_low": 0.9444444444444444,4250 "ci_high": 1.0,4251 "n_items": 55,4252 "n_groups": 154253 }4254 },4255 "background": {4256 "n": 36,4257 "chrf": {4258 "mean": 74.22902645576045,4259 "ci_low": 71.35428227130328,4260 "ci_high": 76.70751906324995,4261 "n_items": 36,4262 "n_groups": 74263 },4264 "edit_sim": {4265 "mean": 0.7378076335100467,4266 "ci_low": 0.7090290072538282,4267 "ci_high": 0.7654031329050552,4268 "n_items": 36,4269 "n_groups": 74270 },4271 "rougeL": {4272 "mean": 0.7407454831322376,4273 "ci_low": 0.7243033813952519,4274 "ci_high": 0.7602368597146665,4275 "n_items": 36,4276 "n_groups": 74277 },4278 "exact_match": {4279 "mean": 0.0,4280 "ci_low": 0.0,4281 "ci_high": 0.0,4282 "n_items": 36,4283 "n_groups": 74284 },4285 "number_recall": {4286 "mean": 0.9984567901234568,4287 "ci_low": 0.9953703703703702,4288 "ci_high": 1.0,4289 "n_items": 36,4290 "n_groups": 74291 },4292 "placeholders_exact": {4293 "mean": 1.0,4294 "ci_low": 1.0,4295 "ci_high": 1.0,4296 "n_items": 36,4297 "n_groups": 74298 }4299 },4300 "conclusion": {4301 "n": 36,4302 "chrf": {4303 "mean": 70.08631317758868,4304 "ci_low": 66.72506128281984,4305 "ci_high": 73.39552146829999,4306 "n_items": 36,4307 "n_groups": 94308 },4309 "edit_sim": {4310 "mean": 0.700784359105145,4311 "ci_low": 0.6636139101940153,4312 "ci_high": 0.7407588413852768,4313 "n_items": 36,4314 "n_groups": 94315 },4316 "rougeL": {4317 "mean": 0.6927748582192926,4318 "ci_low": 0.6531479546371685,4319 "ci_high": 0.7318547554212217,4320 "n_items": 36,4321 "n_groups": 94322 },4323 "exact_match": {4324 "mean": 0.0,4325 "ci_low": 0.0,4326 "ci_high": 0.0,4327 "n_items": 36,4328 "n_groups": 94329 },4330 "number_recall": {4331 "mean": 0.9861111111111112,4332 "ci_low": 0.9583333333333334,4333 "ci_high": 1.0,4334 "n_items": 36,4335 "n_groups": 94336 },4337 "placeholders_exact": {4338 "mean": 1.0,4339 "ci_low": 1.0,4340 "ci_high": 1.0,4341 "n_items": 36,4342 "n_groups": 94343 }4344 },4345 "data": {4346 "n": 41,4347 "chrf": {4348 "mean": 76.43559865666091,4349 "ci_low": 73.37210764737564,4350 "ci_high": 79.60454259097956,4351 "n_items": 41,4352 "n_groups": 104353 },4354 "edit_sim": {4355 "mean": 0.7330178136773396,4356 "ci_low": 0.6936626703480063,4357 "ci_high": 0.7793631771455302,4358 "n_items": 41,4359 "n_groups": 104360 },4361 "rougeL": {4362 "mean": 0.7579734082188122,4363 "ci_low": 0.722330050484305,4364 "ci_high": 0.795760687021274,4365 "n_items": 41,4366 "n_groups": 104367 },4368 "exact_match": {4369 "mean": 0.0,4370 "ci_low": 0.0,4371 "ci_high": 0.0,4372 "n_items": 41,4373 "n_groups": 104374 },4375 "number_recall": {4376 "mean": 0.9912239557618248,4377 "ci_low": 0.9805209994683679,4378 "ci_high": 0.9985214078374455,4379 "n_items": 41,4380 "n_groups": 104381 },4382 "placeholders_exact": {4383 "mean": 1.0,4384 "ci_low": 1.0,4385 "ci_high": 1.0,4386 "n_items": 41,4387 "n_groups": 104388 }4389 },4390 "discussion": {4391 "n": 69,4392 "chrf": {4393 "mean": 73.75230609753476,4394 "ci_low": 71.60539733012982,4395 "ci_high": 75.98513465760377,4396 "n_items": 69,4397 "n_groups": 144398 },4399 "edit_sim": {4400 "mean": 0.7321689495948147,4401 "ci_low": 0.7055899699780123,4402 "ci_high": 0.758395359388355,4403 "n_items": 69,4404 "n_groups": 144405 },4406 "rougeL": {4407 "mean": 0.7320854544085336,4408 "ci_low": 0.7034369158490441,4409 "ci_high": 0.7622695986942984,4410 "n_items": 69,4411 "n_groups": 144412 },4413 "exact_match": {4414 "mean": 0.0,4415 "ci_low": 0.0,4416 "ci_high": 0.0,4417 "n_items": 69,4418 "n_groups": 144419 },4420 "number_recall": {4421 "mean": 1.0,4422 "ci_low": 1.0,4423 "ci_high": 1.0,4424 "n_items": 69,4425 "n_groups": 144426 },4427 "placeholders_exact": {4428 "mean": 1.0,4429 "ci_low": 1.0,4430 "ci_high": 1.0,4431 "n_items": 69,4432 "n_groups": 144433 }4434 },4435 "introduction": {4436 "n": 63,4437 "chrf": {4438 "mean": 72.3501015901756,4439 "ci_low": 70.247997173628,4440 "ci_high": 74.53693523987441,4441 "n_items": 63,4442 "n_groups": 144443 },4444 "edit_sim": {4445 "mean": 0.7078109684144313,4446 "ci_low": 0.687725937993,4447 "ci_high": 0.7267722064677781,4448 "n_items": 63,4449 "n_groups": 144450 },4451 "rougeL": {4452 "mean": 0.7117868558522029,4453 "ci_low": 0.6942303698251877,4454 "ci_high": 0.7297067436356488,4455 "n_items": 63,4456 "n_groups": 144457 },4458 "exact_match": {4459 "mean": 0.0,4460 "ci_low": 0.0,4461 "ci_high": 0.0,4462 "n_items": 63,4463 "n_groups": 144464 },4465 "number_recall": {4466 "mean": 0.9929453262786596,4467 "ci_low": 0.977391389051237,4468 "ci_high": 1.0,4469 "n_items": 63,4470 "n_groups": 144471 },4472 "placeholders_exact": {4473 "mean": 1.0,4474 "ci_low": 1.0,4475 "ci_high": 1.0,4476 "n_items": 63,4477 "n_groups": 144478 }4479 },4480 "limitations": {4481 "n": 28,4482 "chrf": {4483 "mean": 73.67756734907883,4484 "ci_low": 70.56031002283393,4485 "ci_high": 75.94718084746683,4486 "n_items": 28,4487 "n_groups": 44488 },4489 "edit_sim": {4490 "mean": 0.7265803526146409,4491 "ci_low": 0.7048903451188402,4492 "ci_high": 0.7514659992758278,4493 "n_items": 28,4494 "n_groups": 44495 },4496 "rougeL": {4497 "mean": 0.726528394231021,4498 "ci_low": 0.6885692782042576,4499 "ci_high": 0.758904756291175,4500 "n_items": 28,4501 "n_groups": 44502 },4503 "exact_match": {4504 "mean": 0.0,4505 "ci_low": 0.0,4506 "ci_high": 0.0,4507 "n_items": 28,4508 "n_groups": 44509 },4510 "number_recall": {4511 "mean": 1.0,4512 "ci_low": 1.0,4513 "ci_high": 1.0,4514 "n_items": 28,4515 "n_groups": 44516 },4517 "placeholders_exact": {4518 "mean": 1.0,4519 "ci_low": 1.0,4520 "ci_high": 1.0,4521 "n_items": 28,4522 "n_groups": 44523 }4524 },4525 "methods": {4526 "n": 67,4527 "chrf": {4528 "mean": 72.5490775623406,4529 "ci_low": 69.53186476225979,4530 "ci_high": 75.65506162318805,4531 "n_items": 67,4532 "n_groups": 124533 },4534 "edit_sim": {4535 "mean": 0.7227698961738447,4536 "ci_low": 0.6943778741746054,4537 "ci_high": 0.7520109299174784,4538 "n_items": 67,4539 "n_groups": 124540 },4541 "rougeL": {4542 "mean": 0.7288210019149355,4543 "ci_low": 0.6975397420475663,4544 "ci_high": 0.7604743000121544,4545 "n_items": 67,4546 "n_groups": 124547 },4548 "exact_match": {4549 "mean": 0.0,4550 "ci_low": 0.0,4551 "ci_high": 0.0,4552 "n_items": 67,4553 "n_groups": 124554 },4555 "number_recall": {4556 "mean": 0.9601990049751246,4557 "ci_low": 0.9027693089430895,4558 "ci_high": 1.0,4559 "n_items": 67,4560 "n_groups": 124561 },4562 "placeholders_exact": {4563 "mean": 1.0,4564 "ci_low": 1.0,4565 "ci_high": 1.0,4566 "n_items": 67,4567 "n_groups": 124568 }4569 },4570 "other": {4571 "n": 52,4572 "chrf": {4573 "mean": 72.6656860382559,4574 "ci_low": 68.16162165024222,4575 "ci_high": 77.68444292970653,4576 "n_items": 52,4577 "n_groups": 94578 },4579 "edit_sim": {4580 "mean": 0.718356440088347,4581 "ci_low": 0.6763317175158585,4582 "ci_high": 0.7716468795217816,4583 "n_items": 52,4584 "n_groups": 94585 },4586 "rougeL": {4587 "mean": 0.7162999185310102,4588 "ci_low": 0.66773624511833,4589 "ci_high": 0.777172030327078,4590 "n_items": 52,4591 "n_groups": 94592 },4593 "exact_match": {4594 "mean": 0.0,4595 "ci_low": 0.0,4596 "ci_high": 0.0,4597 "n_items": 52,4598 "n_groups": 94599 },4600 "number_recall": {4601 "mean": 0.9961538461538461,4602 "ci_low": 0.9863636363636364,4603 "ci_high": 1.0,4604 "n_items": 52,4605 "n_groups": 94606 },4607 "placeholders_exact": {4608 "mean": 0.9423076923076923,4609 "ci_low": 0.8301886792452831,4610 "ci_high": 1.0,4611 "n_items": 52,4612 "n_groups": 94613 }4614 },4615 "related_work": {4616 "n": 4,4617 "chrf": {4618 "mean": 79.51686247721264,4619 "ci_low": 79.51686247721264,4620 "ci_high": 79.51686247721264,4621 "n_items": 4,4622 "n_groups": 14623 },4624 "edit_sim": {4625 "mean": 0.7897151119209153,4626 "ci_low": 0.7897151119209153,4627 "ci_high": 0.7897151119209153,4628 "n_items": 4,4629 "n_groups": 14630 },4631 "rougeL": {4632 "mean": 0.7909292258622863,4633 "ci_low": 0.7909292258622863,4634 "ci_high": 0.7909292258622863,4635 "n_items": 4,4636 "n_groups": 14637 },4638 "exact_match": {4639 "mean": 0.0,4640 "ci_low": 0.0,4641 "ci_high": 0.0,4642 "n_items": 4,4643 "n_groups": 14644 },4645 "number_recall": {4646 "mean": 1.0,4647 "ci_low": 1.0,4648 "ci_high": 1.0,4649 "n_items": 4,4650 "n_groups": 14651 },4652 "placeholders_exact": {4653 "mean": 1.0,4654 "ci_low": 1.0,4655 "ci_high": 1.0,4656 "n_items": 4,4657 "n_groups": 14658 }4659 },4660 "results": {4661 "n": 46,4662 "chrf": {4663 "mean": 71.2324267596034,4664 "ci_low": 68.91572043620738,4665 "ci_high": 73.51852677144946,4666 "n_items": 46,4667 "n_groups": 94668 },4669 "edit_sim": {4670 "mean": 0.703218632028333,4671 "ci_low": 0.6808576772093519,4672 "ci_high": 0.7279235786972579,4673 "n_items": 46,4674 "n_groups": 94675 },4676 "rougeL": {4677 "mean": 0.7168452352761494,4678 "ci_low": 0.702862998857852,4679 "ci_high": 0.7316103685720918,4680 "n_items": 46,4681 "n_groups": 94682 },4683 "exact_match": {4684 "mean": 0.0,4685 "ci_low": 0.0,4686 "ci_high": 0.0,4687 "n_items": 46,4688 "n_groups": 94689 },4690 "number_recall": {4691 "mean": 0.9919772256728779,4692 "ci_low": 0.9819798034641786,4693 "ci_high": 0.9992860644257704,4694 "n_items": 46,4695 "n_groups": 94696 },4697 "placeholders_exact": {4698 "mean": 1.0,4699 "ci_low": 1.0,4700 "ci_high": 1.0,4701 "n_items": 46,4702 "n_groups": 94703 }4704 },4705 "theory": {4706 "n": 34,4707 "chrf": {4708 "mean": 71.91351438350023,4709 "ci_low": 69.42430033916713,4710 "ci_high": 76.40097933871482,4711 "n_items": 34,4712 "n_groups": 64713 },4714 "edit_sim": {4715 "mean": 0.7047600948811258,4716 "ci_low": 0.6864062952013665,4717 "ci_high": 0.7343489690137238,4718 "n_items": 34,4719 "n_groups": 64720 },4721 "rougeL": {4722 "mean": 0.7087433040625671,4723 "ci_low": 0.6908896960911672,4724 "ci_high": 0.7457560982418168,4725 "n_items": 34,4726 "n_groups": 64727 },4728 "exact_match": {4729 "mean": 0.0,4730 "ci_low": 0.0,4731 "ci_high": 0.0,4732 "n_items": 34,4733 "n_groups": 64734 },4735 "number_recall": {4736 "mean": 0.9931245225362872,4737 "ci_low": 0.9787485242030697,4738 "ci_high": 1.0,4739 "n_items": 34,4740 "n_groups": 64741 },4742 "placeholders_exact": {4743 "mean": 1.0,4744 "ci_low": 1.0,4745 "ci_high": 1.0,4746 "n_items": 34,4747 "n_groups": 64748 }4749 }4750 }4751 },4752 "htr-m1-tiny": {4753 "overall": {4754 "n": 531,4755 "chrf": {4756 "mean": 73.12535052225765,4757 "ci_low": 72.12354094030275,4758 "ci_high": 74.39446291895351,4759 "n_items": 531,4760 "n_groups": 554761 },4762 "edit_sim": {4763 "mean": 0.7206553404812085,4764 "ci_low": 0.711381582283469,4765 "ci_high": 0.7320592941800964,4766 "n_items": 531,4767 "n_groups": 554768 },4769 "rougeL": {4770 "mean": 0.7251674640959713,4771 "ci_low": 0.714454141807672,4772 "ci_high": 0.7389454966256382,4773 "n_items": 531,4774 "n_groups": 554775 },4776 "exact_match": {4777 "mean": 0.0,4778 "ci_low": 0.0,4779 "ci_high": 0.0,4780 "n_items": 531,4781 "n_groups": 554782 },4783 "number_recall": {4784 "mean": 0.9930156211229657,4785 "ci_low": 0.9880682720923706,4786 "ci_high": 0.9964454433598575,4787 "n_items": 531,4788 "n_groups": 554789 },4790 "placeholders_exact": {4791 "mean": 0.9905838041431262,4792 "ci_low": 0.9709299073929556,4793 "ci_high": 1.0,4794 "n_items": 531,4795 "n_groups": 554796 }4797 },4798 "by_variant": {4799 "A": {4800 "n": 267,4801 "chrf": {4802 "mean": 69.61428711832835,4803 "ci_low": 68.55261122549283,4804 "ci_high": 70.85797036098246,4805 "n_items": 267,4806 "n_groups": 534807 },4808 "edit_sim": {4809 "mean": 0.6726474212596033,4810 "ci_low": 0.6604303325182718,4811 "ci_high": 0.6867112031888266,4812 "n_items": 267,4813 "n_groups": 534814 },4815 "rougeL": {4816 "mean": 0.6782589780292214,4817 "ci_low": 0.6661818164754063,4818 "ci_high": 0.6926322866522959,4819 "n_items": 267,4820 "n_groups": 534821 },4822 "exact_match": {4823 "mean": 0.0,4824 "ci_low": 0.0,4825 "ci_high": 0.0,4826 "n_items": 267,4827 "n_groups": 534828 },4829 "number_recall": {4830 "mean": 0.9932631143305302,4831 "ci_low": 0.9862308938513068,4832 "ci_high": 0.9980103261166693,4833 "n_items": 267,4834 "n_groups": 534835 },4836 "placeholders_exact": {4837 "mean": 0.9887640449438202,4838 "ci_low": 0.968623476417594,4839 "ci_high": 1.0,4840 "n_items": 267,4841 "n_groups": 534842 }4843 },4844 "B": {4845 "n": 264,4846 "chrf": {4847 "mean": 76.67631237395887,4848 "ci_low": 75.50158870081158,4849 "ci_high": 78.05007407982232,4850 "n_items": 264,4851 "n_groups": 544852 },4853 "edit_sim": {4854 "mean": 0.7692088042394228,4855 "ci_low": 0.7586046203298914,4856 "ci_high": 0.7822292201904152,4857 "n_items": 264,4858 "n_groups": 544859 },4860 "rougeL": {4861 "mean": 0.7726090011407526,4862 "ci_low": 0.7599808312179095,4863 "ci_high": 0.7877075787518447,4864 "n_items": 264,4865 "n_groups": 544866 },4867 "exact_match": {4868 "mean": 0.0,4869 "ci_low": 0.0,4870 "ci_high": 0.0,4871 "n_items": 264,4872 "n_groups": 544873 },4874 "number_recall": {4875 "mean": 0.9927653154925881,4876 "ci_low": 0.986872919494441,4877 "ci_high": 0.9972116061821946,4878 "n_items": 264,4879 "n_groups": 544880 },4881 "placeholders_exact": {4882 "mean": 0.9924242424242424,4883 "ci_low": 0.9719626168224299,4884 "ci_high": 1.0,4885 "n_items": 264,4886 "n_groups": 544887 }4888 }4889 },4890 "by_discipline": {4891 "biomedicine": {4892 "n": 118,4893 "chrf": {4894 "mean": 74.73972002985818,4895 "ci_low": 72.90505639193749,4896 "ci_high": 76.41307646393996,4897 "n_items": 118,4898 "n_groups": 264899 },4900 "edit_sim": {4901 "mean": 0.7309173801091716,4902 "ci_low": 0.7117185685869413,4903 "ci_high": 0.7470959410749964,4904 "n_items": 118,4905 "n_groups": 264906 },4907 "rougeL": {4908 "mean": 0.7374184171046604,4909 "ci_low": 0.7182512950217006,4910 "ci_high": 0.7545279045105316,4911 "n_items": 118,4912 "n_groups": 264913 },4914 "exact_match": {4915 "mean": 0.0,4916 "ci_low": 0.0,4917 "ci_high": 0.0,4918 "n_items": 118,4919 "n_groups": 264920 },4921 "number_recall": {4922 "mean": 0.9838310465429109,4923 "ci_low": 0.9689139482281076,4924 "ci_high": 0.9957778209109732,4925 "n_items": 118,4926 "n_groups": 264927 },4928 "placeholders_exact": {4929 "mean": 1.0,4930 "ci_low": 1.0,4931 "ci_high": 1.0,4932 "n_items": 118,4933 "n_groups": 264934 }4935 },4936 "computer_science": {4937 "n": 57,4938 "chrf": {4939 "mean": 72.69168630786149,4940 "ci_low": 71.44839958801425,4941 "ci_high": 75.38547420086385,4942 "n_items": 57,4943 "n_groups": 24944 },4945 "edit_sim": {4946 "mean": 0.7269676391428828,4947 "ci_low": 0.7241479501757656,4948 "ci_high": 0.7330769652383036,4949 "n_items": 57,4950 "n_groups": 24951 },4952 "rougeL": {4953 "mean": 0.7203186187867299,4954 "ci_low": 0.710729765399041,4955 "ci_high": 0.7410944677933893,4956 "n_items": 57,4957 "n_groups": 24958 },4959 "exact_match": {4960 "mean": 0.0,4961 "ci_low": 0.0,4962 "ci_high": 0.0,4963 "n_items": 57,4964 "n_groups": 24965 },4966 "number_recall": {4967 "mean": 0.9980239059186429,4968 "ci_low": 0.9937423687423687,4969 "ci_high": 1.0,4970 "n_items": 57,4971 "n_groups": 24972 },4973 "placeholders_exact": {4974 "mean": 1.0,4975 "ci_low": 1.0,4976 "ci_high": 1.0,4977 "n_items": 57,4978 "n_groups": 24979 }4980 },4981 "earth_sciences": {4982 "n": 64,4983 "chrf": {4984 "mean": 71.26033105482159,4985 "ci_low": 68.50544132533204,4986 "ci_high": 73.88889793193427,4987 "n_items": 64,4988 "n_groups": 34989 },4990 "edit_sim": {4991 "mean": 0.7082961227248716,4992 "ci_low": 0.6792758988137217,4993 "ci_high": 0.7251036041957554,4994 "n_items": 64,4995 "n_groups": 34996 },4997 "rougeL": {4998 "mean": 0.7109589603627708,4999 "ci_low": 0.6727931317576227,5000 "ci_high": 0.7393124107869576,5001 "n_items": 64,5002 "n_groups": 35003 },5004 "exact_match": {5005 "mean": 0.0,5006 "ci_low": 0.0,5007 "ci_high": 0.0,5008 "n_items": 64,5009 "n_groups": 35010 },5011 "number_recall": {5012 "mean": 0.9991319444444444,5013 "ci_low": 0.9980842911877394,5014 "ci_high": 1.0,5015 "n_items": 64,5016 "n_groups": 35017 },5018 "placeholders_exact": {5019 "mean": 1.0,5020 "ci_low": 1.0,5021 "ci_high": 1.0,5022 "n_items": 64,5023 "n_groups": 35024 }5025 },5026 "economics": {5027 "n": 64,5028 "chrf": {5029 "mean": 70.99548219343734,5030 "ci_low": 70.99548219343734,5031 "ci_high": 70.99548219343734,5032 "n_items": 64,5033 "n_groups": 15034 },5035 "edit_sim": {5036 "mean": 0.6948846879629946,5037 "ci_low": 0.6948846879629946,5038 "ci_high": 0.6948846879629946,5039 "n_items": 64,5040 "n_groups": 15041 },5042 "rougeL": {5043 "mean": 0.6970029291256983,5044 "ci_low": 0.6970029291256983,5045 "ci_high": 0.6970029291256983,5046 "n_items": 64,5047 "n_groups": 15048 },5049 "exact_match": {5050 "mean": 0.0,5051 "ci_low": 0.0,5052 "ci_high": 0.0,5053 "n_items": 64,5054 "n_groups": 15055 },5056 "number_recall": {5057 "mean": 0.9947916666666667,5058 "ci_low": 0.9947916666666667,5059 "ci_high": 0.9947916666666667,5060 "n_items": 64,5061 "n_groups": 15062 },5063 "placeholders_exact": {5064 "mean": 1.0,5065 "ci_low": 1.0,5066 "ci_high": 1.0,5067 "n_items": 64,5068 "n_groups": 15069 }5070 },5071 "engineering": {5072 "n": 11,5073 "chrf": {5074 "mean": 73.00182525707447,5075 "ci_low": 73.00182525707447,5076 "ci_high": 73.00182525707447,5077 "n_items": 11,5078 "n_groups": 15079 },5080 "edit_sim": {5081 "mean": 0.7058724810328952,5082 "ci_low": 0.7058724810328952,5083 "ci_high": 0.7058724810328952,5084 "n_items": 11,5085 "n_groups": 15086 },5087 "rougeL": {5088 "mean": 0.6857698559722754,5089 "ci_low": 0.6857698559722754,5090 "ci_high": 0.6857698559722754,5091 "n_items": 11,5092 "n_groups": 15093 },5094 "exact_match": {5095 "mean": 0.0,5096 "ci_low": 0.0,5097 "ci_high": 0.0,5098 "n_items": 11,5099 "n_groups": 15100 },5101 "number_recall": {5102 "mean": 1.0,5103 "ci_low": 1.0,5104 "ci_high": 1.0,5105 "n_items": 11,5106 "n_groups": 15107 },5108 "placeholders_exact": {5109 "mean": 1.0,5110 "ci_low": 1.0,5111 "ci_high": 1.0,5112 "n_items": 11,5113 "n_groups": 15114 }5115 },5116 "life_sciences": {5117 "n": 95,5118 "chrf": {5119 "mean": 75.40333127353186,5120 "ci_low": 73.01090046789477,5121 "ci_high": 78.14236044672575,5122 "n_items": 95,5123 "n_groups": 165124 },5125 "edit_sim": {5126 "mean": 0.7455677275717995,5127 "ci_low": 0.7187119622579052,5128 "ci_high": 0.775938955899793,5129 "n_items": 95,5130 "n_groups": 165131 },5132 "rougeL": {5133 "mean": 0.7523754071304339,5134 "ci_low": 0.7223812434513998,5135 "ci_high": 0.7867817514760056,5136 "n_items": 95,5137 "n_groups": 165138 },5139 "exact_match": {5140 "mean": 0.0,5141 "ci_low": 0.0,5142 "ci_high": 0.0,5143 "n_items": 95,5144 "n_groups": 165145 },5146 "number_recall": {5147 "mean": 0.9924641148325358,5148 "ci_low": 0.9793261272874951,5149 "ci_high": 1.0,5150 "n_items": 95,5151 "n_groups": 165152 },5153 "placeholders_exact": {5154 "mean": 0.9578947368421052,5155 "ci_low": 0.8680952380952381,5156 "ci_high": 1.0,5157 "n_items": 95,5158 "n_groups": 165159 }5160 },5161 "social_sciences": {5162 "n": 75,5163 "chrf": {5164 "mean": 72.36495960005266,5165 "ci_low": 66.84415063688046,5166 "ci_high": 75.28041950610128,5167 "n_items": 75,5168 "n_groups": 45169 },5170 "edit_sim": {5171 "mean": 0.7142062126098575,5172 "ci_low": 0.6789247329485951,5173 "ci_high": 0.7323364337196788,5174 "n_items": 75,5175 "n_groups": 45176 },5177 "rougeL": {5178 "mean": 0.7240185289607519,5179 "ci_low": 0.6701342168796752,5180 "ci_high": 0.7495681939370045,5181 "n_items": 75,5182 "n_groups": 45183 },5184 "exact_match": {5185 "mean": 0.0,5186 "ci_low": 0.0,5187 "ci_high": 0.0,5188 "n_items": 75,5189 "n_groups": 45190 },5191 "number_recall": {5192 "mean": 0.9966666666666667,5193 "ci_low": 0.9924242424242424,5194 "ci_high": 1.0,5195 "n_items": 75,5196 "n_groups": 45197 },5198 "placeholders_exact": {5199 "mean": 1.0,5200 "ci_low": 1.0,5201 "ci_high": 1.0,5202 "n_items": 75,5203 "n_groups": 45204 }5205 },5206 "statistics": {5207 "n": 47,5208 "chrf": {5209 "mean": 71.67590377748024,5210 "ci_low": 70.36540144704423,5211 "ci_high": 72.35229207706014,5212 "n_items": 47,5213 "n_groups": 25214 },5215 "edit_sim": {5216 "mean": 0.7025534100223324,5217 "ci_low": 0.6841957744597527,5218 "ci_high": 0.7120283186997929,5219 "n_items": 47,5220 "n_groups": 25221 },5222 "rougeL": {5223 "mean": 0.7140490692204815,5224 "ci_low": 0.71151322240862,5225 "ci_high": 0.7153578933814423,5226 "n_items": 47,5227 "n_groups": 25228 },5229 "exact_match": {5230 "mean": 0.0,5231 "ci_low": 0.0,5232 "ci_high": 0.0,5233 "n_items": 47,5234 "n_groups": 25235 },5236 "number_recall": {5237 "mean": 0.9929078014184397,5238 "ci_low": 0.9892473118279569,5239 "ci_high": 1.0,5240 "n_items": 47,5241 "n_groups": 25242 },5243 "placeholders_exact": {5244 "mean": 0.9787234042553191,5245 "ci_low": 0.9375,5246 "ci_high": 1.0,5247 "n_items": 47,5248 "n_groups": 25249 }5250 }5251 },5252 "by_era": {5253 "1980-1999": {5254 "n": 5,5255 "chrf": {5256 "mean": 76.4268092948189,5257 "ci_low": 74.68958035598935,5258 "ci_high": 79.0326527030632,5259 "n_items": 5,5260 "n_groups": 25261 },5262 "edit_sim": {5263 "mean": 0.7870203494807141,5264 "ci_low": 0.7784493844653988,5265 "ci_high": 0.792734326157591,5266 "n_items": 5,5267 "n_groups": 25268 },5269 "rougeL": {5270 "mean": 0.7780329652419556,5271 "ci_low": 0.7732099691589562,5272 "ci_high": 0.7852674593664547,5273 "n_items": 5,5274 "n_groups": 25275 },5276 "exact_match": {5277 "mean": 0.0,5278 "ci_low": 0.0,5279 "ci_high": 0.0,5280 "n_items": 5,5281 "n_groups": 25282 },5283 "number_recall": {5284 "mean": 1.0,5285 "ci_low": 1.0,5286 "ci_high": 1.0,5287 "n_items": 5,5288 "n_groups": 25289 },5290 "placeholders_exact": {5291 "mean": 1.0,5292 "ci_low": 1.0,5293 "ci_high": 1.0,5294 "n_items": 5,5295 "n_groups": 25296 }5297 },5298 "2000-2009": {5299 "n": 58,5300 "chrf": {5301 "mean": 72.65653827496655,5302 "ci_low": 70.6044485987521,5303 "ci_high": 75.5833972697089,5304 "n_items": 58,5305 "n_groups": 75306 },5307 "edit_sim": {5308 "mean": 0.7116058654430788,5309 "ci_low": 0.692442900879138,5310 "ci_high": 0.7409560509406155,5311 "n_items": 58,5312 "n_groups": 75313 },5314 "rougeL": {5315 "mean": 0.7159704558768314,5316 "ci_low": 0.6935590124217201,5317 "ci_high": 0.7469756265768411,5318 "n_items": 58,5319 "n_groups": 75320 },5321 "exact_match": {5322 "mean": 0.0,5323 "ci_low": 0.0,5324 "ci_high": 0.0,5325 "n_items": 58,5326 "n_groups": 75327 },5328 "number_recall": {5329 "mean": 1.0,5330 "ci_low": 1.0,5331 "ci_high": 1.0,5332 "n_items": 58,5333 "n_groups": 75334 },5335 "placeholders_exact": {5336 "mean": 0.9827586206896551,5337 "ci_low": 0.9599864864864864,5338 "ci_high": 1.0,5339 "n_items": 58,5340 "n_groups": 75341 }5342 },5343 "2010-2017": {5344 "n": 468,5345 "chrf": {5346 "mean": 73.14817918995011,5347 "ci_low": 71.98216477528155,5348 "ci_high": 74.54227957757199,5349 "n_items": 468,5350 "n_groups": 465351 },5352 "edit_sim": {5353 "mean": 0.7210678287444863,5354 "ci_low": 0.7106162701573995,5355 "ci_high": 0.7336047648233214,5356 "n_items": 468,5357 "n_groups": 465358 },5359 "rougeL": {5360 "mean": 0.7257424618972111,5361 "ci_low": 0.7132750487108179,5362 "ci_high": 0.7409708536873924,5363 "n_items": 468,5364 "n_groups": 465365 },5366 "exact_match": {5367 "mean": 0.0,5368 "ci_low": 0.0,5369 "ci_high": 0.0,5370 "n_items": 468,5371 "n_groups": 465372 },5373 "number_recall": {5374 "mean": 0.9920754162741342,5375 "ci_low": 0.9865389226945248,5376 "ci_high": 0.9958797985231276,5377 "n_items": 468,5378 "n_groups": 465379 },5380 "placeholders_exact": {5381 "mean": 0.9914529914529915,5382 "ci_low": 0.9683152600974383,5383 "ci_high": 1.0,5384 "n_items": 468,5385 "n_groups": 465386 }5387 }5388 },5389 "by_role": {5390 "abstract": {5391 "n": 55,5392 "chrf": {5393 "mean": 75.77548690151383,5394 "ci_low": 73.81865599834184,5395 "ci_high": 77.76889130370255,5396 "n_items": 55,5397 "n_groups": 155398 },5399 "edit_sim": {5400 "mean": 0.7493117099905477,5401 "ci_low": 0.7292026131683195,5402 "ci_high": 0.7673302621227748,5403 "n_items": 55,5404 "n_groups": 155405 },5406 "rougeL": {5407 "mean": 0.7413210548342106,5408 "ci_low": 0.7196226633376515,5409 "ci_high": 0.7648831102734283,5410 "n_items": 55,5411 "n_groups": 155412 },5413 "exact_match": {5414 "mean": 0.0,5415 "ci_low": 0.0,5416 "ci_high": 0.0,5417 "n_items": 55,5418 "n_groups": 155419 },5420 "number_recall": {5421 "mean": 1.0,5422 "ci_low": 1.0,5423 "ci_high": 1.0,5424 "n_items": 55,5425 "n_groups": 155426 },5427 "placeholders_exact": {5428 "mean": 0.9818181818181818,5429 "ci_low": 0.9444444444444444,5430 "ci_high": 1.0,5431 "n_items": 55,5432 "n_groups": 155433 }5434 },5435 "background": {5436 "n": 36,5437 "chrf": {5438 "mean": 74.58190730928091,5439 "ci_low": 71.71159697892004,5440 "ci_high": 77.06791572022584,5441 "n_items": 36,5442 "n_groups": 75443 },5444 "edit_sim": {5445 "mean": 0.7386957789810656,5446 "ci_low": 0.7108241188990568,5447 "ci_high": 0.7655020275707881,5448 "n_items": 36,5449 "n_groups": 75450 },5451 "rougeL": {5452 "mean": 0.7438350959099528,5453 "ci_low": 0.7243985543861418,5454 "ci_high": 0.7613698412533179,5455 "n_items": 36,5456 "n_groups": 75457 },5458 "exact_match": {5459 "mean": 0.0,5460 "ci_low": 0.0,5461 "ci_high": 0.0,5462 "n_items": 36,5463 "n_groups": 75464 },5465 "number_recall": {5466 "mean": 0.9984567901234568,5467 "ci_low": 0.9953703703703705,5468 "ci_high": 1.0,5469 "n_items": 36,5470 "n_groups": 75471 },5472 "placeholders_exact": {5473 "mean": 1.0,5474 "ci_low": 1.0,5475 "ci_high": 1.0,5476 "n_items": 36,5477 "n_groups": 75478 }5479 },5480 "conclusion": {5481 "n": 36,5482 "chrf": {5483 "mean": 70.71783125722719,5484 "ci_low": 67.46713170277546,5485 "ci_high": 73.69159930196601,5486 "n_items": 36,5487 "n_groups": 95488 },5489 "edit_sim": {5490 "mean": 0.7033151359255565,5491 "ci_low": 0.667755173138218,5492 "ci_high": 0.740279844368953,5493 "n_items": 36,5494 "n_groups": 95495 },5496 "rougeL": {5497 "mean": 0.696957260266139,5498 "ci_low": 0.6550330802481719,5499 "ci_high": 0.7356337908168521,5500 "n_items": 36,5501 "n_groups": 95502 },5503 "exact_match": {5504 "mean": 0.0,5505 "ci_low": 0.0,5506 "ci_high": 0.0,5507 "n_items": 36,5508 "n_groups": 95509 },5510 "number_recall": {5511 "mean": 0.9861111111111112,5512 "ci_low": 0.9583333333333334,5513 "ci_high": 1.0,5514 "n_items": 36,5515 "n_groups": 95516 },5517 "placeholders_exact": {5518 "mean": 1.0,5519 "ci_low": 1.0,5520 "ci_high": 1.0,5521 "n_items": 36,5522 "n_groups": 95523 }5524 },5525 "data": {5526 "n": 41,5527 "chrf": {5528 "mean": 76.27310630166997,5529 "ci_low": 73.30921315979779,5530 "ci_high": 79.22941278127156,5531 "n_items": 41,5532 "n_groups": 105533 },5534 "edit_sim": {5535 "mean": 0.724427052579582,5536 "ci_low": 0.6836789071510901,5537 "ci_high": 0.772278683840537,5538 "n_items": 41,5539 "n_groups": 105540 },5541 "rougeL": {5542 "mean": 0.7539978628152125,5543 "ci_low": 0.718023924976582,5544 "ci_high": 0.7924888848629312,5545 "n_items": 41,5546 "n_groups": 105547 },5548 "exact_match": {5549 "mean": 0.0,5550 "ci_low": 0.0,5551 "ci_high": 0.0,5552 "n_items": 41,5553 "n_groups": 105554 },5555 "number_recall": {5556 "mean": 0.9901969981238274,5557 "ci_low": 0.9766986434108528,5558 "ci_high": 1.0,5559 "n_items": 41,5560 "n_groups": 105561 },5562 "placeholders_exact": {5563 "mean": 1.0,5564 "ci_low": 1.0,5565 "ci_high": 1.0,5566 "n_items": 41,5567 "n_groups": 105568 }5569 },5570 "discussion": {5571 "n": 69,5572 "chrf": {5573 "mean": 73.37660812474117,5574 "ci_low": 71.32262270728646,5575 "ci_high": 75.58608493197872,5576 "n_items": 69,5577 "n_groups": 145578 },5579 "edit_sim": {5580 "mean": 0.7290402153183874,5581 "ci_low": 0.7037780531829965,5582 "ci_high": 0.754451676065307,5583 "n_items": 69,5584 "n_groups": 145585 },5586 "rougeL": {5587 "mean": 0.7318847606178903,5588 "ci_low": 0.7034861534298296,5589 "ci_high": 0.7638329721519204,5590 "n_items": 69,5591 "n_groups": 145592 },5593 "exact_match": {5594 "mean": 0.0,5595 "ci_low": 0.0,5596 "ci_high": 0.0,5597 "n_items": 69,5598 "n_groups": 145599 },5600 "number_recall": {5601 "mean": 1.0,5602 "ci_low": 1.0,5603 "ci_high": 1.0,5604 "n_items": 69,5605 "n_groups": 145606 },5607 "placeholders_exact": {5608 "mean": 1.0,5609 "ci_low": 1.0,5610 "ci_high": 1.0,5611 "n_items": 69,5612 "n_groups": 145613 }5614 },5615 "introduction": {5616 "n": 63,5617 "chrf": {5618 "mean": 72.31297473541693,5619 "ci_low": 70.15850950373827,5620 "ci_high": 74.54014509091611,5621 "n_items": 63,5622 "n_groups": 145623 },5624 "edit_sim": {5625 "mean": 0.706127861887135,5626 "ci_low": 0.68546722057182,5627 "ci_high": 0.7258281283558744,5628 "n_items": 63,5629 "n_groups": 145630 },5631 "rougeL": {5632 "mean": 0.7135783290359438,5633 "ci_low": 0.6947114626874816,5634 "ci_high": 0.732181659206742,5635 "n_items": 63,5636 "n_groups": 145637 },5638 "exact_match": {5639 "mean": 0.0,5640 "ci_low": 0.0,5641 "ci_high": 0.0,5642 "n_items": 63,5643 "n_groups": 145644 },5645 "number_recall": {5646 "mean": 0.9911816578483245,5647 "ci_low": 0.9717392363140464,5648 "ci_high": 1.0,5649 "n_items": 63,5650 "n_groups": 145651 },5652 "placeholders_exact": {5653 "mean": 1.0,5654 "ci_low": 1.0,5655 "ci_high": 1.0,5656 "n_items": 63,5657 "n_groups": 145658 }5659 },5660 "limitations": {5661 "n": 28,5662 "chrf": {5663 "mean": 72.71910934862,5664 "ci_low": 68.94803190673164,5665 "ci_high": 75.5128415665883,5666 "n_items": 28,5667 "n_groups": 45668 },5669 "edit_sim": {5670 "mean": 0.7254198204652632,5671 "ci_low": 0.7056976314195791,5672 "ci_high": 0.7445339271149379,5673 "n_items": 28,5674 "n_groups": 45675 },5676 "rougeL": {5677 "mean": 0.7207418143567754,5678 "ci_low": 0.6837983195398524,5679 "ci_high": 0.749030888078308,5680 "n_items": 28,5681 "n_groups": 45682 },5683 "exact_match": {5684 "mean": 0.0,5685 "ci_low": 0.0,5686 "ci_high": 0.0,5687 "n_items": 28,5688 "n_groups": 45689 },5690 "number_recall": {5691 "mean": 1.0,5692 "ci_low": 1.0,5693 "ci_high": 1.0,5694 "n_items": 28,5695 "n_groups": 45696 },5697 "placeholders_exact": {5698 "mean": 1.0,5699 "ci_low": 1.0,5700 "ci_high": 1.0,5701 "n_items": 28,5702 "n_groups": 45703 }5704 },5705 "methods": {5706 "n": 67,5707 "chrf": {5708 "mean": 72.61498130300221,5709 "ci_low": 69.91114374239261,5710 "ci_high": 75.58069867903399,5711 "n_items": 67,5712 "n_groups": 125713 },5714 "edit_sim": {5715 "mean": 0.7215884425335052,5716 "ci_low": 0.6969078762408635,5717 "ci_high": 0.7494987902527941,5718 "n_items": 67,5719 "n_groups": 125720 },5721 "rougeL": {5722 "mean": 0.7312851028982607,5723 "ci_low": 0.7043517277093472,5724 "ci_high": 0.761414768017181,5725 "n_items": 67,5726 "n_groups": 125727 },5728 "exact_match": {5729 "mean": 0.0,5730 "ci_low": 0.0,5731 "ci_high": 0.0,5732 "n_items": 67,5733 "n_groups": 125734 },5735 "number_recall": {5736 "mean": 0.9838308457711443,5737 "ci_low": 0.9623271517187904,5738 "ci_high": 1.0,5739 "n_items": 67,5740 "n_groups": 125741 },5742 "placeholders_exact": {5743 "mean": 1.0,5744 "ci_low": 1.0,5745 "ci_high": 1.0,5746 "n_items": 67,5747 "n_groups": 125748 }5749 },5750 "other": {5751 "n": 52,5752 "chrf": {5753 "mean": 72.2147321636767,5754 "ci_low": 68.15374653357293,5755 "ci_high": 76.58569082790612,5756 "n_items": 52,5757 "n_groups": 95758 },5759 "edit_sim": {5760 "mean": 0.7149743343990617,5761 "ci_low": 0.6790335578640159,5762 "ci_high": 0.7607727524947069,5763 "n_items": 52,5764 "n_groups": 95765 },5766 "rougeL": {5767 "mean": 0.7133311826851328,5768 "ci_low": 0.6678628158419619,5769 "ci_high": 0.770394297927178,5770 "n_items": 52,5771 "n_groups": 95772 },5773 "exact_match": {5774 "mean": 0.0,5775 "ci_low": 0.0,5776 "ci_high": 0.0,5777 "n_items": 52,5778 "n_groups": 95779 },5780 "number_recall": {5781 "mean": 0.9961538461538461,5782 "ci_low": 0.9863636363636364,5783 "ci_high": 1.0,5784 "n_items": 52,5785 "n_groups": 95786 },5787 "placeholders_exact": {5788 "mean": 0.9230769230769231,5789 "ci_low": 0.7735849056603774,5790 "ci_high": 1.0,5791 "n_items": 52,5792 "n_groups": 95793 }5794 },5795 "related_work": {5796 "n": 4,5797 "chrf": {5798 "mean": 80.10920024591131,5799 "ci_low": 80.10920024591131,5800 "ci_high": 80.10920024591131,5801 "n_items": 4,5802 "n_groups": 15803 },5804 "edit_sim": {5805 "mean": 0.7983951943690367,5806 "ci_low": 0.7983951943690367,5807 "ci_high": 0.7983951943690367,5808 "n_items": 4,5809 "n_groups": 15810 },5811 "rougeL": {5812 "mean": 0.7948742211641704,5813 "ci_low": 0.7948742211641704,5814 "ci_high": 0.7948742211641704,5815 "n_items": 4,5816 "n_groups": 15817 },5818 "exact_match": {5819 "mean": 0.0,5820 "ci_low": 0.0,5821 "ci_high": 0.0,5822 "n_items": 4,5823 "n_groups": 15824 },5825 "number_recall": {5826 "mean": 1.0,5827 "ci_low": 1.0,5828 "ci_high": 1.0,5829 "n_items": 4,5830 "n_groups": 15831 },5832 "placeholders_exact": {5833 "mean": 1.0,5834 "ci_low": 1.0,5835 "ci_high": 1.0,5836 "n_items": 4,5837 "n_groups": 15838 }5839 },5840 "results": {5841 "n": 46,5842 "chrf": {5843 "mean": 70.76712698401728,5844 "ci_low": 68.24068744463713,5845 "ci_high": 73.1842286333214,5846 "n_items": 46,5847 "n_groups": 95848 },5849 "edit_sim": {5850 "mean": 0.6955760849208127,5851 "ci_low": 0.675153686524929,5852 "ci_high": 0.7193854630294887,5853 "n_items": 46,5854 "n_groups": 95855 },5856 "rougeL": {5857 "mean": 0.7058715721097301,5858 "ci_low": 0.6900809963371402,5859 "ci_high": 0.722822385019877,5860 "n_items": 46,5861 "n_groups": 95862 },5863 "exact_match": {5864 "mean": 0.0,5865 "ci_low": 0.0,5866 "ci_high": 0.0,5867 "n_items": 46,5868 "n_groups": 95869 },5870 "number_recall": {5871 "mean": 0.9883540372670809,5872 "ci_low": 0.9734842848124097,5873 "ci_high": 0.9992860644257704,5874 "n_items": 46,5875 "n_groups": 95876 },5877 "placeholders_exact": {5878 "mean": 1.0,5879 "ci_low": 1.0,5880 "ci_high": 1.0,5881 "n_items": 46,5882 "n_groups": 95883 }5884 },5885 "theory": {5886 "n": 34,5887 "chrf": {5888 "mean": 72.14672082977194,5889 "ci_low": 69.67646091593795,5890 "ci_high": 76.58641439284092,5891 "n_items": 34,5892 "n_groups": 65893 },5894 "edit_sim": {5895 "mean": 0.7066230236007401,5896 "ci_low": 0.6878495506636195,5897 "ci_high": 0.7409973586136995,5898 "n_items": 34,5899 "n_groups": 65900 },5901 "rougeL": {5902 "mean": 0.7098135768209699,5903 "ci_low": 0.6910307817805441,5904 "ci_high": 0.7467657177384084,5905 "n_items": 34,5906 "n_groups": 65907 },5908 "exact_match": {5909 "mean": 0.0,5910 "ci_low": 0.0,5911 "ci_high": 0.0,5912 "n_items": 34,5913 "n_groups": 65914 },5915 "number_recall": {5916 "mean": 0.9889228418640182,5917 "ci_low": 0.9642857142857143,5918 "ci_high": 1.0,5919 "n_items": 34,5920 "n_groups": 65921 },5922 "placeholders_exact": {5923 "mean": 1.0,5924 "ci_low": 1.0,5925 "ci_high": 1.0,5926 "n_items": 34,5927 "n_groups": 65928 }5929 }5930 }5931 },5932 "htr-m3tokenonly-tiny": {5933 "overall": {5934 "n": 531,5935 "chrf": {5936 "mean": 73.21719312946972,5937 "ci_low": 72.24337404355887,5938 "ci_high": 74.48780292383653,5939 "n_items": 531,5940 "n_groups": 555941 },5942 "edit_sim": {5943 "mean": 0.7217785646676331,5944 "ci_low": 0.7125883555563,5945 "ci_high": 0.7333373089686066,5946 "n_items": 531,5947 "n_groups": 555948 },5949 "rougeL": {5950 "mean": 0.7273080524868685,5951 "ci_low": 0.716336115833156,5952 "ci_high": 0.7412090338952806,5953 "n_items": 531,5954 "n_groups": 555955 },5956 "exact_match": {5957 "mean": 0.0,5958 "ci_low": 0.0,5959 "ci_high": 0.0,5960 "n_items": 531,5961 "n_groups": 555962 },5963 "number_recall": {5964 "mean": 0.9920561790826435,5965 "ci_low": 0.9870066685237286,5966 "ci_high": 0.9964565978457103,5967 "n_items": 531,5968 "n_groups": 555969 },5970 "placeholders_exact": {5971 "mean": 0.9943502824858758,5972 "ci_low": 0.9840953144767758,5973 "ci_high": 1.0,5974 "n_items": 531,5975 "n_groups": 555976 }5977 },5978 "by_variant": {5979 "A": {5980 "n": 267,5981 "chrf": {5982 "mean": 69.31873089373777,5983 "ci_low": 68.30290565428311,5984 "ci_high": 70.52939340634799,5985 "n_items": 267,5986 "n_groups": 535987 },5988 "edit_sim": {5989 "mean": 0.6701463799519356,5990 "ci_low": 0.6576087633005333,5991 "ci_high": 0.68461907335233,5992 "n_items": 267,5993 "n_groups": 535994 },5995 "rougeL": {5996 "mean": 0.6766538621852023,5997 "ci_low": 0.6643806935246634,5998 "ci_high": 0.6914150138265406,5999 "n_items": 267,6000 "n_groups": 536001 },6002 "exact_match": {6003 "mean": 0.0,6004 "ci_low": 0.0,6005 "ci_high": 0.0,6006 "n_items": 267,6007 "n_groups": 536008 },6009 "number_recall": {6010 "mean": 0.9906271452664119,6011 "ci_low": 0.9824418432617177,6012 "ci_high": 0.9975990900539092,6013 "n_items": 267,6014 "n_groups": 536015 },6016 "placeholders_exact": {6017 "mean": 0.9962546816479401,6018 "ci_low": 0.9876543209876543,6019 "ci_high": 1.0,6020 "n_items": 267,6021 "n_groups": 536022 }6023 },6024 "B": {6025 "n": 264,6026 "chrf": {6027 "mean": 77.15995607242594,6028 "ci_low": 75.92512083560898,6029 "ci_high": 78.60038174369251,6030 "n_items": 264,6031 "n_groups": 546032 },6033 "edit_sim": {6034 "mean": 0.7739974787550998,6035 "ci_low": 0.7630188014895963,6036 "ci_high": 0.787028651044701,6037 "n_items": 264,6038 "n_groups": 546039 },6040 "rougeL": {6041 "mean": 0.778537858587417,6042 "ci_low": 0.7648125037409937,6043 "ci_high": 0.7947092847833049,6044 "n_items": 264,6045 "n_groups": 546046 },6047 "exact_match": {6048 "mean": 0.0,6049 "ci_low": 0.0,6050 "ci_high": 0.0,6051 "n_items": 264,6052 "n_groups": 546053 },6054 "number_recall": {6055 "mean": 0.993501451919514,6056 "ci_low": 0.9860870155305251,6057 "ci_high": 0.9980167990710141,6058 "n_items": 264,6059 "n_groups": 546060 },6061 "placeholders_exact": {6062 "mean": 0.9924242424242424,6063 "ci_low": 0.9719626168224299,6064 "ci_high": 1.0,6065 "n_items": 264,6066 "n_groups": 546067 }6068 }6069 },6070 "by_discipline": {6071 "biomedicine": {6072 "n": 118,6073 "chrf": {6074 "mean": 75.06046770643032,6075 "ci_low": 73.44718553745554,6076 "ci_high": 76.55607953728597,6077 "n_items": 118,6078 "n_groups": 266079 },6080 "edit_sim": {6081 "mean": 0.7312934440077115,6082 "ci_low": 0.7126170304631781,6083 "ci_high": 0.7472817103952828,6084 "n_items": 118,6085 "n_groups": 266086 },6087 "rougeL": {6088 "mean": 0.7397496485164147,6089 "ci_low": 0.7221049599175798,6090 "ci_high": 0.7553443493710298,6091 "n_items": 118,6092 "n_groups": 266093 },6094 "exact_match": {6095 "mean": 0.0,6096 "ci_low": 0.0,6097 "ci_high": 0.0,6098 "n_items": 118,6099 "n_groups": 266100 },6101 "number_recall": {6102 "mean": 0.9925376647834274,6103 "ci_low": 0.9803384360404376,6104 "ci_high": 1.0,6105 "n_items": 118,6106 "n_groups": 266107 },6108 "placeholders_exact": {6109 "mean": 1.0,6110 "ci_low": 1.0,6111 "ci_high": 1.0,6112 "n_items": 118,6113 "n_groups": 266114 }6115 },6116 "computer_science": {6117 "n": 57,6118 "chrf": {6119 "mean": 72.18234291305137,6120 "ci_low": 70.7939777115421,6121 "ci_high": 75.19046751632149,6122 "n_items": 57,6123 "n_groups": 26124 },6125 "edit_sim": {6126 "mean": 0.7253392259047475,6127 "ci_low": 0.7215030168412516,6128 "ci_high": 0.7336510122089885,6129 "n_items": 57,6130 "n_groups": 26131 },6132 "rougeL": {6133 "mean": 0.7192087741912002,6134 "ci_low": 0.7067855485908207,6135 "ci_high": 0.746125762992023,6136 "n_items": 57,6137 "n_groups": 26138 },6139 "exact_match": {6140 "mean": 0.0,6141 "ci_low": 0.0,6142 "ci_high": 0.0,6143 "n_items": 57,6144 "n_groups": 26145 },6146 "number_recall": {6147 "mean": 0.9805764411027568,6148 "ci_low": 0.9743589743589743,6149 "ci_high": 0.9940476190476191,6150 "n_items": 57,6151 "n_groups": 26152 },6153 "placeholders_exact": {6154 "mean": 1.0,6155 "ci_low": 1.0,6156 "ci_high": 1.0,6157 "n_items": 57,6158 "n_groups": 26159 }6160 },6161 "earth_sciences": {6162 "n": 64,6163 "chrf": {6164 "mean": 70.72547024718708,6165 "ci_low": 69.13154619903162,6166 "ci_high": 72.58295470588358,6167 "n_items": 64,6168 "n_groups": 36169 },6170 "edit_sim": {6171 "mean": 0.7020784072967785,6172 "ci_low": 0.6868864748945948,6173 "ci_high": 0.7082980494422147,6174 "n_items": 64,6175 "n_groups": 36176 },6177 "rougeL": {6178 "mean": 0.7076236969107887,6179 "ci_low": 0.6750925114620051,6180 "ci_high": 0.7303906473231885,6181 "n_items": 64,6182 "n_groups": 36183 },6184 "exact_match": {6185 "mean": 0.0,6186 "ci_low": 0.0,6187 "ci_high": 0.0,6188 "n_items": 64,6189 "n_groups": 36190 },6191 "number_recall": {6192 "mean": 0.9912828947368422,6193 "ci_low": 0.9807622504537205,6194 "ci_high": 1.0,6195 "n_items": 64,6196 "n_groups": 36197 },6198 "placeholders_exact": {6199 "mean": 0.984375,6200 "ci_low": 0.9655172413793104,6201 "ci_high": 1.0,6202 "n_items": 64,6203 "n_groups": 36204 }6205 },6206 "economics": {6207 "n": 64,6208 "chrf": {6209 "mean": 71.34304543406788,6210 "ci_low": 71.34304543406788,6211 "ci_high": 71.34304543406788,6212 "n_items": 64,6213 "n_groups": 16214 },6215 "edit_sim": {6216 "mean": 0.6986731948422643,6217 "ci_low": 0.6986731948422643,6218 "ci_high": 0.6986731948422643,6219 "n_items": 64,6220 "n_groups": 16221 },6222 "rougeL": {6223 "mean": 0.7000810549392348,6224 "ci_low": 0.7000810549392348,6225 "ci_high": 0.7000810549392348,6226 "n_items": 64,6227 "n_groups": 16228 },6229 "exact_match": {6230 "mean": 0.0,6231 "ci_low": 0.0,6232 "ci_high": 0.0,6233 "n_items": 64,6234 "n_groups": 16235 },6236 "number_recall": {6237 "mean": 0.9973958333333334,6238 "ci_low": 0.9973958333333334,6239 "ci_high": 0.9973958333333334,6240 "n_items": 64,6241 "n_groups": 16242 },6243 "placeholders_exact": {6244 "mean": 1.0,6245 "ci_low": 1.0,6246 "ci_high": 1.0,6247 "n_items": 64,6248 "n_groups": 16249 }6250 },6251 "engineering": {6252 "n": 11,6253 "chrf": {6254 "mean": 73.1105388475115,6255 "ci_low": 73.1105388475115,6256 "ci_high": 73.1105388475115,6257 "n_items": 11,6258 "n_groups": 16259 },6260 "edit_sim": {6261 "mean": 0.7090890276723439,6262 "ci_low": 0.7090890276723439,6263 "ci_high": 0.7090890276723439,6264 "n_items": 11,6265 "n_groups": 16266 },6267 "rougeL": {6268 "mean": 0.6887114948917085,6269 "ci_low": 0.6887114948917085,6270 "ci_high": 0.6887114948917085,6271 "n_items": 11,6272 "n_groups": 16273 },6274 "exact_match": {6275 "mean": 0.0,6276 "ci_low": 0.0,6277 "ci_high": 0.0,6278 "n_items": 11,6279 "n_groups": 16280 },6281 "number_recall": {6282 "mean": 1.0,6283 "ci_low": 1.0,6284 "ci_high": 1.0,6285 "n_items": 11,6286 "n_groups": 16287 },6288 "placeholders_exact": {6289 "mean": 1.0,6290 "ci_low": 1.0,6291 "ci_high": 1.0,6292 "n_items": 11,6293 "n_groups": 16294 }6295 },6296 "life_sciences": {6297 "n": 95,6298 "chrf": {6299 "mean": 75.40968986275965,6300 "ci_low": 72.71317186708367,6301 "ci_high": 78.50605364967743,6302 "n_items": 95,6303 "n_groups": 166304 },6305 "edit_sim": {6306 "mean": 0.7467222990267455,6307 "ci_low": 0.715777310804997,6308 "ci_high": 0.7803931585161825,6309 "n_items": 95,6310 "n_groups": 166311 },6312 "rougeL": {6313 "mean": 0.7526291752636829,6314 "ci_low": 0.7192645367832315,6315 "ci_high": 0.7886259576791249,6316 "n_items": 95,6317 "n_groups": 166318 },6319 "exact_match": {6320 "mean": 0.0,6321 "ci_low": 0.0,6322 "ci_high": 0.0,6323 "n_items": 95,6324 "n_groups": 166325 },6326 "number_recall": {6327 "mean": 0.9950956937799043,6328 "ci_low": 0.9869316654447702,6329 "ci_high": 1.0,6330 "n_items": 95,6331 "n_groups": 166332 },6333 "placeholders_exact": {6334 "mean": 0.9789473684210527,6335 "ci_low": 0.934047619047619,6336 "ci_high": 1.0,6337 "n_items": 95,6338 "n_groups": 166339 }6340 },6341 "social_sciences": {6342 "n": 75,6343 "chrf": {6344 "mean": 72.68751813436926,6345 "ci_low": 67.44906843694818,6346 "ci_high": 75.26055972750763,6347 "n_items": 75,6348 "n_groups": 46349 },6350 "edit_sim": {6351 "mean": 0.7178054805533542,6352 "ci_low": 0.6822174782398359,6353 "ci_high": 0.7351803036385217,6354 "n_items": 75,6355 "n_groups": 46356 },6357 "rougeL": {6358 "mean": 0.7269264469529572,6359 "ci_low": 0.6716086845292473,6360 "ci_high": 0.7495949251075696,6361 "n_items": 75,6362 "n_groups": 46363 },6364 "exact_match": {6365 "mean": 0.0,6366 "ci_low": 0.0,6367 "ci_high": 0.0,6368 "n_items": 75,6369 "n_groups": 46370 },6371 "number_recall": {6372 "mean": 0.9911111111111113,6373 "ci_low": 0.9666666666666666,6374 "ci_high": 1.0,6375 "n_items": 75,6376 "n_groups": 46377 },6378 "placeholders_exact": {6379 "mean": 1.0,6380 "ci_low": 1.0,6381 "ci_high": 1.0,6382 "n_items": 75,6383 "n_groups": 46384 }6385 },6386 "statistics": {6387 "n": 47,6388 "chrf": {6389 "mean": 72.22798911453017,6390 "ci_low": 71.4779306007041,6391 "ci_high": 72.61511608940816,6392 "n_items": 47,6393 "n_groups": 26394 },6395 "edit_sim": {6396 "mean": 0.7107520059296963,6397 "ci_low": 0.6978528302413269,6398 "ci_high": 0.7174096449946612,6399 "n_items": 47,6400 "n_groups": 26401 },6402 "rougeL": {6403 "mean": 0.7282347124033993,6404 "ci_low": 0.7252916558378666,6405 "ci_high": 0.733936884499119,6406 "n_items": 47,6407 "n_groups": 26408 },6409 "exact_match": {6410 "mean": 0.0,6411 "ci_low": 0.0,6412 "ci_high": 0.0,6413 "n_items": 47,6414 "n_groups": 26415 },6416 "number_recall": {6417 "mean": 0.9920567375886524,6418 "ci_low": 0.9879569892473118,6419 "ci_high": 1.0,6420 "n_items": 47,6421 "n_groups": 26422 },6423 "placeholders_exact": {6424 "mean": 1.0,6425 "ci_low": 1.0,6426 "ci_high": 1.0,6427 "n_items": 47,6428 "n_groups": 26429 }6430 }6431 },6432 "by_era": {6433 "1980-1999": {6434 "n": 5,6435 "chrf": {6436 "mean": 75.2766472295251,6437 "ci_low": 72.9317077821582,6438 "ci_high": 78.79405640057544,6439 "n_items": 5,6440 "n_groups": 26441 },6442 "edit_sim": {6443 "mean": 0.7847297888781647,6444 "ci_low": 0.7809553466644218,6445 "ci_high": 0.7903914521987789,6446 "n_items": 5,6447 "n_groups": 26448 },6449 "rougeL": {6450 "mean": 0.7748709408162266,6451 "ci_low": 0.7646650645686327,6452 "ci_high": 0.7901797551876175,6453 "n_items": 5,6454 "n_groups": 26455 },6456 "exact_match": {6457 "mean": 0.0,6458 "ci_low": 0.0,6459 "ci_high": 0.0,6460 "n_items": 5,6461 "n_groups": 26462 },6463 "number_recall": {6464 "mean": 1.0,6465 "ci_low": 1.0,6466 "ci_high": 1.0,6467 "n_items": 5,6468 "n_groups": 26469 },6470 "placeholders_exact": {6471 "mean": 1.0,6472 "ci_low": 1.0,6473 "ci_high": 1.0,6474 "n_items": 5,6475 "n_groups": 26476 }6477 },6478 "2000-2009": {6479 "n": 58,6480 "chrf": {6481 "mean": 73.2232946274471,6482 "ci_low": 71.29795994790176,6483 "ci_high": 76.2093632465059,6484 "n_items": 58,6485 "n_groups": 76486 },6487 "edit_sim": {6488 "mean": 0.7169503434249256,6489 "ci_low": 0.698718585125416,6490 "ci_high": 0.7447361014705131,6491 "n_items": 58,6492 "n_groups": 76493 },6494 "rougeL": {6495 "mean": 0.7260635810779001,6496 "ci_low": 0.7004521191845002,6497 "ci_high": 0.758950188683631,6498 "n_items": 58,6499 "n_groups": 76500 },6501 "exact_match": {6502 "mean": 0.0,6503 "ci_low": 0.0,6504 "ci_high": 0.0,6505 "n_items": 58,6506 "n_groups": 76507 },6508 "number_recall": {6509 "mean": 1.0,6510 "ci_low": 1.0,6511 "ci_high": 1.0,6512 "n_items": 58,6513 "n_groups": 76514 },6515 "placeholders_exact": {6516 "mean": 1.0,6517 "ci_low": 1.0,6518 "ci_high": 1.0,6519 "n_items": 58,6520 "n_groups": 76521 }6522 },6523 "2010-2017": {6524 "n": 468,6525 "chrf": {6526 "mean": 73.1944342461728,6527 "ci_low": 72.06693795472991,6528 "ci_high": 74.6025451915939,6529 "n_items": 468,6530 "n_groups": 466531 },6532 "edit_sim": {6533 "mean": 0.7217043781527279,6534 "ci_low": 0.7114707417036709,6535 "ci_high": 0.7340170897779908,6536 "n_items": 468,6537 "n_groups": 466538 },6539 "rougeL": {6540 "mean": 0.726954131333179,6541 "ci_low": 0.7143751972468844,6542 "ci_high": 0.7418906751348939,6543 "n_items": 468,6544 "n_groups": 466545 },6546 "exact_match": {6547 "mean": 0.0,6548 "ci_low": 0.0,6549 "ci_high": 0.0,6550 "n_items": 468,6551 "n_groups": 466552 },6553 "number_recall": {6554 "mean": 0.9909868185745379,6555 "ci_low": 0.9856288761041435,6556 "ci_high": 0.9962027133772341,6557 "n_items": 468,6558 "n_groups": 466559 },6560 "placeholders_exact": {6561 "mean": 0.9935897435897436,6562 "ci_low": 0.9821764462728579,6563 "ci_high": 1.0,6564 "n_items": 468,6565 "n_groups": 466566 }6567 }6568 },6569 "by_role": {6570 "abstract": {6571 "n": 55,6572 "chrf": {6573 "mean": 76.01019651894391,6574 "ci_low": 74.17203077289764,6575 "ci_high": 77.95095944894484,6576 "n_items": 55,6577 "n_groups": 156578 },6579 "edit_sim": {6580 "mean": 0.7520324396759868,6581 "ci_low": 0.7334148596553601,6582 "ci_high": 0.7703439549682098,6583 "n_items": 55,6584 "n_groups": 156585 },6586 "rougeL": {6587 "mean": 0.7501117915044773,6588 "ci_low": 0.7294041474649209,6589 "ci_high": 0.7723134203775647,6590 "n_items": 55,6591 "n_groups": 156592 },6593 "exact_match": {6594 "mean": 0.0,6595 "ci_low": 0.0,6596 "ci_high": 0.0,6597 "n_items": 55,6598 "n_groups": 156599 },6600 "number_recall": {6601 "mean": 0.9992727272727273,6602 "ci_low": 0.9977777777777779,6603 "ci_high": 1.0,6604 "n_items": 55,6605 "n_groups": 156606 },6607 "placeholders_exact": {6608 "mean": 1.0,6609 "ci_low": 1.0,6610 "ci_high": 1.0,6611 "n_items": 55,6612 "n_groups": 156613 }6614 },6615 "background": {6616 "n": 36,6617 "chrf": {6618 "mean": 73.98055656000851,6619 "ci_low": 70.90059349515687,6620 "ci_high": 76.88759126064252,6621 "n_items": 36,6622 "n_groups": 76623 },6624 "edit_sim": {6625 "mean": 0.736526910716718,6626 "ci_low": 0.70139093590013,6627 "ci_high": 0.7695272686342997,6628 "n_items": 36,6629 "n_groups": 76630 },6631 "rougeL": {6632 "mean": 0.7407501570574502,6633 "ci_low": 0.7154586351234123,6634 "ci_high": 0.7665509563681653,6635 "n_items": 36,6636 "n_groups": 76637 },6638 "exact_match": {6639 "mean": 0.0,6640 "ci_low": 0.0,6641 "ci_high": 0.0,6642 "n_items": 36,6643 "n_groups": 76644 },6645 "number_recall": {6646 "mean": 1.0,6647 "ci_low": 1.0,6648 "ci_high": 1.0,6649 "n_items": 36,6650 "n_groups": 76651 },6652 "placeholders_exact": {6653 "mean": 1.0,6654 "ci_low": 1.0,6655 "ci_high": 1.0,6656 "n_items": 36,6657 "n_groups": 76658 }6659 },6660 "conclusion": {6661 "n": 36,6662 "chrf": {6663 "mean": 70.1739708130422,6664 "ci_low": 67.30455352671001,6665 "ci_high": 73.06715079862087,6666 "n_items": 36,6667 "n_groups": 96668 },6669 "edit_sim": {6670 "mean": 0.6968951490228841,6671 "ci_low": 0.6626414641611778,6672 "ci_high": 0.7363902601486029,6673 "n_items": 36,6674 "n_groups": 96675 },6676 "rougeL": {6677 "mean": 0.6945809023209177,6678 "ci_low": 0.6595101679523167,6679 "ci_high": 0.7307484250494597,6680 "n_items": 36,6681 "n_groups": 96682 },6683 "exact_match": {6684 "mean": 0.0,6685 "ci_low": 0.0,6686 "ci_high": 0.0,6687 "n_items": 36,6688 "n_groups": 96689 },6690 "number_recall": {6691 "mean": 1.0,6692 "ci_low": 1.0,6693 "ci_high": 1.0,6694 "n_items": 36,6695 "n_groups": 96696 },6697 "placeholders_exact": {6698 "mean": 1.0,6699 "ci_low": 1.0,6700 "ci_high": 1.0,6701 "n_items": 36,6702 "n_groups": 96703 }6704 },6705 "data": {6706 "n": 41,6707 "chrf": {6708 "mean": 76.41611127404042,6709 "ci_low": 72.82674031228461,6710 "ci_high": 79.98901409596348,6711 "n_items": 41,6712 "n_groups": 106713 },6714 "edit_sim": {6715 "mean": 0.7291280944992641,6716 "ci_low": 0.6873281310516739,6717 "ci_high": 0.7778786248096446,6718 "n_items": 41,6719 "n_groups": 106720 },6721 "rougeL": {6722 "mean": 0.7540781199619178,6723 "ci_low": 0.7116697963006241,6724 "ci_high": 0.7982725180620793,6725 "n_items": 41,6726 "n_groups": 106727 },6728 "exact_match": {6729 "mean": 0.0,6730 "ci_low": 0.0,6731 "ci_high": 0.0,6732 "n_items": 41,6733 "n_groups": 106734 },6735 "number_recall": {6736 "mean": 0.9821245186136071,6737 "ci_low": 0.9591281025717703,6738 "ci_high": 1.0,6739 "n_items": 41,6740 "n_groups": 106741 },6742 "placeholders_exact": {6743 "mean": 1.0,6744 "ci_low": 1.0,6745 "ci_high": 1.0,6746 "n_items": 41,6747 "n_groups": 106748 }6749 },6750 "discussion": {6751 "n": 69,6752 "chrf": {6753 "mean": 72.96933760857605,6754 "ci_low": 70.6366827720362,6755 "ci_high": 75.40166981905473,6756 "n_items": 69,6757 "n_groups": 146758 },6759 "edit_sim": {6760 "mean": 0.7224213147633455,6761 "ci_low": 0.6956629905853734,6762 "ci_high": 0.7495208577728428,6763 "n_items": 69,6764 "n_groups": 146765 },6766 "rougeL": {6767 "mean": 0.7260620604256809,6768 "ci_low": 0.6947896524665145,6769 "ci_high": 0.7588196008093863,6770 "n_items": 69,6771 "n_groups": 146772 },6773 "exact_match": {6774 "mean": 0.0,6775 "ci_low": 0.0,6776 "ci_high": 0.0,6777 "n_items": 69,6778 "n_groups": 146779 },6780 "number_recall": {6781 "mean": 0.9903381642512077,6782 "ci_low": 0.970137946630484,6783 "ci_high": 1.0,6784 "n_items": 69,6785 "n_groups": 146786 },6787 "placeholders_exact": {6788 "mean": 1.0,6789 "ci_low": 1.0,6790 "ci_high": 1.0,6791 "n_items": 69,6792 "n_groups": 146793 }6794 },6795 "introduction": {6796 "n": 63,6797 "chrf": {6798 "mean": 72.10051477852099,6799 "ci_low": 70.02583760066027,6800 "ci_high": 74.33473049691575,6801 "n_items": 63,6802 "n_groups": 146803 },6804 "edit_sim": {6805 "mean": 0.7044699340611396,6806 "ci_low": 0.6834140274803516,6807 "ci_high": 0.7247799611437292,6808 "n_items": 63,6809 "n_groups": 146810 },6811 "rougeL": {6812 "mean": 0.7099243955802637,6813 "ci_low": 0.6913290989008614,6814 "ci_high": 0.7289046249811867,6815 "n_items": 63,6816 "n_groups": 146817 },6818 "exact_match": {6819 "mean": 0.0,6820 "ci_low": 0.0,6821 "ci_high": 0.0,6822 "n_items": 63,6823 "n_groups": 146824 },6825 "number_recall": {6826 "mean": 0.9891975308641975,6827 "ci_low": 0.9691091954022989,6828 "ci_high": 1.0,6829 "n_items": 63,6830 "n_groups": 146831 },6832 "placeholders_exact": {6833 "mean": 1.0,6834 "ci_low": 1.0,6835 "ci_high": 1.0,6836 "n_items": 63,6837 "n_groups": 146838 }6839 },6840 "limitations": {6841 "n": 28,6842 "chrf": {6843 "mean": 73.3018737121017,6844 "ci_low": 70.21082777762891,6845 "ci_high": 75.49223279568805,6846 "n_items": 28,6847 "n_groups": 46848 },6849 "edit_sim": {6850 "mean": 0.7251557086162548,6851 "ci_low": 0.707576898713067,6852 "ci_high": 0.7474819528714821,6853 "n_items": 28,6854 "n_groups": 46855 },6856 "rougeL": {6857 "mean": 0.7273097730602149,6858 "ci_low": 0.6884289471946993,6859 "ci_high": 0.7606437913604613,6860 "n_items": 28,6861 "n_groups": 46862 },6863 "exact_match": {6864 "mean": 0.0,6865 "ci_low": 0.0,6866 "ci_high": 0.0,6867 "n_items": 28,6868 "n_groups": 46869 },6870 "number_recall": {6871 "mean": 1.0,6872 "ci_low": 1.0,6873 "ci_high": 1.0,6874 "n_items": 28,6875 "n_groups": 46876 },6877 "placeholders_exact": {6878 "mean": 1.0,6879 "ci_low": 1.0,6880 "ci_high": 1.0,6881 "n_items": 28,6882 "n_groups": 46883 }6884 },6885 "methods": {6886 "n": 67,6887 "chrf": {6888 "mean": 73.58276163647616,6889 "ci_low": 70.74537441640594,6890 "ci_high": 76.58887410621239,6891 "n_items": 67,6892 "n_groups": 126893 },6894 "edit_sim": {6895 "mean": 0.7287579331555669,6896 "ci_low": 0.7067387135289313,6897 "ci_high": 0.752636552836086,6898 "n_items": 67,6899 "n_groups": 126900 },6901 "rougeL": {6902 "mean": 0.7439686622211217,6903 "ci_low": 0.7206296180822603,6904 "ci_high": 0.7692741990047557,6905 "n_items": 67,6906 "n_groups": 126907 },6908 "exact_match": {6909 "mean": 0.0,6910 "ci_low": 0.0,6911 "ci_high": 0.0,6912 "n_items": 67,6913 "n_groups": 126914 },6915 "number_recall": {6916 "mean": 0.9890547263681592,6917 "ci_low": 0.9673733075435204,6918 "ci_high": 1.0,6919 "n_items": 67,6920 "n_groups": 126921 },6922 "placeholders_exact": {6923 "mean": 0.9850746268656716,6924 "ci_low": 0.9433962264150944,6925 "ci_high": 1.0,6926 "n_items": 67,6927 "n_groups": 126928 }6929 },6930 "other": {6931 "n": 52,6932 "chrf": {6933 "mean": 72.52626887164978,6934 "ci_low": 68.32081357398715,6935 "ci_high": 77.25064493899873,6936 "n_items": 52,6937 "n_groups": 96938 },6939 "edit_sim": {6940 "mean": 0.7190137734165549,6941 "ci_low": 0.6782721496885846,6942 "ci_high": 0.7704672360584617,6943 "n_items": 52,6944 "n_groups": 96945 },6946 "rougeL": {6947 "mean": 0.7128735091688383,6948 "ci_low": 0.6642926286956873,6949 "ci_high": 0.7722664836807254,6950 "n_items": 52,6951 "n_groups": 96952 },6953 "exact_match": {6954 "mean": 0.0,6955 "ci_low": 0.0,6956 "ci_high": 0.0,6957 "n_items": 52,6958 "n_groups": 96959 },6960 "number_recall": {6961 "mean": 1.0,6962 "ci_low": 1.0,6963 "ci_high": 1.0,6964 "n_items": 52,6965 "n_groups": 96966 },6967 "placeholders_exact": {6968 "mean": 0.9615384615384616,6969 "ci_low": 0.8867924528301887,6970 "ci_high": 1.0,6971 "n_items": 52,6972 "n_groups": 96973 }6974 },6975 "related_work": {6976 "n": 4,6977 "chrf": {6978 "mean": 80.39474988316184,6979 "ci_low": 80.39474988316184,6980 "ci_high": 80.39474988316184,6981 "n_items": 4,6982 "n_groups": 16983 },6984 "edit_sim": {6985 "mean": 0.8030622293893577,6986 "ci_low": 0.8030622293893577,6987 "ci_high": 0.8030622293893577,6988 "n_items": 4,6989 "n_groups": 16990 },6991 "rougeL": {6992 "mean": 0.8069193765837637,6993 "ci_low": 0.8069193765837637,6994 "ci_high": 0.8069193765837637,6995 "n_items": 4,6996 "n_groups": 16997 },6998 "exact_match": {6999 "mean": 0.0,7000 "ci_low": 0.0,7001 "ci_high": 0.0,7002 "n_items": 4,7003 "n_groups": 17004 },7005 "number_recall": {7006 "mean": 1.0,7007 "ci_low": 1.0,7008 "ci_high": 1.0,7009 "n_items": 4,7010 "n_groups": 17011 },7012 "placeholders_exact": {7013 "mean": 1.0,7014 "ci_low": 1.0,7015 "ci_high": 1.0,7016 "n_items": 4,7017 "n_groups": 17018 }7019 },7020 "results": {7021 "n": 46,7022 "chrf": {7023 "mean": 70.7914660171291,7024 "ci_low": 68.04698476205695,7025 "ci_high": 73.57052092721169,7026 "n_items": 46,7027 "n_groups": 97028 },7029 "edit_sim": {7030 "mean": 0.6998196889127158,7031 "ci_low": 0.6791880231460585,7032 "ci_high": 0.7239258841378609,7033 "n_items": 46,7034 "n_groups": 97035 },7036 "rougeL": {7037 "mean": 0.7124547709736709,7038 "ci_low": 0.696172880806911,7039 "ci_high": 0.7299416676635456,7040 "n_items": 46,7041 "n_groups": 97042 },7043 "exact_match": {7044 "mean": 0.0,7045 "ci_low": 0.0,7046 "ci_high": 0.0,7047 "n_items": 46,7048 "n_groups": 97049 },7050 "number_recall": {7051 "mean": 0.9940476190476192,7052 "ci_low": 0.9869614512471655,7053 "ci_high": 1.0,7054 "n_items": 46,7055 "n_groups": 97056 },7057 "placeholders_exact": {7058 "mean": 1.0,7059 "ci_low": 1.0,7060 "ci_high": 1.0,7061 "n_items": 46,7062 "n_groups": 97063 }7064 },7065 "theory": {7066 "n": 34,7067 "chrf": {7068 "mean": 72.53172230215702,7069 "ci_low": 69.73077653158516,7070 "ci_high": 77.33895371285257,7071 "n_items": 34,7072 "n_groups": 67073 },7074 "edit_sim": {7075 "mean": 0.7133146729068951,7076 "ci_low": 0.6954142325434963,7077 "ci_high": 0.748554234147305,7078 "n_items": 34,7079 "n_groups": 67080 },7081 "rougeL": {7082 "mean": 0.7132704037761082,7083 "ci_low": 0.6939723346599551,7084 "ci_high": 0.7504893815500561,7085 "n_items": 34,7086 "n_groups": 67087 },7088 "exact_match": {7089 "mean": 0.0,7090 "ci_low": 0.0,7091 "ci_high": 0.0,7092 "n_items": 34,7093 "n_groups": 67094 },7095 "number_recall": {7096 "mean": 0.9679144385026737,7097 "ci_low": 0.9090909090909091,7098 "ci_high": 1.0,7099 "n_items": 34,7100 "n_groups": 67101 },7102 "placeholders_exact": {7103 "mean": 1.0,7104 "ci_low": 1.0,7105 "ci_high": 1.0,7106 "n_items": 34,7107 "n_groups": 67108 }7109 }7110 }7111 }7112 },7113 "paired_vs_baseline": {7114 "B1_generic_paraphrase": {7115 "chrf": {7116 "mean": -3.5338331999109935,7117 "ci_low": -3.9518277464232465,7118 "ci_high": -3.157737899604414,7119 "n_items": 531,7120 "n_groups": 55,7121 "p_value_two_sided": 0.0,7122 "p_holm": 0.0,7123 "significant_holm_0_05": true7124 },7125 "edit_sim": {7126 "mean": -0.13225052738892867,7127 "ci_low": -0.14435378648041647,7128 "ci_high": -0.12075915661969579,7129 "n_items": 531,7130 "n_groups": 55,7131 "p_value_two_sided": 0.0,7132 "p_holm": 0.0,7133 "significant_holm_0_05": true7134 },7135 "rougeL": {7136 "mean": -0.09543401606540321,7137 "ci_low": -0.10346159498309598,7138 "ci_high": -0.08788411037233251,7139 "n_items": 531,7140 "n_groups": 55,7141 "p_value_two_sided": 0.0,7142 "p_holm": 0.0,7143 "significant_holm_0_05": true7144 },7145 "exact_match": {7146 "mean": 0.0,7147 "ci_low": 0.0,7148 "ci_high": 0.0,7149 "n_items": 531,7150 "n_groups": 55,7151 "p_value_two_sided": 0.0,7152 "p_holm": 0.0,7153 "significant_holm_0_05": true7154 },7155 "number_recall": {7156 "mean": -0.00047080979284369113,7157 "ci_low": -0.0013043478260869566,7158 "ci_high": 0.0,7159 "n_items": 531,7160 "n_groups": 55,7161 "p_value_two_sided": 0.0,7162 "p_holm": 0.0,7163 "significant_holm_0_05": true7164 },7165 "placeholders_exact": {7166 "mean": 0.0,7167 "ci_low": 0.0,7168 "ci_high": 0.0,7169 "n_items": 531,7170 "n_groups": 55,7171 "p_value_two_sided": 0.0,7172 "p_holm": 0.0,7173 "significant_holm_0_05": true7174 }7175 },7176 "htr-m1-small": {7177 "chrf": {7178 "mean": -1.0828449171318835,7179 "ci_low": -1.469733894594182,7180 "ci_high": -0.6843965947696177,7181 "n_items": 531,7182 "n_groups": 55,7183 "p_value_two_sided": 0.0,7184 "p_holm": 0.0,7185 "significant_holm_0_05": true7186 },7187 "edit_sim": {7188 "mean": -0.012574981627211785,7189 "ci_low": -0.017658323205277975,7190 "ci_high": -0.007059252129911641,7191 "n_items": 531,7192 "n_groups": 55,7193 "p_value_two_sided": 0.0,7194 "p_holm": 0.0,7195 "significant_holm_0_05": true7196 },7197 "rougeL": {7198 "mean": -0.012494181749671646,7199 "ci_low": -0.017725284882283122,7200 "ci_high": -0.007305483515426781,7201 "n_items": 531,7202 "n_groups": 55,7203 "p_value_two_sided": 0.0,7204 "p_holm": 0.0,7205 "significant_holm_0_05": true7206 },7207 "exact_match": {7208 "mean": 0.0,7209 "ci_low": 0.0,7210 "ci_high": 0.0,7211 "n_items": 531,7212 "n_groups": 55,7213 "p_value_two_sided": 0.0,7214 "p_holm": 0.0,7215 "significant_holm_0_05": true7216 },7217 "number_recall": {7218 "mean": -0.007151234411121417,7219 "ci_low": -0.0126047569955454,7220 "ci_high": -0.0034942686402926683,7221 "n_items": 531,7222 "n_groups": 55,7223 "p_value_two_sided": 0.0,7224 "p_holm": 0.0,7225 "significant_holm_0_05": true7226 },7227 "placeholders_exact": {7228 "mean": -0.005649717514124294,7229 "ci_low": -0.015707063434102386,7230 "ci_high": 0.0,7231 "n_items": 531,7232 "n_groups": 55,7233 "p_value_two_sided": 0.0,7234 "p_holm": 0.0,7235 "significant_holm_0_05": true7236 }7237 },7238 "htr-m1-tiny-s3": {7239 "chrf": {7240 "mean": -0.8511852968458533,7241 "ci_low": -1.3296753287111236,7242 "ci_high": -0.4805688552126319,7243 "n_items": 531,7244 "n_groups": 55,7245 "p_value_two_sided": 0.0,7246 "p_holm": 0.0,7247 "significant_holm_0_05": true7248 },7249 "edit_sim": {7250 "mean": -0.006519437145979195,7251 "ci_low": -0.010979397517333619,7252 "ci_high": -0.001936852432768834,7253 "n_items": 531,7254 "n_groups": 55,7255 "p_value_two_sided": 0.0032000000000000917,7256 "p_holm": 0.0032000000000000917,7257 "significant_holm_0_05": true7258 },7259 "rougeL": {7260 "mean": -0.009033015704206823,7261 "ci_low": -0.015002318114999438,7262 "ci_high": -0.004174702600102339,7263 "n_items": 531,7264 "n_groups": 55,7265 "p_value_two_sided": 0.00019999999999997797,7266 "p_holm": 0.00039999999999995595,7267 "significant_holm_0_05": true7268 },7269 "exact_match": {7270 "mean": 0.0,7271 "ci_low": 0.0,7272 "ci_high": 0.0,7273 "n_items": 531,7274 "n_groups": 55,7275 "p_value_two_sided": 0.0,7276 "p_holm": 0.0,7277 "significant_holm_0_05": true7278 },7279 "number_recall": {7280 "mean": -0.009094723791423167,7281 "ci_low": -0.01699859737065034,7282 "ci_high": -0.002914369364559119,7283 "n_items": 531,7284 "n_groups": 55,7285 "p_value_two_sided": 0.0,7286 "p_holm": 0.0,7287 "significant_holm_0_05": true7288 },7289 "placeholders_exact": {7290 "mean": -0.007532956685499058,7291 "ci_low": -0.022473175422613623,7292 "ci_high": 0.0,7293 "n_items": 531,7294 "n_groups": 55,7295 "p_value_two_sided": 0.0,7296 "p_holm": 0.0,7297 "significant_holm_0_05": true7298 }7299 },7300 "htr-m1-tiny": {7301 "chrf": {7302 "mean": -0.9720079807949406,7303 "ci_low": -1.3834799284753927,7304 "ci_high": -0.6159458425104477,7305 "n_items": 531,7306 "n_groups": 55,7307 "p_value_two_sided": 0.0,7308 "p_holm": 0.0,7309 "significant_holm_0_05": true7310 },7311 "edit_sim": {7312 "mean": -0.0089611905581209,7313 "ci_low": -0.013529748977612107,7314 "ci_high": -0.004277909202722014,7315 "n_items": 531,7316 "n_groups": 55,7317 "p_value_two_sided": 0.00019999999999997797,7318 "p_holm": 0.00019999999999997797,7319 "significant_holm_0_05": true7320 },7321 "rougeL": {7322 "mean": -0.009855029475363606,7323 "ci_low": -0.015294758507920761,7324 "ci_high": -0.004878024087346438,7325 "n_items": 531,7326 "n_groups": 55,7327 "p_value_two_sided": 0.0,7328 "p_holm": 0.0,7329 "significant_holm_0_05": true7330 },7331 "exact_match": {7332 "mean": 0.0,7333 "ci_low": 0.0,7334 "ci_high": 0.0,7335 "n_items": 531,7336 "n_groups": 55,7337 "p_value_two_sided": 0.0,7338 "p_holm": 0.0,7339 "significant_holm_0_05": true7340 },7341 "number_recall": {7342 "mean": -0.006984378877034244,7343 "ci_low": -0.011931727907629431,7344 "ci_high": -0.003554556640142634,7345 "n_items": 531,7346 "n_groups": 55,7347 "p_value_two_sided": 0.0,7348 "p_holm": 0.0,7349 "significant_holm_0_05": true7350 },7351 "placeholders_exact": {7352 "mean": -0.009416195856873822,7353 "ci_low": -0.02907009260704438,7354 "ci_high": 0.0,7355 "n_items": 531,7356 "n_groups": 55,7357 "p_value_two_sided": 0.0,7358 "p_holm": 0.0,7359 "significant_holm_0_05": true7360 }7361 },7362 "htr-m3tokenonly-tiny": {7363 "chrf": {7364 "mean": -0.8801653735828521,7365 "ci_low": -1.2724329299976265,7366 "ci_high": -0.5465476202114589,7367 "n_items": 531,7368 "n_groups": 55,7369 "p_value_two_sided": 0.0,7370 "p_holm": 0.0,7371 "significant_holm_0_05": true7372 },7373 "edit_sim": {7374 "mean": -0.007837966371696295,7375 "ci_low": -0.01224334526958089,7376 "ci_high": -0.003121620061460411,7377 "n_items": 531,7378 "n_groups": 55,7379 "p_value_two_sided": 0.0005999999999999339,7380 "p_holm": 0.0011999999999998678,7381 "significant_holm_0_05": true7382 },7383 "rougeL": {7384 "mean": -0.007714441084466711,7385 "ci_low": -0.013118594757605405,7386 "ci_high": -0.0028666756256117885,7387 "n_items": 531,7388 "n_groups": 55,7389 "p_value_two_sided": 0.0009999999999998899,7390 "p_holm": 0.0011999999999998678,7391 "significant_holm_0_05": true7392 },7393 "exact_match": {7394 "mean": 0.0,7395 "ci_low": 0.0,7396 "ci_high": 0.0,7397 "n_items": 531,7398 "n_groups": 55,7399 "p_value_two_sided": 0.0,7400 "p_holm": 0.0,7401 "significant_holm_0_05": true7402 },7403 "number_recall": {7404 "mean": -0.007943820917356452,7405 "ci_low": -0.012993331476271313,7406 "ci_high": -0.0035434021542896403,7407 "n_items": 531,7408 "n_groups": 55,7409 "p_value_two_sided": 0.0,7410 "p_holm": 0.0,7411 "significant_holm_0_05": true7412 },7413 "placeholders_exact": {7414 "mean": -0.005649717514124294,7415 "ci_low": -0.01590468552322429,7416 "ci_high": 0.0,7417 "n_items": 531,7418 "n_groups": 55,7419 "p_value_two_sided": 0.0,7420 "p_holm": 0.0,7421 "significant_holm_0_05": true7422 }7423 }7424 },7425 "stylometry": {7426 "rewrite_vs_original": {7427 "W1_mean_sent_len": 0.13318091877216057,7428 "W1_sd_sent_len": 0.09809996335078412,7429 "W1_ttr": 0.33608262808679934,7430 "W1_mtld": 0.4946488305516617,7431 "W1_mean_word_len": 0.2901333265136195,7432 "W1_long_word_rate": 0.09603648080194438,7433 "W1_comma_rate": 0.49021281032893294,7434 "W1_semicolon_rate": 0.07802422547830698,7435 "W1_paren_rate": 0.05149434459705541,7436 "W1_discourse_rate": 0.09638968408065016,7437 "W1_passive_rate": 0.08972647340927765,7438 "W1_nominal_rate": 0.11107471688097156,7439 "W1_first_person_rate": 0.06580881142950977,7440 "W1_subord_rate": 0.21087641062051948,7441 "W1_hedge_rate": 0.061853832158202456,7442 "W1_negation_rate": 0.05150151171677734,7443 "W1_digit_rate": 0.017946744112095826,7444 "W1_flesch": 0.16966426504925844,7445 "W1_mean": 0.163486443218807127446 },7447 "feature_means": {7448 "original": {7449 "mean_sent_len": 25.80580226950281,7450 "sd_sent_len": 8.480312246276549,7451 "ttr": 0.6376272849766947,7452 "mtld": 73.58385151514256,7453 "mean_word_len": 5.585113889365692,7454 "long_word_rate": 0.1268511519706568,7455 "comma_rate": 0.04920855315481087,7456 "semicolon_rate": 0.0019007373461337644,7457 "paren_rate": 0.015118832886339284,7458 "discourse_rate": 0.011082952706045715,7459 "passive_rate": 0.43322225483242455,7460 "nominal_rate": 0.06583633207865298,7461 "first_person_rate": 0.002575227699237606,7462 "subord_rate": 0.02681688354084387,7463 "hedge_rate": 0.007619835097318459,7464 "negation_rate": 0.005235128874886877,7465 "digit_rate": 0.008951668578790213,7466 "flesch": 16.4315529659991067467 },7468 "rewrite": {7469 "mean_sent_len": 25.25480517076562,7470 "sd_sent_len": 8.1167730334782,7471 "ttr": 0.6700093849339616,7472 "mtld": 87.82970086044989,7473 "mean_word_len": 5.708329427652223,7474 "long_word_rate": 0.13069062584396496,7475 "comma_rate": 0.06443170536761768,7476 "semicolon_rate": 0.002135690133032927,7477 "paren_rate": 0.014950765572591822,7478 "discourse_rate": 0.011944354362099242,7479 "passive_rate": 0.441045985819997,7480 "nominal_rate": 0.06331580852843248,7481 "first_person_rate": 0.0022346580802391183,7482 "subord_rate": 0.030322082536698717,7483 "hedge_rate": 0.007682480485321515,7484 "negation_rate": 0.005551572596878977,7485 "digit_rate": 0.009027050727351714,7486 "flesch": 14.2756293489263267487 }7488 },7489 "feature_sds": {7490 "original": {7491 "mean_sent_len": 6.98502228609813,7492 "sd_sent_len": 4.423594629306136,7493 "ttr": 0.09454588237221213,7494 "mtld": 23.53533869400621,7495 "mean_word_len": 0.4160080201550301,7496 "long_word_rate": 0.04172960415586606,7497 "comma_rate": 0.030093857860351493,7498 "semicolon_rate": 0.005609105190320024,7499 "paren_rate": 0.017805079071775125,7500 "discourse_rate": 0.010342207029166512,7501 "passive_rate": 0.34152152423497184,7502 "nominal_rate": 0.030889299527157715,7503 "first_person_rate": 0.005988587836620324,7504 "subord_rate": 0.016380505579957218,7505 "hedge_rate": 0.009171289789579372,7506 "negation_rate": 0.007564457201908807,7507 "digit_rate": 0.013718226018082959,7508 "flesch": 12.820883156489467509 },7510 "rewrite": {7511 "mean_sent_len": 6.133260437751693,7512 "sd_sent_len": 4.068235514415373,7513 "ttr": 0.09704626526636556,7514 "mtld": 31.92448676782491,7515 "mean_word_len": 0.43245778175453325,7516 "long_word_rate": 0.04277852647025009,7517 "comma_rate": 0.030266343318137164,7518 "semicolon_rate": 0.005688471114916606,7519 "paren_rate": 0.017120235375681237,7520 "discourse_rate": 0.010821218102393152,7521 "passive_rate": 0.3864346355912153,7522 "nominal_rate": 0.02964640694594822,7523 "first_person_rate": 0.00539174309002147,7524 "subord_rate": 0.017121161059613053,7525 "hedge_rate": 0.009708999267153837,7526 "negation_rate": 0.008380958202143319,7527 "digit_rate": 0.013893184524100035,7528 "flesch": 13.3986795081930647529 }7530 },7531 "B0_identity": {7532 "vs_original": {7533 "W1_mean_sent_len": 0.13318091877216057,7534 "W1_sd_sent_len": 0.09809996335078412,7535 "W1_ttr": 0.33608262808679934,7536 "W1_mtld": 0.4946488305516617,7537 "W1_mean_word_len": 0.2901333265136195,7538 "W1_long_word_rate": 0.09603648080194438,7539 "W1_comma_rate": 0.49021281032893294,7540 "W1_semicolon_rate": 0.07802422547830698,7541 "W1_paren_rate": 0.05149434459705541,7542 "W1_discourse_rate": 0.09638968408065016,7543 "W1_passive_rate": 0.08972647340927765,7544 "W1_nominal_rate": 0.11107471688097156,7545 "W1_first_person_rate": 0.06580881142950977,7546 "W1_subord_rate": 0.21087641062051948,7547 "W1_hedge_rate": 0.061853832158202456,7548 "W1_negation_rate": 0.05150151171677734,7549 "W1_digit_rate": 0.017946744112095826,7550 "W1_flesch": 0.16966426504925844,7551 "W1_mean": 0.163486443218807127552 },7553 "feature_means": {7554 "mean_sent_len": 25.25480517076562,7555 "sd_sent_len": 8.1167730334782,7556 "ttr": 0.6700093849339616,7557 "mtld": 87.82970086044989,7558 "mean_word_len": 5.708329427652223,7559 "long_word_rate": 0.13069062584396496,7560 "comma_rate": 0.06443170536761768,7561 "semicolon_rate": 0.002135690133032927,7562 "paren_rate": 0.014950765572591822,7563 "discourse_rate": 0.011944354362099242,7564 "passive_rate": 0.441045985819997,7565 "nominal_rate": 0.06331580852843248,7566 "first_person_rate": 0.0022346580802391183,7567 "subord_rate": 0.030322082536698717,7568 "hedge_rate": 0.007682480485321515,7569 "negation_rate": 0.005551572596878977,7570 "digit_rate": 0.009027050727351714,7571 "flesch": 14.2756293489263267572 },7573 "probe": {7574 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7575 "probe_acc_heldout": 0.6959247648902821,7576 "eval_mean_p_original": 0.4168699106071383,7577 "eval_frac_classified_original": 0.32203389830508477578 }7579 },7580 "B1_generic_paraphrase": {7581 "vs_original": {7582 "W1_mean_sent_len": 0.61506601605995,7583 "W1_sd_sent_len": 0.564542042875604,7584 "W1_ttr": 0.3056541214526802,7585 "W1_mtld": 0.4394785020195384,7586 "W1_mean_word_len": 0.5107747952490126,7587 "W1_long_word_rate": 0.3596520275981538,7588 "W1_comma_rate": 0.48308869296063317,7589 "W1_semicolon_rate": 0.07852583190155599,7590 "W1_paren_rate": 0.050956362590561,7591 "W1_discourse_rate": 0.07048160573218862,7592 "W1_passive_rate": 0.32914001018216893,7593 "W1_nominal_rate": 0.13946235421584954,7594 "W1_first_person_rate": 0.05260422378637363,7595 "W1_subord_rate": 0.15523529197646274,7596 "W1_hedge_rate": 0.1885548595202886,7597 "W1_negation_rate": 0.05001527973414083,7598 "W1_digit_rate": 0.018337181628695024,7599 "W1_flesch": 0.7247217361326688,7600 "W1_mean": 0.28534949642314037601 },7602 "feature_means": {7603 "mean_sent_len": 29.7127868051597,7604 "sd_sent_len": 10.692089101801889,7605 "ttr": 0.6671479971558147,7606 "mtld": 86.22750735247025,7607 "mean_word_len": 5.80355245511723,7608 "long_word_rate": 0.14201240674837623,7609 "comma_rate": 0.06420061414253359,7610 "semicolon_rate": 0.0021315531446201423,7611 "paren_rate": 0.014889764430265202,7612 "discourse_rate": 0.010743721235723544,7613 "passive_rate": 0.5468193921583754,7614 "nominal_rate": 0.06851496940048715,7615 "first_person_rate": 0.002330285835090697,7616 "subord_rate": 0.029362646113482542,7617 "hedge_rate": 0.005857502947270137,7618 "negation_rate": 0.005527663316221782,7619 "digit_rate": 0.008878684025449366,7620 "flesch": 7.0488930730218497621 },7622 "probe": {7623 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7624 "probe_acc_heldout": 0.6959247648902821,7625 "eval_mean_p_original": 0.42329454076815665,7626 "eval_frac_classified_original": 0.33709981167608297627 }7628 },7629 "htr-m1-small": {7630 "vs_original": {7631 "W1_mean_sent_len": 0.11941944507839737,7632 "W1_sd_sent_len": 0.07773726799209828,7633 "W1_ttr": 0.1319450364929091,7634 "W1_mtld": 0.1796096066370391,7635 "W1_mean_word_len": 0.06562253652125541,7636 "W1_long_word_rate": 0.06589852523974524,7637 "W1_comma_rate": 0.3259291491420788,7638 "W1_semicolon_rate": 0.06812347712108882,7639 "W1_paren_rate": 0.050597206316066956,7640 "W1_discourse_rate": 0.08517639442257598,7641 "W1_passive_rate": 0.166965474243075,7642 "W1_nominal_rate": 0.11828712226707759,7643 "W1_first_person_rate": 0.02468958758224132,7644 "W1_subord_rate": 0.1176903623953103,7645 "W1_hedge_rate": 0.05512485133746591,7646 "W1_negation_rate": 0.08241723227673849,7647 "W1_digit_rate": 0.021347044457828618,7648 "W1_flesch": 0.0713164654330845,7649 "W1_mean": 0.10154982138644877650 },7651 "feature_means": {7652 "mean_sent_len": 25.300386075527328,7653 "sd_sent_len": 8.356454564421043,7654 "ttr": 0.650060548991615,7655 "mtld": 77.62489539311069,7656 "mean_word_len": 5.5931230336638125,7657 "long_word_rate": 0.12599429106515783,7658 "comma_rate": 0.05933970407740084,7659 "semicolon_rate": 0.0016680892024856693,7660 "paren_rate": 0.015038576923042855,7661 "discourse_rate": 0.011605510153356322,7662 "passive_rate": 0.4858117034670705,7663 "nominal_rate": 0.06310143407997813,7664 "first_person_rate": 0.0026284967192461307,7665 "subord_rate": 0.02866619235094809,7666 "hedge_rate": 0.0076110642995452435,7667 "negation_rate": 0.005872360714001618,7668 "digit_rate": 0.009125833138481683,7669 "flesch": 17.11881742295197670 },7671 "probe": {7672 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7673 "probe_acc_heldout": 0.6959247648902821,7674 "eval_mean_p_original": 0.5099800970517695,7675 "eval_frac_classified_original": 0.5197740112994357676 }7677 },7678 "htr-m1-tiny-s3": {7679 "vs_original": {7680 "W1_mean_sent_len": 0.12773475623984068,7681 "W1_sd_sent_len": 0.08221071915670797,7682 "W1_ttr": 0.15321820875258493,7683 "W1_mtld": 0.22032576461545453,7684 "W1_mean_word_len": 0.06908395150330376,7685 "W1_long_word_rate": 0.05940691966374593,7686 "W1_comma_rate": 0.3446049889912555,7687 "W1_semicolon_rate": 0.09344657341367821,7688 "W1_paren_rate": 0.04759782868377054,7689 "W1_discourse_rate": 0.08999857323408558,7690 "W1_passive_rate": 0.14224829499115754,7691 "W1_nominal_rate": 0.10639856580516373,7692 "W1_first_person_rate": 0.022563270432332607,7693 "W1_subord_rate": 0.12685104669658048,7694 "W1_hedge_rate": 0.05527539160318712,7695 "W1_negation_rate": 0.0894052452746357,7696 "W1_digit_rate": 0.023546079506012504,7697 "W1_flesch": 0.09340585123383655,7698 "W1_mean": 0.108184557210962987699 },7700 "feature_means": {7701 "mean_sent_len": 25.19526793566342,7702 "sd_sent_len": 8.242370935024532,7703 "ttr": 0.6522327658549668,7704 "mtld": 78.84920147605888,7705 "mean_word_len": 5.591548234305979,7706 "long_word_rate": 0.12573145409430422,7707 "comma_rate": 0.059853068651431494,7708 "semicolon_rate": 0.0014629439916427108,7709 "paren_rate": 0.015093785716999743,7710 "discourse_rate": 0.011729765814597818,7711 "passive_rate": 0.48252525879644526,7712 "nominal_rate": 0.06345214091380433,7713 "first_person_rate": 0.0026521447923829947,7714 "subord_rate": 0.02887822891756908,7715 "hedge_rate": 0.007644100459292774,7716 "negation_rate": 0.005924916715929316,7717 "digit_rate": 0.00920779967729526,7718 "flesch": 17.1709553276341087719 },7720 "probe": {7721 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7722 "probe_acc_heldout": 0.6959247648902821,7723 "eval_mean_p_original": 0.5045759496269002,7724 "eval_frac_classified_original": 0.51789077212806027725 }7726 },7727 "htr-m1-tiny": {7728 "vs_original": {7729 "W1_mean_sent_len": 0.10982743247925732,7730 "W1_sd_sent_len": 0.09024217495223931,7731 "W1_ttr": 0.14532851153862225,7732 "W1_mtld": 0.21495538843748188,7733 "W1_mean_word_len": 0.07308937651241201,7734 "W1_long_word_rate": 0.07071406365203046,7735 "W1_comma_rate": 0.3697921192108891,7736 "W1_semicolon_rate": 0.13401049682687985,7737 "W1_paren_rate": 0.047162025172345585,7738 "W1_discourse_rate": 0.10077055749843052,7739 "W1_passive_rate": 0.14149369469123152,7740 "W1_nominal_rate": 0.12222152007398888,7741 "W1_first_person_rate": 0.04165886865758971,7742 "W1_subord_rate": 0.09020106795996025,7743 "W1_hedge_rate": 0.05292969028924753,7744 "W1_negation_rate": 0.08455280090036876,7745 "W1_digit_rate": 0.0188075127351203,7746 "W1_flesch": 0.0785034516201159,7747 "W1_mean": 0.110347819622678427748 },7749 "feature_means": {7750 "mean_sent_len": 25.330718564758094,7751 "sd_sent_len": 8.212582111104409,7752 "ttr": 0.6512870116473944,7753 "mtld": 78.59143969679805,7754 "mean_word_len": 5.596770573870624,7755 "long_word_rate": 0.12643121291171838,7756 "comma_rate": 0.06060245846227633,7757 "semicolon_rate": 0.0012417493135300653,7758 "paren_rate": 0.015007666940530422,7759 "discourse_rate": 0.011858400104453413,7760 "passive_rate": 0.4834575552089677,7761 "nominal_rate": 0.06310557442515588,7762 "first_person_rate": 0.002792483880185742,7763 "subord_rate": 0.028193151754024412,7764 "hedge_rate": 0.007382158925259415,7765 "negation_rate": 0.0058823013681728155,7766 "digit_rate": 0.009042603721901573,7767 "flesch": 16.905013320888567768 },7769 "probe": {7770 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7771 "probe_acc_heldout": 0.6959247648902821,7772 "eval_mean_p_original": 0.5066188838835892,7773 "eval_frac_classified_original": 0.51035781544256127774 }7775 },7776 "htr-m3tokenonly-tiny": {7777 "vs_original": {7778 "W1_mean_sent_len": 0.11706489805471607,7779 "W1_sd_sent_len": 0.08033365782084742,7780 "W1_ttr": 0.17186164441626273,7781 "W1_mtld": 0.23587655972304328,7782 "W1_mean_word_len": 0.0745424447252519,7783 "W1_long_word_rate": 0.06382716023272116,7784 "W1_comma_rate": 0.308862907103302,7785 "W1_semicolon_rate": 0.12096866410484579,7786 "W1_paren_rate": 0.053244844967292794,7787 "W1_discourse_rate": 0.0842872939919295,7788 "W1_passive_rate": 0.13998677873993323,7789 "W1_nominal_rate": 0.11133038497203282,7790 "W1_first_person_rate": 0.030085981449573945,7791 "W1_subord_rate": 0.14842069070172434,7792 "W1_hedge_rate": 0.06811268264520491,7793 "W1_negation_rate": 0.09389373046930725,7794 "W1_digit_rate": 0.02051168929198045,7795 "W1_flesch": 0.07093633825764956,7796 "W1_mean": 0.110786019537089967797 },7798 "feature_means": {7799 "mean_sent_len": 25.342585694280633,7800 "sd_sent_len": 8.230330533237188,7801 "ttr": 0.6541617365481243,7802 "mtld": 79.89910846654756,7803 "mean_word_len": 5.606477190247986,7804 "long_word_rate": 0.12657465598713577,7805 "comma_rate": 0.05874988089350449,7806 "semicolon_rate": 0.0013682503031753725,7807 "paren_rate": 0.01507645723978258,7808 "discourse_rate": 0.011561215465139014,7809 "passive_rate": 0.48342996196103516,7810 "nominal_rate": 0.06349203532684163,7811 "first_person_rate": 0.0025545218987152703,7812 "subord_rate": 0.029281287246099443,7813 "hedge_rate": 0.007384961239644863,7814 "negation_rate": 0.0059777460722255085,7815 "digit_rate": 0.009160363704467864,7816 "flesch": 16.590332938930027817 },7818 "probe": {7819 "probe_auc_orig_vs_rewrite": 0.7344917053227455,7820 "probe_acc_heldout": 0.6959247648902821,7821 "eval_mean_p_original": 0.5004232531877222,7822 "eval_frac_classified_original": 0.51412429378531087823 }7824 }7825 },7826 "confirmatory": {7827 "preregistration_frozen": true,7828 "n_boot": 100007829 }7830}