{"meta":{"query_hash":"34948cb5f57d","filters":{"venue":"Empirical Methods in Natural Language Processing"},"cohort_total":11,"direct_labels_cover":0,"predictions_cover":11,"exported":11,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/34948cb5f57d","api":"https://metacan.xera.ac/api/v1/cohort?venue=Empirical+Methods+in+Natural+Language+Processing"},"results":[{"id":"W1569397218","doi":"","title":"Utilizing Extra-Sentential Context for Parsing","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Treebank; Parsing; Computer science; Natural language processing; Artificial intelligence; Context (archaeology); Consistency (knowledge bases); Conditional random field; Generative grammar; Set (abstract data type); Feature (linguistics); Linguistics; Programming language","score_opus":0.05448447238682705,"score_gpt":0.44656764896122564,"score_spread":0.3920831765743986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569397218","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20882133,0.00087209174,0.769417,0.0009804724,0.00014109722,0.00017358697,0.0018626169,0.010209896,0.007521971],"genre_scores_gemma":[0.7508827,0.00026483418,0.24395072,0.00018286992,0.00008836942,0.000090967595,0.0019842044,0.0011454141,0.0014099748],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971641,0.0012878877,0.00014705538,0.00072590413,0.0005401171,0.00013492424],"domain_scores_gemma":[0.99041325,0.0059827724,0.0005411411,0.002054213,0.0008802782,0.00012838036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036075686,0.0010105975,0.00087955594,0.0023878135,0.0012524108,0.0025242115,0.0011939825,0.0011745576,0.0029562495],"category_scores_gemma":[0.016475491,0.0010100858,0.00080567476,0.0021186522,0.0011072704,0.005743702,0.0020362972,0.002147874,0.0011275724],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007121082,0.00042036627,0.030850729,0.0006706361,0.00030370595,0.0010927769,0.0021790075,0.105183855,0.073343396,0.06751309,0.017106965,0.70062333],"study_design_scores_gemma":[0.00007630782,0.00016272637,0.013058858,0.000101908794,0.00030141987,0.000717827,0.00034100015,0.78410006,0.05567835,0.1249592,0.02026481,0.00023750907],"about_ca_topic_score_codex":0.004363167,"about_ca_topic_score_gemma":0.013463791,"teacher_disagreement_score":0.004363167,"about_ca_system_score_codex":0.0009030251,"about_ca_system_score_gemma":0.0019991563,"threshold_uncertainty_score":0.01907891},"labels":[],"label_agreement":null},{"id":"W2117424365","doi":"","title":"Learning Noun Phrase Query Segmentation","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Query expansion; Web query classification; Query language; Natural language processing; RDF query language; Information retrieval; Artificial intelligence; Precision and recall; Web search query; Noun phrase; Sargable; Query optimization; Segmentation; Phrase; Set (abstract data type); Noun; Search engine","score_opus":0.028399328598676603,"score_gpt":0.44222973249310743,"score_spread":0.4138304038944308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117424365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25050855,0.002030118,0.6917123,0.0010633345,0.00026298198,0.001148817,0.006863247,0.036268998,0.010141596],"genre_scores_gemma":[0.56066024,0.00050805433,0.40411666,0.000647672,0.00019136112,0.0005061697,0.025483562,0.0008227079,0.0070635485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975783,0.0005348501,0.00019392687,0.00094788714,0.000542721,0.00020221129],"domain_scores_gemma":[0.9960024,0.0019544782,0.00032582122,0.000390885,0.001186548,0.00013998036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017649435,0.0014613075,0.0013603509,0.0025547903,0.0009095654,0.00168334,0.00208545,0.0016077085,0.0044530006],"category_scores_gemma":[0.008356786,0.00057998253,0.001203247,0.0022643995,0.00095044426,0.0048339474,0.001263835,0.0013949742,0.004793142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012238083,0.0008117332,0.01734042,0.0012220303,0.0002690185,0.0008031325,0.0013679931,0.05544667,0.10955614,0.012651204,0.064100266,0.73520756],"study_design_scores_gemma":[0.00010419522,0.0003907371,0.004715692,0.00005155077,0.00009915551,0.00046752888,0.000544894,0.92465705,0.04218281,0.011568925,0.01515079,0.000066753084],"about_ca_topic_score_codex":0.010329683,"about_ca_topic_score_gemma":0.010213315,"teacher_disagreement_score":0.010329683,"about_ca_system_score_codex":0.0017981628,"about_ca_system_score_gemma":0.0027169113,"threshold_uncertainty_score":0.020539165},"labels":[],"label_agreement":null},{"id":"W2151839123","doi":"","title":"Translating Unknown Words by Analogical Learning","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Lexicon; Computer science; Artificial intelligence; Natural language processing; Machine translation; Quality (philosophy); Translation (biology)","score_opus":0.030972761303358447,"score_gpt":0.432158857636875,"score_spread":0.40118609633351654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151839123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034192465,0.00054030673,0.9551979,0.0008488593,0.00016161577,0.0001424862,0.00013682236,0.0009328793,0.007846642],"genre_scores_gemma":[0.4625249,0.00074032205,0.52742946,0.00085273053,0.0003532822,0.00032793323,0.00088997855,0.0002751131,0.0066063865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972542,0.0012379753,0.00017742711,0.00081569003,0.00043627067,0.00007846116],"domain_scores_gemma":[0.9905122,0.0070236046,0.00048737976,0.0014352339,0.00045596415,0.00008548981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023345472,0.0009315308,0.0008510428,0.0015251262,0.0008260175,0.0020360027,0.0018016848,0.0015343847,0.009029192],"category_scores_gemma":[0.019955331,0.0005088205,0.0011958532,0.001564461,0.0026206768,0.0051969215,0.0028493379,0.002304941,0.0021275887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023352476,0.0003457711,0.0024854492,0.00069655303,0.00021412644,0.00052726414,0.00091829116,0.06547508,0.0072395736,0.18602836,0.007289914,0.728546],"study_design_scores_gemma":[0.000096751624,0.00012731424,0.0007754393,0.00006335229,0.000053424086,0.00042470597,0.00025733592,0.3256868,0.004840369,0.65792274,0.009701287,0.000050438233],"about_ca_topic_score_codex":0.0008260214,"about_ca_topic_score_gemma":0.0011055972,"teacher_disagreement_score":0.009029192,"about_ca_system_score_codex":0.0007952209,"about_ca_system_score_gemma":0.0007048314,"threshold_uncertainty_score":0.030205607},"labels":[],"label_agreement":null},{"id":"W2186073939","doi":"","title":"Sentiment Analysis of Social Media Texts","year":2014,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"SemEval; Computer science; Sentiment analysis; Negation; Lexicon; Task (project management); Artificial intelligence; Natural language processing; Focus (optics); Social media; Scope (computer science); World Wide Web","score_opus":0.038254256486088135,"score_gpt":0.4293544643095399,"score_spread":0.39110020782345173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186073939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5346519,0.005686185,0.32335663,0.0042192875,0.002749317,0.0021352314,0.04133147,0.010760675,0.07510943],"genre_scores_gemma":[0.80016255,0.0036717243,0.14114128,0.00080885936,0.0014444458,0.00095120416,0.031687476,0.00094265316,0.019189838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813807,0.00050850154,0.00020667542,0.00027232186,0.00076651387,0.00010788389],"domain_scores_gemma":[0.9966654,0.001207646,0.00041719884,0.00018892363,0.0014333704,0.000087451546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001756024,0.0008367223,0.00048677687,0.0036026118,0.00054984196,0.0018714106,0.00026348766,0.00039820172,0.0043041795],"category_scores_gemma":[0.0075598205,0.00021623334,0.00069717946,0.00192128,0.00032365735,0.0014873035,0.000667153,0.0005621551,0.0036708326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066176086,0.00019486595,0.030168315,0.0017421662,0.00044146428,0.00055951794,0.0017174825,0.004812416,0.105735615,0.0047141965,0.073814586,0.7754376],"study_design_scores_gemma":[0.00016614555,0.00091394095,0.18949047,0.0008176641,0.00053236977,0.0014809254,0.005723152,0.3212771,0.13272534,0.030515222,0.31607687,0.0002807767],"about_ca_topic_score_codex":0.00097339076,"about_ca_topic_score_gemma":0.0014701742,"teacher_disagreement_score":0.0043041795,"about_ca_system_score_codex":0.00047161747,"about_ca_system_score_gemma":0.00039728958,"threshold_uncertainty_score":0.014398873},"labels":[],"label_agreement":null},{"id":"W2252227670","doi":"","title":"Resolving “This-issue†Anaphora","year":2012,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Anaphora (linguistics); Computer science; Natural language processing; Artificial intelligence; Resolution (logic)","score_opus":0.07225211446287715,"score_gpt":0.4151775315217796,"score_spread":0.34292541705890245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252227670","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32848024,0.004578263,0.5699951,0.024680832,0.0014558317,0.00037036647,0.0018918785,0.0009254813,0.067621954],"genre_scores_gemma":[0.86621124,0.0009495942,0.12203691,0.0014143866,0.0007314433,0.00015888936,0.0019066344,0.0004304611,0.0061603985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9789256,0.012127056,0.0017831433,0.003306428,0.0031547856,0.0007029876],"domain_scores_gemma":[0.92501974,0.05646777,0.004487348,0.010037536,0.003493107,0.00049455155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027047303,0.0006308134,0.0013160757,0.003577998,0.003477312,0.010259456,0.0027703291,0.0036645525,0.011469586],"category_scores_gemma":[0.12950005,0.0008669135,0.001027381,0.0038791974,0.0034062222,0.01558231,0.008012157,0.0044849175,0.0010860877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002817865,0.0002847794,0.024828648,0.0006210641,0.0002448396,0.00044182272,0.0041631367,0.0022927965,0.001935671,0.7701298,0.012473977,0.18230164],"study_design_scores_gemma":[0.00008060931,0.000032794007,0.009405055,0.00029222574,0.00014039836,0.000950702,0.0031472105,0.024506345,0.0042278594,0.9149805,0.04217871,0.00005763003],"about_ca_topic_score_codex":0.0017434923,"about_ca_topic_score_gemma":0.0020294345,"teacher_disagreement_score":0.027047303,"about_ca_system_score_codex":0.001792166,"about_ca_system_score_gemma":0.0030179352,"threshold_uncertainty_score":0.14304155},"labels":[],"label_agreement":null},{"id":"W2996912688","doi":"","title":"Discreteness in Neural Natural Language Processing","year":2019,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Focus (optics); Process (computing); Point (geometry); Space (punctuation); Natural language processing; Natural language; Machine learning; Programming language; Mathematics","score_opus":0.03199366781166351,"score_gpt":0.4167666648137828,"score_spread":0.38477299700211925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996912688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036146885,0.025255864,0.94389904,0.004830928,0.0004760487,0.000049627157,0.0003468149,0.00029857448,0.021228457],"genre_scores_gemma":[0.31938472,0.06627134,0.57834977,0.0033230092,0.0039652125,0.00079997577,0.0014531821,0.0004947727,0.025958002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986045,0.0005509247,0.0001267985,0.0002790199,0.00037881333,0.00006007013],"domain_scores_gemma":[0.99672264,0.0027253984,0.00010360211,0.00022887686,0.00016484817,0.00005470367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026968534,0.0006411536,0.0008731439,0.0014517121,0.00051706936,0.0030947884,0.0012737924,0.001437101,0.0056475857],"category_scores_gemma":[0.008808486,0.00055805,0.00082591287,0.002033613,0.0034380779,0.007027759,0.0016777097,0.0045277374,0.0011701041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008682474,0.000012571715,0.00017173054,0.00018680556,0.00001803061,0.00004403601,0.00011964623,0.008050798,0.00029567437,0.9580468,0.0028933098,0.030151831],"study_design_scores_gemma":[0.0000022906881,0.0000063644793,0.00010621962,0.00006262793,0.0000036876781,0.000046745794,0.000017196375,0.031842202,0.00017938491,0.9566795,0.011044798,0.000008947861],"about_ca_topic_score_codex":0.0017103464,"about_ca_topic_score_gemma":0.0014868022,"teacher_disagreement_score":0.0056475857,"about_ca_system_score_codex":0.0017098791,"about_ca_system_score_gemma":0.0009223366,"threshold_uncertainty_score":0.018893123},"labels":[],"label_agreement":null},{"id":"W3044276988","doi":"","title":"Low-Resource Neural Network Modelling for Universal Dependency Parsing","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Parsing; Dependency grammar; Dependency (UML); Artificial neural network; Artificial intelligence; Resource (disambiguation); Natural language processing; Computer network","score_opus":0.07949367515106834,"score_gpt":0.41001134372687936,"score_spread":0.330517668575811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044276988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02560513,0.0004439971,0.9689622,0.0005397766,0.00006158111,0.000026043146,0.00039449867,0.00069348584,0.0032733579],"genre_scores_gemma":[0.7781634,0.00072570326,0.20845053,0.00021566023,0.00013074193,0.00023979129,0.0013085537,0.00071395945,0.01005172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946195,0.000262005,0.000031504755,0.00012712603,0.000057975238,0.000059450747],"domain_scores_gemma":[0.99648297,0.0028030837,0.00010456384,0.00035185096,0.00018934299,0.000068137415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017863314,0.00067375053,0.0011506025,0.00091084634,0.0006451018,0.0017932977,0.0024596774,0.0016883647,0.007228578],"category_scores_gemma":[0.012065165,0.00090197776,0.00092571246,0.0014688553,0.0009003588,0.0050817532,0.0015854344,0.0031573018,0.0011055361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010789983,0.00005428618,0.0007181022,0.00011664795,0.00007244438,0.00012675885,0.00011383272,0.80918133,0.0011439074,0.13974713,0.002964171,0.045653492],"study_design_scores_gemma":[0.000002531635,0.0000017096392,0.00005109473,0.0000040368577,0.0000048251823,0.000006936749,0.0000033349002,0.9490854,0.00011096057,0.050542176,0.00018391093,0.0000031014274],"about_ca_topic_score_codex":0.009068697,"about_ca_topic_score_gemma":0.015144796,"teacher_disagreement_score":0.009068697,"about_ca_system_score_codex":0.0013717571,"about_ca_system_score_gemma":0.0013836971,"threshold_uncertainty_score":0.024182022},"labels":[],"label_agreement":null},{"id":"W3088099248","doi":"","title":"Memory Augmented Neural Networks for Natural Language Processing","year":2017,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Scalability; Set (abstract data type); Focus (optics); Auxiliary memory; Deep learning; Machine learning; Theoretical computer science; Programming language","score_opus":0.040286962499015484,"score_gpt":0.46035881602918827,"score_spread":0.4200718535301728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088099248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058908877,0.028746337,0.9328775,0.003434018,0.0009876898,0.00007014274,0.0007113497,0.002375619,0.024906466],"genre_scores_gemma":[0.35584688,0.04099201,0.53757054,0.0017247502,0.0018400659,0.0006925424,0.002768675,0.00062646484,0.05793811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997805,0.000055740056,0.000015902588,0.00006147766,0.00006569506,0.000020747295],"domain_scores_gemma":[0.99972004,0.00015564934,0.000022743734,0.000039835417,0.000051435163,0.000010224222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038816713,0.00068026705,0.0005380233,0.00045555792,0.00026003493,0.0014295406,0.0011779469,0.001329491,0.008225783],"category_scores_gemma":[0.0016813603,0.00028950375,0.0005790612,0.0008275581,0.00075514684,0.002462023,0.0008592088,0.0025157458,0.001992282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010642108,0.00004813491,0.00034506354,0.00084133795,0.00012422523,0.00017906893,0.0001333182,0.124098554,0.0056834416,0.46993023,0.031252764,0.36725748],"study_design_scores_gemma":[0.000010655918,0.000033695756,0.00022749769,0.0001019693,0.00002183604,0.00008919403,0.000025122557,0.5015792,0.0017641161,0.4447472,0.051375736,0.000023639384],"about_ca_topic_score_codex":0.0028723248,"about_ca_topic_score_gemma":0.0035836163,"teacher_disagreement_score":0.008225783,"about_ca_system_score_codex":0.0009191722,"about_ca_system_score_gemma":0.00058626704,"threshold_uncertainty_score":0.027517915},"labels":[],"label_agreement":null},{"id":"W3089160253","doi":"","title":"Semantic Similarity Frontiers: From Concepts to Documents","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Semantic similarity; Similarity (geometry); Semantics (computer science); Natural language processing; Information retrieval; Sentence; SemEval; Artificial intelligence; Word (group theory); Semantic computing; Component (thermodynamics); Semantic Web; Linguistics","score_opus":0.07529857966887143,"score_gpt":0.46713590103802416,"score_spread":0.3918373213691527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089160253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018297687,0.17468423,0.6704322,0.03950157,0.003943226,0.00082345377,0.0051009576,0.0025080831,0.08470862],"genre_scores_gemma":[0.26131946,0.075438574,0.6234647,0.0059491494,0.0053607333,0.0017027092,0.007486814,0.0013465519,0.017931258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98896503,0.0048953597,0.0009885584,0.001958112,0.0027789874,0.00041399366],"domain_scores_gemma":[0.9829217,0.012517802,0.00066836114,0.0015278409,0.0017515738,0.0006126796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007030482,0.0016750013,0.0019059106,0.01577358,0.0022697148,0.017457986,0.003467682,0.0032737602,0.016323077],"category_scores_gemma":[0.041531414,0.0010694809,0.0018536847,0.015969729,0.009744746,0.044080645,0.008495122,0.0047148303,0.004286126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012837608,0.000062677784,0.0009319545,0.0020403434,0.00009078026,0.00021759259,0.0043061464,0.0020564303,0.00083508954,0.70620435,0.02874314,0.25438312],"study_design_scores_gemma":[0.000019068497,0.00003541071,0.000801977,0.0006318014,0.00002357598,0.00035815188,0.0019291028,0.006017998,0.0005252186,0.8562193,0.13340206,0.00003633168],"about_ca_topic_score_codex":0.0040528555,"about_ca_topic_score_gemma":0.0018162557,"teacher_disagreement_score":0.017457986,"about_ca_system_score_codex":0.004879111,"about_ca_system_score_gemma":0.003480307,"threshold_uncertainty_score":0.0546062},"labels":[],"label_agreement":null},{"id":"W3213820586","doi":"","title":"How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding.","year":2021,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Robustness (evolution); Computer science; Adversarial system; Distillation; Artificial intelligence; Machine learning; Benchmark (surveying); Domain knowledge; Natural language; Artificial neural network; Theoretical computer science","score_opus":0.10184368763546528,"score_gpt":0.4440969145619636,"score_spread":0.3422532269264983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213820586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23399444,0.031462923,0.6979976,0.008438332,0.0005060991,0.0004465457,0.0014180003,0.0021717472,0.023564298],"genre_scores_gemma":[0.85418296,0.0035619556,0.13575122,0.0011238353,0.00015720868,0.00013391716,0.0017778953,0.00034365573,0.0029674391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99219984,0.0036664489,0.0004425801,0.0019340379,0.0015175233,0.0002395153],"domain_scores_gemma":[0.96384037,0.028590195,0.0011810428,0.0047176676,0.0012896039,0.00038111332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012739208,0.0014752103,0.0011162859,0.0018034556,0.0010223258,0.0021328714,0.0017630913,0.002141556,0.0031240496],"category_scores_gemma":[0.056393493,0.00044081823,0.0011165773,0.0014402652,0.0029978415,0.0066098426,0.0020558888,0.0040385034,0.0011270392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007186966,0.0005284288,0.01774077,0.0012521197,0.00085227285,0.00017188094,0.00035004906,0.3827002,0.0033726888,0.053738754,0.021370945,0.51720315],"study_design_scores_gemma":[0.00006294808,0.00026986827,0.003425262,0.00026835967,0.00011306097,0.0004560672,0.0003088182,0.8818595,0.006287686,0.095632836,0.011251107,0.000064516054],"about_ca_topic_score_codex":0.0029153454,"about_ca_topic_score_gemma":0.003289579,"teacher_disagreement_score":0.012739208,"about_ca_system_score_codex":0.001286654,"about_ca_system_score_gemma":0.0012457281,"threshold_uncertainty_score":0.0673722},"labels":[],"label_agreement":null},{"id":"W34986029","doi":"10.1089/cmb.2021.0438","title":"Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Artificial intelligence; Natural language processing; Conversation; Segmentation; Exploit; Market segmentation; Thread (computing); Text segmentation; Information retrieval; Linguistics","score_opus":0.2587489947827946,"score_gpt":0.5735565170127669,"score_spread":0.31480752222997227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W34986029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33611968,0.001403931,0.6511336,0.000896129,0.00012405602,0.0003041842,0.0013128344,0.0031101415,0.005595543],"genre_scores_gemma":[0.8661972,0.00025169516,0.12858832,0.00009874607,0.00017240355,0.00020216465,0.0020380798,0.0002204974,0.0022309136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998323,0.00076190766,0.00008100609,0.00043857392,0.00019583323,0.0001994865],"domain_scores_gemma":[0.9934228,0.004861163,0.00054073165,0.0003445669,0.00058881723,0.00024190191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732757,0.0007635469,0.0008066572,0.0039932965,0.0010264546,0.0013508591,0.0008228426,0.0014195464,0.0019534866],"category_scores_gemma":[0.011669074,0.00048644337,0.00077761494,0.00164479,0.0007591173,0.0025654412,0.0010497331,0.0012262821,0.00149955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014388702,0.0006650648,0.050624818,0.0005870352,0.00024589853,0.0003909521,0.0038523115,0.13537863,0.033224795,0.018905306,0.013918896,0.74076736],"study_design_scores_gemma":[0.000020764286,0.000057872025,0.01044869,0.00003213785,0.000030921856,0.000115186805,0.00038478486,0.9657826,0.004934063,0.015501825,0.002656739,0.000034410557],"about_ca_topic_score_codex":0.004840827,"about_ca_topic_score_gemma":0.007943881,"teacher_disagreement_score":0.004840827,"about_ca_system_score_codex":0.0010728295,"about_ca_system_score_gemma":0.0010916558,"threshold_uncertainty_score":0.014452338},"labels":[],"label_agreement":null}]}