{"meta":{"query_hash":"34b188fc4f0f","filters":{"venue":"Transactions of the Association for Computational Linguistics"},"cohort_total":52,"direct_labels_cover":0,"predictions_cover":52,"exported":52,"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/34b188fc4f0f","api":"https://metacan.xera.ac/api/v1/cohort?venue=Transactions+of+the+Association+for+Computational+Linguistics"},"results":[{"id":"W1794039122","doi":"10.1162/tacl_a_00080","title":"Learning to Understand Phrases by Embedding the Dictionary","year":2016,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada","keywords":"Computer science; Natural language processing; Word embedding; Artificial intelligence; Bridging (networking); Embedding; Lexical semantics; Semantics (computer science); Word (group theory); Task (project management); Linguistics; Lexical item","score_opus":0.011370769647575057,"score_gpt":0.2784432967756493,"score_spread":0.2670725271280742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794039122","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":[0.049868435,0.00041955593,0.94227546,0.00088109035,0.00012624558,0.00009159806,0.00065734383,0.0015324283,0.004147825],"genre_scores_gemma":[0.5329585,0.0012616996,0.45155883,0.0005519855,0.00012451001,0.000252118,0.0034711102,0.00041412996,0.009407132],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997166,0.00009447097,0.000017935623,0.00011956871,0.000033149245,0.000018324217],"domain_scores_gemma":[0.99899954,0.0006065253,0.00008055145,0.00017682787,0.00010636727,0.000030307934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054015906,0.00075889815,0.00030664538,0.00064974936,0.00022575489,0.0009960396,0.0008028085,0.0008797898,0.005467405],"category_scores_gemma":[0.0039061792,0.00043316258,0.00067419535,0.000615159,0.0006714675,0.0055837473,0.0013560137,0.002013062,0.0023778828],"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":[0.00019021008,0.00017404326,0.004908606,0.00061604736,0.00014428198,0.00032834624,0.0011919372,0.08137792,0.027119959,0.088985935,0.015148487,0.7798142],"study_design_scores_gemma":[0.000029749282,0.00012410925,0.0011325981,0.00009771817,0.00005069407,0.00029957105,0.00038635978,0.807824,0.0090639265,0.16547418,0.015486087,0.000030971056],"about_ca_topic_score_codex":0.0010278564,"about_ca_topic_score_gemma":0.0020932974,"teacher_disagreement_score":0.005467405,"about_ca_system_score_codex":0.00037008413,"about_ca_system_score_gemma":0.00046914464,"threshold_uncertainty_score":0.01829034},"labels":[],"label_agreement":null},{"id":"W2115008472","doi":"10.1162/tacl_a_00233","title":"Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase","year":2013,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Paraphrase; Natural language processing; Similarity (geometry); Artificial intelligence; Computer science; Analogy; Distributional semantics; Word (group theory); Tuple; Pairwise comparison; Noun; Function (biology); Noun phrase; Semantic similarity; Linguistics; Mathematics","score_opus":0.016507278521685844,"score_gpt":0.25692435607696473,"score_spread":0.24041707755527889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115008472","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":[0.2442998,0.0023685512,0.7426266,0.0011759911,0.00012292324,0.00023156549,0.00076297234,0.0016345155,0.0067769815],"genre_scores_gemma":[0.91325074,0.00033675233,0.08240594,0.00027273415,0.00018124229,0.00020358738,0.0019357933,0.00010310715,0.00131002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959468,0.002221786,0.0002515734,0.0009380958,0.0005056971,0.00013610342],"domain_scores_gemma":[0.98967,0.006453741,0.00094027724,0.0017052173,0.00086976273,0.00036101168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032841144,0.00091714994,0.0014385148,0.0031885204,0.0008811745,0.0017626355,0.0021556395,0.0017088449,0.0016635197],"category_scores_gemma":[0.018825782,0.00039118985,0.0011405298,0.0028639976,0.0014945164,0.0064441417,0.0027774058,0.0025023846,0.00067861524],"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":[0.0008186728,0.0014080633,0.029062033,0.0006459027,0.00055563275,0.00039964655,0.0018264543,0.094848655,0.0059104227,0.052333187,0.012429037,0.79976225],"study_design_scores_gemma":[0.00007330934,0.00021573999,0.0048825517,0.000052793577,0.000055269396,0.00019352531,0.0003051455,0.7836914,0.0016947786,0.20654543,0.0022494507,0.000040634106],"about_ca_topic_score_codex":0.0010844897,"about_ca_topic_score_gemma":0.0015845629,"teacher_disagreement_score":0.0032841144,"about_ca_system_score_codex":0.0007890144,"about_ca_system_score_gemma":0.0007073039,"threshold_uncertainty_score":0.017368257},"labels":[],"label_agreement":null},{"id":"W2179519966","doi":"10.1162/tacl_a_00104","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","year":2016,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":115,"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":"Computer science; Feature engineering; Feature (linguistics); Word (group theory); Artificial intelligence; Lexicon; Named-entity recognition; Task (project management); Natural language processing; Encoding (memory); State (computer science); Architecture; Entity linking; Deep learning; Knowledge base","score_opus":0.02717742762268828,"score_gpt":0.2607877003144704,"score_spread":0.23361027269178214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179519966","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":[0.07416549,0.0020486112,0.8748081,0.00087007985,0.00043674748,0.00016374876,0.0047446955,0.027812544,0.014950044],"genre_scores_gemma":[0.6360032,0.0011562776,0.32774952,0.0006165208,0.00019054915,0.00024809624,0.016910939,0.000487703,0.016637264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994825,0.000079707104,0.000044297187,0.00020948779,0.000106627966,0.000077285134],"domain_scores_gemma":[0.9992834,0.0002051736,0.00009350174,0.00020427899,0.00018873556,0.0000250026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073928083,0.0010313287,0.00053871935,0.0012141226,0.00035863044,0.0011497725,0.0015635727,0.0008704101,0.0037904799],"category_scores_gemma":[0.0020853232,0.00045305028,0.00057000027,0.0018834773,0.00028396837,0.0041503785,0.0013972144,0.0009036603,0.0034788426],"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":[0.00032681934,0.00019410552,0.002698951,0.0002794128,0.00018663848,0.00029336338,0.00013186398,0.07590875,0.029778074,0.00873275,0.029004117,0.8524651],"study_design_scores_gemma":[0.000019350608,0.00005665546,0.0011302665,0.000028789322,0.0000628322,0.00012264393,0.000053291747,0.9504978,0.02069166,0.014536359,0.012771919,0.000028440161],"about_ca_topic_score_codex":0.0072223013,"about_ca_topic_score_gemma":0.012624188,"teacher_disagreement_score":0.0072223013,"about_ca_system_score_codex":0.00088347256,"about_ca_system_score_gemma":0.00069419463,"threshold_uncertainty_score":0.014360487},"labels":[],"label_agreement":null},{"id":"W2185701500","doi":"10.1162/tacl_a_00239","title":"Measuring Machine Translation Errors in New Domains","year":2013,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Machine translation; Natural language processing; Domain (mathematical analysis); Phrase; Machine translation software usability; Artificial intelligence; Evaluation of machine translation; Porting; Example-based machine translation; Rule-based machine translation; Translation (biology); Programming language","score_opus":0.02489167998879905,"score_gpt":0.26812889941354556,"score_spread":0.24323721942474652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185701500","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":[0.92027324,0.0005929952,0.07176959,0.0003876248,0.0000814173,0.00023462955,0.0005695323,0.0007559647,0.005335064],"genre_scores_gemma":[0.936502,0.00024878437,0.059591707,0.00017852691,0.00006242957,0.00027578973,0.0012982327,0.0003394027,0.00150309],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9780115,0.009939123,0.0024730016,0.0024273954,0.006657641,0.00049140834],"domain_scores_gemma":[0.880864,0.079896905,0.011043936,0.008937624,0.01810442,0.0011531292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009788002,0.0008871593,0.00096669904,0.0029992072,0.00086016924,0.0020391566,0.0009784834,0.0013674254,0.0011994895],"category_scores_gemma":[0.0958329,0.00053220266,0.0005606752,0.0038442363,0.0014049634,0.0041180835,0.0025354526,0.0021827498,0.0008006678],"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":[0.0026223315,0.0017838477,0.22179864,0.0017206036,0.0011087285,0.0009711884,0.009714782,0.1574432,0.14900646,0.0053068697,0.003571769,0.44495156],"study_design_scores_gemma":[0.00018303681,0.0031140747,0.33062586,0.00018262898,0.0004841894,0.0014092657,0.004379227,0.35233277,0.28383154,0.012633031,0.010490172,0.0003341504],"about_ca_topic_score_codex":0.0021494543,"about_ca_topic_score_gemma":0.0021593773,"teacher_disagreement_score":0.009788002,"about_ca_system_score_codex":0.0009975034,"about_ca_system_score_gemma":0.00071213336,"threshold_uncertainty_score":0.051764548},"labels":[],"label_agreement":null},{"id":"W2404429704","doi":"10.1162/tacl_a_00084","title":"Decoding Anagrammed Texts Written in an Unknown Language and Script","year":2016,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Intelligence, Security, War Strategy","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Decipherment; Computer science; Hebrew; Substitution (logic); Decoding methods; Natural language processing; Set (abstract data type); Cipher; Artificial intelligence; Identification (biology); Encryption; Speech recognition; Linguistics; Algorithm; Programming language","score_opus":0.023738375801858082,"score_gpt":0.3242809997761862,"score_spread":0.3005426239743281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404429704","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":[0.24313834,0.00043705723,0.7456625,0.0008047718,0.00012917748,0.00015355588,0.0005731006,0.0018754526,0.0072260355],"genre_scores_gemma":[0.63114,0.00037482346,0.36046672,0.00015452925,0.0000820043,0.00006981606,0.0014708369,0.00030390668,0.005937332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985104,0.00061799155,0.00013894468,0.00041698595,0.00024573904,0.00006996132],"domain_scores_gemma":[0.99282104,0.0044085057,0.00051974074,0.0012405954,0.0009156528,0.00009444065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012988237,0.0006858622,0.0004989371,0.0009158149,0.0008486649,0.0020518983,0.00074700074,0.0009831894,0.0024674677],"category_scores_gemma":[0.012692437,0.00026851278,0.00039528435,0.0006017634,0.0015328439,0.0025362172,0.00094125187,0.0010275743,0.003136323],"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":[0.0005832792,0.00013256846,0.010827436,0.0005844165,0.00013797011,0.0008648733,0.0031294588,0.03428008,0.10175644,0.04476913,0.0047191405,0.79821527],"study_design_scores_gemma":[0.000036085432,0.00040560588,0.0080528585,0.00023392995,0.00007092295,0.0026395405,0.0030394457,0.52786666,0.3152809,0.11432971,0.027916713,0.00012759608],"about_ca_topic_score_codex":0.0008829227,"about_ca_topic_score_gemma":0.0016104899,"teacher_disagreement_score":0.0024674677,"about_ca_system_score_codex":0.00052985083,"about_ca_system_score_gemma":0.0009402023,"threshold_uncertainty_score":0.008254468},"labels":[],"label_agreement":null},{"id":"W2531207078","doi":"10.1162/tacl_a_00067","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":415,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Samsung Advanced Institute of Technology; Samsung; Nvidia","keywords":"Computer science; Machine translation; Character (mathematics); Pooling; Encoder; Convolutional neural network; Artificial intelligence; Translation (biology); Natural language processing; Segmentation; Speech recognition; Task (project management); Language model; Representation (politics)","score_opus":0.038881259439473397,"score_gpt":0.3152326302466266,"score_spread":0.2763513708071532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531207078","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":[0.06779244,0.0007854792,0.9006131,0.0003423279,0.00023692379,0.00011273133,0.0013587138,0.014669129,0.014088998],"genre_scores_gemma":[0.6053543,0.00052268646,0.36572236,0.00039105985,0.000104567,0.00020415416,0.007608874,0.00093440735,0.019157542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957794,0.00008596748,0.00003321502,0.00016696187,0.00008662008,0.000049267353],"domain_scores_gemma":[0.9991353,0.00023459185,0.0000637335,0.0003126864,0.00022577246,0.000027890066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040190128,0.0009828565,0.00066124415,0.00045984826,0.0003852232,0.0008666583,0.001083708,0.00087407074,0.0061237444],"category_scores_gemma":[0.0021532942,0.00034396126,0.00059000624,0.0010211072,0.00037856968,0.0018106056,0.00090742606,0.001024423,0.0045761485],"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":[0.0005324047,0.0003176903,0.001353153,0.000491166,0.00016107854,0.00048594724,0.00018088486,0.18456735,0.09449791,0.018318903,0.020804856,0.6782887],"study_design_scores_gemma":[0.000024890289,0.00011860493,0.00058795844,0.000021266314,0.00003288747,0.000222429,0.000027940447,0.93966883,0.03822535,0.011165153,0.009879828,0.000024935502],"about_ca_topic_score_codex":0.0036810718,"about_ca_topic_score_gemma":0.007645729,"teacher_disagreement_score":0.0061237444,"about_ca_system_score_codex":0.00050638994,"about_ca_system_score_gemma":0.00116801,"threshold_uncertainty_score":0.020485997},"labels":[],"label_agreement":null},{"id":"W2570431255","doi":"10.1162/tacl_a_00077","title":"Aspect-augmented Adversarial Networks for Domain Adaptation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Army Research Office","keywords":"Computer science; Adversarial system; Domain adaptation; Classifier (UML); Artificial intelligence; Transfer of learning; Sentence; Training set; Domain (mathematical analysis); Relevance (law); Natural language processing; Machine learning; Invariant (physics)","score_opus":0.025433414884880583,"score_gpt":0.27190490475990986,"score_spread":0.2464714898750293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570431255","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":[0.009802936,0.0004252828,0.9858505,0.00021484254,0.00007480339,0.000046789602,0.00015027619,0.0009782031,0.0024562373],"genre_scores_gemma":[0.69157255,0.0010182488,0.2935808,0.0007031672,0.0002706828,0.000406338,0.0015004621,0.00039594976,0.0105519],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99942625,0.00022169197,0.000026922438,0.00014401072,0.00012984539,0.00005128136],"domain_scores_gemma":[0.9990277,0.00046482962,0.00009732901,0.0002330008,0.00013239181,0.000044715125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011555144,0.0011749084,0.0007708182,0.00054914306,0.00025769812,0.00077452144,0.0013838743,0.00087964896,0.002353759],"category_scores_gemma":[0.0037943241,0.00037351032,0.0007593727,0.0007037246,0.0007265564,0.001420522,0.0019514479,0.002241588,0.0011260015],"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":[0.000171961,0.000114485745,0.0015722563,0.00013724827,0.00013507971,0.00017643323,0.0001745366,0.73551625,0.0083013475,0.03332645,0.009190292,0.2111837],"study_design_scores_gemma":[0.000005125274,0.000018877745,0.00011461298,0.0000068764575,0.0000075057324,0.00003130525,0.0000065399518,0.9847269,0.0009373505,0.01257219,0.0015664469,0.0000062437875],"about_ca_topic_score_codex":0.0012754264,"about_ca_topic_score_gemma":0.0017589369,"teacher_disagreement_score":0.002353759,"about_ca_system_score_codex":0.0005888284,"about_ca_system_score_gemma":0.000507691,"threshold_uncertainty_score":0.007874131},"labels":[],"label_agreement":null},{"id":"W2605118633","doi":"10.1162/tacl_a_00047","title":"A Generative Model of Phonotactics","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"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":"National Science Foundation","keywords":"Phonotactics; Computer science; Generative grammar; Artificial intelligence; Generative model; Feature (linguistics); Natural language processing; Set (abstract data type); Probabilistic logic; Phonology; Hierarchy; Linguistics; Programming language","score_opus":0.02717737201804962,"score_gpt":0.30507878804265487,"score_spread":0.2779014160246053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605118633","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":[0.046919692,0.00038551426,0.93782383,0.0009921156,0.00008644919,0.00007673486,0.0014986537,0.0013503211,0.010866715],"genre_scores_gemma":[0.84742165,0.0007016422,0.13246138,0.0005059533,0.00015383458,0.00037363858,0.0020735373,0.00068216084,0.015626213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945754,0.00017035718,0.0000269048,0.00017623165,0.000100737874,0.00006814725],"domain_scores_gemma":[0.9986345,0.0008625222,0.00010641645,0.00021350876,0.00012243274,0.00006061276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084870006,0.0006577195,0.00081594265,0.0012150869,0.0006652,0.0020763632,0.0019428002,0.00151388,0.007475665],"category_scores_gemma":[0.00446942,0.0008622581,0.0016359487,0.001217455,0.001403302,0.00320331,0.0015407373,0.001966697,0.001697197],"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":[0.00011711003,0.00007617051,0.005626055,0.00013569981,0.000107343905,0.0004244125,0.0010275883,0.53893876,0.006493406,0.38913697,0.006781249,0.051135182],"study_design_scores_gemma":[0.000015181019,0.000016312924,0.0005902626,0.000019029283,0.000023338878,0.00018422061,0.000034320557,0.88884705,0.0004636635,0.10634659,0.0034385019,0.000021602275],"about_ca_topic_score_codex":0.007385026,"about_ca_topic_score_gemma":0.009196887,"teacher_disagreement_score":0.007475665,"about_ca_system_score_codex":0.0010350001,"about_ca_system_score_gemma":0.0010332714,"threshold_uncertainty_score":0.025008619},"labels":[],"label_agreement":null},{"id":"W2621376330","doi":"10.1162/tacl_a_00055","title":"Joint Modeling of Topics, Citations, and Topical Authority in Academic Corpora","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science, ICT and Future Planning","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Citation; Search engine indexing; Information retrieval; Process (computing); Joint (building); Generative grammar; Data science; Artificial intelligence; World Wide Web","score_opus":0.07106014512581252,"score_gpt":0.318250592846475,"score_spread":0.24719044772066248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621376330","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":[0.3560072,0.0077786786,0.6035477,0.0038060406,0.00045331192,0.0005694352,0.008518483,0.005805213,0.013513992],"genre_scores_gemma":[0.8158143,0.002586906,0.15588714,0.000314413,0.001016593,0.0009815642,0.015004647,0.0006796211,0.0077149044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956542,0.0022157414,0.00034091348,0.0009961798,0.0005692671,0.00022366544],"domain_scores_gemma":[0.97457707,0.019741692,0.0015250313,0.0018261218,0.0018848637,0.0004451852],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.010390579,0.0011157229,0.0015515826,0.008389806,0.0016346027,0.004208154,0.0020734398,0.0021871626,0.0024341065],"category_scores_gemma":[0.045555748,0.000909063,0.0020142193,0.010194884,0.0016084472,0.0083046695,0.0022597138,0.002778608,0.0017647923],"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":[0.0008235031,0.0007243739,0.0446758,0.00097236596,0.00065774686,0.00067392236,0.0036620614,0.552632,0.0050151516,0.08699914,0.028907582,0.27425635],"study_design_scores_gemma":[0.000054784083,0.00003389429,0.0032311315,0.00004069344,0.0000602016,0.00008290669,0.00013184587,0.9552019,0.0006297481,0.03624069,0.004258548,0.000033607183],"about_ca_topic_score_codex":0.016475938,"about_ca_topic_score_gemma":0.0224506,"teacher_disagreement_score":0.99161017,"about_ca_system_score_codex":0.0023868072,"about_ca_system_score_gemma":0.0027237453,"threshold_uncertainty_score":0.05495131},"labels":[],"label_agreement":null},{"id":"W2769298630","doi":"10.1162/tacl_a_00011","title":"Modeling Past and Future for Neural Machine Translation","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"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":"National Natural Science Foundation of China; National Science Foundation","keywords":"Machine translation; Computer science; Decoding methods; Translation (biology); German; Artificial intelligence; Natural language processing; Mechanism (biology); Speech recognition; Machine learning; Algorithm; Linguistics","score_opus":0.01634169044876612,"score_gpt":0.28153284019936564,"score_spread":0.26519114975059954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769298630","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":[0.045944355,0.0041804863,0.94020426,0.0012672617,0.0002635128,0.000035936664,0.0005661241,0.0017767523,0.005761333],"genre_scores_gemma":[0.83075124,0.0025090543,0.1570445,0.00039890656,0.0002552245,0.00015094751,0.0014286898,0.00024995787,0.007211437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996451,0.00011257095,0.000030885032,0.00012698912,0.00005607917,0.000028349104],"domain_scores_gemma":[0.9990958,0.00048010857,0.000093739785,0.00017221189,0.00012964668,0.000028424707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091359636,0.00066192704,0.000573656,0.00070674595,0.0005064672,0.0010373702,0.0011394416,0.000997578,0.0034974127],"category_scores_gemma":[0.0038847865,0.00043964028,0.00077932375,0.0009936851,0.00068613683,0.003852327,0.0009964558,0.0014965514,0.0011962759],"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":[0.00066745636,0.00013989431,0.0040025655,0.0006286479,0.00022835737,0.00068002805,0.00090586994,0.37664717,0.02355266,0.13701594,0.008923014,0.4466084],"study_design_scores_gemma":[0.000015386975,0.000045348013,0.000562121,0.00003487427,0.000068666304,0.00015421759,0.00003344014,0.9291243,0.0034203343,0.059313953,0.0072031016,0.000024265726],"about_ca_topic_score_codex":0.0052925306,"about_ca_topic_score_gemma":0.008616557,"teacher_disagreement_score":0.0052925306,"about_ca_system_score_codex":0.0007702792,"about_ca_system_score_gemma":0.00081983133,"threshold_uncertainty_score":0.011700034},"labels":[],"label_agreement":null},{"id":"W2774582842","doi":"10.1162/tacl_a_00076","title":"Joint Prediction of Word Alignment with Alignment Types","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Task (project management); Probabilistic logic; Natural language processing; Joint (building); Generative grammar; Pattern recognition (psychology)","score_opus":0.01894919867233834,"score_gpt":0.26651702727514015,"score_spread":0.2475678286028018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774582842","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":[0.16451982,0.000686596,0.82563275,0.0006548646,0.00021491,0.00013966335,0.0012148536,0.004391225,0.0025453875],"genre_scores_gemma":[0.824299,0.00022443291,0.16918427,0.0002194831,0.00015717106,0.00016710168,0.0027992928,0.0005205815,0.002428737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956328,0.0016082249,0.0002634276,0.0016449989,0.00060615275,0.00024436344],"domain_scores_gemma":[0.9849518,0.009473177,0.0017609766,0.001729292,0.0016385877,0.0004461689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038249542,0.0012038465,0.0015564909,0.0025898633,0.00072962395,0.001767745,0.0016908104,0.0019418346,0.0024511432],"category_scores_gemma":[0.019834494,0.00089378405,0.001553261,0.0023980662,0.0010780205,0.0068042637,0.0021178517,0.0036238611,0.003123739],"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":[0.0021251147,0.0008137728,0.067475684,0.00056098,0.0005576672,0.0004373915,0.0006687481,0.25853342,0.030395335,0.019005261,0.012799805,0.60662687],"study_design_scores_gemma":[0.000023634098,0.000061279214,0.0033426445,0.000016122834,0.0000353315,0.000082364,0.00005275379,0.96353,0.0037915453,0.028219473,0.00081629294,0.000028436942],"about_ca_topic_score_codex":0.0020358271,"about_ca_topic_score_gemma":0.0038919046,"teacher_disagreement_score":0.0038249542,"about_ca_system_score_codex":0.0007521151,"about_ca_system_score_gemma":0.0013714136,"threshold_uncertainty_score":0.020228505},"labels":[],"label_agreement":null},{"id":"W2799424953","doi":"10.1162/tacl_a_00018","title":"Questionable Answers in Question Answering Research: Reproducibility and Variability of Published Results","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":73,"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":"Reproducibility; Computer science; Popularity; Reliability (semiconductor); Sample (material); Field (mathematics); Range (aeronautics); Code (set theory); Artificial intelligence; Data science; Statistics; Psychology; Mathematics; Social psychology","score_opus":0.03935335336173296,"score_gpt":0.33721246740520183,"score_spread":0.2978591140434689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799424953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31482244,0.05308382,0.487966,0.082993835,0.0066912947,0.002654075,0.004265961,0.002661117,0.04486143],"genre_scores_gemma":[0.90298015,0.0033385626,0.07670691,0.009177021,0.0018074865,0.0019134573,0.0016466372,0.001162835,0.0012669717],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.2660926,0.5193769,0.061443217,0.043640055,0.1070568,0.0023904233],"domain_scores_gemma":[0.032214243,0.8001816,0.036147065,0.10371199,0.02684278,0.0009023547],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59403616,0.001063335,0.0021591543,0.009942214,0.00283769,0.011904271,0.006442023,0.0045937765,0.0026199478],"category_scores_gemma":[0.87922937,0.0017508409,0.0032391963,0.008855718,0.020076035,0.010664267,0.011398935,0.0054614185,0.0010267153],"study_design_candidate":"observational","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":[0.0035345284,0.00050509477,0.2064272,0.016835537,0.012797857,0.0015555106,0.07247434,0.011130325,0.0063079824,0.14070442,0.03080142,0.49692583],"study_design_scores_gemma":[0.00095031236,0.0010536865,0.14460945,0.016018838,0.004067644,0.0028336353,0.012597892,0.0252607,0.024863077,0.6349392,0.1318739,0.0009316446],"about_ca_topic_score_codex":0.0018055299,"about_ca_topic_score_gemma":0.0018630445,"teacher_disagreement_score":0.40596384,"about_ca_system_score_codex":0.004891441,"about_ca_system_score_gemma":0.005183619,"threshold_uncertainty_score":0.5006257},"labels":[],"label_agreement":null},{"id":"W2906152891","doi":"10.1162/tacl_a_00254","title":"Analysis Methods in Neural Language Processing: A Survey","year":2019,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":486,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Categorization; Artificial neural network; Field (mathematics); Feature (linguistics); Artificial intelligence; Point (geometry); Data science; Natural language processing; Machine learning; Linguistics","score_opus":0.029637724967615017,"score_gpt":0.3494461539490562,"score_spread":0.3198084289814412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906152891","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004142226,0.507405,0.47500902,0.0034250747,0.0008518541,0.00016084961,0.00053162826,0.00094141375,0.0075329836],"genre_scores_gemma":[0.09496226,0.54976726,0.3416665,0.0014634586,0.0041957134,0.0005342282,0.0016020169,0.00064952386,0.005159032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962387,0.0011962429,0.00042164308,0.0006630212,0.0013786331,0.0001018874],"domain_scores_gemma":[0.989958,0.0071156304,0.00037459744,0.0005820197,0.001865727,0.00010402895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052472623,0.0011753333,0.0015038105,0.006815145,0.0005551925,0.0033278705,0.0021171414,0.0013811911,0.0033386108],"category_scores_gemma":[0.0135822585,0.0006397034,0.0013988793,0.008449441,0.0011510465,0.004993781,0.0012643527,0.0019748725,0.00211179],"study_design_candidate":"not_applicable","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":[0.000088158355,0.00011778804,0.0029042237,0.0036488199,0.00025758648,0.00007869989,0.00022937522,0.0055933446,0.0012275785,0.049447425,0.016287267,0.9201197],"study_design_scores_gemma":[0.00007161051,0.00021386819,0.008603497,0.00473148,0.00041577066,0.0011577583,0.00066121324,0.24980146,0.0070504462,0.31669512,0.41039133,0.00020645266],"about_ca_topic_score_codex":0.0026796907,"about_ca_topic_score_gemma":0.0015001078,"teacher_disagreement_score":0.006815145,"about_ca_system_score_codex":0.0013949091,"about_ca_system_score_gemma":0.0017379277,"threshold_uncertainty_score":0.027750552},"labels":[],"label_agreement":null},{"id":"W2911227954","doi":"10.1162/tacl_a_00041","title":"Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":808,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Macquarie University; York University; University of Washington; University of California, San Diego; National Science Foundation","keywords":"Embarrassment; Computer science; Natural (archaeology); Data science; Field (mathematics); Natural language; Lead (geology); Style (visual arts); Engineering ethics; Natural language processing; Psychology; Social psychology","score_opus":0.06724238139102369,"score_gpt":0.34862671363229547,"score_spread":0.2813843322412718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911227954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068340334,0.00018225149,0.9646278,0.019342646,0.00040048416,0.00091623276,0.00038868672,0.0029390063,0.004368837],"genre_scores_gemma":[0.110289656,0.0002772553,0.87141496,0.00985027,0.00045422648,0.003254656,0.0010997661,0.0012828625,0.002076316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7011495,0.2327128,0.019739613,0.013440354,0.030838603,0.002119228],"domain_scores_gemma":[0.3909179,0.3800997,0.032558627,0.12905554,0.06091979,0.006448459],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25439033,0.0012852662,0.0015191343,0.0039262646,0.0041392543,0.01144222,0.0053340346,0.004844823,0.005221077],"category_scores_gemma":[0.41203615,0.0020097855,0.0014945989,0.0037312629,0.013341458,0.03602486,0.016105805,0.012317075,0.0028403967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009271836,0.00031649193,0.009593546,0.0022633388,0.0001574796,0.00045848347,0.017378602,0.0040050917,0.008293481,0.77331114,0.026017835,0.15727735],"study_design_scores_gemma":[0.0003561995,0.00047659667,0.0015266831,0.0015883291,0.00016884407,0.00047160243,0.0035564264,0.034604494,0.021619147,0.68600714,0.24937345,0.0002509995],"about_ca_topic_score_codex":0.0013721178,"about_ca_topic_score_gemma":0.00091061817,"teacher_disagreement_score":0.74560964,"about_ca_system_score_codex":0.0030595541,"about_ca_system_score_gemma":0.011024692,"threshold_uncertainty_score":0.9194695},"labels":[],"label_agreement":null},{"id":"W3036116903","doi":"10.1162/tacl_a_00316","title":"Learning Lexical Subspaces in a Distributional Vector Space","year":2020,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Distributional semantics; Linear subspace; Artificial intelligence; Natural language processing; Similarity (geometry); Vector space; Word (group theory); Space (punctuation); Relation (database); Semantics (computer science); Semantic similarity; Suite; Code (set theory); Linguistics; Programming language; Data mining; Mathematics","score_opus":0.013875671878323446,"score_gpt":0.2681135972948576,"score_spread":0.25423792541653417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036116903","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":[0.055032782,0.0007160115,0.9394506,0.0004169782,0.000048225847,0.00007728327,0.0007656198,0.0016939209,0.0017987245],"genre_scores_gemma":[0.5963921,0.0008294194,0.38916337,0.00047889806,0.00016655552,0.00034509588,0.007380394,0.00040524727,0.004838897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813145,0.0006467518,0.0001342734,0.00064173125,0.00030551146,0.00014030767],"domain_scores_gemma":[0.99808264,0.0008137062,0.00021507099,0.0003656897,0.0003592963,0.00016355871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017422653,0.0011632977,0.0013780601,0.002530649,0.0006995851,0.002564076,0.0013695849,0.0011629409,0.002647024],"category_scores_gemma":[0.0055560893,0.00052513665,0.0011599815,0.0024954777,0.0010757794,0.0060747922,0.0031297496,0.0020186738,0.0016383686],"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":[0.0005051931,0.00053411076,0.017444262,0.0004795365,0.00031198096,0.0003299372,0.0010401017,0.12514746,0.009618644,0.14221428,0.015902992,0.6864715],"study_design_scores_gemma":[0.000024378796,0.00013504457,0.001144367,0.000052317115,0.000021308386,0.000109905275,0.00032571342,0.77694535,0.0012299297,0.21574076,0.0042360565,0.00003492108],"about_ca_topic_score_codex":0.0024928297,"about_ca_topic_score_gemma":0.0041198484,"teacher_disagreement_score":0.002647024,"about_ca_system_score_codex":0.0008138457,"about_ca_system_score_gemma":0.0009682217,"threshold_uncertainty_score":0.009214044},"labels":[],"label_agreement":null},{"id":"W3127907679","doi":"10.1162/tacl_a_00378","title":"A Computational Framework for Slang Generation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Swearing, Euphemism, Multilingualism","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Slang; Natural language; Word (group theory); Interpretation (philosophy); Construct (python library); Inference; Meaning (existential); Probabilistic logic","score_opus":0.04744032429022425,"score_gpt":0.3581615381772568,"score_spread":0.31072121388703255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127907679","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":[0.010934395,0.00005998857,0.9850853,0.00043552704,0.0000277188,0.00004805227,0.0001395601,0.00040379167,0.0028657485],"genre_scores_gemma":[0.5875412,0.00007923697,0.408675,0.00019151688,0.00006565655,0.0001961373,0.00051621976,0.0001871898,0.0025478736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984717,0.00072832115,0.000073117335,0.00033432854,0.0002862149,0.000106360145],"domain_scores_gemma":[0.99575764,0.0029850453,0.00026447236,0.00049297075,0.00036811683,0.00013174406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020702435,0.00046845264,0.0004971514,0.0016130466,0.0010763895,0.0018911355,0.0023949894,0.0010384693,0.006742869],"category_scores_gemma":[0.010850276,0.00045700825,0.0012454368,0.0009586507,0.0030503701,0.0033488078,0.0025683101,0.0019471713,0.0007413518],"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":[0.000050657556,0.00010003344,0.0016691777,0.00010185915,0.000039266793,0.0002237394,0.0004962777,0.3662158,0.0016246138,0.5673882,0.0026350275,0.059455466],"study_design_scores_gemma":[0.000005502819,0.0000076311035,0.00010880312,0.000009450487,0.0000026410694,0.000022837912,0.00003213946,0.80574447,0.0002566192,0.1927167,0.001085663,0.0000075310295],"about_ca_topic_score_codex":0.0063925865,"about_ca_topic_score_gemma":0.008025387,"teacher_disagreement_score":0.006742869,"about_ca_system_score_codex":0.0017518672,"about_ca_system_score_gemma":0.0014595934,"threshold_uncertainty_score":0.02255714},"labels":[],"label_agreement":null},{"id":"W3137010024","doi":"10.1162/tacl_a_00447","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":167,"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; Google (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Computer science; USable; Audit; Natural language processing; Quality (philosophy); Artificial intelligence; Information retrieval; World Wide Web; Accounting","score_opus":0.021970551721164733,"score_gpt":0.3306852318074935,"score_spread":0.30871468008632874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137010024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70204556,0.0058487775,0.059483822,0.009382596,0.0017443822,0.0026674161,0.11685233,0.0827925,0.019182699],"genre_scores_gemma":[0.51107514,0.0016432845,0.1286201,0.0025777775,0.0003854511,0.0020085403,0.3251124,0.01962509,0.00895226],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.89964235,0.028618874,0.016830813,0.010182744,0.042489927,0.0022352845],"domain_scores_gemma":[0.49999642,0.12704392,0.030558437,0.1397169,0.19572927,0.006955071],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06712028,0.0013971047,0.0013271903,0.017156474,0.0034351202,0.007021653,0.0033195333,0.0016078869,0.0013709468],"category_scores_gemma":[0.21080942,0.0016156565,0.0012024564,0.01735238,0.0035907335,0.005904365,0.007036,0.0029385095,0.0030484057],"study_design_candidate":"observational","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":[0.0021886,0.0015372297,0.27039644,0.0046564774,0.0013479162,0.0026935723,0.014175259,0.006669717,0.039679494,0.004891357,0.30200702,0.349757],"study_design_scores_gemma":[0.00040336043,0.0008357639,0.46844193,0.0022615187,0.0007260713,0.0026223608,0.00593911,0.05185007,0.08352879,0.004778695,0.37783757,0.0007747139],"about_ca_topic_score_codex":0.020012474,"about_ca_topic_score_gemma":0.028378762,"teacher_disagreement_score":0.93287975,"about_ca_system_score_codex":0.0023211828,"about_ca_system_score_gemma":0.0056340466,"threshold_uncertainty_score":0.35497022},"labels":[],"label_agreement":null},{"id":"W3151929433","doi":"10.1162/tacl_a_00360","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":602,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Kepler; Embedding; Benchmark (surveying); Language model; Representation (politics); Natural language processing; Construct (python library); ENCODE; Artificial intelligence; Programming language","score_opus":0.03147363115435537,"score_gpt":0.3240863137469095,"score_spread":0.29261268259255413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151929433","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":[0.017343387,0.0010194231,0.9703542,0.0007331039,0.00014101183,0.0001401233,0.0016710949,0.0067641637,0.001833591],"genre_scores_gemma":[0.44338354,0.0014137506,0.52432823,0.0010410087,0.0002326722,0.00087198964,0.016266946,0.0009986747,0.011463219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989231,0.00031487033,0.000081702354,0.00043364716,0.00014295544,0.000103744234],"domain_scores_gemma":[0.9974995,0.0013124248,0.00016704587,0.00054583885,0.0003765058,0.00009871783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016194383,0.0016385411,0.001056161,0.0019528219,0.0005481688,0.0018078871,0.0034889902,0.0019793813,0.0038445247],"category_scores_gemma":[0.008467794,0.00085093087,0.0015986672,0.001977759,0.00081028196,0.006360384,0.0029092887,0.0036855463,0.0026577788],"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":[0.00028600797,0.00030525678,0.0021270397,0.00033517537,0.00023734602,0.00026025754,0.0002888322,0.4736743,0.0045394814,0.020317582,0.023665605,0.47396296],"study_design_scores_gemma":[0.000011916734,0.000024553596,0.000119253804,0.000020776573,0.000021780057,0.000032804117,0.000019724419,0.9861498,0.0011783793,0.010473519,0.001935419,0.000012134307],"about_ca_topic_score_codex":0.0070424457,"about_ca_topic_score_gemma":0.010327704,"teacher_disagreement_score":0.0070424457,"about_ca_system_score_codex":0.0012970454,"about_ca_system_score_gemma":0.0016518781,"threshold_uncertainty_score":0.014002919},"labels":[],"label_agreement":null},{"id":"W3183195595","doi":"10.1162/tacl_a_00386","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"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; Huawei Technologies (Canada)","funders":"","keywords":"Adversarial system; Focus (optics); Testbed; Named-entity recognition; Training set; Noise (video); Training (meteorology)","score_opus":0.0861111343750003,"score_gpt":0.2954547619652698,"score_spread":0.20934362759026953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183195595","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":[0.27179238,0.0017042925,0.71447563,0.00088328955,0.0003390352,0.000092918504,0.0005567345,0.0060043093,0.004151265],"genre_scores_gemma":[0.93791556,0.00016918645,0.059003476,0.00030019932,0.00006552102,0.0000501406,0.0006612039,0.00024725156,0.0015874268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902916,0.00047615482,0.00004290468,0.0002603734,0.00009831541,0.00009307304],"domain_scores_gemma":[0.99483985,0.003737454,0.00021779668,0.0008696502,0.00023090096,0.00010440735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029144764,0.0009759403,0.00081585214,0.0003711851,0.00036974327,0.0005509856,0.0016012815,0.0011470203,0.0017256653],"category_scores_gemma":[0.00915727,0.00048390325,0.0004993653,0.00034321786,0.0010111285,0.0018332405,0.0017110264,0.0028071604,0.00065641035],"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":[0.00037496476,0.00014750162,0.0025842236,0.00012650179,0.00010476592,0.00013006994,0.00010567938,0.8866991,0.011521505,0.003537005,0.0033603932,0.09130825],"study_design_scores_gemma":[0.000006172966,0.000038823982,0.00023046353,0.000010525906,0.000008682974,0.000022450064,0.000008732326,0.99349606,0.0040181824,0.0018034076,0.00034913188,0.0000074151726],"about_ca_topic_score_codex":0.002651697,"about_ca_topic_score_gemma":0.0036885624,"teacher_disagreement_score":0.0029144764,"about_ca_system_score_codex":0.00054259936,"about_ca_system_score_gemma":0.0005648591,"threshold_uncertainty_score":0.0154134035},"labels":[],"label_agreement":null},{"id":"W3196986263","doi":"10.1162/tacl_a_00519","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Interpretability; Computer science; Representation (politics); Artificial intelligence; Domain (mathematical analysis); Adaptation (eye); Interpretation (philosophy); Artificial neural network; Domain adaptation; Machine learning; Natural language processing; Data science; Neuroscience","score_opus":0.054858845230862235,"score_gpt":0.2844312671001392,"score_spread":0.22957242186927698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196986263","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020294465,0.032936275,0.9260633,0.004829828,0.00015602545,0.00008171075,0.00080219866,0.0013040915,0.013532088],"genre_scores_gemma":[0.6195332,0.050684128,0.31924403,0.0010392929,0.00044834486,0.0001920197,0.002043397,0.0005978137,0.0062178117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987226,0.00052916567,0.00010950216,0.00020461988,0.0003767159,0.000057324898],"domain_scores_gemma":[0.9975198,0.0015539634,0.00015062556,0.00039334924,0.00032381245,0.000058389138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021138329,0.0007394412,0.00081174565,0.002120973,0.00029689932,0.003687259,0.0026090988,0.0012810542,0.003743128],"category_scores_gemma":[0.006304968,0.0005866983,0.0010874562,0.0021641839,0.0015108688,0.0047296598,0.0016972237,0.0019467301,0.00094471086],"study_design_candidate":"not_applicable","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":[0.00012235277,0.00012730672,0.004502519,0.0017825096,0.00028730274,0.00039326932,0.0009402689,0.17680863,0.0031974446,0.36380273,0.008139981,0.43989575],"study_design_scores_gemma":[0.000009143918,0.000038400707,0.0008404394,0.00050024944,0.000040039977,0.00020915183,0.00024885123,0.52635133,0.0022614682,0.44402722,0.025439337,0.00003438543],"about_ca_topic_score_codex":0.0024877482,"about_ca_topic_score_gemma":0.0023142816,"teacher_disagreement_score":0.003743128,"about_ca_system_score_codex":0.0017180706,"about_ca_system_score_gemma":0.0011375167,"threshold_uncertainty_score":0.012522042},"labels":[],"label_agreement":null},{"id":"W3198711991","doi":"10.1162/tacl_a_00478","title":"It’s not Rocket Science: Interpreting Figurative Language in Narratives","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"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":"Literal and figurative language; Computer science; Natural language processing; Principle of compositionality; Narrative; Generative grammar; Interpretation (philosophy); Artificial intelligence; Linguistics; Context (archaeology); Expression (computer science); Programming language; History","score_opus":0.012093882901237876,"score_gpt":0.3034295858987213,"score_spread":0.29133570299748346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198711991","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":[0.7994957,0.0023724863,0.16230823,0.0040067197,0.00028059634,0.00034729514,0.0073010004,0.004466206,0.019421685],"genre_scores_gemma":[0.9297994,0.00037170088,0.06238274,0.0002950877,0.00003712642,0.00006407498,0.0051535526,0.00015754184,0.0017388762],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988996,0.00070530886,0.00004643949,0.00022707337,0.00007719911,0.000044423818],"domain_scores_gemma":[0.9926323,0.005790607,0.00044184583,0.0007236254,0.0002859941,0.00012561097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019888207,0.0009794856,0.00023556306,0.0010159275,0.000521685,0.0026538495,0.0010459985,0.0013094777,0.0035422123],"category_scores_gemma":[0.015115927,0.0003454076,0.00072251644,0.0006158512,0.001275472,0.0048800167,0.0010582352,0.0014322174,0.0013064706],"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":[0.0017627584,0.0006217144,0.09854395,0.003207957,0.00043235757,0.0043288446,0.051030107,0.15198609,0.036406465,0.06904928,0.045773596,0.53685683],"study_design_scores_gemma":[0.000100528654,0.0002337553,0.021364786,0.0007934897,0.00013292822,0.002029757,0.011199162,0.7836898,0.029771745,0.06796018,0.08251569,0.00020806614],"about_ca_topic_score_codex":0.0049745715,"about_ca_topic_score_gemma":0.008166929,"teacher_disagreement_score":0.0049745715,"about_ca_system_score_codex":0.0011422249,"about_ca_system_score_gemma":0.0006394879,"threshold_uncertainty_score":0.01184988},"labels":[],"label_agreement":null},{"id":"W3206313044","doi":"10.1162/tacl_a_00441","title":"Quantifying Cognitive Factors in Lexical Decline","year":2021,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"German; Lexical diversity; Variety (cybernetics); Affect (linguistics); Cognition; Linguistics; Set (abstract data type); Logistic regression; Ecological niche; Psychology; Cognitive psychology; Computer science; Artificial intelligence; Ecology; Biology; Vocabulary; Communication","score_opus":0.06521040049384863,"score_gpt":0.36774251653791246,"score_spread":0.3025321160440638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206313044","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":[0.9960663,0.00010437996,0.0016866585,0.000039213475,0.0000024323147,0.000014197738,0.00019446608,0.000016371836,0.0018760489],"genre_scores_gemma":[0.9993461,0.000017426617,0.0003499872,0.000007779392,0.0000034596778,0.000008502585,0.00017034223,0.000005512755,0.000090877526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988953,0.00031308807,0.00010982901,0.00032275065,0.00023686534,0.00012217808],"domain_scores_gemma":[0.97660214,0.014720958,0.0044941534,0.001215413,0.0021611606,0.0008062581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027706942,0.00042642507,0.000435402,0.0033070776,0.00048956677,0.002139625,0.00052375544,0.000746868,0.0025924055],"category_scores_gemma":[0.03317388,0.0002198582,0.00037093554,0.002344891,0.0015332374,0.0022007874,0.0011670275,0.0006514678,0.00034769764],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025236717,0.00011337478,0.97491574,0.00006987963,0.00008791062,0.00015415587,0.0015708357,0.0030439293,0.0031554447,0.001222322,0.00013287635,0.015281204],"study_design_scores_gemma":[0.0000052897044,0.0000812061,0.9886615,0.000013964628,0.000025266281,0.00013151004,0.0011622556,0.005076732,0.0007808185,0.0036648738,0.00037446257,0.000022119044],"about_ca_topic_score_codex":0.005009676,"about_ca_topic_score_gemma":0.0040842704,"teacher_disagreement_score":0.005009676,"about_ca_system_score_codex":0.0007309626,"about_ca_system_score_gemma":0.0003340903,"threshold_uncertainty_score":0.014652967},"labels":[],"label_agreement":null},{"id":"W3207937903","doi":"10.1162/tacl_a_00416","title":"MasakhaNER: Named Entity Recognition for African Languages","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":235,"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; Google (Canada)","funders":"","keywords":"Computer science; Named-entity recognition; Variety (cybernetics); Natural language processing; Artificial intelligence; Representation (politics); Code (set theory); Quality (philosophy); Data science; Information retrieval; Programming language; Task (project management); Political science","score_opus":0.024774853785437097,"score_gpt":0.27454927867574097,"score_spread":0.24977442489030388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207937903","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12734428,0.0051169107,0.100572236,0.005284137,0.0019121146,0.0018048099,0.5555237,0.18422633,0.018215438],"genre_scores_gemma":[0.1003961,0.0009504109,0.10636958,0.00058472034,0.00022075714,0.0013371044,0.7819177,0.0018415326,0.0063821203],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968129,0.0011336047,0.0003197939,0.0008801511,0.00054324174,0.00031032934],"domain_scores_gemma":[0.9954313,0.0015477785,0.00036770187,0.001680911,0.00061035616,0.0003618619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004316772,0.0022081567,0.0013965566,0.0047165514,0.0021673723,0.0027111422,0.0028022912,0.0019764446,0.012045322],"category_scores_gemma":[0.0110689765,0.0007505238,0.001626501,0.003952262,0.00084892125,0.0073099267,0.0051943846,0.0030490248,0.015280195],"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":[0.0017969569,0.00081522035,0.013343049,0.0021741376,0.00044588756,0.000940068,0.00095022394,0.014205088,0.012753737,0.010503031,0.72939986,0.2126728],"study_design_scores_gemma":[0.00096690655,0.0006499147,0.030581031,0.00070554705,0.00040052994,0.0021771751,0.0019073321,0.26418003,0.054028288,0.02406138,0.6198926,0.00044921867],"about_ca_topic_score_codex":0.0118306065,"about_ca_topic_score_gemma":0.013772555,"teacher_disagreement_score":0.012045322,"about_ca_system_score_codex":0.0011111832,"about_ca_system_score_gemma":0.0025695954,"threshold_uncertainty_score":0.0402956},"labels":[],"label_agreement":null},{"id":"W3208625967","doi":"10.1162/tacl_a_00427","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Government of Canada; National Endowment for the Humanities; National Science Foundation","keywords":"Computer science; Decoding methods; Optical character recognition; Consistency (knowledge bases); Artificial intelligence; Natural language processing; Language model; Raw data; Vocabulary; Error detection and correction; Machine learning; Speech recognition; Image (mathematics); Algorithm","score_opus":0.013893598658533842,"score_gpt":0.26406367339091125,"score_spread":0.2501700747323774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208625967","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":[0.037639212,0.00015255071,0.9543724,0.00011330295,0.000058722522,0.00008650655,0.000087094784,0.0065958346,0.0008944007],"genre_scores_gemma":[0.59502137,0.00008055998,0.3996906,0.00016246068,0.000055529134,0.00024358406,0.000510118,0.00052870857,0.0037069803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984806,0.00047800664,0.0001302597,0.0003770059,0.0004385783,0.00009555593],"domain_scores_gemma":[0.9925141,0.0033108732,0.00064021314,0.0012391962,0.0021664454,0.0001291434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001381945,0.0009173825,0.000897059,0.00070100935,0.00060174643,0.0008160943,0.002388001,0.001092281,0.0024922856],"category_scores_gemma":[0.008213647,0.00045478734,0.00064998126,0.00047083246,0.0009261576,0.001442339,0.0011655472,0.0017373445,0.0016045833],"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":[0.00027452796,0.00037738596,0.0016386412,0.000234335,0.000091457536,0.00013269798,0.00022394251,0.2345565,0.058128852,0.0027870866,0.002455893,0.6990987],"study_design_scores_gemma":[0.0000050903145,0.000038463142,0.00020366104,0.000006975134,0.000005896439,0.000028969418,0.00001529363,0.98036516,0.017891878,0.001065004,0.00036439812,0.000009274471],"about_ca_topic_score_codex":0.004704421,"about_ca_topic_score_gemma":0.010346983,"teacher_disagreement_score":0.004704421,"about_ca_system_score_codex":0.00082775805,"about_ca_system_score_gemma":0.0016326444,"threshold_uncertainty_score":0.009354055},"labels":[],"label_agreement":null},{"id":"W3213458975","doi":"10.1162/tacl_a_00419","title":"<scp>ParsiNLU</scp>: A Suite of Language Understanding Challenges for Persian","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada); International Medias Data Services (Canada)","funders":"","keywords":"Computer science; Natural language understanding; Natural language processing; Suite; Benchmark (surveying); Artificial intelligence; Persian; Natural language; Linguistics","score_opus":0.053844189722149584,"score_gpt":0.28161477226806203,"score_spread":0.22777058254591245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213458975","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":[0.6244645,0.010143142,0.048771054,0.016925117,0.0021807386,0.0005722797,0.18911153,0.048113808,0.059717897],"genre_scores_gemma":[0.60130185,0.0011557904,0.043444943,0.0017260293,0.00036799506,0.0004199042,0.34032878,0.0017359968,0.009518782],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99752575,0.0010414777,0.00019295223,0.00062146573,0.00043827758,0.0001799329],"domain_scores_gemma":[0.9946214,0.0025354326,0.00020100563,0.0010353022,0.0012672788,0.00033962476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020708523,0.0019299705,0.0008625564,0.0029155158,0.0022568882,0.0021855503,0.0016472975,0.0016759759,0.0078751715],"category_scores_gemma":[0.009059928,0.0002945137,0.0006941662,0.0029611925,0.0012440592,0.0039162855,0.0028468135,0.0018288923,0.005960732],"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":[0.00073087745,0.00044177094,0.014574258,0.0017320957,0.00019055043,0.003280389,0.0035336134,0.019816294,0.00939104,0.00863805,0.61807954,0.3195915],"study_design_scores_gemma":[0.00041758188,0.000474011,0.05564914,0.0007659082,0.0001663215,0.0059808455,0.017981257,0.1691344,0.057866875,0.05207434,0.63911057,0.0003787563],"about_ca_topic_score_codex":0.025297292,"about_ca_topic_score_gemma":0.032802656,"teacher_disagreement_score":0.025297292,"about_ca_system_score_codex":0.0016360655,"about_ca_system_score_gemma":0.0024148687,"threshold_uncertainty_score":0.05030006},"labels":[],"label_agreement":null},{"id":"W4221053465","doi":"10.1162/tacl_a_00458","title":"Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Inference; Generalization; Introspection; Spurious relationship; Machine learning; Rule of inference; Natural language; Natural (archaeology); Overfitting; Artificial neural network; Cognitive psychology","score_opus":0.01236504266629197,"score_gpt":0.2721111208052126,"score_spread":0.25974607813892064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221053465","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":[0.020584852,0.00027885425,0.9748824,0.0004582441,0.000036207643,0.000061128696,0.00014010858,0.0012879563,0.0022701996],"genre_scores_gemma":[0.7641208,0.00022189441,0.23333044,0.00020865757,0.00005914608,0.00015733199,0.00026786106,0.00011301127,0.0015207307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874544,0.00051897427,0.00007245454,0.0002496143,0.00032022604,0.00009310909],"domain_scores_gemma":[0.99690944,0.0017125926,0.00028936792,0.0006043874,0.00037113644,0.00011309936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018431821,0.0005528256,0.00063372304,0.0008508851,0.00045766545,0.0014039811,0.0017927582,0.0006745504,0.0031331866],"category_scores_gemma":[0.0066421763,0.00033350286,0.0011320383,0.0005914749,0.0017912085,0.0027184607,0.0015744091,0.0020966379,0.00040301945],"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":[0.00020577153,0.00018852933,0.0017939106,0.00020107446,0.00014037311,0.00031224728,0.0003263401,0.6272089,0.0048861885,0.20202866,0.0027422162,0.15996574],"study_design_scores_gemma":[0.00001037496,0.000015300271,0.00009419651,0.000008019105,0.000009638651,0.0000228229,0.0000070465367,0.9390288,0.0006276523,0.059622042,0.00054721313,0.0000069128746],"about_ca_topic_score_codex":0.005793418,"about_ca_topic_score_gemma":0.008246122,"teacher_disagreement_score":0.005793418,"about_ca_system_score_codex":0.0016618416,"about_ca_system_score_gemma":0.0020159255,"threshold_uncertainty_score":0.012057543},"labels":[],"label_agreement":null},{"id":"W4226059645","doi":"10.1162/tacl_a_00471","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Minnow Environmental (Canada); Research Canada; Microsoft (Canada); McGill University","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Conversation; Computer science; Question answering; Open domain; Domain (mathematical analysis); Information retrieval; Interdependence; Natural language processing; Artificial intelligence; Relevance (law); Code (set theory); Linguistics; Set (abstract data type)","score_opus":0.015187584352610738,"score_gpt":0.25792401609927124,"score_spread":0.24273643174666049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226059645","genre_codex":"dataset","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":[0.21077205,0.012377717,0.21660125,0.0051048356,0.0017385945,0.0050865244,0.3328103,0.18974109,0.025767628],"genre_scores_gemma":[0.291302,0.00088209467,0.20516017,0.0017817171,0.00039242097,0.003031041,0.48823872,0.0015715217,0.0076402943],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99447244,0.0023815425,0.0003820398,0.0016350816,0.00076294184,0.0003658794],"domain_scores_gemma":[0.9894555,0.005302078,0.00042679417,0.002410132,0.0016174435,0.0007880501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041930336,0.0024624004,0.0013719068,0.003432803,0.001971981,0.0026590226,0.0044109654,0.0030631414,0.007699486],"category_scores_gemma":[0.020064658,0.0006903227,0.0019215929,0.0024376323,0.0009859382,0.005132341,0.005119776,0.0035130072,0.006802582],"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":[0.00328068,0.0018235833,0.01207427,0.0049089156,0.00063587487,0.0010127898,0.0030712718,0.03275208,0.02015776,0.008756197,0.6344944,0.27703208],"study_design_scores_gemma":[0.0010290723,0.0008591131,0.015385165,0.00048760648,0.0003217899,0.0011904399,0.0022608284,0.6801566,0.023591295,0.02129519,0.25304788,0.00037505914],"about_ca_topic_score_codex":0.039864566,"about_ca_topic_score_gemma":0.045868874,"teacher_disagreement_score":0.039864566,"about_ca_system_score_codex":0.0024400011,"about_ca_system_score_gemma":0.0031037575,"threshold_uncertainty_score":0.07926506},"labels":[],"label_agreement":null},{"id":"W4285138469","doi":"10.1162/tacl_a_00487","title":"Heterogeneous Supervised Topic Models","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":10,"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; Mila - Quebec Artificial Intelligence Institute","funders":"Office of Naval Research; Simons Foundation; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Computer science; Inference; Artificial intelligence; Outcome (game theory); Machine learning; Topic model; Bayes' theorem; Bayesian inference; Latent variable; Language model; Bayesian probability; Natural language processing; Probabilistic logic; Tone (literature); Linguistics","score_opus":0.043110221112365184,"score_gpt":0.32375089316931716,"score_spread":0.280640672056952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285138469","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":[0.09319498,0.0011810911,0.8991059,0.0012079036,0.00015698982,0.00012844872,0.0013614288,0.0010433345,0.002619868],"genre_scores_gemma":[0.9010714,0.0005177825,0.08842243,0.00030644645,0.00053973764,0.00027815445,0.0030937055,0.00022591183,0.0055443607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719256,0.0015122871,0.00012574643,0.0007497307,0.00025806756,0.00016164247],"domain_scores_gemma":[0.9859291,0.011291061,0.0008556317,0.000882067,0.00085968577,0.00018249151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055256085,0.001037423,0.0015834174,0.0018084612,0.00066263555,0.0017145844,0.0024817877,0.0018815026,0.003574236],"category_scores_gemma":[0.015116297,0.0006279444,0.001554629,0.0016057565,0.0012006727,0.0030596298,0.0012240584,0.0024888772,0.001135734],"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":[0.00044696275,0.00023764289,0.007444682,0.0003188367,0.0003539177,0.00022908338,0.00051292765,0.81522673,0.0017427471,0.054147914,0.008340361,0.11099816],"study_design_scores_gemma":[0.00001033277,0.000009427908,0.00026104215,0.000010410643,0.000010645904,0.000012608694,0.000010413394,0.9825963,0.00015222069,0.01663852,0.0002828065,0.000005456902],"about_ca_topic_score_codex":0.004565104,"about_ca_topic_score_gemma":0.0063799573,"teacher_disagreement_score":0.0055256085,"about_ca_system_score_codex":0.0012327665,"about_ca_system_score_gemma":0.000775667,"threshold_uncertainty_score":0.029222548},"labels":[],"label_agreement":null},{"id":"W4287120901","doi":"10.1162/tacl_a_00492","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"Defense Advanced Research Projects Agency","keywords":"Computer science; Artificial intelligence; Transformer; Natural language processing; Classifier (UML); Machine learning; Labeled data; Task (project management); Distillation; Language model","score_opus":0.012829661286926128,"score_gpt":0.2278401156433895,"score_spread":0.21501045435646338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287120901","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":[0.17636134,0.0007228936,0.7923977,0.0022512237,0.00040315287,0.00028205922,0.003608165,0.013176553,0.010796974],"genre_scores_gemma":[0.6470042,0.00016514186,0.3397616,0.00041239272,0.000099164674,0.00032401734,0.00590084,0.0007953396,0.0055372184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982247,0.0010025067,0.000056768735,0.0003669994,0.00027577847,0.00007326284],"domain_scores_gemma":[0.99004793,0.007523117,0.00024122754,0.0013813397,0.00063211535,0.00017425862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027076362,0.0008602803,0.00048027412,0.00053639576,0.00056359987,0.0010477084,0.0014526291,0.0012586011,0.0040445435],"category_scores_gemma":[0.015430701,0.0003060373,0.0005009374,0.0005995124,0.0012895856,0.0031716696,0.0019122087,0.0018574374,0.0016790696],"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":[0.0010519257,0.0006229797,0.003493272,0.0006655763,0.00013124397,0.00054170965,0.0008018955,0.57675785,0.012920911,0.063366696,0.0351302,0.3045157],"study_design_scores_gemma":[0.000050557283,0.000051558174,0.00015482171,0.000016807686,0.000006946076,0.000040284183,0.00006872984,0.9605917,0.0093613975,0.025367115,0.004277063,0.000012997452],"about_ca_topic_score_codex":0.0021027985,"about_ca_topic_score_gemma":0.0036578614,"teacher_disagreement_score":0.0040445435,"about_ca_system_score_codex":0.0008224361,"about_ca_system_score_gemma":0.0006645097,"threshold_uncertainty_score":0.014319479},"labels":[],"label_agreement":null},{"id":"W4296711106","doi":"10.1162/tacl_a_00506","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"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; Spurious relationship; Benchmark (surveying); Attribution; Artificial intelligence; Natural language processing; Grounded theory; Data science; Machine learning; Qualitative research","score_opus":0.04673618613088275,"score_gpt":0.30956918011848517,"score_spread":0.2628329939876024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296711106","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":[0.73103005,0.01103184,0.15626968,0.0015897434,0.0015991917,0.0019223475,0.029711638,0.042405706,0.024439735],"genre_scores_gemma":[0.8645595,0.0006093174,0.06819958,0.000445379,0.0002618006,0.0011525924,0.057925884,0.0015903887,0.005255618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9777314,0.014776288,0.0011039358,0.0031783422,0.0024833926,0.0007266432],"domain_scores_gemma":[0.96450174,0.021673985,0.0016378951,0.0056798817,0.004821747,0.001684825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01285615,0.0028834313,0.0013141662,0.003055743,0.0012040054,0.0028749462,0.0025310463,0.0026465117,0.0038888773],"category_scores_gemma":[0.05178178,0.0005784282,0.0010920241,0.0018417037,0.0014094716,0.003660867,0.0047868458,0.0030145852,0.0033331919],"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":[0.007725429,0.004401443,0.05878584,0.0056298,0.0015873449,0.000884786,0.005734972,0.21265575,0.030051304,0.008207325,0.12640616,0.5379299],"study_design_scores_gemma":[0.0010292466,0.0050476273,0.054935865,0.0007914133,0.00039167807,0.00075554755,0.0041089244,0.7847366,0.059958328,0.022159478,0.065623224,0.00046207898],"about_ca_topic_score_codex":0.005043851,"about_ca_topic_score_gemma":0.0072882837,"teacher_disagreement_score":0.01285615,"about_ca_system_score_codex":0.001877344,"about_ca_system_score_gemma":0.001374885,"threshold_uncertainty_score":0.06799066},"labels":[],"label_agreement":null},{"id":"W4307680525","doi":"10.1162/tacl_a_00545","title":"Generative Spoken Dialogue Language Modeling","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Paralanguage; Computer science; Transformer; Spoken language; Generative grammar; Speech recognition; Natural language processing; Laughter; Language model; Artificial intelligence; Communication; Psychology","score_opus":0.03106876500409547,"score_gpt":0.2777580017736145,"score_spread":0.246689236769519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307680525","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":[0.023002263,0.00042965912,0.9671104,0.00049681804,0.00012103909,0.00006603313,0.00083720003,0.0025696952,0.00536694],"genre_scores_gemma":[0.81064475,0.00028495124,0.17178015,0.00038248836,0.00013653177,0.00028184318,0.0021113798,0.00055173214,0.013826091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958843,0.00016568485,0.000014808523,0.000121512305,0.000071107825,0.000038510923],"domain_scores_gemma":[0.99944645,0.00035493073,0.00002593448,0.00006309454,0.00007718395,0.00003228414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049640134,0.00071427744,0.00052026653,0.00045562137,0.00025790583,0.0008967351,0.0015859085,0.001001605,0.006105737],"category_scores_gemma":[0.0018760302,0.00044770577,0.0010897991,0.00029563645,0.0005971885,0.0007330337,0.0012271286,0.0013124814,0.0014856282],"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":[0.00011820755,0.00006031333,0.0008217345,0.00012561846,0.00009771445,0.00023384659,0.00036048205,0.8972139,0.0056109745,0.036701065,0.004247938,0.054408234],"study_design_scores_gemma":[0.0000053985214,0.0000060641546,0.000036983718,0.0000035122453,0.0000037941345,0.000016078844,0.0000070137903,0.9925356,0.0004099288,0.006069771,0.00090235216,0.0000034788727],"about_ca_topic_score_codex":0.003346221,"about_ca_topic_score_gemma":0.003912078,"teacher_disagreement_score":0.006105737,"about_ca_system_score_codex":0.00065837236,"about_ca_system_score_gemma":0.0005910396,"threshold_uncertainty_score":0.020425797},"labels":[],"label_agreement":null},{"id":"W4312516176","doi":"10.1162/tacl_a_00511","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Causal inference; Computer science; Interpretability; Inference; Artificial intelligence; Causality (physics); Natural language processing; Robustness (evolution); Machine learning; Interpretation (philosophy); Data science; Econometrics","score_opus":0.008751666553274558,"score_gpt":0.26541263141212373,"score_spread":0.25666096485884915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312516176","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":[0.006548898,0.008914301,0.9654197,0.014036601,0.00024237428,0.00009624548,0.0004610413,0.0004408295,0.0038400418],"genre_scores_gemma":[0.6168602,0.01481231,0.3547273,0.004995914,0.0036075239,0.0006780988,0.0013720113,0.0004345402,0.0025121071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9587908,0.033040702,0.0013193854,0.0035924145,0.0028366959,0.000419992],"domain_scores_gemma":[0.6363848,0.3413191,0.0070098923,0.009663693,0.0048919134,0.00073055405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052185364,0.001321264,0.0025606796,0.0055780527,0.0018762801,0.009268486,0.0036120897,0.0031571547,0.0057395264],"category_scores_gemma":[0.22255951,0.0013560724,0.0021597391,0.005388177,0.011311748,0.013101841,0.005131652,0.007863645,0.00091602566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012695204,0.000083097504,0.007146084,0.0009523456,0.00046653298,0.00024919538,0.0010441217,0.038596474,0.0003530164,0.8501629,0.0061941594,0.09462497],"study_design_scores_gemma":[0.0000133696785,0.00000948745,0.00051978166,0.00022890502,0.000034480116,0.000041199033,0.00006605686,0.0632639,0.00014823866,0.9326429,0.003011555,0.000020156313],"about_ca_topic_score_codex":0.0064282916,"about_ca_topic_score_gemma":0.003429423,"teacher_disagreement_score":0.052185364,"about_ca_system_score_codex":0.0035563917,"about_ca_system_score_gemma":0.0039088055,"threshold_uncertainty_score":0.2759859},"labels":[],"label_agreement":null},{"id":"W4313459314","doi":"10.1162/tacl_a_00524","title":"The Emergence of Argument Structure in Artificial Languages","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Language and cultural evolution","field":"Social Sciences","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":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Word order; Transitive relation; Predicate (mathematical logic); Natural language processing; Contrast (vision); Artificial intelligence; Argument (complex analysis); Sentence; Natural language; Relation (database); Object (grammar); Verb; Mathematics; Programming language","score_opus":0.012503081893501404,"score_gpt":0.29884191553172335,"score_spread":0.28633883363822193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313459314","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":[0.8894517,0.00015510105,0.10324815,0.00075732,0.000019411027,0.00004348811,0.00015233383,0.00042578316,0.005746733],"genre_scores_gemma":[0.98541844,0.000026035988,0.014060501,0.000032030737,0.000009695964,0.00003047494,0.000081851336,0.00005373038,0.00028716153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640626,0.002167649,0.00019701972,0.00044000012,0.0006176312,0.00017136906],"domain_scores_gemma":[0.96628475,0.02448543,0.0039012842,0.002612093,0.0017949971,0.000921459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029847368,0.0002593906,0.00056229363,0.001344941,0.00082775654,0.0026957558,0.00061193487,0.0009699428,0.0020637263],"category_scores_gemma":[0.026546612,0.0005428841,0.0005022924,0.00092411746,0.0041857287,0.004273042,0.0023444984,0.0014516279,0.00018224824],"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":[0.0010245527,0.0004547041,0.06496318,0.00069783826,0.00024657082,0.0024272646,0.013216633,0.08834636,0.122024804,0.635683,0.0020392167,0.068875924],"study_design_scores_gemma":[0.00012419978,0.00044331426,0.03930751,0.0000859986,0.000069621674,0.0010682005,0.0024061827,0.35265112,0.025404206,0.57189065,0.006442546,0.00010638872],"about_ca_topic_score_codex":0.00052081526,"about_ca_topic_score_gemma":0.0004719925,"teacher_disagreement_score":0.0029847368,"about_ca_system_score_codex":0.0012745715,"about_ca_system_score_gemma":0.0004747305,"threshold_uncertainty_score":0.015784979},"labels":[],"label_agreement":null},{"id":"W4313459318","doi":"10.1162/tacl_a_00529","title":"<scp>FaithDial</scp>: A Faithful Benchmark for Information-Seeking Dialogue","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Benchmark (surveying); Computer science; Utterance; Hallucinating; Natural language processing; Artificial intelligence; Crowdsourcing; Machine learning; World Wide Web","score_opus":0.012802059413064245,"score_gpt":0.23327537375003826,"score_spread":0.220473314336974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313459318","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":[0.63366073,0.00894468,0.16756919,0.0037707202,0.0031100567,0.0025518616,0.055120267,0.086245805,0.039026666],"genre_scores_gemma":[0.75801027,0.00062405487,0.11138412,0.0010192979,0.00041177648,0.0011389221,0.11325579,0.002625508,0.011530277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99071336,0.005456122,0.0004929999,0.0016526806,0.0012531548,0.00043166088],"domain_scores_gemma":[0.9827779,0.009158574,0.00065969565,0.0034600128,0.002586874,0.0013568354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069312924,0.0025942014,0.0010373964,0.002702551,0.0017454464,0.0027569104,0.0028962754,0.00326904,0.0062167747],"category_scores_gemma":[0.026048586,0.00046189944,0.0012759641,0.0012932185,0.0016966413,0.0031484384,0.004144596,0.0029489922,0.0044606905],"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":[0.006063689,0.004719162,0.017323036,0.005191254,0.0009193003,0.0015230889,0.0039719245,0.12583335,0.043824118,0.008591704,0.24759313,0.5344463],"study_design_scores_gemma":[0.0009337985,0.0039047725,0.020055862,0.0004995764,0.00020500069,0.0013770428,0.0032031864,0.7813051,0.07424955,0.016947102,0.09688436,0.00043474374],"about_ca_topic_score_codex":0.0092393,"about_ca_topic_score_gemma":0.014117369,"teacher_disagreement_score":0.0092393,"about_ca_system_score_codex":0.0017298006,"about_ca_system_score_gemma":0.0013571933,"threshold_uncertainty_score":0.036656618},"labels":[],"label_agreement":null},{"id":"W4317897852","doi":"10.1162/tacl_a_00539","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Naturalness; Natural language processing; Machine translation; Artificial intelligence; Modular design; Process (computing); Annotation; Benchmark (surveying); Information retrieval; Programming language","score_opus":0.039882268698897924,"score_gpt":0.31943519721844155,"score_spread":0.2795529285195436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317897852","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":[0.1761277,0.0027197285,0.49184614,0.0019973363,0.0023476917,0.0037198788,0.19048384,0.09455238,0.03620532],"genre_scores_gemma":[0.2140879,0.00029963805,0.36212668,0.00057752256,0.00016969808,0.0037124245,0.40910858,0.0029006333,0.0070169396],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99248356,0.0030426825,0.0007109788,0.0023345817,0.0011060253,0.00032221264],"domain_scores_gemma":[0.9879822,0.0036359418,0.00057490537,0.003953732,0.0031680206,0.00068521785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057684584,0.0015601098,0.0008414801,0.0030258563,0.00195977,0.002244485,0.0026670469,0.0015489535,0.005085057],"category_scores_gemma":[0.018401427,0.0004998351,0.0016040136,0.001702635,0.001114367,0.0028563521,0.006356001,0.002460239,0.0051294663],"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":[0.002467707,0.0017418885,0.020375872,0.004620685,0.00056692126,0.0018570736,0.010099903,0.029430669,0.06755533,0.019004676,0.31922954,0.5230498],"study_design_scores_gemma":[0.0005220053,0.0007840219,0.032792415,0.00087971834,0.00028119577,0.0014665755,0.0077177044,0.22366853,0.07518837,0.020573758,0.6355611,0.0005645612],"about_ca_topic_score_codex":0.0057424577,"about_ca_topic_score_gemma":0.011217095,"teacher_disagreement_score":0.0057684584,"about_ca_system_score_codex":0.001149979,"about_ca_system_score_gemma":0.0020503406,"threshold_uncertainty_score":0.030506909},"labels":[],"label_agreement":null},{"id":"W4381686872","doi":"10.1162/tacl_a_00564","title":"Questions Are All You Need to Train a Dense Passage Retriever","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"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; Mila - Quebec Artificial Intelligence Institute","funders":"DeepMind","keywords":"Computer science; Initialization; Code (set theory); Task (project management); Set (abstract data type); Encoder; Artificial intelligence; Information retrieval; Scheme (mathematics); Training set; Domain (mathematical analysis); Language model; Natural language processing; Machine learning","score_opus":0.030327127669755687,"score_gpt":0.2833717000899555,"score_spread":0.2530445724201998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381686872","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":[0.030926432,0.0009200069,0.915548,0.0010389492,0.00036328015,0.00033195474,0.002370875,0.043448154,0.0050523425],"genre_scores_gemma":[0.36474124,0.00048122235,0.60400504,0.0016328715,0.0003314927,0.0005021151,0.01096152,0.003015699,0.014328825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987608,0.00036985826,0.000076104254,0.0004994872,0.00019573422,0.00009803634],"domain_scores_gemma":[0.9974956,0.0012442976,0.00007598365,0.00071931875,0.0003563901,0.000108357985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022639849,0.0011000491,0.0011488792,0.0007977537,0.00053327536,0.0017151737,0.0020977736,0.0018206605,0.014852851],"category_scores_gemma":[0.0092214085,0.0006025795,0.0013267644,0.00056898437,0.0009781343,0.004097463,0.0024572439,0.0030813138,0.010779975],"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":[0.0008348469,0.00033718836,0.0030570242,0.00084203127,0.00024827124,0.00056660466,0.00095581496,0.07300904,0.052695207,0.016959542,0.06127658,0.7892178],"study_design_scores_gemma":[0.000120086894,0.00027919124,0.0011127241,0.00009616559,0.00012717595,0.0005483529,0.00026739988,0.8834192,0.049927082,0.028149815,0.035870858,0.0000818731],"about_ca_topic_score_codex":0.0044152937,"about_ca_topic_score_gemma":0.004821027,"teacher_disagreement_score":0.014852851,"about_ca_system_score_codex":0.00078221987,"about_ca_system_score_gemma":0.0010504614,"threshold_uncertainty_score":0.049687743},"labels":[],"label_agreement":null},{"id":"W4382449327","doi":"10.1162/tacl_a_00556","title":"Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Language model; Security token; Aggregate (composite); Exploit; Overhead (engineering); Encoder; Code (set theory); Artificial intelligence; Natural language processing; Set (abstract data type); Machine learning; Programming language","score_opus":0.042005300289154314,"score_gpt":0.28978427921608074,"score_spread":0.24777897892692644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382449327","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":[0.020907385,0.00068433036,0.93969494,0.00040428122,0.00023892686,0.00034768294,0.0011119251,0.034074266,0.0025362181],"genre_scores_gemma":[0.26034537,0.00045058088,0.72018397,0.0005412574,0.0002004548,0.00052989833,0.0051058675,0.0022494374,0.010393213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998899,0.00028981408,0.0000851709,0.00037818064,0.00021558935,0.0001323288],"domain_scores_gemma":[0.9983304,0.0005434905,0.00010835925,0.00061240053,0.00030728863,0.00009797362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018460057,0.0018475861,0.0015563731,0.0024087033,0.0006698607,0.0017106321,0.0036889045,0.001475402,0.0106222695],"category_scores_gemma":[0.0060450057,0.00077383756,0.0014893152,0.0019208593,0.0010552312,0.0046816273,0.003638043,0.002208554,0.007996951],"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":[0.00047324933,0.00043074143,0.0013464831,0.00036496986,0.00015487878,0.00036457714,0.00041739063,0.09544717,0.024709344,0.015883382,0.03080574,0.8296021],"study_design_scores_gemma":[0.00006738585,0.0002031749,0.0002706144,0.000029840874,0.00005821669,0.00017830794,0.00011561298,0.9597753,0.012495643,0.016956598,0.009801117,0.000048238897],"about_ca_topic_score_codex":0.0077317148,"about_ca_topic_score_gemma":0.0131170545,"teacher_disagreement_score":0.0106222695,"about_ca_system_score_codex":0.00091564516,"about_ca_system_score_gemma":0.0016891725,"threshold_uncertainty_score":0.035535038},"labels":[],"label_agreement":null},{"id":"W4386488973","doi":"10.1162/tacl_a_00595","title":"<b>MIRACL</b>: A Multilingual Retrieval Dataset Covering 18 Diverse Languages","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Relevance (law); Natural language processing; Information retrieval; Process (computing); Quality (philosophy); Artificial intelligence; Resource (disambiguation); World Wide Web","score_opus":0.027441409683995673,"score_gpt":0.33102321209940083,"score_spread":0.30358180241540517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386488973","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019041667,0.0013930508,0.0040184115,0.0005867735,0.00025876393,0.0004399314,0.95332134,0.012171822,0.008768313],"genre_scores_gemma":[0.009179716,0.00009346559,0.0065516345,0.00013320408,0.000028569024,0.00026119073,0.9817632,0.00033840246,0.0016506384],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99573225,0.0010675262,0.00074373366,0.00097341056,0.0010699106,0.00041309907],"domain_scores_gemma":[0.9931892,0.0015683466,0.00047018778,0.0013182411,0.002697692,0.00075638946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002839488,0.0023430488,0.0015584885,0.008977263,0.0022430175,0.0031396241,0.0026531566,0.0029793864,0.023030382],"category_scores_gemma":[0.011861596,0.0007697366,0.001334622,0.0068334173,0.0009814847,0.0034484563,0.0036414978,0.001993055,0.043897513],"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":[0.00050338526,0.00025965858,0.003980467,0.002816411,0.00016221908,0.00032845465,0.0004677125,0.0009957766,0.0079573365,0.0012197614,0.9553984,0.025910493],"study_design_scores_gemma":[0.00081470335,0.0003360078,0.026161341,0.0005403364,0.0001891932,0.0013124172,0.0015134165,0.011822992,0.012136758,0.0021710065,0.94268405,0.0003178157],"about_ca_topic_score_codex":0.03527757,"about_ca_topic_score_gemma":0.057656307,"teacher_disagreement_score":0.03527757,"about_ca_system_score_codex":0.0017853057,"about_ca_system_score_gemma":0.00242796,"threshold_uncertainty_score":0.07704425},"labels":[],"label_agreement":null},{"id":"W4390037801","doi":"10.1162/tacl_a_00627","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"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; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmark (surveying); Computer science; Speech recognition; Domain (mathematical analysis); Set (abstract data type); Productivity; Natural language processing; Test set; Test (biology); Artificial intelligence; Biology","score_opus":0.05812305070298272,"score_gpt":0.34878724945583334,"score_spread":0.2906641987528506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390037801","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14853415,0.0039276625,0.019514978,0.0015491768,0.0026000205,0.0019123617,0.7791665,0.022266991,0.020528192],"genre_scores_gemma":[0.05424718,0.00052610616,0.00978362,0.00028511763,0.0002632073,0.0009302304,0.9259215,0.00039623753,0.007646847],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983625,0.00037097587,0.0002008902,0.00037789083,0.00045097686,0.00023675954],"domain_scores_gemma":[0.9982704,0.0004125146,0.0000833612,0.00045719725,0.0005982194,0.00017835508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016123172,0.0028517502,0.0011601378,0.002197735,0.0010394328,0.0011759597,0.001630493,0.0022900007,0.014187371],"category_scores_gemma":[0.0041284985,0.00038602753,0.0010450572,0.0012722858,0.0006244834,0.0011204819,0.0018897491,0.0013747273,0.024796717],"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":[0.0027296648,0.00096390885,0.0062846714,0.0019522682,0.00031569687,0.0020890012,0.0004693149,0.0072908266,0.037050962,0.00079659675,0.7566945,0.18336253],"study_design_scores_gemma":[0.0021069949,0.0027000117,0.12753895,0.001002795,0.000568519,0.011015433,0.003192896,0.08682817,0.0729942,0.0037324035,0.68748283,0.0008367677],"about_ca_topic_score_codex":0.016124586,"about_ca_topic_score_gemma":0.022277288,"teacher_disagreement_score":0.016124586,"about_ca_system_score_codex":0.0007158857,"about_ca_system_score_gemma":0.0015242398,"threshold_uncertainty_score":0.04746145},"labels":[],"label_agreement":null},{"id":"W4394647506","doi":"10.1162/tacl_a_00670","title":"Scope Ambiguities in Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; National Research Council Canada; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Scope (computer science); Computer science; Linguistics; Cognitive science; Psychology; Programming language; Philosophy","score_opus":0.024324775830183193,"score_gpt":0.2884349640007543,"score_spread":0.2641101881705711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394647506","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":[0.32422498,0.001955675,0.66450864,0.0017971792,0.00008947296,0.00012172361,0.0010379842,0.0018619086,0.0044024996],"genre_scores_gemma":[0.9528204,0.00029830134,0.04485708,0.00017806866,0.00008096759,0.000067724475,0.0010065337,0.0001398449,0.0005511562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911237,0.006212833,0.00039819733,0.0011724443,0.00089714874,0.00019580295],"domain_scores_gemma":[0.93122303,0.06177311,0.0029612384,0.002255571,0.0013806575,0.00040644905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012148114,0.00095815846,0.0011454097,0.0024156775,0.0008754414,0.0032000912,0.0011766035,0.0011723896,0.001467629],"category_scores_gemma":[0.05126545,0.00070427475,0.0012645321,0.0022815946,0.001747151,0.004489352,0.0016169407,0.0026255946,0.00036859524],"study_design_candidate":"theoretical_or_conceptual","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":[0.0006892596,0.00019534885,0.027911369,0.00051724777,0.0004694706,0.0010804855,0.0046810526,0.7596234,0.004019022,0.10697125,0.0073307687,0.08651127],"study_design_scores_gemma":[0.000020365314,0.000021587452,0.0014829377,0.000036006015,0.000026209651,0.000076453915,0.00023191486,0.90921956,0.00057952484,0.087237135,0.001040671,0.000027618986],"about_ca_topic_score_codex":0.007378241,"about_ca_topic_score_gemma":0.00832256,"teacher_disagreement_score":0.012148114,"about_ca_system_score_codex":0.0015280144,"about_ca_system_score_gemma":0.0009840496,"threshold_uncertainty_score":0.06424612},"labels":[],"label_agreement":null},{"id":"W4394773742","doi":"10.1162/tacl_a_00645","title":"To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Divergence (linguistics); Machine translation; Perspective (graphical); Computer science; Translation (biology); Artificial intelligence; Natural language processing; Diversity (politics); Linguistics; Sociology; Biology","score_opus":0.0292461547114884,"score_gpt":0.3409946650393249,"score_spread":0.3117485103278365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394773742","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":[0.91995776,0.004843834,0.0498286,0.0038518733,0.000088554516,0.000034560315,0.00058732426,0.00022923251,0.020578349],"genre_scores_gemma":[0.9933867,0.0003315083,0.0056309565,0.00017803433,0.000036784302,0.000010873398,0.00015859955,0.000064649896,0.0002018292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99627304,0.0023306054,0.000156055,0.00048698616,0.0006082986,0.00014499112],"domain_scores_gemma":[0.98371243,0.012822358,0.0011469749,0.0009854997,0.0009758917,0.00035681576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00486376,0.00036844844,0.0006066866,0.002959391,0.00089859887,0.0032786469,0.00046033773,0.0007479464,0.0026829767],"category_scores_gemma":[0.018674683,0.00018334456,0.00029307287,0.0028090577,0.003564146,0.0037500353,0.0015922482,0.0017407467,0.00042136337],"study_design_candidate":"observational","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":[0.0029607126,0.0003920102,0.19736306,0.0012800625,0.00097285066,0.0022599834,0.027387133,0.01921145,0.15904878,0.2539157,0.0060013747,0.3292069],"study_design_scores_gemma":[0.0001295136,0.0009818107,0.48088744,0.00036926317,0.00038545686,0.0026759796,0.018509686,0.060270254,0.035178296,0.37685463,0.023523709,0.00023402339],"about_ca_topic_score_codex":0.0011833953,"about_ca_topic_score_gemma":0.0020424887,"teacher_disagreement_score":0.00486376,"about_ca_system_score_codex":0.00095232826,"about_ca_system_score_gemma":0.0005157721,"threshold_uncertainty_score":0.025722325},"labels":[],"label_agreement":null},{"id":"W4398757454","doi":"10.1162/tacl_a_00667","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute; Minnow Environmental (Canada); Research Canada","funders":"","keywords":"Correctness; Computer science; Question answering; Natural language processing; Artificial intelligence; Programming language","score_opus":0.037789028206600114,"score_gpt":0.3285510699647791,"score_spread":0.290762041758179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398757454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6171094,0.001053758,0.3619538,0.001319619,0.00019162724,0.00066373753,0.0010974233,0.012134383,0.004476221],"genre_scores_gemma":[0.9459374,0.00008363485,0.051544532,0.00017416294,0.000027124594,0.00015640388,0.00108523,0.00031009995,0.0006813122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98790956,0.007259812,0.0008078537,0.0021618367,0.001418576,0.00044220377],"domain_scores_gemma":[0.8792539,0.09748355,0.0043364423,0.01080103,0.0064685987,0.0016565819],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01909782,0.0011155009,0.0009150107,0.0017524393,0.0006676409,0.002926078,0.0023026743,0.002493935,0.002085758],"category_scores_gemma":[0.10400178,0.0005551682,0.0008927653,0.00090172986,0.0016451441,0.0034264047,0.0024253388,0.0025984256,0.0009658962],"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":[0.0044874405,0.0011657058,0.06192508,0.0012092706,0.0006914596,0.00030912,0.0046416195,0.51508117,0.027958756,0.009305319,0.011284415,0.36194074],"study_design_scores_gemma":[0.00004629346,0.00029813134,0.0029318405,0.000042507727,0.00005636044,0.00006380582,0.0001859486,0.98193467,0.009088089,0.0044881315,0.00083025923,0.000033981898],"about_ca_topic_score_codex":0.008827999,"about_ca_topic_score_gemma":0.008541726,"teacher_disagreement_score":0.9809022,"about_ca_system_score_codex":0.0020612844,"about_ca_system_score_gemma":0.0016766933,"threshold_uncertainty_score":0.10100013},"labels":[],"label_agreement":null},{"id":"W4399426318","doi":"10.1162/tacl_a_00669","title":"Source-Free Domain Adaptation for Question Answering with Masked Self-training","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","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":"Western University","funders":"","keywords":"Computer science; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Question answering; Training (meteorology); Training set; Natural language processing; Artificial intelligence; Information retrieval; Speech recognition; Psychology","score_opus":0.019462492397112383,"score_gpt":0.25327610768223807,"score_spread":0.23381361528512568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399426318","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":[0.06854468,0.00094272086,0.92134887,0.00034809194,0.00012671965,0.00014781157,0.00029625747,0.006584733,0.0016601612],"genre_scores_gemma":[0.75128883,0.0002728077,0.24208963,0.00076922163,0.000119505785,0.00032625496,0.0016598208,0.00042713893,0.003046776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987387,0.0005694845,0.00005777819,0.00043018835,0.00012888745,0.00007501158],"domain_scores_gemma":[0.9966581,0.0017167389,0.00015788988,0.000950499,0.00039749802,0.00011918245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026995838,0.0010523901,0.00081868446,0.00076986244,0.00045456633,0.0007461662,0.0019479749,0.0013915416,0.0018513402],"category_scores_gemma":[0.0061693806,0.0005001897,0.0009997393,0.00066329737,0.00089090434,0.0023782344,0.002549531,0.002318628,0.0012718829],"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":[0.00077236263,0.0007603513,0.0064165476,0.00038561365,0.00032110023,0.00026280395,0.0009438813,0.26889172,0.05941187,0.007608148,0.013298191,0.6409274],"study_design_scores_gemma":[0.00001800668,0.000070863265,0.0006737737,0.000013360108,0.000022347123,0.00006229043,0.000045061523,0.9837277,0.008378778,0.0051131817,0.0018596542,0.000014966665],"about_ca_topic_score_codex":0.002303574,"about_ca_topic_score_gemma":0.0025671916,"teacher_disagreement_score":0.0026995838,"about_ca_system_score_codex":0.0006379754,"about_ca_system_score_gemma":0.00071498705,"threshold_uncertainty_score":0.014276922},"labels":[],"label_agreement":null},{"id":"W4400678062","doi":"10.1162/tacl_a_00678","title":"Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Authorship Attribution and Profiling","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":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Conversation; Punctuation; Natural language processing; Benchmark (surveying); Attribution; Spurious relationship; Task (project management); Speech recognition; Artificial intelligence; Transcription (linguistics); Suite; Construct (python library); Linguistics; Psychology; Machine learning; Communication","score_opus":0.04126170943162795,"score_gpt":0.2890382353474506,"score_spread":0.24777652591582267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400678062","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":[0.8448912,0.0016605292,0.13959296,0.0017312586,0.00065347424,0.0001889277,0.001261804,0.0032727038,0.0067471177],"genre_scores_gemma":[0.9809574,0.00014521628,0.01593953,0.00008231399,0.00009870767,0.00004732312,0.0010239439,0.00006876824,0.0016369201],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996847,0.0018604875,0.00013944869,0.0007048766,0.00023607955,0.00021215098],"domain_scores_gemma":[0.98155826,0.012979657,0.001382747,0.0020802277,0.0014887119,0.00051039003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061521926,0.0009932863,0.0007322036,0.0011320016,0.0006508416,0.0021661506,0.0011947823,0.001494875,0.0024723292],"category_scores_gemma":[0.032604992,0.00030200556,0.0005922641,0.0007048139,0.0006858785,0.0026388804,0.0013314277,0.002200357,0.0022153796],"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":[0.0027788193,0.0010152046,0.060067367,0.00053297443,0.00041975908,0.00041588445,0.0020830624,0.15149352,0.028828938,0.002285995,0.008552332,0.7415262],"study_design_scores_gemma":[0.000040422903,0.00017811928,0.0090336315,0.00006784711,0.00006738426,0.0001092492,0.00056220696,0.9691664,0.013128548,0.0064336974,0.001168805,0.00004370304],"about_ca_topic_score_codex":0.002441399,"about_ca_topic_score_gemma":0.002510987,"teacher_disagreement_score":0.0061521926,"about_ca_system_score_codex":0.0006568084,"about_ca_system_score_gemma":0.0007589965,"threshold_uncertainty_score":0.032536328},"labels":[],"label_agreement":null},{"id":"W4411934141","doi":"10.1162/tacl_a_00759","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Audit; Natural language processing; Linguistics; Speech recognition; Data science; Artificial intelligence; World Wide Web; Accounting; Business","score_opus":0.030497832723930175,"score_gpt":0.29480967779670436,"score_spread":0.26431184507277417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411934141","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":[0.17001481,0.0015858165,0.7810168,0.0013300374,0.000449969,0.0011102752,0.0052370913,0.014668073,0.024587087],"genre_scores_gemma":[0.35515332,0.00037896936,0.63463527,0.00022739288,0.00014617621,0.00050430093,0.003885173,0.00095039525,0.0041190768],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98816663,0.0046687634,0.0009603114,0.0019515596,0.0038116872,0.00044094372],"domain_scores_gemma":[0.96839005,0.0077804155,0.0018230262,0.007962522,0.013064839,0.0009791758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008241626,0.00089352095,0.0007599272,0.0074893553,0.0020163292,0.0033961122,0.0025237398,0.0013337313,0.007476762],"category_scores_gemma":[0.0327965,0.0006214657,0.000655517,0.00462818,0.0011086151,0.0033203252,0.0049565765,0.0012551263,0.0032990512],"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":[0.0012321378,0.00041866102,0.032647017,0.0009832545,0.00028722032,0.0013555823,0.0070505654,0.009237997,0.10908742,0.009038255,0.011176769,0.81748503],"study_design_scores_gemma":[0.00030463006,0.0016339,0.12670118,0.00090566685,0.0007534023,0.005274907,0.019650964,0.36817104,0.2681974,0.030186707,0.17757004,0.0006501582],"about_ca_topic_score_codex":0.0059289606,"about_ca_topic_score_gemma":0.015480884,"teacher_disagreement_score":0.008241626,"about_ca_system_score_codex":0.001287349,"about_ca_system_score_gemma":0.0030373689,"threshold_uncertainty_score":0.043586373},"labels":[],"label_agreement":null},{"id":"W4416372001","doi":"10.1162/tacl.a.50","title":"Objectifying the Subjective: Cognitive Biases in Topic Interpretations","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","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 Victoria","funders":"","keywords":"Representativeness heuristic; Interpretation (philosophy); Salient; Cognitive bias; Quality (philosophy); Heuristics; Context (archaeology); Coherence (philosophical gambling strategy); Cognition","score_opus":0.022742452538391057,"score_gpt":0.3057547969801711,"score_spread":0.28301234444178003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416372001","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":[0.43459925,0.002171145,0.5183964,0.007792767,0.0002877057,0.0005416407,0.00019679921,0.0008541177,0.035160225],"genre_scores_gemma":[0.9612249,0.00026422227,0.036805496,0.000507564,0.0000874319,0.00020316124,0.000067741756,0.0001784945,0.00066097564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88410014,0.09107905,0.0042135315,0.005254555,0.014171165,0.001181616],"domain_scores_gemma":[0.60282075,0.32326096,0.025631877,0.026621528,0.018907746,0.0027571463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08430993,0.00093414023,0.00075445813,0.0036769959,0.0023747298,0.01286434,0.0015870453,0.0018100016,0.0025265408],"category_scores_gemma":[0.33018917,0.0008402878,0.00092771766,0.002216997,0.012971289,0.0135213705,0.0058147092,0.0033692953,0.00045303325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009672212,0.00023474132,0.07207017,0.0017277579,0.00048943283,0.00051189255,0.3134026,0.007408341,0.014791591,0.33517653,0.0067617763,0.246458],"study_design_scores_gemma":[0.00017903977,0.00047290372,0.04222086,0.0015670885,0.0003717869,0.0008689147,0.07332376,0.060347058,0.013971278,0.76445043,0.04163784,0.0005890975],"about_ca_topic_score_codex":0.0021105472,"about_ca_topic_score_gemma":0.0014908286,"teacher_disagreement_score":0.08430993,"about_ca_system_score_codex":0.0027949854,"about_ca_system_score_gemma":0.0018443923,"threshold_uncertainty_score":0.44587886},"labels":[],"label_agreement":null},{"id":"W4417275930","doi":"10.1162/tacl.a.54","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","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 TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Attribution; Transcription (linguistics); Task (project management); Speaker diarisation; Phonetic transcription; Speech processing","score_opus":0.018552587854670767,"score_gpt":0.296895449186917,"score_spread":0.2783428613322462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417275930","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":[0.922733,0.001250912,0.06596328,0.00078412244,0.00063300703,0.00014946754,0.00067223073,0.003159028,0.0046550254],"genre_scores_gemma":[0.98836356,0.00017739546,0.009109929,0.00015305459,0.000104016035,0.000033431483,0.00076779973,0.00044417454,0.0008467015],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96177024,0.02243109,0.0029727789,0.0046029193,0.007254244,0.0009686448],"domain_scores_gemma":[0.63117677,0.29191208,0.021598045,0.031641115,0.021343224,0.0023287397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0181842,0.0010880143,0.0008494884,0.0010292875,0.0010067031,0.0026159761,0.0010232369,0.0012367283,0.0021407674],"category_scores_gemma":[0.22789109,0.00042846528,0.00038979814,0.0011191192,0.0014089161,0.0024953685,0.0022098592,0.0015754737,0.0020500235],"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":[0.008938152,0.0008559735,0.1188267,0.0014863713,0.0007077683,0.0012966581,0.006582418,0.12743634,0.17676246,0.0019333714,0.0072918767,0.5478819],"study_design_scores_gemma":[0.00021513167,0.004442165,0.22772919,0.0006374141,0.0006670598,0.002714825,0.0045610247,0.39416787,0.3484959,0.009045025,0.006651521,0.00067297544],"about_ca_topic_score_codex":0.0027458053,"about_ca_topic_score_gemma":0.0016129268,"teacher_disagreement_score":0.0181842,"about_ca_system_score_codex":0.0009321132,"about_ca_system_score_gemma":0.0009023989,"threshold_uncertainty_score":0.0961684},"labels":[],"label_agreement":null},{"id":"W7086984966","doi":"10.1162/tacl.a.38","title":"Elements of World Knowledge (<scp>EWoK</scp>): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Schizophrenia research and treatment","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Quest for Intelligence, Massachusetts Institute of Technology; Yuhan","keywords":"Situated; Language model; Conceptual model; Domain knowledge; Simple (philosophy); Conceptual framework; Knowledge-based systems","score_opus":0.046250593576374836,"score_gpt":0.38671307829039525,"score_spread":0.3404624847140204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7086984966","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":[0.1754205,0.0040249536,0.6953224,0.0030183021,0.0005002106,0.0018851755,0.08051805,0.018071521,0.02123893],"genre_scores_gemma":[0.55275434,0.00068552693,0.36594048,0.00058637344,0.00012618086,0.0013098287,0.07644338,0.00071268773,0.0014411847],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910358,0.0046470044,0.0010100584,0.0014044887,0.0016518679,0.00025074388],"domain_scores_gemma":[0.9636072,0.025028162,0.0021606036,0.00600261,0.0024256774,0.0007757291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010254393,0.0018583102,0.0009416936,0.008193426,0.0010801583,0.005221235,0.002839415,0.0029555033,0.0053282087],"category_scores_gemma":[0.058745116,0.0005915812,0.0020214058,0.0048794774,0.0018608414,0.006650415,0.005277615,0.0031341428,0.0015841238],"study_design_candidate":"theoretical_or_conceptual","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":[0.0016538316,0.0016698781,0.06574433,0.003428713,0.0016011357,0.0007277629,0.0018534024,0.26415166,0.005503545,0.069330476,0.100525476,0.48380977],"study_design_scores_gemma":[0.0001458486,0.0003421513,0.011369793,0.0003997107,0.00013793899,0.00026460466,0.0005839518,0.8748009,0.004959216,0.0806859,0.026158106,0.00015180092],"about_ca_topic_score_codex":0.010328826,"about_ca_topic_score_gemma":0.016369177,"teacher_disagreement_score":0.010328826,"about_ca_system_score_codex":0.0020056388,"about_ca_system_score_gemma":0.0016720019,"threshold_uncertainty_score":0.054231107},"labels":[],"label_agreement":null},{"id":"W7108223155","doi":"10.1162/tacl.a.57","title":"Persona-Aware Alignment Framework for Personalized Dialogue Generation","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Persona Design and Applications","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":"Novelis (Canada)","funders":"","keywords":"Persona; Leverage (statistics); Inference; Security token; Meaning (existential); Semantics (computer science); Adversarial system; Language model","score_opus":0.028959832512340362,"score_gpt":0.29899721699781007,"score_spread":0.2700373844854697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108223155","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":[0.005282699,0.00024449546,0.9851511,0.00015374454,0.000071489194,0.00011372318,0.00018860813,0.006829716,0.0019643994],"genre_scores_gemma":[0.27781543,0.00020953166,0.7119561,0.00043341133,0.00013267084,0.00043637096,0.0013643266,0.00097395707,0.006678258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99617803,0.0018966742,0.00014342251,0.0010243364,0.000561705,0.00019575324],"domain_scores_gemma":[0.9984669,0.0007173606,0.00011485422,0.0003261991,0.00025197002,0.0001226569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027350853,0.0011983857,0.0009239528,0.0009271067,0.00083786366,0.0010954587,0.0023062057,0.0015268342,0.009285955],"category_scores_gemma":[0.005624664,0.00058597594,0.0011836478,0.00069438654,0.00094235875,0.0024139672,0.002879157,0.0022386443,0.0037328762],"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":[0.0009060718,0.00063944317,0.0023586836,0.00052033906,0.00022156355,0.0005603241,0.0025396512,0.10359742,0.03482255,0.046023425,0.024966659,0.7828439],"study_design_scores_gemma":[0.00007371424,0.00015926512,0.0006125622,0.000045069337,0.000070484,0.00040488428,0.00031248416,0.92197406,0.013915027,0.038258698,0.024096034,0.00007767383],"about_ca_topic_score_codex":0.0027380146,"about_ca_topic_score_gemma":0.0030909833,"teacher_disagreement_score":0.009285955,"about_ca_system_score_codex":0.00066511694,"about_ca_system_score_gemma":0.00127648,"threshold_uncertainty_score":0.03106463},"labels":[],"label_agreement":null},{"id":"W7114916806","doi":"10.1162/tacl.a.62","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Adversarial Robustness in Machine Learning","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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Adversarial system; Adversary; Perspective (graphical); Training set; Memorization; Attack model","score_opus":0.014302450615151271,"score_gpt":0.33941185395921875,"score_spread":0.32510940334406746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114916806","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":[0.100952886,0.00048858824,0.8818971,0.0041555213,0.0001829155,0.00024205248,0.00043843462,0.0013411449,0.010301379],"genre_scores_gemma":[0.9277842,0.00024725436,0.06723172,0.00082428014,0.00009896348,0.00012819657,0.0002241364,0.00018779647,0.003273391],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99408674,0.0032100054,0.00023830436,0.000770865,0.0012329065,0.00046115275],"domain_scores_gemma":[0.95825267,0.031059982,0.0017231996,0.0075443345,0.0010532683,0.00036664083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006008617,0.00097610755,0.00083225744,0.0008660495,0.0009449301,0.0022548072,0.0014049147,0.0022856363,0.0032433681],"category_scores_gemma":[0.037091862,0.0005844443,0.0009360754,0.0005581822,0.0031941193,0.0051622307,0.004250068,0.004898091,0.0008256504],"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":[0.00036714057,0.00020424133,0.0040273773,0.00017843627,0.00013131894,0.0006959915,0.00045326105,0.7845139,0.0124506485,0.15593332,0.0059489254,0.0350955],"study_design_scores_gemma":[0.000019364732,0.00006508721,0.00028849146,0.000039360028,0.000014907372,0.00023906337,0.00006456278,0.9081494,0.005793771,0.08284262,0.002458101,0.000025142965],"about_ca_topic_score_codex":0.0007787325,"about_ca_topic_score_gemma":0.0006660346,"teacher_disagreement_score":0.006008617,"about_ca_system_score_codex":0.0011507954,"about_ca_system_score_gemma":0.00088481914,"threshold_uncertainty_score":0.031776965},"labels":[],"label_agreement":null},{"id":"W7128225249","doi":"10.1162/tacl.a.27","title":"Investigating Adversarial Trigger Transfer in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Adversarial Robustness in Machine Learning","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":"Canadian Institute for Advanced Research","funders":"","keywords":"Adversarial system; Security token; Offensive; Robustness (evolution); Language model; Threat model; Language understanding","score_opus":0.012176640850124919,"score_gpt":0.28045051901156787,"score_spread":0.26827387816144294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128225249","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":[0.52153987,0.00038276665,0.46985766,0.0012337972,0.00008825446,0.00017300705,0.00032516473,0.0021830373,0.0042164745],"genre_scores_gemma":[0.97947866,0.00005598449,0.019152492,0.00014631981,0.00001855554,0.00008373985,0.00018380203,0.00014864243,0.00073170196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99552226,0.0028290402,0.00013800144,0.0005897134,0.00055975374,0.00036115455],"domain_scores_gemma":[0.96929574,0.025448058,0.0015361719,0.0025690463,0.0006957865,0.0004551501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068124244,0.0009049687,0.0008230606,0.000564665,0.00060630945,0.0011329133,0.0014539334,0.0013897966,0.0029727123],"category_scores_gemma":[0.03289236,0.0004792129,0.000870406,0.00034329575,0.0020583812,0.0025988359,0.0022712348,0.0028829256,0.000415513],"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":[0.00017051138,0.00008950493,0.0019414898,0.00006111289,0.00005557678,0.00011659157,0.00016378007,0.9713169,0.0020780643,0.012993211,0.0006445194,0.010368811],"study_design_scores_gemma":[0.000010252478,0.00005567039,0.00015957677,0.000005990378,0.000006206842,0.000011932813,0.000021842834,0.9839468,0.0009916908,0.014630656,0.00015164926,0.000007609715],"about_ca_topic_score_codex":0.0022953595,"about_ca_topic_score_gemma":0.0020846555,"teacher_disagreement_score":0.0068124244,"about_ca_system_score_codex":0.0015041413,"about_ca_system_score_gemma":0.0011411286,"threshold_uncertainty_score":0.036027968},"labels":[],"label_agreement":null},{"id":"W7133230913","doi":"10.1162/tacl_a_00723","title":"The Causal Influence of Grammatical Gender on Distributional Semantics","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Adjective; Noun; Meaning (existential); Grammatical gender; Semantics (computer science); Cognitive linguistics; Cognition; Proxy (statistics)","score_opus":0.02570939632152445,"score_gpt":0.26820166206015733,"score_spread":0.2424922657386329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133230913","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":[0.8558045,0.00038530023,0.122932956,0.0025847997,0.000071882954,0.000040023584,0.00065179623,0.00037614314,0.017152496],"genre_scores_gemma":[0.9971854,0.00004313949,0.0022734075,0.00004079106,0.000015362199,0.0000065276586,0.000059337795,0.000038126927,0.00033785967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961487,0.002711349,0.000096113734,0.0005592773,0.00032807086,0.00015649662],"domain_scores_gemma":[0.9607947,0.032270223,0.003002327,0.0020288285,0.0012178121,0.0006860621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044256332,0.00029599378,0.00037249795,0.0013754921,0.00049953145,0.002206976,0.0006569505,0.00064936024,0.0071524535],"category_scores_gemma":[0.045425072,0.0003592719,0.00059976475,0.001085916,0.0034851711,0.0037608,0.0015883559,0.00089189806,0.0003810216],"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":[0.00082719605,0.00023788407,0.30481842,0.00035389332,0.00052632554,0.0008309061,0.006848236,0.02065531,0.018294604,0.5756664,0.003254651,0.06768613],"study_design_scores_gemma":[0.000055861514,0.00013764786,0.11949915,0.00007526299,0.00022781425,0.0005912818,0.0018333755,0.05355122,0.0034415221,0.81667626,0.003800859,0.00010972738],"about_ca_topic_score_codex":0.0043312735,"about_ca_topic_score_gemma":0.0036933566,"teacher_disagreement_score":0.0071524535,"about_ca_system_score_codex":0.00082366983,"about_ca_system_score_gemma":0.00054957636,"threshold_uncertainty_score":0.02392739},"labels":[],"label_agreement":null}]}