{"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041233952,0.00007215376,0.9943598,0.0041225087,0.0004665031,0.00020720446,0.000076176555,0.00014561495,0.00013772826],"genre_scores_gemma":[0.86384,0.0000036239217,0.13461062,0.00016384237,0.000079835954,0.000013264027,0.000004338168,0.000008536604,0.0012759559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990501,0.00006549459,0.00022449151,0.00015358585,0.00037041592,0.00013592091],"domain_scores_gemma":[0.9972918,0.0016944346,0.00023659584,0.00014800676,0.0005999867,0.000029170107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036481343,0.00008303657,0.00009171615,0.0000569358,0.0004958106,0.000059595175,0.0004999684,0.00005021749,0.000003448285],"category_scores_gemma":[0.001842179,0.000048136477,0.00009787539,0.0002967379,0.000030611114,0.00007766522,0.000026660082,0.000107446576,0.000002586404],"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":[0.00008869166,0.00033342018,0.0019271706,0.00009295414,0.00047394674,5.8550563e-7,0.0058784783,0.36579677,0.00445762,0.5491351,0.031987682,0.039827604],"study_design_scores_gemma":[0.0013437943,0.0004089774,0.00075517315,0.00031241874,0.00017904055,0.000007289225,0.0005124059,0.2000605,0.01893387,0.7295284,0.047326658,0.00063147256],"about_ca_topic_score_codex":0.0000083153145,"about_ca_topic_score_gemma":0.0000028189343,"teacher_disagreement_score":0.86342764,"about_ca_system_score_codex":0.00025996243,"about_ca_system_score_gemma":0.00007722082,"threshold_uncertainty_score":0.38134244},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012282122,0.000097386896,0.98490125,0.0005786795,0.0011603135,0.00037473583,0.00044634676,0.000040494673,0.000118658594],"genre_scores_gemma":[0.8806467,0.000019961924,0.118858516,0.00002588593,0.000116123374,0.00002458863,0.00014655064,0.000010746097,0.0001509317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826187,0.00011697545,0.00064719433,0.00030122104,0.0004980354,0.00017473193],"domain_scores_gemma":[0.995948,0.0011826346,0.00083908584,0.00027825596,0.001703799,0.00004820276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004547349,0.00017044765,0.00034392197,0.00013091318,0.00022280031,0.000065307315,0.0005201662,0.00021896396,0.0000049805094],"category_scores_gemma":[0.0011832569,0.00016711543,0.000239561,0.00019444444,0.000066094944,0.000044923294,0.00011786892,0.00040252515,7.75291e-7],"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":[0.000005641678,0.000077371515,0.0035330092,0.00018092465,0.00019074009,9.2342106e-8,0.00035598982,0.8270766,0.000012513737,0.16787164,0.000069166264,0.0006262732],"study_design_scores_gemma":[0.00034499745,0.0000291988,0.0034801497,0.00006138639,0.00011982789,8.3687235e-7,0.000023922137,0.8357258,0.00008851662,0.15959103,0.00039538115,0.00013898865],"about_ca_topic_score_codex":0.000056557805,"about_ca_topic_score_gemma":0.000005997992,"teacher_disagreement_score":0.8683646,"about_ca_system_score_codex":0.00014705029,"about_ca_system_score_gemma":0.00029026056,"threshold_uncertainty_score":0.68147695},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010559565,0.000021584327,0.9913074,0.0010272245,0.0038142127,0.0005396473,0.0008144261,0.00013775831,0.0012818173],"genre_scores_gemma":[0.7926186,0.000007765815,0.20550442,0.00007299522,0.00051955145,0.000100537975,0.00010810846,0.000023379273,0.0010446833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798363,0.00010682504,0.0005223708,0.00042019397,0.0007569281,0.00021005084],"domain_scores_gemma":[0.99509424,0.0009232767,0.0009036153,0.00040403823,0.0026235692,0.0000512341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049171824,0.00020520716,0.00027429883,0.00015935297,0.0003289576,0.000102088336,0.0006733891,0.0002312499,0.0000098883365],"category_scores_gemma":[0.00086396403,0.00016216112,0.00029431356,0.00021848596,0.00004399561,0.00007342455,0.0000729962,0.00033730626,0.000006957234],"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":[0.00007398837,0.0004107382,0.0024931568,0.00033721165,0.0009733625,5.6611776e-7,0.00050995115,0.89866775,0.000033524666,0.08651488,0.0009340167,0.009050834],"study_design_scores_gemma":[0.0011357553,0.00008062233,0.0026243269,0.0003635176,0.00028825697,0.0000037646264,0.000011176423,0.41258764,0.0006234305,0.577189,0.0046292227,0.000463219],"about_ca_topic_score_codex":0.000037852486,"about_ca_topic_score_gemma":0.000033385426,"teacher_disagreement_score":0.7915626,"about_ca_system_score_codex":0.00055197085,"about_ca_system_score_gemma":0.00059320964,"threshold_uncertainty_score":0.66127384},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044747646,0.00019072871,0.9968857,0.0012587787,0.0003947939,0.00039275057,0.000018341605,0.00011215581,0.00029927044],"genre_scores_gemma":[0.5807684,0.0000013485251,0.41892847,0.00004525401,0.00003708514,0.000011791081,0.000006223426,0.0000059084273,0.00019551214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895555,0.00004755844,0.0003450801,0.00015281905,0.0003541507,0.0001448285],"domain_scores_gemma":[0.9985641,0.00046168995,0.00026027072,0.00015400338,0.00052621646,0.00003371488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002902656,0.000092960145,0.00012985413,0.00013760578,0.00013044757,0.00005985178,0.00044377713,0.00007732515,0.0000056609433],"category_scores_gemma":[0.00059830537,0.00008207193,0.000110175606,0.0004354404,0.000014177348,0.00014880399,0.000010709024,0.00015304197,0.000003032959],"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":[0.00003642566,0.00044400853,0.008568615,0.0002013625,0.00019925997,6.1533126e-7,0.003468418,0.53905314,0.0010762427,0.3646112,0.0013391594,0.08100156],"study_design_scores_gemma":[0.0007418247,0.000035694287,0.004412647,0.00005691333,0.000028195494,0.0000012057515,0.000012344467,0.5488575,0.0020778107,0.44258532,0.0010145179,0.00017605399],"about_ca_topic_score_codex":0.00025394952,"about_ca_topic_score_gemma":0.00010518646,"teacher_disagreement_score":0.58032095,"about_ca_system_score_codex":0.0002070497,"about_ca_system_score_gemma":0.00016553009,"threshold_uncertainty_score":0.3346796},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5933885,0.0002622396,0.36925402,0.0071000275,0.0047481516,0.002158409,0.00085102994,0.00023870118,0.021998921],"genre_scores_gemma":[0.99543595,0.000013089103,0.003374538,0.00004160766,0.00017016447,0.000009965105,0.0000072023417,0.00000804805,0.0009394137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989985,0.00013040855,0.00025572328,0.00013134583,0.0003016702,0.00018235185],"domain_scores_gemma":[0.99829906,0.00083437545,0.00017328934,0.00007558038,0.00057068164,0.000047003807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006853499,0.00006851428,0.00011266171,0.00009145037,0.00032890606,0.000039908475,0.0001687571,0.000089792964,0.000012542994],"category_scores_gemma":[0.0018312641,0.00005491374,0.000060400816,0.00022511116,0.00009839463,0.00007421928,0.000005142998,0.00007418736,0.0000020221244],"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":[0.000054214965,0.00030606092,0.042011827,0.000043856133,0.000088304936,8.603907e-7,0.020251822,0.010377444,0.00020159532,0.90644634,0.00019143776,0.020026267],"study_design_scores_gemma":[0.0043275505,0.0003967386,0.14903438,0.00042378114,0.00038471047,0.000002163513,0.015775824,0.04484607,0.0025271808,0.73886216,0.042174753,0.0012447094],"about_ca_topic_score_codex":0.00040460535,"about_ca_topic_score_gemma":0.0050650253,"teacher_disagreement_score":0.4020475,"about_ca_system_score_codex":0.00025624616,"about_ca_system_score_gemma":0.00015233585,"threshold_uncertainty_score":0.2826403},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075398874,0.00009202367,0.9957358,0.001437056,0.001019021,0.0004084456,0.00021744675,0.0001360117,0.00020015372],"genre_scores_gemma":[0.66481704,0.0000020607358,0.33467793,0.0000673311,0.000100672,0.000023906192,0.0000346947,0.000009692662,0.0002666587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987463,0.000050208346,0.0003708081,0.00021487923,0.00045791783,0.00015991823],"domain_scores_gemma":[0.997462,0.00031147656,0.0008655998,0.0003826049,0.00094404345,0.00003427954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037980388,0.00013327932,0.00016960822,0.00008567418,0.0008613162,0.00023276413,0.0008889502,0.00009183127,0.000003070911],"category_scores_gemma":[0.0007420413,0.000117291725,0.0001633846,0.00011436359,0.000031582298,0.00029924721,0.000024695264,0.00016450802,0.0000017096368],"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":[0.0003536101,0.0011929001,0.034454662,0.000664079,0.00094929576,0.0000025282827,0.005456393,0.13449647,0.008753503,0.43010807,0.00094441324,0.3826241],"study_design_scores_gemma":[0.0011117033,0.00008624076,0.01301074,0.00005492312,0.00011209211,0.0000034468853,0.000011721576,0.9091198,0.007931241,0.067256734,0.0010231172,0.00027823384],"about_ca_topic_score_codex":0.000048187103,"about_ca_topic_score_gemma":0.000028349394,"teacher_disagreement_score":0.77462333,"about_ca_system_score_codex":0.00015377857,"about_ca_system_score_gemma":0.000084647705,"threshold_uncertainty_score":0.66246355},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024336399,0.000009498177,0.99427605,0.0010221339,0.0033048992,0.0005067077,0.000093301685,0.000047814385,0.00049622543],"genre_scores_gemma":[0.73724896,0.0000011260223,0.2619934,0.000045194025,0.00034250188,0.000035019984,0.000019331843,0.0000080877935,0.0003063817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989459,0.000036028807,0.00034404887,0.00019907285,0.00030865084,0.00016628134],"domain_scores_gemma":[0.9971829,0.00068097305,0.0006928365,0.00036996658,0.0010412392,0.000032068143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049465586,0.00009524406,0.00014579235,0.000048914848,0.0009805651,0.00013722811,0.0007026093,0.00008707289,0.0000014238094],"category_scores_gemma":[0.001332584,0.000091997885,0.00020823441,0.000070538226,0.000028263537,0.00010862692,0.000023204531,0.00009149282,8.9746214e-7],"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":[0.000019007137,0.00003763592,0.00020953866,0.000010460025,0.00006814336,3.1984072e-8,0.00016748594,0.8014472,0.0000046927403,0.19684313,0.00011240402,0.0010802364],"study_design_scores_gemma":[0.0009980309,0.00003742903,0.0019941078,0.000014422148,0.00004689369,2.585358e-7,0.000019172809,0.89399165,0.000043238815,0.09947993,0.0032869473,0.00008790343],"about_ca_topic_score_codex":0.000030096247,"about_ca_topic_score_gemma":0.00003133962,"teacher_disagreement_score":0.7370056,"about_ca_system_score_codex":0.0001971995,"about_ca_system_score_gemma":0.00013505176,"threshold_uncertainty_score":0.75418127},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002897388,0.00002950201,0.99796945,0.00055739057,0.0004200153,0.00015389147,0.000116738636,0.000041626576,0.00042167562],"genre_scores_gemma":[0.53943396,0.0000013358325,0.46026766,0.000022973274,0.000028281938,0.0000052706123,0.0000020969285,0.0000035813991,0.00023484882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921966,0.000021480037,0.00025782385,0.00011577109,0.00029540493,0.000089844994],"domain_scores_gemma":[0.9969627,0.00030978012,0.0008362265,0.00033669057,0.0015367744,0.0000178018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025495203,0.0000710305,0.00013383268,0.00004740572,0.00043321916,0.00006782914,0.0008270067,0.00006379435,6.292266e-7],"category_scores_gemma":[0.0019861115,0.00006065244,0.0001278084,0.000073000105,0.00004730103,0.00010216353,0.000032605407,0.00009714454,3.1623122e-7],"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":[0.000011388066,0.00010520775,0.0003088743,0.0000471498,0.00009422466,5.8179662e-8,0.00048239058,0.38689744,0.0006765085,0.6096516,0.00025423485,0.0014708688],"study_design_scores_gemma":[0.00017107547,0.00001875547,0.00014622834,0.000015267447,0.000029302664,2.0560987e-7,0.00000287609,0.66037333,0.017235134,0.3218551,0.00009820362,0.000054543045],"about_ca_topic_score_codex":0.000015763815,"about_ca_topic_score_gemma":0.0000060347484,"teacher_disagreement_score":0.5391442,"about_ca_system_score_codex":0.000097319346,"about_ca_system_score_gemma":0.0001747023,"threshold_uncertainty_score":0.33320153},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021973165,0.00002458694,0.9753662,0.001515569,0.0006601588,0.00017222119,0.000028228998,0.000013111972,0.00024679402],"genre_scores_gemma":[0.8918392,0.0000063714233,0.10794838,0.000018454692,0.00007301617,0.00000594277,0.0000022909924,0.0000031700247,0.000103161176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990754,0.000035631372,0.0004119432,0.0001403731,0.00024128487,0.00009534788],"domain_scores_gemma":[0.99855864,0.00024105328,0.00041918535,0.00023409085,0.0005232532,0.000023797036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046199415,0.000061036364,0.00015063719,0.00006714269,0.00024364956,0.00003442957,0.00037488472,0.0000880679,5.708993e-7],"category_scores_gemma":[0.0018801184,0.00005939988,0.00007151208,0.000063506275,0.0000324798,0.00008196546,0.000033680204,0.0001671056,1.7884311e-7],"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":[0.0000042322495,0.000036293113,0.012440406,0.00004274265,0.000021392494,7.598566e-8,0.00039829605,0.5883651,0.000015012834,0.39677447,0.000009792241,0.0018921875],"study_design_scores_gemma":[0.00027081257,0.000012430139,0.02045474,0.000028145772,0.000013462664,2.8756773e-7,0.00001464572,0.803604,0.000051850322,0.1754325,0.00007048487,0.00004662848],"about_ca_topic_score_codex":0.00008015302,"about_ca_topic_score_gemma":0.00002417538,"teacher_disagreement_score":0.8698661,"about_ca_system_score_codex":0.0000849045,"about_ca_system_score_gemma":0.0001014329,"threshold_uncertainty_score":0.24222569},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023660684,0.00030798165,0.9964927,0.001648284,0.0007440937,0.00031479285,0.000107442036,0.00010020273,0.00004791327],"genre_scores_gemma":[0.5655377,0.0000020202526,0.4339546,0.00006226112,0.00038118212,0.00001254278,0.000013266203,0.0000059226863,0.000030531093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992739,0.000024285158,0.00023435065,0.00015391494,0.00020090661,0.00011266326],"domain_scores_gemma":[0.9982671,0.00030598155,0.00016252644,0.00011160058,0.0011305402,0.000022257123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002611635,0.00008384592,0.00010629324,0.00006474793,0.0003456677,0.00005621154,0.00025297658,0.000073252566,7.257689e-7],"category_scores_gemma":[0.00019298964,0.000071123286,0.00009054879,0.00017881942,0.000025444197,0.000083506646,0.000008699598,0.00008121326,1.7476451e-7],"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":[0.00014826034,0.00019569849,0.0004641765,0.00023563957,0.0002224423,1.1992537e-7,0.0026201725,0.3187037,0.0002610674,0.5493402,0.00041925546,0.12738925],"study_design_scores_gemma":[0.00030292035,0.00006176331,0.000048433605,0.000009314146,0.000035369634,9.2268357e-7,0.000007593253,0.91466075,0.00024991232,0.08274306,0.0018058077,0.00007415025],"about_ca_topic_score_codex":0.000008425446,"about_ca_topic_score_gemma":0.000012191625,"teacher_disagreement_score":0.59595704,"about_ca_system_score_codex":0.0000572743,"about_ca_system_score_gemma":0.000040709438,"threshold_uncertainty_score":0.29003233},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006449082,0.000042736207,0.9973396,0.00061593263,0.00051166594,0.00026720148,0.00012671996,0.0000615514,0.00038966487],"genre_scores_gemma":[0.70418394,0.0000022204574,0.29550162,0.000018163453,0.00004436417,0.000013613615,0.0000063305642,0.0000052411683,0.00022451223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990051,0.000025306193,0.00028387678,0.00013852328,0.00044710323,0.00010011606],"domain_scores_gemma":[0.9977826,0.00016164524,0.00078332354,0.00033227672,0.00091841404,0.000021738651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003124765,0.00008165953,0.00013967248,0.00005360671,0.00035921455,0.0000632453,0.0005218115,0.00005400479,0.0000017171227],"category_scores_gemma":[0.0005043264,0.00006219477,0.00009147352,0.00008231278,0.000048797796,0.00008571857,0.000027030863,0.0000757643,4.5648525e-7],"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":[0.000119771576,0.00077328825,0.008057245,0.0003771384,0.0008942732,9.3752226e-7,0.0017434122,0.20914675,0.0015661106,0.76217127,0.0015997123,0.013550072],"study_design_scores_gemma":[0.0025790343,0.00066489173,0.033510286,0.00055500533,0.00049058575,0.0000064295577,0.000063170744,0.272737,0.10819595,0.575377,0.0053256475,0.00049500406],"about_ca_topic_score_codex":0.00002881069,"about_ca_topic_score_gemma":0.000006582221,"teacher_disagreement_score":0.703539,"about_ca_system_score_codex":0.0001600528,"about_ca_system_score_gemma":0.00010357189,"threshold_uncertainty_score":0.27628243},"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":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046107173,0.000033546945,0.9450108,0.0026234258,0.0023284648,0.0008299167,0.00021090699,0.00008359756,0.0027722043],"genre_scores_gemma":[0.9599282,0.0000027678689,0.03972273,0.000009646972,0.00013059433,0.000016075388,0.000010859682,0.000005334638,0.00017378456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99769646,0.00046827237,0.00065017457,0.00049748644,0.000510078,0.0001775381],"domain_scores_gemma":[0.9936976,0.0020864615,0.00038543236,0.0006454781,0.0031484093,0.0000366158],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0119419275,0.000078159326,0.00018282032,0.00018647559,0.000262208,0.000055416735,0.00034549614,0.00009912577,9.353631e-7],"category_scores_gemma":[0.025010332,0.00007229423,0.00006476821,0.0007528743,0.00016837288,0.00013592624,0.000031797885,0.0001744432,5.2937867e-7],"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":[0.00025562115,0.0008296469,0.08088548,0.0003592137,0.00012883876,2.6143715e-7,0.0066653104,0.14411739,0.0006060645,0.7634407,0.0012124268,0.0014990184],"study_design_scores_gemma":[0.0015403535,0.0003705999,0.16958913,0.0002595996,0.000027109176,0.0000017954143,0.0001445967,0.39960715,0.0028715578,0.42230436,0.0030404597,0.00024327122],"about_ca_topic_score_codex":0.00048346707,"about_ca_topic_score_gemma":0.000099566474,"teacher_disagreement_score":0.91382104,"about_ca_system_score_codex":0.00029835638,"about_ca_system_score_gemma":0.00021732484,"threshold_uncertainty_score":0.9832024},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00855588,0.00003770179,0.9902783,0.00013181833,0.00047684164,0.00019335806,0.00004133898,0.000029210394,0.0002555696],"genre_scores_gemma":[0.78103954,2.6522028e-7,0.2185252,0.000037312373,0.000020481843,0.0000063127272,0.000014194097,0.000004230401,0.00035248089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989086,0.00018445034,0.00033410135,0.00018063118,0.00026693963,0.00012529937],"domain_scores_gemma":[0.99781984,0.0010991211,0.00028016669,0.00020581119,0.0005759592,0.000019118233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091843,0.00007097794,0.00018532516,0.00018258711,0.000070944334,0.000042942494,0.00039731213,0.000053884545,0.0000041448257],"category_scores_gemma":[0.0009145654,0.000064497566,0.00015727928,0.0010306789,0.000008384871,0.00005422533,0.000015132678,0.00010883489,0.0000014162031],"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":[0.00000421122,0.000041500476,0.04908028,0.000016088108,0.000078633435,3.9665252e-8,0.0004784254,0.9440999,0.000010751151,0.002546921,0.0000041281187,0.0036390917],"study_design_scores_gemma":[0.00023068827,0.00001078579,0.095353,0.0000051021375,0.000055750756,1.2129348e-7,0.000019373228,0.90234995,0.00004010436,0.0017971095,0.000076096294,0.00006194824],"about_ca_topic_score_codex":0.00013266676,"about_ca_topic_score_gemma":0.000118436095,"teacher_disagreement_score":0.77248365,"about_ca_system_score_codex":0.00013503399,"about_ca_system_score_gemma":0.00010284927,"threshold_uncertainty_score":0.26301345},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006648411,0.00005461713,0.99119574,0.00036608017,0.0010494166,0.0003257825,0.000217587,0.000058245543,0.00008412446],"genre_scores_gemma":[0.69460064,2.5162282e-7,0.30507058,0.000056484278,0.00019011869,0.000008881297,0.000018184279,0.000005469771,0.000049371905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987336,0.000025832633,0.00033451655,0.000294184,0.0004242021,0.00018769027],"domain_scores_gemma":[0.9974296,0.00044977802,0.00037311745,0.00026533863,0.0014491688,0.00003297594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010403618,0.00008277925,0.00011545611,0.000088003144,0.00063076225,0.00017445281,0.00075155083,0.00003308117,2.7528534e-7],"category_scores_gemma":[0.001464541,0.00007252009,0.00004040891,0.0002829642,0.00008156747,0.00026332392,0.00007212115,0.00007421917,4.4181863e-7],"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":[0.00017521219,0.00062545115,0.011639497,0.0049991305,0.0010148665,0.000001681007,0.041475084,0.2156678,0.0031273921,0.36793447,0.0011787809,0.35216063],"study_design_scores_gemma":[0.00040528987,0.000025008481,0.00036268274,0.00006722376,0.000035560875,9.827248e-7,0.000241395,0.9950996,0.00066522654,0.002375625,0.0006384904,0.000082931954],"about_ca_topic_score_codex":0.00001639019,"about_ca_topic_score_gemma":0.0000073670285,"teacher_disagreement_score":0.77943176,"about_ca_system_score_codex":0.0001918678,"about_ca_system_score_gemma":0.00023034109,"threshold_uncertainty_score":0.48513773},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007746071,0.000067029985,0.99259466,0.005869948,0.00023009052,0.00016627705,0.000059709833,0.00012711254,0.000110551744],"genre_scores_gemma":[0.81696534,0.0000012942002,0.18275455,0.000089874295,0.00008126389,0.000010028353,0.000017267219,0.0000052695286,0.00007512144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904054,0.00006387007,0.0002471537,0.00016632056,0.00034825478,0.00013384204],"domain_scores_gemma":[0.9984587,0.000642937,0.00023892615,0.0000752728,0.0005465141,0.000037686223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023388205,0.000081989594,0.00013185697,0.000046505134,0.00015851883,0.000049530485,0.00039235846,0.00007105937,0.0000028147842],"category_scores_gemma":[0.0028455306,0.00007393916,0.00010754443,0.00047789526,0.000025147927,0.000066931505,0.000022815819,0.00024075281,0.0000017483435],"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":[0.00003882823,0.00012682992,0.006541947,0.00007877633,0.00005648837,7.748241e-7,0.0010819084,0.24621415,0.0002692057,0.7443233,0.0005079906,0.00075981335],"study_design_scores_gemma":[0.0007952275,0.0001713885,0.0059475265,0.000057054363,0.000038336086,0.0000015587636,0.000047699603,0.8271922,0.0041320985,0.15592512,0.0054376647,0.0002541304],"about_ca_topic_score_codex":0.000012892903,"about_ca_topic_score_gemma":0.0000056951963,"teacher_disagreement_score":0.8161907,"about_ca_system_score_codex":0.00017463497,"about_ca_system_score_gemma":0.00013576318,"threshold_uncertainty_score":0.34065714},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004269757,0.000050797484,0.9891877,0.0015959829,0.002570356,0.00052480743,0.00046607768,0.000065098364,0.0012694076],"genre_scores_gemma":[0.73676664,0.000004827632,0.25999022,0.00020304104,0.0010851948,0.000050076116,0.00019303283,0.000018690973,0.0016882736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984584,0.00012215963,0.00040334373,0.00020697876,0.00059592706,0.000213193],"domain_scores_gemma":[0.9928963,0.0030689263,0.0004190403,0.00012072514,0.0034427259,0.00005227],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00070087455,0.000100881385,0.00017110564,0.000054809778,0.0010066797,0.00007972201,0.00018553673,0.00017632972,0.000035069657],"category_scores_gemma":[0.011306168,0.0001103084,0.00026983145,0.00031614845,0.00006867952,0.000042276668,0.000008015686,0.000136178,0.0000030444073],"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":[0.000013856124,0.00011697465,0.000671177,0.000029023984,0.00012865917,1.1996437e-7,0.003262226,0.5458144,0.000038252092,0.44846866,0.00086785585,0.0005888382],"study_design_scores_gemma":[0.0013722384,0.000041992145,0.0021551654,0.00007323486,0.0003219236,0.0000010774258,0.001360739,0.30791646,0.0014154189,0.6108054,0.074192874,0.0003434689],"about_ca_topic_score_codex":0.00007288108,"about_ca_topic_score_gemma":0.0001749963,"teacher_disagreement_score":0.7324969,"about_ca_system_score_codex":0.00040030273,"about_ca_system_score_gemma":0.0007646505,"threshold_uncertainty_score":0.99702203},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011212462,0.00015249616,0.9812422,0.00033359145,0.0014858276,0.0004672054,0.0047898856,0.00020912012,0.0001072298],"genre_scores_gemma":[0.7642645,7.697161e-7,0.23522522,0.000059203794,0.000055854143,0.000025002952,0.0002065392,0.0000073301385,0.00015557471],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834317,0.00018408542,0.0004607408,0.00021386571,0.0006618442,0.00013629727],"domain_scores_gemma":[0.9971779,0.00078565395,0.00075800146,0.00033759855,0.00090983155,0.000030992844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088751136,0.00009488399,0.00018973277,0.00008926034,0.0005031255,0.000022003822,0.0008587202,0.000047714704,0.0000128593765],"category_scores_gemma":[0.0015664384,0.000091210735,0.00013595629,0.00037498018,0.00003577304,0.000074436524,0.00009772754,0.0001745594,5.19751e-7],"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":[0.00033993743,0.0018797433,0.0059956755,0.00039310125,0.00043566618,0.0000016354888,0.0037601863,0.76563954,0.0041247914,0.20199913,0.0052254926,0.010205112],"study_design_scores_gemma":[0.002193061,0.00035763712,0.0036307517,0.000034039007,0.0001259193,0.0000061188057,0.000107553904,0.80413085,0.012363315,0.16203251,0.01454772,0.00047050088],"about_ca_topic_score_codex":0.000042692416,"about_ca_topic_score_gemma":0.00003349575,"teacher_disagreement_score":0.75305206,"about_ca_system_score_codex":0.00037285578,"about_ca_system_score_gemma":0.0002542236,"threshold_uncertainty_score":0.38696852},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026306603,0.000054446504,0.99561685,0.00044463313,0.00049552356,0.00030853218,0.00011451452,0.000052377574,0.00028247343],"genre_scores_gemma":[0.67368037,0.0000022874194,0.32467252,0.00003791565,0.000075451884,0.000027931397,0.000027456608,0.0000072307516,0.0014688398],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999116,0.000044742043,0.0002995125,0.00021967165,0.00019390497,0.00012614703],"domain_scores_gemma":[0.99732184,0.0011118439,0.00021676693,0.00019345513,0.0011257237,0.000030346602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029172815,0.000080294434,0.00013681156,0.000054387583,0.00024702583,0.0000615193,0.00019584449,0.00006295403,9.218451e-7],"category_scores_gemma":[0.0016815282,0.000080803075,0.00012448669,0.00020182526,0.000014269384,0.00006531322,0.000021435751,0.00007029317,2.7038993e-7],"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":[0.000008329846,0.000054202967,0.000080594495,0.000050253406,0.000055427387,6.754033e-8,0.0028228217,0.897187,0.0001539181,0.09796598,0.000079599806,0.0015417811],"study_design_scores_gemma":[0.00056694855,0.000013466729,0.00028820705,0.000018007164,0.000051127183,0.0000010265851,0.000093568335,0.9495437,0.00058657926,0.04854103,0.00021859095,0.000077721386],"about_ca_topic_score_codex":0.0000071957706,"about_ca_topic_score_gemma":0.000022801063,"teacher_disagreement_score":0.6710497,"about_ca_system_score_codex":0.00010566832,"about_ca_system_score_gemma":0.00020824418,"threshold_uncertainty_score":0.32950538},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046147485,0.000017956188,0.9916773,0.0009005243,0.001958403,0.00036696938,0.0002951966,0.000042637992,0.0001262508],"genre_scores_gemma":[0.8654615,0.0000018704071,0.13394496,0.00009927167,0.0001644267,0.00003726227,0.00009067329,0.000007903566,0.00019209302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869305,0.00010877497,0.00045496173,0.00024461758,0.00032505754,0.00017355471],"domain_scores_gemma":[0.99647063,0.0013996942,0.00033804306,0.00017946132,0.0015813094,0.000030851537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000693304,0.00009372538,0.00019701419,0.00007607152,0.00022835504,0.000058194637,0.00026148147,0.00011111307,0.000004773474],"category_scores_gemma":[0.003625738,0.00010175443,0.00021792093,0.00026592775,0.00001916701,0.00008954848,0.000016024971,0.00014192754,0.00000108941],"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":[0.00010668521,0.00053147064,0.0029387043,0.00022258087,0.00032775322,0.0000014267829,0.0043449514,0.7570647,0.00007458376,0.1905416,0.00030834443,0.04353723],"study_design_scores_gemma":[0.0016800681,0.000032123025,0.001833383,0.00006165829,0.000060144208,0.0000015592628,0.0001703969,0.8222667,0.00056456425,0.17077737,0.0024061392,0.0001458815],"about_ca_topic_score_codex":0.000039589493,"about_ca_topic_score_gemma":0.00017641606,"teacher_disagreement_score":0.8608468,"about_ca_system_score_codex":0.0002959526,"about_ca_system_score_gemma":0.00040133265,"threshold_uncertainty_score":0.4340609},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015035472,0.000019350457,0.9958049,0.00020701492,0.0012518066,0.0002977118,0.00041834233,0.000035604793,0.00046170776],"genre_scores_gemma":[0.9622099,0.0000014450022,0.03735965,0.000075377044,0.000027582555,0.00004174737,0.00004126428,0.00001104868,0.0002320121],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982402,0.0002652663,0.0005298559,0.00019517256,0.00061463215,0.0001548797],"domain_scores_gemma":[0.9956962,0.0018085415,0.000604507,0.0002472107,0.0016157367,0.00002784106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010049124,0.00009404695,0.00017168598,0.00013598564,0.00041417367,0.000030647727,0.0007351246,0.00003713732,0.00000970963],"category_scores_gemma":[0.0015177942,0.000099308825,0.0001733835,0.000644578,0.00003250706,0.00010943483,0.000056757213,0.00015678904,0.0000014639982],"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":[0.00002701781,0.00013361771,0.00028751095,0.0000143509715,0.000045478566,6.7492614e-8,0.0008840095,0.9043493,0.000017152313,0.09289635,0.00008256871,0.0012625512],"study_design_scores_gemma":[0.00014106164,0.00009210363,0.00219451,0.00000466263,0.000025049603,6.813883e-7,0.00008269501,0.89274883,0.00037825262,0.10402059,0.00023064786,0.000080930964],"about_ca_topic_score_codex":0.00017215633,"about_ca_topic_score_gemma":0.00010004921,"teacher_disagreement_score":0.96070635,"about_ca_system_score_codex":0.0002691149,"about_ca_system_score_gemma":0.0001850884,"threshold_uncertainty_score":0.40496963},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035417888,0.000054650573,0.98990935,0.00397183,0.0009375658,0.00038185038,0.00015191457,0.000114927636,0.0009361233],"genre_scores_gemma":[0.8185074,2.9547957e-7,0.18085968,0.00032762485,0.000025275904,0.00004508509,0.0000072136722,0.000005424185,0.00022202227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998587,0.00010332294,0.00031178255,0.0002092827,0.0006233978,0.00016518937],"domain_scores_gemma":[0.9981942,0.00061314926,0.00036467274,0.00015870828,0.00064835465,0.000020915691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097178924,0.00008418872,0.00012536222,0.00022083241,0.0006501803,0.0000673199,0.00090890203,0.000028723129,0.000008421675],"category_scores_gemma":[0.0017281744,0.00007815174,0.00008506452,0.00096409576,0.000059878363,0.00012839731,0.00008742232,0.00026092015,4.526899e-7],"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":[0.0001200533,0.00063169684,0.00157045,0.00010883461,0.00012757511,0.0000033239496,0.119888686,0.5001276,0.005457729,0.36105496,0.0022199382,0.008689185],"study_design_scores_gemma":[0.0013215849,0.00031861072,0.0016109484,0.00013068464,0.00003782655,0.0000089711475,0.0059274957,0.6409163,0.042578045,0.30139995,0.0051650363,0.00058457564],"about_ca_topic_score_codex":0.000020279422,"about_ca_topic_score_gemma":0.000013748287,"teacher_disagreement_score":0.8149656,"about_ca_system_score_codex":0.000613291,"about_ca_system_score_gemma":0.00033278018,"threshold_uncertainty_score":0.5000727},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6604463,0.0006021264,0.31182802,0.0030176213,0.0119153485,0.0026919101,0.002369402,0.00018358008,0.006945722],"genre_scores_gemma":[0.99634814,0.000025257663,0.002294301,0.00005228386,0.00031517356,0.000022516131,0.00038905573,0.0000102644935,0.00054299424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9984391,0.00022050651,0.00041086497,0.00019287464,0.0005600813,0.00017659382],"domain_scores_gemma":[0.9963778,0.0013604994,0.00044869568,0.00007610411,0.0017006296,0.00003623053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005678628,0.00011654691,0.0002376624,0.00006807679,0.00040534633,0.000074634096,0.00020358089,0.00029717808,0.000030751144],"category_scores_gemma":[0.0063168267,0.00010420117,0.00030697236,0.00026089247,0.000069530164,0.00003356398,0.00003134874,0.00036743958,9.38981e-7],"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":[0.00010838396,0.0009557565,0.10475303,0.0003914998,0.00072079024,0.0000019101312,0.05544528,0.77227724,0.00003173377,0.06360572,0.0003348449,0.0013737904],"study_design_scores_gemma":[0.0064224373,0.0002075155,0.5645517,0.0034046546,0.0030217108,0.0000012594123,0.092956915,0.105574705,0.0015730105,0.20274568,0.016877852,0.0026625355],"about_ca_topic_score_codex":0.0019059209,"about_ca_topic_score_gemma":0.008131826,"teacher_disagreement_score":0.66670257,"about_ca_system_score_codex":0.0005444078,"about_ca_system_score_gemma":0.00061310886,"threshold_uncertainty_score":0.7562288},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008115541,0.000027609502,0.995745,0.00095786504,0.0010972944,0.00024531866,0.00029955828,0.000054084398,0.00076172233],"genre_scores_gemma":[0.7305915,0.0000024507353,0.26820147,0.00008969352,0.00015869111,0.000034454966,0.00006995219,0.000007012081,0.0008448005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909353,0.000049918726,0.0002752571,0.00018028499,0.00027060648,0.0001304221],"domain_scores_gemma":[0.99696887,0.0009105659,0.00025030438,0.0001797331,0.0016639712,0.000026570468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002995397,0.00007146581,0.00012285983,0.000047802954,0.0002264105,0.00005390561,0.00024707665,0.000060726343,0.0000053909516],"category_scores_gemma":[0.0018699882,0.0000714427,0.00018387685,0.00021827614,0.000012513986,0.000050270344,0.000013821885,0.00007257163,0.0000019871402],"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":[0.000045382996,0.00061774335,0.0015770057,0.00032842124,0.00054595264,0.0000010365742,0.001832302,0.5917858,0.00042618127,0.36162964,0.0017355346,0.03947499],"study_design_scores_gemma":[0.00097571156,0.000044751807,0.0012731164,0.000036739697,0.00013405636,0.0000024496726,0.00013536777,0.78040165,0.0038158493,0.20026605,0.012715587,0.00019866726],"about_ca_topic_score_codex":0.000013746252,"about_ca_topic_score_gemma":0.000026932603,"teacher_disagreement_score":0.7297799,"about_ca_system_score_codex":0.00011950311,"about_ca_system_score_gemma":0.00017538147,"threshold_uncertainty_score":0.29133487},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040821152,0.000013786834,0.99571127,0.0009731967,0.0016613659,0.0003858138,0.00012517834,0.00020720603,0.0005139672],"genre_scores_gemma":[0.83721393,0.0000064739684,0.15934196,0.0002586471,0.00020134746,0.0000968961,0.00017064992,0.00001939862,0.002690698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867094,0.00010210448,0.00041256085,0.00025090147,0.00038041154,0.0001830935],"domain_scores_gemma":[0.99292195,0.0015562979,0.00032976718,0.00017681456,0.004972375,0.000042768123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039212845,0.00011814063,0.00018509952,0.00009061831,0.00049648405,0.00009705746,0.00031175118,0.00012298273,0.0000114245595],"category_scores_gemma":[0.0032474082,0.00011947422,0.00031616757,0.0003858344,0.000020755475,0.00009304576,0.000019968249,0.00018511302,0.0000036668837],"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":[0.00015130715,0.0013042832,0.003183178,0.00048483853,0.000916824,0.0000018203394,0.002003108,0.75785506,0.003335119,0.14976783,0.009348501,0.07164813],"study_design_scores_gemma":[0.001000422,0.00020575478,0.0018082509,0.00008038197,0.0001307388,0.0000072471585,0.00010044781,0.91441816,0.023360994,0.04334361,0.015268068,0.00027591095],"about_ca_topic_score_codex":0.000010908791,"about_ca_topic_score_gemma":0.000015734386,"teacher_disagreement_score":0.8368057,"about_ca_system_score_codex":0.00021645369,"about_ca_system_score_gemma":0.00034385305,"threshold_uncertainty_score":0.48720172},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016728557,0.00020233142,0.9955479,0.0006329029,0.00074240065,0.00021664827,0.00014480692,0.00003172466,0.0008084133],"genre_scores_gemma":[0.88978153,0.00001004854,0.10954115,0.000033792603,0.00009859251,0.000011066325,0.000016483835,0.000008743681,0.0004986054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990283,0.000045640685,0.0003003686,0.00017647265,0.0003039461,0.00014527414],"domain_scores_gemma":[0.9963433,0.0022554868,0.00030912398,0.0001749412,0.00088926347,0.000027890666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032304248,0.00007847394,0.00016246317,0.000068502275,0.00018157724,0.000029033903,0.00026129844,0.00006853254,9.174919e-7],"category_scores_gemma":[0.0020721478,0.00007971112,0.00021055518,0.0001902889,0.00001917119,0.00004565814,0.00001574799,0.00007239422,3.767705e-7],"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":[0.000004644088,0.00014728536,0.00028605564,0.00023245453,0.00022893463,2.4704312e-7,0.006186066,0.27683416,0.000110148045,0.71473676,0.00013390058,0.0010993425],"study_design_scores_gemma":[0.001307549,0.00008435754,0.0012888868,0.00011886758,0.00018412039,0.000002659366,0.0032211293,0.8253283,0.0023884228,0.16330431,0.0026635546,0.00010782597],"about_ca_topic_score_codex":0.0000059622394,"about_ca_topic_score_gemma":0.000019701156,"teacher_disagreement_score":0.8881087,"about_ca_system_score_codex":0.00019848483,"about_ca_system_score_gemma":0.00019231088,"threshold_uncertainty_score":0.32505253},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002208699,0.00007158885,0.99443185,0.0009521377,0.0015147278,0.00052967906,0.00013605054,0.000066015746,0.00008927295],"genre_scores_gemma":[0.89032197,7.5943876e-7,0.108936176,0.00022490458,0.000111588044,0.00005202253,0.000029672701,0.000008863304,0.0003140533],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884665,0.000068169604,0.0002587635,0.00022710627,0.00044113904,0.00015819845],"domain_scores_gemma":[0.99727553,0.001337115,0.00034001694,0.00019890955,0.0008273078,0.000021132211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030008578,0.00010069739,0.00015177001,0.00007863023,0.00055931543,0.0000475597,0.0005100151,0.000025967407,0.0000030200779],"category_scores_gemma":[0.0011836749,0.000084032006,0.000132589,0.00031804576,0.000019034738,0.000060600847,0.00004162686,0.00023348072,4.5878025e-7],"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":[0.000041679163,0.000072507995,0.00032592315,0.0000287762,0.00006284696,2.3214734e-7,0.00093196135,0.8032641,0.00004377042,0.19321951,0.00013173738,0.0018769884],"study_design_scores_gemma":[0.0007117529,0.00013743962,0.0014090749,0.000011824274,0.000044295124,0.000002812228,0.00009364087,0.9640448,0.00010617772,0.031697772,0.0016107837,0.00012959445],"about_ca_topic_score_codex":0.000016225458,"about_ca_topic_score_gemma":0.000009645544,"teacher_disagreement_score":0.88811326,"about_ca_system_score_codex":0.0002973982,"about_ca_system_score_gemma":0.00014203887,"threshold_uncertainty_score":0.43018588},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044795116,0.000009144667,0.9917049,0.0014508541,0.001070447,0.00037636017,0.00004969589,0.000045051172,0.0008140377],"genre_scores_gemma":[0.8094958,3.717986e-7,0.18972279,0.00014067221,0.00007873505,0.00005678426,0.000015772888,0.00000723056,0.00048184514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874884,0.000102055,0.0002918787,0.00020719461,0.0005162236,0.00013379643],"domain_scores_gemma":[0.99852437,0.00043374675,0.00033169647,0.00020577852,0.00047803955,0.000026352878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062519516,0.00008483184,0.00012720423,0.00007006726,0.00080733915,0.00008607232,0.0007350856,0.000028493962,0.000011999873],"category_scores_gemma":[0.0001970824,0.00008025282,0.00007655113,0.00026802145,0.000011418744,0.00011076927,0.00008183779,0.00016821297,6.3214014e-7],"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":[0.000011030071,0.000048759066,0.0012454565,0.000009972111,0.00004227079,1.6104428e-7,0.00040627678,0.66554093,0.000016933507,0.3321195,0.000042153148,0.0005165403],"study_design_scores_gemma":[0.0013996145,0.00014503341,0.0040945983,0.000024094441,0.000050326722,0.000006773493,0.00018512012,0.8025433,0.00012915321,0.17593813,0.0152676515,0.00021622241],"about_ca_topic_score_codex":0.00007153599,"about_ca_topic_score_gemma":0.00001775618,"teacher_disagreement_score":0.8050163,"about_ca_system_score_codex":0.00041962016,"about_ca_system_score_gemma":0.0002498195,"threshold_uncertainty_score":0.62094814},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007819326,0.00008126294,0.9752662,0.002335436,0.002604886,0.0005898018,0.0004812233,0.000081677215,0.010740179],"genre_scores_gemma":[0.98086804,0.000002916399,0.015074666,0.00012756715,0.00018734462,0.000045495824,0.000035982146,0.000008103453,0.003649909],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846476,0.00030882555,0.00027767557,0.00012048973,0.00068988814,0.00013833874],"domain_scores_gemma":[0.9976499,0.0012034116,0.00023403238,0.00008528784,0.00079365465,0.000033700606],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008554866,0.00006227857,0.00012826677,0.00007776876,0.0015739317,0.000023993072,0.00026322,0.000033679837,0.00013086868],"category_scores_gemma":[0.00063490256,0.00006355612,0.0002718547,0.00039295078,0.0000413357,0.000025982303,0.000016032474,0.00010954341,0.0000010881897],"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":[0.000009354818,0.00007268327,0.00030467633,0.0000043814116,0.00007489677,5.484512e-8,0.0010824206,0.86950964,0.0000017801478,0.12791942,0.00014972639,0.000870941],"study_design_scores_gemma":[0.0004479703,0.000042831085,0.0005759547,0.0000032133264,0.00016493503,4.421018e-7,0.0004929247,0.4539331,0.000021873951,0.47343555,0.07075175,0.00012947948],"about_ca_topic_score_codex":0.00022493253,"about_ca_topic_score_gemma":0.00009579504,"teacher_disagreement_score":0.9730487,"about_ca_system_score_codex":0.000380406,"about_ca_system_score_gemma":0.00027153082,"threshold_uncertainty_score":0.9997259},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031726619,0.000043845946,0.9945679,0.00082204404,0.0005367109,0.00021204514,0.000095361764,0.000044677476,0.0005047997],"genre_scores_gemma":[0.92061186,0.0000016563591,0.07821162,0.00009229883,0.000041547897,0.000032132833,0.000007652599,0.000008229345,0.0009929793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990729,0.00006746583,0.00020414942,0.00017475277,0.00036449966,0.00011624368],"domain_scores_gemma":[0.998769,0.0004054737,0.00021188869,0.00016137846,0.0004274392,0.000024851206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002956139,0.00007284671,0.00010489994,0.0000623304,0.0005657605,0.000041581214,0.0002870388,0.000022484805,0.000005390613],"category_scores_gemma":[0.00017097035,0.000064285654,0.000054689965,0.00024639457,0.000022232347,0.00003780467,0.000031401018,0.00012691652,6.010141e-7],"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":[0.000007867027,0.000047277128,0.00055146555,0.000011191374,0.000042814052,1.68352e-7,0.00027472514,0.9435134,0.000009539143,0.05448517,0.00007760255,0.0009788168],"study_design_scores_gemma":[0.00047631992,0.0001083037,0.0010679683,0.0000071152367,0.000045266737,0.0000072940134,0.000056473516,0.9713184,0.000103949824,0.016600156,0.010089664,0.00011903671],"about_ca_topic_score_codex":0.000020721192,"about_ca_topic_score_gemma":0.000006446199,"teacher_disagreement_score":0.9174392,"about_ca_system_score_codex":0.00013367948,"about_ca_system_score_gemma":0.00012165301,"threshold_uncertainty_score":0.43514293},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004118812,0.000058213096,0.9912609,0.0012618856,0.0024478415,0.00050638046,0.00015131322,0.000031960895,0.0001627247],"genre_scores_gemma":[0.9821219,9.344745e-7,0.017305663,0.00006905398,0.00013262668,0.0001294092,0.000031988413,0.0000059576423,0.00020248824],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.00030083748,0.0004228133,0.00017328905,0.00064923626,0.00015540763],"domain_scores_gemma":[0.99743515,0.0013852072,0.00039387192,0.00023583688,0.0005340975,0.00001582378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018940871,0.000074970274,0.00012353278,0.000080832346,0.00069227366,0.000049350943,0.0006068226,0.00003413863,0.000003645364],"category_scores_gemma":[0.0009724029,0.00006319057,0.00011215088,0.0004569704,0.000016014015,0.000043864788,0.00004913532,0.00021883838,8.195505e-7],"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":[0.0000036833053,0.000039213974,0.00078190165,0.000009559121,0.000018967028,5.3619118e-8,0.00034610913,0.8677119,0.0000059480076,0.13056006,0.00007326783,0.00044936224],"study_design_scores_gemma":[0.00035589965,0.000040001523,0.0030938978,0.0000098739265,0.00002460541,0.0000012594516,0.00008095613,0.9683258,0.000011708218,0.025051277,0.0029360207,0.0000687051],"about_ca_topic_score_codex":0.000112506474,"about_ca_topic_score_gemma":0.000018663955,"teacher_disagreement_score":0.9780031,"about_ca_system_score_codex":0.00060811255,"about_ca_system_score_gemma":0.0002137584,"threshold_uncertainty_score":0.53244793},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026197801,0.000008111875,0.9939814,0.00074266706,0.0010412465,0.0001927447,0.00022754264,0.00015305266,0.001033427],"genre_scores_gemma":[0.89606196,0.0000044924436,0.102542266,0.00011297422,0.00016236398,0.000027208984,0.000050872284,0.000009641694,0.0010282442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990723,0.000058048525,0.00025625908,0.00014638268,0.00032772042,0.00013927567],"domain_scores_gemma":[0.9981995,0.0007700344,0.00016242263,0.00014799347,0.0006903863,0.000029613517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037885763,0.00007701094,0.00011995999,0.00011909651,0.00026679542,0.00004750771,0.00032060978,0.000057770387,0.0000064012584],"category_scores_gemma":[0.0011929813,0.00006874448,0.00016839194,0.000494014,0.000013098409,0.000048485912,0.000014995077,0.00007721843,0.000026375836],"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":[0.000005890661,0.00005781431,0.00012470609,0.000016929505,0.00010341155,4.3495615e-7,0.000975523,0.9443718,0.00009044241,0.049263537,0.00078013353,0.004209383],"study_design_scores_gemma":[0.00023263063,0.000013668203,0.00033954228,0.00000975468,0.000027076716,5.019593e-7,0.00006681948,0.9604092,0.00084836956,0.037255306,0.00071579585,0.00008129659],"about_ca_topic_score_codex":0.000018345107,"about_ca_topic_score_gemma":0.000012839455,"teacher_disagreement_score":0.89344215,"about_ca_system_score_codex":0.00010090839,"about_ca_system_score_gemma":0.00009153716,"threshold_uncertainty_score":0.28033182},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051934808,0.000095389536,0.9929555,0.00048221767,0.00076563243,0.00024070876,0.00008363696,0.000045695848,0.00013775649],"genre_scores_gemma":[0.9406909,7.7450494e-7,0.058960102,0.00008152298,0.000030354566,0.00004747977,0.000031731768,0.000005392746,0.00015177586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989764,0.00007125798,0.00032714635,0.00016890328,0.00035338438,0.00010288217],"domain_scores_gemma":[0.9986883,0.0005336072,0.00026076048,0.00011226025,0.0003871779,0.000017893404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039418018,0.00007093567,0.0001008973,0.0001233042,0.0003168692,0.00004702772,0.00025574374,0.000028424143,0.0000024147769],"category_scores_gemma":[0.0009841025,0.0000722758,0.00004290715,0.00033485945,0.000018385905,0.00011026568,0.00003591328,0.00017568718,2.2040716e-7],"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":[0.000008095644,0.000045751513,0.001715385,0.000023482551,0.000013327803,1.0785768e-7,0.0026612098,0.9693738,0.000010719881,0.01874815,0.000023802782,0.007376159],"study_design_scores_gemma":[0.0003364751,0.000029433892,0.005066474,0.000010240789,0.000015719466,0.0000013656534,0.00015671825,0.974398,0.00002364614,0.0197674,0.0001321985,0.000062306775],"about_ca_topic_score_codex":0.000023139139,"about_ca_topic_score_gemma":0.000018177581,"teacher_disagreement_score":0.9354974,"about_ca_system_score_codex":0.00024918184,"about_ca_system_score_gemma":0.00015935049,"threshold_uncertainty_score":0.29473215},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8321181,0.0024451392,0.07438308,0.02597017,0.023029631,0.0067771096,0.007725867,0.00023113722,0.027319774],"genre_scores_gemma":[0.9985945,0.000006599138,0.0004411562,0.000020788313,0.00010629057,0.000016256405,0.000018643455,0.0000028631137,0.00079286285],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99906373,0.00013447866,0.00022520796,0.000058434423,0.00042269012,0.00009547989],"domain_scores_gemma":[0.9989393,0.00041104987,0.00024498993,0.000054142216,0.00033995393,0.00001060028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046730405,0.000035840127,0.00006458729,0.000024531168,0.0008686617,0.000009643785,0.00017538163,0.000025701087,0.000064538835],"category_scores_gemma":[0.0008802375,0.0000266692,0.00007919663,0.00027278066,0.00004587643,0.000015115395,0.0000075625026,0.000092226546,2.457977e-7],"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":[0.00004390841,0.00011407888,0.002346295,0.000013215792,0.000062894265,9.998737e-8,0.012531224,0.67230093,0.00022009287,0.30940196,0.0009909768,0.0019743189],"study_design_scores_gemma":[0.0017566956,0.00031147228,0.05637022,0.000050451923,0.00039422378,0.0000010864583,0.12918621,0.04208656,0.0027759445,0.58354515,0.18291764,0.0006043684],"about_ca_topic_score_codex":0.0005127078,"about_ca_topic_score_gemma":0.0019628424,"teacher_disagreement_score":0.6302144,"about_ca_system_score_codex":0.00017031857,"about_ca_system_score_gemma":0.00012820978,"threshold_uncertainty_score":0.6681131},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047960776,0.000014914256,0.9940663,0.00043970108,0.0021888178,0.00064868707,0.000530003,0.00007777368,0.001554195],"genre_scores_gemma":[0.8601776,9.902162e-7,0.13851523,0.0002864749,0.00019343349,0.00023176818,0.0001394159,0.00001077723,0.00044431534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838483,0.00007455309,0.0005330361,0.0001780892,0.000602384,0.00022708173],"domain_scores_gemma":[0.9955707,0.0024455055,0.0006061906,0.00024300552,0.0010944592,0.00004010269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076887256,0.00011615347,0.00017404147,0.00015784908,0.00096627657,0.0000965979,0.0007127409,0.000056483885,0.0000031044146],"category_scores_gemma":[0.002465747,0.00012130549,0.00025285594,0.00040756995,0.000017773578,0.00017327027,0.000057241374,0.00017452742,0.0000018262976],"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":[0.0000038706926,0.000053511685,0.00039076578,0.000031005107,0.00006741825,3.2150517e-8,0.0011847713,0.8315013,0.000003914636,0.16434532,0.0014528381,0.0009652646],"study_design_scores_gemma":[0.00069468585,0.00007170009,0.0007840109,0.000007370297,0.000053381536,0.0000010916831,0.00012276079,0.7987117,0.000042732383,0.0804075,0.11902988,0.00007315829],"about_ca_topic_score_codex":0.00002490416,"about_ca_topic_score_gemma":0.000006852781,"teacher_disagreement_score":0.859698,"about_ca_system_score_codex":0.000365542,"about_ca_system_score_gemma":0.00029694207,"threshold_uncertainty_score":0.7431916},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002890198,0.0000056532435,0.9924868,0.00064392004,0.0021022118,0.00030896574,0.0013195592,0.00015230139,0.00009041908],"genre_scores_gemma":[0.9277753,0.0000012615432,0.068929784,0.00014691778,0.00045218001,0.000035207697,0.002279399,0.000013686901,0.0003662142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984911,0.000074472926,0.00047425748,0.00025949295,0.00051431503,0.0001863461],"domain_scores_gemma":[0.99741614,0.000776443,0.00037539005,0.00032417747,0.001069715,0.00003815059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069891283,0.00011399562,0.00014453393,0.00014992135,0.00043174464,0.00011224309,0.00046395755,0.00009921613,0.000004669763],"category_scores_gemma":[0.0014358332,0.00011047721,0.00014046155,0.0005200891,0.000028677212,0.000097010874,0.00002126347,0.00011339213,0.000016114724],"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":[0.000005464336,0.000048074206,0.0008398361,0.000017670825,0.00003310909,1.4437298e-7,0.00011136975,0.9836686,0.00007932082,0.013074078,0.0006838621,0.0014384582],"study_design_scores_gemma":[0.00052235107,0.000028588533,0.001946123,0.000008184677,0.00003624488,3.387149e-7,0.000003605207,0.9784149,0.0010568153,0.013312333,0.0045595295,0.00011101644],"about_ca_topic_score_codex":0.000045067907,"about_ca_topic_score_gemma":0.000027499338,"teacher_disagreement_score":0.92488515,"about_ca_system_score_codex":0.00018953565,"about_ca_system_score_gemma":0.00020989566,"threshold_uncertainty_score":0.45051298},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018415693,0.0000059623885,0.9889662,0.00672966,0.0013972822,0.00035830014,0.00021778894,0.00021636627,0.00026682866],"genre_scores_gemma":[0.87542164,0.0000019534634,0.121664114,0.00036972648,0.00016635352,0.000040647024,0.000023911245,0.000014880264,0.0022967462],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986047,0.0000709677,0.0003802735,0.00023297998,0.0004897182,0.00022135435],"domain_scores_gemma":[0.99758255,0.0008448114,0.0002673519,0.00028635166,0.00094950886,0.00006942686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935582,0.00010761643,0.00015928493,0.00017836042,0.00027737286,0.00006531456,0.0004944394,0.00008611333,0.0000028871395],"category_scores_gemma":[0.0024747595,0.00010544877,0.00017512545,0.0008877633,0.000014632138,0.00005545412,0.000028515562,0.00013307318,0.000022914628],"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":[0.0000075303424,0.000055423483,0.000622758,0.000018629027,0.000079638354,5.109342e-7,0.00076300075,0.92425674,0.00003743697,0.07090283,0.0026013905,0.000654098],"study_design_scores_gemma":[0.0005781777,0.000045648205,0.01313299,0.00004629962,0.000079549085,0.0000013984063,0.00010526575,0.8803675,0.00014782131,0.0824341,0.022843096,0.00021812809],"about_ca_topic_score_codex":0.000026539055,"about_ca_topic_score_gemma":0.00002188654,"teacher_disagreement_score":0.8735801,"about_ca_system_score_codex":0.00023313626,"about_ca_system_score_gemma":0.00013351138,"threshold_uncertainty_score":0.43000764},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012334463,0.00000785228,0.9948376,0.0009467769,0.000750252,0.00092838856,0.00052821066,0.00019116698,0.00057631667],"genre_scores_gemma":[0.6668717,0.0000023892826,0.33045307,0.00013617372,0.00023729628,0.00008582233,0.00016157412,0.00002181582,0.0020301344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982146,0.0000661476,0.0005064255,0.00035875448,0.0005632214,0.00029084025],"domain_scores_gemma":[0.99601495,0.0016911363,0.00037012182,0.00036913544,0.001477049,0.00007761773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007641824,0.00013407937,0.00020460557,0.0001979086,0.00052370003,0.00009802851,0.00061501935,0.000099648634,0.0000017153851],"category_scores_gemma":[0.0042221816,0.00013259269,0.00026332535,0.0011930071,0.000022430051,0.00007790944,0.000043533404,0.000122691,0.000009434714],"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":[0.000026505932,0.000069151705,0.00020153483,0.00003287923,0.00008007375,1.1220258e-7,0.0004465889,0.92903286,0.000020036616,0.066053905,0.003574841,0.00046151565],"study_design_scores_gemma":[0.0006675228,0.000053904307,0.0012757066,0.00001340029,0.0000654806,0.0000010120389,0.00009541114,0.94950247,0.00022148999,0.04233556,0.0056134434,0.00015457382],"about_ca_topic_score_codex":0.00002066875,"about_ca_topic_score_gemma":0.000007225321,"teacher_disagreement_score":0.66563827,"about_ca_system_score_codex":0.00022644892,"about_ca_system_score_gemma":0.00020553645,"threshold_uncertainty_score":0.5406973},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012373915,0.000049494527,0.9942373,0.00031098828,0.0007573956,0.00029724088,0.0024585272,0.00048759117,0.00016409159],"genre_scores_gemma":[0.7035652,0.0000040439013,0.29523095,0.00010347551,0.00010980441,0.00000837638,0.00035187817,0.000013270251,0.00061298936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988029,0.000039613045,0.0002858982,0.00020492564,0.00047932687,0.00018735779],"domain_scores_gemma":[0.99792176,0.00081785704,0.0003114844,0.00025088483,0.00066466146,0.000033367975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050232897,0.000106405314,0.0001412832,0.00013660123,0.00031510845,0.00007341236,0.0006532577,0.00008460315,0.0000036178794],"category_scores_gemma":[0.002730084,0.00009632376,0.00012133972,0.0006405192,0.00003073275,0.00010058329,0.00006495441,0.0001592435,0.0000081100825],"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":[0.000076167446,0.00019959289,0.00073063665,0.00021374835,0.00023739395,0.0000050076865,0.0016688046,0.88842475,0.001054186,0.08216144,0.020185875,0.0050423965],"study_design_scores_gemma":[0.0006211293,0.00004698206,0.00054793176,0.000045971847,0.00006715233,0.0000020925497,0.00007361288,0.9226215,0.0064502037,0.064129494,0.0051606493,0.00023326716],"about_ca_topic_score_codex":0.000017166385,"about_ca_topic_score_gemma":0.000006799247,"teacher_disagreement_score":0.7023278,"about_ca_system_score_codex":0.00015357877,"about_ca_system_score_gemma":0.00014120783,"threshold_uncertainty_score":0.3927969},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004646251,0.0000127705525,0.9822262,0.0024006818,0.001841101,0.0007155606,0.0077104303,0.00013544245,0.00031159775],"genre_scores_gemma":[0.35934556,0.000052782114,0.6367134,0.0004424211,0.0005730782,0.00010620885,0.0015428051,0.00003146881,0.0011922971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848443,0.000114318675,0.0005347872,0.00027904252,0.00037190493,0.00021549054],"domain_scores_gemma":[0.99603134,0.002563846,0.0003467819,0.00023151998,0.0007614666,0.00006503862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011142275,0.00011910739,0.0002262917,0.00013752948,0.00035474583,0.0000871831,0.00042157035,0.00010797433,0.0000062935574],"category_scores_gemma":[0.0022359372,0.00010881566,0.00021186458,0.00047747197,0.00005942516,0.00006553385,0.000031969354,0.000113811875,0.000010210983],"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":[0.0005093823,0.0021406019,0.022171088,0.00045516738,0.0026034927,0.00000748578,0.0015130311,0.03347242,0.0002495657,0.36198834,0.3560663,0.21882313],"study_design_scores_gemma":[0.0031283628,0.00019909881,0.03233039,0.000039141392,0.00024087749,0.0000068514782,0.00012918987,0.53453594,0.0006791473,0.20516138,0.22309673,0.000452887],"about_ca_topic_score_codex":0.000013066066,"about_ca_topic_score_gemma":0.000016748594,"teacher_disagreement_score":0.5010635,"about_ca_system_score_codex":0.00007179853,"about_ca_system_score_gemma":0.00012300904,"threshold_uncertainty_score":0.44373736},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011631859,0.00038631484,0.9907159,0.0006545199,0.0038056877,0.00045112937,0.0006563903,0.00011074642,0.002056109],"genre_scores_gemma":[0.91173834,0.000013305056,0.08667691,0.00006985012,0.00022506664,0.000054854467,0.000044036948,0.000019272922,0.0011583578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983252,0.00007481411,0.00055489904,0.00033429838,0.0004977028,0.00021306342],"domain_scores_gemma":[0.9981161,0.00050636515,0.00034482576,0.0003790976,0.00062675646,0.00002690401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006891214,0.00016484316,0.00026733574,0.00021012692,0.00011190636,0.0001275178,0.0007808955,0.00020183873,0.000002375405],"category_scores_gemma":[0.0004853776,0.0001590203,0.00027471082,0.00025176557,0.000016937023,0.000039945447,0.00019964162,0.00053019274,0.000003907081],"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":[0.000002047634,0.000048487702,0.000030055593,0.0001754659,0.000057353318,3.5525753e-7,0.0012222299,0.7876428,0.0000013418371,0.21038632,0.0001253349,0.0003082244],"study_design_scores_gemma":[0.00016875639,0.0000065015065,0.00008083854,0.00013688326,0.000037368274,2.4067742e-7,0.00003763238,0.6484197,0.00003762421,0.35072938,0.00024649542,0.00009857232],"about_ca_topic_score_codex":0.00011270045,"about_ca_topic_score_gemma":0.000102702965,"teacher_disagreement_score":0.91057515,"about_ca_system_score_codex":0.00042705634,"about_ca_system_score_gemma":0.00042345288,"threshold_uncertainty_score":0.648466},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005004664,0.000101664264,0.9908423,0.0056236545,0.0010688262,0.00079929,0.0004276235,0.00037086415,0.00026534975],"genre_scores_gemma":[0.7763106,0.0000017948191,0.22271329,0.0003407014,0.00012672889,0.00004115572,0.000025242854,0.000019897934,0.00042054572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982452,0.000077898345,0.0003969655,0.000389787,0.0006841073,0.00020604447],"domain_scores_gemma":[0.997525,0.0010933666,0.00015544635,0.00022834384,0.0009220597,0.00007581787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042670468,0.00018599781,0.00020582056,0.00034679292,0.00042316734,0.00017740353,0.00053574203,0.000105377716,0.000014076846],"category_scores_gemma":[0.00073010713,0.00015282584,0.00020970246,0.0009742859,0.000016755936,0.0001532413,0.000019148727,0.00023996439,0.000013730783],"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":[0.0007681038,0.00055283576,0.00010306376,0.0003328595,0.00051859807,0.0000055416826,0.014272378,0.2984111,0.0027805453,0.6481219,0.0018832234,0.03224983],"study_design_scores_gemma":[0.0014813064,0.0016541496,0.002512637,0.0006220755,0.0005094534,0.000007981934,0.00015086321,0.7603824,0.01756227,0.20084575,0.013232322,0.0010387859],"about_ca_topic_score_codex":0.00011583426,"about_ca_topic_score_gemma":0.000084339255,"teacher_disagreement_score":0.7758102,"about_ca_system_score_codex":0.0007004217,"about_ca_system_score_gemma":0.00014796693,"threshold_uncertainty_score":0.62320566},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01619233,0.00008257401,0.98018587,0.0001559232,0.0028535768,0.00033837848,0.000062111634,0.00006568449,0.00006357394],"genre_scores_gemma":[0.7754974,0.0000013838156,0.22429138,0.000007629467,0.00008232595,0.000032254393,0.000007264649,0.000008556008,0.00007180391],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989496,0.000043383207,0.00038510977,0.00019874757,0.00031473566,0.00010844697],"domain_scores_gemma":[0.9977589,0.0011684466,0.00020522348,0.00012172653,0.0007253863,0.000020266136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007699236,0.00008434834,0.00015215,0.0001057828,0.00021348092,0.00006618185,0.0001916228,0.000063189495,3.5731188e-7],"category_scores_gemma":[0.0007533106,0.000081083694,0.00015447178,0.00024475876,0.00001686121,0.00014995039,0.000014215844,0.00008107107,9.965335e-8],"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":[0.000004891626,0.000012698816,0.00007464747,0.00013699783,0.00006244984,2.5863596e-8,0.0004174364,0.80737805,0.00005528296,0.18159546,0.000004424018,0.010257651],"study_design_scores_gemma":[0.0002811209,0.000032832013,0.0001393257,0.00011318276,0.00007535487,0.0000010202972,0.00003366423,0.85643804,0.00047525598,0.1422618,0.000080665,0.00006773806],"about_ca_topic_score_codex":0.000024655923,"about_ca_topic_score_gemma":0.0000051631055,"teacher_disagreement_score":0.75930506,"about_ca_system_score_codex":0.00012675153,"about_ca_system_score_gemma":0.0001532528,"threshold_uncertainty_score":0.3306497},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010648542,0.000034231885,0.9957943,0.0008533779,0.0012017618,0.0004863207,0.000076736564,0.0002742602,0.00021414872],"genre_scores_gemma":[0.52370894,9.520993e-7,0.47581422,0.00002472953,0.00015911872,0.000048090908,0.00001424991,0.0000132958485,0.0002164037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988038,0.000045847886,0.00033716572,0.00024858283,0.00038606295,0.00017854566],"domain_scores_gemma":[0.99770105,0.0010919814,0.00020229923,0.00022280801,0.00074940105,0.000032477972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006295949,0.00011565972,0.00013995715,0.000117821815,0.00029543618,0.00013345563,0.0003817682,0.000074631185,7.5632704e-7],"category_scores_gemma":[0.0004992173,0.00010209155,0.00014465004,0.00030016596,0.000015577985,0.00012115971,0.0000137615,0.000114936985,8.780513e-7],"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":[0.00001123584,0.000025755196,0.00007441994,0.00009052434,0.00010907134,8.660268e-8,0.0025211682,0.7838908,0.000016888978,0.21063468,0.00004257671,0.0025828069],"study_design_scores_gemma":[0.00045158181,0.000069116424,0.0002087723,0.00008386564,0.00007655966,0.0000020549696,0.00012577437,0.87879896,0.00006065821,0.113734014,0.006277318,0.00011133238],"about_ca_topic_score_codex":0.000017056554,"about_ca_topic_score_gemma":0.000027944037,"teacher_disagreement_score":0.5226441,"about_ca_system_score_codex":0.00027747423,"about_ca_system_score_gemma":0.0002645139,"threshold_uncertainty_score":0.41631728},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014063934,0.00010163991,0.991105,0.0028351352,0.002907874,0.00037945117,0.00039968567,0.00016796186,0.00069684186],"genre_scores_gemma":[0.9690908,0.000004606275,0.029909354,0.00006730719,0.00015740583,0.000023479712,0.00007339751,0.000014799272,0.0006588444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821156,0.00014812882,0.00054896454,0.0003031255,0.0005108243,0.00027742234],"domain_scores_gemma":[0.997973,0.0008604901,0.00018993064,0.00019582889,0.0007189525,0.0000617457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012846546,0.00014807122,0.00019736358,0.0001969506,0.00024811074,0.0001414305,0.00045502235,0.0001531631,0.000004519271],"category_scores_gemma":[0.0008720792,0.00014098386,0.00025176132,0.00096611836,0.00003507323,0.000120223754,0.000013787682,0.00033706214,0.000003904358],"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":[0.000009986757,0.00005749702,0.00061295595,0.00008666189,0.000052623745,0.0000010432176,0.0010751351,0.32908142,0.000018551056,0.6671838,0.00016411174,0.0016562155],"study_design_scores_gemma":[0.00026291402,0.000026028032,0.0020106267,0.000087971544,0.000043654763,0.000002142061,0.000022426944,0.6967576,0.00036925572,0.29688862,0.0033900521,0.00013868186],"about_ca_topic_score_codex":0.000073189345,"about_ca_topic_score_gemma":0.000107733744,"teacher_disagreement_score":0.9676844,"about_ca_system_score_codex":0.00057490234,"about_ca_system_score_gemma":0.00031795175,"threshold_uncertainty_score":0.57491547},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037938202,0.000027321803,0.9929854,0.0003037706,0.000813693,0.0006261557,0.00023193989,0.00006548437,0.0045668287],"genre_scores_gemma":[0.5785294,0.0000011904773,0.4203424,0.00008290379,0.000052747324,0.000077768185,0.000024702582,0.000004551825,0.00088432024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892837,0.00007520547,0.00039060626,0.00021797203,0.00022170751,0.00016611462],"domain_scores_gemma":[0.996176,0.002657177,0.00027607364,0.00014658995,0.0007164948,0.000027675625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027995196,0.00011365312,0.00022947762,0.00014310879,0.00041080968,0.000057361292,0.00040064918,0.00006160774,0.000002206402],"category_scores_gemma":[0.00096948585,0.00010493297,0.00030262335,0.00031751758,0.000047488258,0.000037625283,0.000008974721,0.000101494035,7.271597e-7],"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":[0.00018240498,0.0012649869,0.00040042572,0.00047170412,0.0011675416,1.4168447e-7,0.005709879,0.6580609,0.0009451272,0.2933827,0.0015345113,0.036879644],"study_design_scores_gemma":[0.0010148339,0.000038196245,0.0009533112,0.00003854898,0.00011963577,5.059355e-7,0.00017144077,0.9388521,0.006983152,0.0483165,0.0033875145,0.00012428874],"about_ca_topic_score_codex":0.000005179694,"about_ca_topic_score_gemma":0.0000043612868,"teacher_disagreement_score":0.57815003,"about_ca_system_score_codex":0.000083380255,"about_ca_system_score_gemma":0.00018828044,"threshold_uncertainty_score":0.42790425},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040964386,0.000043297947,0.9910735,0.0011060345,0.001200813,0.00036437498,0.000036588375,0.000034133005,0.002044816],"genre_scores_gemma":[0.98648965,0.0000024166638,0.012625658,0.00019230499,0.00004211275,0.00004791291,0.0000055531314,0.000003842927,0.00059054105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999079,0.00009858641,0.00032383174,0.00015943818,0.00020708641,0.00013209728],"domain_scores_gemma":[0.99419457,0.0046749874,0.00019080592,0.00015877279,0.00076873205,0.000012131564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040832514,0.00007549632,0.000114090704,0.00013232249,0.00029722368,0.000055222703,0.00039024226,0.000049626113,0.0000016133489],"category_scores_gemma":[0.005029233,0.000059889935,0.00011998323,0.0005818768,0.000030425519,0.00005728954,0.000023664601,0.00015590238,9.287535e-7],"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":[0.000010128451,0.000092376446,0.007759156,0.000022847218,0.00010505362,9.780367e-8,0.0014817059,0.8192902,0.0000067847445,0.1676645,0.000049729224,0.0035173842],"study_design_scores_gemma":[0.00051684387,0.000018545801,0.03330974,0.00016687247,0.00005944441,4.1517788e-7,0.00024354694,0.87646174,0.00029788955,0.08840924,0.00043252256,0.000083212784],"about_ca_topic_score_codex":0.00008242325,"about_ca_topic_score_gemma":0.00016094775,"teacher_disagreement_score":0.9823932,"about_ca_system_score_codex":0.00023222422,"about_ca_system_score_gemma":0.0002448569,"threshold_uncertainty_score":0.60208255},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054116473,0.000021251282,0.98953843,0.0008745218,0.0011654343,0.00041675684,0.00016597504,0.000056335808,0.0023496174],"genre_scores_gemma":[0.97541875,0.000007753943,0.023703618,0.00004155175,0.000042610336,0.000019150637,0.0000143091065,0.0000055394053,0.0007467186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987789,0.00011231588,0.00045431362,0.00013605434,0.00037746987,0.00014094275],"domain_scores_gemma":[0.9963386,0.0017973464,0.00038157494,0.0002333609,0.0012272948,0.000021843352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006140794,0.000102587095,0.00016490264,0.000119722376,0.00039116447,0.000054346885,0.00040185062,0.00007545382,0.000007717594],"category_scores_gemma":[0.0011820331,0.00007011711,0.00041200014,0.0005270405,0.000042857788,0.000045069293,0.000007165649,0.00010872378,0.0000037898487],"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":[0.000120474004,0.0008686565,0.0018302446,0.00012882317,0.0010961723,2.320689e-7,0.00036413185,0.2176661,0.000566499,0.62670666,0.0039774603,0.14667456],"study_design_scores_gemma":[0.0010014249,0.00018134488,0.054863006,0.00013058796,0.00015453635,0.0000013424253,0.00003102253,0.79633564,0.0072742915,0.13648069,0.0033907294,0.00015537161],"about_ca_topic_score_codex":0.000028761102,"about_ca_topic_score_gemma":0.000010038573,"teacher_disagreement_score":0.9700071,"about_ca_system_score_codex":0.00034022925,"about_ca_system_score_gemma":0.00022095595,"threshold_uncertainty_score":0.30085605},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10488398,0.0015678209,0.8662854,0.0009351855,0.0019266013,0.0063549667,0.0026151277,0.000119727825,0.015311232],"genre_scores_gemma":[0.90972084,0.000005202445,0.08556057,0.000039191716,0.00010870516,0.00027191878,0.00020894664,0.000018732222,0.0040658982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984742,0.00009306655,0.00063814863,0.00020255559,0.00035640207,0.00023563491],"domain_scores_gemma":[0.9923193,0.0052775242,0.00034029857,0.00016396571,0.0018456592,0.000053283253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068099174,0.00014041361,0.00033814547,0.00053290854,0.00018091238,0.000015672715,0.00013118213,0.000081964645,0.00000817421],"category_scores_gemma":[0.004389526,0.00012969646,0.0002806904,0.0010301516,0.000040649455,0.000027641005,0.000013026065,0.00020588949,0.0000025528593],"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":[0.0036561051,0.009133409,0.031501994,0.0034833143,0.0048624184,0.0000018333668,0.005508846,0.2483558,0.000376326,0.66523683,0.0032729646,0.024610149],"study_design_scores_gemma":[0.01258457,0.0003826045,0.028922733,0.0015319515,0.0013916774,4.707865e-7,0.0005070637,0.5304009,0.0035614977,0.41965646,0.0009312079,0.00012890292],"about_ca_topic_score_codex":0.000020113182,"about_ca_topic_score_gemma":0.0006790148,"teacher_disagreement_score":0.80483687,"about_ca_system_score_codex":0.000481377,"about_ca_system_score_gemma":0.0007345375,"threshold_uncertainty_score":0.5288868},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010332865,0.000045226734,0.99396133,0.0031783078,0.0012223154,0.0007502782,0.00040308572,0.00006418424,0.000271932],"genre_scores_gemma":[0.68114036,0.000005498244,0.3154176,0.00046652206,0.00022022668,0.0003089545,0.0000970708,0.000009259649,0.0023345451],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890333,0.00005225922,0.00033186143,0.0002447823,0.00029938042,0.00016837192],"domain_scores_gemma":[0.99707687,0.0013197813,0.00027423832,0.00022840366,0.0010683645,0.00003232968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003452367,0.000116819836,0.00016761495,0.00009132494,0.0005826833,0.00007675332,0.000451834,0.0001135633,0.0000030975127],"category_scores_gemma":[0.00084515894,0.00011060988,0.00027757068,0.0003836343,0.000036219557,0.00004690128,0.000013401834,0.000094939474,0.0000019107429],"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":[0.0000096288095,0.000109239496,0.00008085446,0.00003129091,0.00011431181,1.4450188e-8,0.00032287362,0.038637523,0.00011635506,0.9570108,0.0027545926,0.0008125091],"study_design_scores_gemma":[0.0008284285,0.00004534017,0.00046888008,0.000037836555,0.00014544108,3.0783747e-7,0.000061960665,0.6331711,0.0010324161,0.32524234,0.038804393,0.0001615668],"about_ca_topic_score_codex":0.000009364324,"about_ca_topic_score_gemma":0.0000060958346,"teacher_disagreement_score":0.681037,"about_ca_system_score_codex":0.00030405464,"about_ca_system_score_gemma":0.00026052044,"threshold_uncertainty_score":0.451054},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023456324,0.000013396769,0.9902978,0.0018322906,0.003384445,0.00032837212,0.000084951585,0.00011956971,0.0037046457],"genre_scores_gemma":[0.8620734,0.0000017132511,0.13665518,0.0001266174,0.0002637356,0.000021119327,0.000028404187,0.000010906537,0.000818901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853474,0.00014379094,0.0003839767,0.00029284268,0.00046526862,0.00017937427],"domain_scores_gemma":[0.99620074,0.0009275091,0.00042530042,0.00030841303,0.0020996444,0.00003840398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052156765,0.00013747068,0.00019456772,0.00016617462,0.0005325443,0.00008026137,0.000636186,0.00012524815,0.000005143613],"category_scores_gemma":[0.0037662308,0.00013355479,0.00019608384,0.0005812046,0.00005234641,0.00016844741,0.000031496325,0.00026250043,0.000001560548],"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":[0.000023974982,0.00008025417,0.00019524962,0.000013846924,0.00008302106,1.2382456e-7,0.00043396695,0.6246652,0.0000078607445,0.37365675,0.00015335536,0.00068637973],"study_design_scores_gemma":[0.0008216348,0.000059747945,0.0076113604,0.000031157568,0.00016170739,9.735311e-7,0.00027333223,0.8221319,0.00010706883,0.16583104,0.0028192755,0.0001508175],"about_ca_topic_score_codex":0.0002179825,"about_ca_topic_score_gemma":0.00003003273,"teacher_disagreement_score":0.8618389,"about_ca_system_score_codex":0.0007902506,"about_ca_system_score_gemma":0.0004632347,"threshold_uncertainty_score":0.5446206},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018474867,0.000021630025,0.99393106,0.00072915474,0.0013058527,0.00030171836,0.000059921542,0.000058912272,0.0017442743],"genre_scores_gemma":[0.93683684,9.3888093e-7,0.06225672,0.0001529149,0.00007603274,0.000018819075,0.000013895114,0.000007976543,0.0006358722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987255,0.00012275229,0.00042861202,0.00019925274,0.00032897096,0.00019495268],"domain_scores_gemma":[0.9980693,0.001138681,0.00015085882,0.00018525816,0.00043306669,0.00002282755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070399867,0.000106499676,0.00018785398,0.0001801754,0.00024650875,0.00004071211,0.0004957511,0.0001020365,0.0000028616466],"category_scores_gemma":[0.0016934525,0.00010326391,0.0001577944,0.00068256026,0.000024339733,0.0001111644,0.00002500827,0.00025716363,8.334024e-7],"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":[0.000005678086,0.000049925187,0.0007924619,0.000021736229,0.000034763132,8.6103796e-8,0.0008322089,0.72148836,0.00001182322,0.27647418,0.000042348598,0.0002464317],"study_design_scores_gemma":[0.0012992576,0.000012296193,0.0016632379,0.00004733353,0.000039096267,1.446556e-7,0.000073163894,0.9168312,0.00014260822,0.07921344,0.0005862161,0.00009200824],"about_ca_topic_score_codex":0.00005206128,"about_ca_topic_score_gemma":0.000048309244,"teacher_disagreement_score":0.93498933,"about_ca_system_score_codex":0.0002576469,"about_ca_system_score_gemma":0.0002638574,"threshold_uncertainty_score":0.421098},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08411512,0.0002032622,0.8302917,0.03556765,0.027080247,0.0024417322,0.01040823,0.00040103804,0.009491015],"genre_scores_gemma":[0.99728996,0.0000043582313,0.0010619651,0.000034208966,0.00072112645,0.000018310688,0.00008756104,0.00001749318,0.0007650066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984504,0.00006362847,0.00056591106,0.00014073083,0.0006163391,0.00016298621],"domain_scores_gemma":[0.99385643,0.0038614182,0.00030755415,0.00015038483,0.0017974151,0.00002678537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055069884,0.00011964008,0.00015786628,0.00006601172,0.0006004998,0.00012268497,0.00020722291,0.00006449685,0.000022400356],"category_scores_gemma":[0.0041603716,0.00008555878,0.00021089113,0.0001004798,0.00018631463,0.000030430301,0.0000093208055,0.00017415793,0.00001109399],"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":[0.000019870382,0.00006773595,0.0001366045,0.00009256747,0.00019925516,1.234378e-7,0.0015465567,0.11572675,0.0000051335805,0.8818843,0.00024179884,0.00007933031],"study_design_scores_gemma":[0.000295633,0.000081764876,0.004112027,0.00011173768,0.0003704613,9.550098e-7,0.00034293655,0.12994653,0.00015891486,0.84666306,0.017765827,0.00015013105],"about_ca_topic_score_codex":0.00005668161,"about_ca_topic_score_gemma":0.00006610358,"teacher_disagreement_score":0.91317487,"about_ca_system_score_codex":0.00019431599,"about_ca_system_score_gemma":0.00019417878,"threshold_uncertainty_score":0.49806535},"labels":[],"label_agreement":null}]}