{"meta":{"query_hash":"66b9019c05d7","filters":{"venue":"Computational Linguistics"},"cohort_total":61,"direct_labels_cover":0,"predictions_cover":61,"exported":61,"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/66b9019c05d7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computational+Linguistics"},"results":[{"id":"W117485591","doi":"10.1162/coli.2004.30.1.107","title":"Book Review","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","score_opus":0.021598479154666134,"score_gpt":0.3148972048835334,"score_spread":0.2932987257288673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W117485591","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059352522,0.8164984,0.080606356,0.0024323936,0.002243967,0.000840014,0.00031674144,0.00096796895,0.09603481],"genre_scores_gemma":[0.12975855,0.009723994,0.4522412,0.38915044,0.0095157605,0.00009319373,0.0032596253,0.00054996443,0.005707257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990093,0.000020507112,0.00027252565,0.00017826515,0.0003590126,0.0001603513],"domain_scores_gemma":[0.99875385,0.00011310006,0.00009791571,0.00014293591,0.00080208614,0.000090110814],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014233447,0.000114231705,0.00015266631,0.0000493467,0.00008644894,0.000018884537,0.00013825702,0.00002675549,0.00042308643],"category_scores_gemma":[0.0035412828,0.000120706616,0.000058213984,0.00019905217,0.00006513846,0.00001543733,0.000037291462,0.00010826144,0.00806801],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038046387,0.000072716786,0.00002015554,0.00022804306,0.000017330358,0.00003240946,0.00002057792,0.12305732,0.0000021040346,0.14078249,0.73566204,0.000100993384],"study_design_scores_gemma":[0.00032099773,0.00001953658,0.00030061323,0.00063498324,0.00003533804,0.000013484264,6.539602e-7,0.0011460889,0.000010808844,0.04698212,0.95038855,0.0001468025],"about_ca_topic_score_codex":0.000002767321,"about_ca_topic_score_gemma":3.3371074e-7,"teacher_disagreement_score":0.8067744,"about_ca_system_score_codex":0.00012751992,"about_ca_system_score_gemma":0.0002281705,"threshold_uncertainty_score":0.99270433},"labels":[],"label_agreement":null},{"id":"W1502796908","doi":"10.1162/coli.2002.28.4.560","title":"<i>Patterns of Text: In Honour of Michael Hoey</i> Mike Scott and Geoff Thompson (editors) (University of Liverpool) Amsterdam: John Benjamins, 2001, vii+323 pp; hardbound, ISBN 90-272-2572-9 and 1-55619-792-6, $100.00, € 110.00","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Pennsylvania","keywords":"Honour; Sociology; Media studies; Political science; Law","score_opus":0.029277488832886354,"score_gpt":0.21196384906464022,"score_spread":0.18268636023175386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1502796908","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":[0.961434,0.0028121448,0.00023657175,0.00012007524,0.0016156533,0.00031471977,0.001927657,0.000035999266,0.031503186],"genre_scores_gemma":[0.99525696,0.0003084188,0.0006361342,0.000088890665,0.0011599163,7.771935e-7,0.00012384163,0.00002466331,0.0024004027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985255,0.00006183654,0.000475794,0.00029861755,0.00037233048,0.0002659258],"domain_scores_gemma":[0.99830264,0.00039537033,0.00035975932,0.00015930954,0.00067525223,0.00010768048],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000219971,0.00023339437,0.00045352083,0.00021449492,0.00023401735,0.00013890157,0.00023010383,0.00011174164,0.00047235467],"category_scores_gemma":[0.00022523155,0.00026420734,0.00009291164,0.00006311639,0.00048504127,0.0001962414,0.00017519135,0.0002828966,0.000009978061],"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":[0.0007433643,0.0037691188,0.11492476,0.0049893516,0.0007875517,0.0003904281,0.1432044,0.0035518012,0.000109754146,0.62168324,0.09553123,0.0103149945],"study_design_scores_gemma":[0.0066132853,0.0017886714,0.09589355,0.0024938555,0.00037180734,0.000044568147,0.02710019,0.033627514,0.00010612847,0.029791526,0.8002272,0.0019416473],"about_ca_topic_score_codex":0.0008059738,"about_ca_topic_score_gemma":0.0010649579,"teacher_disagreement_score":0.704696,"about_ca_system_score_codex":0.000037652313,"about_ca_system_score_gemma":0.00004988693,"threshold_uncertainty_score":0.999981},"labels":[],"label_agreement":null},{"id":"W1521465908","doi":"10.1162/089120101300346831","title":"Book Reviews","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":false,"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","keywords":"Computer science","score_opus":0.04113790453060918,"score_gpt":0.34483954249689,"score_spread":0.3037016379662808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521465908","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016945989,0.048588656,0.12477967,0.00023131406,0.005725112,0.00041891044,0.000037946967,0.00020340219,0.8183204],"genre_scores_gemma":[0.7692511,0.0015156623,0.03768928,0.04936048,0.017070347,0.00016497959,0.0015313248,0.00012248369,0.123294346],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920994,0.000073495736,0.00025175177,0.00018072191,0.00013248285,0.00015161237],"domain_scores_gemma":[0.99932826,0.0001488576,0.00008618462,0.00013510561,0.00024148806,0.000060110197],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015957854,0.000095831274,0.00013751234,0.00005422498,0.000077159755,0.000020182015,0.00009207495,0.00005272818,0.004121761],"category_scores_gemma":[0.00068340974,0.00009015554,0.00006485583,0.00011769895,0.000036896905,0.000010714791,0.000015319545,0.00010094193,0.0029675337],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052154683,0.0002495851,0.00088356907,0.000025349198,0.000060498576,0.00018843757,0.0011591635,0.00036565986,0.000004038284,0.29856414,0.6706462,0.027801204],"study_design_scores_gemma":[0.00027057767,0.00003125216,0.0025612747,0.000016517144,0.000030357167,0.000027430657,0.00004122362,0.00050837785,0.0000016735947,0.025906436,0.9704892,0.00011565134],"about_ca_topic_score_codex":0.000008885443,"about_ca_topic_score_gemma":0.0000013139864,"teacher_disagreement_score":0.7675565,"about_ca_system_score_codex":0.000017462791,"about_ca_system_score_gemma":0.000021878903,"threshold_uncertainty_score":0.99780875},"labels":[],"label_agreement":null},{"id":"W1538392035","doi":"10.1162/coli.2003.29.3.507","title":"Book Review","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"","field":"","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.024111771610737083,"score_gpt":0.3140361472330895,"score_spread":0.2899243756223524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538392035","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012432994,0.6600555,0.024858352,0.00024287826,0.0015890725,0.00045819258,0.00011990047,0.0003774323,0.31228626],"genre_scores_gemma":[0.09390998,0.012547173,0.48986736,0.36374652,0.0048699016,0.00012615747,0.002099936,0.0007081577,0.032124806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897087,0.00008063263,0.00027423352,0.00017844953,0.00032986543,0.00016593747],"domain_scores_gemma":[0.9985578,0.00025386715,0.00009908722,0.00015072017,0.00084842957,0.00009008721],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000261235,0.0001142947,0.00015594471,0.00004574867,0.00008618375,0.00001810244,0.00009979733,0.000026372836,0.0016033318],"category_scores_gemma":[0.0105530275,0.00012108166,0.0000553104,0.00020644917,0.000053459884,0.000012235717,0.000015494696,0.00010255482,0.0065140654],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011603405,0.0000339939,0.000057617875,0.00012800704,0.000010758515,0.000010354861,0.000006387043,0.0053160377,8.1602917e-7,0.17920746,0.81518674,0.000040654424],"study_design_scores_gemma":[0.00015133202,0.000011747613,0.00013500323,0.0002590562,0.000033527394,0.00001319041,7.596091e-7,0.002268718,0.000010152468,0.016406024,0.98057014,0.0001403583],"about_ca_topic_score_codex":4.639015e-7,"about_ca_topic_score_gemma":9.7491345e-8,"teacher_disagreement_score":0.6475083,"about_ca_system_score_codex":0.000058242833,"about_ca_system_score_gemma":0.00016668564,"threshold_uncertainty_score":0.99930936},"labels":[],"label_agreement":null},{"id":"W1894075015","doi":"10.1162/coli_a_00226","title":"CODRA: A Novel Discriminative Framework for Rhetorical Analysis","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":186,"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":"Parsing; Computer science; Natural language processing; Rhetorical question; Discriminative model; Artificial intelligence; Coherence (philosophical gambling strategy); Probabilistic logic; Parse tree; Classifier (UML); Linguistics; Margin (machine learning); Machine learning; Mathematics","score_opus":0.07786810095225595,"score_gpt":0.37519876686569953,"score_spread":0.2973306659134436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1894075015","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":[0.00003288896,0.0002923463,0.99783635,0.00036099707,0.0006130231,0.00013631964,0.000036096713,0.0003235951,0.0003683946],"genre_scores_gemma":[0.3168893,3.0707122e-7,0.6824469,0.00022188977,0.00033479053,0.000015363172,0.00004798208,0.000007174288,0.00003632507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877787,0.000023308126,0.0002482608,0.00034563427,0.00040594136,0.00019898923],"domain_scores_gemma":[0.99677914,0.0008913649,0.00014543669,0.00023522794,0.0018029008,0.00014591425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00028506122,0.00013819772,0.00022102636,0.00020495823,0.00010984288,0.00014460496,0.00057896244,0.0000909786,0.0000012440561],"category_scores_gemma":[0.008746425,0.00012714321,0.00010986383,0.0009114628,0.000056597568,0.00006395414,0.00019039083,0.00016533466,0.000005118034],"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":[0.0000072163634,0.00006834111,0.00008543059,0.000009544587,0.00007421607,0.0000039941106,0.000514692,0.006049588,0.0000015962652,0.99130404,0.00082616863,0.001055194],"study_design_scores_gemma":[0.00011973827,0.000047604895,0.00006812382,0.00001057938,0.00006435032,0.0000016858186,0.000012566347,0.40182483,0.00005455965,0.59528255,0.002390289,0.00012309362],"about_ca_topic_score_codex":0.0000073661904,"about_ca_topic_score_gemma":0.0000012770635,"teacher_disagreement_score":0.39602146,"about_ca_system_score_codex":0.0001238793,"about_ca_system_score_gemma":0.00020024118,"threshold_uncertainty_score":0.99960333},"labels":[],"label_agreement":null},{"id":"W1978620866","doi":"10.1162/coli.2008.34.2.145","title":"Semantic Role Labeling: An Introduction to the Special Issue","year":2008,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Field (mathematics); Computational linguistics; Identification (biology); Computational model; Semantic role labeling; Artificial intelligence; Natural language processing; Data science; Key (lock); Semantics (computer science)","score_opus":0.01392567728635698,"score_gpt":0.2788210233112759,"score_spread":0.26489534602491893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978620866","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":[0.0012072945,0.00023202332,0.98769623,0.006540583,0.0027071415,0.0001888848,0.000004820558,0.0005171378,0.00090587547],"genre_scores_gemma":[0.21517292,0.000002049423,0.7504694,0.0009916762,0.033086702,0.0000056570584,0.000024526946,0.000011165259,0.00023588617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99886143,0.00004927093,0.00020407222,0.00033340772,0.00037396635,0.00017785912],"domain_scores_gemma":[0.99870044,0.00009517739,0.0000714055,0.00034933837,0.00070089987,0.00008276167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021704598,0.0001162558,0.00010436436,0.00009589627,0.00038225393,0.00012905993,0.0007736772,0.00004403409,0.000018602801],"category_scores_gemma":[0.0013542746,0.000093778915,0.00002753405,0.0004030199,0.00005003763,0.000083910985,0.00018224018,0.00017795156,0.00011573769],"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":[0.000017444067,0.00016127632,0.00020492951,0.000018157516,0.000018847908,0.000067713976,0.0042877123,0.054094896,0.00015437824,0.75772375,0.15023452,0.033016395],"study_design_scores_gemma":[0.00012756052,0.00013538108,0.0003566821,0.00001222349,0.0000089329615,0.00011458833,0.000027931663,0.26393262,0.0010698817,0.20921199,0.5247016,0.0003005831],"about_ca_topic_score_codex":0.000011759422,"about_ca_topic_score_gemma":0.000005355355,"teacher_disagreement_score":0.54851174,"about_ca_system_score_codex":0.000045343553,"about_ca_system_score_gemma":0.00010569222,"threshold_uncertainty_score":0.38241932},"labels":[],"label_agreement":null},{"id":"W2017292107","doi":"10.1162/coli_a_00143","title":"Computing Lexical Contrast","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":100,"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; National Research Council Canada","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Contrast (vision); Computer science; Natural language processing; Artificial intelligence; Word (group theory); Meaning (existential); Focus (optics); Linguistics; Information retrieval; Psychology; Philosophy","score_opus":0.020473053507219972,"score_gpt":0.3092489102287959,"score_spread":0.28877585672157596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017292107","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":[0.00040907745,0.0013601898,0.99334645,0.00012862087,0.0010556955,0.000065970344,0.000002969139,0.0006192405,0.0030117924],"genre_scores_gemma":[0.5141332,5.0967594e-7,0.48480374,0.00036610247,0.0006646885,7.992393e-7,0.0000084977955,0.0000054889756,0.000016967904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892163,0.00003903943,0.00022741068,0.00018619948,0.00030342976,0.0003223119],"domain_scores_gemma":[0.9988371,0.00035942448,0.000093852635,0.00017606713,0.00039508077,0.00013847867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002915573,0.00012258625,0.00012905803,0.0000749032,0.00016014365,0.00012585154,0.0005054979,0.000061809835,0.0000064940714],"category_scores_gemma":[0.0012754778,0.00011763277,0.00004293554,0.00021828865,0.000054170712,0.00010521313,0.00022730313,0.00019266266,0.000054787688],"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":[0.000001401425,0.00005334436,0.0009540607,0.000010791887,0.000006820171,0.0000056378567,0.00020258423,0.0005454909,0.000019198393,0.9872227,0.0013370987,0.0096408855],"study_design_scores_gemma":[0.00033952904,0.00004982559,0.0028850026,0.000076381315,0.000013458207,0.00007185684,0.00001254647,0.5267381,0.0010541631,0.44589248,0.02234588,0.0005207412],"about_ca_topic_score_codex":0.0000033404563,"about_ca_topic_score_gemma":1.4484736e-7,"teacher_disagreement_score":0.5413302,"about_ca_system_score_codex":0.000047551326,"about_ca_system_score_gemma":0.00006681745,"threshold_uncertainty_score":0.47969252},"labels":[],"label_agreement":null},{"id":"W2046436395","doi":"10.1162/089120100561755","title":"The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach","year":2000,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":221,"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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Rhetorical question; Computer science; Automatic summarization; Parsing; Natural language processing; Artificial intelligence; Linguistics; Context (archaeology); Natural language understanding; Natural language; Philosophy; History","score_opus":0.020461250025670744,"score_gpt":0.28202723553398357,"score_spread":0.26156598550831284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046436395","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":[0.0011838062,0.0012629762,0.99429595,0.00016199854,0.0002017042,0.00011595723,0.000006106678,0.00029144352,0.0024800568],"genre_scores_gemma":[0.4812593,0.0000034274162,0.5185337,0.00006390238,0.000078203484,0.0000016324433,0.000011128873,0.0000054885586,0.000043203174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987621,0.00007726541,0.00030968504,0.00023047758,0.00042765072,0.00019287081],"domain_scores_gemma":[0.9981668,0.0008222381,0.000120620556,0.00027887197,0.00055515795,0.00005632362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024810457,0.00011724332,0.00013371222,0.000044366236,0.00023883021,0.00013478864,0.00076318264,0.00006212516,0.0000042789447],"category_scores_gemma":[0.00093329046,0.00008804749,0.000052148305,0.00054995134,0.00011690181,0.00003411451,0.00006191197,0.0001793188,0.000005707053],"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":[0.000039270995,0.00024251283,0.00031386063,0.000056078632,0.000025786734,0.000016190368,0.00020594119,0.26872784,0.00004154179,0.6673367,0.0022265436,0.060767755],"study_design_scores_gemma":[0.00016402134,0.000039918523,0.00017146439,0.000028804587,0.0000064122187,0.0000047992594,0.0000023729308,0.8793194,0.00032436993,0.113552816,0.006259916,0.00012567035],"about_ca_topic_score_codex":0.000010832254,"about_ca_topic_score_gemma":2.3295397e-7,"teacher_disagreement_score":0.6105916,"about_ca_system_score_codex":0.00005360713,"about_ca_system_score_gemma":0.00022811309,"threshold_uncertainty_score":0.35904723},"labels":[],"label_agreement":null},{"id":"W2048760284","doi":"10.1162/089120104323093267","title":"Inferable Centers, Centering Transitions, and the Notion of Coherence","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"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":"Cohesion (chemistry); Coherence (philosophical gambling strategy); Computer science; Indeterminacy (philosophy); Transition (genetics); Linguistics; Identity (music); Natural language processing; Epistemology; Mathematics; Philosophy","score_opus":0.010828978407771098,"score_gpt":0.2574355551626614,"score_spread":0.24660657675489034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048760284","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":[0.001757758,0.0005908473,0.9963555,0.0006138477,0.0001703268,0.00009525597,0.0000058796736,0.00009546517,0.00031514792],"genre_scores_gemma":[0.6087928,0.0000052948135,0.39103556,0.000120000564,0.000034023687,0.0000020927323,0.000005415108,0.0000021584967,0.0000026744576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999441,0.000024533967,0.00017030322,0.0001231859,0.00015985627,0.00008108261],"domain_scores_gemma":[0.9993883,0.00011090493,0.000080450416,0.00010851517,0.00028846506,0.000023357627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015537249,0.00006432726,0.000090540445,0.000043582408,0.00011347635,0.000064884436,0.00024316466,0.000024291858,7.6111417e-7],"category_scores_gemma":[0.00033472,0.000049478243,0.000023494053,0.00012735924,0.00011953713,0.000055260807,0.000072898925,0.00008954571,9.635398e-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":[0.000009749515,0.00002627663,0.00004915146,0.000032994456,0.0000065234744,0.0000039610927,0.0004909012,0.009193419,0.000076990815,0.98823965,0.000013488387,0.0018568861],"study_design_scores_gemma":[0.00097119977,0.00003848044,0.0004136492,0.0001516881,0.000009032536,0.00002254652,0.000013484027,0.0696674,0.0014385355,0.9269553,0.0002144902,0.000104233324],"about_ca_topic_score_codex":0.00002658777,"about_ca_topic_score_gemma":0.0000018655504,"teacher_disagreement_score":0.60703504,"about_ca_system_score_codex":0.000022745937,"about_ca_system_score_gemma":0.000054877022,"threshold_uncertainty_score":0.20176642},"labels":[],"label_agreement":null},{"id":"W2051593977","doi":"10.1162/coli_a_00002","title":"Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":302,"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":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Paraphrase; Computer science; Natural language processing; Task (project management); Artificial intelligence; Parallel corpora; Field (mathematics); Linguistics; Machine translation","score_opus":0.06410955906269462,"score_gpt":0.40156873393396203,"score_spread":0.3374591748712674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051593977","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":[0.008246019,0.0003009305,0.9905028,0.00002681942,0.0005927841,0.000070313115,0.000082519684,0.0001313574,0.000046461464],"genre_scores_gemma":[0.37710303,0.0000015733772,0.6225455,0.000057350328,0.00015086375,0.0000010341556,0.00013187973,0.0000056488334,0.000003121746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988407,0.00014350117,0.0002994914,0.00035194,0.00023244528,0.00013193223],"domain_scores_gemma":[0.9975768,0.00093688024,0.00018970444,0.00041745487,0.0008149914,0.00006417209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091069145,0.00011171991,0.00017138114,0.00008992578,0.00010089301,0.00012864252,0.00085600314,0.00006489684,0.000003132662],"category_scores_gemma":[0.0051568514,0.000106804364,0.000017757215,0.00023815477,0.00011284688,0.000110975765,0.00068984,0.00023134302,9.01996e-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":[0.000042461535,0.00036569228,0.020463161,0.00027834257,0.00018730258,0.0000777918,0.0010385158,0.010221103,0.020721676,0.65398407,0.0028836364,0.28973624],"study_design_scores_gemma":[0.00012194761,0.000021177682,0.0024785388,0.000014371837,0.000009153549,0.000015270374,0.0000020577943,0.9685342,0.00079293526,0.02763526,0.0002445883,0.00013050591],"about_ca_topic_score_codex":0.00012455205,"about_ca_topic_score_gemma":0.000046583293,"teacher_disagreement_score":0.9583131,"about_ca_system_score_codex":0.000005324181,"about_ca_system_score_gemma":0.00014788783,"threshold_uncertainty_score":0.61736053},"labels":[],"label_agreement":null},{"id":"W2064296938","doi":"10.1162/coli_a_00064","title":"A Strategy for Information Presentation in Spoken Dialog Systems","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":35,"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":"Ames Research Center; Atomic Energy of Canada Limited; National Aeronautics and Space Administration","keywords":"Dialog box; Computer science; Structuring; Dialog system; Process (computing); Presentation (obstetrics); User satisfaction; Human–computer interaction; Information retrieval; World Wide Web","score_opus":0.06398151558250546,"score_gpt":0.27997948751890905,"score_spread":0.21599797193640358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064296938","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":[0.0011247458,0.000050512648,0.97318643,0.000010600625,0.0021439672,0.0005327339,0.00003439791,0.00009326602,0.02282336],"genre_scores_gemma":[0.9394033,0.0000010331872,0.059969757,0.000051088045,0.00032277787,0.000060504564,0.00016281051,0.000004809206,0.00002390945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902266,0.00003934935,0.00040007767,0.00014794366,0.00021202589,0.00017793993],"domain_scores_gemma":[0.99887204,0.00022059302,0.00015054796,0.00014483613,0.0005504499,0.00006154423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027873018,0.00009396108,0.00012509756,0.00018893986,0.00005717458,0.00014137107,0.00029338387,0.000059115766,0.0000015160874],"category_scores_gemma":[0.00077219645,0.000097533855,0.000033481814,0.00022114319,0.000018932225,0.00023494325,0.000040164352,0.000054862645,0.00004679652],"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":[0.000026268503,0.000046682973,0.0017083185,0.00007107492,0.000008677048,0.000004364913,0.0011721337,0.072429076,0.0000013403186,0.92167896,0.00088099076,0.0019721047],"study_design_scores_gemma":[0.00084590365,0.00013420908,0.02127647,0.000033184726,0.000004944307,0.0000065355957,0.00008094942,0.8362836,0.000028637238,0.13683532,0.0042740623,0.00019618365],"about_ca_topic_score_codex":0.00021364758,"about_ca_topic_score_gemma":0.000012278115,"teacher_disagreement_score":0.93827856,"about_ca_system_score_codex":0.000049980306,"about_ca_system_score_gemma":0.0001588159,"threshold_uncertainty_score":0.3977315},"labels":[],"label_agreement":null},{"id":"W2068580719","doi":"10.1162/coli_r_00056","title":"<b>Cross-Language Information Retrieval Jian-Yun Nie</b> (University of Montreal) San Rafael, CA: Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 8), 2010, xv+125 pp; paperbound, ISBN 978-1-59829-863-5, $40.00; ebook, ISBN 978-1-59829-864-3, $30.00 or by subscription","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Jian; Humanities; Computer science; Art; Literature; Physics","score_opus":0.024129246993715218,"score_gpt":0.2563956028276577,"score_spread":0.2322663558339425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068580719","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":[0.44308364,0.0013885933,0.52868515,0.00075532205,0.0040172753,0.0029559743,0.005458942,0.0031513372,0.010503771],"genre_scores_gemma":[0.97037846,0.00011377922,0.021754913,0.00039330378,0.0003262803,0.000014142443,0.0029211512,0.000058637823,0.004039361],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99598944,0.00017280373,0.001060856,0.0006101836,0.0014286452,0.00073806616],"domain_scores_gemma":[0.9960578,0.00036950965,0.0008507374,0.00088389585,0.001571885,0.0002661584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068029447,0.00056909974,0.00060129137,0.0005492909,0.00094787136,0.00040504616,0.0016417973,0.0005377651,0.0008114989],"category_scores_gemma":[0.0019329167,0.0005642014,0.00021869357,0.00097020314,0.00055229757,0.00080919417,0.00044195994,0.00074179017,0.00049178797],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003620769,0.0028956663,0.008836778,0.0012460393,0.0007403328,0.00042316504,0.050289985,0.0054502385,0.014130359,0.029306868,0.8182618,0.064797975],"study_design_scores_gemma":[0.0134583805,0.004703696,0.08377897,0.0009191293,0.0007076523,0.0002193045,0.010587571,0.22825496,0.042120412,0.009643356,0.5981247,0.007481906],"about_ca_topic_score_codex":0.0019465329,"about_ca_topic_score_gemma":0.00018631987,"teacher_disagreement_score":0.5272948,"about_ca_system_score_codex":0.00041294593,"about_ca_system_score_gemma":0.00038606097,"threshold_uncertainty_score":0.99968094},"labels":[],"label_agreement":null},{"id":"W2077818552","doi":"10.1162/coli.2010.36.1.36104","title":"Automatically Identifying the Source Words of Lexical Blends in English","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"University of Toronto","keywords":"Computer science; Natural language processing; Lexicon; Artificial intelligence; Task (project management); Set (abstract data type); Identification (biology); Word (group theory); Source text; Linguistics; Programming language","score_opus":0.013274499254340271,"score_gpt":0.29620196724369235,"score_spread":0.2829274679893521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077818552","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":[0.0061699734,0.00014056513,0.9907466,0.00022026956,0.0009849074,0.000083699386,0.0000021648966,0.00032059394,0.0013312034],"genre_scores_gemma":[0.5501709,3.935722e-7,0.44949907,0.000083502455,0.00021056151,0.0000027060437,0.0000027007065,0.000004697523,0.000025453213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889183,0.00004107706,0.0003363555,0.00019497605,0.0003742205,0.00016151615],"domain_scores_gemma":[0.9982745,0.0007060957,0.00012397062,0.00026848126,0.00058484974,0.000042072163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048711413,0.000096494965,0.00013047193,0.00011212878,0.000077903554,0.00012502182,0.0009260712,0.000075042575,0.000006998923],"category_scores_gemma":[0.0053117764,0.00007530644,0.000041883257,0.0003932303,0.00013070658,0.0000561041,0.00027449237,0.00044914903,0.000003536475],"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":[0.0000027204712,0.000048376245,0.0005829973,0.000039590857,0.000005846637,0.000010264576,0.0019874691,0.0017998108,0.00015145187,0.9835658,0.00030294168,0.011502695],"study_design_scores_gemma":[0.00012607529,0.000018692012,0.0010187031,0.00006443867,0.0000044702706,0.0000072917474,0.000025845571,0.46411783,0.0008696741,0.531557,0.002062414,0.00012753757],"about_ca_topic_score_codex":0.000009337953,"about_ca_topic_score_gemma":0.000011745835,"teacher_disagreement_score":0.5440009,"about_ca_system_score_codex":0.000016629352,"about_ca_system_score_gemma":0.00016211586,"threshold_uncertainty_score":0.6359076},"labels":[],"label_agreement":null},{"id":"W2084046180","doi":"10.1162/coli_a_00049","title":"Lexicon-Based Methods for Sentiment Analysis","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3255,"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; University of Toronto; Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentiment analysis; Lexicon; Polarity (international relations); Natural language processing; Artificial intelligence; Negation; Consistency (knowledge bases); Orientation (vector space); Word (group theory); Process (computing); Reliability (semiconductor); Linguistics; Mathematics","score_opus":0.08804081832030412,"score_gpt":0.3846883079456333,"score_spread":0.29664748962532916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084046180","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":[0.00010822057,0.00006017566,0.9967714,0.000059382433,0.00060821575,0.000105290805,0.0000064106416,0.00008410008,0.0021967907],"genre_scores_gemma":[0.19232975,3.7819717e-7,0.8070714,0.0002817824,0.00013604747,0.000012555074,0.000067662324,0.000006427489,0.000093982926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882525,0.00007441887,0.0003494935,0.00035621057,0.00020244339,0.0001922109],"domain_scores_gemma":[0.998261,0.0005680443,0.0001736824,0.00028147796,0.0006269315,0.00008890196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005435326,0.0001281036,0.00023342962,0.00034972135,0.00015577569,0.00009657346,0.00043099193,0.0000398345,0.000070391914],"category_scores_gemma":[0.00041825033,0.0001282136,0.00029822486,0.0007635624,0.000031650296,0.000030384537,0.00007314403,0.000049996914,0.000018403667],"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":[0.000011707258,0.00020349963,0.0050201127,0.000015320855,0.00094544195,0.0000031273885,0.00053940556,0.09896165,0.000012141566,0.88180053,0.0007191829,0.011767848],"study_design_scores_gemma":[0.00023722954,0.00003840878,0.002166461,0.00000414228,0.0002717913,1.809339e-7,0.000009582795,0.9514331,0.00059749006,0.04001638,0.0050705527,0.00015463578],"about_ca_topic_score_codex":0.000007259322,"about_ca_topic_score_gemma":8.525061e-7,"teacher_disagreement_score":0.8524715,"about_ca_system_score_codex":0.000030171388,"about_ca_system_score_gemma":0.00011290489,"threshold_uncertainty_score":0.52283996},"labels":[],"label_agreement":null},{"id":"W2092527610","doi":"10.1162/089120102760173625","title":"Near-Synonymy and Lexical Choice","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":258,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Denotation (semiotics); Artificial intelligence; Context (archaeology); Lexicon; Lexical choice; Set (abstract data type); Selection (genetic algorithm); Lexical semantics; Ontology; Lexical item; Linguistics","score_opus":0.02487434097093336,"score_gpt":0.28440130432046784,"score_spread":0.25952696334953446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092527610","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":[0.0014085524,0.0021717383,0.9914245,0.0006884438,0.00036266787,0.00007377549,0.000005211758,0.00054501765,0.0033200777],"genre_scores_gemma":[0.45911565,0.0000033489416,0.54022187,0.00038359076,0.00018407972,0.0000016116709,0.000002719659,0.0000045602123,0.00008254185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992155,0.000021225913,0.00014914347,0.00024219956,0.00022519956,0.00014677068],"domain_scores_gemma":[0.99913454,0.000311794,0.00005344331,0.0001504496,0.0002694555,0.00008033056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008147283,0.00009711654,0.00009454362,0.000043436357,0.0001660164,0.00025435517,0.000346433,0.000052840056,0.000015658821],"category_scores_gemma":[0.0013884144,0.00009360576,0.00002055543,0.00017558782,0.00007182589,0.000061008686,0.00018164759,0.00015259201,0.00003188372],"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":[0.0000012606065,0.000062586536,0.0008228436,0.000032288768,0.000010103673,0.000044652705,0.00031370413,0.0011151445,0.000010307188,0.9567891,0.0061958153,0.034602236],"study_design_scores_gemma":[0.000113928305,0.000030952277,0.00048427572,0.000018720537,0.0000035800053,0.000024363417,8.26975e-7,0.76463854,0.000041973482,0.20303199,0.031468023,0.00014281238],"about_ca_topic_score_codex":0.0000041179555,"about_ca_topic_score_gemma":7.8447704e-7,"teacher_disagreement_score":0.7635234,"about_ca_system_score_codex":0.00001978699,"about_ca_system_score_gemma":0.000022905346,"threshold_uncertainty_score":0.3817132},"labels":[],"label_agreement":null},{"id":"W2104710058","doi":"10.1162/coli_r_00188","title":"<b>Semi-Supervised Learning and Domain Adaptation in Natural Language Processing</b> <b>Anders Søgaard</b> University of Copenhagen Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 21), 2013, x+93 pp; paperbound, ISBN 978-1-60845-985-8, $40.00; e-book, ISBN 978-1-60845-986-5, $30.00 or by subscription","year":2014,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Domain Adaptation and Few-Shot 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":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Machine learning; Parsing; Test set; Test data; Supervised learning; sort; Adaptation (eye); Information retrieval; Artificial neural network; Psychology","score_opus":0.014480307356805262,"score_gpt":0.24449198145169979,"score_spread":0.23001167409489454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104710058","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":[0.10595938,0.011395054,0.8742487,0.0015646898,0.0008945236,0.0011943761,0.00013741656,0.0014980324,0.003107854],"genre_scores_gemma":[0.95901734,0.00011660503,0.036955804,0.0003107226,0.00016568671,0.000010189863,0.00060962245,0.000057435864,0.0027566215],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967514,0.00043968597,0.0006243933,0.00086491305,0.0007902713,0.0005293197],"domain_scores_gemma":[0.99776155,0.0006982699,0.00054654886,0.00035648808,0.00048594267,0.00015121278],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007011403,0.0004668038,0.00053757074,0.00037431406,0.0007155887,0.0003159328,0.0007424465,0.00031407113,0.0002631491],"category_scores_gemma":[0.0020755534,0.00048550672,0.00009619858,0.00074632716,0.00035317428,0.00027719996,0.00022289257,0.00077779015,0.00009295813],"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":[0.002432618,0.0024146035,0.006261586,0.0018531886,0.00066236977,0.00048031512,0.08609911,0.1861687,0.05948982,0.020179596,0.43298757,0.20097052],"study_design_scores_gemma":[0.0029507396,0.0003958239,0.002858226,0.00034271015,0.000067478,0.00001883185,0.0062726554,0.6628407,0.00055334694,0.0009270851,0.32164165,0.001130731],"about_ca_topic_score_codex":0.00044645765,"about_ca_topic_score_gemma":0.00025023214,"teacher_disagreement_score":0.8530579,"about_ca_system_score_codex":0.00025345123,"about_ca_system_score_gemma":0.00020312124,"threshold_uncertainty_score":0.9997597},"labels":[],"label_agreement":null},{"id":"W2105897558","doi":"10.1162/coli.2009.35.4.35402","title":"From Annotator Agreement to Noise Models","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Rough Sets and Fuzzy Logic","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":"Kellogg's (Canada)","funders":"","keywords":"Benchmarking; Computer science; Noise (video); Agreement; Data set; Quality (philosophy); Set (abstract data type); Resource (disambiguation); Data quality; Data mining; Data science; Econometrics; Artificial intelligence; Mathematics; Linguistics; Physics","score_opus":0.028591093906635952,"score_gpt":0.27382490992191555,"score_spread":0.2452338160152796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105897558","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":[0.0014962188,0.00006396708,0.98094094,0.0012011587,0.0008395578,0.00011503688,0.00003174173,0.00010806782,0.015203284],"genre_scores_gemma":[0.5452018,0.0000010042454,0.451488,0.0026751694,0.00057417306,0.0000018051816,0.000027822456,0.0000028492068,0.000027396849],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998859,0.000019664692,0.0002326232,0.0003303178,0.0003601741,0.00019820737],"domain_scores_gemma":[0.9990359,0.00011484787,0.0000549163,0.0002769359,0.00035394303,0.00016347798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008613839,0.00012281493,0.00012837653,0.000067922774,0.00010542614,0.0001519835,0.0005380135,0.000034827357,0.000009374538],"category_scores_gemma":[0.00020920683,0.000118341646,0.00004273839,0.00021098196,0.00001240429,0.000048686423,0.00010775204,0.00007384265,0.00018689591],"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":[0.000004885535,0.00008206347,0.000020952046,0.0000012880204,0.000007538333,0.000025565796,0.0005491913,0.53701377,0.0000058435594,0.43704364,0.00817441,0.017070865],"study_design_scores_gemma":[0.00010741697,0.000065186985,0.0016412564,0.0000058186474,0.000002594358,6.4814253e-7,0.0000037608966,0.5630154,0.0000065144886,0.42704323,0.0079998365,0.000108369306],"about_ca_topic_score_codex":0.000016229234,"about_ca_topic_score_gemma":6.4544076e-7,"teacher_disagreement_score":0.5437056,"about_ca_system_score_codex":0.000042583066,"about_ca_system_score_gemma":0.00007465041,"threshold_uncertainty_score":0.48258322},"labels":[],"label_agreement":null},{"id":"W2109830295","doi":"10.1162/coli.2006.32.3.379","title":"Similarity of Semantic Relations","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"University of Waterloo; Johns Hopkins University","keywords":"Analogy; Word (group theory); Similarity (geometry); Vector space model; Semantic similarity; Relation (database); Vector space; Latent semantic analysis","score_opus":0.01936146345015635,"score_gpt":0.25841519200576835,"score_spread":0.239053728555612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109830295","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":[0.004410035,0.000049270708,0.98208785,0.00015920817,0.000427519,0.00004784648,0.00000536725,0.00007395278,0.012738956],"genre_scores_gemma":[0.6442087,1.9651642e-7,0.35547727,0.000035678666,0.0001697142,6.9554096e-7,0.000011284679,0.0000027170859,0.00009369986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921995,0.000020185267,0.00027267207,0.00015927982,0.00022996386,0.000097918695],"domain_scores_gemma":[0.9989856,0.0002443583,0.00009540632,0.00019493191,0.0004549367,0.000024753399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011709679,0.00006170789,0.00009166336,0.00006771857,0.00007290688,0.00002767917,0.000259325,0.000034133005,0.0000062512227],"category_scores_gemma":[0.00045566406,0.00006803928,0.00003694312,0.00017124927,0.000031574888,0.00002872937,0.00008314009,0.00007258612,0.000018164272],"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":[2.720753e-7,0.000024114323,0.002143857,0.0000060582815,0.0000023390508,0.0000020061686,0.000024121897,0.3621563,0.0000040900013,0.63505185,0.00038593062,0.00019904457],"study_design_scores_gemma":[0.000072708106,0.0000060500124,0.008318843,0.000007417024,0.0000034312764,0.0000014851829,0.0000010467642,0.6573916,0.00002503819,0.33256227,0.0015601652,0.00004994178],"about_ca_topic_score_codex":0.000037610673,"about_ca_topic_score_gemma":0.0000042920055,"teacher_disagreement_score":0.6397987,"about_ca_system_score_codex":0.000021341126,"about_ca_system_score_gemma":0.000094305025,"threshold_uncertainty_score":0.2774561},"labels":[],"label_agreement":null},{"id":"W2111856253","doi":"10.1162/coli.2007.33.1.9","title":"Word-Level Confidence Estimation for Machine Translation","year":2007,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"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":"National Research Council Canada; RWTH Aachen University; European Commission","keywords":"Computer science; Word (group theory); Phrase; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Example-based machine translation; Linguistics","score_opus":0.04620772119004527,"score_gpt":0.3427001006526349,"score_spread":0.2964923794625896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111856253","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":[0.000044040342,0.0007700111,0.9974925,0.00020641042,0.00047453784,0.00022461236,0.000021861033,0.0003890236,0.00037701157],"genre_scores_gemma":[0.42072758,6.866873e-7,0.5788585,0.00017208167,0.00013916606,0.0000045048832,0.00006659253,0.000006407751,0.00002448112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896574,0.00001337215,0.00030227288,0.00024802182,0.00028339887,0.00018717123],"domain_scores_gemma":[0.9980484,0.00087184284,0.00013316603,0.00015536895,0.0007313395,0.000059877417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005494632,0.00011538095,0.000107570544,0.00013203011,0.00015239586,0.000114330134,0.00039296615,0.00006669373,0.000002449378],"category_scores_gemma":[0.0016174739,0.00011825379,0.00004288153,0.00024692548,0.000036725043,0.00010004704,0.000038546317,0.00010792871,0.0000061904334],"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":[0.000015667534,0.00002816488,0.00003019,0.000039866467,0.0000064567994,0.0000055453265,0.0002244146,0.0078050797,0.00005665724,0.7838953,0.00025868148,0.20763399],"study_design_scores_gemma":[0.0001464974,0.000022864415,0.00018207736,0.000022252561,0.0000045775464,0.000005333006,0.0000014902497,0.5880851,0.0007840906,0.4094072,0.0012353478,0.00010316288],"about_ca_topic_score_codex":0.00000794121,"about_ca_topic_score_gemma":0.000006598346,"teacher_disagreement_score":0.58028007,"about_ca_system_score_codex":0.000049101694,"about_ca_system_score_gemma":0.00008798507,"threshold_uncertainty_score":0.48222494},"labels":[],"label_agreement":null},{"id":"W2119168550","doi":"10.1162/0891201042544884","title":"The Alignment Template Approach to Statistical Machine Translation","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":933,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; NIST; Machine translation; Evaluation of machine translation; Natural language processing; Example-based machine translation; Artificial intelligence; Phrase; Machine translation software usability; Generalization; Transfer-based machine translation; Translation (biology); Task (project management); Context (archaeology); Feature (linguistics); Rule-based machine translation; Word (group theory); Linguistics","score_opus":0.021864809993940373,"score_gpt":0.2953628508639949,"score_spread":0.2734980408700545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119168550","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":[0.000019640429,0.00060755777,0.99571985,0.00079197733,0.00030404935,0.00019338283,0.000019044055,0.00026654967,0.0020779644],"genre_scores_gemma":[0.35593185,0.0000017970026,0.64357793,0.0003137761,0.00010923787,0.000010790874,0.000033351702,0.0000067647757,0.000014507814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988167,0.00003302265,0.00024939034,0.00027025014,0.0004276061,0.0002029738],"domain_scores_gemma":[0.99904007,0.00031852134,0.000060427355,0.000215184,0.00026764112,0.00009815669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027608927,0.00012093286,0.00009473804,0.00005579262,0.0003183471,0.00023805726,0.0005850637,0.000039256065,8.468202e-7],"category_scores_gemma":[0.0005605682,0.00009054558,0.000026858981,0.00024132649,0.000049559825,0.000037828428,0.000103005754,0.00014131317,0.00002181112],"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":[0.000005691914,0.000043155575,0.0000057608872,0.000008354309,0.000007212757,0.000005883958,0.00024106236,0.040184304,0.000009316496,0.94189477,0.00035662868,0.017237874],"study_design_scores_gemma":[0.00021698713,0.000054423093,0.00012341027,0.000016096166,0.000006033273,0.000014704989,0.0000048507463,0.23678179,0.00016396285,0.75142896,0.011024588,0.00016421295],"about_ca_topic_score_codex":0.00001634068,"about_ca_topic_score_gemma":0.0000023047348,"teacher_disagreement_score":0.3559122,"about_ca_system_score_codex":0.00008865212,"about_ca_system_score_gemma":0.000111072295,"threshold_uncertainty_score":0.36923417},"labels":[],"label_agreement":null},{"id":"W2123215530","doi":"10.1162/coli.08-010-r1-07-048","title":"Unsupervised Type and Token Identification of Idiomatic Expressions","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Atomic Energy of Canada Limited; University of Toronto","keywords":"Linguistics; Identification (biology); Interpretation (philosophy); Computer science; Natural language processing; Literal (mathematical logic); Task (project management); Context (archaeology); Security token; Artificial intelligence; Semantic property; Expression (computer science); Psychology; History","score_opus":0.015640231814246133,"score_gpt":0.29692181395150163,"score_spread":0.2812815821372555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123215530","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":[0.0075691543,0.0010986115,0.99020433,0.0002482025,0.0002105895,0.00009606723,0.0000040308614,0.00020553765,0.00036344465],"genre_scores_gemma":[0.6096856,0.0000037484042,0.3901688,0.00007969642,0.0000393273,6.4430117e-7,0.0000088132365,0.0000020450113,0.000011321666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99930835,0.000023359802,0.000249956,0.00015174969,0.00018973605,0.00007682151],"domain_scores_gemma":[0.99887973,0.00010756938,0.00012026217,0.00016967922,0.0006842895,0.000038479073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013080238,0.00006790786,0.000095641495,0.000086310385,0.00006676902,0.000061017487,0.00029431112,0.000036054746,0.0000012465916],"category_scores_gemma":[0.0013796501,0.00006378917,0.000013923289,0.0002907392,0.00002588565,0.000060211925,0.00006178629,0.00005905602,0.0000027550198],"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":[0.000006065298,0.000081363476,0.0001398941,0.000060887916,0.000008423167,0.0000069351204,0.000667673,0.0013028141,0.010139053,0.96915257,0.0005407694,0.017893538],"study_design_scores_gemma":[0.000119594006,0.00006118437,0.0033326256,0.000070097485,0.000008154714,0.000006895634,0.000008525846,0.22763838,0.0068270145,0.7616497,0.00016048805,0.000117324045],"about_ca_topic_score_codex":0.0000013578589,"about_ca_topic_score_gemma":6.6840386e-8,"teacher_disagreement_score":0.60211647,"about_ca_system_score_codex":0.000011772217,"about_ca_system_score_gemma":0.000058570982,"threshold_uncertainty_score":0.26012468},"labels":[],"label_agreement":null},{"id":"W2129909699","doi":"10.1162/coli_a_00085","title":"Learning Entailment Relations by Global Graph Structure Optimization","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"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":"University of Haifa; Azrieli Foundation; Israel Science Foundation","keywords":"Logical consequence; Computer science; Textual entailment; Inference; Graph; Transitive relation; Artificial intelligence; Constraint (computer-aided design); Theoretical computer science; Natural language processing; Mathematics; Combinatorics","score_opus":0.010916148327742984,"score_gpt":0.2556109568737796,"score_spread":0.24469480854603662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129909699","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":[0.00016913268,0.00034779072,0.9964669,0.00004963134,0.0003751002,0.00008812803,0.000024485487,0.00050231925,0.001976538],"genre_scores_gemma":[0.41126856,0.0000016837646,0.58840376,0.00009671122,0.000053890923,0.0000020494863,0.00012857067,0.000005054576,0.000039702725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902827,0.000045044595,0.00021909038,0.0002671885,0.00028244668,0.00015795256],"domain_scores_gemma":[0.99910027,0.000058707265,0.0001426376,0.00014473204,0.00048518463,0.00006845385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008022197,0.00012624153,0.00009294367,0.000060845166,0.00021697162,0.000102028825,0.0004229275,0.00007770752,0.000035404966],"category_scores_gemma":[0.0005576499,0.00012843429,0.000034264496,0.00037553904,0.00004330838,0.00009876205,0.00013636521,0.00018344067,0.000011264132],"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":[0.0000056110566,0.00006401337,0.0029638412,0.000012394203,0.000023746723,0.000011811679,0.0005306072,0.26322758,0.000015261583,0.7263942,0.0035585926,0.0031923372],"study_design_scores_gemma":[0.00014243947,0.00006594973,0.0002837994,0.00001981221,0.0000115033345,0.000010289603,0.000011871782,0.51540214,0.00022751064,0.4824274,0.0011904617,0.00020681943],"about_ca_topic_score_codex":0.000013276292,"about_ca_topic_score_gemma":9.622009e-7,"teacher_disagreement_score":0.41109943,"about_ca_system_score_codex":0.00009295539,"about_ca_system_score_gemma":0.000077465666,"threshold_uncertainty_score":0.5237399},"labels":[],"label_agreement":null},{"id":"W2131526828","doi":"10.1162/coli.2006.32.2.223","title":"Building and Using a Lexical Knowledge Base of Near-Synonym Differences","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":82,"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; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Ottawa; University of Pennsylvania","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Knowledge base; Artificial intelligence; Mistake; Natural language; Bilingual dictionary; Word (group theory); Linguistics","score_opus":0.026568550280453792,"score_gpt":0.3117453974176719,"score_spread":0.2851768471372181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131526828","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":[0.044403393,0.0015452587,0.9533795,0.000034940233,0.000185562,0.000051359973,0.00000537647,0.00013287175,0.0002617146],"genre_scores_gemma":[0.49956164,4.4829284e-7,0.5002994,0.000017148452,0.00010897204,5.894105e-7,0.0000018604427,0.000003449056,0.0000065172935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916697,0.000040054387,0.00023836437,0.00022152097,0.00018630248,0.00014677896],"domain_scores_gemma":[0.99892664,0.0003831478,0.000113243565,0.00011367553,0.0004181362,0.00004516936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001873533,0.00010516546,0.0001506744,0.00007838413,0.0001284155,0.00012651947,0.00023759996,0.000051878316,0.0000020149087],"category_scores_gemma":[0.0006222121,0.00009798116,0.000028364857,0.0002225359,0.00013885956,0.00004859341,0.00020327735,0.000103915365,7.4156765e-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":[0.0000028940538,0.00006380349,0.0018149754,0.00006159167,0.000005387628,0.000014861603,0.000099963065,0.0026918722,0.0004753615,0.99009746,0.00007070715,0.0046011456],"study_design_scores_gemma":[0.00007910151,0.000019416388,0.0013577478,0.000058868514,0.000005908827,0.000012743831,0.0000012914925,0.67322135,0.00071404874,0.32427478,0.00015823868,0.00009650443],"about_ca_topic_score_codex":0.000054555992,"about_ca_topic_score_gemma":0.00000353382,"teacher_disagreement_score":0.6705295,"about_ca_system_score_codex":0.000026825724,"about_ca_system_score_gemma":0.00014219129,"threshold_uncertainty_score":0.39955556},"labels":[],"label_agreement":null},{"id":"W2136930489","doi":"10.1162/coli.2006.32.1.13","title":"Evaluating WordNet-based Measures of Lexical Semantic Relatedness","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1414,"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":"University of Toronto; University of Pennsylvania","keywords":"WordNet; Computer science; Semantic similarity; Natural language processing; Spelling; Artificial intelligence; Lexical database; Proxy (statistics); Similarity (geometry); Information retrieval; Measure (data warehouse); Linguistics; Machine learning; Data mining","score_opus":0.058731127994592104,"score_gpt":0.34696039051580496,"score_spread":0.28822926252121284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136930489","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":[0.0030447457,0.0008110262,0.9944451,0.00011296384,0.00035865197,0.0000950504,0.0000040880964,0.00034511392,0.0007832989],"genre_scores_gemma":[0.51450604,1.7045811e-7,0.48527557,0.000056590125,0.000117520605,0.0000021639644,0.000016162536,0.0000062246963,0.000019561006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984685,0.00007507822,0.0003981639,0.00026617263,0.00061910605,0.00017294177],"domain_scores_gemma":[0.9979158,0.00045668762,0.00021144756,0.00022747545,0.0011499558,0.000038649003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043997966,0.00012790659,0.00017310695,0.00013793199,0.00010459322,0.00007501498,0.0005196149,0.00007948533,0.0000037180064],"category_scores_gemma":[0.0019398849,0.00012308492,0.00005784373,0.00040183112,0.000084574,0.000039542658,0.00009851288,0.00017193849,0.0000060087973],"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":[0.000012956651,0.00013736363,0.0007909734,0.000094304865,0.000012168387,0.000027280596,0.000069823094,0.19708847,0.00048116452,0.7902249,0.0006374067,0.010423169],"study_design_scores_gemma":[0.00017167667,0.00004543959,0.00043513405,0.000082901584,0.000010118214,0.000003556346,0.000001052018,0.6532295,0.002272144,0.34343287,0.00019330904,0.000122343],"about_ca_topic_score_codex":0.000039836294,"about_ca_topic_score_gemma":0.0000023483974,"teacher_disagreement_score":0.51146126,"about_ca_system_score_codex":0.00004478522,"about_ca_system_score_gemma":0.00025212462,"threshold_uncertainty_score":0.5019257},"labels":[],"label_agreement":null},{"id":"W2137006453","doi":"10.1162/coli_a_00206","title":"Towards Topic-to-Question Generation","year":2015,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":82,"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 Lethbridge","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Predicate (mathematical logic); Natural language processing; Correctness; Artificial intelligence; Topic model; Similarity (geometry); Subsequence; Context (archaeology); String (physics); Information retrieval; Algorithm; Mathematics; Programming language","score_opus":0.08126377489865644,"score_gpt":0.32306504233377414,"score_spread":0.2418012674351177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137006453","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":[0.00301433,0.00003248185,0.9867741,0.00077622815,0.0024751902,0.00008590688,0.0000020153973,0.00014540025,0.0066943523],"genre_scores_gemma":[0.48864713,2.9032293e-7,0.50943816,0.0005696138,0.0012204405,0.0000038676285,0.000016716005,0.0000038417606,0.00009996509],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902713,0.000039086382,0.00019972725,0.00024626544,0.00035781556,0.00012994617],"domain_scores_gemma":[0.9986648,0.000037078164,0.000043990396,0.00021100775,0.00087989157,0.00016325607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027131665,0.00008291971,0.00008223266,0.000079871366,0.000063864914,0.00012526497,0.0003046051,0.000039202812,0.0000024414417],"category_scores_gemma":[0.0015907681,0.00008868984,0.000021292497,0.00016854978,0.000009745845,0.00005161215,0.0001283754,0.000067176006,0.000100733785],"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":[8.7121555e-7,0.000013014511,0.00009540563,0.0000021604253,0.0000024934436,0.0000044570975,0.00026066208,0.36957103,0.000006966484,0.61654747,0.0019436638,0.011551805],"study_design_scores_gemma":[0.00012733438,0.00003674771,0.0003845765,0.000005826154,0.0000022587462,0.0000041022267,0.0000038735375,0.8794093,0.00006790484,0.09683399,0.023021525,0.00010252144],"about_ca_topic_score_codex":0.000017415769,"about_ca_topic_score_gemma":0.000002636399,"teacher_disagreement_score":0.51971346,"about_ca_system_score_codex":0.000093411545,"about_ca_system_score_gemma":0.00023013409,"threshold_uncertainty_score":0.36166668},"labels":[],"label_agreement":null},{"id":"W2144719390","doi":"10.1162/coli_a_00077","title":"Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"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":"Atomic Energy of Canada Limited","keywords":"Automatic summarization; Computer science; Salience (neuroscience); Affect (linguistics); Context (archaeology); Information retrieval; Natural language processing; Artificial intelligence; Linguistics; History","score_opus":0.09209636236490953,"score_gpt":0.33507287718669815,"score_spread":0.24297651482178861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144719390","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":[0.61649466,0.000009350111,0.382322,0.00001620665,0.00021013315,0.00013698183,0.0000068027216,0.00003527289,0.00076860044],"genre_scores_gemma":[0.840021,0.0000014228212,0.15985748,0.000055400305,0.00003578394,0.00001092892,0.000013171815,0.000002421583,0.0000023680325],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990447,0.00005901064,0.00038541108,0.00015794502,0.00022063656,0.00013227377],"domain_scores_gemma":[0.9991326,0.0001649712,0.00009478484,0.00019464364,0.00031387838,0.00009915228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014130997,0.00008126213,0.00012926372,0.00018951112,0.00009654233,0.000062297266,0.00021542625,0.000029682638,0.0000035851947],"category_scores_gemma":[0.0010844853,0.00007873586,0.000008958368,0.0002536046,0.0000177103,0.00021636982,0.00021371403,0.00008921577,0.000002246755],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003725066,0.0005678919,0.70058197,0.000035364606,0.000011746064,0.0000031543736,0.12066244,0.08985949,0.000002712751,0.07577664,0.00007601114,0.0123853395],"study_design_scores_gemma":[0.00032946916,0.00028890057,0.69362104,0.000031587813,0.000005397898,0.0000011656123,0.0042691305,0.28167975,0.000004352401,0.018977026,0.00065567443,0.00013650289],"about_ca_topic_score_codex":0.00079578505,"about_ca_topic_score_gemma":0.00093201647,"teacher_disagreement_score":0.22352637,"about_ca_system_score_codex":0.000025838921,"about_ca_system_score_gemma":0.00009072454,"threshold_uncertainty_score":0.32107553},"labels":[],"label_agreement":null},{"id":"W2151552691","doi":"10.1162/089120102762671963","title":"Generating Indicative-Informative Summaries with SumUM","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":140,"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; Université du Québec à Montréal","funders":"Université de Montréal; McGill University","keywords":"Automatic summarization; Computer science; Identification (biology); Information retrieval; Natural language processing; Process (computing); Artificial intelligence","score_opus":0.02829016747849478,"score_gpt":0.24873866525715468,"score_spread":0.2204484977786599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151552691","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":[0.0028503758,0.000092627946,0.98373955,0.000210948,0.0003023953,0.0000890099,0.000008083615,0.00015337828,0.012553653],"genre_scores_gemma":[0.5201121,0.0000018199441,0.47919303,0.00033609924,0.00022970534,0.0000047831772,0.0000134760385,0.0000054463985,0.00010353475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998931,0.000029622657,0.00025625151,0.00022612004,0.00035883294,0.0001982077],"domain_scores_gemma":[0.998735,0.00026561605,0.00020416323,0.00021670833,0.00050202344,0.00007647874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113513226,0.0001274499,0.00012391173,0.0000877924,0.00025347804,0.00018864575,0.00040752906,0.000036025373,0.00001933667],"category_scores_gemma":[0.00065453304,0.0001132733,0.000023882241,0.0002267813,0.000072536895,0.000119913246,0.0001336591,0.00014621518,0.00006835842],"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":[0.0000017467352,0.000033792036,0.0012517497,0.000015290081,0.000025500964,0.000016220822,0.0033044457,0.44409132,0.000001146957,0.54290354,0.000948429,0.0074068015],"study_design_scores_gemma":[0.00019875815,0.000040749226,0.00043013316,0.0000193807,0.000004171493,0.000008989932,0.00003656173,0.98406065,0.00002149255,0.009939238,0.005083399,0.00015647332],"about_ca_topic_score_codex":0.0000052544333,"about_ca_topic_score_gemma":0.0000024278097,"teacher_disagreement_score":0.5399693,"about_ca_system_score_codex":0.000043680127,"about_ca_system_score_gemma":0.00006430297,"threshold_uncertainty_score":0.46191514},"labels":[],"label_agreement":null},{"id":"W2154889602","doi":"10.1162/coli.2010.36.1.36101","title":"A Graph-Theoretic Framework for Semantic Distance","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Semantic similarity; Natural language processing; Artificial intelligence; Coherence (philosophical gambling strategy); Information retrieval; Set (abstract data type); Semantic computing; Semantic Web; Mathematics","score_opus":0.012063363554660086,"score_gpt":0.3012501952456227,"score_spread":0.2891868316909626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154889602","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":[0.03195066,0.00020294578,0.9654597,0.00016169314,0.0014419374,0.00010589563,0.00006028356,0.00003208904,0.0005847709],"genre_scores_gemma":[0.70062304,0.000006194758,0.29795185,0.00021466495,0.00095797016,0.000012746527,0.00015062062,0.000011304038,0.000071638715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993603,0.0000115229395,0.00014744076,0.00021727267,0.000102487116,0.00016095783],"domain_scores_gemma":[0.9992435,0.00021743595,0.000057113808,0.00015616918,0.00025961205,0.0000661581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012188698,0.00009680245,0.000094905015,0.000023483044,0.00010057862,0.000021607924,0.00015186486,0.00016259066,0.000009463297],"category_scores_gemma":[0.0060099913,0.00009080475,0.0000670043,0.000057063055,0.00024390678,2.4716508e-7,0.00003684827,0.000134147,0.00000621624],"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":[0.000077827004,0.00009179907,0.0016265769,0.000074072195,0.00004722706,0.0000036836573,0.000053837968,0.00072520255,0.0015755489,0.9848264,0.005076896,0.005820945],"study_design_scores_gemma":[0.0003208071,0.00017701839,0.0013471001,0.000023802366,0.000023622728,0.0000074126056,0.00001858147,0.0059264735,0.0009776072,0.7469691,0.24399488,0.0002135745],"about_ca_topic_score_codex":7.3968494e-7,"about_ca_topic_score_gemma":0.0000039935867,"teacher_disagreement_score":0.6686724,"about_ca_system_score_codex":0.0000026290109,"about_ca_system_score_gemma":0.000061442035,"threshold_uncertainty_score":0.7194955},"labels":[],"label_agreement":null},{"id":"W2164948578","doi":"10.1162/089120103321337458","title":"Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":257,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Task (project management); Machine translation; Vocabulary; Beam search; Word error rate; Sentence; Translation (biology); Artificial intelligence; Natural language processing; Dynamic programming; Search algorithm; Speech recognition; Set (abstract data type); Algorithm; Linguistics; Programming language","score_opus":0.01830414375166094,"score_gpt":0.31965641621504903,"score_spread":0.3013522724633881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164948578","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":[0.0000749093,0.0017095411,0.99732375,0.0000645002,0.00017851994,0.00029435722,0.000030617317,0.00025502266,0.00006876071],"genre_scores_gemma":[0.17294164,0.00000444744,0.8268375,0.00004869045,0.000049419647,0.000018626484,0.00007178765,0.000013347706,0.00001456124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989419,0.000038417827,0.00022553236,0.00031991614,0.00024634475,0.00022787593],"domain_scores_gemma":[0.9987721,0.00058962853,0.00005355659,0.00011433385,0.0003923052,0.00007808103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036049695,0.00012767423,0.00013131788,0.000103587416,0.00019346147,0.00019936345,0.00019150566,0.00005628932,0.0000016868642],"category_scores_gemma":[0.0008416311,0.00013093185,0.00002459237,0.0002009559,0.00006134166,0.00005973696,0.00004471504,0.00015793323,9.862298e-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":[0.000003461803,0.000033615815,0.000029138495,0.00006003354,0.000009739777,0.000008815572,0.00019042092,0.00082683464,0.00001230049,0.2049632,0.000014417333,0.79384804],"study_design_scores_gemma":[0.0002379481,0.00005790232,0.00004165336,0.000025821013,0.000007742315,0.000018733479,0.000006095666,0.8301212,0.000094552975,0.16634098,0.0029028186,0.00014452833],"about_ca_topic_score_codex":0.0000053405365,"about_ca_topic_score_gemma":0.0000024127726,"teacher_disagreement_score":0.8292944,"about_ca_system_score_codex":0.00004220701,"about_ca_system_score_gemma":0.00010068096,"threshold_uncertainty_score":0.5339246},"labels":[],"label_agreement":null},{"id":"W2166391512","doi":"10.1162/089120101317066122","title":"Automatic Verb Classification Based on Statistical Distributions of Argument Structure","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":199,"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; National Science Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Verb; Sentence; Argument (complex analysis); Classifier (UML); Predicate (mathematical logic)","score_opus":0.01714931419756963,"score_gpt":0.3015708389109142,"score_spread":0.28442152471334453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166391512","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":[0.0012804714,0.000047912315,0.9972195,0.00025980853,0.0002660084,0.000120091565,0.0001487252,0.0002496978,0.00040777135],"genre_scores_gemma":[0.53336036,4.2880265e-7,0.46630108,0.00009294384,0.000055159202,0.000003060586,0.00017860235,0.000004137556,0.000004236224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878675,0.000051118728,0.00031379104,0.00024654428,0.00045151063,0.000150292],"domain_scores_gemma":[0.9984072,0.00050747726,0.00016981621,0.00028267526,0.0005654882,0.00006737462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117339325,0.00012332978,0.00014058164,0.00011269217,0.00010954462,0.000068992405,0.00041634496,0.00006321901,0.00003585215],"category_scores_gemma":[0.0016276954,0.00011518742,0.00003282929,0.0003335315,0.00007641276,0.000034306147,0.000056197754,0.00015249013,0.000007979969],"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":[0.0000064018827,0.00011421661,0.00033839417,0.00003665547,0.000007050457,0.000013182366,0.00003385678,0.007837563,0.000063805135,0.97849655,0.00076670107,0.012285623],"study_design_scores_gemma":[0.00012958099,0.00006304944,0.0034398653,0.000041077918,0.000007808873,0.000003726035,0.0000016654619,0.74408567,0.00029300284,0.25114644,0.00069267285,0.000095442636],"about_ca_topic_score_codex":0.0000034746697,"about_ca_topic_score_gemma":6.768471e-7,"teacher_disagreement_score":0.73624814,"about_ca_system_score_codex":0.00010698738,"about_ca_system_score_gemma":0.00017564808,"threshold_uncertainty_score":0.46972066},"labels":[],"label_agreement":null},{"id":"W2168801328","doi":"10.1162/089120103322711587","title":"Embedding Web-Based Statistical Translation Models in Cross-Language Information Retrieval","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Cross-language information retrieval; Machine translation; Natural language processing; Information retrieval; Artificial intelligence; Process (computing); Translation (biology); Machine translation software usability; Language model; Embedding; Example-based machine translation; Programming language","score_opus":0.019591668201522305,"score_gpt":0.3257819259314265,"score_spread":0.3061902577299042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168801328","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":[0.0018311238,0.00026829625,0.9952231,0.0000373578,0.00031213308,0.00016026443,0.000031484644,0.00032904168,0.0018072127],"genre_scores_gemma":[0.5022816,5.901915e-7,0.49745178,0.00015130697,0.00002989678,0.0000027062135,0.000073541894,0.000005278765,0.0000033132114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848014,0.00009080976,0.00046940442,0.00023396187,0.00048426556,0.00024143871],"domain_scores_gemma":[0.998595,0.0005175382,0.00013666526,0.00018926403,0.00048831507,0.0000732082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052257214,0.0001539222,0.0001512467,0.00021916493,0.00010832713,0.00033027283,0.00033470825,0.000107275155,0.000011105445],"category_scores_gemma":[0.0024537635,0.00016401935,0.000034833585,0.0004855964,0.000056703284,0.00044369642,0.000031102078,0.00025527523,0.0000134408465],"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":[0.000017552395,0.000035935245,0.00011872459,0.00004691873,0.0000029697344,0.00002051147,0.00052404276,0.4167165,0.000026496198,0.5791559,0.00006382804,0.003270628],"study_design_scores_gemma":[0.00046349305,0.000022944605,0.000070136826,0.000030580617,0.0000026554758,0.000004228568,0.0000082825345,0.78592867,0.00035846652,0.212554,0.00040165012,0.00015488981],"about_ca_topic_score_codex":0.0000070549495,"about_ca_topic_score_gemma":0.0000017022236,"teacher_disagreement_score":0.5004505,"about_ca_system_score_codex":0.00012131192,"about_ca_system_score_gemma":0.0003620649,"threshold_uncertainty_score":0.6688515},"labels":[],"label_agreement":null},{"id":"W2170471032","doi":"10.1162/089120103322753365","title":"Disambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":141,"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":"Engineering and Physical Sciences Research Council; Atomic Energy of Canada Limited","keywords":"Computer science; Adjective; Noun; Natural language processing; Verb; Artificial intelligence; Word (group theory); Heuristic; Argument (complex analysis); Part of speech; Linguistics","score_opus":0.024330433789640626,"score_gpt":0.30231777277498023,"score_spread":0.2779873389853396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170471032","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":[0.013285158,0.00078075094,0.9839089,0.00003326331,0.00036441605,0.00010278696,0.0000047508597,0.00038854536,0.0011314234],"genre_scores_gemma":[0.4772487,0.0000016422185,0.5225801,0.000069092006,0.00007779127,0.0000023428847,0.000004497317,0.000005811007,0.000010027758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987483,0.0000955924,0.00026681554,0.00033644968,0.00035169398,0.00020116082],"domain_scores_gemma":[0.9986271,0.0004731213,0.0001333999,0.00012637433,0.0005636302,0.00007635766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002641315,0.0001512248,0.00014942378,0.00010301366,0.0003029068,0.0002689135,0.00026743583,0.00006521814,0.000006226759],"category_scores_gemma":[0.003470494,0.00014595904,0.000027960241,0.00031036424,0.00009718001,0.00013182317,0.00010341107,0.00011662209,0.0000027849537],"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":[0.0000039116903,0.00006473531,0.0015931934,0.00005599161,0.000028022567,0.0000103426855,0.00057107327,0.0040098894,0.00026910758,0.98769665,0.00009310671,0.0056039784],"study_design_scores_gemma":[0.00011765777,0.00004001143,0.0008666211,0.00004938451,0.000009978561,0.000042132917,0.000014371488,0.5108938,0.0004758117,0.48715016,0.000164158,0.00017589286],"about_ca_topic_score_codex":0.00000850012,"about_ca_topic_score_gemma":0.0000014286973,"teacher_disagreement_score":0.5068839,"about_ca_system_score_codex":0.00006196801,"about_ca_system_score_gemma":0.0002645136,"threshold_uncertainty_score":0.5952037},"labels":[],"label_agreement":null},{"id":"W2562910494","doi":"10.1162/coli_a_00278","title":"Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications","year":2016,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":80,"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":"Computational linguistics; Perspective (graphical); Computer science; Linguistics; Field (mathematics); Sociocultural linguistics; Subjectivity; Multidisciplinary approach; Interpretation (philosophy); Sentiment analysis; Affect (linguistics); Artificial intelligence; Natural language processing; Sociology; Natural language; Epistemology; Social science; Comprehension approach","score_opus":0.01678670568591051,"score_gpt":0.3042419730166649,"score_spread":0.2874552673307544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562910494","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":[0.00522464,0.0005433976,0.98997533,0.0001441241,0.0002531571,0.00015899882,0.000025481178,0.00005709563,0.0036177817],"genre_scores_gemma":[0.7955231,0.000009312895,0.20390771,0.00010505983,0.0002817103,0.00001250522,0.000045127093,0.000007984817,0.00010747775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985452,0.00006384946,0.0004243321,0.0003530367,0.000469695,0.00014387257],"domain_scores_gemma":[0.9972406,0.0012445984,0.00025157732,0.00021058983,0.00095892244,0.000093725255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021849405,0.00014073087,0.00021188808,0.0002100481,0.00014054288,0.000059013433,0.00031318725,0.000043215623,0.000024426974],"category_scores_gemma":[0.0008776138,0.00011152095,0.000061063656,0.00035327536,0.00014154654,0.00005236793,0.00016173943,0.00006060956,0.000029349954],"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":[0.0000062113268,0.000096664604,0.0014395315,0.00002470632,0.000091109374,0.000004795413,0.0024592313,0.0129038505,0.00008215947,0.9657454,0.00025741002,0.016888939],"study_design_scores_gemma":[0.00093558506,0.00008587289,0.007106108,0.00010252733,0.000059795486,0.0000054150128,0.00012095269,0.5485553,0.00019423997,0.43618527,0.0063185487,0.00033038933],"about_ca_topic_score_codex":0.0000034285856,"about_ca_topic_score_gemma":0.0000013655203,"teacher_disagreement_score":0.79029846,"about_ca_system_score_codex":0.000034078443,"about_ca_system_score_gemma":0.00013827976,"threshold_uncertainty_score":0.45476925},"labels":[],"label_agreement":null},{"id":"W2602799059","doi":"10.1162/coli_a_00290","title":"Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease","year":2017,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health; Alzheimer Society; AGE-WELL; Carnegie Mellon University; Natural Sciences and Engineering Research Council of Canada; University of Pittsburgh","keywords":"Computer science; Confusion; Dementia; Cognitive psychology; Vocabulary; Function (biology); Cognition; Process (computing); Parsing; Spoken language; Decision tree; Artificial intelligence; Natural language processing; Psychology; Disease; Linguistics; Medicine","score_opus":0.030383408812927348,"score_gpt":0.2762257908780106,"score_spread":0.24584238206508324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602799059","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":[0.20977518,0.0005087041,0.78442377,0.00033773997,0.0012297418,0.00043194284,0.000024431863,0.0001265857,0.0031418968],"genre_scores_gemma":[0.9628205,0.0000039762226,0.036824547,0.000058124908,0.00024079076,0.000008387057,0.000024839588,0.000009266337,0.000009627535],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990162,0.00004148197,0.0001645777,0.00031290622,0.00028239065,0.00018243557],"domain_scores_gemma":[0.99890065,0.00022481002,0.00015965503,0.00031776165,0.00024163321,0.00015547022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021784351,0.00012193251,0.0001518039,0.00008797803,0.0005081863,0.0005253215,0.0003649056,0.000027039758,0.0000010357261],"category_scores_gemma":[0.0006443737,0.000101160265,0.000014401446,0.00008372544,0.00008240357,0.00012699232,0.00017776822,0.0001143293,0.000008118946],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019592857,0.00013841361,0.5498988,0.00010875023,0.00006842176,0.000587602,0.0027329822,0.02188277,0.000017660186,0.4210097,0.00018607278,0.0031729273],"study_design_scores_gemma":[0.0013897421,0.00010062801,0.74584216,0.00028162808,0.000032343454,0.000027441565,0.00005930679,0.21584527,0.000029206378,0.03563805,0.00039716612,0.00035709084],"about_ca_topic_score_codex":0.00018428052,"about_ca_topic_score_gemma":0.0002669663,"teacher_disagreement_score":0.75304526,"about_ca_system_score_codex":0.000018448,"about_ca_system_score_gemma":0.00016692298,"threshold_uncertainty_score":0.50656873},"labels":[],"label_agreement":null},{"id":"W2884082915","doi":"10.1162/coli_a_00327","title":"Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey","year":2018,"lang":"en","type":"article","venue":"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":"Simon Fraser University","funders":"Ruhr-Universität Bochum; Universität Hamburg","keywords":"Anaphora (linguistics); Antecedent (behavioral psychology); Computer science; Automatic summarization; Natural language processing; Linguistics; Sentence; Artificial intelligence; Machine translation; Computational linguistics; Field (mathematics); Resolution (logic); Psychology; Philosophy","score_opus":0.018271616867919945,"score_gpt":0.30533072661077887,"score_spread":0.2870591097428589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884082915","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":[0.0074852197,0.0001452673,0.9890861,0.000059037182,0.0009161118,0.00022115716,0.0000471458,0.00028939202,0.0017505646],"genre_scores_gemma":[0.5324219,6.291424e-7,0.46676248,0.00021091335,0.0004735674,0.000005311867,0.00008884546,0.000015271704,0.000021080545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771583,0.00010298934,0.0004965241,0.0006145286,0.0006714435,0.0003986924],"domain_scores_gemma":[0.99527997,0.0006397661,0.00024387815,0.00032859712,0.0033706953,0.00013707999],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000620689,0.00028034064,0.00029590804,0.00038336733,0.0002171606,0.00029084936,0.0009829828,0.00010991729,0.000010093677],"category_scores_gemma":[0.0040428294,0.00026698844,0.000039535218,0.00096327584,0.00026626958,0.00006998261,0.00028891081,0.0003238199,0.000053106753],"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":[0.0006150641,0.0013028492,0.122267954,0.00029421013,0.00020016624,0.0011045345,0.0031018113,0.101998545,0.000049427566,0.7462318,0.009933242,0.012900398],"study_design_scores_gemma":[0.00080797746,0.00037479968,0.055203248,0.00021578293,0.000009791947,0.000033300013,0.000011293047,0.7899166,0.00015112947,0.15146592,0.0012762765,0.0005339265],"about_ca_topic_score_codex":0.00020716706,"about_ca_topic_score_gemma":0.00020196162,"teacher_disagreement_score":0.687918,"about_ca_system_score_codex":0.00014656698,"about_ca_system_score_gemma":0.00050297304,"threshold_uncertainty_score":0.99997824},"labels":[],"label_agreement":null},{"id":"W2891212627","doi":"10.1162/coli_a_00333","title":"Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information","year":2018,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"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; University of Ottawa","funders":"","keywords":"Computer science; Social media; Context (archaeology); Perspective (graphical); Process (computing); Interpretation (philosophy); Task (project management); Linguistics; Artificial intelligence; Natural language processing; World Wide Web","score_opus":0.021970997074845143,"score_gpt":0.2991216231871204,"score_spread":0.27715062611227526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891212627","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":[0.059037834,0.000011382106,0.9163428,0.009706011,0.0052538672,0.00026982426,0.00002348927,0.00009070085,0.009264087],"genre_scores_gemma":[0.89164275,2.1993978e-7,0.022920758,0.0015425384,0.08384754,0.0000053463345,0.000011537733,0.000005014557,0.000024268296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926513,0.000036423287,0.00019976767,0.00014698187,0.00023153379,0.00012013491],"domain_scores_gemma":[0.99944556,0.00018247165,0.000061905754,0.00010264758,0.00017610368,0.000031294217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002609091,0.000072050716,0.0000742284,0.00009400973,0.00016578918,0.000117268646,0.00018459589,0.00002940781,0.000019038649],"category_scores_gemma":[0.0014996361,0.000060786977,0.00001193529,0.00014935466,0.000054220724,0.00008162871,0.00009101287,0.000100824036,0.00011320986],"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":[0.000023214467,0.00002850443,0.00016176565,0.0000076131514,0.0000064399533,0.0000028967129,0.07021653,0.017207474,0.000003149628,0.74223584,0.018245323,0.15186124],"study_design_scores_gemma":[0.00072327274,0.000115197574,0.004300438,0.000039436454,0.0000070133647,0.000007888567,0.004582058,0.6048424,0.000070878865,0.023109829,0.36188585,0.00031570226],"about_ca_topic_score_codex":0.000010632548,"about_ca_topic_score_gemma":0.000033450833,"teacher_disagreement_score":0.89342207,"about_ca_system_score_codex":0.000038197057,"about_ca_system_score_gemma":0.000033414715,"threshold_uncertainty_score":0.2478821},"labels":[],"label_agreement":null},{"id":"W2895279374","doi":"10.1162/coli_a_00363","title":"Scalable Micro-planned Generation of Discourse from Structured Data","year":2019,"lang":"en","type":"preprint","venue":"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":"Université de Montréal","funders":"","keywords":"Computer science; Interpretability; Natural language processing; Scalability; Artificial intelligence; Natural language generation; Sentence; Pipeline (software); Paragraph; Fluency; Text simplification; Natural language understanding; Robustness (evolution); Natural language; Programming language; Database","score_opus":0.08137583821686917,"score_gpt":0.32304697739436655,"score_spread":0.24167113917749738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895279374","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":[0.015537111,0.0003972509,0.9752601,0.00013392992,0.0062507656,0.00024777133,0.0017294664,0.000072592644,0.00037104834],"genre_scores_gemma":[0.4768005,0.0000053534336,0.51565963,0.00006916194,0.0013916397,0.0000018303123,0.0060096723,0.000013020834,0.000049192146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977296,0.00007251936,0.00059325615,0.00089832384,0.00052289857,0.00018341579],"domain_scores_gemma":[0.9965972,0.00025888803,0.00047344624,0.0018847618,0.0007183728,0.00006736271],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021785227,0.0002417251,0.0003726125,0.000108091124,0.000065707376,0.00019725978,0.002402661,0.00021045082,0.0000233821],"category_scores_gemma":[0.00073975895,0.00025805837,0.000059026068,0.00008883825,0.000050677867,0.000061840816,0.0028224515,0.0003621982,0.000033670018],"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":[0.0000047049025,0.000034406024,0.00044538509,0.00006534631,0.00006237205,0.0000047919807,0.0001902297,0.97782874,0.00009925945,0.016992623,0.0029063097,0.0013658073],"study_design_scores_gemma":[0.00020372946,0.000012812466,0.00054582284,0.00008791415,0.000034428987,0.0000010067381,0.000005837819,0.93052155,0.00019549823,0.067296706,0.0008638701,0.0002308339],"about_ca_topic_score_codex":0.00009122794,"about_ca_topic_score_gemma":0.000015285665,"teacher_disagreement_score":0.4612634,"about_ca_system_score_codex":0.000056895547,"about_ca_system_score_gemma":0.000662004,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W2986265153","doi":"10.1162/coli_a_00367","title":"On the Linguistic Representational Power of Neural Machine Translation Models","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"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; Natural language processing; Machine translation; Artificial intelligence; Interpretability; Semantics (computer science); Rule-based machine translation; Word (group theory); Contrast (vision); Linguistics","score_opus":0.05564198337220849,"score_gpt":0.3233539129337652,"score_spread":0.2677119295615567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986265153","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":[0.0001439908,0.0019241835,0.9909416,0.0021259445,0.0012450502,0.00038881396,0.00016676963,0.00034689426,0.0027167979],"genre_scores_gemma":[0.61598706,0.0000031267232,0.3829848,0.00055400614,0.00024776187,0.000013138063,0.00018351438,0.000018297596,0.000008316805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749047,0.0001463559,0.0006356502,0.00062282715,0.00091992336,0.00018479067],"domain_scores_gemma":[0.99572545,0.0018151589,0.0005253474,0.00057891815,0.0012757216,0.00007938723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030019088,0.0003100345,0.00033042525,0.00015458155,0.00013779817,0.00018423416,0.0015127136,0.00017038251,0.000013987436],"category_scores_gemma":[0.004135843,0.00025091603,0.00017637042,0.00028376645,0.0001195653,0.000038835595,0.0006349058,0.00089675374,0.0000062268496],"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":[0.000018868997,0.000043216118,0.000006423096,0.00007339352,0.00003149264,0.000016535469,0.00083257986,0.28204787,0.000005472172,0.7153385,0.0005710868,0.0010145344],"study_design_scores_gemma":[0.000066088214,0.0000311585,0.000018494,0.000066401284,0.000012286399,0.000001933191,0.0000018630288,0.50774896,0.000052307758,0.4918212,0.00005604725,0.00012324107],"about_ca_topic_score_codex":0.000021544374,"about_ca_topic_score_gemma":8.6475535e-7,"teacher_disagreement_score":0.61584306,"about_ca_system_score_codex":0.000055471774,"about_ca_system_score_gemma":0.0003201678,"threshold_uncertainty_score":0.99999434},"labels":[],"label_agreement":null},{"id":"W3008170323","doi":"10.1162/coli_a_00380","title":"The Limitations of Stylometry for Detecting Machine-Generated Fake News","year":2020,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":15,"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":"Stylometry; Misinformation; Computer science; Artificial intelligence; Authorship attribution; Natural language processing; Machine learning; Computer security","score_opus":0.1728446409505819,"score_gpt":0.37575612472199554,"score_spread":0.20291148377141363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008170323","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":[0.008279372,0.0009793306,0.86140615,0.0066230316,0.00960237,0.0023929258,0.0017197574,0.0003443576,0.1086527],"genre_scores_gemma":[0.9480206,0.00017741909,0.04916722,0.0004120571,0.0014508317,0.000009214691,0.00050130807,0.00001774547,0.00024360514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985673,0.00010920179,0.0005279487,0.00015328113,0.00045299556,0.00018931659],"domain_scores_gemma":[0.9941486,0.0032696223,0.0005125175,0.00012632654,0.001815709,0.0001272173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00056808995,0.0001300425,0.00018711742,0.00008917998,0.0008673275,0.0002204032,0.0003275859,0.00013953648,0.0000075072203],"category_scores_gemma":[0.053297218,0.000115856965,0.00011984396,0.00027168143,0.00014871493,0.000018979987,0.000117329655,0.00027221953,0.000008482636],"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":[0.00004680807,0.000046659097,0.00009318096,0.00014690305,0.0001535077,7.2518566e-7,0.026419923,0.291219,0.000007884362,0.6214941,0.011049616,0.049321707],"study_design_scores_gemma":[0.0003947165,0.000060162154,0.0006117737,0.00006572065,0.000081878716,2.8138734e-7,0.005816284,0.40056995,0.000049256156,0.15841125,0.4336226,0.0003161525],"about_ca_topic_score_codex":0.00013364054,"about_ca_topic_score_gemma":0.00029364604,"teacher_disagreement_score":0.93974125,"about_ca_system_score_codex":0.0000774161,"about_ca_system_score_gemma":0.0010525555,"threshold_uncertainty_score":0.9546773},"labels":[],"label_agreement":null},{"id":"W3193068792","doi":"10.1162/coli_a_00422","title":"Probing Classifiers: Promises, Shortcomings, and Advances","year":2021,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"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":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Artificial intelligence; Variety (cybernetics); Classifier (UML); Machine learning; Property (philosophy); Artificial neural network; Deep neural networks; Natural language processing; Epistemology","score_opus":0.03569677429684543,"score_gpt":0.2887908698049079,"score_spread":0.2530940955080625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193068792","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":[0.0031367217,0.0034565553,0.98729736,0.00024138007,0.0027367165,0.00027481638,0.0000116353785,0.00020752376,0.0026372909],"genre_scores_gemma":[0.4142305,0.00007310679,0.58471185,0.00017224957,0.00064403366,0.000020557558,0.00007635282,0.000015379444,0.0000559677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979324,0.00006127217,0.00046563213,0.0008673725,0.0004219654,0.00025140194],"domain_scores_gemma":[0.9981336,0.0002827734,0.00024681306,0.00046768057,0.0007436311,0.00012550238],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024154314,0.0002736971,0.0003386974,0.00011194949,0.00016179006,0.000681244,0.00066786463,0.00018107981,0.000003448753],"category_scores_gemma":[0.0011265506,0.00030545157,0.00007448009,0.000114642295,0.00006978245,0.00008416878,0.0017893853,0.0005543225,0.00000236914],"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":[0.0000050896247,0.00009434447,0.0011143115,0.0009144395,0.00009535552,0.00015505962,0.0020020744,0.56751585,0.000008241533,0.38559395,0.00031029648,0.042190976],"study_design_scores_gemma":[0.00014278025,0.000012848818,0.00025103096,0.0003267005,0.00002005197,0.000016409644,0.000039401282,0.88060254,0.000022459657,0.11068464,0.0075384816,0.0003426272],"about_ca_topic_score_codex":0.000008811446,"about_ca_topic_score_gemma":0.000003833994,"teacher_disagreement_score":0.41109377,"about_ca_system_score_codex":0.000089201545,"about_ca_system_score_gemma":0.0006261425,"threshold_uncertainty_score":0.99993974},"labels":[],"label_agreement":null},{"id":"W3201284223","doi":"10.1162/coli_a_00433","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","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":"National Research Council Canada","funders":"","keywords":"Harm; Emotion recognition; Sentiment analysis; Key (lock); Computer science; Psychology; Social psychology; Artificial intelligence; Computer security","score_opus":0.0701563089762093,"score_gpt":0.3225153650597269,"score_spread":0.2523590560835176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201284223","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":[0.011858259,0.00006776201,0.98660403,0.00044352197,0.00055330654,0.00014594338,0.00005123908,0.00008120747,0.00019473127],"genre_scores_gemma":[0.71749324,0.0000029961425,0.28111792,0.0004617834,0.0001560097,0.000032350035,0.00066246855,0.0000066691173,0.00006657585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873155,0.00011440653,0.00029284818,0.00029922163,0.00043240236,0.00012955688],"domain_scores_gemma":[0.9985962,0.0006616344,0.00017022587,0.00013572951,0.0003837904,0.00005241583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076159695,0.00009184471,0.00016205088,0.0003109789,0.00058608304,0.00014625603,0.0001864293,0.00002873281,0.00006349319],"category_scores_gemma":[0.00048951013,0.00010557868,0.00011548372,0.00066698977,0.000020829262,0.000037765843,0.00018505273,0.0001381428,0.000006641029],"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":[0.000010770641,0.00027410116,0.003108358,0.0000836019,0.0011297758,0.0000073959086,0.0040792245,0.8130454,0.00001185451,0.14596944,0.0023799168,0.029900204],"study_design_scores_gemma":[0.00022204929,0.00005578115,0.0021116876,0.0000048283405,0.00022519288,0.0000019909346,0.00009125397,0.95229656,0.000008036979,0.04239473,0.0024638467,0.00012407394],"about_ca_topic_score_codex":0.00000519262,"about_ca_topic_score_gemma":9.45907e-7,"teacher_disagreement_score":0.70563495,"about_ca_system_score_codex":0.00005812809,"about_ca_system_score_gemma":0.000068943016,"threshold_uncertainty_score":0.45077363},"labels":[],"label_agreement":null},{"id":"W4205635927","doi":"10.1162/coli_a_00426","title":"Deep Learning for Text Style Transfer: A Survey","year":2021,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Politeness; Style (visual arts); Task (project management); Variety (cybernetics); Natural language processing; Artificial intelligence; Transfer of learning; Field (mathematics); Natural language; Deep learning; Natural (archaeology); Linguistics","score_opus":0.04084954962181789,"score_gpt":0.2874410351691519,"score_spread":0.24659148554733404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205635927","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":[0.0014919083,0.00019928972,0.9961666,0.000097103824,0.0008042656,0.00008313664,0.00000777606,0.000106649226,0.0010433076],"genre_scores_gemma":[0.65321296,0.0000029483663,0.3460503,0.00016979668,0.00027507247,0.000005896417,0.00009707687,0.0000091492675,0.00017680909],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988807,0.00009399404,0.00024814103,0.00034123924,0.00023579015,0.0002001706],"domain_scores_gemma":[0.9976185,0.0008819739,0.00003299944,0.00018296822,0.0012107682,0.00007279617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033789893,0.00010148439,0.00013952004,0.000045141365,0.00018480542,0.00014438738,0.00029341754,0.000048485308,0.000010370069],"category_scores_gemma":[0.0033941085,0.000118168544,0.00006302074,0.00020166572,0.000018266035,0.000031523272,0.00007832192,0.00013195898,0.00001784065],"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":[0.0000042237316,0.000040104147,0.0011236335,0.000024773526,0.000013855839,0.000013449811,0.0003920356,0.6917797,0.000007944066,0.2926371,0.00010848622,0.013854699],"study_design_scores_gemma":[0.00029870315,0.00002569384,0.0035566895,0.000010518614,0.000005282318,0.0000061397573,0.00001227179,0.9616269,0.000036312846,0.023040093,0.011243384,0.0001380258],"about_ca_topic_score_codex":0.000009119675,"about_ca_topic_score_gemma":0.000022228578,"teacher_disagreement_score":0.65172106,"about_ca_system_score_codex":0.00003258877,"about_ca_system_score_gemma":0.00020510609,"threshold_uncertainty_score":0.48187733},"labels":[],"label_agreement":null},{"id":"W4220732108","doi":"10.1162/coli_a_00434","title":"Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Automatic summarization; Computer science; Transformer; Domain adaptation; Natural language processing; Adaptation (eye); Artificial intelligence; Transfer of learning; Task (project management); Information retrieval","score_opus":0.01946222096216806,"score_gpt":0.24978835952530382,"score_spread":0.23032613856313575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220732108","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":[0.0031246257,0.00001831803,0.99406415,0.00034781595,0.0005187061,0.00051812374,0.000067637884,0.00012972261,0.0012109106],"genre_scores_gemma":[0.57246333,3.916956e-7,0.42693433,0.00014067376,0.0001375649,0.000080471356,0.00017686599,0.000012016255,0.00005436566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985887,0.00005708299,0.00029684833,0.0003637947,0.00048656968,0.00020702757],"domain_scores_gemma":[0.99872124,0.00043992553,0.00016180582,0.00012671074,0.00048487211,0.00006546019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030345042,0.00013721001,0.00013443848,0.00012650952,0.00044835813,0.00008611022,0.00029066237,0.000033850003,0.000009495976],"category_scores_gemma":[0.00016477989,0.00014545607,0.00005070554,0.00027476638,0.000032229877,0.000094934,0.000047809728,0.00015289843,0.0000018413921],"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":[0.00006026992,0.00005397799,0.00006555458,0.000015501144,0.000021650718,0.0000034842622,0.0017594598,0.7262504,0.000012391058,0.26296,0.000048869115,0.008748415],"study_design_scores_gemma":[0.00091137167,0.00020978725,0.0011571752,0.000008447727,0.000013101512,0.0000057567654,0.00020970494,0.9140549,0.00001743965,0.074374706,0.008849119,0.00018853227],"about_ca_topic_score_codex":0.000023416273,"about_ca_topic_score_gemma":0.000014802989,"teacher_disagreement_score":0.5693387,"about_ca_system_score_codex":0.0001619794,"about_ca_system_score_gemma":0.0003769749,"threshold_uncertainty_score":0.59315264},"labels":[],"label_agreement":null},{"id":"W4231077011","doi":"10.4018/978-1-4666-6042-7.ch085","title":"Learning Words from Experience","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Language Development and Disorders","field":"Psychology","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":"Queen's University","funders":"","keywords":"Experiential learning; Psychology; Vocabulary; Quality (philosophy); Word learning; Cognition; Cognitive psychology; Linguistics; Epistemology; Pedagogy","score_opus":0.022908332874132763,"score_gpt":0.29867766466870005,"score_spread":0.2757693317945673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231077011","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002230675,0.00051342393,0.022608155,0.00001604872,0.0034264198,0.00009233367,0.000038036847,0.00013262089,0.9729499],"genre_scores_gemma":[0.17238645,0.00000865254,0.010188576,0.0006009255,0.0031083564,0.000011283579,0.0023296233,0.000090641326,0.8112755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879384,0.000020567486,0.00032027523,0.0003914655,0.0002944515,0.00017941053],"domain_scores_gemma":[0.99880815,0.00047422812,0.00020876128,0.00017038053,0.00026005908,0.00007843949],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000066777415,0.00025168617,0.00025182925,0.00009471739,0.00011322427,0.000041629428,0.00020552204,0.0002500837,0.007193161],"category_scores_gemma":[0.0005488473,0.00027292987,0.0000807752,0.00002061374,0.00009993108,0.0000043579294,0.00006916244,0.00037528595,0.0022578787],"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":[0.00003112789,0.000016984424,0.00058601826,0.00001137168,0.00014380297,0.00009832138,0.008706838,0.0017836669,1.5652276e-7,0.95843077,0.016293772,0.013897167],"study_design_scores_gemma":[0.000304615,0.000031917592,0.00061435025,0.00006116333,0.0000348585,0.000001736131,0.00018544322,0.00069804717,2.0500336e-7,0.113713026,0.88395697,0.00039765376],"about_ca_topic_score_codex":0.000027651206,"about_ca_topic_score_gemma":0.000003037843,"teacher_disagreement_score":0.8676632,"about_ca_system_score_codex":0.00003707018,"about_ca_system_score_gemma":0.000071706636,"threshold_uncertainty_score":0.9999723},"labels":[],"label_agreement":null},{"id":"W4233779307","doi":"10.1162/coli.2000.27.1.140","title":"<i>Construing Experience through Meaning: A Language-based Approach to Cognition</i> M. A. K. Halliday and Christian M. I. M. Matthiessen London: Cassell (Open linguistics series, edited by Robin Fawcett), 1999, xiii+657 pp; paperback, ISBN 0-304-70490-3, $102.00, £65.00","year":2001,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Meaning (existential); Philosophy; Linguistics; Cognitive linguistics; Cognitive science; Cognition; Series (stratigraphy); Psychology; Epistemology; Neuroscience","score_opus":0.02494040335504384,"score_gpt":0.29636894422158067,"score_spread":0.27142854086653684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233779307","genre_codex":"other","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":[0.03627457,0.022645067,0.17995536,0.0016487184,0.012964065,0.0054365415,0.0053129136,0.0014610364,0.73430175],"genre_scores_gemma":[0.8911629,0.00022883143,0.08809224,0.00906942,0.0039091487,0.00029848798,0.0050100065,0.00019161825,0.0020373452],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958392,0.00029465824,0.0010040051,0.0012685857,0.0007572837,0.00083631685],"domain_scores_gemma":[0.99599713,0.0007269563,0.00045230283,0.0005838641,0.0018086578,0.00043107435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044820594,0.0006920403,0.0007297127,0.00012763415,0.0006505843,0.00057634956,0.0007096275,0.00038061177,0.0005516226],"category_scores_gemma":[0.0030241169,0.0007487727,0.00012376496,0.0009196451,0.00042055437,0.00011550334,0.00025814,0.0005978848,0.00022410051],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001812223,0.0037140949,0.0028534974,0.00073820853,0.0010088611,0.0016057054,0.07969505,0.0053642644,0.0009092508,0.19079387,0.70594484,0.005560145],"study_design_scores_gemma":[0.0052383677,0.0005836587,0.00025544243,0.0004449411,0.00043458093,0.00044638777,0.014468462,0.007862926,0.0012428549,0.013810502,0.9529945,0.0022173405],"about_ca_topic_score_codex":0.0008351832,"about_ca_topic_score_gemma":0.000041854957,"teacher_disagreement_score":0.8548883,"about_ca_system_score_codex":0.00012161388,"about_ca_system_score_gemma":0.00027444775,"threshold_uncertainty_score":0.99949634},"labels":[],"label_agreement":null},{"id":"W4233966082","doi":"10.1162/coli_x_00181","title":"Publications Received","year":2014,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.017556002457512956,"score_gpt":0.29004651036624157,"score_spread":0.27249050790872864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233966082","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":[0.000042554995,0.000113670474,0.98425573,0.00084265135,0.00037752604,0.000052371826,0.0000020100968,0.00083066063,0.013482799],"genre_scores_gemma":[0.34612882,6.6147504e-7,0.6529525,0.00048297457,0.00023715022,0.0000049825694,0.000020415757,0.000004953442,0.00016755643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992164,0.000037118254,0.00016789272,0.00022304794,0.0002232968,0.00013228614],"domain_scores_gemma":[0.9984615,0.00030913745,0.00008438666,0.0002776928,0.0008019227,0.00006537126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021345277,0.00008107737,0.00008043518,0.000109178,0.0001385294,0.00018968398,0.0006771668,0.000042380663,0.000007516235],"category_scores_gemma":[0.003903999,0.00007971009,0.00002774462,0.00032190673,0.000036504556,0.000067729576,0.00013680344,0.000115401876,0.00005497265],"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":[3.7894486e-7,0.000016353897,0.00007990825,0.0000048034917,0.0000026462299,5.044745e-7,0.000042739295,0.00089250226,0.000010299282,0.9854079,0.0037804681,0.009761497],"study_design_scores_gemma":[0.00005597171,0.00001421669,0.00032446953,0.000007839943,0.0000018502302,0.0000034589923,6.391475e-7,0.3045827,0.0001129547,0.6330258,0.06177956,0.000090522975],"about_ca_topic_score_codex":0.0000026836485,"about_ca_topic_score_gemma":5.8948353e-7,"teacher_disagreement_score":0.35238206,"about_ca_system_score_codex":0.000028734219,"about_ca_system_score_gemma":0.00007298741,"threshold_uncertainty_score":0.46737334},"labels":[],"label_agreement":null},{"id":"W4235310004","doi":"10.4018/978-1-4666-6042-7.ch077","title":"Integrating Chinese Community into Canadian Society","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Radio, Podcasts, and Digital Media","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":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Set (abstract data type); English as a second language; Language acquisition; Pedagogy; Public relations; Computer science; Knowledge management; Medical education; Mathematics education; Psychology; Political science; Medicine","score_opus":0.02837525078318943,"score_gpt":0.3030507985673399,"score_spread":0.2746755477841505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235310004","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000958182,0.00017698322,0.0021400037,0.0002054656,0.0031457134,0.00016700596,0.00012712061,0.00008853701,0.99385333],"genre_scores_gemma":[0.6668839,0.0000788961,0.02955317,0.0028977548,0.016226074,0.0000069422367,0.0021553666,0.00013786503,0.28206003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984939,0.00008618041,0.00036655398,0.00021040713,0.0005341754,0.0003087749],"domain_scores_gemma":[0.99671465,0.0014632138,0.00020926636,0.00021220978,0.0009109931,0.0004896651],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006817665,0.0002790447,0.0003339849,0.00010769105,0.0013567423,0.00022053292,0.0004623323,0.00036769616,0.00015387459],"category_scores_gemma":[0.0061810585,0.00029018894,0.00021048741,0.000057634992,0.00063990685,0.000023767687,0.00006490092,0.0008931343,0.00017919531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016329117,0.0000087546505,0.00023710272,0.000040493145,0.00004219237,0.000006742077,0.011387894,0.0003462826,2.305438e-8,0.9591871,0.021548066,0.0071937027],"study_design_scores_gemma":[0.00006504494,0.000018880924,0.00007953371,0.00008491282,0.000016894452,7.9524006e-7,0.00027997626,0.0015377442,1.8285213e-8,0.37012452,0.62755936,0.00023228626],"about_ca_topic_score_codex":0.072518535,"about_ca_topic_score_gemma":0.3050329,"teacher_disagreement_score":0.7117933,"about_ca_system_score_codex":0.00056504697,"about_ca_system_score_gemma":0.0019724388,"threshold_uncertainty_score":0.999955},"labels":[],"label_agreement":null},{"id":"W4235980152","doi":"10.4018/978-1-4666-6042-7.ch012","title":"Demystifying Domain Specific Languages","year":2014,"lang":"en","type":"book-chapter","venue":"Computational Linguistics","topic":"Model-Driven Software Engineering Techniques","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":"École de Technologie Supérieure","funders":"","keywords":"Vagueness; Digital subscriber line; Domain-specific language; Computer science; Domain (mathematical analysis); Software engineering; Programming language; Artificial intelligence; Mathematics","score_opus":0.020484544248111955,"score_gpt":0.2533815354641975,"score_spread":0.23289699121608554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235980152","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":[6.9193885e-7,0.00042688212,0.8806438,0.00006664284,0.0008832307,0.00014368848,0.000028956278,0.0010262048,0.11677989],"genre_scores_gemma":[0.0020678013,0.000032966713,0.97433513,0.00016062205,0.001707263,0.000007384313,0.00014985197,0.00008112383,0.021457857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981413,0.00001932114,0.00044579376,0.0005789958,0.0005638245,0.00025075147],"domain_scores_gemma":[0.99814075,0.00033319826,0.00023937732,0.0006214464,0.00054075255,0.00012449396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024357805,0.00039263925,0.00038341535,0.00025478017,0.00011149204,0.00014878329,0.0009927882,0.000273358,0.00003191256],"category_scores_gemma":[0.000048476875,0.0004464426,0.00013810351,0.000050476567,0.000080218815,0.000021970018,0.00036215252,0.0004535864,0.00021700023],"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":[0.0000010482726,0.000004854376,0.0000033736264,0.000044141532,0.000023437093,0.00008519114,0.000055788434,0.013988246,6.50715e-7,0.9695546,0.00525823,0.010980414],"study_design_scores_gemma":[0.000060948456,0.000018620454,0.000010260085,0.00013436166,0.0000062994063,0.000017604383,1.16178946e-7,0.01975177,0.0000029373298,0.34942222,0.6302682,0.0003066538],"about_ca_topic_score_codex":0.0000011471099,"about_ca_topic_score_gemma":3.6314077e-7,"teacher_disagreement_score":0.62501,"about_ca_system_score_codex":0.0001387655,"about_ca_system_score_gemma":0.00009954895,"threshold_uncertainty_score":0.9997987},"labels":[],"label_agreement":null},{"id":"W4240118341","doi":"10.1162/coli_r_00161","title":"Publications Received","year":2013,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.027100620379252753,"score_gpt":0.27570986432487815,"score_spread":0.2486092439456254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240118341","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":[0.0010392223,0.00004593827,0.9631068,0.0014705535,0.00061557867,0.00008759497,0.0000013976301,0.00017401653,0.033458915],"genre_scores_gemma":[0.56969005,0.0000024695864,0.4284414,0.0004853021,0.00030803666,0.000014088642,0.000055497054,0.0000048993497,0.0009982723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999228,0.000021528924,0.00020482224,0.00019759209,0.00022131285,0.00012676594],"domain_scores_gemma":[0.998604,0.00019111161,0.000080767626,0.0002140705,0.0008330537,0.000076990924],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009033994,0.0000689741,0.00007890149,0.00012015042,0.00014010386,0.00031460187,0.00040639075,0.00002420937,0.00019775024],"category_scores_gemma":[0.00060876587,0.00006795184,0.000046015586,0.00036806744,0.00002242177,0.00009486065,0.000095098236,0.000058244048,0.00079134095],"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":[1.7577393e-7,0.000045333203,0.002058834,0.0000023090602,0.000023959254,4.9275445e-7,0.000120089055,0.014335606,0.000009990035,0.9389618,0.03843573,0.006005699],"study_design_scores_gemma":[0.0000934751,0.00000944703,0.017760564,0.000004404891,0.0000040712634,0.0000010551358,0.0000103762195,0.8374069,0.000014105711,0.089309014,0.055283055,0.00010353675],"about_ca_topic_score_codex":0.000008577492,"about_ca_topic_score_gemma":3.4139433e-7,"teacher_disagreement_score":0.84965277,"about_ca_system_score_codex":0.00001875288,"about_ca_system_score_gemma":0.00005719519,"threshold_uncertainty_score":0.99998665},"labels":[],"label_agreement":null},{"id":"W4245430175","doi":"10.1162/coli_r_00117","title":"Publications Received","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Semantic Web and Ontologies","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":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.04609064291162508,"score_gpt":0.3010136732916446,"score_spread":0.2549230303800195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245430175","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":[0.0011488122,0.00022119957,0.95137835,0.0007872526,0.0018004525,0.00005686082,0.0000027594688,0.00031019974,0.044294126],"genre_scores_gemma":[0.6707694,0.0000021007825,0.32821974,0.00031691126,0.00047171433,0.0000042982592,0.000014114917,0.0000031705745,0.00019852922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99931425,0.000024578974,0.00015057072,0.00012581196,0.00018106394,0.00020369772],"domain_scores_gemma":[0.99890095,0.00033977552,0.000057234563,0.00021822721,0.00039210593,0.00009173113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016794157,0.00006837023,0.00007360488,0.00007398748,0.00012271352,0.00008683778,0.00040201453,0.000032787593,0.000015629286],"category_scores_gemma":[0.0020290946,0.000065880784,0.000029597246,0.00022633892,0.000036011235,0.0000958325,0.00010771466,0.00006502445,0.00020024512],"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":[3.961164e-7,0.00004939895,0.0067348434,0.0000028160764,0.00000669416,4.554213e-7,0.00018482881,0.0012676303,0.0000019605523,0.982565,0.0070796297,0.0021063641],"study_design_scores_gemma":[0.00022777446,0.000024075707,0.21214992,0.000009127345,0.000010805902,0.000018754026,0.00003224631,0.18908827,0.000064612475,0.21978489,0.37831062,0.0002789128],"about_ca_topic_score_codex":0.0000031372606,"about_ca_topic_score_gemma":5.031724e-7,"teacher_disagreement_score":0.7627801,"about_ca_system_score_codex":0.000023070766,"about_ca_system_score_gemma":0.00006775629,"threshold_uncertainty_score":0.26865405},"labels":[],"label_agreement":null},{"id":"W4250326346","doi":"10.1162/coli_r_00106","title":"Briefly Noted","year":2012,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.028066313871546286,"score_gpt":0.2845006114861258,"score_spread":0.25643429761457953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250326346","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":[0.0008992796,0.00015231254,0.9846731,0.0005809663,0.0011568422,0.000056061715,0.000003071678,0.0006235207,0.011854839],"genre_scores_gemma":[0.7512671,0.0000018033833,0.24800707,0.00028103724,0.00026225718,0.0000038916864,0.000013466517,0.000003963615,0.00015941172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992785,0.000014862302,0.00016301294,0.00013405476,0.00021398814,0.00019561383],"domain_scores_gemma":[0.9992053,0.00017728584,0.00007121139,0.0002300432,0.00024744155,0.00006873436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012383048,0.00007763308,0.00007096436,0.000081119724,0.00010470568,0.00008385441,0.0004294763,0.00004505741,0.00001860109],"category_scores_gemma":[0.0009910046,0.000077304685,0.000028700302,0.0002414149,0.000045776185,0.000099637226,0.00014038845,0.000080603546,0.00027614817],"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":[5.973178e-7,0.00004264635,0.0018319822,0.000002724883,0.0000046082337,7.0170466e-7,0.000084637526,0.0005714396,0.000008972668,0.9854346,0.004348788,0.007668334],"study_design_scores_gemma":[0.00031833458,0.000037700105,0.048416197,0.000010097488,0.000008220517,0.0000099451645,0.00002441749,0.137531,0.00067118893,0.3207998,0.49181825,0.00035486303],"about_ca_topic_score_codex":0.0000016628061,"about_ca_topic_score_gemma":9.9117926e-8,"teacher_disagreement_score":0.7503678,"about_ca_system_score_codex":0.000030547137,"about_ca_system_score_gemma":0.00004307582,"threshold_uncertainty_score":0.35494182},"labels":[],"label_agreement":null},{"id":"W4280632712","doi":"10.1162/coli_a_00447","title":"Noun2Verb: Probabilistic Frame Semantics for Word Class Conversion","year":2022,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","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":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Verb; Principle of compositionality; Semantics (computer science); Programming language","score_opus":0.016793507886842647,"score_gpt":0.27922083496854416,"score_spread":0.2624273270817015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280632712","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":[0.00042107608,0.0003252768,0.9958996,0.0006362111,0.0014770634,0.0003810573,0.000058015557,0.0005403469,0.00026133098],"genre_scores_gemma":[0.43705457,7.466301e-7,0.56183565,0.00064041076,0.00020741488,0.00004397785,0.000086781496,0.000013340844,0.00011710188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853796,0.00005408267,0.00027569834,0.0003855844,0.0005005325,0.00024612702],"domain_scores_gemma":[0.99804765,0.00068952556,0.0001719636,0.000276771,0.00074504287,0.00006906089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033133998,0.00014807616,0.00016376843,0.0001267216,0.0005324479,0.0001412592,0.00089435466,0.00004999388,0.00001527552],"category_scores_gemma":[0.0017754924,0.00016152489,0.00007333996,0.00035246945,0.00005844897,0.000051874234,0.0005701618,0.00027955425,0.000007898912],"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":[0.00002003067,0.000104450926,0.00006633513,0.00009017148,0.000015152578,0.000020718924,0.00027131915,0.045847617,0.000020044783,0.9423415,0.008753261,0.002449376],"study_design_scores_gemma":[0.00019876329,0.00009000966,0.000020998836,0.000011926764,0.000009347643,0.000011152871,0.000011291831,0.5695459,0.00006044129,0.38192278,0.047952615,0.00016474655],"about_ca_topic_score_codex":0.0000038967196,"about_ca_topic_score_gemma":4.2111895e-7,"teacher_disagreement_score":0.5604187,"about_ca_system_score_codex":0.00019229855,"about_ca_system_score_gemma":0.0002563512,"threshold_uncertainty_score":0.65867937},"labels":[],"label_agreement":null},{"id":"W4383822224","doi":"10.1162/coli_a_00485","title":"Obituary: Yorick Wilks","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Obituary; Computer science; Philosophy; Theology","score_opus":0.06742586085169608,"score_gpt":0.41015240737440634,"score_spread":0.3427265465227103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383822224","genre_codex":"other","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":[0.027290696,0.0002800634,0.3063712,0.0053466023,0.008552639,0.0004852506,0.0000779691,0.0021422135,0.64945334],"genre_scores_gemma":[0.9471681,0.000020753927,0.043655563,0.0003373462,0.002880916,0.000007041503,0.00020433638,0.000014268749,0.0057116915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998625,0.0001574068,0.00021551827,0.00019469904,0.0005710465,0.00023632297],"domain_scores_gemma":[0.9977118,0.0013525969,0.000072192764,0.00007698716,0.00066674186,0.00011973134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078969455,0.00008448737,0.00012809552,0.00018606619,0.00060348195,0.000077945515,0.00018658252,0.000053462343,0.00016322637],"category_scores_gemma":[0.004333251,0.00009116305,0.00008882838,0.0011486075,0.00014443287,0.000022262971,0.00005229453,0.00009591051,0.00075446634],"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":[0.0000035242756,0.00002849931,0.002218477,0.0000055260725,0.00003124158,0.000017081382,0.001621014,0.097611055,9.071696e-7,0.87162864,0.018597897,0.008236168],"study_design_scores_gemma":[0.00010408517,0.000009857337,0.010357743,0.0000068209715,0.000019112636,3.4626441e-7,0.00030998958,0.07057307,8.6994027e-7,0.45623296,0.462256,0.00012913495],"about_ca_topic_score_codex":0.00015385493,"about_ca_topic_score_gemma":0.00004759891,"teacher_disagreement_score":0.9198774,"about_ca_system_score_codex":0.000062606436,"about_ca_system_score_gemma":0.000298677,"threshold_uncertainty_score":0.969739},"labels":[],"label_agreement":null},{"id":"W4389613952","doi":"10.1162/coli_a_00501","title":"Stance Detection with Explanations","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","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":"University of British Columbia","funders":"","keywords":"Computer science; Automatic summarization; Artificial intelligence; Parsing; Benchmark (surveying); Machine learning; Focus (optics); Grammaticality; Natural language processing; Linguistics","score_opus":0.02863169177005188,"score_gpt":0.26809391849028813,"score_spread":0.23946222672023626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389613952","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":[0.00316686,0.000011877421,0.99316394,0.00015862586,0.0005878059,0.000056293982,0.0000041697153,0.00043385205,0.0024165676],"genre_scores_gemma":[0.80745107,0.0000014442032,0.19204564,0.00011067818,0.0002373663,0.0000073757437,0.000015298921,0.0000057361326,0.0001253778],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992245,0.000016785943,0.00013755872,0.00020300431,0.00028727943,0.00013090814],"domain_scores_gemma":[0.99915177,0.00021407843,0.000050777468,0.00016937123,0.00037051446,0.000043515254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011880594,0.00006515751,0.00006063707,0.00011631421,0.00014830641,0.000073159244,0.00022573573,0.000021739628,0.0000021404594],"category_scores_gemma":[0.00040175853,0.00006342355,0.000014759004,0.00050914206,0.000017587769,0.000045267006,0.000054852953,0.00007018746,0.000094091374],"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":[0.0000017297134,0.000008714783,0.00021696465,0.000007440302,0.0000071338286,0.000016590804,0.0001725326,0.6302264,0.000009512262,0.36359584,0.00031499245,0.0054221544],"study_design_scores_gemma":[0.00011682652,0.000020648618,0.002077898,0.000010737731,0.0000021691621,0.0000044931817,0.000013045757,0.9265939,0.000049735463,0.06571292,0.0053125583,0.0000850709],"about_ca_topic_score_codex":0.0000037927068,"about_ca_topic_score_gemma":0.0000088287015,"teacher_disagreement_score":0.8042842,"about_ca_system_score_codex":0.000034459263,"about_ca_system_score_gemma":0.00007647699,"threshold_uncertainty_score":0.2586337},"labels":[],"label_agreement":null},{"id":"W4391017630","doi":"10.1162/coli_a_00510","title":"Context-aware Transliteration of Romanized South Asian Languages","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"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":"Institute for Catastrophic Loss Reduction","keywords":"Transliteration; Computer science; Romanization; Natural language processing; Context (archaeology); Artificial intelligence; Sentence; Word (group theory); Linguistics; History","score_opus":0.01638905617639773,"score_gpt":0.29555217385449595,"score_spread":0.2791631176780982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391017630","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":[0.0015757894,0.00029062285,0.99565315,0.00030756873,0.00029125225,0.00012229805,0.00003795369,0.00089089345,0.0008304857],"genre_scores_gemma":[0.755289,9.464952e-7,0.24428537,0.00012596928,0.00012723729,0.0000041862763,0.00009643649,0.000008684204,0.000062142346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902225,0.00004061929,0.00026827081,0.00021952085,0.00030520212,0.00014413723],"domain_scores_gemma":[0.99892247,0.00016832953,0.00012531494,0.00018485154,0.0005553298,0.00004372722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018224138,0.00010728439,0.00015158439,0.00018618342,0.00008181569,0.00008417305,0.00042612248,0.000060215123,0.000005606549],"category_scores_gemma":[0.00067280856,0.00010444543,0.000051737927,0.00052420294,0.00004296631,0.000060973,0.00007797809,0.000105152874,0.000023669067],"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":[0.000010688744,0.00003803947,0.00038377644,0.00011943654,0.000025857456,0.00006306955,0.005425244,0.0018406339,0.00020278797,0.97113055,0.0016207037,0.019139238],"study_design_scores_gemma":[0.0007829254,0.00012642746,0.0022339015,0.00020471255,0.000022927477,0.000012798034,0.0003498165,0.55542547,0.0046400223,0.43296477,0.002783504,0.00045274952],"about_ca_topic_score_codex":0.000005438433,"about_ca_topic_score_gemma":0.0000025583292,"teacher_disagreement_score":0.75371325,"about_ca_system_score_codex":0.000018926574,"about_ca_system_score_gemma":0.00008573226,"threshold_uncertainty_score":0.4259161},"labels":[],"label_agreement":null},{"id":"W4392367355","doi":"10.1162/coli_a_00512","title":"A Novel Alignment-based Approach for PARSEVAL Measuress","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Parsing; Sentence; Natural language processing; Artificial intelligence; Lexical analysis; Parseval's theorem; Machine translation; Word (group theory); Linguistics","score_opus":0.055118956961616714,"score_gpt":0.3166822825463177,"score_spread":0.26156332558470097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392367355","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":[0.000024820709,0.00011444542,0.9975126,0.00016602429,0.00042633543,0.00025613524,0.000043366497,0.0010836925,0.00037259771],"genre_scores_gemma":[0.22350302,2.8941835e-7,0.7755782,0.0003372966,0.00027220315,0.000055466182,0.00018420564,0.000014359873,0.000054969354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986968,0.000020230797,0.00021981666,0.00035615393,0.0004524512,0.0002545154],"domain_scores_gemma":[0.9984713,0.00041167237,0.00010035266,0.00022901979,0.0007172892,0.00007033479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041487196,0.00013646622,0.0001375059,0.00015744247,0.00017276964,0.00015644694,0.0006695569,0.00006674378,7.6955155e-7],"category_scores_gemma":[0.0016852879,0.00013405325,0.00006936133,0.00047320002,0.000043056596,0.000036978276,0.00012614086,0.00009703215,0.000009307281],"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":[0.000015345686,0.00014264841,0.00004954293,0.0001393208,0.000024849443,0.000008890592,0.00014640437,0.20226352,0.0004073539,0.78521085,0.006959952,0.0046313414],"study_design_scores_gemma":[0.00033202584,0.000031829837,0.00003046138,0.000018323939,0.000007575174,0.0000027786325,0.0000039364427,0.89245,0.0009464008,0.10325992,0.002751252,0.00016551375],"about_ca_topic_score_codex":0.0000030054048,"about_ca_topic_score_gemma":2.2066094e-7,"teacher_disagreement_score":0.69018644,"about_ca_system_score_codex":0.000053044554,"about_ca_system_score_gemma":0.00019143154,"threshold_uncertainty_score":0.5466533},"labels":[],"label_agreement":null},{"id":"W4401117478","doi":"10.1162/coli_a_00533","title":"Exploring Temporal Sensitivity in the Brain Using Multi-timescale Language Models: An EEG Decoding Study","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Cognitive Science and Mapping","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":"University of Alberta","funders":"","keywords":"Electroencephalography; Decoding methods; Sensitivity (control systems); Computer science; Language model; Speech recognition; Artificial intelligence; Psychology; Neuroscience; Algorithm","score_opus":0.2609003131987414,"score_gpt":0.37658984532571577,"score_spread":0.11568953212697436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401117478","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":[0.32445383,0.00004982806,0.6744866,0.00008207034,0.00050090515,0.00016354228,0.0000043401433,0.00009904806,0.00015984621],"genre_scores_gemma":[0.91033036,5.7713885e-7,0.08916347,0.00022289794,0.00024882003,0.000008812525,0.0000082769375,0.000008365857,0.000008453252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849063,0.00021090024,0.00023244966,0.00043339195,0.0003940427,0.0002386055],"domain_scores_gemma":[0.99875957,0.0007568168,0.00003743283,0.00020393958,0.00018632058,0.000055914777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015583183,0.00013104564,0.0001221014,0.00020867362,0.00022152907,0.0004974689,0.00035249762,0.000020582427,9.810519e-7],"category_scores_gemma":[0.00058692385,0.000111992,0.000041543666,0.0006651922,0.000037251026,0.00049769034,0.00018652824,0.00020803834,0.000008399255],"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":[0.000005483317,0.0005595091,0.0037692222,0.000047019534,0.00002544693,0.0016808573,0.08335877,0.8052892,0.00022483298,0.07120082,0.00003425705,0.033804562],"study_design_scores_gemma":[0.00014495132,0.000037998845,0.004564207,0.000062150524,0.0000058096916,0.000020050438,0.003209465,0.9859132,0.000007798115,0.0058245114,0.000061427585,0.00014842687],"about_ca_topic_score_codex":0.00018214926,"about_ca_topic_score_gemma":0.0001370644,"teacher_disagreement_score":0.58587646,"about_ca_system_score_codex":0.00006418323,"about_ca_system_score_gemma":0.0001561817,"threshold_uncertainty_score":0.47971046},"labels":[],"label_agreement":null},{"id":"W4404534114","doi":"10.1162/coli_a_00545","title":"The Emergence of Chunking Structures with Hierarchical RNN","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; University of Alberta; DeepMind; Canadian Institute for Advanced Research","keywords":"Chunking (psychology); Computer science; Natural language processing; Artificial intelligence","score_opus":0.011301540709767867,"score_gpt":0.25126442258731396,"score_spread":0.2399628818775461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404534114","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":[0.0013968829,0.00079636375,0.9927365,0.00024988689,0.000688829,0.000040973147,0.0000053909707,0.00007100234,0.004014161],"genre_scores_gemma":[0.87282795,0.000007605451,0.1267795,0.000023458502,0.0002900488,0.0000011872194,0.0000053425206,0.0000056486742,0.00005925868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912,0.00002115561,0.00021959624,0.0001853782,0.00031768242,0.00013618842],"domain_scores_gemma":[0.9989621,0.00048368744,0.000060283866,0.00015879325,0.0002975742,0.000037581864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016780036,0.000078880505,0.00009099914,0.000048215505,0.0002174122,0.00018807032,0.00039440987,0.000018874898,0.000010494005],"category_scores_gemma":[0.0003264382,0.000048284273,0.000048754508,0.00038131044,0.00011074536,0.000030161822,0.000114007,0.0001201104,0.0000038578632],"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":[0.0000027092763,0.000003861086,0.00008765836,0.000016261336,0.000035313027,0.000009479655,0.00020069677,0.084828265,0.0000040014193,0.89868623,0.00030837333,0.015817175],"study_design_scores_gemma":[0.000027067255,0.000038131137,0.00091740064,0.00003175663,0.000011033668,0.000008448487,0.000018315517,0.8261019,0.000024195982,0.15962301,0.013131665,0.000067080655],"about_ca_topic_score_codex":0.0000057237785,"about_ca_topic_score_gemma":0.0000038059852,"teacher_disagreement_score":0.87143105,"about_ca_system_score_codex":0.000007466908,"about_ca_system_score_gemma":0.000115400566,"threshold_uncertainty_score":0.19689755},"labels":[],"label_agreement":null},{"id":"W4412158322","doi":"10.1162/coli.a.16","title":"🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":142,"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 Waterloo","funders":"","keywords":"Siren (mythology); Computer science; Natural language processing; Linguistics; Art; Literature; Philosophy","score_opus":0.025782207768242967,"score_gpt":0.34966651908309326,"score_spread":0.3238843113148503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412158322","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":[0.028049437,0.00021639116,0.95796794,0.0035604027,0.0010264387,0.0004052241,0.000045313413,0.000115344825,0.008613486],"genre_scores_gemma":[0.9845143,0.000001727642,0.012083538,0.0031110544,0.00009151656,0.000006391571,0.000113419126,0.0000061469586,0.000071903974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983162,0.00050081837,0.0003116855,0.0002973137,0.0003517386,0.00022218656],"domain_scores_gemma":[0.9976754,0.0016570957,0.00007107719,0.00027623252,0.00029556704,0.000024604436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001507917,0.00011225073,0.00013407825,0.0002948351,0.000101567355,0.00010736929,0.0006095241,0.000062545005,0.0000027067028],"category_scores_gemma":[0.0035042677,0.00009994808,0.00002362512,0.00071015104,0.000016297116,0.00004315704,0.00011714686,0.00044666883,0.00000884303],"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":[0.0000063414486,0.00007106833,0.025285563,0.000017130344,0.0000017734435,0.000020826126,0.0016600362,0.48150402,2.4730705e-8,0.48985246,0.0004173033,0.0011634628],"study_design_scores_gemma":[0.00023172928,0.000023119333,0.25380132,0.00005113423,7.5371827e-7,5.6164106e-7,0.0000240142,0.7033906,2.8639116e-7,0.042037804,0.00037563394,0.00006307061],"about_ca_topic_score_codex":0.0005339435,"about_ca_topic_score_gemma":0.0008635564,"teacher_disagreement_score":0.9564649,"about_ca_system_score_codex":0.00013138217,"about_ca_system_score_gemma":0.00023287631,"threshold_uncertainty_score":0.4195189},"labels":[],"label_agreement":null},{"id":"W4414596705","doi":"10.1162/coli.a.24","title":"Are Formal and Functional Linguistic Mechanisms Dissociated in Language Models?","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"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":"Azrieli Foundation; Universiteit van Amsterdam; European Commission; Open Philanthropy Project","keywords":"Set (abstract data type); Formal language; Task (project management); Formal system; Theory; Formal methods; Functional approach","score_opus":0.021967691500343927,"score_gpt":0.2635182464301234,"score_spread":0.24155055492977948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414596705","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":[0.007967318,0.00018966003,0.98659617,0.00014991057,0.00094766053,0.000095572665,0.000008895476,0.00011034128,0.0039344975],"genre_scores_gemma":[0.87330014,0.0000017797644,0.12591255,0.00046863806,0.00012995726,0.0000068489685,0.00001966567,0.000005664737,0.0001547813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891865,0.000032420732,0.0002841092,0.0003114468,0.00023106948,0.0002222938],"domain_scores_gemma":[0.999087,0.00027882523,0.00010763222,0.00015983162,0.0003148062,0.00005193103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002267956,0.00012244104,0.00015691528,0.00019208067,0.00012970046,0.00010215702,0.00021206163,0.0000678721,0.0000026785015],"category_scores_gemma":[0.0014167604,0.00013479362,0.000029569032,0.00028223792,0.000026248454,0.00006735372,0.00023932898,0.00016804619,0.0000040058853],"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":[0.0000041281346,0.000029230481,0.00049446715,0.000021158963,0.000009029336,0.00002272272,0.00028521972,0.1975999,0.000003254254,0.8003232,0.00005353534,0.0011541552],"study_design_scores_gemma":[0.00024373179,0.00000501891,0.006684212,0.00003939684,0.0000040474147,0.0000015466321,0.000034881374,0.6147938,0.00000538279,0.378017,0.00009235023,0.00007867791],"about_ca_topic_score_codex":0.00002125413,"about_ca_topic_score_gemma":0.00002057064,"teacher_disagreement_score":0.8653328,"about_ca_system_score_codex":0.00007835047,"about_ca_system_score_gemma":0.00011761356,"threshold_uncertainty_score":0.5496724},"labels":[],"label_agreement":null},{"id":"W4416872671","doi":"10.1162/coli.a.583","title":"LLMs and Cultural Values: The Impact of Prompt Language and Explicit Cultural Framing","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":3,"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; Mila - Quebec Artificial Intelligence Institute","funders":"Canada First Research Excellence Fund","keywords":"Framing (construction); Cultural diversity; Cultural values; Cultural bias; Hofstede's cultural dimensions theory; Perspective (graphical); Set (abstract data type); Cultural issues; Cultural psychology","score_opus":0.031044744766767877,"score_gpt":0.43185472382640566,"score_spread":0.4008099790596378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416872671","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":[0.9730208,0.0012333799,0.012141925,0.00032769475,0.00021574195,0.00016980706,0.00001849625,0.000033146567,0.012839007],"genre_scores_gemma":[0.9884768,0.00002379628,0.010765174,0.000051517705,0.00028663094,0.000002944365,0.000020910167,0.0000028594582,0.00036934976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921244,0.00014185869,0.0001880487,0.00013551759,0.00021000659,0.0001121155],"domain_scores_gemma":[0.99825495,0.0010363291,0.00008711043,0.000050165705,0.000527157,0.00004429514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040244544,0.00008326643,0.0001422692,0.000055514905,0.00041672378,0.00009812474,0.00010329215,0.00003770181,0.000013920139],"category_scores_gemma":[0.0023977295,0.00005372548,0.00006705699,0.00026882562,0.00027611837,0.000032025244,0.00004826257,0.000087229615,8.936158e-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":[0.00002982253,0.00009440942,0.03414664,0.000066313834,0.0003587259,0.00000491444,0.0751088,0.035379402,0.00012684906,0.82593924,0.0015388966,0.027205968],"study_design_scores_gemma":[0.000684448,0.00009004586,0.32083395,0.00015010317,0.00021627617,0.0000038694757,0.025241515,0.2513372,0.000050082243,0.39663297,0.004390483,0.00036906195],"about_ca_topic_score_codex":0.0011060622,"about_ca_topic_score_gemma":0.000032417098,"teacher_disagreement_score":0.4293063,"about_ca_system_score_codex":0.000035342047,"about_ca_system_score_gemma":0.00013349087,"threshold_uncertainty_score":0.32051447},"labels":[],"label_agreement":null}]}