{"meta":{"query_hash":"84f0ed203413","filters":{"venue":"Language Resources and Evaluation"},"cohort_total":41,"direct_labels_cover":0,"predictions_cover":41,"exported":41,"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/84f0ed203413","api":"https://metacan.xera.ac/api/v1/cohort?venue=Language+Resources+and+Evaluation"},"results":[{"id":"W1921587136","doi":"10.1007/s10579-015-9318-3","title":"Cross level semantic similarity: an evaluation framework for universal measures of similarity","year":2015,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"European Research Council","keywords":"Computer science; Natural language processing; Similarity (geometry); Semantic similarity; Sentence; Task (project management); Artificial intelligence; Word (group theory); SemEval; Paragraph; Process (computing); Meaning (existential); WordNet; Information retrieval; Linguistics; Psychology; World Wide Web","score_opus":0.21232820109561595,"score_gpt":0.3869887300338786,"score_spread":0.17466052893826267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1921587136","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":[0.5476088,0.00057818973,0.45107195,0.00019131524,0.00009610457,0.00031733047,0.000006149855,0.00002857829,0.00010161671],"genre_scores_gemma":[0.9372215,0.000004252731,0.06250168,0.000072623654,0.00013379531,0.00001815306,0.000018912675,0.000007355911,0.00002169596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805176,0.00030171662,0.00022035636,0.00033270658,0.0009269362,0.00016654845],"domain_scores_gemma":[0.998542,0.000135312,0.00014386886,0.0004233865,0.000657859,0.0000975883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004648539,0.00010421853,0.00015427482,0.00008391269,0.00010717646,0.00013845834,0.00028217878,0.0001186903,0.000012352673],"category_scores_gemma":[0.0008957342,0.00009853405,0.000039134546,0.00014734964,0.000040851086,0.00042872454,0.00008647648,0.000090247144,8.0189346e-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":[0.00012247334,0.000149998,0.009041608,0.0001339356,0.00006718814,0.0000024769404,0.08972238,0.06784435,0.0011732565,0.014539617,0.00006871789,0.817134],"study_design_scores_gemma":[0.0008422256,0.000111830705,0.0069548143,0.00003536484,0.000064324355,0.0000024506217,0.0016868543,0.96618557,0.00060861144,0.02324813,0.00014039037,0.00011945353],"about_ca_topic_score_codex":0.00027872314,"about_ca_topic_score_gemma":0.0001448171,"teacher_disagreement_score":0.8983412,"about_ca_system_score_codex":0.0000732385,"about_ca_system_score_gemma":0.00013349789,"threshold_uncertainty_score":0.4018102},"labels":[],"label_agreement":null},{"id":"W1990825561","doi":"10.1007/s10579-008-9072-x","title":"Disambiguation of partial cognates","year":2008,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"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 Ottawa","funders":"","keywords":"Cognate; Computer science; Natural language processing; Meaning (existential); Context (archaeology); Artificial intelligence; Word (group theory); Word-sense disambiguation; Machine translation; Linguistics; Psychology; Biology","score_opus":0.024028377565879798,"score_gpt":0.3017247175024333,"score_spread":0.2776963399365535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990825561","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":[0.94173974,0.008320369,0.049173813,0.00018459695,0.000034798195,0.00013579869,0.0000011260122,0.0001229301,0.0002868133],"genre_scores_gemma":[0.9636712,0.000039892784,0.0361434,0.000042595108,0.000042497773,0.000010824168,0.0000068789327,0.0000037278708,0.00003899112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918044,0.00007650661,0.00014070897,0.00016092313,0.00035009452,0.00009135925],"domain_scores_gemma":[0.9995572,0.000047773072,0.00009920167,0.000171857,0.000096523385,0.000027419122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044216507,0.00006352308,0.000089193396,0.00006636569,0.0000812416,0.00002770664,0.00016385045,0.000041361807,0.000017894285],"category_scores_gemma":[0.00012938058,0.000051757008,0.000021344009,0.00016706374,0.000049450056,0.00023469023,0.000067052126,0.000049159687,0.0000019927131],"study_design_candidate":"design_other","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":[0.000031407562,0.00009097348,0.005521553,0.00009210053,0.000027759526,0.000018239276,0.06661563,0.000084189574,0.052208852,0.008218353,0.00031675896,0.8667742],"study_design_scores_gemma":[0.0015288669,0.00035174875,0.02841665,0.00019218371,0.000078203484,0.0001583942,0.0011444984,0.5958166,0.3489443,0.022076804,0.0007138376,0.0005779119],"about_ca_topic_score_codex":0.00009957244,"about_ca_topic_score_gemma":0.0000048961642,"teacher_disagreement_score":0.8661963,"about_ca_system_score_codex":0.000012564108,"about_ca_system_score_gemma":0.000019217689,"threshold_uncertainty_score":0.21105894},"labels":[],"label_agreement":null},{"id":"W2037256905","doi":"10.1007/s10579-014-9271-6","title":"A qualitative comparison method for rhetorical structures: identifying different discourse structures in multilingual corpora","year":2014,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Rhetorical question; Linguistics; Computer science; Natural language processing; Annotation; Translation (biology); Artificial intelligence; Contrastive linguistics; Applied linguistics; Philosophy","score_opus":0.08234689324121308,"score_gpt":0.47851651750124213,"score_spread":0.39616962426002905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037256905","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":[0.4539799,0.0023058937,0.5430584,0.00013170931,0.00008408455,0.0003342635,0.000003615298,0.00008810943,0.000014023136],"genre_scores_gemma":[0.6687624,0.0000026669043,0.331013,0.000049037328,0.00009020341,0.000041937834,0.00001949393,0.000009212013,0.000012051582],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977228,0.0006991182,0.00034839,0.00046894338,0.0005087679,0.00025196347],"domain_scores_gemma":[0.99862856,0.00066807185,0.000244284,0.0002777719,0.00011185091,0.000069483074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019482768,0.00019598479,0.0003163669,0.00018482521,0.00013761656,0.00025212902,0.000361049,0.00011042662,0.0000071851123],"category_scores_gemma":[0.0006850537,0.00014473719,0.00005655681,0.00019087527,0.000050199902,0.00023022543,0.00013883521,0.00020099588,3.5227606e-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":[0.00006557876,0.00004889168,0.00048153743,0.00015599401,0.000022987295,0.0000023849452,0.2505527,0.0002669537,0.0072479337,0.030015802,0.000058104768,0.7110811],"study_design_scores_gemma":[0.0011360934,0.00014987536,0.0025090966,0.000094290524,0.00004264941,0.000007781666,0.013789871,0.7848694,0.011527292,0.18548502,0.00006917815,0.00031950593],"about_ca_topic_score_codex":0.00022062055,"about_ca_topic_score_gemma":0.00019206734,"teacher_disagreement_score":0.7846024,"about_ca_system_score_codex":0.00007806121,"about_ca_system_score_gemma":0.00002034676,"threshold_uncertainty_score":0.59022117},"labels":[],"label_agreement":null},{"id":"W2062046281","doi":"10.1007/s10579-009-9083-2","title":"Classification of semantic relations between nominals","year":2009,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Task (project management); Natural language processing; SemEval; Sentence; Artificial intelligence; Process (computing); Semantic similarity; Linguistics","score_opus":0.030966356234334785,"score_gpt":0.33024747582626307,"score_spread":0.29928111959192827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062046281","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":[0.89353406,0.0059342496,0.09812055,0.0011463506,0.000016135738,0.00020161178,0.0000016586829,0.00014016392,0.00090520154],"genre_scores_gemma":[0.9510652,0.000007326876,0.048758067,0.000043739285,0.000046049834,0.000004657357,0.000010213655,0.000002784981,0.00006199342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991525,0.000093348994,0.00019235333,0.00017886375,0.0002910592,0.000091875896],"domain_scores_gemma":[0.9993939,0.000073620606,0.00015499917,0.00024362897,0.00010307359,0.000030777563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076963246,0.000067308414,0.00010599745,0.0001169362,0.00006912046,0.00006112283,0.00020271224,0.000058053905,0.000010949676],"category_scores_gemma":[0.00013075375,0.000057642275,0.00002425253,0.00024505705,0.000021548021,0.00025759533,0.000031094463,0.00006990705,0.000003494512],"study_design_candidate":"design_other","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":[0.000004782157,0.000029599423,0.004659724,0.00002809703,0.000010761627,0.0000013412254,0.012173713,0.000019206715,0.037116,0.010921169,0.00015157669,0.934884],"study_design_scores_gemma":[0.00065919996,0.00032283034,0.6593317,0.0002647887,0.00014444765,0.000015960082,0.0009841742,0.2325833,0.021041524,0.08393388,0.0003099826,0.00040823987],"about_ca_topic_score_codex":0.000021127486,"about_ca_topic_score_gemma":0.000003210391,"teacher_disagreement_score":0.9344758,"about_ca_system_score_codex":0.000022405704,"about_ca_system_score_gemma":0.00001810804,"threshold_uncertainty_score":0.23505838},"labels":[],"label_agreement":null},{"id":"W2250536124","doi":"","title":"Discovering frames in specialized domains","year":2014,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"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":"FrameNet; Computer science; Complement (music); Field (mathematics); Artificial intelligence; Natural language processing; Information retrieval; Parsing; Mathematics","score_opus":0.011399440839449463,"score_gpt":0.2946918213716688,"score_spread":0.2832923805322194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250536124","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":[0.8799372,0.0038799276,0.113835655,0.00034652743,0.000055016793,0.00015470755,4.2132956e-7,0.00015321745,0.0016373352],"genre_scores_gemma":[0.9282765,0.000016432534,0.07139755,0.00013867742,0.00010533826,0.000013472723,0.000002719397,0.0000053208882,0.000044000673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908215,0.00013409009,0.0001288321,0.00022367599,0.00029041286,0.0001408573],"domain_scores_gemma":[0.99959445,0.00007251545,0.00005833437,0.0002194221,0.000024304283,0.000030965653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009428695,0.00008015735,0.000106166284,0.00010633767,0.000055507273,0.0001869667,0.0002296711,0.000049496834,0.000016592703],"category_scores_gemma":[0.00020075271,0.00006549283,0.000018625034,0.00019572681,0.00002156511,0.00028395883,0.00011663298,0.00009111156,0.0000030642143],"study_design_candidate":"design_other","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":[0.000013489757,0.00002674073,0.0022633933,0.00004259739,0.0000057708835,0.000008337368,0.027243076,0.00009429877,0.0072712917,0.024013357,0.00006742362,0.93895024],"study_design_scores_gemma":[0.0024604057,0.00018273591,0.026946383,0.00039427797,0.000031676354,0.000034327117,0.0017546007,0.8076603,0.014453574,0.13833317,0.006969606,0.00077894516],"about_ca_topic_score_codex":0.00017937114,"about_ca_topic_score_gemma":0.00012855431,"teacher_disagreement_score":0.93817127,"about_ca_system_score_codex":0.000033173634,"about_ca_system_score_gemma":0.000009701909,"threshold_uncertainty_score":0.267072},"labels":[],"label_agreement":null},{"id":"W2251445713","doi":"","title":"Capturing syntactico-semantic regularities among terms: An application of the FrameNet methodology to terminology","year":2012,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"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":"FrameNet; Computer science; Terminology; Annotation; Focus (optics); Natural language processing; Artificial intelligence; Point (geometry); Resource (disambiguation); Lexicon; Computational linguistics; Semantics (computer science); Linguistics; Parsing; Programming language","score_opus":0.03784322549439183,"score_gpt":0.3385109969376508,"score_spread":0.30066777144325896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2251445713","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":[0.8573638,0.0018872891,0.13999069,0.0002745118,0.00006421138,0.00028117793,8.493574e-7,0.000079263016,0.000058202964],"genre_scores_gemma":[0.8916192,0.0000030577498,0.108074464,0.00015369475,0.000077152734,0.000045115896,0.000002416254,0.0000063994376,0.000018496385],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99875766,0.00042947088,0.00017097182,0.00020556644,0.00024664728,0.00018967691],"domain_scores_gemma":[0.9991478,0.00012275929,0.00015147297,0.0004695841,0.000055401128,0.000053029515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013666358,0.00009125408,0.00013535214,0.00009726585,0.0000949491,0.00005342451,0.00041235864,0.000094188305,0.000004600447],"category_scores_gemma":[0.00022710666,0.00006404249,0.000024594601,0.00016552018,0.00006731166,0.00036635148,0.00021727307,0.00010534785,8.860342e-7],"study_design_candidate":"design_other","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":[0.000017391842,0.00006947419,0.053729262,0.00013520908,0.000028318493,0.0000012709614,0.09192279,0.00006021436,0.11711879,0.012815761,0.000021970394,0.72407955],"study_design_scores_gemma":[0.00052553875,0.0002648601,0.50755155,0.00023601249,0.00020667336,0.00016137703,0.0060624066,0.08408744,0.36126077,0.038581185,0.00040546886,0.00065676053],"about_ca_topic_score_codex":0.0005302223,"about_ca_topic_score_gemma":0.00008389153,"teacher_disagreement_score":0.72342277,"about_ca_system_score_codex":0.000029369608,"about_ca_system_score_gemma":0.00000996426,"threshold_uncertainty_score":0.2611577},"labels":[],"label_agreement":null},{"id":"W2577349305","doi":"","title":"Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida.","year":2016,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"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 Alberta","funders":"","keywords":"Optical character recognition; Computer science; Character (mathematics); Language model; Unicode; Porting; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; Set (abstract data type); Image (mathematics)","score_opus":0.12266473322717336,"score_gpt":0.38797495915431435,"score_spread":0.265310225927141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577349305","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":[0.5494052,0.000020214133,0.44986635,0.00016343247,0.000012750772,0.00021591144,0.000015984739,0.000052324154,0.00024779956],"genre_scores_gemma":[0.89926636,0.000007110665,0.10041912,0.00007082118,0.000057101464,0.000106463944,0.000030938245,0.000007057726,0.000035041834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988783,0.00014900265,0.00025644427,0.00025810732,0.0003238359,0.00013433804],"domain_scores_gemma":[0.9991954,0.00015576436,0.00014464831,0.00020830099,0.0002371745,0.000058715555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019998343,0.00008227371,0.00014140774,0.000071189905,0.000058497997,0.00005442922,0.00013358574,0.000062401625,0.000020489093],"category_scores_gemma":[0.00013206212,0.00005870962,0.000043256747,0.00005849314,0.0000320948,0.0004420023,0.00003415371,0.00003743924,0.0000014750748],"study_design_candidate":"design_other","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":[0.000009485324,0.00003286807,0.00010664787,0.000016577904,0.000006971291,1.9982068e-7,0.0044937325,0.000008503348,0.022796053,0.00028420988,0.0000015533025,0.9722432],"study_design_scores_gemma":[0.00093292934,0.00022495356,0.009958346,0.00010819838,0.00003125879,0.0000049847913,0.00051712815,0.9643353,0.011937032,0.01172173,0.000038334612,0.0001897604],"about_ca_topic_score_codex":0.000019042835,"about_ca_topic_score_gemma":0.000073229814,"teacher_disagreement_score":0.9720534,"about_ca_system_score_codex":0.000034000364,"about_ca_system_score_gemma":0.000045718807,"threshold_uncertainty_score":0.23941088},"labels":[],"label_agreement":null},{"id":"W2582792602","doi":"","title":"Detecting semantic changes in Alzheimer’s disease with vector space models","year":2016,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"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; Natural language processing; Artificial intelligence; Disease; Space (punctuation); Medicine; Pathology","score_opus":0.0302507815983099,"score_gpt":0.2936973496375037,"score_spread":0.2634465680391938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582792602","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":[0.98966235,0.008432244,0.0007140879,0.000929485,0.00001798872,0.00011660869,0.000003817025,0.00001263516,0.00011079421],"genre_scores_gemma":[0.9993069,0.0001328157,0.0002911251,0.000056690234,0.00010046468,0.000024566134,0.000008170007,0.000008217091,0.00007100725],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993995,0.00006825114,0.000061539184,0.00019834383,0.00013957056,0.00013278623],"domain_scores_gemma":[0.99973965,0.00002460837,0.00003623901,0.00012074001,0.000022966664,0.000055813933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028709683,0.00007446145,0.000070118185,0.00003271942,0.000034531997,0.0000126021005,0.00004417519,0.000054551172,0.000013140426],"category_scores_gemma":[0.00010700326,0.000043621432,0.000012265754,0.000046546003,0.00005514201,0.0000027649523,0.000031667136,0.000026709338,0.0000011874426],"study_design_candidate":"design_other","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":[0.00035499723,0.00003644964,0.011143621,0.00003220103,0.000056456403,0.000015978452,0.0026714278,0.00015230736,0.14161809,0.000019177434,0.00007297522,0.84382635],"study_design_scores_gemma":[0.019835852,0.005002838,0.5175943,0.0028372235,0.0014272963,0.00013977487,0.025351258,0.12851296,0.27112934,0.002140297,0.022680301,0.003348539],"about_ca_topic_score_codex":0.000053263608,"about_ca_topic_score_gemma":0.00055425504,"teacher_disagreement_score":0.84047776,"about_ca_system_score_codex":0.000006392933,"about_ca_system_score_gemma":0.000016665008,"threshold_uncertainty_score":0.17788303},"labels":[],"label_agreement":null},{"id":"W2583305969","doi":"10.1007/s10579-017-9383-x","title":"RST Signalling Corpus: a corpus of signals of coherence relations","year":2017,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Treebank; Annotation; Corpus linguistics; Natural language processing; Computer science; Parsing; Coherence (philosophical gambling strategy); Artificial intelligence; Text corpus; Linguistics; British National Corpus","score_opus":0.030780822958553684,"score_gpt":0.3193694584320568,"score_spread":0.2885886354735031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583305969","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":[0.90489393,0.013620656,0.07961407,0.00023170424,0.0000503868,0.0002979668,0.0000068659906,0.00008407338,0.0012003598],"genre_scores_gemma":[0.94462776,0.000024335115,0.05514988,0.000016750764,0.000027202977,0.000010301144,0.0000037236327,0.0000052528417,0.00013481073],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989318,0.00008717026,0.000251595,0.00020337828,0.0004169203,0.0001090938],"domain_scores_gemma":[0.99858946,0.00011099066,0.00057045696,0.00044902027,0.00024429627,0.000035776207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009737079,0.00008691274,0.00016841663,0.0000862018,0.00019039768,0.00012280211,0.00054403377,0.00006672897,0.00002835179],"category_scores_gemma":[0.00043700708,0.00007379581,0.00003706739,0.00009930004,0.00010791847,0.00035751692,0.0001652716,0.000087002794,0.0000014458774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003539021,0.0000795824,0.006584845,0.00020364007,0.000049336093,0.000009851588,0.02293183,0.0003563767,0.40307337,0.008786154,0.00011279542,0.5577768],"study_design_scores_gemma":[0.0014264773,0.0004817624,0.020250788,0.0013944227,0.00017767753,0.0000339379,0.0010127905,0.4388496,0.47515547,0.06036011,0.00026219757,0.00059474556],"about_ca_topic_score_codex":0.00033433954,"about_ca_topic_score_gemma":0.000034809367,"teacher_disagreement_score":0.5571821,"about_ca_system_score_codex":0.000015838483,"about_ca_system_score_gemma":0.000041445233,"threshold_uncertainty_score":0.3009306},"labels":[],"label_agreement":null},{"id":"W2896826757","doi":"10.1007/s10579-018-9430-2","title":"VERTa: a linguistic approach to automatic machine translation evaluation","year":2018,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"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":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Alberta-Pacific Forest Industries","keywords":"Metric (unit); Computer science; Machine translation; Natural language processing; Variety (cybernetics); Artificial intelligence; Linguistics; Engineering","score_opus":0.030387430137635726,"score_gpt":0.32967932798055893,"score_spread":0.2992918978429232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896826757","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":[0.27439386,0.015961187,0.7005414,0.00050982786,0.00020637161,0.0014691781,0.0000036156068,0.0006882392,0.0062263473],"genre_scores_gemma":[0.73129785,0.0000030740207,0.26819906,0.0001879124,0.00018337468,0.00007200095,0.000022110053,0.000009359922,0.000025241596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998081,0.0002486102,0.00022733546,0.0004103941,0.000834307,0.00019832612],"domain_scores_gemma":[0.99905163,0.00006839908,0.00009724451,0.00036880776,0.0003298882,0.000084051775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022618112,0.00014425973,0.00013959224,0.00019886218,0.0001879458,0.00023716279,0.00031688993,0.00007584579,0.000038368606],"category_scores_gemma":[0.00050259265,0.000121662415,0.00002963949,0.0004712407,0.00003635996,0.00024137303,0.000076526456,0.00009440009,0.00001873319],"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":[0.00000868506,0.000032564072,0.000035415575,0.000040709405,0.0000103657685,7.146752e-7,0.03481027,0.000052438638,0.0019454177,0.0007063916,0.000076149256,0.96228087],"study_design_scores_gemma":[0.0003631843,0.00011523949,0.00056192925,0.000057319827,0.000057708683,0.000013468915,0.00015612462,0.99290407,0.0012997828,0.0039525395,0.00034933287,0.00016932475],"about_ca_topic_score_codex":0.00012861757,"about_ca_topic_score_gemma":0.000041087278,"teacher_disagreement_score":0.9928516,"about_ca_system_score_codex":0.0000780308,"about_ca_system_score_gemma":0.00004767184,"threshold_uncertainty_score":0.49612492},"labels":[],"label_agreement":null},{"id":"W3028657247","doi":"","title":"A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Robustness (evolution); Hyperparameter; Word (group theory); Artificial intelligence; Grid; Stability (learning theory); Unsupervised learning; Machine learning; Natural language processing; Mathematics","score_opus":0.0626216750026778,"score_gpt":0.3642289984244982,"score_spread":0.3016073234218204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028657247","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":[0.2960221,0.0012413345,0.69993836,0.0014249231,0.000064963155,0.00051897165,9.816877e-7,0.00012881526,0.0006595262],"genre_scores_gemma":[0.34952986,0.000011349364,0.64944,0.0005197074,0.00030474813,0.000042077474,0.000004672603,0.000018900142,0.0001286868],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975189,0.00050543406,0.00041307727,0.0007482059,0.0005404448,0.00027396838],"domain_scores_gemma":[0.99840796,0.0004959538,0.0003015329,0.00046665958,0.00026097972,0.00006690686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058367667,0.00016651966,0.00025637558,0.00007682934,0.0002887269,0.00030924554,0.00050931866,0.000086805936,0.00005749528],"category_scores_gemma":[0.0012520024,0.00013096814,0.00010038685,0.00039157443,0.00002301015,0.00023597633,0.0002585585,0.00021541507,0.0000044758967],"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":[0.000074766765,0.000024749468,0.00044617415,0.00029008545,0.00007966516,0.00000385946,0.17928182,0.48835292,0.005684498,0.0008056504,0.0000778367,0.32487798],"study_design_scores_gemma":[0.00059701066,0.000106438754,0.00025890768,0.000063099906,0.00007157078,0.0000137543375,0.00528372,0.9872324,0.0019843697,0.00041684744,0.0038158265,0.0001560798],"about_ca_topic_score_codex":0.00012104622,"about_ca_topic_score_gemma":0.0000051198126,"teacher_disagreement_score":0.49887946,"about_ca_system_score_codex":0.000031804768,"about_ca_system_score_gemma":0.00006371574,"threshold_uncertainty_score":0.5340725},"labels":[],"label_agreement":null},{"id":"W3028807070","doi":"","title":"Extraction of Hyponymic Relations in French with Knowledge-Pattern-Based Word Sketches.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"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 du Québec","funders":"","keywords":"Computer science; Sketch; Natural language processing; Artificial intelligence; Word (group theory); Grammar; Domain (mathematical analysis); Thesaurus; Process (computing); Information extraction; Information retrieval; Linguistics","score_opus":0.021142584555562678,"score_gpt":0.29778985129183766,"score_spread":0.276647266736275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028807070","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":[0.8229669,0.0058702175,0.1694433,0.00101336,0.000017090468,0.00022791149,0.0000014237908,0.00011987594,0.00033993847],"genre_scores_gemma":[0.9570439,0.000004552476,0.042761672,0.00010242213,0.00003373023,0.000019332963,0.00000799592,0.0000065499394,0.000019859794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910295,0.00011906921,0.00017625929,0.00023805216,0.00025948763,0.00010417119],"domain_scores_gemma":[0.9994798,0.0001055578,0.00012448902,0.00016405563,0.00008392951,0.00004221911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040991604,0.00008867979,0.00011638751,0.00012272847,0.00003970956,0.000051277093,0.0001796665,0.00005804223,0.000028714727],"category_scores_gemma":[0.00010728896,0.00007225348,0.00001875021,0.00046515005,0.000028409067,0.000236833,0.000039435443,0.00013737314,0.0000033019267],"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":[0.000030858984,0.000089053734,0.011181783,0.00015302602,0.000012897384,0.000013804841,0.043431923,0.0010062797,0.017287055,0.00016898413,0.00013845193,0.9264859],"study_design_scores_gemma":[0.000989933,0.00019764455,0.037751406,0.000264191,0.000035527064,0.0000087384915,0.0006499444,0.94340783,0.015321043,0.0008715929,0.00025613667,0.00024602553],"about_ca_topic_score_codex":0.00018885016,"about_ca_topic_score_gemma":0.00015646491,"teacher_disagreement_score":0.9424015,"about_ca_system_score_codex":0.000036428977,"about_ca_system_score_gemma":0.000054733624,"threshold_uncertainty_score":0.29464114},"labels":[],"label_agreement":null},{"id":"W3029096252","doi":"","title":"A Lexicon-Based Approach for Detecting Hedges in Informal Text","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Hedge; Lexicon; Natural language processing; Sentence; Interview; Artificial intelligence; Part-of-speech tagging; Linguistics; Part of speech; Sociology","score_opus":0.03137950489801756,"score_gpt":0.300703666162043,"score_spread":0.2693241612640255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029096252","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":[0.27040702,0.0045158025,0.7232941,0.00072614005,0.000015204558,0.00049400906,0.0000016008964,0.00022948266,0.00031664313],"genre_scores_gemma":[0.73553586,0.00000128697,0.26385075,0.0004824114,0.000054226577,0.000057562702,0.000007724808,0.000005239978,0.000004902719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991583,0.000056483947,0.00015931998,0.00023874038,0.00022454049,0.00016260531],"domain_scores_gemma":[0.99959874,0.00008936315,0.000080834514,0.00012691591,0.00005498562,0.000049188315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070219114,0.00009185033,0.00011082989,0.00008488895,0.00007442343,0.00015992232,0.00023953785,0.00006043341,0.0000037100137],"category_scores_gemma":[0.00033924103,0.00007815137,0.000027968072,0.0002637224,0.000017561437,0.00027267417,0.00007236953,0.00010265678,6.81299e-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":[0.000051726645,0.000021839181,0.00073327887,0.00024278191,0.0000060373573,0.0000026542093,0.035087135,0.0017171641,0.006821169,0.00067213475,0.000035920948,0.95460814],"study_design_scores_gemma":[0.0005279567,0.0000895242,0.00027572407,0.000026011176,0.000006467237,0.00000226209,0.0008388279,0.98826206,0.009349185,0.00037653247,0.00012852119,0.00011693778],"about_ca_topic_score_codex":0.000038169102,"about_ca_topic_score_gemma":0.000011740613,"teacher_disagreement_score":0.9865449,"about_ca_system_score_codex":0.000020103833,"about_ca_system_score_gemma":0.000040460774,"threshold_uncertainty_score":0.31869206},"labels":[],"label_agreement":null},{"id":"W3029265130","doi":"","title":"Multilingual Dictionary Based Construction of Core Vocabulary.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"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 British Columbia","funders":"","keywords":"Computer science; Vocabulary; Natural language processing; Core (optical fiber); Artificial intelligence; Set (abstract data type); Bilingual dictionary; Field (mathematics); Resource (disambiguation); Machine translation; Linguistics; Programming language","score_opus":0.028694671351722077,"score_gpt":0.3027328626012327,"score_spread":0.2740381912495106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029265130","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":[0.8814127,0.00689925,0.11011294,0.0008683192,0.000056930305,0.00021617136,0.00000485066,0.00026192324,0.00016692324],"genre_scores_gemma":[0.8237203,0.000007697978,0.17591599,0.00026433053,0.000064263484,0.0000062436006,0.000012568716,0.0000047420567,0.0000039250535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991015,0.000066175046,0.00016447254,0.00022302265,0.00035660056,0.00008821044],"domain_scores_gemma":[0.99950045,0.000055591463,0.00012327018,0.00014748618,0.00011964891,0.000053543845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032092162,0.00008095968,0.00010766535,0.00006053844,0.0000631257,0.00003888663,0.00017793308,0.000057219324,0.00002909522],"category_scores_gemma":[0.0001419278,0.00007070444,0.000029474402,0.00022383696,0.000054435626,0.00016989166,0.00006831094,0.00008845132,0.0000014643136],"study_design_candidate":"design_other","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":[0.00004722909,0.00002751455,0.0019323209,0.00012792327,0.0000159695,0.00001079689,0.014417854,0.00024076986,0.037082378,0.0015776664,0.00009510119,0.94442445],"study_design_scores_gemma":[0.0005740243,0.00016279743,0.0011465853,0.000063629195,0.00003147709,0.000017709383,0.00076359743,0.9300492,0.065114975,0.0016311185,0.0002903273,0.00015455592],"about_ca_topic_score_codex":0.00003461879,"about_ca_topic_score_gemma":0.0000021097994,"teacher_disagreement_score":0.9442699,"about_ca_system_score_codex":0.000014479017,"about_ca_system_score_gemma":0.000037389742,"threshold_uncertainty_score":0.28832433},"labels":[],"label_agreement":null},{"id":"W3029614628","doi":"","title":"CantoMap: a Hong Kong Cantonese MapTask Corpus.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Geographic Information Systems Studies","field":"Social Sciences","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 du Québec à Montréal","funders":"","keywords":"Transcription (linguistics); Computer science; Utterance; Annotation; Natural language processing; Phonetic transcription; Phonology; Artificial intelligence; Task (project management); Speech recognition; Linguistics; Engineering","score_opus":0.03570656174926953,"score_gpt":0.31776180215982264,"score_spread":0.2820552404105531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029614628","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":[0.96039444,0.0023680008,0.000037469566,0.003576588,0.00010158433,0.0003812645,0.000007721489,0.00008741,0.033045545],"genre_scores_gemma":[0.9987488,0.00016242772,0.000053138923,0.00041185,0.00030540844,0.000025303276,0.000009711624,0.000005405699,0.0002779851],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99865735,0.0001709338,0.00018337644,0.00013655155,0.00066043,0.00019133944],"domain_scores_gemma":[0.9994912,0.000057166875,0.000112546855,0.000077531964,0.0001457983,0.00011574104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011574487,0.000078611665,0.00012241784,0.000055749348,0.00046351674,0.000107840366,0.00008583909,0.000053222844,0.00014862588],"category_scores_gemma":[0.000301626,0.00006986825,0.000033011805,0.00030095142,0.00010460702,0.0001748315,0.00003863443,0.000060463783,0.000034356726],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019036337,0.0000075322096,0.027174946,0.00004988758,0.00003864629,0.000004847843,0.9121115,0.000045481465,0.00018058914,0.0012068859,0.0009166814,0.058243953],"study_design_scores_gemma":[0.0015437835,0.000101569465,0.110343285,0.000084104846,0.0001287219,0.000005368853,0.7005152,0.012776148,0.000055239485,0.00023285826,0.17377338,0.00044032282],"about_ca_topic_score_codex":0.012715577,"about_ca_topic_score_gemma":0.006530082,"teacher_disagreement_score":0.21159628,"about_ca_system_score_codex":0.00003358179,"about_ca_system_score_gemma":0.000043379354,"threshold_uncertainty_score":0.9938588},"labels":[],"label_agreement":null},{"id":"W3029712483","doi":"","title":"Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Word (group theory); Computer science; Language model; Natural language processing; Artificial intelligence; Indigenous language; Linguistics; Indigenous","score_opus":0.04360119139160799,"score_gpt":0.3828779568686983,"score_spread":0.3392767654770903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029712483","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":[0.9738932,0.0047564963,0.020414589,0.00029136482,0.000024153247,0.00033084615,0.0000060753364,0.0001417455,0.00014149972],"genre_scores_gemma":[0.9816262,0.000031155243,0.01795025,0.0002443197,0.00009966587,0.000015023172,0.000015520513,0.0000099051795,0.000007924223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841017,0.00016435215,0.00033359602,0.00026177053,0.0006273326,0.0002027601],"domain_scores_gemma":[0.99897695,0.00020027898,0.00030633822,0.00025921786,0.00017871257,0.00007849462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015566788,0.00016904986,0.00017577957,0.00010053363,0.00019217457,0.00043227692,0.000339213,0.00008413292,0.000014609587],"category_scores_gemma":[0.0005190167,0.000113530274,0.00006366464,0.00034242938,0.00006589433,0.00072187965,0.00018107897,0.00022573983,0.0000029401733],"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":[0.0001417316,0.000017105851,0.00043125247,0.000115405855,0.000034859648,0.000003390391,0.14526998,0.03314385,0.011465976,0.00030715752,0.000062397856,0.80900687],"study_design_scores_gemma":[0.0004286174,0.00031304653,0.00078556465,0.000095503325,0.000024523746,0.000009737882,0.0012508346,0.9856439,0.01040249,0.0008774888,0.0000122697675,0.00015601452],"about_ca_topic_score_codex":0.00031676286,"about_ca_topic_score_gemma":0.0000058987075,"teacher_disagreement_score":0.95250005,"about_ca_system_score_codex":0.000040298444,"about_ca_system_score_gemma":0.000053448483,"threshold_uncertainty_score":0.462963},"labels":[],"label_agreement":null},{"id":"W3029889931","doi":"","title":"The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"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 British Columbia","funders":"","keywords":"Computer science; Natural language processing; Variety (cybernetics); Representation (politics); Linguistics; Corpus linguistics; Parallel corpora; Pronoun; Artificial intelligence; Information retrieval; History; Machine translation; Philosophy","score_opus":0.04572153790965464,"score_gpt":0.29345114168665953,"score_spread":0.2477296037770049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029889931","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":[0.21575175,0.008942667,0.7533713,0.01834793,0.00014095247,0.0010577344,0.000011275596,0.0007873097,0.0015890843],"genre_scores_gemma":[0.94144267,0.0009410963,0.056806255,0.0005364575,0.00017622251,0.000015168116,0.00001892144,0.0000070065357,0.000056209843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924934,0.00011053958,0.00008782236,0.00021466376,0.00021378812,0.0001238394],"domain_scores_gemma":[0.9994751,0.00015378294,0.000075713906,0.0001433523,0.00010277099,0.000049248636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004986699,0.000072982984,0.000073808,0.000070731876,0.00029556477,0.00018717203,0.00030487322,0.000052450472,0.000005249361],"category_scores_gemma":[0.00025183684,0.00004942688,0.000029716883,0.0004232268,0.00004152854,0.00034356496,0.00011485198,0.00007105064,0.0000027744104],"study_design_candidate":"design_other","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":[0.00011335616,0.000023308981,0.00019742061,0.000048624224,0.000020923351,0.00000850193,0.027681861,0.00007008603,0.003805647,0.029904183,0.0019951605,0.93613094],"study_design_scores_gemma":[0.0013163636,0.00076407543,0.00088760455,0.0000627971,0.00008872807,0.000012279902,0.007898438,0.7067691,0.014417841,0.012341758,0.25494006,0.0005009186],"about_ca_topic_score_codex":0.000088213914,"about_ca_topic_score_gemma":0.00006377166,"teacher_disagreement_score":0.93563,"about_ca_system_score_codex":0.000023651855,"about_ca_system_score_gemma":0.00002247071,"threshold_uncertainty_score":0.22732751},"labels":[],"label_agreement":null},{"id":"W3029927342","doi":"","title":"Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Transformer; Encoder; Computer science; Sentence; Artificial intelligence; Language model; Natural language processing; Feature selection; Selection (genetic algorithm); Engineering; Voltage","score_opus":0.057425820451554886,"score_gpt":0.309027963334743,"score_spread":0.25160214288318816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029927342","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":[0.4152704,0.00023514066,0.5829093,0.0011704499,0.000023370181,0.00029117224,0.0000017972968,0.000039048475,0.000059326063],"genre_scores_gemma":[0.97600573,0.0000063270113,0.022802955,0.0010421906,0.00007169878,0.00004767693,0.000008584572,0.0000068516583,0.000007995477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988823,0.00009105614,0.00021629993,0.00034782678,0.0002866925,0.00017582187],"domain_scores_gemma":[0.9996323,0.000064629865,0.0000468318,0.00010031888,0.000094857074,0.00006109245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007529304,0.000098089586,0.00013503605,0.000059580776,0.000081539525,0.000092437804,0.00013643382,0.000061842344,0.000016983693],"category_scores_gemma":[0.00012690264,0.00009208454,0.000040647945,0.00018435223,0.000009908582,0.00027402188,0.000014799587,0.00009040017,9.403873e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021857177,0.00006847989,0.001456871,0.00021847851,0.000025507452,0.0000034745624,0.1247628,0.5823465,0.035507206,0.0006980278,0.00006988762,0.2546242],"study_design_scores_gemma":[0.0011448511,0.000048254606,0.00007407389,0.000027024385,0.000013872339,0.0000010981113,0.0009591128,0.9965039,0.0006629552,0.00027620094,0.00017767014,0.00011100466],"about_ca_topic_score_codex":0.00017339055,"about_ca_topic_score_gemma":0.00011378808,"teacher_disagreement_score":0.56073534,"about_ca_system_score_codex":0.000034360273,"about_ca_system_score_gemma":0.00003601439,"threshold_uncertainty_score":0.37550986},"labels":[],"label_agreement":null},{"id":"W3029985558","doi":"","title":"The Nunavut Hansard Inuktitut-English Parallel Corpus 3.0 with Preliminary Machine Translation Results.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Sentence; Machine translation; Indigenous; Natural language processing; Indigenous language; Linguistics; Artificial intelligence; Speech recognition","score_opus":0.021495609075024055,"score_gpt":0.266804596939113,"score_spread":0.24530898786408895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029985558","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":[0.22672457,0.20836149,0.5281528,0.02646733,0.00027442363,0.0025680652,0.000041745316,0.0022475661,0.0051619913],"genre_scores_gemma":[0.92682976,0.00012945448,0.072278336,0.00043787627,0.0001663515,0.00004248713,0.000035592693,0.000013277045,0.00006684927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985309,0.00017609069,0.0002179338,0.00035500212,0.0005361178,0.00018392687],"domain_scores_gemma":[0.999167,0.00016667374,0.00014488396,0.00029467937,0.00014692893,0.00007983297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080733065,0.00014274554,0.000120749835,0.00003648587,0.00028656295,0.00035527442,0.00041243926,0.00006632825,0.000005408998],"category_scores_gemma":[0.00023825692,0.00008716647,0.000028825183,0.00029058976,0.00006623735,0.00038365682,0.000080382895,0.00019450132,0.0000025483657],"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":[0.0005256292,0.000017379372,0.00013421627,0.0000434204,0.000023882114,0.000018736855,0.0631484,0.00042814334,0.00053392944,0.0008345634,0.0003808679,0.93391085],"study_design_scores_gemma":[0.0021776415,0.00093021785,0.0011177392,0.00012544652,0.00008804892,0.000032996646,0.001576946,0.9750209,0.0022890992,0.0017602678,0.014456155,0.0004245375],"about_ca_topic_score_codex":0.000069828944,"about_ca_topic_score_gemma":0.000089556255,"teacher_disagreement_score":0.97459275,"about_ca_system_score_codex":0.000022766739,"about_ca_system_score_gemma":0.000035490022,"threshold_uncertainty_score":0.35545453},"labels":[],"label_agreement":null},{"id":"W3029996834","doi":"","title":"Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Chinese history and philosophy","field":"Social Sciences","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":"Lexicon; Computer science; Dominance (genetics); License; Focus (optics); Semantics (computer science); Linguistics; Natural language processing; History; Classical Chinese; Space (punctuation); Corpus linguistics; Artificial intelligence","score_opus":0.03543237694785305,"score_gpt":0.3434333187503363,"score_spread":0.3080009418024832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029996834","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":[0.9796237,0.005091895,0.00011298803,0.00037312548,0.00008782918,0.00013028797,0.000013829142,0.00002532821,0.0145410495],"genre_scores_gemma":[0.9992406,0.0000211695,0.00005838035,0.00017141755,0.00036190357,0.0000050177878,0.000024206605,0.0000056404974,0.000111691],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9988701,0.0002265545,0.00015909375,0.00017394913,0.00048234867,0.00008799863],"domain_scores_gemma":[0.9995086,0.00009822063,0.00011383754,0.00010228576,0.00007704989,0.00009995807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005585013,0.00008080676,0.00018452693,0.0000798527,0.00019686809,0.000018899596,0.00008461551,0.000043431224,0.0005998648],"category_scores_gemma":[0.0003284507,0.000068345464,0.00008711715,0.0006078966,0.00011199979,0.0000772497,0.000020620588,0.000057559915,0.00000393195],"study_design_candidate":"qualitative","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":[0.000103345585,0.00003903744,0.06952887,0.00006233724,0.00023795136,0.00000465393,0.9201532,0.0018699871,0.0010462705,0.00172897,0.00014298019,0.005082421],"study_design_scores_gemma":[0.008631343,0.0006343219,0.44568914,0.0000704619,0.008187454,0.000004006549,0.057980925,0.2888829,0.0000695714,0.05160351,0.13601185,0.0022344901],"about_ca_topic_score_codex":0.0013694855,"about_ca_topic_score_gemma":0.0011364328,"teacher_disagreement_score":0.86217225,"about_ca_system_score_codex":0.000058003025,"about_ca_system_score_gemma":0.00003702308,"threshold_uncertainty_score":0.6568099},"labels":[],"label_agreement":null},{"id":"W3030000665","doi":"","title":"FAB: The French Absolute Beginner Corpus for Pronunciation Training.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Pronunciation; Context (archaeology); Natural language processing; Set (abstract data type); Partition (number theory); Artificial intelligence; Training set; Speech recognition; Word (group theory); Linguistics; Mathematics","score_opus":0.10830507150931382,"score_gpt":0.37666659247843487,"score_spread":0.268361520969121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030000665","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":[0.98493177,0.004538592,0.0004195269,0.0064631016,0.00013826933,0.00071656617,0.00002133652,0.00002835157,0.0027425108],"genre_scores_gemma":[0.9977614,0.000014108211,0.000089812835,0.0007261169,0.00042680308,0.0002059513,0.000045261084,0.000012075364,0.00071842724],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9990823,0.00016280741,0.00012909538,0.00021378216,0.00021370477,0.00019829093],"domain_scores_gemma":[0.99947876,0.00017332351,0.00007106359,0.00014215343,0.00007711688,0.000057602643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088926876,0.000075361175,0.00009772825,0.000027198203,0.0001486269,0.000042913955,0.00010935929,0.00007942798,0.00039367567],"category_scores_gemma":[0.0001935672,0.000052221505,0.000034067078,0.00010703449,0.000056835353,0.000024110264,0.000025407853,0.00011814621,0.000035154673],"study_design_candidate":"qualitative","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":[0.0001415286,0.000030083738,0.0006837281,0.000031214968,0.00009392446,0.0000023842956,0.5691436,0.00007745116,0.002951798,0.00036675634,0.009864007,0.41661355],"study_design_scores_gemma":[0.005942931,0.0014998112,0.59769917,0.00003867273,0.0003361275,0.000030273966,0.035935137,0.20433766,0.00040428262,0.0054045944,0.14782639,0.0005449659],"about_ca_topic_score_codex":0.00023940658,"about_ca_topic_score_gemma":0.000120215234,"teacher_disagreement_score":0.59701544,"about_ca_system_score_codex":0.000012495101,"about_ca_system_score_gemma":0.00002522498,"threshold_uncertainty_score":0.43104726},"labels":[],"label_agreement":null},{"id":"W3030151190","doi":"","title":"Evaluating Approaches to Personalizing Language Models","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Perplexity; Computer science; Language model; Personalization; Artificial intelligence; Natural language processing; Adaptation (eye); Word (group theory); World Wide Web","score_opus":0.3079769636386057,"score_gpt":0.34640647007214864,"score_spread":0.038429506433542926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030151190","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":[0.7205886,0.002067743,0.27273768,0.0027774454,0.000028414828,0.00025935876,0.0000010945387,0.000101531936,0.0014381224],"genre_scores_gemma":[0.9282846,0.000002865739,0.07033808,0.0010690201,0.0002187771,0.000028215467,0.0000043976556,0.000009453503,0.000044612974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846196,0.0001598153,0.00016734443,0.00042986494,0.0005870679,0.00019397128],"domain_scores_gemma":[0.99946725,0.000054081498,0.00005693877,0.00024178006,0.00003571631,0.00014425925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010539148,0.00011046872,0.00012528554,0.000052519546,0.00011407849,0.00018884381,0.00028035181,0.000040341147,0.000025764606],"category_scores_gemma":[0.00014820648,0.000100911195,0.000033852535,0.00021126396,0.000009500902,0.0002837761,0.000203755,0.000088782515,0.000015122417],"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":[0.000008581416,0.000008421223,0.00006473602,0.000039998413,0.000012625212,0.000004365577,0.33552355,0.09157415,0.0044406992,0.0024732896,0.000034319895,0.56581527],"study_design_scores_gemma":[0.0002463419,0.000057550238,0.000115775874,0.000021933542,0.000015724836,0.0000039209986,0.007921465,0.99072254,0.00031447108,0.00037954416,0.00007342746,0.00012732222],"about_ca_topic_score_codex":0.00008509235,"about_ca_topic_score_gemma":0.000008988974,"teacher_disagreement_score":0.8991484,"about_ca_system_score_codex":0.000028657461,"about_ca_system_score_gemma":0.000025144835,"threshold_uncertainty_score":0.4115039},"labels":[],"label_agreement":null},{"id":"W3030267806","doi":"","title":"On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Pooling; Computer science; Benchmark (surveying); Artificial intelligence; Dimension (graph theory); Representation (politics); Set (abstract data type); Spoken language; Identification (biology); Machine learning; Selection (genetic algorithm); Language model; Natural language processing; Test set; Mathematics","score_opus":0.0337936629644121,"score_gpt":0.28381202723240906,"score_spread":0.25001836426799695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030267806","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":[0.98614466,0.00022335013,0.010416672,0.0017008992,0.000026492224,0.0003523841,0.00001073084,0.000037868143,0.0010869495],"genre_scores_gemma":[0.99689966,0.0000090568155,0.0022800658,0.00059075677,0.00007462371,0.000041942032,0.000009801497,0.0000055018495,0.00008859824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991698,0.000080331,0.00015946466,0.00018677655,0.00030592407,0.00009766883],"domain_scores_gemma":[0.9993379,0.0002729423,0.00008774473,0.0001801766,0.00007699589,0.000044245095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078153284,0.000070153284,0.00009105584,0.000049724775,0.00010404372,0.00014247822,0.00022625405,0.00002576356,0.00021144816],"category_scores_gemma":[0.00021811521,0.0000495952,0.000034824407,0.00016739975,0.000020152218,0.0001481586,0.000035769895,0.00004119432,0.000046282898],"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":[0.00008078053,0.00003887194,0.00007601148,0.000109693756,0.000044062734,0.0000015580857,0.08896527,0.0015222152,0.09817736,0.003704509,0.000872997,0.8064067],"study_design_scores_gemma":[0.00030026486,0.00017767784,0.0021961597,0.00005144296,0.000033235345,0.0000023737348,0.008244388,0.93428034,0.053732812,0.0003457523,0.00049948867,0.00013608721],"about_ca_topic_score_codex":0.000017901344,"about_ca_topic_score_gemma":0.000004471851,"teacher_disagreement_score":0.9327581,"about_ca_system_score_codex":0.000009531365,"about_ca_system_score_gemma":0.000023001588,"threshold_uncertainty_score":0.2315209},"labels":[],"label_agreement":null},{"id":"W3030307641","doi":"","title":"An Analysis of Massively Multilingual Neural Machine Translation for Low-Resource Languages.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"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 British Columbia","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Artificial intelligence; Set (abstract data type); Resource (disambiguation); Massively parallel; Programming language","score_opus":0.028529584331923822,"score_gpt":0.33911117094096893,"score_spread":0.3105815866090451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030307641","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":[0.67702687,0.0125376545,0.30895555,0.0006776242,0.000014906578,0.0004556866,0.000048230017,0.00024258734,0.000040855917],"genre_scores_gemma":[0.92181975,0.0000048568827,0.07754623,0.00032777523,0.000071571005,0.000020079566,0.00019367659,0.000011257321,0.0000048334596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986143,0.00015171853,0.000274765,0.00039103997,0.0004043756,0.0001637997],"domain_scores_gemma":[0.99917984,0.00013556439,0.00019758723,0.00025691508,0.00013174313,0.00009832048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006032512,0.0001407594,0.00026103735,0.00020393192,0.00008318379,0.00010600212,0.0003689756,0.000080934115,0.000016313383],"category_scores_gemma":[0.0001624353,0.00012087656,0.00010347773,0.0006247695,0.00003456083,0.00030471568,0.000045340006,0.00009446658,3.8532434e-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":[0.0000959764,0.000048094123,0.0006330395,0.00011772335,0.00013423829,0.000004982102,0.04686682,0.004692921,0.04473345,0.00023120384,0.000015368358,0.9024262],"study_design_scores_gemma":[0.0004711415,0.00015220178,0.0007918029,0.000013424133,0.000317104,0.0000013068534,0.00095262,0.98604673,0.010961682,0.00007178991,0.00007887412,0.00014131617],"about_ca_topic_score_codex":0.00008912192,"about_ca_topic_score_gemma":0.000050333543,"teacher_disagreement_score":0.9813538,"about_ca_system_score_codex":0.000016870634,"about_ca_system_score_gemma":0.000017779434,"threshold_uncertainty_score":0.4929203},"labels":[],"label_agreement":null},{"id":"W3030379882","doi":"","title":"On the Creation of a Corpus for Coherence Evaluation of Discursive Units","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Bank of Canada; National Bank of Canada","funders":"","keywords":"Computer science; Coherence (philosophical gambling strategy); Natural language processing; Artificial intelligence; Sentence; Argument (complex analysis); Focus (optics); Classifier (UML); Linguistics; Textual entailment; Logical consequence; Mathematics","score_opus":0.05399198577407965,"score_gpt":0.33059146662545824,"score_spread":0.2765994808513786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030379882","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":[0.9004104,0.005382247,0.09077033,0.0018346693,0.000030102161,0.0011707847,0.000014075544,0.000051193845,0.000336164],"genre_scores_gemma":[0.992542,0.000006610713,0.007191289,0.0001398028,0.000027841681,0.00006784746,0.000014085153,0.0000042656434,0.0000062051904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987492,0.0002210793,0.0001675063,0.00016988229,0.0006204004,0.000071933704],"domain_scores_gemma":[0.9985774,0.00031658242,0.00024425972,0.00017835958,0.0006590853,0.000024277591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014720141,0.00007014058,0.00010553958,0.00004106939,0.000057918573,0.00003419262,0.00024076314,0.000038074395,0.0000152120265],"category_scores_gemma":[0.001669672,0.000045137414,0.000023306546,0.0003152666,0.0000451323,0.00011977693,0.00004695754,0.000051375748,4.1023287e-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":[0.00009923928,0.000036483703,0.00013106315,0.00014072724,0.000031573552,3.0036176e-7,0.054520242,0.0007156392,0.038004708,0.03769985,0.00029130757,0.86832887],"study_design_scores_gemma":[0.0006651152,0.0004293285,0.0006366202,0.00014242058,0.00011462994,0.0000012880189,0.0015621226,0.875591,0.09011885,0.030576695,0.00005447091,0.00010749625],"about_ca_topic_score_codex":0.000039050698,"about_ca_topic_score_gemma":0.000008061206,"teacher_disagreement_score":0.8748753,"about_ca_system_score_codex":0.00002014944,"about_ca_system_score_gemma":0.00005250784,"threshold_uncertainty_score":0.1998874},"labels":[],"label_agreement":null},{"id":"W3030512995","doi":"","title":"Evaluating Sub-word Embeddings in Cross-lingual Models.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","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 New Brunswick","funders":"","keywords":"Computer science; Word (group theory); Natural language processing; Artificial intelligence; Lexicon; Task (project management); Space (punctuation); Vocabulary; Resource (disambiguation); Linguistics","score_opus":0.08551581455221315,"score_gpt":0.37443450547402246,"score_spread":0.28891869092180933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030512995","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":[0.9574541,0.0016614407,0.03932577,0.0005991943,0.000056095232,0.00021418309,7.247127e-7,0.000084347506,0.0006041463],"genre_scores_gemma":[0.98624283,0.000013107629,0.013098585,0.00042932454,0.00017099101,0.000015674701,0.000003863263,0.000008594588,0.00001701184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983926,0.00014278345,0.0002626626,0.00042678855,0.00056313525,0.00021206359],"domain_scores_gemma":[0.9994675,0.00007161105,0.000086569366,0.00021153947,0.000079105135,0.000083661165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014663548,0.00010851535,0.00013495304,0.00006573172,0.00008554028,0.00024543182,0.00027002927,0.000059635997,0.000019977155],"category_scores_gemma":[0.00026802308,0.00010437136,0.000029703055,0.00025067443,0.000019137915,0.0004189084,0.00017839686,0.00013958184,0.000007602949],"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":[0.000018680388,0.000013716725,0.0015663389,0.000041127107,0.00000683233,0.000010797225,0.09973284,0.22427788,0.0046676253,0.0007513145,0.000011571632,0.66890126],"study_design_scores_gemma":[0.000565826,0.000041416464,0.0016107395,0.000028971122,0.000007016303,0.000003555546,0.0007098564,0.99466896,0.0006486962,0.0015602298,0.000033328633,0.00012142244],"about_ca_topic_score_codex":0.00012229176,"about_ca_topic_score_gemma":0.000027435251,"teacher_disagreement_score":0.77039105,"about_ca_system_score_codex":0.00003843964,"about_ca_system_score_gemma":0.00004019452,"threshold_uncertainty_score":0.42561406},"labels":[],"label_agreement":null},{"id":"W3030811146","doi":"","title":"Language Modeling with a General Second-Order RNN.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"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 du Québec à Montréal","funders":"","keywords":"Recurrent neural network; Computer science; Multiplicative function; Treebank; Language model; State space; State (computer science); Artificial intelligence; Space (punctuation); Sequence (biology); Artificial neural network; Algorithm; Mathematics; Statistics; Parsing","score_opus":0.030082924266851083,"score_gpt":0.2736927433707653,"score_spread":0.24360981910391424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030811146","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":[0.64460385,0.0012028404,0.3525272,0.00065552734,0.000017854187,0.000109342516,8.7393505e-7,0.00006934238,0.0008131657],"genre_scores_gemma":[0.9581193,0.000005131705,0.040598366,0.0009346282,0.00023157572,0.000012293397,0.000006237512,0.000009024469,0.00008349287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898326,0.00007101252,0.00012610973,0.00031429194,0.00034795707,0.00015733646],"domain_scores_gemma":[0.9995769,0.000016353764,0.00004394786,0.0002153553,0.00006011083,0.000087326414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002993016,0.00009745761,0.00010521934,0.000034927823,0.000075685326,0.00013819618,0.0001883864,0.00003725946,0.00008935911],"category_scores_gemma":[0.000032351414,0.00007692558,0.000018300349,0.00016742588,0.000010140031,0.00020797431,0.00009064284,0.00008910006,0.000008619442],"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":[0.000048782196,0.00003058681,0.0005323814,0.00011902749,0.000064174295,0.000057289053,0.2741372,0.26312345,0.009830733,0.0034403931,0.00010680059,0.4485092],"study_design_scores_gemma":[0.00033850214,0.000047159585,0.00008691903,0.000012812797,0.000013180355,0.000009138699,0.0017665966,0.9970929,0.00024451458,0.00008775234,0.00018654551,0.00011397185],"about_ca_topic_score_codex":0.000102072736,"about_ca_topic_score_gemma":0.000055302266,"teacher_disagreement_score":0.73396945,"about_ca_system_score_codex":0.0000144995565,"about_ca_system_score_gemma":0.000028347045,"threshold_uncertainty_score":0.3136934},"labels":[],"label_agreement":null},{"id":"W3031043157","doi":"","title":"WEXEA: Wikipedia EXhaustive Entity Annotation","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","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 Alberta","funders":"","keywords":"Computer science; Annotation; Hyperlink; Information retrieval; Entity linking; Named-entity recognition; Relationship extraction; Natural language processing; Task (project management); Publication; Information extraction; Named entity; Relation (database); Artificial intelligence; World Wide Web; Web page; Knowledge base; Database","score_opus":0.033941972694160195,"score_gpt":0.2878343625034358,"score_spread":0.2538923898092756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031043157","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":[0.8502939,0.00091094925,0.14598356,0.001428636,0.00006635437,0.00014518073,9.831158e-7,0.00007449655,0.0010959523],"genre_scores_gemma":[0.9928231,0.000013174771,0.0064735347,0.00042311556,0.00021621294,0.000008212893,0.000006243842,0.0000032792143,0.00003309222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920356,0.000061353516,0.00010614965,0.00023252414,0.00030183076,0.00009458626],"domain_scores_gemma":[0.99967307,0.000025623709,0.000053154636,0.00012777408,0.00005892515,0.000061483435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003437254,0.000059835635,0.00006748402,0.000027122449,0.00006709217,0.000103302744,0.0001286043,0.0000307348,0.000034455934],"category_scores_gemma":[0.0000874877,0.000055258304,0.000017356539,0.00013158905,0.00001136007,0.0002536369,0.00007543446,0.00005758767,0.000018579802],"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":[0.000018298693,0.000024216795,0.0045703975,0.000063801344,0.000023084196,0.000011250429,0.15798476,0.0040763053,0.004772296,0.0034552075,0.0005018791,0.8244985],"study_design_scores_gemma":[0.00031841313,0.00003811624,0.010613201,0.0000090581925,0.000015546906,0.0000018190036,0.001153165,0.986012,0.00035813695,0.00045247382,0.000940656,0.00008744989],"about_ca_topic_score_codex":0.000056529494,"about_ca_topic_score_gemma":0.0000095977375,"teacher_disagreement_score":0.9819357,"about_ca_system_score_codex":0.0000156371,"about_ca_system_score_gemma":0.000015027988,"threshold_uncertainty_score":0.22533682},"labels":[],"label_agreement":null},{"id":"W3031229455","doi":"","title":"SEDAR: a Large Scale French-English Financial Domain Parallel Corpus","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"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":"Machine translation; Computer science; Domain (mathematical analysis); Preprocessor; Natural language processing; Sentence; Translation (biology); Artificial intelligence; Scale (ratio); Speech recognition; Chemistry","score_opus":0.011982349944706733,"score_gpt":0.26276082289982794,"score_spread":0.25077847295512123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031229455","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":[0.67501503,0.01966318,0.30042943,0.0021127367,0.00014639692,0.00047781135,0.000015335409,0.0008217991,0.001318256],"genre_scores_gemma":[0.80651784,0.000023577511,0.19128463,0.0016243285,0.0004207074,0.000034668545,0.000022116712,0.000011791967,0.000060364928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854064,0.00014492236,0.00018419328,0.00039493604,0.00048714073,0.00024815518],"domain_scores_gemma":[0.999359,0.000041988027,0.000106619125,0.0002424413,0.00013074937,0.00011917162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006982129,0.00013961464,0.00016098461,0.000054592354,0.0001599816,0.00023001479,0.00039549908,0.0000986356,0.00004327601],"category_scores_gemma":[0.0003135253,0.00012015929,0.00004441828,0.000319001,0.00003141639,0.00032930815,0.00021936069,0.00018156524,0.000009422372],"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":[0.00007444064,0.00013768778,0.0028270367,0.00023173813,0.000031804535,0.000105771,0.439784,0.00008844609,0.0076673124,0.011940919,0.010077098,0.52703375],"study_design_scores_gemma":[0.007512795,0.0011648933,0.012213031,0.00040624943,0.0001749114,0.00008084433,0.008321859,0.78968567,0.008396556,0.07013818,0.09958011,0.0023249157],"about_ca_topic_score_codex":0.000049558632,"about_ca_topic_score_gemma":0.000048283066,"teacher_disagreement_score":0.7895972,"about_ca_system_score_codex":0.000027656912,"about_ca_system_score_gemma":0.000047379785,"threshold_uncertainty_score":0.48999536},"labels":[],"label_agreement":null},{"id":"W3031309641","doi":"","title":"Temporal Histories of Epidemic Events (THEE): A Case Study in Temporal Annotation for Public Health","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; University of Toronto","funders":"","keywords":"Annotation; Computer science; Metadata; Domain (mathematical analysis); Event (particle physics); Public domain; Information retrieval; Process (computing); Temporal annotation; Style (visual arts); Natural language processing; Artificial intelligence; World Wide Web; History; Natural language","score_opus":0.10611195314227607,"score_gpt":0.38414537583421693,"score_spread":0.27803342269194087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031309641","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":[0.99428046,0.0027481087,0.00074713863,0.0017054019,0.000029481396,0.00046056992,0.0000132595405,0.000008119857,0.00000747237],"genre_scores_gemma":[0.9986964,0.0000114549175,0.0008579012,0.00016678753,0.00007841443,0.00004650302,0.00011945737,0.0000065535364,0.000016564109],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99909157,0.00021464512,0.0002422631,0.00019711025,0.0001356061,0.000118781776],"domain_scores_gemma":[0.99962854,0.000029180477,0.0001415449,0.00008566205,0.00005264641,0.00006242514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001103155,0.00007124977,0.00015026583,0.000037057696,0.000045051624,0.000006926432,0.000048053902,0.000060463142,0.0000043063005],"category_scores_gemma":[0.00051884993,0.00006129262,0.000027900074,0.00008931877,0.00003601295,0.0000038618095,0.000028524923,0.00004009085,1.3834551e-7],"study_design_candidate":"qualitative","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":[0.00033251604,0.00034160385,0.44086957,0.00028980998,0.00008480895,0.00003073954,0.119596645,0.000083565734,0.0072778123,0.000009623271,0.0007852736,0.43029803],"study_design_scores_gemma":[0.020773252,0.019543286,0.15785365,0.00014696362,0.00021544391,0.0002783679,0.6555247,0.07044589,0.0018309951,0.00024476342,0.07191181,0.0012309247],"about_ca_topic_score_codex":0.0005714019,"about_ca_topic_score_gemma":0.0007684382,"teacher_disagreement_score":0.535928,"about_ca_system_score_codex":0.000018216071,"about_ca_system_score_gemma":0.000067351946,"threshold_uncertainty_score":0.24994406},"labels":[],"label_agreement":null},{"id":"W3032025286","doi":"","title":"Cifu: a Frequency Lexicon of Hong Kong Cantonese.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":10,"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 du Québec à Montréal","funders":"","keywords":"Lexicon; Computer science; Lexical database; Word lists by frequency; Natural language processing; Lexical diversity; Artificial intelligence; Linguistics; Word (group theory); Phonology; Speech recognition; Vocabulary","score_opus":0.0484546324202565,"score_gpt":0.34967562486616527,"score_spread":0.3012209924459088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032025286","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":[0.9654391,0.0008908827,0.00016535452,0.0029616156,0.00009270228,0.00016680869,0.0000049780115,0.000027025617,0.030251535],"genre_scores_gemma":[0.99882597,0.00003903075,0.00031199693,0.0003371142,0.00035283284,0.0000046696277,0.000009114796,0.0000038888484,0.00011536416],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99915963,0.00020622676,0.00012991969,0.00011803791,0.00028449044,0.0001017154],"domain_scores_gemma":[0.9996209,0.00006411186,0.00008758479,0.00005460763,0.00009988269,0.000072881616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071916083,0.000043459917,0.000091635775,0.000027259326,0.000111165275,0.00002132361,0.00006186598,0.00005370418,0.0007047836],"category_scores_gemma":[0.0011263039,0.000040139774,0.000020885745,0.00012443934,0.000073068884,0.000039363822,0.000015501253,0.00004366959,0.0000074073123],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036290185,0.00003418645,0.032189757,0.0000608727,0.00003861334,0.000011834184,0.86332136,0.00006005712,0.014151415,0.04181497,0.00046744966,0.047813166],"study_design_scores_gemma":[0.0077675353,0.0009131889,0.30350256,0.00025401654,0.0008329482,0.000013621409,0.5191343,0.05179376,0.004616823,0.020743735,0.08894236,0.0014852042],"about_ca_topic_score_codex":0.0054058973,"about_ca_topic_score_gemma":0.0011485049,"teacher_disagreement_score":0.3441871,"about_ca_system_score_codex":0.000018249018,"about_ca_system_score_gemma":0.000085005006,"threshold_uncertainty_score":0.81721354},"labels":[],"label_agreement":null},{"id":"W3032097118","doi":"","title":"Multilingual Corpus Creation for Multilingual Semantic Similarity Task","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"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 Waterloo; Western University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Semantic similarity; Similarity (geometry); Sentence; Focus (optics); Information retrieval","score_opus":0.04671167661381604,"score_gpt":0.32804333242450934,"score_spread":0.2813316558106933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032097118","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":[0.80382043,0.0008858159,0.19372952,0.0008247023,0.00008797162,0.00042715145,0.000005159732,0.000104769584,0.000114457514],"genre_scores_gemma":[0.98002803,0.000009841014,0.019092096,0.00046503672,0.00031560624,0.000024249282,0.000022411765,0.000008750627,0.00003397029],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987983,0.00009159589,0.00020941741,0.0003913254,0.00033707384,0.00017224805],"domain_scores_gemma":[0.9993408,0.00014349537,0.00009551755,0.00020464619,0.00012436915,0.000091212125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065113296,0.00010946026,0.0001359102,0.00004005731,0.00013915481,0.00013486594,0.00019545754,0.00006697531,0.000008505257],"category_scores_gemma":[0.0005390021,0.00010255018,0.000044908047,0.00010836732,0.000020019277,0.00016947079,0.000087345616,0.000080811194,0.000004162205],"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":[0.000043515036,0.000032894106,0.00107606,0.00010736337,0.000021942213,0.00000533914,0.07613178,0.0075434055,0.009864903,0.00027492156,0.000045652712,0.9048522],"study_design_scores_gemma":[0.00080591644,0.00007386634,0.0011249287,0.000016640672,0.00003159022,0.0000032043347,0.0008750768,0.9926744,0.0031424956,0.00024297244,0.0008877255,0.00012115133],"about_ca_topic_score_codex":0.000102041064,"about_ca_topic_score_gemma":0.000037520647,"teacher_disagreement_score":0.985131,"about_ca_system_score_codex":0.000022696378,"about_ca_system_score_gemma":0.000035010227,"threshold_uncertainty_score":0.41818747},"labels":[],"label_agreement":null},{"id":"W3032201847","doi":"","title":"SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"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 British Columbia","funders":"","keywords":"Computer science; Transcription (linguistics); Spice; Sentence; Annotation; Natural language processing; Speech corpus; Storyboard; Phonetic transcription; Speech recognition; Linguistics; Artificial intelligence; Speech synthesis; Multimedia; Engineering","score_opus":0.04815606913529093,"score_gpt":0.3652228133420278,"score_spread":0.31706674420673686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032201847","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":[0.98669326,0.0079293735,0.0034119443,0.0012132598,0.000039172082,0.00035792164,0.0000035562537,0.00006750745,0.00028398988],"genre_scores_gemma":[0.9626037,0.000041103256,0.036772877,0.000431999,0.000097977376,0.000005641415,0.000008711297,0.000005686111,0.000032317446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990151,0.00008361334,0.00019054534,0.00028577042,0.00031936896,0.00010560143],"domain_scores_gemma":[0.99946654,0.00007437942,0.00012480182,0.0001358997,0.00011750838,0.00008088714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005656009,0.00008767751,0.00015152003,0.0000826334,0.00003322471,0.00033809937,0.0005612857,0.00005208274,0.000044276007],"category_scores_gemma":[0.00047620045,0.00007642994,0.000011981733,0.00035494898,0.000035668345,0.0008995893,0.0005676495,0.00009661028,4.3209658e-7],"study_design_candidate":"design_other","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":[0.00012718566,0.000049434635,0.014366356,0.00021638369,0.000021419943,0.000049066446,0.15078177,0.00007364901,0.0115736015,0.0054319734,0.00030077324,0.8170084],"study_design_scores_gemma":[0.010037861,0.00097402267,0.057601962,0.00076066784,0.00013858918,0.00010533676,0.010462067,0.7991656,0.08504624,0.029624984,0.004557213,0.001525424],"about_ca_topic_score_codex":0.0022432944,"about_ca_topic_score_gemma":0.00026444544,"teacher_disagreement_score":0.815483,"about_ca_system_score_codex":0.000022066988,"about_ca_system_score_gemma":0.0001478117,"threshold_uncertainty_score":0.3391205},"labels":[],"label_agreement":null},{"id":"W3032216439","doi":"","title":"Fine-grained Morphosyntactic Analysis and Generation Tools for More Than One Thousand Languages.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"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 British Columbia","funders":"","keywords":"Computer science; Natural language processing; Security token; Metric (unit); Artificial intelligence; Machine translation; Parallel corpora; Linguistics; Engineering","score_opus":0.04463166772679519,"score_gpt":0.3218636676018755,"score_spread":0.2772319998750803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032216439","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":[0.6865679,0.009259092,0.29973406,0.003740316,0.000014606979,0.00042943857,0.000012994044,0.00020021667,0.000041365016],"genre_scores_gemma":[0.8926434,0.00002939947,0.106368855,0.00057516707,0.00019249813,0.000053041098,0.00009771516,0.000010079508,0.000029867013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883217,0.000089387795,0.00017816055,0.00040525472,0.00033465755,0.00016039624],"domain_scores_gemma":[0.99932784,0.00013410226,0.00012343974,0.00021584469,0.00010824165,0.00009050396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055839244,0.00013407276,0.00020732176,0.00012768127,0.0001420304,0.0004685094,0.00018841024,0.00007521122,0.000016700402],"category_scores_gemma":[0.00046811058,0.00011476567,0.000056979294,0.00047902946,0.000029872022,0.0004770698,0.00009886998,0.00008376241,7.9702295e-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":[0.000062704465,0.000049807844,0.002035508,0.00023033084,0.0003725397,0.000015215404,0.04952738,0.00020228181,0.124470495,0.0017645626,0.0004601154,0.82080907],"study_design_scores_gemma":[0.00078578136,0.00018737743,0.0045367116,0.00003145165,0.00063557446,0.000008360171,0.0010188508,0.9554849,0.036051754,0.00064687536,0.00027344443,0.0003388987],"about_ca_topic_score_codex":0.00009388574,"about_ca_topic_score_gemma":0.00010813027,"teacher_disagreement_score":0.9552826,"about_ca_system_score_codex":0.000021226622,"about_ca_system_score_gemma":0.000018203467,"threshold_uncertainty_score":0.46800083},"labels":[],"label_agreement":null},{"id":"W3032420555","doi":"","title":"Cooking Up a Neural-based Model for Recipe Classification","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","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":"Concordia University; Bank of Canada; Université du Québec à Montréal; Polytechnique Montréal; National Bank of Canada","funders":"","keywords":"Embedding; Computer science; Task (project management); Artificial intelligence; Layer (electronics); Macro; Artificial neural network; Recipe; Natural language processing; Language model; Deep learning; State (computer science); Machine learning; Pattern recognition (psychology); Algorithm; Engineering","score_opus":0.1262190574827426,"score_gpt":0.33255425756928014,"score_spread":0.20633520008653755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032420555","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":[0.27072105,0.00030937803,0.7256548,0.0028659648,0.000037950624,0.0002364797,0.0000014278156,0.0000634689,0.00010950378],"genre_scores_gemma":[0.97829634,0.0000024619885,0.020505445,0.0009925546,0.00010344211,0.00004414546,0.000011218438,0.000005851404,0.00003851421],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992118,0.000052816766,0.00013262338,0.00026274117,0.00023284374,0.000107159314],"domain_scores_gemma":[0.9995732,0.00005922535,0.000069895956,0.00017371876,0.00007003523,0.00005394648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004236827,0.00006427943,0.00007333424,0.00003052684,0.000088775305,0.000104098785,0.00015660145,0.00003647521,0.0000048166985],"category_scores_gemma":[0.00012154125,0.000059403887,0.00002719682,0.00009318389,0.000008457097,0.00013842317,0.00003108847,0.000045249275,0.0000016217149],"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":[0.000037671853,0.000012290212,0.00021771935,0.000073259165,0.000008003473,6.568968e-7,0.038132254,0.3101797,0.009951029,0.002190327,0.00022815913,0.6389689],"study_design_scores_gemma":[0.00041913637,0.000027565506,0.00020726315,0.000009619907,0.000012322407,4.556525e-7,0.00025463803,0.9982149,0.00022506107,0.0003207457,0.00023664247,0.00007167744],"about_ca_topic_score_codex":0.000009418794,"about_ca_topic_score_gemma":0.000007773088,"teacher_disagreement_score":0.7075753,"about_ca_system_score_codex":0.000018768553,"about_ca_system_score_gemma":0.000026149068,"threshold_uncertainty_score":0.24224202},"labels":[],"label_agreement":null},{"id":"W3032491810","doi":"","title":"GM-RKB WikiText Error Correction Task and Baselines.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Error detection and correction; Artificial intelligence; Natural language processing; Task (project management); Language model; Ground truth; Speech recognition; Information retrieval; Machine learning; Algorithm","score_opus":0.021723023275288137,"score_gpt":0.2949398695453348,"score_spread":0.27321684627004666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032491810","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":[0.7818754,0.04119306,0.16804305,0.0065735145,0.0002654354,0.00054077624,0.000004727102,0.0007315506,0.00077251386],"genre_scores_gemma":[0.96648145,0.000048636433,0.031969804,0.00120481,0.00018355604,0.000014607672,0.000015924366,0.0000083720915,0.00007283807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989866,0.00010680925,0.0001406548,0.00032867267,0.00030866687,0.00012861275],"domain_scores_gemma":[0.99953294,0.00005897475,0.000083983854,0.00015358483,0.00008066073,0.000089861256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004935308,0.00010874019,0.00011197911,0.00005754086,0.000114035705,0.00019862589,0.00016649191,0.00006400943,0.000034849472],"category_scores_gemma":[0.00026317104,0.00009067075,0.00001976035,0.0002433908,0.00003124597,0.00032704603,0.00012994054,0.00011913655,0.000005391306],"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":[0.000021142945,0.000013070989,0.00033762315,0.00005748226,0.000009670541,0.000010073697,0.023817379,0.00004586246,0.011301088,0.00027919683,0.0027620983,0.9613453],"study_design_scores_gemma":[0.00046095165,0.00015256781,0.0014231243,0.00006755063,0.000038511967,0.00004290437,0.0010524482,0.9863434,0.0044728406,0.0010693076,0.004614589,0.0002618301],"about_ca_topic_score_codex":0.00009913586,"about_ca_topic_score_gemma":0.000017960865,"teacher_disagreement_score":0.9862975,"about_ca_system_score_codex":0.00001772309,"about_ca_system_score_gemma":0.000017639157,"threshold_uncertainty_score":0.3697446},"labels":[],"label_agreement":null},{"id":"W3032504444","doi":"","title":"PhonBank and Data Sharing: Recent Developments in European Portuguese","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Portuguese; Computer science; Data sharing; Data science","score_opus":0.12966803402925817,"score_gpt":0.3399750691332857,"score_spread":0.2103070351040275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032504444","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":[0.9861171,0.0059873373,0.0019522237,0.001663189,0.000043303273,0.00013881101,0.0000015025217,0.000056127938,0.004040352],"genre_scores_gemma":[0.99462295,0.00043128102,0.0042759785,0.00057343015,0.000044720764,0.0000020050652,0.000025333571,0.0000042694746,0.000020062897],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991092,0.000086904045,0.00013074355,0.00037178214,0.00019553868,0.00010579975],"domain_scores_gemma":[0.99957746,0.000025098625,0.000042497773,0.00028402935,0.000018691839,0.000052220817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096716266,0.00006222428,0.00007755815,0.000033662145,0.00003517757,0.00010013951,0.0004361233,0.00001713196,0.0000125193965],"category_scores_gemma":[0.00021768363,0.000052190313,0.0000041410417,0.00013355773,0.000014567359,0.00020597909,0.0007263126,0.000050193008,0.0000073746864],"study_design_candidate":"design_other","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":[0.0000067993874,0.000010396372,0.01490134,0.000018266612,0.000006559451,0.000034005832,0.026698263,0.000012502597,0.0003225409,0.0001488338,0.00019019669,0.9576503],"study_design_scores_gemma":[0.0009136865,0.000049454233,0.7193,0.00004973863,0.0000145521535,0.0000151603645,0.0025362864,0.265954,0.00016667799,0.0002578858,0.010535287,0.00020732042],"about_ca_topic_score_codex":0.000054140844,"about_ca_topic_score_gemma":0.000046248297,"teacher_disagreement_score":0.957443,"about_ca_system_score_codex":0.000008346256,"about_ca_system_score_gemma":0.000013358926,"threshold_uncertainty_score":0.21282592},"labels":[],"label_agreement":null},{"id":"W3122399969","doi":"10.1007/s10579-020-09519-z","title":"Exploring the role of lexis and grammar for the stable identification of register in an unrestricted corpus of web documents","year":2021,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Brockhouse Institute for Materials Research; Brock University","funders":"National Science Foundation of Sri Lanka; Social Sciences and Humanities Research Council of Canada; Turun Yliopisto; Emil Aaltosen Säätiö; AGE-WELL; National Science Foundation","keywords":"Lexis; Register (sociolinguistics); Computer science; Natural language processing; Variation (astronomy); Artificial intelligence; Corpus linguistics; Identification (biology); Linguistics; Text corpus","score_opus":0.05024759076246877,"score_gpt":0.3165752133910301,"score_spread":0.26632762262856136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122399969","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":[0.9805016,0.014374313,0.004705509,0.00011532081,0.000022069144,0.00024299813,0.0000041426024,0.000012035239,0.0000220365],"genre_scores_gemma":[0.99425155,0.000165795,0.0054918085,0.00000873835,0.000013128545,0.00003837658,0.0000063641946,0.0000033119966,0.000020945763],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992399,0.00011789233,0.00021551803,0.00013354838,0.00022653914,0.00006657093],"domain_scores_gemma":[0.99918246,0.0001627846,0.00020498851,0.00026549707,0.00017349576,0.000010773439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094628846,0.00004665173,0.00008821138,0.000054646738,0.000044637756,0.000054919125,0.00018553581,0.000020643607,0.0000013471797],"category_scores_gemma":[0.0001737624,0.000029411196,0.0000155272,0.00025433704,0.00004024344,0.00029922774,0.0000748471,0.00004058191,2.2407379e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003621254,0.000041346477,0.0035884362,0.000122768,0.000015909287,6.5661646e-7,0.023630489,0.0001059782,0.29074824,0.0029641679,0.0000049794803,0.6787408],"study_design_scores_gemma":[0.00083167106,0.00015116522,0.035649512,0.00021128013,0.00008356016,0.000007637528,0.008954267,0.28838992,0.6504436,0.014756891,0.00037619108,0.000144288],"about_ca_topic_score_codex":0.0002895359,"about_ca_topic_score_gemma":0.0001374528,"teacher_disagreement_score":0.6785965,"about_ca_system_score_codex":0.000010406009,"about_ca_system_score_gemma":0.000027738552,"threshold_uncertainty_score":0.11993538},"labels":[],"label_agreement":null},{"id":"W4285793742","doi":"10.1007/s10579-022-09602-7","title":"Speech acts in the Dutch COVID-19 Press Conferences","year":2022,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":25,"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":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Speech act; Computer science; Metadata; Linguistics; Reciprocal; Coronavirus disease 2019 (COVID-19); Direct speech; Natural language processing; Mean reciprocal rank; Artificial intelligence; Classifier (UML); Transformer; British National Corpus; World Wide Web; Medicine; Philosophy","score_opus":0.07035566898821673,"score_gpt":0.3433580144822387,"score_spread":0.27300234549402197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285793742","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":[0.98899275,0.0010897631,0.0027610606,0.0043673594,0.0000530876,0.0003953821,0.0000052084465,0.000035791454,0.002299572],"genre_scores_gemma":[0.9987834,0.000014118334,0.0002451121,0.0007540997,0.000028175558,0.00009432803,0.000016749307,0.00000164206,0.00006233972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983601,0.000660178,0.00012548204,0.00021719046,0.00052795786,0.00010909271],"domain_scores_gemma":[0.9993416,0.00024300048,0.00006161502,0.00029482273,0.000022373837,0.000036573434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023728167,0.000055348548,0.00006367545,0.000046011228,0.00024427916,0.0001566095,0.00042841383,0.00002048951,0.00008311733],"category_scores_gemma":[0.00017805184,0.000039969444,0.0000162361,0.00020023751,0.000027204742,0.00011885684,0.00011969925,0.00010854483,0.0000018225094],"study_design_candidate":"design_other","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":[0.000044009466,0.00022049202,0.008580747,0.0000722308,0.000013159212,0.00002467424,0.40206158,0.0058054356,0.0009459436,0.02996774,0.0012337456,0.5510303],"study_design_scores_gemma":[0.0015810891,0.00032104342,0.18366334,0.000012172772,0.000038780774,0.00015403844,0.07491803,0.47305793,0.00032817308,0.01562825,0.24985869,0.00043844982],"about_ca_topic_score_codex":0.0014163691,"about_ca_topic_score_gemma":0.00048282038,"teacher_disagreement_score":0.5505918,"about_ca_system_score_codex":0.00005352507,"about_ca_system_score_gemma":0.000077206016,"threshold_uncertainty_score":0.21411358},"labels":[],"label_agreement":null},{"id":"W4393949820","doi":"10.1007/s10579-024-09720-4","title":"Depression symptoms modelling from social media text: an LLM driven semi-supervised learning approach","year":2024,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Mental Health via Writing","field":"Psychology","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Alberta Machine Intelligence Institute","keywords":"Social media; Depression (economics); Psychology; Artificial intelligence; Computer science; Cognitive psychology; Natural language processing; World Wide Web","score_opus":0.053996650337715724,"score_gpt":0.36384960739755323,"score_spread":0.3098529570598375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393949820","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":[0.98087335,0.010033188,0.0028024355,0.000044422686,0.00022195892,0.0002867736,0.00001580096,0.0001832268,0.005538828],"genre_scores_gemma":[0.9972106,0.000018569443,0.0007841751,0.000055334207,0.0011787033,0.00007070693,0.0005066467,0.00004081881,0.00013441751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979627,0.00057229854,0.00025953405,0.0004835551,0.00044786828,0.00027402266],"domain_scores_gemma":[0.9994142,0.00024585612,0.00006654857,0.00014083022,0.000028470562,0.00010411392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009681821,0.00014512509,0.00016842899,0.00010244861,0.00029423597,0.00012864596,0.000096290154,0.00017690365,0.00081989495],"category_scores_gemma":[0.000027720978,0.00013251911,0.000041947453,0.00012895309,0.000032236687,0.00014872564,0.00004612488,0.00032092,0.0000510794],"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":[0.000076225355,0.0000771964,0.0030114728,0.00012497367,0.00005105239,0.0000143814705,0.40194434,0.007915939,0.0019197457,0.00012156764,0.00008015382,0.584663],"study_design_scores_gemma":[0.0005503915,0.00004410802,0.0045469753,0.00013405681,0.00008637151,0.000007099923,0.040682558,0.95324993,0.000038284044,0.00015213001,0.00035158955,0.00015653053],"about_ca_topic_score_codex":0.0006034539,"about_ca_topic_score_gemma":0.000033425105,"teacher_disagreement_score":0.94533396,"about_ca_system_score_codex":0.000065120395,"about_ca_system_score_gemma":0.000017011358,"threshold_uncertainty_score":0.8977275},"labels":[],"label_agreement":null},{"id":"W4407752103","doi":"10.1007/s10579-025-09813-8","title":"The narratives of war (NoW) corpus of written testimonies of the Russia-Ukraine war","year":2025,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Mental Health via Writing","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Ukrainian; Documentation; Narrative; Spanish Civil War; History; Psychology; Political science; Linguistics; Law; Computer science","score_opus":0.024401145646535418,"score_gpt":0.369499880025237,"score_spread":0.3450987343787016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407752103","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":[0.9624433,0.025403857,0.000010510184,0.0010566039,0.000115531235,0.00038935588,0.0000128279025,0.0000068682616,0.01056114],"genre_scores_gemma":[0.99893427,0.000086376844,0.00011190207,0.000058729507,0.000032335935,0.00002516285,0.000004318039,0.0000054939856,0.00074142835],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9987612,0.00039496523,0.00035357778,0.0001185674,0.0002530247,0.00011869269],"domain_scores_gemma":[0.9989659,0.00037636518,0.00029497177,0.00025868783,0.00008778864,0.000016291715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012289094,0.00007100226,0.00015649803,0.000043286418,0.00013946462,0.0000036054155,0.00013919533,0.00004997158,0.00008612864],"category_scores_gemma":[0.00019246564,0.00004047946,0.00004011293,0.00018912788,0.00021336187,0.0000202805,0.000056727247,0.00007940148,0.0000011543583],"study_design_candidate":"qualitative","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":[0.0005200102,0.00024430954,0.0933589,0.00096692273,0.00026587307,0.0000017004841,0.5022244,0.00010057029,0.035801288,0.004520771,0.0019383882,0.3600569],"study_design_scores_gemma":[0.0021973548,0.00041268772,0.64055467,0.00095002144,0.00017132281,0.000008468594,0.33304268,0.0036947222,0.013022711,0.0023004063,0.0034930247,0.00015190768],"about_ca_topic_score_codex":0.00037497317,"about_ca_topic_score_gemma":0.00014012326,"teacher_disagreement_score":0.5471958,"about_ca_system_score_codex":0.000018347984,"about_ca_system_score_gemma":0.000031577187,"threshold_uncertainty_score":0.16507044},"labels":[],"label_agreement":null}]}