{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":41,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":41,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"84f0ed203413","filters":{"venue":"Language Resources and Evaluation"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08234689324121308,"gpt":0.4785165175012421,"spread":0.3961696242600291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001948277,0.0001959848,0.0003163669,0.0001848252,0.0001376166,0.000252129,0.000361049,0.0001104266,0.000007185112],"category_scores_gemma":[0.0006850537,0.0001447372,0.00005655681,0.0001908753,0.0000501999,0.0002302254,0.0001388352,0.0002009959,3.522761e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007806121,"about_ca_system_score_gemma":0.00002034676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002206206,"about_ca_topic_score_gemma":0.0001920673,"domain_scores_codex":[0.9977228,0.0006991182,0.00034839,0.0004689434,0.0005087679,0.0002519635],"domain_scores_gemma":[0.9986286,0.0006680719,0.000244284,0.0002777719,0.0001118509,0.00006948307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006557876,0.00004889168,0.0004815374,0.000155994,0.00002298729,0.000002384945,0.2505527,0.0002669537,0.007247934,0.0300158,0.00005810477,0.7110811],"study_design_scores_gemma":[0.001136093,0.0001498754,0.002509097,0.00009429052,0.00004264941,0.000007781666,0.01378987,0.7848694,0.01152729,0.185485,0.00006917815,0.0003195059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4539799,0.002305894,0.5430584,0.0001317093,0.00008408455,0.0003342635,0.000003615298,0.00008810943,0.00001402314],"genre_scores_gemma":[0.6687624,0.000002666904,0.331013,0.00004903733,0.00009020341,0.00004193783,0.00001949393,0.000009212013,0.00001205158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7846024,"threshold_uncertainty_score":0.5902212,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03096635623433478,"gpt":0.3302474758262631,"spread":0.2992811195919283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007696325,0.00006730841,0.0001059975,0.0001169362,0.00006912046,0.00006112283,0.0002027122,0.00005805391,0.00001094968],"category_scores_gemma":[0.0001307537,0.00005764228,0.00002425253,0.000245057,0.00002154802,0.0002575953,0.00003109446,0.00006990705,0.000003494512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000224057,"about_ca_system_score_gemma":0.00001810804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002112749,"about_ca_topic_score_gemma":0.000003210391,"domain_scores_codex":[0.9991525,0.00009334899,0.0001923533,0.0001788637,0.0002910592,0.0000918759],"domain_scores_gemma":[0.9993939,0.00007362061,0.0001549992,0.000243629,0.0001030736,0.00003077756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004782157,0.00002959942,0.004659724,0.00002809703,0.00001076163,0.000001341225,0.01217371,0.00001920671,0.037116,0.01092117,0.0001515767,0.934884],"study_design_scores_gemma":[0.0006592,0.0003228303,0.6593317,0.0002647887,0.0001444477,0.00001596008,0.0009841742,0.2325833,0.02104152,0.08393388,0.0003099826,0.0004082399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8935341,0.00593425,0.09812055,0.001146351,0.00001613574,0.0002016118,0.000001658683,0.0001401639,0.0009052015],"genre_scores_gemma":[0.9510652,0.000007326876,0.04875807,0.00004373928,0.00004604983,0.000004657357,0.00001021365,0.000002784981,0.00006199342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9344758,"threshold_uncertainty_score":0.2350584,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05742582045155489,"gpt":0.309027963334743,"spread":0.2516021428831882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007529304,0.00009808959,0.0001350361,0.00005958078,0.00008153953,0.0000924378,0.0001364338,0.00006184234,0.00001698369],"category_scores_gemma":[0.0001269026,0.00009208454,0.00004064794,0.0001843522,0.000009908582,0.0002740219,0.00001479959,0.00009040017,9.403873e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003436027,"about_ca_system_score_gemma":0.00003601439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001733906,"about_ca_topic_score_gemma":0.0001137881,"domain_scores_codex":[0.9988823,0.00009105614,0.0002162999,0.0003478268,0.0002866925,0.0001758219],"domain_scores_gemma":[0.9996323,0.00006462986,0.0000468318,0.0001003189,0.00009485707,0.00006109245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002185718,0.00006847989,0.001456871,0.0002184785,0.00002550745,0.000003474562,0.1247628,0.5823465,0.03550721,0.0006980278,0.00006988762,0.2546242],"study_design_scores_gemma":[0.001144851,0.00004825461,0.00007407389,0.00002702439,0.00001387234,0.000001098111,0.0009591128,0.9965039,0.0006629552,0.0002762009,0.0001776701,0.0001110047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4152704,0.0002351407,0.5829093,0.00117045,0.00002337018,0.0002911722,0.000001797297,0.00003904847,0.00005932606],"genre_scores_gemma":[0.9760057,0.000006327011,0.02280295,0.001042191,0.00007169878,0.00004767693,0.000008584572,0.000006851658,0.000007995477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5607353,"threshold_uncertainty_score":0.3755099,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03078082295855368,"gpt":0.3193694584320568,"spread":0.2885886354735031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009737079,0.00008691274,0.0001684166,0.0000862018,0.0001903977,0.0001228021,0.0005440338,0.00006672897,0.00002835179],"category_scores_gemma":[0.0004370071,0.00007379581,0.00003706739,0.00009930004,0.0001079185,0.0003575169,0.0001652716,0.00008700279,0.000001445877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001583848,"about_ca_system_score_gemma":0.00004144523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003343395,"about_ca_topic_score_gemma":0.00003480937,"domain_scores_codex":[0.9989318,0.00008717026,0.000251595,0.0002033783,0.0004169203,0.0001090938],"domain_scores_gemma":[0.9985895,0.0001109907,0.000570457,0.0004490203,0.0002442963,0.00003577621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003539021,0.0000795824,0.006584845,0.0002036401,0.00004933609,0.000009851588,0.02293183,0.0003563767,0.4030734,0.008786154,0.0001127954,0.5577768],"study_design_scores_gemma":[0.001426477,0.0004817624,0.02025079,0.001394423,0.0001776775,0.0000339379,0.00101279,0.4388496,0.4751555,0.06036011,0.0002621976,0.0005947456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9048939,0.01362066,0.07961407,0.0002317042,0.0000503868,0.0002979668,0.000006865991,0.00008407338,0.00120036],"genre_scores_gemma":[0.9446278,0.00002433512,0.05514988,0.00001675076,0.00002720298,0.00001030114,0.000003723633,0.000005252842,0.0001348107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5571821,"threshold_uncertainty_score":0.3009306,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04572153790965464,"gpt":0.2934511416866595,"spread":0.2477296037770049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004986699,0.00007298298,0.000073808,0.00007073188,0.0002955648,0.000187172,0.0003048732,0.00005245047,0.000005249361],"category_scores_gemma":[0.0002518368,0.00004942688,0.00002971688,0.0004232268,0.00004152854,0.000343565,0.000114852,0.00007105064,0.00000277441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002365186,"about_ca_system_score_gemma":0.00002247071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008821391,"about_ca_topic_score_gemma":0.00006377166,"domain_scores_codex":[0.9992493,0.0001105396,0.00008782236,0.0002146638,0.0002137881,0.0001238394],"domain_scores_gemma":[0.9994751,0.0001537829,0.00007571391,0.0001433523,0.000102771,0.00004924864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001133562,0.00002330898,0.0001974206,0.00004862422,0.00002092335,0.00000850193,0.02768186,0.00007008603,0.003805647,0.02990418,0.00199516,0.9361309],"study_design_scores_gemma":[0.001316364,0.0007640754,0.0008876045,0.0000627971,0.00008872807,0.0000122799,0.007898438,0.7067691,0.01441784,0.01234176,0.2549401,0.0005009186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2157518,0.008942667,0.7533713,0.01834793,0.0001409525,0.001057734,0.0000112756,0.0007873097,0.001589084],"genre_scores_gemma":[0.9414427,0.0009410963,0.05680626,0.0005364575,0.0001762225,0.00001516812,0.00001892144,0.000007006536,0.00005620984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.93563,"threshold_uncertainty_score":0.2273275,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02114258455556268,"gpt":0.2977898512918377,"spread":0.276647266736275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000409916,0.00008867979,0.0001163875,0.0001227285,0.00003970956,0.00005127709,0.0001796665,0.00005804223,0.00002871473],"category_scores_gemma":[0.000107289,0.00007225348,0.00001875021,0.00046515,0.00002840907,0.000236833,0.00003943544,0.0001373731,0.000003301927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003642898,"about_ca_system_score_gemma":0.00005473362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001888502,"about_ca_topic_score_gemma":0.0001564649,"domain_scores_codex":[0.999103,0.0001190692,0.0001762593,0.0002380522,0.0002594876,0.0001041712],"domain_scores_gemma":[0.9994798,0.0001055578,0.000124489,0.0001640556,0.00008392951,0.00004221911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003085898,0.00008905373,0.01118178,0.000153026,0.00001289738,0.00001380484,0.04343192,0.00100628,0.01728706,0.0001689841,0.0001384519,0.9264859],"study_design_scores_gemma":[0.000989933,0.0001976445,0.03775141,0.000264191,0.00003552706,0.000008738491,0.0006499444,0.9434078,0.01532104,0.0008715929,0.0002561367,0.0002460255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8229669,0.005870217,0.1694433,0.00101336,0.00001709047,0.0002279115,0.000001423791,0.0001198759,0.0003399385],"genre_scores_gemma":[0.9570439,0.000004552476,0.04276167,0.0001024221,0.00003373023,0.00001933296,0.00000799592,0.000006549939,0.00001985979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9424015,"threshold_uncertainty_score":0.2946411,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Sentence; Machine translation; Indigenous; Natural language processing; Indigenous language; Linguistics; Artificial intelligence; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.02149560907502406,"gpt":0.266804596939113,"spread":0.2453089878640889,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008073307,0.0001427455,0.0001207498,0.00003648587,0.000286563,0.0003552744,0.0004124393,0.00006632825,0.000005408998],"category_scores_gemma":[0.0002382569,0.00008716647,0.00002882518,0.0002905898,0.00006623735,0.0003836568,0.0000803829,0.0001945013,0.000002548366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002276674,"about_ca_system_score_gemma":0.00003549002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006982894,"about_ca_topic_score_gemma":0.00008955626,"domain_scores_codex":[0.9985309,0.0001760907,0.0002179338,0.0003550021,0.0005361178,0.0001839269],"domain_scores_gemma":[0.999167,0.0001666737,0.000144884,0.0002946794,0.0001469289,0.00007983297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005256292,0.00001737937,0.0001342163,0.0000434204,0.00002388211,0.00001873686,0.0631484,0.0004281433,0.0005339294,0.0008345634,0.0003808679,0.9339108],"study_design_scores_gemma":[0.002177641,0.0009302179,0.001117739,0.0001254465,0.00008804892,0.00003299665,0.001576946,0.9750209,0.002289099,0.001760268,0.01445615,0.0004245375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2267246,0.2083615,0.5281528,0.02646733,0.0002744236,0.002568065,0.00004174532,0.002247566,0.005161991],"genre_scores_gemma":[0.9268298,0.0001294545,0.07227834,0.0004378763,0.0001663515,0.00004248713,0.00003559269,0.00001327704,0.00006684927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745927,"threshold_uncertainty_score":0.3554545,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05399665033771572,"gpt":0.3638496073975532,"spread":0.3098529570598375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009681821,0.0001451251,0.000168429,0.0001024486,0.000294236,0.000128646,0.00009629015,0.0001769036,0.000819895],"category_scores_gemma":[0.00002772098,0.0001325191,0.00004194745,0.0001289531,0.00003223669,0.0001487256,0.00004612488,0.00032092,0.0000510794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000651204,"about_ca_system_score_gemma":0.00001701136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006034539,"about_ca_topic_score_gemma":0.00003342511,"domain_scores_codex":[0.9979627,0.0005722985,0.000259534,0.0004835551,0.0004478683,0.0002740227],"domain_scores_gemma":[0.9994142,0.0002458561,0.00006654857,0.0001408302,0.00002847056,0.0001041139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007622535,0.0000771964,0.003011473,0.0001249737,0.00005105239,0.00001438147,0.4019443,0.007915939,0.001919746,0.0001215676,0.00008015382,0.584663],"study_design_scores_gemma":[0.0005503915,0.00004410802,0.004546975,0.0001340568,0.00008637151,0.000007099923,0.04068256,0.9532499,0.00003828404,0.00015213,0.0003515896,0.0001565305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9808733,0.01003319,0.002802436,0.00004442269,0.0002219589,0.0002867736,0.00001580096,0.0001832268,0.005538828],"genre_scores_gemma":[0.9972106,0.00001856944,0.0007841751,0.00005533421,0.001178703,0.00007070693,0.0005066467,0.00004081881,0.0001344175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.945334,"threshold_uncertainty_score":0.8977275,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07035566898821673,"gpt":0.3433580144822387,"spread":0.273002345494022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002372817,0.00005534855,0.00006367545,0.00004601123,0.0002442792,0.0001566095,0.0004284138,0.00002048951,0.00008311733],"category_scores_gemma":[0.0001780518,0.00003996944,0.0000162361,0.0002002375,0.00002720474,0.0001188568,0.0001196993,0.0001085448,0.000001822509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005352507,"about_ca_system_score_gemma":0.00007720602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001416369,"about_ca_topic_score_gemma":0.0004828204,"domain_scores_codex":[0.9983601,0.000660178,0.000125482,0.0002171905,0.0005279579,0.0001090927],"domain_scores_gemma":[0.9993416,0.0002430005,0.00006161502,0.0002948227,0.00002237384,0.00003657343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004400947,0.000220492,0.008580747,0.0000722308,0.00001315921,0.00002467424,0.4020616,0.005805436,0.0009459436,0.02996774,0.001233746,0.5510303],"study_design_scores_gemma":[0.001581089,0.0003210434,0.1836633,0.00001217277,0.00003878077,0.0001540384,0.07491803,0.4730579,0.0003281731,0.01562825,0.2498587,0.0004384498],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889928,0.001089763,0.002761061,0.004367359,0.0000530876,0.0003953821,0.000005208447,0.00003579145,0.002299572],"genre_scores_gemma":[0.9987834,0.00001411833,0.0002451121,0.0007540997,0.00002817556,0.00009432803,0.00001674931,0.00000164206,0.00006233972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5505918,"threshold_uncertainty_score":0.2141136,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02852958433192382,"gpt":0.3391111709409689,"spread":0.3105815866090451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006032512,0.0001407594,0.0002610373,0.0002039319,0.00008318379,0.0001060021,0.0003689756,0.00008093411,0.00001631338],"category_scores_gemma":[0.0001624353,0.0001208766,0.0001034777,0.0006247695,0.00003456083,0.0003047157,0.00004534001,0.00009446658,3.853243e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001687063,"about_ca_system_score_gemma":0.00001777943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008912192,"about_ca_topic_score_gemma":0.00005033354,"domain_scores_codex":[0.9986143,0.0001517185,0.000274765,0.00039104,0.0004043756,0.0001637997],"domain_scores_gemma":[0.9991798,0.0001355644,0.0001975872,0.0002569151,0.0001317431,0.00009832048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000959764,0.00004809412,0.0006330395,0.0001177233,0.0001342383,0.000004982102,0.04686682,0.004692921,0.04473345,0.0002312038,0.00001536836,0.9024262],"study_design_scores_gemma":[0.0004711415,0.0001522018,0.0007918029,0.00001342413,0.000317104,0.000001306853,0.00095262,0.9860467,0.01096168,0.00007178991,0.00007887412,0.0001413162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6770269,0.01253765,0.3089556,0.0006776242,0.00001490658,0.0004556866,0.00004823002,0.0002425873,0.00004085592],"genre_scores_gemma":[0.9218197,0.000004856883,0.07754623,0.0003277752,0.000071571,0.00002007957,0.0001936766,0.00001125732,0.00000483346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9813538,"threshold_uncertainty_score":0.4929203,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05024759076246877,"gpt":0.3165752133910301,"spread":0.2663276226285614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009462885,0.00004665173,0.00008821138,0.00005464674,0.00004463776,0.00005491912,0.0001855358,0.00002064361,0.00000134718],"category_scores_gemma":[0.0001737624,0.0000294112,0.0000155272,0.000254337,0.00004024344,0.0002992277,0.0000748471,0.00004058191,2.240738e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001040601,"about_ca_system_score_gemma":0.00002773855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002895359,"about_ca_topic_score_gemma":0.0001374528,"domain_scores_codex":[0.9992399,0.0001178923,0.000215518,0.0001335484,0.0002265391,0.00006657093],"domain_scores_gemma":[0.9991825,0.0001627846,0.0002049885,0.0002654971,0.0001734958,0.00001077344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003621254,0.00004134648,0.003588436,0.000122768,0.00001590929,6.566165e-7,0.02363049,0.0001059782,0.2907482,0.002964168,0.00000497948,0.6787408],"study_design_scores_gemma":[0.0008316711,0.0001511652,0.03564951,0.0002112801,0.00008356016,0.000007637528,0.008954267,0.2883899,0.6504436,0.01475689,0.0003761911,0.000144288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805016,0.01437431,0.004705509,0.0001153208,0.00002206914,0.0002429981,0.000004142602,0.00001203524,0.0000220365],"genre_scores_gemma":[0.9942515,0.000165795,0.005491809,0.00000873835,0.00001312855,0.00003837658,0.000006364195,0.000003311997,0.00002094576],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6785965,"threshold_uncertainty_score":0.1199354,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04463166772679519,"gpt":0.3218636676018755,"spread":0.2772319998750803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005583924,0.0001340728,0.0002073218,0.0001276813,0.0001420304,0.0004685094,0.0001884102,0.00007521122,0.0000167004],"category_scores_gemma":[0.0004681106,0.0001147657,0.00005697929,0.0004790295,0.00002987202,0.0004770698,0.00009886998,0.00008376241,7.970229e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002122662,"about_ca_system_score_gemma":0.00001820347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009388574,"about_ca_topic_score_gemma":0.0001081303,"domain_scores_codex":[0.9988322,0.0000893878,0.0001781606,0.0004052547,0.0003346576,0.0001603962],"domain_scores_gemma":[0.9993278,0.0001341023,0.0001234397,0.0002158447,0.0001082416,0.00009050396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006270446,0.00004980784,0.002035508,0.0002303308,0.0003725397,0.0000152154,0.04952738,0.0002022818,0.1244705,0.001764563,0.0004601154,0.8208091],"study_design_scores_gemma":[0.0007857814,0.0001873774,0.004536712,0.00003145165,0.0006355745,0.000008360171,0.001018851,0.9554849,0.03605175,0.0006468754,0.0002734444,0.0003388987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6865679,0.009259092,0.2997341,0.003740316,0.00001460698,0.0004294386,0.00001299404,0.0002002167,0.00004136502],"genre_scores_gemma":[0.8926434,0.00002939947,0.1063689,0.0005751671,0.0001924981,0.0000530411,0.00009771516,0.00001007951,0.00002986701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9552826,"threshold_uncertainty_score":0.4680008,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03038743013763573,"gpt":0.3296793279805589,"spread":0.2992918978429232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002261811,0.0001442597,0.0001395922,0.0001988622,0.0001879458,0.0002371628,0.0003168899,0.00007584579,0.00003836861],"category_scores_gemma":[0.0005025927,0.0001216624,0.00002963949,0.0004712407,0.00003635996,0.000241373,0.00007652646,0.00009440009,0.00001873319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000780308,"about_ca_system_score_gemma":0.00004767184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286176,"about_ca_topic_score_gemma":0.00004108728,"domain_scores_codex":[0.998081,0.0002486102,0.0002273355,0.0004103941,0.000834307,0.0001983261],"domain_scores_gemma":[0.9990516,0.00006839908,0.00009724451,0.0003688078,0.0003298882,0.00008405178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000868506,0.00003256407,0.00003541557,0.0000407094,0.00001036577,7.146752e-7,0.03481027,0.00005243864,0.001945418,0.0007063916,0.00007614926,0.9622809],"study_design_scores_gemma":[0.0003631843,0.0001152395,0.0005619292,0.00005731983,0.00005770868,0.00001346892,0.0001561246,0.9929041,0.001299783,0.00395254,0.0003493329,0.0001693247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2743939,0.01596119,0.7005414,0.0005098279,0.0002063716,0.001469178,0.000003615607,0.0006882392,0.006226347],"genre_scores_gemma":[0.7312979,0.000003074021,0.2681991,0.0001879124,0.0001833747,0.00007200095,0.00002211005,0.000009359922,0.0000252416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9928516,"threshold_uncertainty_score":0.4961249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.212328201095616,"gpt":0.3869887300338786,"spread":0.1746605289382627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004648539,0.0001042185,0.0001542748,0.00008391269,0.0001071765,0.0001384583,0.0002821788,0.0001186903,0.00001235267],"category_scores_gemma":[0.0008957342,0.00009853405,0.00003913455,0.0001473496,0.00004085109,0.0004287245,0.00008647648,0.00009024714,8.018935e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000732385,"about_ca_system_score_gemma":0.0001334979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002787231,"about_ca_topic_score_gemma":0.0001448171,"domain_scores_codex":[0.9980518,0.0003017166,0.0002203564,0.0003327066,0.0009269362,0.0001665484],"domain_scores_gemma":[0.998542,0.000135312,0.0001438689,0.0004233865,0.000657859,0.0000975883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001224733,0.000149998,0.009041608,0.0001339356,0.00006718814,0.00000247694,0.08972238,0.06784435,0.001173257,0.01453962,0.00006871789,0.817134],"study_design_scores_gemma":[0.0008422256,0.0001118307,0.006954814,0.00003536484,0.00006432435,0.000002450622,0.001686854,0.9661856,0.0006086114,0.02324813,0.0001403904,0.0001194535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5476088,0.0005781897,0.4510719,0.0001913152,0.00009610457,0.0003173305,0.000006149855,0.00002857829,0.0001016167],"genre_scores_gemma":[0.9372215,0.000004252731,0.06250168,0.00007262365,0.0001337953,0.00001815306,0.00001891267,0.000007355911,0.00002169596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8983412,"threshold_uncertainty_score":0.4018102,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Disease; Space (punctuation); Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.0302507815983099,"gpt":0.2936973496375037,"spread":0.2634465680391938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002870968,0.00007446145,0.00007011819,0.00003271942,0.000034532,0.0000126021,0.00004417519,0.00005455117,0.00001314043],"category_scores_gemma":[0.0001070033,0.00004362143,0.00001226575,0.000046546,0.00005514201,0.000002764952,0.00003166714,0.00002670934,0.000001187443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006392933,"about_ca_system_score_gemma":0.00001666501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005326361,"about_ca_topic_score_gemma":0.000554255,"domain_scores_codex":[0.9993995,0.00006825114,0.00006153918,0.0001983438,0.0001395706,0.0001327862],"domain_scores_gemma":[0.9997396,0.00002460837,0.00003623901,0.00012074,0.00002296666,0.00005581393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003549972,0.00003644964,0.01114362,0.00003220103,0.0000564564,0.00001597845,0.002671428,0.0001523074,0.1416181,0.00001917743,0.00007297522,0.8438264],"study_design_scores_gemma":[0.01983585,0.005002838,0.5175943,0.002837223,0.001427296,0.0001397749,0.02535126,0.128513,0.2711293,0.002140297,0.0226803,0.003348539],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896623,0.008432244,0.0007140879,0.000929485,0.00001798872,0.0001166087,0.000003817025,0.00001263516,0.0001107942],"genre_scores_gemma":[0.9993069,0.0001328157,0.0002911251,0.00005669023,0.0001004647,0.00002456613,0.000008170007,0.000008217091,0.00007100725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8404778,"threshold_uncertainty_score":0.177883,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01139944083944946,"gpt":0.2946918213716688,"spread":0.2832923805322194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009428695,0.00008015735,0.0001061663,0.0001063377,0.00005550727,0.0001869667,0.0002296711,0.00004949683,0.0000165927],"category_scores_gemma":[0.0002007527,0.00006549283,0.00001862503,0.0001957268,0.00002156511,0.0002839588,0.000116633,0.00009111156,0.000003064214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003317363,"about_ca_system_score_gemma":0.000009701909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001793711,"about_ca_topic_score_gemma":0.0001285543,"domain_scores_codex":[0.9990821,0.0001340901,0.0001288321,0.000223676,0.0002904129,0.0001408573],"domain_scores_gemma":[0.9995944,0.00007251545,0.00005833437,0.0002194221,0.00002430428,0.00003096565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001348976,0.00002674073,0.002263393,0.00004259739,0.000005770883,0.000008337368,0.02724308,0.00009429877,0.007271292,0.02401336,0.00006742362,0.9389502],"study_design_scores_gemma":[0.002460406,0.0001827359,0.02694638,0.000394278,0.00003167635,0.00003432712,0.001754601,0.8076603,0.01445357,0.1383332,0.006969606,0.0007789452],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8799372,0.003879928,0.1138357,0.0003465274,0.00005501679,0.0001547076,4.213296e-7,0.0001532175,0.001637335],"genre_scores_gemma":[0.9282765,0.00001643253,0.07139755,0.0001386774,0.0001053383,0.00001347272,0.000002719397,0.000005320888,0.00004400067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9381713,"threshold_uncertainty_score":0.267072,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0484546324202565,"gpt":0.3496756248661653,"spread":0.3012209924459088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007191608,0.00004345992,0.00009163577,0.00002725933,0.0001111653,0.00002132361,0.00006186598,0.00005370418,0.0007047836],"category_scores_gemma":[0.001126304,0.00004013977,0.00002088575,0.0001244393,0.00007306888,0.00003936382,0.00001550125,0.00004366959,0.000007407312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001824902,"about_ca_system_score_gemma":0.00008500501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005405897,"about_ca_topic_score_gemma":0.001148505,"domain_scores_codex":[0.9991596,0.0002062268,0.0001299197,0.0001180379,0.0002844904,0.0001017154],"domain_scores_gemma":[0.9996209,0.00006411186,0.00008758479,0.00005460763,0.00009988269,0.00007288162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003629018,0.00003418645,0.03218976,0.0000608727,0.00003861334,0.00001183418,0.8633214,0.00006005712,0.01415141,0.04181497,0.0004674497,0.04781317],"study_design_scores_gemma":[0.007767535,0.0009131889,0.3035026,0.0002540165,0.0008329482,0.00001362141,0.5191343,0.05179376,0.004616823,0.02074374,0.08894236,0.001485204],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9654391,0.0008908827,0.0001653545,0.002961616,0.00009270228,0.0001668087,0.000004978011,0.00002702562,0.03025153],"genre_scores_gemma":[0.998826,0.00003903075,0.0003119969,0.0003371142,0.0003528328,0.000004669628,0.000009114796,0.000003888848,0.0001153642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3441871,"threshold_uncertainty_score":0.8172135,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04815606913529093,"gpt":0.3652228133420278,"spread":0.3170667442067369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005656009,0.00008767751,0.00015152,0.0000826334,0.00003322471,0.0003380994,0.0005612857,0.00005208274,0.00004427601],"category_scores_gemma":[0.0004762005,0.00007642994,0.00001198173,0.000354949,0.00003566834,0.0008995893,0.0005676495,0.00009661028,4.320966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002206699,"about_ca_system_score_gemma":0.0001478117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243294,"about_ca_topic_score_gemma":0.0002644454,"domain_scores_codex":[0.9990151,0.00008361334,0.0001905453,0.0002857704,0.000319369,0.0001056014],"domain_scores_gemma":[0.9994665,0.00007437942,0.0001248018,0.0001358997,0.0001175084,0.00008088714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001271857,0.00004943464,0.01436636,0.0002163837,0.00002141994,0.00004906645,0.1507818,0.00007364901,0.0115736,0.005431973,0.0003007732,0.8170084],"study_design_scores_gemma":[0.01003786,0.0009740227,0.05760196,0.0007606678,0.0001385892,0.0001053368,0.01046207,0.7991656,0.08504624,0.02962498,0.004557213,0.001525424],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866933,0.007929374,0.003411944,0.00121326,0.00003917208,0.0003579216,0.000003556254,0.00006750745,0.0002839899],"genre_scores_gemma":[0.9626037,0.00004110326,0.03677288,0.000431999,0.00009797738,0.000005641415,0.000008711297,0.000005686111,0.00003231745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.815483,"threshold_uncertainty_score":0.3391205,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3079769636386057,"gpt":0.3464064700721486,"spread":0.03842950643354293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001053915,0.0001104687,0.0001252855,0.00005251955,0.0001140785,0.0001888438,0.0002803518,0.00004034115,0.00002576461],"category_scores_gemma":[0.0001482065,0.0001009112,0.00003385254,0.000211264,0.000009500902,0.0002837761,0.000203755,0.00008878252,0.00001512242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002865746,"about_ca_system_score_gemma":0.00002514483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008509235,"about_ca_topic_score_gemma":0.000008988974,"domain_scores_codex":[0.998462,0.0001598153,0.0001673444,0.0004298649,0.0005870679,0.0001939713],"domain_scores_gemma":[0.9994673,0.0000540815,0.00005693877,0.0002417801,0.00003571631,0.0001442592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008581416,0.000008421223,0.00006473602,0.00003999841,0.00001262521,0.000004365577,0.3355235,0.09157415,0.004440699,0.00247329,0.0000343199,0.5658153],"study_design_scores_gemma":[0.0002463419,0.00005755024,0.0001157759,0.00002193354,0.00001572484,0.000003920999,0.007921465,0.9907225,0.0003144711,0.0003795442,0.00007342746,0.0001273222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7205886,0.002067743,0.2727377,0.002777445,0.00002841483,0.0002593588,0.000001094539,0.0001015319,0.001438122],"genre_scores_gemma":[0.9282846,0.000002865739,0.07033808,0.00106902,0.0002187771,0.00002821547,0.000004397656,0.000009453503,0.00004461297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8991484,"threshold_uncertainty_score":0.4115039,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03137950489801756,"gpt":0.300703666162043,"spread":0.2693241612640255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007021911,0.00009185033,0.0001108299,0.00008488895,0.00007442343,0.0001599223,0.0002395379,0.00006043341,0.000003710014],"category_scores_gemma":[0.000339241,0.00007815137,0.00002796807,0.0002637224,0.00001756144,0.0002726742,0.00007236953,0.0001026568,6.81299e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002010383,"about_ca_system_score_gemma":0.00004046077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000381691,"about_ca_topic_score_gemma":0.00001174061,"domain_scores_codex":[0.9991583,0.00005648395,0.00015932,0.0002387404,0.0002245405,0.0001626053],"domain_scores_gemma":[0.9995987,0.00008936315,0.00008083451,0.0001269159,0.00005498562,0.00004918831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005172665,0.00002183918,0.0007332789,0.0002427819,0.000006037357,0.000002654209,0.03508713,0.001717164,0.006821169,0.0006721347,0.00003592095,0.9546081],"study_design_scores_gemma":[0.0005279567,0.0000895242,0.0002757241,0.00002601118,0.000006467237,0.00000226209,0.0008388279,0.9882621,0.009349185,0.0003765325,0.0001285212,0.0001169378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.270407,0.004515802,0.7232941,0.00072614,0.00001520456,0.0004940091,0.000001600896,0.0002294827,0.0003166431],"genre_scores_gemma":[0.7355359,0.00000128697,0.2638507,0.0004824114,0.00005422658,0.0000575627,0.000007724808,0.000005239978,0.000004902719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9865449,"threshold_uncertainty_score":0.3186921,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01198234994470673,"gpt":0.2627608228998279,"spread":0.2507784729551212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006982129,0.0001396146,0.0001609846,0.00005459235,0.0001599816,0.0002300148,0.0003954991,0.0000986356,0.00004327601],"category_scores_gemma":[0.0003135253,0.0001201593,0.00004441828,0.000319001,0.00003141639,0.0003293082,0.0002193607,0.0001815652,0.000009422372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002765691,"about_ca_system_score_gemma":0.00004737978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004955863,"about_ca_topic_score_gemma":0.00004828307,"domain_scores_codex":[0.9985406,0.0001449224,0.0001841933,0.000394936,0.0004871407,0.0002481552],"domain_scores_gemma":[0.999359,0.00004198803,0.0001066191,0.0002424413,0.0001307494,0.0001191716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007444064,0.0001376878,0.002827037,0.0002317381,0.00003180453,0.000105771,0.439784,0.00008844609,0.007667312,0.01194092,0.0100771,0.5270337],"study_design_scores_gemma":[0.007512795,0.001164893,0.01221303,0.0004062494,0.0001749114,0.00008084433,0.008321859,0.7896857,0.008396556,0.07013818,0.09958011,0.002324916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.675015,0.01966318,0.3004294,0.002112737,0.0001463969,0.0004778114,0.00001533541,0.0008217991,0.001318256],"genre_scores_gemma":[0.8065178,0.00002357751,0.1912846,0.001624329,0.0004207074,0.00003466854,0.00002211671,0.00001179197,0.00006036493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7895972,"threshold_uncertainty_score":0.4899954,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.1226647332271734,"gpt":0.3879749591543143,"spread":0.265310225927141,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001999834,0.00008227371,0.0001414077,0.0000711899,0.000058498,0.00005442922,0.0001335857,0.00006240162,0.00002048909],"category_scores_gemma":[0.0001320621,0.00005870962,0.00004325675,0.00005849314,0.0000320948,0.0004420023,0.00003415371,0.00003743924,0.000001475075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400036,"about_ca_system_score_gemma":0.00004571881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001904283,"about_ca_topic_score_gemma":0.00007322981,"domain_scores_codex":[0.9988783,0.0001490026,0.0002564443,0.0002581073,0.0003238359,0.000134338],"domain_scores_gemma":[0.9991954,0.0001557644,0.0001446483,0.000208301,0.0002371745,0.00005871556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009485324,0.00003286807,0.0001066479,0.0000165779,0.000006971291,1.998207e-7,0.004493732,0.000008503348,0.02279605,0.0002842099,0.000001553302,0.9722432],"study_design_scores_gemma":[0.0009329293,0.0002249536,0.009958346,0.0001081984,0.00003125879,0.000004984791,0.0005171282,0.9643353,0.01193703,0.01172173,0.00003833461,0.0001897604],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5494052,0.00002021413,0.4498664,0.0001634325,0.00001275077,0.0002159114,0.00001598474,0.00005232415,0.0002477996],"genre_scores_gemma":[0.8992664,0.000007110665,0.1004191,0.00007082118,0.00005710146,0.0001064639,0.00003093824,0.000007057726,0.00003504183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9720534,"threshold_uncertainty_score":0.2394109,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02869467135172208,"gpt":0.3027328626012327,"spread":0.2740381912495106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003209216,0.00008095968,0.0001076653,0.00006053844,0.0000631257,0.00003888663,0.0001779331,0.00005721932,0.00002909522],"category_scores_gemma":[0.0001419278,0.00007070444,0.0000294744,0.000223837,0.00005443563,0.0001698917,0.00006831094,0.00008845132,0.000001464314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001447902,"about_ca_system_score_gemma":0.00003738974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003461879,"about_ca_topic_score_gemma":0.000002109799,"domain_scores_codex":[0.9991015,0.00006617505,0.0001644725,0.0002230227,0.0003566006,0.00008821044],"domain_scores_gemma":[0.9995005,0.00005559146,0.0001232702,0.0001474862,0.0001196489,0.00005354384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004722909,0.00002751455,0.001932321,0.0001279233,0.0000159695,0.00001079689,0.01441785,0.0002407699,0.03708238,0.001577666,0.00009510119,0.9444245],"study_design_scores_gemma":[0.0005740243,0.0001627974,0.001146585,0.0000636292,0.00003147709,0.00001770938,0.0007635974,0.9300492,0.06511497,0.001631118,0.0002903273,0.0001545559],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8814127,0.00689925,0.1101129,0.0008683192,0.0000569303,0.0002161714,0.00000485066,0.0002619232,0.0001669232],"genre_scores_gemma":[0.8237203,0.000007697978,0.175916,0.0002643305,0.00006426348,0.000006243601,0.00001256872,0.000004742057,0.000003925054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9442699,"threshold_uncertainty_score":0.2883243,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03784322549439183,"gpt":0.3385109969376508,"spread":0.300667771443259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001366636,0.00009125408,0.0001353521,0.00009726585,0.0000949491,0.00005342451,0.0004123586,0.0000941883,0.000004600447],"category_scores_gemma":[0.0002271067,0.00006404249,0.0000245946,0.0001655202,0.00006731166,0.0003663515,0.0002172731,0.0001053478,8.860342e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002936961,"about_ca_system_score_gemma":0.00000996426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005302223,"about_ca_topic_score_gemma":0.00008389153,"domain_scores_codex":[0.9987577,0.0004294709,0.0001709718,0.0002055664,0.0002466473,0.0001896769],"domain_scores_gemma":[0.9991478,0.0001227593,0.000151473,0.0004695841,0.00005540113,0.00005302951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001739184,0.00006947419,0.05372926,0.0001352091,0.00002831849,0.000001270961,0.09192279,0.00006021436,0.1171188,0.01281576,0.00002197039,0.7240795],"study_design_scores_gemma":[0.0005255388,0.0002648601,0.5075516,0.0002360125,0.0002066734,0.000161377,0.006062407,0.08408744,0.3612608,0.03858119,0.0004054689,0.0006567605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8573638,0.001887289,0.1399907,0.0002745118,0.00006421138,0.0002811779,8.493574e-7,0.00007926302,0.00005820296],"genre_scores_gemma":[0.8916192,0.00000305775,0.1080745,0.0001536948,0.00007715273,0.0000451159,0.000002416254,0.000006399438,0.00001849638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7234228,"threshold_uncertainty_score":0.2611577,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0240283775658798,"gpt":0.3017247175024333,"spread":0.2776963399365535,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004421651,0.00006352308,0.0000891934,0.00006636569,0.0000812416,0.00002770664,0.0001638504,0.00004136181,0.00001789428],"category_scores_gemma":[0.0001293806,0.00005175701,0.00002134401,0.0001670637,0.00004945006,0.0002346902,0.00006705213,0.00004915969,0.000001992713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001256411,"about_ca_system_score_gemma":0.00001921769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009957244,"about_ca_topic_score_gemma":0.000004896164,"domain_scores_codex":[0.9991804,0.00007650661,0.000140709,0.0001609231,0.0003500945,0.00009135925],"domain_scores_gemma":[0.9995572,0.00004777307,0.00009920167,0.000171857,0.00009652338,0.00002741912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003140756,0.00009097348,0.005521553,0.00009210053,0.00002775953,0.00001823928,0.06661563,0.00008418957,0.05220885,0.008218353,0.000316759,0.8667742],"study_design_scores_gemma":[0.001528867,0.0003517487,0.02841665,0.0001921837,0.00007820348,0.0001583942,0.001144498,0.5958166,0.3489443,0.0220768,0.0007138376,0.0005779119],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9417397,0.008320369,0.04917381,0.000184597,0.00003479819,0.0001357987,0.000001126012,0.0001229301,0.0002868133],"genre_scores_gemma":[0.9636712,0.00003989278,0.0361434,0.00004259511,0.00004249777,0.00001082417,0.000006878933,0.000003727871,0.00003899112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8661963,"threshold_uncertainty_score":0.2110589,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0337936629644121,"gpt":0.2838120272324091,"spread":0.250018364267997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007815328,0.00007015328,0.00009105584,0.00004972477,0.0001040437,0.0001424782,0.0002262541,0.00002576356,0.0002114482],"category_scores_gemma":[0.0002181152,0.0000495952,0.00003482441,0.0001673997,0.00002015222,0.0001481586,0.0000357699,0.00004119432,0.0000462829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009531365,"about_ca_system_score_gemma":0.00002300159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001790134,"about_ca_topic_score_gemma":0.000004471851,"domain_scores_codex":[0.9991698,0.000080331,0.0001594647,0.0001867766,0.0003059241,0.00009766883],"domain_scores_gemma":[0.9993379,0.0002729423,0.00008774473,0.0001801766,0.00007699589,0.00004424509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008078053,0.00003887194,0.00007601148,0.0001096938,0.00004406273,0.000001558086,0.08896527,0.001522215,0.09817736,0.003704509,0.000872997,0.8064067],"study_design_scores_gemma":[0.0003002649,0.0001776778,0.00219616,0.00005144296,0.00003323534,0.000002373735,0.008244388,0.9342803,0.05373281,0.0003457523,0.0004994887,0.0001360872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861447,0.0002233501,0.01041667,0.001700899,0.00002649222,0.0003523841,0.00001073084,0.00003786814,0.001086949],"genre_scores_gemma":[0.9968997,0.000009056816,0.002280066,0.0005907568,0.00007462371,0.00004194203,0.000009801497,0.00000550185,0.00008859824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9327581,"threshold_uncertainty_score":0.2315209,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04671167661381604,"gpt":0.3280433324245093,"spread":0.2813316558106933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000651133,0.0001094603,0.0001359102,0.00004005731,0.0001391548,0.0001348659,0.0001954575,0.00006697531,0.000008505257],"category_scores_gemma":[0.0005390021,0.0001025502,0.00004490805,0.0001083673,0.00002001928,0.0001694708,0.00008734562,0.00008081119,0.000004162205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002269638,"about_ca_system_score_gemma":0.00003501023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001020411,"about_ca_topic_score_gemma":0.00003752065,"domain_scores_codex":[0.9987983,0.00009159589,0.0002094174,0.0003913254,0.0003370738,0.0001722481],"domain_scores_gemma":[0.9993408,0.0001434954,0.00009551755,0.0002046462,0.0001243692,0.00009121212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004351504,0.00003289411,0.00107606,0.0001073634,0.00002194221,0.00000533914,0.07613178,0.007543406,0.009864903,0.0002749216,0.00004565271,0.9048522],"study_design_scores_gemma":[0.0008059164,0.00007386634,0.001124929,0.00001664067,0.00003159022,0.000003204335,0.0008750768,0.9926744,0.003142496,0.0002429724,0.0008877255,0.0001211513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8038204,0.0008858159,0.1937295,0.0008247023,0.00008797162,0.0004271514,0.000005159732,0.0001047696,0.0001144575],"genre_scores_gemma":[0.980028,0.000009841014,0.0190921,0.0004650367,0.0003156062,0.00002424928,0.00002241176,0.000008750627,0.00003397029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.985131,"threshold_uncertainty_score":0.4181875,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05399198577407965,"gpt":0.3305914666254582,"spread":0.2765994808513786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001472014,0.00007014058,0.0001055396,0.00004106939,0.00005791857,0.00003419262,0.0002407631,0.00003807439,0.00001521203],"category_scores_gemma":[0.001669672,0.00004513741,0.00002330655,0.0003152666,0.0000451323,0.0001197769,0.00004695754,0.00005137575,4.102329e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002014944,"about_ca_system_score_gemma":0.00005250784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000390507,"about_ca_topic_score_gemma":0.000008061206,"domain_scores_codex":[0.9987492,0.0002210793,0.0001675063,0.0001698823,0.0006204004,0.0000719337],"domain_scores_gemma":[0.9985774,0.0003165824,0.0002442597,0.0001783596,0.0006590853,0.00002427759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009923928,0.0000364837,0.0001310631,0.0001407272,0.00003157355,3.003618e-7,0.05452024,0.0007156392,0.03800471,0.03769985,0.0002913076,0.8683289],"study_design_scores_gemma":[0.0006651152,0.0004293285,0.0006366202,0.0001424206,0.0001146299,0.000001288019,0.001562123,0.875591,0.09011885,0.03057669,0.00005447091,0.0001074962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9004104,0.005382247,0.09077033,0.001834669,0.00003010216,0.001170785,0.00001407554,0.00005119385,0.000336164],"genre_scores_gemma":[0.992542,0.000006610713,0.007191289,0.0001398028,0.00002784168,0.00006784746,0.00001408515,0.000004265643,0.00000620519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8748753,"threshold_uncertainty_score":0.1998874,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1061119531422761,"gpt":0.3841453758342169,"spread":0.2780334226919409,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001103155,0.00007124977,0.0001502658,0.0000370577,0.00004505162,0.000006926432,0.0000480539,0.00006046314,0.000004306301],"category_scores_gemma":[0.0005188499,0.00006129262,0.00002790007,0.00008931877,0.00003601295,0.00000386181,0.00002852492,0.00004009085,1.383455e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001821607,"about_ca_system_score_gemma":0.00006735195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005714019,"about_ca_topic_score_gemma":0.0007684382,"domain_scores_codex":[0.9990916,0.0002146451,0.0002422631,0.0001971102,0.0001356061,0.0001187818],"domain_scores_gemma":[0.9996285,0.00002918048,0.0001415449,0.00008566205,0.00005264641,0.00006242514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000332516,0.0003416039,0.4408696,0.00028981,0.00008480895,0.00003073954,0.1195966,0.00008356573,0.007277812,0.000009623271,0.0007852736,0.430298],"study_design_scores_gemma":[0.02077325,0.01954329,0.1578536,0.0001469636,0.0002154439,0.0002783679,0.6555247,0.07044589,0.001830995,0.0002447634,0.07191181,0.001230925],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942805,0.002748109,0.0007471386,0.001705402,0.0000294814,0.0004605699,0.00001325954,0.000008119857,0.00000747237],"genre_scores_gemma":[0.9986964,0.00001145492,0.0008579012,0.0001667875,0.00007841443,0.00004650302,0.0001194574,0.000006553536,0.00001656411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.535928,"threshold_uncertainty_score":0.2499441,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03008292426685108,"gpt":0.2736927433707653,"spread":0.2436098191039142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002993016,0.00009745761,0.0001052193,0.00003492782,0.00007568533,0.0001381962,0.0001883864,0.00003725946,0.00008935911],"category_scores_gemma":[0.00003235141,0.00007692558,0.00001830035,0.0001674259,0.00001014003,0.0002079743,0.00009064284,0.00008910006,0.000008619442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001449956,"about_ca_system_score_gemma":0.00002834705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001020727,"about_ca_topic_score_gemma":0.00005530227,"domain_scores_codex":[0.9989833,0.00007101252,0.0001261097,0.0003142919,0.0003479571,0.0001573365],"domain_scores_gemma":[0.9995769,0.00001635376,0.00004394786,0.0002153553,0.00006011083,0.00008732641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000487822,0.00003058681,0.0005323814,0.0001190275,0.0000641743,0.00005728905,0.2741372,0.2631235,0.009830733,0.003440393,0.0001068006,0.4485092],"study_design_scores_gemma":[0.0003385021,0.00004715958,0.00008691903,0.0000128128,0.00001318036,0.000009138699,0.001766597,0.9970929,0.0002445146,0.00008775234,0.0001865455,0.0001139719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6446038,0.00120284,0.3525272,0.0006555273,0.00001785419,0.0001093425,8.739351e-7,0.00006934238,0.0008131657],"genre_scores_gemma":[0.9581193,0.000005131705,0.04059837,0.0009346282,0.0002315757,0.0000122934,0.000006237512,0.000009024469,0.00008349287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7339694,"threshold_uncertainty_score":0.3136934,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08551581455221315,"gpt":0.3744345054740225,"spread":0.2889186909218093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001466355,0.0001085153,0.000134953,0.00006573172,0.00008554028,0.0002454318,0.0002700293,0.000059636,0.00001997715],"category_scores_gemma":[0.0002680231,0.0001043714,0.00002970305,0.0002506744,0.00001913791,0.0004189084,0.0001783969,0.0001395818,0.000007602949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003843964,"about_ca_system_score_gemma":0.00004019452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001222918,"about_ca_topic_score_gemma":0.00002743525,"domain_scores_codex":[0.9983926,0.0001427835,0.0002626626,0.0004267886,0.0005631353,0.0002120636],"domain_scores_gemma":[0.9994675,0.00007161105,0.00008656937,0.0002115395,0.00007910514,0.00008366117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001868039,0.00001371673,0.001566339,0.00004112711,0.00000683233,0.00001079722,0.09973284,0.2242779,0.004667625,0.0007513145,0.00001157163,0.6689013],"study_design_scores_gemma":[0.000565826,0.00004141646,0.00161074,0.00002897112,0.000007016303,0.000003555546,0.0007098564,0.994669,0.0006486962,0.00156023,0.00003332863,0.0001214224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574541,0.001661441,0.03932577,0.0005991943,0.00005609523,0.0002141831,7.247127e-7,0.00008434751,0.0006041463],"genre_scores_gemma":[0.9862428,0.00001310763,0.01309859,0.0004293245,0.000170991,0.0000156747,0.000003863263,0.000008594588,0.00001701184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.770391,"threshold_uncertainty_score":0.4256141,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1262190574827426,"gpt":0.3325542575692801,"spread":0.2063352000865376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004236827,0.00006427943,0.00007333424,0.00003052684,0.0000887753,0.0001040988,0.0001566015,0.00003647521,0.000004816698],"category_scores_gemma":[0.0001215412,0.00005940389,0.00002719682,0.00009318389,0.000008457097,0.0001384232,0.00003108847,0.00004524927,0.000001621715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001876855,"about_ca_system_score_gemma":0.00002614907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009418794,"about_ca_topic_score_gemma":0.000007773088,"domain_scores_codex":[0.9992118,0.00005281677,0.0001326234,0.0002627412,0.0002328437,0.0001071593],"domain_scores_gemma":[0.9995732,0.00005922535,0.00006989596,0.0001737188,0.00007003523,0.00005394648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003767185,0.00001229021,0.0002177194,0.00007325917,0.000008003473,6.568968e-7,0.03813225,0.3101797,0.009951029,0.002190327,0.0002281591,0.6389689],"study_design_scores_gemma":[0.0004191364,0.00002756551,0.0002072631,0.000009619907,0.00001232241,4.556525e-7,0.000254638,0.9982149,0.0002250611,0.0003207457,0.0002366425,0.00007167744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.270721,0.000309378,0.7256548,0.002865965,0.00003795062,0.0002364797,0.000001427816,0.0000634689,0.0001095038],"genre_scores_gemma":[0.9782963,0.000002461989,0.02050545,0.0009925546,0.0001034421,0.00004414546,0.00001121844,0.000005851404,0.00003851421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7075753,"threshold_uncertainty_score":0.242242,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03543237694785305,"gpt":0.3434333187503363,"spread":0.3080009418024832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005585013,0.00008080676,0.0001845269,0.0000798527,0.0001968681,0.0000188996,0.00008461551,0.00004343122,0.0005998648],"category_scores_gemma":[0.0003284507,0.00006834546,0.00008711715,0.0006078966,0.0001119998,0.0000772497,0.00002062059,0.00005755992,0.00000393195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005800302,"about_ca_system_score_gemma":0.00003702308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001369486,"about_ca_topic_score_gemma":0.001136433,"domain_scores_codex":[0.9988701,0.0002265545,0.0001590937,0.0001739491,0.0004823487,0.00008799863],"domain_scores_gemma":[0.9995086,0.00009822063,0.0001138375,0.0001022858,0.00007704989,0.00009995807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001033456,0.00003903744,0.06952887,0.00006233724,0.0002379514,0.00000465393,0.9201532,0.001869987,0.00104627,0.00172897,0.0001429802,0.005082421],"study_design_scores_gemma":[0.008631343,0.0006343219,0.4456891,0.0000704619,0.008187454,0.000004006549,0.05798092,0.2888829,0.0000695714,0.05160351,0.1360119,0.00223449],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9796237,0.005091895,0.000112988,0.0003731255,0.00008782918,0.000130288,0.00001382914,0.00002532821,0.01454105],"genre_scores_gemma":[0.9992406,0.0000211695,0.00005838035,0.0001714175,0.0003619036,0.000005017788,0.00002420661,0.000005640497,0.000111691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8621722,"threshold_uncertainty_score":0.6568099,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0339419726941602,"gpt":0.2878343625034358,"spread":0.2538923898092756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003437254,0.00005983563,0.00006748402,0.00002712245,0.00006709217,0.0001033027,0.0001286043,0.0000307348,0.00003445593],"category_scores_gemma":[0.0000874877,0.0000552583,0.00001735654,0.0001315891,0.00001136007,0.0002536369,0.00007543446,0.00005758767,0.0000185798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000156371,"about_ca_system_score_gemma":0.00001502799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005652949,"about_ca_topic_score_gemma":0.000009597738,"domain_scores_codex":[0.9992036,0.00006135352,0.0001061497,0.0002325241,0.0003018308,0.00009458626],"domain_scores_gemma":[0.9996731,0.00002562371,0.00005315464,0.0001277741,0.00005892515,0.00006148344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001829869,0.0000242168,0.004570398,0.00006380134,0.0000230842,0.00001125043,0.1579848,0.004076305,0.004772296,0.003455207,0.0005018791,0.8244985],"study_design_scores_gemma":[0.0003184131,0.00003811624,0.0106132,0.000009058193,0.00001554691,0.000001819004,0.001153165,0.986012,0.000358137,0.0004524738,0.000940656,0.00008744989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8502939,0.0009109493,0.1459836,0.001428636,0.00006635437,0.0001451807,9.831158e-7,0.00007449655,0.001095952],"genre_scores_gemma":[0.9928231,0.00001317477,0.006473535,0.0004231156,0.0002162129,0.000008212893,0.000006243842,0.000003279214,0.00003309222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9819357,"threshold_uncertainty_score":0.2253368,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02440114564653542,"gpt":0.369499880025237,"spread":0.3450987343787016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001228909,0.00007100226,0.000156498,0.00004328642,0.0001394646,0.000003605415,0.0001391953,0.00004997158,0.00008612864],"category_scores_gemma":[0.0001924656,0.00004047946,0.00004011293,0.0001891279,0.0002133619,0.0000202805,0.00005672725,0.00007940148,0.000001154358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001834798,"about_ca_system_score_gemma":0.00003157719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003749732,"about_ca_topic_score_gemma":0.0001401233,"domain_scores_codex":[0.9987612,0.0003949652,0.0003535778,0.0001185674,0.0002530247,0.0001186927],"domain_scores_gemma":[0.9989659,0.0003763652,0.0002949718,0.0002586878,0.00008778864,0.00001629171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005200102,0.0002443095,0.0933589,0.0009669227,0.0002658731,0.000001700484,0.5022244,0.0001005703,0.03580129,0.004520771,0.001938388,0.3600569],"study_design_scores_gemma":[0.002197355,0.0004126877,0.6405547,0.0009500214,0.0001713228,0.000008468594,0.3330427,0.003694722,0.01302271,0.002300406,0.003493025,0.0001519077],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624433,0.02540386,0.00001051018,0.001056604,0.0001155312,0.0003893559,0.0000128279,0.000006868262,0.01056114],"genre_scores_gemma":[0.9989343,0.00008637684,0.0001119021,0.00005872951,0.00003233593,0.00002516285,0.000004318039,0.000005493986,0.0007414283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5471958,"threshold_uncertainty_score":0.1650704,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02172302327528814,"gpt":0.2949398695453348,"spread":0.2732168462700467,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004935308,0.0001087402,0.0001119791,0.00005754086,0.0001140357,0.0001986259,0.0001664919,0.00006400943,0.00003484947],"category_scores_gemma":[0.000263171,0.00009067075,0.00001976035,0.0002433908,0.00003124597,0.000327046,0.0001299405,0.0001191366,0.000005391306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001772309,"about_ca_system_score_gemma":0.00001763916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009913586,"about_ca_topic_score_gemma":0.00001796087,"domain_scores_codex":[0.9989866,0.0001068093,0.0001406548,0.0003286727,0.0003086669,0.0001286128],"domain_scores_gemma":[0.9995329,0.00005897475,0.00008398385,0.0001535848,0.00008066073,0.00008986126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002114295,0.00001307099,0.0003376231,0.00005748226,0.000009670541,0.0000100737,0.02381738,0.00004586246,0.01130109,0.0002791968,0.002762098,0.9613453],"study_design_scores_gemma":[0.0004609516,0.0001525678,0.001423124,0.00006755063,0.00003851197,0.00004290437,0.001052448,0.9863434,0.004472841,0.001069308,0.004614589,0.0002618301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7818754,0.04119306,0.168043,0.006573515,0.0002654354,0.0005407762,0.000004727102,0.0007315506,0.0007725139],"genre_scores_gemma":[0.9664814,0.00004863643,0.0319698,0.00120481,0.000183556,0.00001460767,0.00001592437,0.000008372092,0.00007283807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9862975,"threshold_uncertainty_score":0.3697446,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0626216750026778,"gpt":0.3642289984244982,"spread":0.3016073234218204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005836767,0.0001665197,0.0002563756,0.00007682934,0.0002887269,0.0003092455,0.0005093187,0.00008680594,0.00005749528],"category_scores_gemma":[0.001252002,0.0001309681,0.0001003869,0.0003915744,0.00002301015,0.0002359763,0.0002585585,0.0002154151,0.000004475897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003180477,"about_ca_system_score_gemma":0.00006371574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001210462,"about_ca_topic_score_gemma":0.000005119813,"domain_scores_codex":[0.9975189,0.0005054341,0.0004130773,0.0007482059,0.0005404448,0.0002739684],"domain_scores_gemma":[0.998408,0.0004959538,0.0003015329,0.0004666596,0.0002609797,0.00006690686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007476677,0.00002474947,0.0004461741,0.0002900854,0.00007966516,0.00000385946,0.1792818,0.4883529,0.005684498,0.0008056504,0.0000778367,0.324878],"study_design_scores_gemma":[0.0005970107,0.0001064388,0.0002589077,0.00006309991,0.00007157078,0.00001375434,0.00528372,0.9872324,0.00198437,0.0004168474,0.003815826,0.0001560798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2960221,0.001241334,0.6999384,0.001424923,0.00006496315,0.0005189716,9.816877e-7,0.0001288153,0.0006595262],"genre_scores_gemma":[0.3495299,0.00001134936,0.64944,0.0005197074,0.0003047481,0.00004207747,0.000004672603,0.00001890014,0.0001286868],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4988795,"threshold_uncertainty_score":0.5340725,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04360119139160799,"gpt":0.3828779568686983,"spread":0.3392767654770903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001556679,0.0001690499,0.0001757796,0.0001005336,0.0001921746,0.0004322769,0.000339213,0.00008413292,0.00001460959],"category_scores_gemma":[0.0005190167,0.0001135303,0.00006366464,0.0003424294,0.00006589433,0.0007218797,0.000181079,0.0002257398,0.000002940173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004029844,"about_ca_system_score_gemma":0.00005344848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003167629,"about_ca_topic_score_gemma":0.000005898708,"domain_scores_codex":[0.9984102,0.0001643522,0.000333596,0.0002617705,0.0006273326,0.0002027601],"domain_scores_gemma":[0.9989769,0.000200279,0.0003063382,0.0002592179,0.0001787126,0.00007849462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001417316,0.00001710585,0.0004312525,0.0001154059,0.00003485965,0.000003390391,0.14527,0.03314385,0.01146598,0.0003071575,0.00006239786,0.8090069],"study_design_scores_gemma":[0.0004286174,0.0003130465,0.0007855647,0.00009550332,0.00002452375,0.000009737882,0.001250835,0.9856439,0.01040249,0.0008774888,0.00001226977,0.0001560145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9738932,0.004756496,0.02041459,0.0002913648,0.00002415325,0.0003308461,0.000006075336,0.0001417455,0.0001414997],"genre_scores_gemma":[0.9816262,0.00003115524,0.01795025,0.0002443197,0.00009966587,0.00001502317,0.00001552051,0.000009905179,0.000007924223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9525,"threshold_uncertainty_score":0.462963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Portuguese; Computer science; Data sharing; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.1296680340292582,"gpt":0.3399750691332857,"spread":0.2103070351040275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009671627,0.00006222428,0.00007755815,0.00003366215,0.00003517757,0.0001001395,0.0004361233,0.00001713196,0.0000125194],"category_scores_gemma":[0.0002176836,0.00005219031,0.000004141042,0.0001335577,0.00001456736,0.0002059791,0.0007263126,0.00005019301,0.000007374686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008346256,"about_ca_system_score_gemma":0.00001335893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005414084,"about_ca_topic_score_gemma":0.0000462483,"domain_scores_codex":[0.9991092,0.00008690405,0.0001307435,0.0003717821,0.0001955387,0.0001057998],"domain_scores_gemma":[0.9995775,0.00002509862,0.00004249777,0.0002840293,0.00001869184,0.00005222082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000006799387,0.00001039637,0.01490134,0.00001826661,0.000006559451,0.00003400583,0.02669826,0.0000125026,0.0003225409,0.0001488338,0.0001901967,0.9576503],"study_design_scores_gemma":[0.0009136865,0.00004945423,0.7193,0.00004973863,0.00001455215,0.00001516036,0.002536286,0.265954,0.000166678,0.0002578858,0.01053529,0.0002073204],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861171,0.005987337,0.001952224,0.001663189,0.00004330327,0.000138811,0.000001502522,0.00005612794,0.004040352],"genre_scores_gemma":[0.9946229,0.000431281,0.004275979,0.0005734302,0.00004472076,0.000002005065,0.00002533357,0.000004269475,0.0000200629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.957443,"threshold_uncertainty_score":0.2128259,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1083050715093138,"gpt":0.3766665924784349,"spread":0.268361520969121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008892688,0.00007536117,0.00009772825,0.0000271982,0.0001486269,0.00004291395,0.0001093593,0.00007942798,0.0003936757],"category_scores_gemma":[0.0001935672,0.00005222151,0.00003406708,0.0001070345,0.00005683535,0.00002411026,0.00002540785,0.0001181462,0.00003515467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000124951,"about_ca_system_score_gemma":0.00002522498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002394066,"about_ca_topic_score_gemma":0.0001202152,"domain_scores_codex":[0.9990823,0.0001628074,0.0001290954,0.0002137822,0.0002137048,0.0001982909],"domain_scores_gemma":[0.9994788,0.0001733235,0.00007106359,0.0001421534,0.00007711688,0.00005760264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001415286,0.00003008374,0.0006837281,0.00003121497,0.00009392446,0.000002384296,0.5691436,0.00007745116,0.002951798,0.0003667563,0.009864007,0.4166135],"study_design_scores_gemma":[0.005942931,0.001499811,0.5976992,0.00003867273,0.0003361275,0.00003027397,0.03593514,0.2043377,0.0004042826,0.005404594,0.1478264,0.0005449659],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9849318,0.004538592,0.0004195269,0.006463102,0.0001382693,0.0007165662,0.00002133652,0.00002835157,0.002742511],"genre_scores_gemma":[0.9977614,0.00001410821,0.00008981283,0.0007261169,0.0004268031,0.0002059513,0.00004526108,0.00001207536,0.0007184272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5970154,"threshold_uncertainty_score":0.4310473,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03570656174926953,"gpt":0.3177618021598226,"spread":0.2820552404105531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157449,0.00007861167,0.0001224178,0.00005574935,0.0004635167,0.0001078404,0.00008583909,0.00005322284,0.0001486259],"category_scores_gemma":[0.000301626,0.00006986825,0.00003301181,0.0003009514,0.000104607,0.0001748315,0.00003863443,0.00006046378,0.00003435673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003358179,"about_ca_system_score_gemma":0.00004337935,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01271558,"about_ca_topic_score_gemma":0.006530082,"domain_scores_codex":[0.9986573,0.0001709338,0.0001833764,0.0001365515,0.00066043,0.0001913394],"domain_scores_gemma":[0.9994912,0.00005716688,0.0001125469,0.00007753196,0.0001457983,0.000115741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001903634,0.00000753221,0.02717495,0.00004988758,0.00003864629,0.000004847843,0.9121115,0.00004548147,0.0001805891,0.001206886,0.0009166814,0.05824395],"study_design_scores_gemma":[0.001543783,0.0001015695,0.1103433,0.00008410485,0.0001287219,0.000005368853,0.7005152,0.01277615,0.00005523948,0.0002328583,0.1737734,0.0004403228],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9603944,0.002368001,0.00003746957,0.003576588,0.0001015843,0.0003812645,0.000007721489,0.00008741,0.03304555],"genre_scores_gemma":[0.9987488,0.0001624277,0.00005313892,0.00041185,0.0003054084,0.00002530328,0.000009711624,0.000005405699,0.0002779851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2115963,"threshold_uncertainty_score":0.9938588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}