{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2769,"total_is_capped":false,"direct_labels_cover":6,"predictions_cover":2769,"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":"e471de49da32","filters":{"topic":"Topic Modeling"}},"results":[{"id":"W1662133657","doi":"10.1613/jair.2934","title":"From Frequency to Meaning: Vector Space Models of Semantics","year":2010,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Topic Modeling","field":"Computer Science","cited_by":2883,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Semantics (computer science); Meaning (existential); Computer science; Context (archaeology); Space (punctuation); Perspective (graphical); Artificial intelligence; Programming language; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2081680926678031,"gpt":0.4142808458992752,"spread":0.2061127532314721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003213811,0.0001176282,0.0002966262,0.0005455058,0.000113519,0.0002029921,0.002119904,0.0001140216,0.00007000169],"category_scores_gemma":[0.001232785,0.0001025442,0.0001204978,0.0008725387,0.0001227681,0.0006347563,0.000373881,0.001159121,0.00005990903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006027037,"about_ca_system_score_gemma":0.0004517125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005379259,"about_ca_topic_score_gemma":0.0001955649,"domain_scores_codex":[0.9967297,0.0001750543,0.0008508869,0.0002872933,0.001499836,0.0004572186],"domain_scores_gemma":[0.9964998,0.0005914351,0.0002454885,0.0006953375,0.001644908,0.000322985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003205932,0.0001407617,0.00008810333,0.00001268341,0.00002690838,0.00005958229,0.007730806,0.01119216,0.3854487,0.5441409,0.0001437419,0.05098359],"study_design_scores_gemma":[0.00001660492,0.000209433,0.00001778377,0.00006690537,0.000003495115,0.0000142826,0.0006188275,0.2786266,0.2547538,0.4654956,0.00008375358,0.00009292806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2848188,0.00004541676,0.7103081,0.003408977,0.0007623553,0.00009915532,0.000001380825,0.0000105386,0.0005452791],"genre_scores_gemma":[0.7964733,0.00001941509,0.2028827,0.00002013514,0.0005668564,0.000001277343,1.096644e-7,0.000009334332,0.00002687202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5116545,"threshold_uncertainty_score":0.5035867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020278455","doi":"10.1075/li.30.1.03nad","title":"A survey of named entity recognition and classification","year":2007,"lang":"en","type":"article","venue":"Lingvisticae Investigationes","topic":"Topic Modeling","field":"Computer Science","cited_by":2488,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"Natural Environment Research Council; Alfred P. Sloan Foundation","keywords":"Computer science; Natural language processing; Matching (statistics); Artificial intelligence; Field (mathematics); Information retrieval; Named entity; Key (lock); Word (group theory); Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1391236913969597,"gpt":0.291564756940622,"spread":0.1524410655436623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117789,0.00006522706,0.00009734499,0.00009683724,0.00006261452,0.00005681126,0.0001601355,0.0000513895,0.000004140653],"category_scores_gemma":[0.001418968,0.00006853951,0.00001201002,0.000280802,0.0001054132,0.0002119605,0.000051333,0.00006565557,0.00001301577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000014837,"about_ca_system_score_gemma":0.0000462235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002239544,"about_ca_topic_score_gemma":0.00008769597,"domain_scores_codex":[0.9991266,0.00006669325,0.0003052846,0.0002229654,0.0001660903,0.0001123552],"domain_scores_gemma":[0.9989266,0.0003552068,0.000143931,0.0002300088,0.0002643354,0.00007995602],"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":[0.00001818056,0.0001210797,0.2097689,0.0001714589,0.00003157621,0.000003724846,0.002256163,0.00005471837,0.0239538,0.3013134,0.00007351463,0.4622335],"study_design_scores_gemma":[0.0001503918,0.00002258386,0.7463974,0.00003927819,0.000006699703,0.000003025695,0.00001847549,0.1947369,0.003461302,0.05498087,0.00006537583,0.0001176778],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4003949,0.00003333774,0.5988668,0.0001302226,0.0001061395,0.00006114188,0.000003956045,0.00004516589,0.0003583961],"genre_scores_gemma":[0.9026676,0.00000523313,0.09717278,0.00006892584,0.00003181904,0.000002756506,0.00002681557,0.000003519418,0.00002051004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5366285,"threshold_uncertainty_score":0.279496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963929190","doi":"10.18653/v1/k16-1028","title":"Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2209,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Automatic summarization; Sequence (biology); Computer science; Natural language processing; Artificial intelligence; Information retrieval; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.07923942989030704,"gpt":0.3157808564587726,"spread":0.2365414265684656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002945754,0.0002820988,0.0002691238,0.0002039248,0.0001255043,0.0003872117,0.0009478129,0.0002504221,0.00002940328],"category_scores_gemma":[0.00007872171,0.0002374904,0.00005099802,0.0001483798,0.00006355652,0.0006036849,0.002035933,0.0003230206,0.00003804407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002391577,"about_ca_system_score_gemma":0.0003541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003401756,"about_ca_topic_score_gemma":0.00002906137,"domain_scores_codex":[0.9978275,0.00005738684,0.0003529034,0.001069339,0.0003500779,0.0003427813],"domain_scores_gemma":[0.9983839,0.000102362,0.0001989078,0.0009426425,0.0001916033,0.0001805717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001836218,0.00009785961,0.002908358,0.0003077505,0.000150982,0.0001325364,0.006224663,0.04277358,0.1088875,0.4511378,0.0003208148,0.3870398],"study_design_scores_gemma":[0.0002562839,0.00003590213,0.0009405413,0.0004163207,0.00002268153,0.00005174505,0.00005574581,0.8223833,0.006174138,0.1682118,0.0004998134,0.0009517106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0403166,0.00004176645,0.9466335,0.001436619,0.0007280678,0.0003824147,0.0000188399,0.0001859584,0.01025619],"genre_scores_gemma":[0.6938267,0.00002642131,0.3048522,0.0005148061,0.000162289,0.00001761072,0.000004964082,0.00001670508,0.0005783935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7796097,"threshold_uncertainty_score":0.9684578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158139315","doi":"","title":"Word Representations: A Simple and General Method for Semi-Supervised Learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1948,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Chunking (psychology); Computer science; Word (group theory); Natural language processing; Artificial intelligence; Simple (philosophy); Word embedding; Speech recognition; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03624813891496347,"gpt":0.3391485912100758,"spread":0.3029004522951123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003322214,0.00005857632,0.00007735725,0.0000423884,0.000122229,0.0001275838,0.0002228791,0.0000370851,0.00002914094],"category_scores_gemma":[0.0001494023,0.00005244952,0.00002798363,0.00008763912,0.000009005977,0.0002400343,0.0001379835,0.0001189786,0.00000262164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003549305,"about_ca_system_score_gemma":0.00002111957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001316907,"about_ca_topic_score_gemma":0.0000601682,"domain_scores_codex":[0.999332,0.00003439793,0.0001198999,0.0002867072,0.00007990946,0.0001471624],"domain_scores_gemma":[0.9993864,0.0002051438,0.00002502348,0.0002799807,0.00004687377,0.0000566208],"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":[0.000004113426,0.00001700202,0.004194188,0.00001644786,0.00001507727,0.000001824634,0.001571377,0.003275895,0.05455559,0.1932544,0.0008937337,0.7422004],"study_design_scores_gemma":[0.0002271341,0.00001124517,0.0004458894,0.00000106494,0.000002381105,0.000007320909,0.00004352707,0.9744841,0.002082067,0.01350677,0.009113777,0.00007471094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07241453,0.00001331968,0.9252523,0.0009045572,0.0001213627,0.0001326249,2.846191e-7,0.0001189866,0.001042056],"genre_scores_gemma":[0.08296044,0.000001949339,0.9147415,0.0002929469,0.00009871546,0.0000308554,0.000001583223,0.000004914515,0.001867062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9712082,"threshold_uncertainty_score":0.2138829,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962883855","doi":"10.1609/aaai.v30i1.9883","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1725,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Generative grammar; Computer science; Bootstrapping (finance); Word (group theory); Artificial intelligence; End-to-end principle; Artificial neural network; Language model; Domain (mathematical analysis); Encoder; Recurrent neural network; Task (project management); Natural language processing; Generative model; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06428255094117762,"gpt":0.2761510849675109,"spread":0.2118685340263333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004055073,0.0001878242,0.0002424781,0.00009298053,0.0001951386,0.0002847347,0.0007839491,0.000076581,0.0000110913],"category_scores_gemma":[0.00002785929,0.0001243274,0.00006630438,0.0002660689,0.00003582194,0.0007036934,0.000562578,0.0001235408,0.00001494675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001090648,"about_ca_system_score_gemma":0.0000755439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002268608,"about_ca_topic_score_gemma":0.00001528524,"domain_scores_codex":[0.997924,0.0001826563,0.0003392405,0.0006185231,0.0003468633,0.00058872],"domain_scores_gemma":[0.9988165,0.0002157405,0.00006273585,0.000599679,0.00007034503,0.0002350118],"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":[0.00000203734,0.000005081255,0.00005044509,0.000002277977,0.000008082949,0.000009170398,0.0001374153,0.5833902,0.003816863,0.3977775,0.0001054244,0.01469549],"study_design_scores_gemma":[0.0001588363,0.00002595506,0.00001660269,0.00004712131,0.000003499975,0.00002776115,0.000003900217,0.9822811,0.0003468812,0.01662206,0.0002606887,0.000205556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09970267,0.00008561205,0.8969024,0.001028419,0.001228432,0.0002029102,0.000002174768,0.0001900127,0.0006573214],"genre_scores_gemma":[0.6494449,0.000001614955,0.3493308,0.000352596,0.0007027478,0.00001051622,2.321432e-7,0.00001012877,0.0001465129],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5497422,"threshold_uncertainty_score":0.5069926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889787757","doi":"10.18653/v1/d18-1259","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1582,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Office of Naval Research; Defense Advanced Research Projects Agency; Université de Montréal; Nvidia; National Science Foundation","keywords":"Zhàng; Question answering; Computer science; Artificial intelligence; Natural language processing; Information retrieval; History; China; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.06108907148323083,"gpt":0.3121959901327288,"spread":0.2511069186494979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002469346,0.00007712805,0.00007540946,0.00005082932,0.0001645953,0.0001027414,0.0004744481,0.00003454226,0.00002313211],"category_scores_gemma":[0.00005041309,0.00007084428,0.00002123295,0.00009718935,0.00002213311,0.0006668782,0.0002614535,0.00003592603,0.00006530648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003088665,"about_ca_system_score_gemma":0.00002300858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002290943,"about_ca_topic_score_gemma":0.0001140961,"domain_scores_codex":[0.9992207,0.00001530378,0.0001147968,0.0003197809,0.0001000965,0.0002293197],"domain_scores_gemma":[0.9993242,0.000031966,0.00003113194,0.000480187,0.00007588419,0.00005663878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007614522,0.000438397,0.002251973,0.0002250929,0.00008955826,0.00005104122,0.006496566,0.002162502,0.01605991,0.4697003,0.1985192,0.3039293],"study_design_scores_gemma":[0.0004585729,0.00007737394,0.0001412629,0.00001400476,0.000003445047,0.00000522116,0.00009423505,0.9326215,0.003997256,0.000899751,0.06153224,0.0001551578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004263993,0.00001264351,0.9943596,0.0002725204,0.0003903614,0.0001730958,0.00004015704,0.0001362952,0.0003513343],"genre_scores_gemma":[0.2100769,0.000002834592,0.7883681,0.0004294417,0.0001924139,0.0000278295,0.00005797013,0.000006076058,0.0008384414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.930459,"threshold_uncertainty_score":0.2888946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2608787653","doi":"10.18653/v1/p17-1152","title":"Enhanced LSTM for Natural Language Inference","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; York University; National Research Council Canada","funders":"Fundamental Research Funds for the Central Universities; Chinese Academy of Sciences","keywords":"Inference; Computer science; Artificial intelligence; Parsing; Language model; Machine learning; Natural language; Artificial neural network; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.03843647516708471,"gpt":0.3355466537017409,"spread":0.2971101785346562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828932,0.0001847408,0.0002325664,0.00005655256,0.0001081291,0.0004604324,0.002704789,0.0001622889,0.00001363675],"category_scores_gemma":[0.0002258727,0.0001591636,0.000118892,0.00001813308,0.00002114594,0.0002064002,0.002211144,0.0003526119,0.00002519124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003812389,"about_ca_system_score_gemma":0.0001707928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001521189,"about_ca_topic_score_gemma":0.00007719436,"domain_scores_codex":[0.9987295,0.00001603999,0.0001891609,0.0006278502,0.0001785922,0.0002588544],"domain_scores_gemma":[0.9977115,0.0000996141,0.0001687668,0.001856385,0.0001089951,0.0000546754],"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":[0.000008284051,0.0000413978,0.0000335175,0.0003651794,0.00006748217,0.00001291215,0.004681819,0.001523757,0.00455143,0.2036732,0.001164988,0.7838761],"study_design_scores_gemma":[0.000280703,0.00001748568,0.0001616623,0.0001374949,0.000007782719,0.000001638897,0.00002395677,0.9524945,0.01548301,0.03007574,0.0008368498,0.0004791904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008169777,0.0003383315,0.978385,0.0006069916,0.002324293,0.0003544967,0.000004389683,0.0002652908,0.009551418],"genre_scores_gemma":[0.7560462,0.000008206799,0.2382822,0.0001781811,0.0002018647,0.00006567398,0.000007673018,0.000006781213,0.005203173],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9509707,"threshold_uncertainty_score":0.6490502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W196214544","doi":"","title":"Generating Text with Recurrent Neural Networks","year":2011,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Recurrent neural network; Computer science; Language model; Sequence (biology); Artificial intelligence; Hessian matrix; Artificial neural network; Multiplicative function; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04898282774934054,"gpt":0.2321847635042877,"spread":0.1832019357549472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000780874,0.00006567065,0.00005686446,0.00001903694,0.00005672097,0.00005344203,0.0003438172,0.00001903663,0.00003420027],"category_scores_gemma":[0.000002929793,0.00004532373,0.00001495916,0.00009261105,0.000009195297,0.0002047054,0.0001161378,0.00007981079,0.000008209561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000783808,"about_ca_system_score_gemma":0.00001042043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003479283,"about_ca_topic_score_gemma":0.00003624874,"domain_scores_codex":[0.9994098,0.00001834799,0.00009691939,0.0002118168,0.00009113717,0.0001719761],"domain_scores_gemma":[0.9995754,0.000009694758,0.00002776344,0.0003109294,0.00002579682,0.00005042356],"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":[0.000004531865,0.00004403006,0.005398781,0.000004351088,0.00001168687,0.00002553019,0.001667319,0.05920076,0.00005599836,0.08985364,0.0004814982,0.8432519],"study_design_scores_gemma":[0.00006732159,0.0000407965,0.0003397128,0.000003942795,0.000001014451,0.00001106266,0.000009447175,0.9992257,0.00006756403,0.0000922834,0.00006434572,0.00007682036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03941758,0.00004469147,0.9522316,0.00008580167,0.0002428769,0.0000467391,1.948522e-8,0.0001287953,0.007801845],"genre_scores_gemma":[0.6916773,9.886186e-7,0.3078077,0.0002855608,0.0000710051,0.000003390829,1.285802e-7,0.000002911274,0.0001509939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9400249,"threshold_uncertainty_score":0.1848248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963903950","doi":"10.18653/v1/d16-1230","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":916,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science; Empirical research; Artificial intelligence; Machine learning; Natural language processing; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2550579332141903,"gpt":0.3930564024462317,"spread":0.1379984692320415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006673118,0.0001679202,0.00028308,0.0004269074,0.0001186963,0.0001714551,0.0006975773,0.00008847511,0.000003489981],"category_scores_gemma":[0.00207707,0.000113781,0.000063953,0.0006043391,0.00001082707,0.0006733279,0.0001645678,0.00004046387,0.000008152426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002584695,"about_ca_system_score_gemma":0.000234544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007360114,"about_ca_topic_score_gemma":0.0001695687,"domain_scores_codex":[0.996129,0.001395629,0.0004658456,0.0006885901,0.001052992,0.0002679643],"domain_scores_gemma":[0.997132,0.0005350269,0.0001347645,0.001031848,0.001008711,0.0001576348],"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":[0.001712132,0.001895783,0.006831488,0.0001111407,0.0001888749,0.00001051969,0.02493049,0.01975474,0.4562955,0.00915315,0.001363337,0.4777528],"study_design_scores_gemma":[0.002695557,0.00167884,0.006000621,0.0000152464,0.00005970445,0.000002015784,0.0005347801,0.9783614,0.01021887,0.0001686121,0.00004782202,0.0002165055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4955571,0.000004970046,0.5013325,0.001517159,0.0003406292,0.001170243,0.000006217076,0.00006380085,0.000007371614],"genre_scores_gemma":[0.9523298,5.445966e-7,0.04687208,0.0001559312,0.0002280359,0.0002718078,0.000006446245,0.0000136502,0.0001217226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9586067,"threshold_uncertainty_score":0.4639854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2247119764","doi":"10.1609/aaai.v25i1.7917","title":"Learning Structured Embeddings of Knowledge Bases","year":2011,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":861,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"WordNet; Computer science; Artificial intelligence; Process (computing); Natural language processing; Information retrieval; Knowledge extraction; Word (group theory); Annotation; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03699051865105631,"gpt":0.2521480397486367,"spread":0.2151575210975804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001013877,0.00005384479,0.00008311048,0.00005187734,0.00003020776,0.0000112498,0.0003983018,0.0000254281,0.0001761743],"category_scores_gemma":[0.00003556875,0.00004480149,0.00002968847,0.0001111538,0.00001518562,0.0001755964,0.0001684126,0.00006454559,0.00001882106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006659582,"about_ca_system_score_gemma":0.00002338056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005925358,"about_ca_topic_score_gemma":0.000008270773,"domain_scores_codex":[0.9995099,0.00002259529,0.0001240271,0.0001594898,0.00007281933,0.0001111496],"domain_scores_gemma":[0.9996137,0.00002672753,0.00004308259,0.0002308191,0.00005126507,0.0000344304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005685888,0.00007138583,0.01717259,0.00005292262,0.00002608035,0.000006255829,0.02522447,0.0003760264,0.007830676,0.6711524,0.0004730095,0.2776085],"study_design_scores_gemma":[0.0004783072,0.0002162626,0.01371041,0.000049565,0.000009664572,0.00001772903,0.0004354973,0.7970368,0.1629552,0.02045305,0.004240487,0.0003970921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1588257,0.00003975036,0.7657936,0.00001665447,0.0001592378,0.00003391895,8.131894e-8,0.0001308544,0.07500026],"genre_scores_gemma":[0.8240632,0.000001117337,0.1748437,0.00002167992,0.00001512026,8.285304e-7,9.338878e-8,0.000002620122,0.001051712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7966607,"threshold_uncertainty_score":0.1928985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2911227954","doi":"10.1162/tacl_a_00041","title":"Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science","year":2018,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":808,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Macquarie University; York University; University of Washington; University of California, San Diego; National Science Foundation","keywords":"Embarrassment; Computer science; Natural (archaeology); Data science; Field (mathematics); Natural language; Lead (geology); Style (visual arts); Engineering ethics; Natural language processing; Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06724238139102369,"gpt":0.3486267136322955,"spread":0.2813843322412718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001040362,0.00008277925,0.0001154561,0.00008800314,0.0006307623,0.0001744528,0.0007515508,0.00003308117,2.752853e-7],"category_scores_gemma":[0.001464541,0.00007252009,0.00004040891,0.0002829642,0.00008156747,0.0002633239,0.00007212115,0.00007421917,4.418186e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001918678,"about_ca_system_score_gemma":0.0002303411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001639019,"about_ca_topic_score_gemma":0.000007367029,"domain_scores_codex":[0.9987336,0.00002583263,0.0003345165,0.000294184,0.0004242021,0.0001876903],"domain_scores_gemma":[0.9974296,0.000449778,0.0003731175,0.0002653386,0.001449169,0.00003297594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001752122,0.0006254512,0.0116395,0.00499913,0.001014867,0.000001681007,0.04147508,0.2156678,0.003127392,0.3679345,0.001178781,0.3521606],"study_design_scores_gemma":[0.0004052899,0.00002500848,0.0003626827,0.00006722376,0.00003556088,9.827248e-7,0.000241395,0.9950996,0.0006652265,0.002375625,0.0006384904,0.00008293195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006648411,0.00005461713,0.9911957,0.0003660802,0.001049417,0.0003257825,0.000217587,0.00005824554,0.00008412446],"genre_scores_gemma":[0.6946006,2.516228e-7,0.3050706,0.00005648428,0.0001901187,0.000008881297,0.00001818428,0.000005469771,0.00004937191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7794318,"threshold_uncertainty_score":0.4851377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2557764419","doi":"10.18653/v1/w17-2623","title":"NewsQA: A Machine Comprehension Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":742,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Textual entailment; Computer science; Comprehension; Natural language processing; Artificial intelligence; Matching (statistics); Set (abstract data type); Word (group theory); Process (computing); Exploratory analysis; Information retrieval; Machine learning; Logical consequence; Data science; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05848331174708454,"gpt":0.3064087311719761,"spread":0.2479254194248916,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008816955,0.00005403512,0.00006646345,0.00001828972,0.0002461974,0.0002628193,0.001319198,0.00001860932,0.00004017734],"category_scores_gemma":[0.00001923999,0.00004236995,0.00001518855,0.00001404128,0.00001686241,0.0004687571,0.0008312701,0.00005373596,0.000159751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005861908,"about_ca_system_score_gemma":0.00001114465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004917207,"about_ca_topic_score_gemma":0.00007834107,"domain_scores_codex":[0.9994643,0.00001065036,0.00008077696,0.0002159422,0.0001122197,0.0001160659],"domain_scores_gemma":[0.9982005,0.00001384705,0.00004423927,0.001677472,0.00001302975,0.00005087146],"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":[0.000006191231,0.0000914506,0.004994242,0.00001879569,0.00001926218,0.00009480955,0.0002121711,0.0003528376,0.00240844,0.3509961,0.1368288,0.5039768],"study_design_scores_gemma":[0.0002558783,0.00001355173,0.004238506,0.000006139664,0.000001461999,0.00001344819,0.000001737012,0.870136,0.0003671494,0.002993393,0.1218651,0.0001076397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00401394,0.0000300604,0.9840404,0.003687455,0.0003046205,0.00005090975,0.00001817085,0.00009306747,0.007761398],"genre_scores_gemma":[0.7826574,0.000005585123,0.2153838,0.00111857,0.00006825837,0.000001685306,0.00003516429,0.000003475196,0.0007260134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8697832,"threshold_uncertainty_score":0.2534372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3022187094","doi":"10.1609/aaai.v31i1.10983","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":702,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research","keywords":"Computer science; Latent variable; Generative grammar; Generative model; Latent variable model; Artificial intelligence; Variable (mathematics); Artificial neural network; Encoder; Task (project management); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09665800747503062,"gpt":0.2927783749652687,"spread":0.1961203674902381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003595554,0.0001126959,0.0001480982,0.00003266364,0.0006183906,0.000577991,0.001176994,0.00006830913,0.000007627094],"category_scores_gemma":[0.0001412715,0.00009423242,0.00006116986,0.00002057719,0.00002744918,0.0005513821,0.0004772572,0.00009647853,0.000009684418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002201713,"about_ca_system_score_gemma":0.000102256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008627069,"about_ca_topic_score_gemma":0.00005201518,"domain_scores_codex":[0.9988582,0.00001676324,0.000210155,0.000424587,0.0001609162,0.0003293934],"domain_scores_gemma":[0.9986754,0.00006789796,0.0000783155,0.001011974,0.00007152594,0.00009488119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004082646,0.00004621932,0.0002883459,0.00001775259,0.00001798295,0.000002417448,0.000803214,0.1992843,0.002607117,0.7689807,0.001008978,0.02693883],"study_design_scores_gemma":[0.0002377357,0.00001457517,0.00002595189,0.000006911134,0.000003001792,0.000002345747,0.000001348914,0.9206507,0.0003279624,0.07835956,0.0002441443,0.0001257778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00416594,0.0000179789,0.9889501,0.001519604,0.0003167327,0.0001802015,0.000002650793,0.0001371745,0.004709592],"genre_scores_gemma":[0.2977768,0.000002503065,0.6988483,0.0004695146,0.0001486688,0.00004030995,0.000001404631,0.000007032905,0.002705534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7213664,"threshold_uncertainty_score":0.557358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131876387","doi":"10.1145/2661829.2661935","title":"A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Explicit semantic analysis; Artificial intelligence; Natural language processing; Sentence; Word (group theory); Information retrieval; Context (archaeology); Probabilistic latent semantic analysis; Ranking (information retrieval); SemEval; Pooling; Semantic computing; Task (project management); Semantic Web; Semantic technology","retraction":null,"screen_n_in":null,"score":{"opus":0.01307392977358029,"gpt":0.2120307665124632,"spread":0.1989568367388829,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000149019,0.00007437658,0.00008194666,0.00005523649,0.00008147712,0.00009740917,0.0002441365,0.00003345094,0.00000266071],"category_scores_gemma":[0.00003191337,0.00005447581,0.00002293961,0.00008989045,0.0000102747,0.0007535902,0.00005552214,0.00005552864,0.000005161412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002735862,"about_ca_system_score_gemma":0.00005851064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000755148,"about_ca_topic_score_gemma":0.000005175665,"domain_scores_codex":[0.9993479,0.000008000284,0.0001536083,0.0001359432,0.0001982054,0.0001563434],"domain_scores_gemma":[0.9994816,0.00003408064,0.00005715089,0.0002430263,0.0001416666,0.00004249186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001425029,0.000003476054,0.0001094063,0.00002821309,0.000007295104,8.030069e-8,0.0002789272,0.4802617,0.0001698322,0.51647,0.00009594951,0.00256084],"study_design_scores_gemma":[0.0003580814,0.00003227453,0.0001089376,0.00001006723,0.000003814654,0.000007332786,0.000004859276,0.9803374,0.00043537,0.01834271,0.0002707826,0.0000883086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03557831,0.000003758068,0.9630482,0.0005826077,0.00008120578,0.0001680004,0.000002020166,0.00010638,0.0004295818],"genre_scores_gemma":[0.6910501,3.016264e-7,0.3084114,0.0004126761,0.00002627371,0.000002300711,0.000004464844,0.00000220265,0.00009034661],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6554717,"threshold_uncertainty_score":0.2221459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W68132019","doi":"10.1007/s10994-013-5363-6","title":"A semantic matching energy function for learning with multi-relational data","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agence Nationale de la Recherche; Compute Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; WordNet; Artificial intelligence; Statistical relational learning; Natural language processing; Sentence; Relational database; Relation (database); Semantic matching; Semantics (computer science); Parsing; Word (group theory); Context (archaeology); Information retrieval; Matching (statistics); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03555843756672505,"gpt":0.2470883916188504,"spread":0.2115299540521254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003938468,0.0001559131,0.0001496432,0.000107549,0.0004376358,0.0002358764,0.0005869463,0.00005343849,0.00004724959],"category_scores_gemma":[0.0001144741,0.0001338279,0.00003206465,0.0001650836,0.00001445449,0.001060323,0.0004217863,0.0003336057,0.00003385874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002730786,"about_ca_system_score_gemma":0.00003851376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009437639,"about_ca_topic_score_gemma":0.0001124578,"domain_scores_codex":[0.9985829,0.0001065829,0.0002151714,0.0005529302,0.0002456186,0.0002967699],"domain_scores_gemma":[0.999032,0.000198396,0.0001438876,0.0004784648,0.00007970477,0.00006753036],"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":[0.00001723725,0.00004543965,0.02787056,0.00004503271,0.00007097876,0.000003785454,0.0008413686,0.7546744,0.001073619,0.02800208,0.00009737399,0.1872581],"study_design_scores_gemma":[0.0005311448,0.00008330824,0.00302763,0.0000340678,0.00001165143,0.00001508151,0.0000427985,0.9867896,0.00001072467,0.0010097,0.008264799,0.0001794394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01512985,0.0001256628,0.9832813,0.00062011,0.0001360496,0.0001452741,8.061429e-7,0.0003179715,0.0002429923],"genre_scores_gemma":[0.725957,0.000002594358,0.2718276,0.0001518331,0.0001091587,0.00003197351,0.00008460276,0.00002163663,0.001813511],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7114537,"threshold_uncertainty_score":0.5457344,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2744909235","doi":"10.1016/j.neunet.2014.09.005","title":"Challenges in representation learning: A report on three machine learning contests","year":2014,"lang":"en","type":"article","venue":"Neural Networks","topic":"Topic Modeling","field":"Computer Science","cited_by":676,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Learning to learn; Feature learning; Machine learning; Mathematics education; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.07473609516329448,"gpt":0.2917676883922016,"spread":0.2170315932289071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144415,0.0001301689,0.0001855015,0.00007952236,0.0000871722,0.00007324638,0.000343226,0.00008019137,0.000003145375],"category_scores_gemma":[0.0003460436,0.0001221898,0.00004594608,0.0001719917,0.00001491108,0.0002112414,0.000150488,0.0006556227,0.000007056291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002475058,"about_ca_system_score_gemma":0.000006460659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006786645,"about_ca_topic_score_gemma":0.0003858974,"domain_scores_codex":[0.9984179,0.000226255,0.0002913612,0.0005523593,0.0002305856,0.0002814977],"domain_scores_gemma":[0.9989905,0.0002876694,0.0001566452,0.0004699576,0.00003415188,0.00006103532],"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":[0.000007137201,0.00001236979,0.04595502,0.000002843898,0.000002152008,0.00007558255,0.0001294615,0.6221628,0.000009898873,0.003880547,0.000009214436,0.3277529],"study_design_scores_gemma":[0.0002637584,0.0001256665,0.02849583,0.00002968001,0.000001355133,0.00006939829,0.000007092927,0.9690793,0.000009936835,0.0007947084,0.001007022,0.0001162951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2017872,0.0009344963,0.7801663,0.004447049,0.0008267298,0.0002449321,2.939139e-8,0.0004842367,0.011109],"genre_scores_gemma":[0.9979354,0.00007591283,0.00136187,0.0001497248,0.0002488069,0.00001272446,0.000003597356,0.0000122323,0.0001997113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7961482,"threshold_uncertainty_score":0.4982754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392193048","doi":"10.1038/s41591-024-02855-5","title":"Adapted large language models can outperform medical experts in clinical text summarization","year":2024,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":664,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Biomedical Imaging and Bioengineering; Foundation for the National Institutes of Health; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Agency for Healthcare Research and Quality; National Institutes of Health; National Heart, Lung, and Blood Institute","keywords":"Automatic summarization; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02209648554058223,"gpt":0.3445173154923743,"spread":0.3224208299517921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001697275,0.000147522,0.0002728208,0.0002362946,0.00003229342,0.00003330201,0.0006487123,0.0005139924,0.0001934108],"category_scores_gemma":[0.0007093954,0.0001063249,0.00005047096,0.0005773604,0.000048225,0.0002477739,0.0001936377,0.00115871,0.000009347729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006827145,"about_ca_system_score_gemma":0.0002167703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001321044,"about_ca_topic_score_gemma":0.0005467939,"domain_scores_codex":[0.9976817,0.0000949334,0.0005220096,0.0005187021,0.0008674898,0.0003151027],"domain_scores_gemma":[0.9989724,0.0002614072,0.00003921461,0.0004784951,0.00005052609,0.0001979525],"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":[0.00002515987,0.0001780246,0.001939504,0.0001536113,0.00005250004,0.001802775,0.01992762,0.0003798933,0.0001234939,0.3332027,0.02083486,0.6213799],"study_design_scores_gemma":[0.000723307,0.00005914799,0.0003317877,0.0004507411,0.000006290835,0.00002806899,0.0002219752,0.9864346,0.00004463844,0.001320864,0.01025204,0.0001265042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05393868,0.01582626,0.8707203,0.04340168,0.004932643,0.0002876872,0.00000458886,0.0005362181,0.0103519],"genre_scores_gemma":[0.9914723,0.0001687015,0.002546114,0.004273975,0.001012152,0.000009508309,0.00002703611,0.00001471914,0.0004754621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9860547,"threshold_uncertainty_score":0.5034082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3151929433","doi":"10.1162/tacl_a_00360","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":602,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Kepler; Embedding; Benchmark (surveying); Language model; Representation (politics); Natural language processing; Construct (python library); ENCODE; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03147363115435537,"gpt":0.3240863137469095,"spread":0.2926126825925541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002917282,0.00008029443,0.0001368116,0.00005438758,0.0002470258,0.0000615193,0.0001958445,0.00006295403,9.218451e-7],"category_scores_gemma":[0.001681528,0.00008080307,0.0001244867,0.0002018253,0.00001426938,0.00006531322,0.00002143575,0.00007029317,2.703899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056683,"about_ca_system_score_gemma":0.0002082442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007195771,"about_ca_topic_score_gemma":0.00002280106,"domain_scores_codex":[0.999116,0.00004474204,0.0002995125,0.0002196717,0.000193905,0.000126147],"domain_scores_gemma":[0.9973218,0.001111844,0.0002167669,0.0001934551,0.001125724,0.0000303466],"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":[0.000008329846,0.00005420297,0.00008059449,0.00005025341,0.00005542739,6.754033e-8,0.002822822,0.897187,0.0001539181,0.09796598,0.00007959981,0.001541781],"study_design_scores_gemma":[0.0005669486,0.00001346673,0.0002882071,0.00001800716,0.00005112718,0.000001026585,0.00009356833,0.9495437,0.0005865793,0.04854103,0.000218591,0.00007772139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00263066,0.0000544465,0.9956169,0.0004446331,0.0004955236,0.0003085322,0.0001145145,0.00005237757,0.0002824734],"genre_scores_gemma":[0.6736804,0.000002287419,0.3246725,0.00003791565,0.00007545188,0.0000279314,0.00002745661,0.000007230752,0.00146884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6710497,"threshold_uncertainty_score":0.3295054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3096266342","doi":"10.1007/978-3-030-61377-8_28","title":"BERTimbau: Pretrained BERT Models for Brazilian Portuguese","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":598,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Transformer; Language model; Sentence; Encoder; Portuguese; Transfer of learning; Textual entailment; Named-entity recognition; Logical consequence; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02926096844476913,"gpt":0.252910922927005,"spread":0.2236499544822358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007552507,0.0006648118,0.0007257988,0.0005448005,0.0002323744,0.0004543343,0.004793234,0.0004302938,0.00001075957],"category_scores_gemma":[0.0001491781,0.0006411715,0.0002644695,0.0004792425,0.0003851264,0.001003216,0.001497004,0.0007529471,0.00002179507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002583589,"about_ca_system_score_gemma":0.00081582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000190124,"about_ca_topic_score_gemma":0.00003855459,"domain_scores_codex":[0.9948258,0.00002380076,0.0007489099,0.002460178,0.001089032,0.0008522155],"domain_scores_gemma":[0.9967499,0.0004318216,0.0002997886,0.00183163,0.0003182157,0.0003686573],"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":[0.00001049129,0.00001971531,0.000003399311,0.00007536585,0.00001713391,0.00005677943,0.001018105,0.1321606,0.0001495577,0.1085206,0.00008727958,0.7578809],"study_design_scores_gemma":[0.0002226103,0.0001181228,0.000006411401,0.0001426698,0.000006736633,0.00001840783,7.125085e-8,0.6552728,0.0002268736,0.3425184,0.0009998253,0.0004671118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001280685,0.0005960683,0.9876415,0.003522066,0.00169521,0.0009306915,0.00001453876,0.0003243498,0.005262733],"genre_scores_gemma":[0.07136209,0.00003047293,0.9214533,0.005473265,0.0008855305,0.0000375368,0.00001400745,0.00006968385,0.0006741227],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7574138,"threshold_uncertainty_score":0.9996039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400949264","doi":"10.1038/s41586-024-07566-y","title":"AI models collapse when trained on recursively generated data","year":2024,"lang":"en","type":"article","venue":"Nature","topic":"Topic Modeling","field":"Computer Science","cited_by":583,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Generative grammar; Generative model; Intuition; Computer science; Variety (cybernetics); The Internet; Artificial intelligence; Data science; Psychology; Cognitive science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0509041440660831,"gpt":0.3005333002021868,"spread":0.2496291561361037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002357904,0.0001272654,0.0001121216,0.0001010458,0.00006243731,0.0003086839,0.001636961,0.0005257963,0.00001755915],"category_scores_gemma":[0.00004397265,0.0001068325,0.00003040709,0.0003458491,0.00001136389,0.0006887991,0.000318677,0.001417031,0.00004446961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004933295,"about_ca_system_score_gemma":0.0001718681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008952771,"about_ca_topic_score_gemma":0.000009625984,"domain_scores_codex":[0.9986193,0.00004292385,0.0001303119,0.0006778495,0.0003200958,0.000209478],"domain_scores_gemma":[0.9986145,0.00005101007,0.00001870601,0.001173451,0.00007210367,0.00007020986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001167696,0.00003346723,0.000001048428,0.00003220093,0.0000453824,0.0001728294,0.001469124,0.008399446,0.0009933041,0.5033867,0.4207263,0.06472844],"study_design_scores_gemma":[0.000115549,0.00002187937,0.000003312738,0.00005338455,0.000005313222,0.00001052318,0.000004660924,0.9038107,0.0003648047,0.03730826,0.05817962,0.0001219896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003036857,0.004796182,0.931289,0.05128295,0.00287191,0.0002809689,0.0001191978,0.000746467,0.005576429],"genre_scores_gemma":[0.8798167,0.00003946312,0.1006428,0.01532151,0.0006333007,0.000009513549,0.0001034666,0.00002751944,0.003405756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8954113,"threshold_uncertainty_score":0.6156372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091812280","doi":"10.1145/1273496.1273577","title":"Three new graphical models for statistical language modelling","year":2007,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Probabilistic logic; Language model; Representation (politics); Word (group theory); n-gram; Binary number; Set (abstract data type); Parametric statistics; Artificial intelligence; Natural language processing; Statistical model; Sequence (biology); Theoretical computer science; Probability distribution; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05588757867207705,"gpt":0.2949680272604291,"spread":0.2390804485883521,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000403242,0.00009721056,0.0001168758,0.00007291403,0.00006026348,0.00007230977,0.0004682689,0.00006574425,0.00001384376],"category_scores_gemma":[0.00001666701,0.00008477494,0.0000514163,0.0001222234,0.00001537745,0.0002645861,0.00009820609,0.00009945596,0.000008596734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001742534,"about_ca_system_score_gemma":0.00005153599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002859802,"about_ca_topic_score_gemma":0.0001844916,"domain_scores_codex":[0.9988536,0.000005070748,0.0002204024,0.0003420206,0.0002176423,0.000361247],"domain_scores_gemma":[0.9991432,0.000225175,0.00002353363,0.0003859044,0.00003722001,0.0001849884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000512189,0.00001118331,0.000008664346,0.0000040375,0.000004031152,0.000006225396,0.0002357616,0.05199453,0.00003713382,0.9051994,0.000351421,0.04214245],"study_design_scores_gemma":[0.000156562,0.00001613392,0.000006534678,0.000002574428,0.000002035813,0.000002932127,0.00001214331,0.6584375,0.0001120348,0.3410693,0.0001045143,0.00007769149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001688268,0.00006855802,0.9950765,0.0004187248,0.0001418583,0.0001629019,0.000001777635,0.0002094754,0.002231973],"genre_scores_gemma":[0.2979631,0.000001097208,0.7015104,0.0002541679,0.0001090668,0.000002484213,0.00000147232,0.000006417992,0.0001518253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.606443,"threshold_uncertainty_score":0.3457022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W10957333","doi":"","title":"Data-Driven Response Generation in Social Media","year":2011,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":580,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Phrase; Computer science; Machine translation; Natural language processing; Artificial intelligence; Social media; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.1716762906428433,"gpt":0.2990671782790738,"spread":0.1273908876362305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004234717,0.00004058233,0.0000551875,0.00005447033,0.00003959274,0.00002455067,0.000717394,0.00003386027,0.00005958698],"category_scores_gemma":[0.00008992472,0.00004072767,0.000008692327,0.00009910228,0.00001189306,0.000319603,0.000275183,0.00006306559,0.00003594114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002096342,"about_ca_system_score_gemma":0.00005075895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007081723,"about_ca_topic_score_gemma":0.00009176986,"domain_scores_codex":[0.9993324,0.0001024459,0.0001101928,0.0002194179,0.000123688,0.0001118026],"domain_scores_gemma":[0.9994612,0.00003781596,0.0000242369,0.0004374137,0.00001575396,0.00002358075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001577929,0.0002139691,0.001792278,0.00001066925,0.00001749083,0.0001645028,0.07428807,0.0002358869,0.139841,0.3788167,0.03233733,0.3721243],"study_design_scores_gemma":[0.0002636641,0.00001256106,0.009252013,0.000002999986,0.000001624264,0.00000291217,0.00002980244,0.9711816,0.001594639,0.01541119,0.002132046,0.0001149954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5487756,0.000008488421,0.4439342,0.001033606,0.0003895146,0.00006880958,0.00000643402,0.00007681193,0.005706534],"genre_scores_gemma":[0.8439742,0.000001047336,0.1557019,0.0001027547,0.0001766608,0.000003175873,0.000005857804,0.000002562814,0.00003185394],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9709457,"threshold_uncertainty_score":0.1660826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126034021","doi":"10.1017/s1351324901002765","title":"Discovery of inference rules for question-answering","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":532,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Question answering; Inference; Computer science; Dependency (UML); Set (abstract data type); Parsing; Artificial intelligence; Natural language processing; Rule of inference; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.00715054306742324,"gpt":0.2517287714730841,"spread":0.2445782284056608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001035483,0.00008841202,0.0001118098,0.00007512856,0.00002051287,0.00005107102,0.0003342052,0.00003601382,0.000001223504],"category_scores_gemma":[0.0001826686,0.00008137323,0.0000494281,0.0001123075,0.000005312778,0.0005108453,0.00007745496,0.0001014627,0.000001334058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002739004,"about_ca_system_score_gemma":0.00001259251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003447597,"about_ca_topic_score_gemma":0.000004136893,"domain_scores_codex":[0.9994054,0.000004998661,0.000143718,0.0001622932,0.0001118706,0.0001717006],"domain_scores_gemma":[0.9995571,0.0001168465,0.00003398622,0.0002360065,0.00003339248,0.00002262344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001720593,0.00004269218,0.001535478,0.0003533527,0.00005773759,0.00005923436,0.004347271,0.1269414,0.2998533,0.332292,0.00002624875,0.2344741],"study_design_scores_gemma":[0.0001601156,0.00001479629,0.001101828,0.00009899991,0.000003438613,0.00001145734,0.00003508086,0.9833108,0.01479864,0.0001639665,0.0001471339,0.0001537326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.329692,0.001045096,0.6687211,0.00003587953,0.0002961903,0.00005894586,0.000001678956,0.0001044836,0.0000446069],"genre_scores_gemma":[0.856863,0.0000082973,0.1428883,0.00001408589,0.00009429534,0.000007891576,0.000003143503,0.000006487621,0.0001145748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8563694,"threshold_uncertainty_score":0.3318304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411403346","doi":"10.1145/3744746","title":"A Comprehensive Overview of Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":488,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Context (archaeology); Benchmarking; Frontier; Data science; Engineering ethics; Management science; Political science; Engineering; Management","retraction":null,"screen_n_in":null,"score":{"opus":0.04191685863724989,"gpt":0.307768274351576,"spread":0.2658514157143261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008379653,0.000104039,0.0002337004,0.0004489834,0.00007726258,0.0000202562,0.0005490413,0.0001377687,0.000004707224],"category_scores_gemma":[0.00000838416,0.0000949426,0.00004397932,0.0005242298,0.00004233498,0.00008865819,0.00004203952,0.0001626198,0.000005102089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002354594,"about_ca_system_score_gemma":0.00002686339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001282349,"about_ca_topic_score_gemma":0.00001557465,"domain_scores_codex":[0.9991642,0.00002890949,0.0002802776,0.0002744881,0.00008918262,0.0001630034],"domain_scores_gemma":[0.998916,0.00007590107,0.00005731854,0.0008417134,0.0000865437,0.00002247145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003835628,0.0001094528,0.00003348978,0.0002702415,0.00009010114,0.000005690649,0.0004814888,0.003846236,0.0007166103,0.8747651,0.00002854786,0.1196492],"study_design_scores_gemma":[0.0009412989,0.0003178503,0.00003294102,0.001220798,0.00007089377,0.00009399919,0.005261364,0.8016403,0.04269345,0.1228624,0.02437115,0.0004935798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01333054,0.007140859,0.9775044,0.001015805,0.0003397317,0.0002148138,0.000007517423,0.0001765285,0.0002697848],"genre_scores_gemma":[0.9924573,0.0006583569,0.006416866,0.00008616441,0.000004098734,0.00004258338,4.322369e-7,0.000004286509,0.0003299165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9791268,"threshold_uncertainty_score":0.3871647,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906152891","doi":"10.1162/tacl_a_00254","title":"Analysis Methods in Neural Language Processing: A Survey","year":2019,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":486,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Categorization; Artificial neural network; Field (mathematics); Feature (linguistics); Artificial intelligence; Point (geometry); Data science; Natural language processing; Machine learning; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02963772496761502,"gpt":0.3494461539490562,"spread":0.3198084289814412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091843,0.00007097794,0.0001853252,0.0001825871,0.00007094433,0.00004294249,0.0003973121,0.00005388455,0.000004144826],"category_scores_gemma":[0.0009145654,0.00006449757,0.0001572793,0.001030679,0.000008384871,0.00005422533,0.00001513268,0.0001088349,0.000001416203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135034,"about_ca_system_score_gemma":0.0001028493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001326668,"about_ca_topic_score_gemma":0.0001184361,"domain_scores_codex":[0.9989086,0.0001844503,0.0003341014,0.0001806312,0.0002669396,0.0001252994],"domain_scores_gemma":[0.9978198,0.001099121,0.0002801667,0.0002058112,0.0005759592,0.00001911823],"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":[0.00000421122,0.00004150048,0.04908028,0.00001608811,0.00007863343,3.966525e-8,0.0004784254,0.9440999,0.00001075115,0.002546921,0.000004128119,0.003639092],"study_design_scores_gemma":[0.0002306883,0.00001078579,0.095353,0.000005102137,0.00005575076,1.212935e-7,0.00001937323,0.9023499,0.00004010436,0.001797109,0.00007609629,0.00006194824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00855588,0.00003770179,0.9902783,0.0001318183,0.0004768416,0.0001933581,0.00004133898,0.00002921039,0.0002555696],"genre_scores_gemma":[0.7810395,2.652203e-7,0.2185252,0.00003731237,0.00002048184,0.000006312727,0.0000141941,0.000004230401,0.0003524809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724836,"threshold_uncertainty_score":0.2630135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045929671","doi":"10.1145/1376815.1376819","title":"Semantic text similarity using corpus-based word similarity and string similarity","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Topic Modeling","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Semantic similarity; String metric; Artificial intelligence; Word (group theory); Natural language processing; Longest common subsequence problem; Focus (optics); String searching algorithm; String (physics); Representation (politics); Information retrieval; Matching (statistics); Pattern matching; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1204337695552436,"gpt":0.3074205502158795,"spread":0.186986780660636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004279114,0.000448995,0.0004991243,0.0002411639,0.0008887696,0.0003913397,0.003230168,0.0002317603,0.00004392673],"category_scores_gemma":[0.0001673055,0.0004738807,0.0001300574,0.0006018268,0.0002230122,0.003200896,0.0004491765,0.000779875,0.00002848651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552863,"about_ca_system_score_gemma":0.000453603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009395767,"about_ca_topic_score_gemma":0.001253196,"domain_scores_codex":[0.996618,0.000222386,0.0005515344,0.001596256,0.0004451674,0.0005666909],"domain_scores_gemma":[0.9936689,0.0007663651,0.0001452886,0.005073285,0.0001057097,0.0002404396],"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":[0.001053573,0.01423526,0.08035918,0.00132997,0.002046416,0.001244942,0.009301427,0.1438239,0.0135037,0.005221042,0.003561208,0.7243194],"study_design_scores_gemma":[0.001520633,0.00007072123,0.00786985,0.0002232161,0.0001557927,0.00003782412,0.00005887906,0.9804195,0.00405095,0.003056296,0.00167967,0.0008566504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2578979,0.0004820103,0.7391785,0.000449269,0.000602322,0.000255162,0.0008822596,0.0002009372,0.00005164174],"genre_scores_gemma":[0.9141459,0.0001758536,0.08496581,0.000283262,0.0001203571,0.000007870697,0.0001857914,0.00003426243,0.00008088908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8365957,"threshold_uncertainty_score":0.9997713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100002341","doi":"","title":"Replicated Softmax: an Undirected Topic Model","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":442,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Latent Dirichlet allocation; Softmax function; Computer science; Graphical model; Inference; Artificial intelligence; Topic model; Latent variable; Undirected graph; Dirichlet distribution; Theoretical computer science; Data mining; Machine learning; Algorithm; Graph; Deep learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03266415990600878,"gpt":0.2715287157289674,"spread":0.2388645558229586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002458199,0.0001297607,0.0001482047,0.0001365825,0.0001994962,0.0008681432,0.0005798952,0.00008110482,8.156398e-7],"category_scores_gemma":[0.00003721239,0.0001163407,0.00002607995,0.0003528797,0.000009940114,0.006639922,0.00003627888,0.0001267453,0.00002065439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000605917,"about_ca_system_score_gemma":0.00009210513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002282958,"about_ca_topic_score_gemma":6.288028e-7,"domain_scores_codex":[0.9986908,0.0000341144,0.0005033295,0.0002048129,0.0003051104,0.0002618614],"domain_scores_gemma":[0.9989194,0.000008337716,0.0002426827,0.0004939411,0.0002319308,0.0001037573],"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":[0.000008846892,0.00004689192,0.0001224538,0.0001649738,0.000004717107,0.000002045926,0.004878316,0.360736,0.001607439,0.02805504,0.0006336647,0.6037396],"study_design_scores_gemma":[0.0001511588,0.00003798939,0.0002501727,0.00002938705,0.000001919104,0.00002937775,0.00004052312,0.9978875,0.0002400599,0.0006462719,0.0005453687,0.0001402901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04927099,0.00006550938,0.9446685,0.0007851637,0.0002516204,0.0002264909,0.000001026517,0.001003862,0.003726852],"genre_scores_gemma":[0.987062,0.000001248079,0.01162013,0.00102461,0.00006098294,0.00001404779,0.00001623015,0.000003750854,0.0001970434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.937791,"threshold_uncertainty_score":0.8371525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1654173042","doi":"","title":"Unsupervised Modeling of Twitter Conversations","year":2010,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":434,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"Microsoft Research","keywords":"Computer science; Conversation; Task (project management); Cluster analysis; Visualization; Domain (mathematical analysis); Artificial intelligence; Social media; Natural language processing; Microblogging; Topic model; Data science; World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03234468296183593,"gpt":0.247503627607715,"spread":0.215158944645879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001186943,0.00004629785,0.00006826643,0.00004736882,0.0000323692,0.00002229803,0.0004038534,0.00003558517,0.000116838],"category_scores_gemma":[0.00002203344,0.00004413213,0.00003049837,0.00008855739,0.00001625351,0.0001643119,0.00008837485,0.0001123218,0.00002149175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004377816,"about_ca_system_score_gemma":0.0000390064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000162183,"about_ca_topic_score_gemma":0.000004412886,"domain_scores_codex":[0.9994717,0.00001035147,0.0001317851,0.0001475974,0.0001323983,0.0001061851],"domain_scores_gemma":[0.999417,0.00002318844,0.00002406113,0.000429767,0.00006720483,0.00003878682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002888082,0.00006559414,0.001917048,0.00002595287,0.00001904542,0.000003640133,0.005337212,0.01270888,0.519723,0.4369479,0.0004660857,0.02278276],"study_design_scores_gemma":[0.0001229624,0.000004886395,0.00005208413,0.000003269142,0.000001671792,0.000001675849,0.00001762371,0.9714461,0.003056674,0.02505805,0.000186175,0.00004883748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3287658,0.000001597034,0.6605502,0.0009192606,0.0002176124,0.00003522808,3.02003e-7,0.00004094643,0.009469037],"genre_scores_gemma":[0.7990257,5.802063e-7,0.2007044,0.0001611203,0.00003563826,0.000002598559,3.488969e-7,0.000002691026,0.00006700399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9587372,"threshold_uncertainty_score":0.1799656,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2399456070","doi":"10.21437/interspeech.2013-596","title":"Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding","year":2013,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":432,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Spoken language; Artificial neural network; Natural language processing; Recurrent neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.0788804892206361,"gpt":0.329259228172978,"spread":0.2503787389523419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004887004,0.00006259464,0.0000977091,0.00005047934,0.00007740417,0.00006061743,0.0001426666,0.00002804179,0.000007598853],"category_scores_gemma":[0.0001318448,0.00005174798,0.00002332859,0.0001029548,0.0000262026,0.0001169257,0.00009369488,0.00009387323,4.829901e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001385295,"about_ca_system_score_gemma":0.000009852108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006400818,"about_ca_topic_score_gemma":0.000005767933,"domain_scores_codex":[0.9993488,0.0001311314,0.0001378683,0.0001785044,0.00006257564,0.0001411586],"domain_scores_gemma":[0.9992325,0.0005160402,0.00006674596,0.0001177201,0.00002165319,0.00004533132],"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":[0.000005489824,0.000004375755,0.009897255,0.000146384,0.00003002746,3.69042e-7,0.01221668,0.01635663,0.01040052,0.107166,0.0002166173,0.8435597],"study_design_scores_gemma":[0.0001322215,0.00004114776,0.000909274,0.0000319827,0.000003820743,0.000002244503,0.000351086,0.9477496,0.001882042,0.04879839,0.00002195017,0.0000762324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2318305,0.0001664849,0.7672009,0.0003058575,0.00007174395,0.0001549203,7.154e-8,0.00005248584,0.0002170044],"genre_scores_gemma":[0.5112598,0.000001426335,0.4885896,0.00005459411,0.00002830376,0.000007138741,4.972676e-7,0.000002744172,0.00005583945],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.931393,"threshold_uncertainty_score":0.2110221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3100107515","doi":"10.18653/v1/2020.findings-emnlp.63","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":414,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Ranking (information retrieval); Sequence (biology); Encoder; Relevance (law); Artificial intelligence; Transformer; Task (project management); Information retrieval; Machine learning; Natural language processing; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07025758913945321,"gpt":0.2760678251045512,"spread":0.205810235965098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001472693,0.0001436873,0.0001464468,0.00004204926,0.0000729165,0.0001785706,0.0009712667,0.00003226061,0.00002546585],"category_scores_gemma":[0.00002857773,0.0001112503,0.00003110623,0.0003778729,0.00002061353,0.0005351232,0.0002626748,0.0001198384,0.00005370077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005692181,"about_ca_system_score_gemma":0.0001510473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003456594,"about_ca_topic_score_gemma":0.000008083916,"domain_scores_codex":[0.9984974,0.00002246019,0.0001931039,0.0005695237,0.000403314,0.0003142609],"domain_scores_gemma":[0.9991676,0.00002198657,0.00003999622,0.0004631472,0.00006062422,0.0002467124],"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":[0.00002869228,0.00001818241,0.0001734434,0.00003798465,0.00002492456,0.00007911667,0.009963069,0.5920449,0.01632544,0.3455039,0.0002933769,0.03550697],"study_design_scores_gemma":[0.0002601371,0.00009085287,0.000006163823,0.00002321989,0.000002758904,0.000009102299,0.000025285,0.9927471,0.001809986,0.004682474,0.0001614312,0.0001815257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01809654,0.000008154066,0.9631709,0.01269801,0.00003590262,0.0002530267,7.256189e-7,0.0003669574,0.005369809],"genre_scores_gemma":[0.5726404,9.222338e-7,0.4222623,0.004873293,0.00002544727,0.00001551558,2.913827e-7,0.000005496609,0.0001762816],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5545439,"threshold_uncertainty_score":0.4536657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2252143850","doi":"","title":"Training recurrent neural networks","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":391,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Initialization; Computer science; Sequence (biology); Artificial intelligence; Probabilistic logic; Gradient descent; Artificial neural network; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05334820093018022,"gpt":0.2900405536168376,"spread":0.2366923526866574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009215784,0.0001743071,0.000182674,0.00007241793,0.00006159161,0.0002169711,0.0007861396,0.0001629004,0.00008726389],"category_scores_gemma":[0.00001318262,0.0001545202,0.00007800807,0.0001123834,0.000003773111,0.0002474766,0.0000525184,0.0003240535,0.00004120708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002210581,"about_ca_system_score_gemma":0.00004493443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000311095,"about_ca_topic_score_gemma":0.00006160525,"domain_scores_codex":[0.9988457,0.00002620504,0.0002426838,0.000413517,0.0002004351,0.0002714857],"domain_scores_gemma":[0.9992852,0.00003273287,0.000104247,0.0004386414,0.00006273187,0.00007644093],"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":[6.853483e-7,0.000005650236,0.000005212399,0.00001256021,0.000007216348,0.000002411768,0.001351625,0.002502441,0.000005225345,0.01880828,0.001037572,0.9762611],"study_design_scores_gemma":[0.00004805985,0.00001374503,0.0001375074,0.00003378873,0.000003769472,0.00000226431,0.000151595,0.997963,0.00001073852,0.0005221151,0.0009251119,0.0001883233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01319252,0.000481867,0.9236661,0.0001309933,0.00703693,0.0002483705,1.825525e-7,0.0003760677,0.05486699],"genre_scores_gemma":[0.8651414,0.00006261159,0.08302503,0.000590175,0.001107177,0.0001118658,0.0002019952,0.00004891532,0.04971082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9954606,"threshold_uncertainty_score":0.6301152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3043222912","doi":"10.3389/frai.2020.00042","title":"Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis","year":2020,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Latent semantic analysis; Popularity; Information retrieval; Social media; Matrix decomposition; Context (archaeology); Artificial intelligence; Precision and recall; Natural language processing; Data science; Machine learning; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.4952072856871249,"gpt":0.4730338297708425,"spread":0.02217345591628234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008143571,0.0001866109,0.0005150767,0.0002693822,0.0001289249,0.0001933882,0.001897458,0.00008277502,0.000006203705],"category_scores_gemma":[0.000203823,0.0001986788,0.000125257,0.001581298,0.00004993823,0.0006698933,0.0005112023,0.0002082234,0.000003476748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008139008,"about_ca_system_score_gemma":0.00008792921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008640205,"about_ca_topic_score_gemma":0.0000527215,"domain_scores_codex":[0.99764,0.0001809818,0.0006668121,0.0009436798,0.0001881166,0.000380419],"domain_scores_gemma":[0.9986843,0.0001289878,0.00008131285,0.0008696752,0.0001037103,0.0001320452],"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":[0.00001909972,0.00002711432,0.0003334781,0.0000127984,0.0001158105,0.000002710711,0.003538098,0.7611758,0.0003489654,0.01483607,0.0000474457,0.2195426],"study_design_scores_gemma":[0.00001658262,0.00002225441,0.000002548848,0.00000953354,0.00007522258,4.257576e-7,0.0008918464,0.9730126,0.002803313,0.02269005,0.0002654483,0.000210233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002544735,0.0005148146,0.9950877,0.0005668722,0.0007657738,0.0003391464,0.000008272566,0.00007679546,0.00009591894],"genre_scores_gemma":[0.3765037,0.000008768868,0.6231927,0.0001667282,0.0001024207,0.00001036344,0.000007168841,0.000004771419,0.000003425973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3739589,"threshold_uncertainty_score":0.8101886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2912817604","doi":"10.18653/v1/n19-4013","title":"End-to-End Open-Domain Question Answering with","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; Open domain; Benchmark (surveying); Information retrieval; Reading (process); End-to-end principle; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Reading comprehension; Language model; Open source; Programming language; Linguistics; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.02837405652156753,"gpt":0.2801999427192826,"spread":0.2518258861977151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878677,0.0002407351,0.0002939245,0.0001317499,0.0000568859,0.0008088303,0.00289382,0.0001389261,0.00007113889],"category_scores_gemma":[0.00001306423,0.0002001027,0.00003961256,0.0001346406,0.00001301749,0.0003816594,0.005750156,0.0003873536,0.0001583227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001225139,"about_ca_system_score_gemma":0.0002640866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364158,"about_ca_topic_score_gemma":0.0002404539,"domain_scores_codex":[0.9980291,0.00007294461,0.0002489576,0.0009935332,0.0003601258,0.0002953261],"domain_scores_gemma":[0.9979312,0.00003736923,0.0001048948,0.001723854,0.00007844139,0.0001242801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002959418,0.00009034377,0.002341917,0.000228998,0.00009287298,0.00007386658,0.002939997,0.2782723,0.0007221336,0.598628,0.001145051,0.1154349],"study_design_scores_gemma":[0.00110281,0.0003080624,0.003574132,0.001473822,0.00002509908,0.0000795427,0.0001302724,0.9128873,0.002369229,0.04917598,0.02679308,0.002080631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01670925,0.00002687064,0.9396752,0.001589937,0.0008335861,0.0006833953,0.000001869302,0.0002213311,0.04025861],"genre_scores_gemma":[0.4007255,0.000003471584,0.5958071,0.0004665676,0.00008781083,0.00004307078,0.000004219763,0.0000149125,0.002847277],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.634615,"threshold_uncertainty_score":0.815995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132052677","doi":"10.14569/ijacsa.2015.060121","title":"A Survey of Topic Modeling in Text Mining","year":2015,"lang":"en","type":"article","venue":"International Journal of Advanced Computer Science and Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Probabilistic latent semantic analysis; Natural language processing; Artificial intelligence; Latent semantic analysis; Field (mathematics); Probabilistic logic; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.0669373198898449,"gpt":0.3294273301311625,"spread":0.2624900102413176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001101844,0.00005664514,0.0001193816,0.0003232212,0.00003015893,0.00008745848,0.001292682,0.00001594633,3.263068e-7],"category_scores_gemma":[0.00009499086,0.0000519591,0.00001794732,0.000521121,0.00007077682,0.0008849879,0.0002662585,0.00007877204,5.662682e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007608223,"about_ca_system_score_gemma":0.0003490605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003699618,"about_ca_topic_score_gemma":0.00001336458,"domain_scores_codex":[0.9987232,0.00002120508,0.0003920246,0.0001799332,0.0005748692,0.0001087445],"domain_scores_gemma":[0.9979047,0.00007228962,0.0002028757,0.0001787693,0.001549522,0.00009186235],"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":[0.000007515986,0.00006513439,0.003986649,0.000002586235,0.000007456737,0.000004941228,0.0009720907,0.2302879,0.0005925843,0.01371821,0.00001129777,0.7503436],"study_design_scores_gemma":[0.0003720721,0.00004209414,0.004615111,0.00003659407,8.451876e-7,0.00004163398,0.00005191677,0.9896502,0.000208815,0.004713719,0.0002066746,0.00006029674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2126212,0.0001156191,0.786495,0.0003925282,0.0002330919,0.00004675342,6.395013e-7,0.000005181421,0.00008999136],"genre_scores_gemma":[0.803445,0.00001764462,0.1963752,0.00009017181,0.00006426326,0.000003108125,2.233032e-7,0.000001534152,0.000002846726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7593623,"threshold_uncertainty_score":0.2402146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963386218","doi":"","title":"A Structured Self-Attentive Sentence Embedding.","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":365,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Embedding; Sentence; Computer science; Natural language processing; Artificial intelligence; Logical consequence; Regularization (linguistics)","retraction":null,"screen_n_in":null,"score":{"opus":0.05458417324847135,"gpt":0.3661503131841141,"spread":0.3115661399356427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001609694,0.0001387082,0.0001185437,0.0001438523,0.0007206844,0.001207229,0.001968035,0.00005213703,0.0001747201],"category_scores_gemma":[0.0005696433,0.0001399169,0.00007505622,0.00005660464,0.00006472192,0.0009221535,0.0004465283,0.0003491981,0.0001578591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006897849,"about_ca_system_score_gemma":0.00009412341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001393074,"about_ca_topic_score_gemma":0.00001814685,"domain_scores_codex":[0.9984345,0.00007258538,0.0002250141,0.0005461299,0.0005153716,0.0002064251],"domain_scores_gemma":[0.9982703,0.00009588754,0.0003101475,0.0008310878,0.0004087544,0.00008387479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001917215,0.0001209369,0.05404845,0.000007798694,0.0001922149,0.0000850249,0.007555213,0.01184489,0.003588795,0.8878938,0.0004385885,0.0342051],"study_design_scores_gemma":[0.0003974006,0.00003781533,0.04874118,0.00005376459,0.000007172565,0.00002206959,0.000396095,0.935191,0.000536455,0.01307705,0.0013325,0.0002075071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2073344,0.000009337242,0.6191267,0.01932611,0.00284407,0.000321693,0.000009187956,0.0006591816,0.1503693],"genre_scores_gemma":[0.9729578,0.00001630551,0.02333252,0.0001273016,0.0001396573,0.00002774577,0.000009214751,0.00000851492,0.003380905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9233461,"threshold_uncertainty_score":0.9998296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173783447","doi":"10.18653/v1/2021.acl-long.72","title":"DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":362,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Vector Institute; University of Toronto","funders":"National Institutes of Health; Compute Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Computational linguistics; Volume (thermodynamics); Association (psychology); Joint (building); Deep learning; Cognitive science; Psychology; Philosophy; Epistemology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03108129907966992,"gpt":0.2870895336430146,"spread":0.2560082345633448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115329,0.00006563251,0.00009494663,0.00003137834,0.0001553482,0.0001191049,0.0002440382,0.00003163768,0.00006876882],"category_scores_gemma":[0.0003093418,0.00006465057,0.00005774858,0.0001636062,0.00001292157,0.0002331882,0.0001315595,0.00007863875,0.00002160917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001897838,"about_ca_system_score_gemma":0.00008495597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248217,"about_ca_topic_score_gemma":0.00004690413,"domain_scores_codex":[0.9991567,0.00004865799,0.0001518245,0.0003345462,0.000119965,0.0001882673],"domain_scores_gemma":[0.9991003,0.0003490103,0.00002687143,0.0002709287,0.000192334,0.00006055795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007944257,0.0000841983,0.003624944,0.00001729361,0.00006428767,0.00003284837,0.003200199,0.03632082,0.004907124,0.7841054,0.0006581229,0.1669768],"study_design_scores_gemma":[0.0005136149,0.00002165032,0.001009198,0.000005416894,0.000005666585,0.00001164183,0.0008706595,0.9862226,0.004417546,0.004321765,0.002492006,0.0001082709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005379884,0.00007804373,0.9833972,0.001362418,0.0001227704,0.0001186799,5.22453e-7,0.0001494933,0.009390983],"genre_scores_gemma":[0.6778063,0.00000444527,0.3192238,0.0003937726,0.00006365338,0.00002972403,0.000006023133,0.000005271088,0.00246696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9499018,"threshold_uncertainty_score":0.2636374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176169354","doi":"10.18653/v1/2021.acl-long.551","title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":352,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Arabic; Transformer; Computer science; Natural language processing; Linguistics; Artificial intelligence; Speech recognition; Electrical engineering; Engineering; Philosophy; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.02856709349934125,"gpt":0.2625137650090602,"spread":0.233946671509719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000126079,0.00008159246,0.00009660102,0.00004338017,0.00008761097,0.00007224285,0.0002029347,0.00004601233,0.0001809896],"category_scores_gemma":[0.00003142933,0.00007574941,0.00009876957,0.0001853638,0.00001086594,0.0002296935,0.00003546252,0.00006172847,0.00004874122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003276566,"about_ca_system_score_gemma":0.00009967976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002375183,"about_ca_topic_score_gemma":0.0003118924,"domain_scores_codex":[0.9991296,0.00001642621,0.0001520258,0.0003280997,0.0001583641,0.0002154632],"domain_scores_gemma":[0.9995211,0.0000883754,0.0000168786,0.0002128907,0.00009037137,0.00007039667],"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":[0.00001526919,0.0001708915,0.0007777142,0.00007093592,0.0001035584,0.00001212666,0.0009052477,0.001852788,0.00761759,0.2705685,0.005342091,0.7125633],"study_design_scores_gemma":[0.0008176357,0.00003162233,0.0007120128,0.00001632836,0.00001420018,0.000111935,0.00004404889,0.5923514,0.01304568,0.0262104,0.3662167,0.0004280714],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003081512,0.0001191326,0.9710876,0.003222484,0.0005850106,0.00009310334,9.496487e-7,0.0001306743,0.02167959],"genre_scores_gemma":[0.1499771,0.00002857494,0.8246242,0.00202831,0.0002046876,0.00006544343,0.00001126004,0.00001389396,0.02304654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7121352,"threshold_uncertainty_score":0.3088971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1596986901","doi":"","title":"Joint learning of words and meaning representations for open-text semantic parsing","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":333,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Natural language processing; WordNet; Artificial intelligence; Parsing; Task (project management); Meaning (existential); Context (archaeology); Representation (politics); Natural language; Process (computing); Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.108195437040194,"gpt":0.337927349450232,"spread":0.229731912410038,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008560257,0.000160558,0.0003539573,0.0001238831,0.000155983,0.0003691234,0.0008175363,0.0001107559,0.00001539845],"category_scores_gemma":[0.0001695559,0.0001582595,0.00007605539,0.00009133422,0.00002962279,0.0003957773,0.004010785,0.0003134164,0.00000200736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000314592,"about_ca_system_score_gemma":0.00009174769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003599554,"about_ca_topic_score_gemma":0.00001905426,"domain_scores_codex":[0.9984574,0.00008535958,0.00044552,0.0005660171,0.0001824702,0.0002632633],"domain_scores_gemma":[0.9986498,0.0001868398,0.0003035413,0.0006753379,0.0001026196,0.00008181328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001287831,0.0001277654,0.008104004,0.001637781,0.0002125358,0.000004341154,0.03312111,0.08127351,0.002045205,0.6538582,0.0003027881,0.2192998],"study_design_scores_gemma":[0.0002816116,0.00001937107,0.0005021706,0.0003867065,0.00003605075,0.00001087453,0.0003832458,0.9610682,0.001308422,0.03550635,0.0002287629,0.0002682683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01046699,0.0003245655,0.9795545,0.0005436649,0.0004479929,0.0005609252,9.152334e-7,0.00008355788,0.008016823],"genre_scores_gemma":[0.6235959,0.00002144395,0.3757077,0.0000308133,0.00006156567,0.00003189471,0.000003272921,0.00001030816,0.0005371576],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8797947,"threshold_uncertainty_score":0.6453634,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2542835211","doi":"10.48550/arxiv.1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":330,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Forcing (mathematics); Computer science; Treebank; Sampling (signal processing); MNIST database; Algorithm; Handwriting; Sample (material); Artificial intelligence; Sequence (biology); Machine learning; Speech recognition; Artificial neural network; Mathematics; Parsing","retraction":null,"screen_n_in":null,"score":{"opus":0.1343603456892092,"gpt":0.2081793152473785,"spread":0.07381896955816938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002045212,0.0001344435,0.0001514474,0.00008589034,0.0001330264,0.00003726096,0.0007505962,0.00007882609,0.000009893302],"category_scores_gemma":[0.00002917558,0.0001146384,0.0001038141,0.000279654,0.00002620801,0.0005195815,0.0001952171,0.00008357201,0.00001359876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009523849,"about_ca_system_score_gemma":0.0001265269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001164657,"about_ca_topic_score_gemma":0.00001385722,"domain_scores_codex":[0.9988117,0.00003607125,0.0001313206,0.0005695627,0.00004739705,0.0004039653],"domain_scores_gemma":[0.9990375,0.0001560323,0.00009105329,0.0004758211,0.00006602769,0.0001735649],"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":[0.00001325949,0.00002227664,0.0001419298,0.000005408408,0.0000243106,0.00002143208,0.0003998982,0.005026475,0.00002941948,0.2432811,0.0007529424,0.7502816],"study_design_scores_gemma":[0.0009864754,0.00007842392,0.00004047159,0.00006087304,0.00001259577,0.000003120723,0.00005348622,0.9693931,0.00005422105,0.02594836,0.003173888,0.0001949536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005434868,0.00003473697,0.9926689,0.0004857356,0.0006143529,0.0002608025,0.000001751292,0.0001830363,0.0003158662],"genre_scores_gemma":[0.9197095,0.00002235835,0.07347507,0.0001177452,0.0002551641,0.000001607739,9.088887e-7,0.00001253818,0.006405078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9643667,"threshold_uncertainty_score":0.4674817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1828724394","doi":"10.48550/arxiv.1410.2455","title":"BilBOWA: Fast Bilingual Distributed Representations without Word Alignments","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":314,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Word (group theory); Bilingual dictionary; Sentence; Feature (linguistics); Set (abstract data type); Machine translation; Translation (biology); Speech recognition; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0557204607827267,"gpt":0.2038580054545029,"spread":0.1481375446717763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001829446,0.0001318348,0.0001397734,0.0001116436,0.000181415,0.00007516473,0.0008402623,0.00005904865,0.00001806863],"category_scores_gemma":[0.00006976611,0.000143886,0.00007029923,0.0005975176,0.00005891147,0.0004588038,0.000344497,0.0001150594,0.0000991214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007713546,"about_ca_system_score_gemma":0.00005928318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009956973,"about_ca_topic_score_gemma":0.00003988825,"domain_scores_codex":[0.9987322,0.0001029069,0.0001457446,0.0006425263,0.000094295,0.000282333],"domain_scores_gemma":[0.998716,0.00008301009,0.0000910437,0.0008870688,0.00007930151,0.0001435747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002254927,0.0001831455,0.1035267,0.00001643886,0.00007913289,0.0001051387,0.0007319194,0.2228393,0.0005693646,0.6628449,0.0004153918,0.008665971],"study_design_scores_gemma":[0.0006595714,0.00003224093,0.004775782,0.00001550576,0.00002057868,0.000005056323,0.0001392401,0.9774767,0.0004346395,0.01470086,0.001494785,0.0002451024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3392994,0.000002789021,0.658565,0.0000942191,0.0001641755,0.0000744604,0.000003462505,0.000154247,0.001642256],"genre_scores_gemma":[0.9936779,0.000004804222,0.004770947,0.00009224128,0.00005858924,3.74515e-7,0.000008809771,0.000007509233,0.001378846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7546373,"threshold_uncertainty_score":0.5867503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035038672","doi":"10.18653/v1/2020.acl-main.204","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":301,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Vector Institute","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Inference; Computer science; Transformer; Language model; Redundancy (engineering); Artificial intelligence; Machine learning; Operating system; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07716608598601515,"gpt":0.2962549808226925,"spread":0.2190888948366773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001078776,0.00009521791,0.0001114831,0.00002255643,0.0001186165,0.000250649,0.000635769,0.0000362999,0.00001599931],"category_scores_gemma":[0.0001970871,0.000089324,0.00004444044,0.0001416259,0.000008035755,0.000485546,0.0002566557,0.00009186014,0.00002749659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001799725,"about_ca_system_score_gemma":0.00004625859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004569367,"about_ca_topic_score_gemma":0.00002051433,"domain_scores_codex":[0.9990374,0.00001431546,0.0002079626,0.0003602021,0.0001320577,0.0002480102],"domain_scores_gemma":[0.9993942,0.0001653891,0.0000517532,0.0002309431,0.00006005041,0.00009765562],"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":[0.000007312496,0.00002777528,0.004984529,0.0001055974,0.0000275038,0.000009798353,0.01109455,0.004333694,0.01047697,0.3987543,0.0002104179,0.5699676],"study_design_scores_gemma":[0.0001563188,0.00004045817,0.0004213571,0.00001066958,0.000001561135,0.000001069843,0.00002753992,0.995522,0.0008165872,0.00255396,0.0003244987,0.0001239888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08990247,0.00001601327,0.903221,0.003388924,0.00008943948,0.0001498811,5.069712e-7,0.000249056,0.002982783],"genre_scores_gemma":[0.6414949,5.736424e-7,0.3570764,0.001241174,0.00005083238,0.00001348326,5.635258e-7,0.000005122051,0.0001169284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9911883,"threshold_uncertainty_score":0.3642527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021792233","doi":"10.1145/3440755","title":"Evolution of Semantic Similarity—A Survey","year":2021,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"","keywords":"Semantic similarity; Similarity (geometry); Semantic computing; Field (mathematics); Natural language; Open research; Semantics (computer science); Strengths and weaknesses; Natural language understanding","retraction":null,"screen_n_in":null,"score":{"opus":0.04743587048223354,"gpt":0.2804255950414988,"spread":0.2329897245592652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005090703,0.000132633,0.0002740105,0.00008440202,0.0001112671,0.00007678826,0.00119991,0.00007781045,0.000007742045],"category_scores_gemma":[0.002304249,0.0001469655,0.00007658312,0.0007737709,0.00003285872,0.0001746619,0.001266556,0.0001737113,0.00001833605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006395261,"about_ca_system_score_gemma":0.0002377433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001130927,"about_ca_topic_score_gemma":0.0004116536,"domain_scores_codex":[0.996581,0.001844747,0.0004176054,0.0004949885,0.000347415,0.0003142382],"domain_scores_gemma":[0.9966226,0.001190936,0.0001577552,0.001506829,0.0004562048,0.00006572491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001943894,0.000164865,0.9175183,0.00009513518,0.00005371182,0.00004883579,0.0005524496,0.01595066,0.001976343,0.01374615,0.0004859199,0.04940564],"study_design_scores_gemma":[0.0001627303,0.00001370382,0.6619964,0.00003687417,0.000002998667,0.00001395636,0.00001069901,0.3333192,0.001328113,0.002949742,0.00002669709,0.0001388372],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3489311,0.0001668901,0.6498258,0.0001486961,0.0005948613,0.00003915093,0.000002582109,0.00009729045,0.0001937128],"genre_scores_gemma":[0.9251045,0.000003044035,0.07469271,0.00005470282,0.00005938788,3.905523e-7,0.00001013477,0.000008932812,0.00006621111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5761734,"threshold_uncertainty_score":0.599308,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798416089","doi":"10.18653/v1/p18-1224","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":276,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Queen's University","funders":"","keywords":"Computer science; Inference; Leverage (statistics); Artificial intelligence; Artificial neural network; Natural language; Machine learning; Task (project management); Language model; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02114323554206217,"gpt":0.2839945996636008,"spread":0.2628513641215386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007631073,0.0001184523,0.00010299,0.00005140685,0.00007413475,0.0001233214,0.000753187,0.00002968938,0.00003736059],"category_scores_gemma":[0.00001076356,0.00008256398,0.00002426572,0.0001675443,0.00005348665,0.0007289691,0.0002501717,0.0001260569,0.00008295733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000207202,"about_ca_system_score_gemma":0.00005281968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007029304,"about_ca_topic_score_gemma":0.0001850453,"domain_scores_codex":[0.9990736,0.00002563251,0.0001237365,0.0003412144,0.0001712429,0.0002645843],"domain_scores_gemma":[0.9992458,0.0000368912,0.00003549587,0.0004938583,0.0001163965,0.00007157],"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":[0.00004093754,0.0001116945,0.0002994691,0.00002583836,0.00002599795,0.00004117479,0.01986011,0.002719226,0.04143073,0.3224529,0.0001767907,0.6128151],"study_design_scores_gemma":[0.0002144057,0.00007513165,0.000204098,0.00002014114,0.000001509798,0.00001251936,0.00003893586,0.9805729,0.01739914,0.001295445,0.00002091286,0.0001448948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2772067,0.0001212631,0.7077587,0.00006624765,0.0002383902,0.00005304586,1.380917e-7,0.0001712478,0.01438436],"genre_scores_gemma":[0.8837935,9.084196e-7,0.1131772,0.0002310331,0.0001717486,0.000005080019,2.352207e-7,0.000005439789,0.002614915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778537,"threshold_uncertainty_score":0.3366861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1879966306","doi":"","title":"Long Short-Term Memory Over Recursive Structures","year":2015,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Parsing; Theoretical computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.03825664726599463,"gpt":0.2786430462546798,"spread":0.2403863989886852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000142546,0.00008992462,0.00009988951,0.00004720133,0.00003829657,0.00008362786,0.0006209682,0.00005006183,0.00006092893],"category_scores_gemma":[0.00003574373,0.00008040344,0.00003356561,0.00009121453,0.00002431731,0.0002858646,0.0002311816,0.0001126822,0.00002749802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005011039,"about_ca_system_score_gemma":0.00007092578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008535117,"about_ca_topic_score_gemma":0.00000847482,"domain_scores_codex":[0.9990684,0.00003353635,0.0001204694,0.0002809615,0.0002900916,0.0002064742],"domain_scores_gemma":[0.9992226,0.00002235595,0.0000275677,0.0005311418,0.00006133886,0.0001350377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002583729,0.00006957012,0.02040811,0.00003885754,0.00006771257,0.0003604396,0.01162112,0.001924677,0.0099361,0.35629,0.03556926,0.5636883],"study_design_scores_gemma":[0.001313581,0.0001947087,0.04756583,0.00007238082,0.00002638487,0.0001713128,0.0002108539,0.1391287,0.02506216,0.7811711,0.004019691,0.001063278],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5028102,0.00009723496,0.4566078,0.0005509709,0.00112602,0.0001193956,0.000001065851,0.0001596555,0.03852765],"genre_scores_gemma":[0.9424332,0.000001911793,0.05667403,0.0002725606,0.0002059237,0.000003921415,9.66376e-7,0.000006426983,0.0004010361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5626251,"threshold_uncertainty_score":0.3278757,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2399880602","doi":"10.1609/aaai.v31i1.10983","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":266,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research","keywords":"Computer science; Latent variable; Generative grammar; Generative model; Latent variable model; Artificial intelligence; Context (archaeology); Variable (mathematics); Artificial neural network; Process (computing); Encoder; Machine learning; Task (project management); Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2165077802991398,"gpt":0.3321390255953345,"spread":0.1156312452961947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001197793,0.0005105379,0.0006759178,0.0001634506,0.0006116684,0.001222425,0.006146485,0.0004221719,0.0000112621],"category_scores_gemma":[0.001175459,0.0004065935,0.0003343269,0.0001328852,0.000279113,0.0004067091,0.003330733,0.001028088,0.00001402307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001027488,"about_ca_system_score_gemma":0.000663186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001077328,"about_ca_topic_score_gemma":0.0000268421,"domain_scores_codex":[0.9962401,0.00002573724,0.001036295,0.001345112,0.0006992769,0.0006534617],"domain_scores_gemma":[0.9961873,0.0001622212,0.001105248,0.001171963,0.00121808,0.0001551523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003879926,0.0001213537,0.00002866995,0.0002255302,0.00004103206,3.149701e-7,0.002262543,0.06282789,0.009158833,0.8904637,0.000149268,0.0346821],"study_design_scores_gemma":[0.00001913088,0.00003724152,0.000002073782,0.0003444214,0.00001787257,0.000001204285,0.00001760585,0.5471921,0.02145899,0.4306555,0.00001608169,0.0002378015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01240939,0.00004859458,0.9778567,0.003849672,0.001323567,0.001122729,0.00004055525,0.0001457832,0.003203035],"genre_scores_gemma":[0.7435789,0.00005196902,0.2549351,0.0002291585,0.0003051507,0.0002449751,0.000003357354,0.00002990152,0.0006215897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7311695,"threshold_uncertainty_score":0.9998386,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160825952","doi":"10.1145/1008992.1009024","title":"Dependence language model for information retrieval","year":2004,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Term (time); Smoothing; Linkage (software); Divergence-from-randomness model; Artificial intelligence; Probabilistic logic; Independence (probability theory); Graph; Sentence; Term Discrimination; Axiom; Natural language processing; Theoretical computer science; Visual Word; Mathematics; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02058730128944972,"gpt":0.2583534641804145,"spread":0.2377661628909648,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001263638,0.00004108004,0.00003986346,0.00003687367,0.00003954088,0.00007579214,0.0003252503,0.00002806456,0.000001704407],"category_scores_gemma":[0.00004095058,0.000036277,0.00002239133,0.00007401196,0.000004074714,0.001192651,0.00006629439,0.00003385191,0.00002896464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003287706,"about_ca_system_score_gemma":0.00006539183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002249913,"about_ca_topic_score_gemma":0.000008563659,"domain_scores_codex":[0.9995573,0.000002140539,0.0001076543,0.00008911034,0.0001296045,0.0001142445],"domain_scores_gemma":[0.9996533,0.00001194567,0.00002507133,0.0002355811,0.00004306196,0.00003098585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004802123,0.000008045926,0.000007797454,0.00001192357,0.000002260855,6.270314e-7,0.003888129,0.2486794,0.0005521706,0.7262545,0.00005846404,0.02053191],"study_design_scores_gemma":[0.0002405943,0.00001008607,0.00001092018,0.000003018303,6.910477e-7,0.000002738424,0.0000332681,0.9798227,0.003656473,0.01610895,0.0000576384,0.00005294794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01310052,0.000008582751,0.9837121,0.0004880262,0.00007387193,0.0001121002,8.896542e-7,0.0001388415,0.002365112],"genre_scores_gemma":[0.5996966,5.73842e-7,0.3996842,0.0004404172,0.00001159527,0.000002585849,9.531121e-7,9.902401e-7,0.000162113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7311433,"threshold_uncertainty_score":0.1479333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2469060249","doi":"10.18653/v1/n16-1108","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":249,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Artificial intelligence; SemEval; Pairwise comparison; Similarity (geometry); Natural language processing; Semantic similarity; Word (group theory); Sentence; Semantics (computer science); Focus (optics); Artificial neural network; Selection (genetic algorithm); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06594859114948542,"gpt":0.254434726655701,"spread":0.1884861355062156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004298521,0.0001299205,0.0001264689,0.00004907572,0.0001004933,0.00009985259,0.0003548573,0.0000436001,0.000008027402],"category_scores_gemma":[0.00003546883,0.00007714452,0.00005445092,0.00008957845,0.00001010288,0.0006156344,0.0001010014,0.00007815084,0.000002743282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001068214,"about_ca_system_score_gemma":0.00002169886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003403782,"about_ca_topic_score_gemma":0.0002629305,"domain_scores_codex":[0.998771,0.00003534473,0.0002112368,0.0003920623,0.0002901902,0.000300163],"domain_scores_gemma":[0.9991599,0.00006310936,0.00005571853,0.0004337867,0.0002091793,0.0000782739],"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":[0.0000449652,0.0000377734,0.000335135,0.00001449445,0.00002410097,0.00000250748,0.0001272683,0.668222,0.0001803108,0.004945842,0.00005454505,0.326011],"study_design_scores_gemma":[0.0004283808,0.00005472103,0.00002826832,0.00004598459,0.000008576813,0.000006264715,0.00001642231,0.9978607,0.0001211098,0.001232923,0.00005319207,0.0001434348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01192894,0.00003516585,0.98487,0.002181734,0.0003702232,0.0002645829,1.289987e-7,0.0002056565,0.000143616],"genre_scores_gemma":[0.915929,0.000002896406,0.08357996,0.0002936591,0.0001147926,0.00003357158,2.457833e-7,0.00000933776,0.00003660334],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.904,"threshold_uncertainty_score":0.3145862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151752770","doi":"10.1023/b:inrt.0000011209.19643.e2","title":"Augmenting Naive Bayes Classifiers with Statistical Language Models","year":2004,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":247,"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":"Naive Bayes classifier; Artificial intelligence; Computer science; Machine learning; Bayes error rate; Bayes classifier; Bayes' theorem; Classifier (UML); Conditional independence; Bayesian programming; Natural language processing; Pattern recognition (psychology); Bayes factor; Bayesian probability; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.01324613556970664,"gpt":0.2371975164125819,"spread":0.2239513808428753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926023,0.00009013081,0.00008838175,0.00009451572,0.0000992097,0.0002317691,0.00028488,0.00004685853,0.00001195911],"category_scores_gemma":[0.0000530533,0.0000753612,0.00001898191,0.000223561,0.00002984456,0.002853663,0.00008076937,0.0001286564,0.00006952407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009778347,"about_ca_system_score_gemma":0.0001347022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003422343,"about_ca_topic_score_gemma":0.000002026844,"domain_scores_codex":[0.9990052,0.00001330831,0.0002491017,0.0001175792,0.0004055533,0.000209247],"domain_scores_gemma":[0.9994519,0.0000364254,0.00009963191,0.000247817,0.00008643734,0.00007773283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000500416,0.0000207407,0.00007901485,0.00004487525,0.00002641756,0.00002097643,0.01684953,0.1065922,0.0000888289,0.8306463,0.00009249901,0.04548853],"study_design_scores_gemma":[0.001193371,0.0001227641,0.0002708093,0.00004549321,0.000007051784,0.00003632784,0.001092968,0.9835308,0.001609518,0.01132223,0.000528303,0.000240426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0353856,0.000009743699,0.9577029,0.0002930962,0.0001128778,0.0001169156,0.000006373999,0.0001663557,0.006206165],"genre_scores_gemma":[0.8069105,0.000001161922,0.1926491,0.0003702589,0.00002383956,0.000002295991,0.00001272458,0.000003116669,0.00002708769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8769385,"threshold_uncertainty_score":0.307314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982424689","doi":"10.1016/j.yjbinx.2019.100057","title":"A survey of word embeddings for clinical text","year":2019,"lang":"en","type":"review","venue":"Journal of Biomedical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":240,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Word (group theory); Computer science; Blueprint; Natural language processing; Artificial intelligence; Information retrieval; Data science; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2610558891467246,"gpt":0.4618205473794558,"spread":0.2007646582327313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00760071,0.000256906,0.002660444,0.0004724343,0.00002683759,0.00008989685,0.00236871,0.0005394145,0.000009976684],"category_scores_gemma":[0.002350724,0.0001678109,0.0009911242,0.0005728049,0.0001300829,0.0004631257,0.0004018021,0.0008226775,0.00002634849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007247286,"about_ca_system_score_gemma":0.001614903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003057062,"about_ca_topic_score_gemma":3.58355e-7,"domain_scores_codex":[0.992845,0.0001895482,0.005673858,0.0001167057,0.000876858,0.0002980497],"domain_scores_gemma":[0.9905851,0.002774305,0.00515148,0.0005844434,0.000606311,0.0002984006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003530454,0.00005962088,0.000004524281,0.008645172,0.0001493733,0.000001864901,0.0001383267,0.00000157009,4.755375e-9,0.0001715405,0.007511883,0.9833126],"study_design_scores_gemma":[0.0004296601,0.0003470613,0.00001073465,0.00779607,0.0001846326,0.0001146348,0.00001329867,0.02342762,6.215451e-8,0.00008128492,0.9674192,0.0001757282],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000004691303,0.482112,0.5158611,0.00003576708,0.001661224,0.0002423361,0.00002370105,0.000007232219,0.0000519424],"genre_scores_gemma":[0.000005071084,0.8512678,0.148267,0.0001101203,0.0002674206,0.000002358902,0.00001292587,0.00001259632,0.00005473792],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9831368,"threshold_uncertainty_score":0.6843128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000545282","doi":"10.1145/383952.384024","title":"Exploiting redundancy in question answering","year":2001,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; Redundancy (engineering); Information retrieval; Questions and answers; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02908871098396682,"gpt":0.2689517235673928,"spread":0.239863012583426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001928926,0.00004173292,0.00004737563,0.00006345531,0.00002612967,0.00005217812,0.000216307,0.00001932666,0.00001156954],"category_scores_gemma":[0.00002402997,0.00004188746,0.00001125033,0.0001758976,0.000003485792,0.0004422766,0.00007618192,0.00005727653,0.00001915781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003117825,"about_ca_system_score_gemma":0.00001145921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001667581,"about_ca_topic_score_gemma":0.00006126937,"domain_scores_codex":[0.9994607,0.00001797209,0.0001214917,0.0001733573,0.00008224875,0.0001442133],"domain_scores_gemma":[0.9997298,0.0000155528,0.00001670765,0.0002008756,0.0000120913,0.00002498073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001719734,0.00003492972,0.03983414,0.000009530717,0.000001773286,0.00008790807,0.001359884,0.00634196,0.003733933,0.536315,0.00003808746,0.4122412],"study_design_scores_gemma":[0.0002059125,0.00001510041,0.008831951,0.00007411231,4.127282e-7,0.00002793116,0.0001043656,0.9684095,0.001227188,0.01975743,0.001180433,0.0001656945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2703959,0.00002405499,0.7153769,0.0004357593,0.0001068683,0.00002605501,8.608747e-9,0.0001264536,0.01350804],"genre_scores_gemma":[0.8745393,0.00001462607,0.1250264,0.0001060911,0.00004044649,0.000003616186,1.056923e-7,0.000002356027,0.000267135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9620675,"threshold_uncertainty_score":0.1708121,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}