{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":208,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":208,"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","author_layer_release":"2026-06-26"},"query_hash":"7972bc65e4ab","filters":{"venue":"Neural Information Processing Systems"}},"results":[{"id":"W2137245235","doi":"","title":"Probabilistic Matrix Factorization","year":2007,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":3578,"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":"Computer science; Collaborative filtering; Probabilistic logic; Matrix decomposition; Recommender system; Factorization; Statistical model; Restricted Boltzmann machine; Artificial intelligence; Machine learning; Algorithm; Deep learning","authors":[{"name":"Andriy Mnih","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01864301288759024,"gpt":0.2788405083286757,"spread":0.2601974954410855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004798536,0.002390801,0.00251368,0.001716696,0.001215384,0.002056759,0.003465956,0.002475635,0.009272612],"category_scores_gemma":[0.01503295,0.001226535,0.002800063,0.003094787,0.001328503,0.003413329,0.001981526,0.003557827,0.004502507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167796,"about_ca_system_score_gemma":0.001626184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009323824,"about_ca_topic_score_gemma":0.01036777,"domain_scores_codex":[0.9961061,0.00155147,0.0001750491,0.0008784189,0.001076306,0.0002127165],"domain_scores_gemma":[0.9931105,0.004351834,0.0004406566,0.001093217,0.0008535365,0.0001502001],"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":[0.0001741941,0.0001960301,0.002121471,0.0007038458,0.0005586457,0.0002312698,0.0003010993,0.4437939,0.002184089,0.1984105,0.02485827,0.3264666],"study_design_scores_gemma":[0.00002498321,0.00003740815,0.0002529267,0.00003290586,0.00003025821,0.0001012238,0.00002703703,0.8899391,0.0003766372,0.1031281,0.00602218,0.00002720634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001308467,0.000474213,0.995666,0.0003543737,0.00009193415,0.00006806324,0.000295611,0.0003265023,0.001414905],"genre_scores_gemma":[0.1612971,0.002377212,0.8246697,0.0005373622,0.0006686589,0.0006617697,0.002010814,0.0001343243,0.007643106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009323824,"threshold_uncertainty_score":0.03101993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139047169","doi":"","title":"Saliency Based on Information Maximization","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":1100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Maximization; Computer science; Measure (data warehouse); Artificial intelligence; Domain (mathematical analysis); Software deployment; Computer vision; Visual attention; Artificial neural network; Pattern recognition (psychology); Machine learning; Data mining; Cognition; Mathematics; Neuroscience; Psychology","authors":[{"name":"Neil D. B. Bruce","is_ca":true},{"name":"John K. Tsotsos","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01368537770078852,"gpt":0.2489936841638926,"spread":0.235308306463104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008506301,0.0004820429,0.0006649462,0.000828578,0.0002839619,0.0009069972,0.001254652,0.0006736276,0.001936339],"category_scores_gemma":[0.002620182,0.0002662023,0.0006585295,0.000514042,0.001204492,0.001838907,0.0008749282,0.0006401,0.0003746286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217232,"about_ca_system_score_gemma":0.0004246233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00121855,"about_ca_topic_score_gemma":0.001005642,"domain_scores_codex":[0.9996312,0.0001118507,0.0000148017,0.00007877946,0.0001147729,0.00004865906],"domain_scores_gemma":[0.9992384,0.0004583516,0.00008637136,0.00006449044,0.00009774946,0.00005466024],"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":[0.0001181022,0.00004242645,0.000816995,0.000188771,0.0000828776,0.0001843905,0.000335194,0.2074172,0.01555023,0.7107717,0.003171131,0.06132083],"study_design_scores_gemma":[0.00001047428,0.00006468375,0.0005021059,0.00001230824,0.00001290607,0.00009260414,0.00001285193,0.8003773,0.001487432,0.1959562,0.001453803,0.00001726746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03048849,0.0008416623,0.9573815,0.0005576868,0.00005331084,0.0000411023,0.00006244848,0.0002055286,0.0103683],"genre_scores_gemma":[0.9147018,0.0005891798,0.07942398,0.0001551526,0.0001327841,0.0000994755,0.00005728054,0.0000739888,0.004766413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001936339,"threshold_uncertainty_score":0.00883168,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2811124557","doi":"","title":"Hierarchical graph representation learning with differentiable pooling","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":909,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Pooling; Differentiable function; Computer science; Graph; Artificial intelligence; Theoretical computer science; Benchmark (surveying); Pattern recognition (psychology); Mathematics","authors":[{"name":"Zhitao Ying","is_ca":false},{"name":"Jiaxuan You","is_ca":false},{"name":"Christopher Morris","is_ca":false},{"name":"Xiang Ren","is_ca":false},{"name":"William L. Hamilton","is_ca":true},{"name":"Jure Leskovec","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01436539982481925,"gpt":0.2542677497504681,"spread":0.2399023499256489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007720315,0.001957163,0.00113872,0.001281392,0.0004535883,0.001009601,0.002451393,0.001124081,0.00405554],"category_scores_gemma":[0.002381074,0.0004999095,0.001403535,0.001599128,0.0007139161,0.003598896,0.001799654,0.001691826,0.001501823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001592271,"about_ca_system_score_gemma":0.001091344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009685178,"about_ca_topic_score_gemma":0.01622303,"domain_scores_codex":[0.9994804,0.00008980309,0.00002308702,0.0002167232,0.0001168022,0.00007322954],"domain_scores_gemma":[0.9994129,0.0001426841,0.000068929,0.0002258272,0.0001044274,0.00004511284],"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":[0.0002202581,0.0001833222,0.00109541,0.000228655,0.0001965268,0.0001550698,0.0001331096,0.36272,0.01324384,0.0280286,0.01997873,0.5738164],"study_design_scores_gemma":[0.00001331205,0.00003903009,0.0002210153,0.000008674614,0.00002113426,0.00002884878,0.00001508644,0.9701634,0.003424375,0.02449279,0.001563608,0.000008803861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03061982,0.0006282172,0.9566175,0.0003791101,0.00008749845,0.00008938764,0.0006044134,0.007794263,0.003179837],"genre_scores_gemma":[0.5373724,0.0006521656,0.4451632,0.0006176488,0.0001076464,0.0002104923,0.004964486,0.0007014129,0.01021047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009685178,"threshold_uncertainty_score":0.01925761,"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","authors":[{"name":"Geoffrey E. Hinton","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00253677,0.001011345,0.001215775,0.00111654,0.0004340289,0.001841758,0.003925291,0.001801184,0.004651243],"category_scores_gemma":[0.008755062,0.0006968254,0.001414285,0.001778101,0.001081588,0.003112356,0.002037663,0.002789772,0.002248765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009531957,"about_ca_system_score_gemma":0.0009476447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002743036,"about_ca_topic_score_gemma":0.003869815,"domain_scores_codex":[0.9985086,0.0006480836,0.00007517381,0.0003823524,0.0002740597,0.000111612],"domain_scores_gemma":[0.9977815,0.001374932,0.0001762602,0.0003973173,0.0001944201,0.0000756003],"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":[0.0007663705,0.0003113491,0.002839805,0.0003650409,0.0003339312,0.0003258665,0.0003670751,0.5802077,0.01394393,0.1008362,0.01360971,0.286093],"study_design_scores_gemma":[0.00001601577,0.00002263188,0.0002337582,0.00001131884,0.0000230329,0.00004081248,0.000009474785,0.9637141,0.001556163,0.03282509,0.00153249,0.00001513398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01010815,0.0001901748,0.9862272,0.0003714082,0.00005935847,0.00005593687,0.0004783367,0.00101642,0.00149297],"genre_scores_gemma":[0.5163999,0.0006980925,0.4654991,0.0007429844,0.0003108467,0.000798258,0.002707825,0.0005161922,0.01232681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004651243,"threshold_uncertainty_score":0.01555997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753798143","doi":"","title":"Deep Sets","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":318,"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":"Anomaly detection; Computer science; Invariant (physics); Statistic; Population; Outlier; Artificial intelligence; Permutation (music); Machine learning; Data mining; Pattern recognition (psychology); Theoretical computer science; Mathematics; Statistics","authors":[{"name":"Manzil Zaheer","is_ca":false},{"name":"Satwik Kottur","is_ca":false},{"name":"Siamak Ravanbakhsh","is_ca":false},{"name":"Barnabás Póczos","is_ca":false},{"name":"Russ R. Salakhutdinov","is_ca":true},{"name":"Alexander J. Smola","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02175104945544126,"gpt":0.2825962630455809,"spread":0.2608452135901397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002264715,0.001427856,0.001356804,0.001173855,0.0004961939,0.00204388,0.002815527,0.00180044,0.004138183],"category_scores_gemma":[0.009025199,0.0007739006,0.001384564,0.001061166,0.00165213,0.004133913,0.002673347,0.003548971,0.0009767226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001815916,"about_ca_system_score_gemma":0.001030446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001978859,"about_ca_topic_score_gemma":0.002049804,"domain_scores_codex":[0.9985775,0.0004598084,0.00007842185,0.0003953527,0.0003501622,0.0001387025],"domain_scores_gemma":[0.9963626,0.002232452,0.0003578023,0.0004972154,0.0003861145,0.0001638752],"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":[0.00009636526,0.0001212371,0.001404064,0.0002234548,0.0001272888,0.00009724515,0.0001215349,0.6174368,0.001484753,0.2634129,0.005909001,0.1095652],"study_design_scores_gemma":[0.000007227005,0.00004052593,0.0001074262,0.00001979617,0.0000106806,0.00002071375,0.00001101287,0.852504,0.0005731491,0.1444103,0.002288624,0.000006752764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01036265,0.0003562012,0.9856572,0.0006148196,0.00006216722,0.00003913448,0.0002626377,0.000303362,0.002341904],"genre_scores_gemma":[0.5200796,0.00146649,0.4617645,0.001114855,0.0003443978,0.0007411595,0.001811661,0.0003144855,0.01236276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004138183,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168148636","doi":"","title":"Incorporating Second-Order Functional Knowledge for Better Option Pricing","year":2000,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Generalization; Computer science; A priori and a posteriori; Class (philosophy); Task (project management); Function (biology); Order (exchange); Convex function; Artificial neural network; Machine learning; Artificial intelligence; Regular polygon; Mathematical optimization; Mathematics","authors":[{"name":"Charles Dugas","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"François Bélisle","is_ca":true},{"name":"Claude Nadeau","is_ca":true},{"name":"René García","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02175691798115745,"gpt":0.2499960200512804,"spread":0.228239102070123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00274523,0.0009902281,0.001225434,0.0005671997,0.000311504,0.001544973,0.0009338008,0.002180309,0.003656572],"category_scores_gemma":[0.008553853,0.000562892,0.0008824836,0.000589206,0.0006535857,0.004974237,0.001139711,0.00303132,0.001130264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006246938,"about_ca_system_score_gemma":0.0009563144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001961522,"about_ca_topic_score_gemma":0.003593667,"domain_scores_codex":[0.9994941,0.000169261,0.00003574916,0.0001014736,0.0001381412,0.00006128831],"domain_scores_gemma":[0.9968342,0.001607283,0.0002515028,0.0008843112,0.0003424593,0.00008023226],"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":[0.0001689462,0.0003899851,0.002248135,0.0001271465,0.0001349474,0.00009044538,0.00008569635,0.7358449,0.01828142,0.02746446,0.001798546,0.2133653],"study_design_scores_gemma":[0.0000094598,0.00002818288,0.0002942579,0.000007653382,0.000007686217,0.00001643474,0.000003302202,0.9901528,0.001692204,0.007283091,0.0004971481,0.00000776209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0418994,0.0004006881,0.9539743,0.0004704314,0.00004902459,0.00002694033,0.00003461886,0.0008457358,0.002298855],"genre_scores_gemma":[0.7320511,0.0005912946,0.2624489,0.0004043712,0.0001254363,0.00007718663,0.0002186017,0.0002100337,0.00387307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003656572,"threshold_uncertainty_score":0.01451832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160163723","doi":"","title":"Parametric Bandits: The Generalized Linear Case","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":261,"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":"Regret; Parameterized complexity; Generalized linear model; Parametric statistics; Computer science; Mathematical optimization; Linear model; Applied mathematics; Mathematics; Algorithm; Machine learning; Statistics","authors":[{"name":"Sarah Filippi","is_ca":false},{"name":"Olivier Cappé","is_ca":false},{"name":"Aurélien Garivier","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1076079387823779,"gpt":0.4263062865630172,"spread":0.3186983477806393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004796262,0.001375101,0.002314568,0.000966577,0.0007434839,0.003075278,0.002419904,0.00298553,0.003788901],"category_scores_gemma":[0.02690956,0.0007497104,0.001091223,0.001786333,0.002917579,0.004336558,0.002557728,0.003919819,0.0007395204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001358666,"about_ca_system_score_gemma":0.0009697663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002793439,"about_ca_topic_score_gemma":0.002219034,"domain_scores_codex":[0.9964722,0.002164506,0.0001014215,0.0005368181,0.0003780416,0.0003469819],"domain_scores_gemma":[0.9866454,0.009924301,0.001724435,0.001047793,0.0003924641,0.0002656093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009152276,0.00006761034,0.0008007946,0.0001004922,0.00007614135,0.0003103268,0.0001117949,0.753856,0.0003980112,0.2226601,0.001387056,0.02014021],"study_design_scores_gemma":[0.0000157395,0.00002467084,0.0001114829,0.00001317716,0.000009080822,0.00005095188,0.00002360749,0.9104796,0.000113674,0.0886912,0.0004545712,0.00001219739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03773119,0.0009692831,0.9541205,0.001410819,0.00006093159,0.00008029519,0.0001475637,0.0002199762,0.005259498],"genre_scores_gemma":[0.8931358,0.001010096,0.09912643,0.0005110618,0.0002034904,0.0002823549,0.0001407428,0.00008648523,0.005503578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004796262,"threshold_uncertainty_score":0.02536541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971278153","doi":"","title":"Latent Ordinary Differential Equations for Irregularly-Sampled Time Series","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":253,"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":"Ode; Recurrent neural network; Ordinary differential equation; Series (stratigraphy); Computer science; Applied mathematics; Time series; Differential equation; Algorithm; Artificial neural network; Artificial intelligence; Mathematics; Machine learning; Mathematical analysis","authors":[{"name":"Yulia Rubanova","is_ca":true},{"name":"Ricky T. Q. Chen","is_ca":true},{"name":"David Duvenaud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0192629939325515,"gpt":0.2673070319413511,"spread":0.2480440380087996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001516092,0.0005219086,0.0006702506,0.0004753375,0.0002569631,0.0008622803,0.00113445,0.001181405,0.002044436],"category_scores_gemma":[0.006789045,0.0004431889,0.0008789213,0.0006209252,0.0009095588,0.001821161,0.000912648,0.001982132,0.0002748013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025381,"about_ca_system_score_gemma":0.0007289068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007972819,"about_ca_topic_score_gemma":0.006901272,"domain_scores_codex":[0.9994158,0.0001417417,0.00004621967,0.0001921451,0.0001522192,0.00005191332],"domain_scores_gemma":[0.9982016,0.001055663,0.0003435589,0.0001344793,0.0002039312,0.00006076911],"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":[0.00003106195,0.00002773256,0.002275797,0.00009641481,0.00004282757,0.0002093588,0.0001319645,0.8531134,0.003506005,0.1279561,0.0009787594,0.01163058],"study_design_scores_gemma":[0.000001490707,0.000001860891,0.0001446649,0.000002358224,0.000001867021,0.00001068417,0.000003224198,0.9907503,0.0001092914,0.008772095,0.0001989831,0.000003139569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03005453,0.0003705777,0.9666666,0.0004453867,0.0001162984,0.0000280505,0.0003176788,0.0002,0.001800871],"genre_scores_gemma":[0.873157,0.001349431,0.1089828,0.0003854173,0.000149791,0.000219628,0.000857125,0.0001712531,0.01472759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007972819,"threshold_uncertainty_score":0.01585281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2551156993","doi":"","title":"Supervised Learning with Tensor Networks","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":214,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Perimeter Institute","funders":"","keywords":"MNIST database; Tensor (intrinsic definition); Artificial intelligence; Computer science; Machine learning; Tensor product; Set (abstract data type); Kernel (algebra); Moment tensor; Interpretation (philosophy); Matrix (chemical analysis); Supervised learning; Mathematics; Algorithm; Deep learning; Artificial neural network; Pure mathematics; Physics","authors":[{"name":"E. Miles Stoudenmire","is_ca":true},{"name":"David J. Schwab","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0299515621861944,"gpt":0.2749004509657065,"spread":0.2449488887795121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003981408,0.001481448,0.001298249,0.001870517,0.0008238954,0.002590495,0.00180293,0.001337885,0.002637927],"category_scores_gemma":[0.0190013,0.0009234506,0.001196856,0.002035971,0.001695283,0.003637744,0.002754788,0.002892578,0.00142186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001372083,"about_ca_system_score_gemma":0.001780948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002488069,"about_ca_topic_score_gemma":0.003190878,"domain_scores_codex":[0.9957176,0.002409882,0.0002281697,0.0007509525,0.0007575896,0.0001359455],"domain_scores_gemma":[0.9914836,0.004189298,0.0008176892,0.00214417,0.00114526,0.0002199331],"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":[0.0001787455,0.0001176198,0.00177831,0.0004464342,0.0002886773,0.000112979,0.0001961736,0.5305836,0.004263234,0.1137828,0.01237329,0.3358782],"study_design_scores_gemma":[0.000009270379,0.0000215515,0.0001365583,0.00002078524,0.000009846007,0.00002137894,0.00001152633,0.9035607,0.001202043,0.09271883,0.002277274,0.00001027578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00337055,0.0003694786,0.9940601,0.0002198948,0.00004484922,0.00003975411,0.0001407165,0.0008932609,0.0008613774],"genre_scores_gemma":[0.2060093,0.001185928,0.7867483,0.0002467548,0.0003033062,0.0003489297,0.00157518,0.0004881994,0.003094153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003981408,"threshold_uncertainty_score":0.021056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W217970951","doi":"","title":"Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"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":"Hidden Markov model; Computer science; Artificial intelligence; Speech recognition; Context (archaeology); Deep belief network; Vocabulary; Deep learning; Pattern recognition (psychology)","authors":[{"name":"Dong Yu","is_ca":false},{"name":"Li Deng","is_ca":false},{"name":"George E. Dahl","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0420777987342523,"gpt":0.2835390570334626,"spread":0.2414612582992103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002368216,0.0009037516,0.0006792231,0.0002482289,0.0004271232,0.0008939229,0.001014967,0.0009694697,0.00114991],"category_scores_gemma":[0.01076601,0.0005981241,0.0002994373,0.0002687143,0.0007572976,0.001834701,0.0008233417,0.002285954,0.0004435473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005206584,"about_ca_system_score_gemma":0.0007364769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002723801,"about_ca_topic_score_gemma":0.005689869,"domain_scores_codex":[0.998961,0.0004882344,0.00007848669,0.0002401548,0.000145004,0.00008711986],"domain_scores_gemma":[0.9953188,0.003090937,0.0001984696,0.0008934874,0.0003424922,0.0001556473],"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":[0.001019309,0.000948187,0.00597988,0.0002653667,0.0001215214,0.0001828043,0.0003519286,0.3391735,0.1617721,0.004298137,0.001051577,0.4848358],"study_design_scores_gemma":[0.0000393183,0.0002396897,0.003631412,0.00003471152,0.00003743851,0.000111494,0.00005617072,0.900795,0.09020231,0.003559868,0.001249311,0.00004330766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2326293,0.001007637,0.7605448,0.000394664,0.0001078977,0.0001296132,0.00007674225,0.002095452,0.003013918],"genre_scores_gemma":[0.8010703,0.0002353623,0.1970919,0.0001770892,0.00002824368,0.0001128555,0.0001499794,0.0001505796,0.0009836755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002723801,"threshold_uncertainty_score":0.01252443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162724919","doi":"","title":"Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes","year":2007,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":188,"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":"Deep belief network; Artificial intelligence; Covariance; Kernel (algebra); Computer science; Gaussian process; Pattern recognition (psychology); Backpropagation; Deep learning; Gaussian; Machine learning; Mathematics; Artificial neural network; Statistics","authors":[{"name":"Geoffrey E. Hinton","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04064166434881589,"gpt":0.3030173763764282,"spread":0.2623757120276123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002116637,0.001169191,0.0009814743,0.0008750045,0.0005016764,0.001869528,0.001746933,0.001514972,0.001768202],"category_scores_gemma":[0.008066268,0.0008132198,0.0009239351,0.001025648,0.001242448,0.003728316,0.001955249,0.003192704,0.0006994141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001517251,"about_ca_system_score_gemma":0.001350551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008180103,"about_ca_topic_score_gemma":0.008884639,"domain_scores_codex":[0.9992017,0.0002553698,0.00004543279,0.0001749966,0.0002289266,0.0000936142],"domain_scores_gemma":[0.9976014,0.001410671,0.0002095289,0.0003690401,0.0003181522,0.0000911697],"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":[0.0001087728,0.0001030601,0.001376498,0.0001010577,0.0001087228,0.0000901485,0.00009875376,0.7537695,0.003328965,0.1048942,0.002482202,0.1335382],"study_design_scores_gemma":[0.000004142847,0.000004566759,0.00004960938,0.000003769512,0.00000451272,0.000007905258,0.000001913791,0.9725282,0.0006898562,0.0264521,0.0002485074,0.000004875962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002650589,0.00007350581,0.9964676,0.00008755802,0.00001309416,0.000006445029,0.00002985337,0.0002759565,0.0003954776],"genre_scores_gemma":[0.3460253,0.0004757337,0.6493198,0.0002151366,0.00008761508,0.0001005195,0.0004000339,0.0002338923,0.003141935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008180103,"threshold_uncertainty_score":0.01626498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964096266","doi":"","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Robustness (evolution); Discriminative model; Artificial intelligence; Inference; Convolutional neural network; Deep neural networks; Pattern recognition (psychology); Machine learning; Noise (video); Training set; Graphical model; Artificial neural network; Noise measurement; Image (mathematics); Noise reduction","authors":[{"name":"Arash Vahdat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0666042164439337,"gpt":0.2991574030539693,"spread":0.2325531866100355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01270445,0.002558243,0.002446637,0.001386195,0.001195142,0.002601301,0.003828435,0.003287358,0.001091059],"category_scores_gemma":[0.05570972,0.001835593,0.001199221,0.001608805,0.003432492,0.005630956,0.005742977,0.007066675,0.000804974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002514095,"about_ca_system_score_gemma":0.001905029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004507687,"about_ca_topic_score_gemma":0.00629003,"domain_scores_codex":[0.9927893,0.003550938,0.0002981987,0.001626106,0.001294522,0.0004409188],"domain_scores_gemma":[0.9700409,0.0207071,0.002265053,0.004767334,0.001790982,0.0004287212],"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":[0.0009956151,0.0002404562,0.004809876,0.0002959676,0.0002319857,0.0001945835,0.0003356329,0.7899922,0.009684678,0.02429932,0.005394794,0.163525],"study_design_scores_gemma":[0.00002500711,0.00004521221,0.0002369122,0.00001940986,0.00001523649,0.00002763011,0.00002017675,0.9748253,0.002812689,0.02154587,0.0004175395,0.000008909649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03078092,0.0004921588,0.9647859,0.0007337268,0.00005692046,0.00005208174,0.0001927116,0.002037569,0.0008679305],"genre_scores_gemma":[0.643769,0.0004823609,0.3483629,0.001296074,0.0002315476,0.00038952,0.001946567,0.0007671797,0.002754842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01270445,"threshold_uncertainty_score":0.06718832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962850650","doi":"","title":"SimplE embedding for link prediction in knowledge graphs","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Simple (philosophy); Embedding; Computer science; Theoretical computer science; Factorization; Link (geometry); Graph embedding; Tying; Artificial intelligence; Algorithm","authors":[{"name":"Seyed Mehran Kazemi","is_ca":true},{"name":"David Poole","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02168659529710737,"gpt":0.3003203198068173,"spread":0.27863372450971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001619047,0.00165345,0.001111328,0.001714003,0.0007784635,0.001907713,0.002144836,0.0015936,0.0105792],"category_scores_gemma":[0.0167665,0.0009463351,0.001539408,0.002607841,0.001516106,0.009229476,0.002751979,0.003067751,0.002826119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001723766,"about_ca_system_score_gemma":0.001297502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005079478,"about_ca_topic_score_gemma":0.009516492,"domain_scores_codex":[0.9982576,0.0004080901,0.0001385211,0.0005731507,0.0004643229,0.0001582661],"domain_scores_gemma":[0.9930328,0.003245059,0.0006126324,0.002141096,0.0007447319,0.0002236878],"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":[0.0003537759,0.0002498822,0.002743556,0.0006559499,0.0001399011,0.000304112,0.0003850941,0.4516407,0.005090694,0.1507879,0.02419419,0.3634543],"study_design_scores_gemma":[0.00001467877,0.00002362816,0.0001854791,0.00003070056,0.00001861495,0.00004689677,0.00003130317,0.8100525,0.001010095,0.1860184,0.00255299,0.00001471215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01880349,0.0003940493,0.9726942,0.0005461517,0.00007842755,0.0001032827,0.001781589,0.003253822,0.002345041],"genre_scores_gemma":[0.4284196,0.0009389913,0.5533822,0.0004627723,0.0001886205,0.0003939879,0.008075178,0.0007471135,0.007391531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0105792,"threshold_uncertainty_score":0.03539097,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970803838","doi":"","title":"Lookahead Optimizer: k steps forward, 1 step back","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":176,"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":"Treebank; Computer science; Stochastic gradient descent; Hyperparameter; Artificial neural network; Machine translation; Computation; Artificial intelligence; Gradient descent; Algorithm; Deep neural networks; Stability (learning theory); Mathematical optimization; Machine learning; Mathematics","authors":[{"name":"Michael R. Zhang","is_ca":true},{"name":"James Lucas","is_ca":true},{"name":"Jimmy Ba","is_ca":true},{"name":"Geoffrey E. Hinton","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01359282323168757,"gpt":0.2465341774647059,"spread":0.2329413542330183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00139436,0.002282244,0.002000096,0.0005904149,0.0005439692,0.001158388,0.002618356,0.002587322,0.009455135],"category_scores_gemma":[0.003832751,0.00105402,0.0008048912,0.0006425067,0.0009128733,0.001626361,0.001449244,0.003083411,0.006158217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009125455,"about_ca_system_score_gemma":0.002323115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006823099,"about_ca_topic_score_gemma":0.01049019,"domain_scores_codex":[0.9993363,0.0001780223,0.00005454863,0.000189898,0.0001724585,0.00006873939],"domain_scores_gemma":[0.999222,0.0003311397,0.0000695203,0.0001743044,0.0001478067,0.0000550663],"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":[0.0008049755,0.0003517779,0.001428415,0.0003365876,0.0002042052,0.0002265959,0.0001077944,0.613649,0.006171588,0.01376205,0.04105739,0.3218997],"study_design_scores_gemma":[0.00005539183,0.00004963327,0.0000752905,0.00001188822,0.00001140654,0.00002441736,0.000007253946,0.993634,0.001476932,0.003242313,0.001400877,0.00001061439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01681593,0.001110017,0.9568142,0.0005395073,0.000297029,0.0001888526,0.0004042523,0.01915729,0.004672947],"genre_scores_gemma":[0.2647398,0.0004347577,0.7129027,0.001095183,0.0001556224,0.0005940909,0.002017586,0.002466964,0.0155933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009455135,"threshold_uncertainty_score":0.03163064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134042548","doi":"","title":"Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; McGill University","funders":"","keywords":"Temporal difference learning; Function approximation; Stochastic approximation; Markov decision process; Mathematics; Function (biology); Stochastic gradient descent; Bellman equation; Mathematical optimization; Convergence (economics); Nonlinear system; Approximation algorithm; Artificial neural network; Gradient descent; Approximation error; Markov process; Rate of convergence; Algorithm; Applied mathematics; Reinforcement learning; Computer science; Artificial intelligence; Key (lock)","authors":[{"name":"Shalabh Bhatnagar","is_ca":false},{"name":"Doina Precup","is_ca":true},{"name":"David Silver","is_ca":true},{"name":"Richard S. Sutton","is_ca":true},{"name":"Hamid Reza Maei","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01454759173183138,"gpt":0.2203356894460717,"spread":0.2057880977142404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002428547,0.0008440595,0.001028083,0.0005100523,0.0004018143,0.001091728,0.001799633,0.001451297,0.002872385],"category_scores_gemma":[0.008947497,0.0004719117,0.0008248786,0.0005218561,0.00176298,0.001887123,0.002068795,0.002300656,0.0005582396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001347799,"about_ca_system_score_gemma":0.001307006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003179274,"about_ca_topic_score_gemma":0.001936952,"domain_scores_codex":[0.9993286,0.0001756819,0.00004290179,0.0001358357,0.0002541276,0.00006286525],"domain_scores_gemma":[0.9976478,0.001377467,0.0001821658,0.000255222,0.0004383454,0.00009886328],"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":[0.0001182077,0.00006276508,0.0005913373,0.0001536661,0.00004692168,0.00009520556,0.0001263292,0.7048174,0.002621078,0.2241525,0.001096876,0.06611783],"study_design_scores_gemma":[0.000006469439,0.00001728161,0.00002152804,0.000005862671,0.000002701945,0.0000128072,0.00000210343,0.9857782,0.0004800543,0.01313381,0.0005346536,0.000004486166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003118963,0.0001842242,0.9950233,0.0001141731,0.00004114212,0.00002142456,0.00001278687,0.00008456127,0.001399549],"genre_scores_gemma":[0.3630849,0.0004497861,0.6290939,0.0002417156,0.00008954435,0.0002337302,0.0000930766,0.0001302213,0.006583024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003179274,"threshold_uncertainty_score":0.01284355,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753686090","doi":"","title":"DropoutNet: Addressing Cold Start in Recommender Systems","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":154,"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":"Cold start (automotive); Computer science; Recommender system; Scalability; Dropout (neural networks); Deep learning; Focus (optics); Artificial neural network; Artificial intelligence; Code (set theory); Machine learning; Deep neural networks; Database","authors":[{"name":"Maksims Volkovs","is_ca":true},{"name":"Guang Yu","is_ca":false},{"name":"Tomi Poutanen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0726473000804211,"gpt":0.3102200947430976,"spread":0.2375727946626766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005234415,0.0015484,0.002626134,0.0007741285,0.001472978,0.001924807,0.004067247,0.003244734,0.005291685],"category_scores_gemma":[0.01427719,0.001282858,0.001385185,0.001124265,0.001433501,0.005240412,0.003587662,0.006096192,0.002146352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002541173,"about_ca_system_score_gemma":0.002233778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.016859,"about_ca_topic_score_gemma":0.03408351,"domain_scores_codex":[0.9974607,0.001091844,0.0001558033,0.0005862904,0.0004430723,0.0002622513],"domain_scores_gemma":[0.9933773,0.004005729,0.0004044374,0.001136925,0.0008038286,0.0002718998],"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":[0.001470795,0.0007288436,0.006957904,0.0007687781,0.000481571,0.0004163497,0.0006595356,0.6806151,0.004333635,0.02943872,0.0337466,0.2403822],"study_design_scores_gemma":[0.00003955828,0.00006961956,0.0001875606,0.00002022876,0.00002392091,0.00002814271,0.00001627724,0.9888483,0.0009634878,0.008670956,0.001119072,0.00001288326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05334657,0.002201137,0.9315229,0.001555339,0.0002508182,0.0002264383,0.001037056,0.005929776,0.003929933],"genre_scores_gemma":[0.7042405,0.0009465954,0.2720304,0.00180694,0.0002891803,0.0004917138,0.003854095,0.0009338735,0.01540662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.016859,"threshold_uncertainty_score":0.03352171,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890732907","doi":"","title":"Supervised autoencoders: Improving generalization performance with unsupervised regularizers","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":152,"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":"Generalization; Computer science; Regularization (linguistics); Artificial intelligence; Artificial neural network; Generalization error; Autoencoder; Stability (learning theory); Norm (philosophy); Machine learning; Encoder; Supervised learning; Unsupervised learning; Pattern recognition (psychology); Mathematics","authors":[{"name":"Lei Le","is_ca":false},{"name":"Andrew Patterson","is_ca":false},{"name":"Martha White","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01489808404131836,"gpt":0.2156842708056817,"spread":0.2007861867643633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003882586,0.001329236,0.001107684,0.0005570212,0.0004539295,0.0008601902,0.001566942,0.001541939,0.001251854],"category_scores_gemma":[0.0135344,0.0006209784,0.0008222359,0.0004443126,0.001308108,0.002692178,0.002168824,0.002421484,0.0005758459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006619469,"about_ca_system_score_gemma":0.001112203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002159657,"about_ca_topic_score_gemma":0.003012485,"domain_scores_codex":[0.998672,0.0005258484,0.00008164458,0.0003498068,0.0002810847,0.00008965732],"domain_scores_gemma":[0.994091,0.003182151,0.0003987238,0.001624112,0.0005812413,0.0001227482],"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":[0.0002767563,0.0002325178,0.002521786,0.00015544,0.0002225446,0.0001033246,0.000209503,0.7546239,0.01099968,0.02792189,0.003256443,0.1994763],"study_design_scores_gemma":[0.00000831436,0.00004523046,0.000176482,0.000008537185,0.00001027282,0.00002317644,0.000008610152,0.9885198,0.001856703,0.009086769,0.0002500806,0.000005965773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05463598,0.0005080863,0.9411266,0.0003576359,0.00005743167,0.00006697112,0.0000721046,0.00112253,0.00205261],"genre_scores_gemma":[0.7093071,0.0005650336,0.2849992,0.0004588916,0.0001380794,0.0001946288,0.0003881475,0.0002860402,0.003662827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003882586,"threshold_uncertainty_score":0.02053332,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753433947","doi":"","title":"A Meta-Learning Perspective on Cold-Start Recommendations for Items","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Cold start (automotive); Deep learning; Artificial intelligence; Machine learning; Artificial neural network; Matrix decomposition; Classifier (UML); Perspective (graphical); Recommender system; Architecture","authors":[{"name":"Manasi Vartak","is_ca":false},{"name":"Arvind Thiagarajan","is_ca":false},{"name":"Conrado Silva Miranda","is_ca":false},{"name":"Jeshua Bratman","is_ca":false},{"name":"Hugo Larochelle","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1200030889267499,"gpt":0.3450282478510309,"spread":0.225025158924281,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006196862,0.002122523,0.003431622,0.002386228,0.001184054,0.002361732,0.004826081,0.003588704,0.002547626],"category_scores_gemma":[0.01637796,0.00147607,0.001799912,0.002733382,0.001780221,0.006689181,0.001733702,0.004738626,0.0008921368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00199741,"about_ca_system_score_gemma":0.001789211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008709659,"about_ca_topic_score_gemma":0.0151717,"domain_scores_codex":[0.996885,0.001187373,0.0002173065,0.0009457215,0.0005251573,0.0002393483],"domain_scores_gemma":[0.9877351,0.007505843,0.0008612297,0.001967674,0.001615252,0.0003149108],"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":[0.0005313231,0.0005512955,0.006912016,0.0006733871,0.001019319,0.0003177444,0.000805709,0.6564293,0.006117711,0.06497921,0.01010613,0.2515568],"study_design_scores_gemma":[0.00002683665,0.0001124034,0.0004009573,0.0000532304,0.00007780536,0.00008928888,0.00003307206,0.9677948,0.001351102,0.02823249,0.001793873,0.00003419235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01363865,0.002200313,0.9804996,0.001190631,0.0001125167,0.00007318397,0.0001871195,0.0004413205,0.001656665],"genre_scores_gemma":[0.62069,0.001901733,0.3667084,0.001011816,0.0007970363,0.0003477303,0.0008075146,0.0001761054,0.007559615],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008709659,"threshold_uncertainty_score":0.03277248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096879261","doi":"","title":"Measures of Clustering Quality: A Working Set of Axioms for Clustering","year":2008,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":141,"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":"Cluster analysis; Axiom; Impossibility; Constrained clustering; Computer science; Correlation clustering; Theoretical computer science; Fuzzy clustering; Data mining; Mathematics; Set (abstract data type); CURE data clustering algorithm; Artificial intelligence","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Margareta Ackerman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1776089612055428,"gpt":0.3598316936246269,"spread":0.182222732419084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02813102,0.001914843,0.002549851,0.008247268,0.003566847,0.009385272,0.007253961,0.005496571,0.002826716],"category_scores_gemma":[0.0516832,0.001360351,0.003657168,0.008383105,0.01772659,0.01819721,0.005802618,0.00820783,0.001111885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004895412,"about_ca_system_score_gemma":0.003450758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243713,"about_ca_topic_score_gemma":0.001323467,"domain_scores_codex":[0.9734018,0.009433039,0.003766489,0.004429996,0.008156549,0.0008121577],"domain_scores_gemma":[0.9396952,0.03007066,0.006609267,0.01223302,0.01009488,0.00129703],"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":[0.00002268387,0.00002909058,0.0008153968,0.0002726815,0.00005407136,0.00003668056,0.0003048441,0.007677815,0.0005794693,0.9724894,0.001541748,0.01617609],"study_design_scores_gemma":[0.00002122353,0.00006400797,0.0005191172,0.0001366716,0.00004051674,0.0001569815,0.0001379918,0.03699968,0.001149011,0.9529071,0.007808596,0.00005904941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003741741,0.0006511424,0.9909189,0.001618608,0.00009125115,0.0001038731,0.000229441,0.0001943502,0.002450815],"genre_scores_gemma":[0.0880386,0.0008861738,0.9074914,0.000851861,0.0003902321,0.0007049525,0.0006577589,0.0001321829,0.0008468429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02813102,"threshold_uncertainty_score":0.1487728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123094878","doi":"","title":"Tree-Structured Stick Breaking for Hierarchical Data","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":137,"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":"Computer science; Markov chain Monte Carlo; Hierarchical database model; Tree structure; Cluster analysis; Tree (set theory); Hierarchical clustering; Bayesian inference; Data mining; Algorithm; Bayesian probability; Theoretical computer science; Mathematics; Artificial intelligence; Binary tree","authors":[{"name":"Zoubin Ghahramani","is_ca":false},{"name":"Michael I. Jordan","is_ca":false},{"name":"Ryan P. Adams","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03733069654240435,"gpt":0.3100610288616286,"spread":0.2727303323192243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012914,0.0009441898,0.002173456,0.003146392,0.001987772,0.003459211,0.004555115,0.003922956,0.00472006],"category_scores_gemma":[0.06182085,0.002076347,0.003143184,0.003826822,0.005090377,0.01046882,0.004189073,0.007394872,0.001039495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003295386,"about_ca_system_score_gemma":0.001946051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009372181,"about_ca_topic_score_gemma":0.009197035,"domain_scores_codex":[0.9939315,0.002285146,0.0004198386,0.001691001,0.001325306,0.0003472839],"domain_scores_gemma":[0.9562507,0.02936709,0.003816841,0.00804866,0.001503912,0.001012796],"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":[0.0001154296,0.00006081293,0.003819789,0.0001972046,0.0001270911,0.000308021,0.0006491812,0.2140475,0.001764753,0.7357679,0.002242276,0.04090016],"study_design_scores_gemma":[0.00001675564,0.00002065211,0.0005375519,0.00003125647,0.00001726013,0.00007174601,0.00002767989,0.6515962,0.0003665053,0.3460554,0.001232691,0.00002632771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005832843,0.0001917337,0.9930058,0.0002194026,0.00001974826,0.00003288411,0.0001580013,0.000196914,0.0003427036],"genre_scores_gemma":[0.3817028,0.001111762,0.6101058,0.0005781553,0.0002572617,0.0005234049,0.001610678,0.0003210714,0.003789183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.012914,"threshold_uncertainty_score":0.06829661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167205245","doi":"","title":"Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors","year":2011,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":133,"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":"Proportional hazards model; Regression; Survival analysis; Regression analysis; Cancer; Statistics; Medicine; Population; Computer science; Machine learning; Oncology; Artificial intelligence; Internal medicine; Mathematics","authors":[{"name":"Hsiu-Chin Lin","is_ca":true},{"name":"Vickie E. Baracos","is_ca":true},{"name":"Russell Greiner","is_ca":true},{"name":"Chun-Nam Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07457355463783148,"gpt":0.3042221427879242,"spread":0.2296485881500927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003113957,0.0006514517,0.0008363222,0.000876344,0.0001641471,0.0006904395,0.0008721914,0.0009530091,0.001432535],"category_scores_gemma":[0.009727355,0.0003754211,0.0008012051,0.0007829951,0.0005489042,0.001274076,0.0004229304,0.002417129,0.0007372838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009006063,"about_ca_system_score_gemma":0.0008759141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004643267,"about_ca_topic_score_gemma":0.005452139,"domain_scores_codex":[0.9992784,0.0003168729,0.00003654122,0.0002262486,0.00008943763,0.00005246702],"domain_scores_gemma":[0.9937159,0.00491037,0.0004802226,0.0003731016,0.0003942091,0.0001260866],"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":[0.0002774368,0.0002481891,0.03936045,0.00007103767,0.0001457013,0.0001552259,0.0001412745,0.862448,0.001779112,0.006475145,0.001801152,0.08709726],"study_design_scores_gemma":[0.00001103228,0.00005164156,0.003150826,0.000008481583,0.00001897325,0.00003095722,0.00001167026,0.9903393,0.0005943556,0.005491979,0.0002785239,0.00001223208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2201108,0.0003587508,0.7756878,0.0009742408,0.00004917712,0.00007617175,0.001204522,0.0008230967,0.000715436],"genre_scores_gemma":[0.9303438,0.0004980616,0.06361961,0.0002337713,0.00008849236,0.0001957818,0.001753103,0.00006862586,0.003198639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004643267,"threshold_uncertainty_score":0.01646835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138448681","doi":"","title":"Learning Sparse Topographic Representations with Products of Student-t Distributions","year":2002,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":129,"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":"Iterated function; Computer science; Filter (signal processing); Artificial intelligence; Pattern recognition (psychology); Product (mathematics); Wiener filter; Orientation (vector space); Algorithm; Computer vision; Mathematics","authors":[{"name":"Max Welling","is_ca":true},{"name":"Simon Osindero","is_ca":false},{"name":"Geoffrey E. Hinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03812047916899464,"gpt":0.2898028860270126,"spread":0.251682406858018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001582332,0.0004057836,0.0006692153,0.0006286665,0.0002888118,0.001101724,0.001233391,0.001198232,0.001714361],"category_scores_gemma":[0.008597187,0.0005655424,0.0008276283,0.0008157025,0.001049635,0.003079217,0.00108659,0.00143431,0.0004719165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005058588,"about_ca_system_score_gemma":0.0005729011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001195596,"about_ca_topic_score_gemma":0.001517717,"domain_scores_codex":[0.9994767,0.0001894616,0.00002533658,0.0001306288,0.0001334038,0.0000443834],"domain_scores_gemma":[0.99749,0.001407193,0.0003502537,0.000337477,0.0003239878,0.00009094469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001421652,0.00006371064,0.0017574,0.00008265562,0.00007154243,0.000170869,0.0002077974,0.7723244,0.005136193,0.1221327,0.00141328,0.09649727],"study_design_scores_gemma":[0.000005621746,0.00001655885,0.0000892597,0.00000217759,0.000003265927,0.00003293253,0.000005722291,0.9634411,0.0006212732,0.03558001,0.0001965296,0.000005569747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01638658,0.00003797245,0.9829385,0.00009733099,0.000006955902,0.00001214035,0.00002267341,0.0001315203,0.000366346],"genre_scores_gemma":[0.6457516,0.000353672,0.3493744,0.0001919906,0.00008559967,0.0001658119,0.0002476991,0.0001288192,0.00370037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001714361,"threshold_uncertainty_score":0.008368313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163097311","doi":"","title":"Proximity Graphs for Clustering and Manifold Learning","year":2004,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":120,"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":"Cluster analysis; Lattice graph; Dimensionality reduction; Computer science; Line graph; Mathematics; Graph; Pattern recognition (psychology); Voltage graph; Theoretical computer science; Artificial intelligence","authors":[{"name":"Richard S. Zemel","is_ca":true},{"name":"Miguel Á. Carreira-Perpiñán","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02268826032061569,"gpt":0.2818249507256548,"spread":0.2591366904050392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739079,0.001482463,0.001724175,0.004793873,0.001432387,0.00254424,0.002152406,0.002227537,0.006908115],"category_scores_gemma":[0.01028299,0.0006651608,0.00151673,0.006542258,0.002750549,0.004406353,0.003418194,0.003401941,0.003370516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001790984,"about_ca_system_score_gemma":0.0008452652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003361639,"about_ca_topic_score_gemma":0.002466742,"domain_scores_codex":[0.997566,0.001100298,0.0001153402,0.000594673,0.0005298595,0.00009381171],"domain_scores_gemma":[0.9962965,0.001942961,0.0003947627,0.0007670574,0.0004853928,0.0001133578],"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":[0.00003696386,0.0000270325,0.0003855949,0.0003673674,0.00008100349,0.0001231954,0.0002504989,0.05199132,0.0007312233,0.8337422,0.01369481,0.09856872],"study_design_scores_gemma":[0.000008880733,0.00001506217,0.000225693,0.00005404506,0.00001509022,0.0001292093,0.00006400668,0.08582034,0.000333235,0.879816,0.03349651,0.00002199772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002691486,0.005706999,0.9813973,0.001258717,0.0002403929,0.00009105352,0.0006579313,0.0008136816,0.007142448],"genre_scores_gemma":[0.165273,0.01162367,0.8044259,0.001083295,0.001437319,0.0009134352,0.003709492,0.000789062,0.01074476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006908115,"threshold_uncertainty_score":0.02310997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098617596","doi":"","title":"Multi-Prediction Deep Boltzmann Machines","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":116,"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":"Boltzmann machine; dBm; Restricted Boltzmann machine; Computer science; Train; Artificial intelligence; Inference; Probabilistic logic; Machine learning; Field (mathematics); Deep learning; Layer (electronics); Algorithm; Mathematics","authors":[{"name":"Ian Goodfellow","is_ca":true},{"name":"Mehdi Mirza","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01458786385312518,"gpt":0.2242547036663998,"spread":0.2096668398132746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008548553,0.0008574966,0.001022964,0.0003924999,0.0003147535,0.001304889,0.002535515,0.001523436,0.005900694],"category_scores_gemma":[0.003462315,0.000594949,0.0007508397,0.0007179138,0.0008091732,0.002499249,0.001959198,0.002610294,0.001958364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007911952,"about_ca_system_score_gemma":0.0007481053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001895817,"about_ca_topic_score_gemma":0.002944956,"domain_scores_codex":[0.9994586,0.000157622,0.00002800436,0.0001430542,0.0001366579,0.00007609413],"domain_scores_gemma":[0.9992862,0.0003470073,0.00005138863,0.0001410723,0.0001186164,0.00005570501],"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":[0.00007915122,0.00006294197,0.000943644,0.0001067479,0.00008023391,0.00007927239,0.00005684197,0.7655347,0.002858427,0.1194893,0.00548503,0.1052238],"study_design_scores_gemma":[0.000003110945,0.000007539125,0.00003699301,0.000006385376,0.000003600983,0.00001520437,0.000002147733,0.968969,0.0004626957,0.02923878,0.001249505,0.000005007444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004108158,0.0006049104,0.9912657,0.0004041138,0.0001124034,0.00002516932,0.0001662386,0.0008216646,0.002491619],"genre_scores_gemma":[0.4627555,0.001418695,0.5180477,0.0007490594,0.000241616,0.0002743793,0.001010488,0.0005590029,0.01494353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005900694,"threshold_uncertainty_score":0.01973975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970641149","doi":"","title":"Residual Flows for Invertible Generative Modeling","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":109,"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":"Invertible matrix; Residual; Lipschitz continuity; Discriminative model; Transformation (genetics); Computer science; Mathematics; Algorithm; Generative model; Artificial neural network; Density estimation; Applied mathematics; Mathematical optimization; Generative grammar; Artificial intelligence; Statistics; Estimator; Pure mathematics","authors":[{"name":"Ricky T. Q. Chen","is_ca":true},{"name":"Jens Behrmann","is_ca":false},{"name":"David Duvenaud","is_ca":true},{"name":"Joern-Henrik Jacobsen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02398896971344965,"gpt":0.2394272595567821,"spread":0.2154382898433325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016921,0.0009239677,0.0005027968,0.0006278319,0.0003183608,0.0007984932,0.001080502,0.0009322083,0.00625964],"category_scores_gemma":[0.004220012,0.000481652,0.0007726405,0.0004450699,0.001292006,0.00155851,0.001646409,0.001969204,0.001273288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006978678,"about_ca_system_score_gemma":0.0007615968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002121809,"about_ca_topic_score_gemma":0.002756505,"domain_scores_codex":[0.9996305,0.0001223086,0.00001840667,0.00009800078,0.00009621806,0.00003468528],"domain_scores_gemma":[0.998973,0.0006699061,0.00008404544,0.0001601525,0.0000809496,0.00003194721],"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":[0.00005913954,0.00003487523,0.000351858,0.00009556126,0.00003230945,0.00008438152,0.0001251444,0.6761876,0.007024287,0.2206327,0.001857278,0.09351496],"study_design_scores_gemma":[0.000003613492,0.00001280068,0.00003524086,0.00000994842,0.000005022715,0.00002569501,0.000004863412,0.9475002,0.001407042,0.04917727,0.001812619,0.000005621399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003127699,0.0001017034,0.9941794,0.00008803472,0.00001529073,0.00001913183,0.00005795546,0.0003457121,0.002065124],"genre_scores_gemma":[0.4842017,0.0007252274,0.5004604,0.0003917788,0.0001152497,0.0003247683,0.0006510193,0.000645058,0.0124848],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00625964,"threshold_uncertainty_score":0.0209406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125113755","doi":"","title":"A Better Way to Pretrain Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":106,"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":"MNIST database; Boltzmann machine; Computer science; Restricted Boltzmann machine; Artificial intelligence; Deep belief network; Deep learning; Layer (electronics); Boltzmann constant; Generative grammar; Generative model; Pattern recognition (psychology); Machine learning; Algorithm","authors":[{"name":"Geoffrey E. Hinton","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0145427736631149,"gpt":0.2387916199599926,"spread":0.2242488462968777,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001393595,0.001314857,0.001252665,0.0005911745,0.000583781,0.001679962,0.002270007,0.002457886,0.009108966],"category_scores_gemma":[0.008306087,0.001152521,0.001003023,0.000878687,0.001027375,0.004190531,0.001626796,0.006718304,0.002348166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000859594,"about_ca_system_score_gemma":0.001078169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002600589,"about_ca_topic_score_gemma":0.004901662,"domain_scores_codex":[0.9990076,0.0002971799,0.00006234398,0.0003225069,0.0002206741,0.00008972998],"domain_scores_gemma":[0.9985445,0.000618198,0.00007748709,0.0004386909,0.0002579779,0.00006320603],"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":[0.0001460074,0.0001787261,0.0008576712,0.0001292157,0.0001650964,0.0001082499,0.0001607724,0.6840776,0.01746992,0.07791934,0.004980077,0.2138074],"study_design_scores_gemma":[0.00002684596,0.00003384878,0.0001166794,0.00002244973,0.00001318286,0.00004843387,0.00001238278,0.9562456,0.008004503,0.03157466,0.003878316,0.00002301681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003087217,0.0001060043,0.9947078,0.00033721,0.00007681258,0.00002283276,0.00003767011,0.0007484208,0.0008759311],"genre_scores_gemma":[0.1482359,0.0002889789,0.8427349,0.0008437572,0.0001319415,0.0002516015,0.0004321087,0.0009381202,0.006142731],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009108966,"threshold_uncertainty_score":0.03047252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970395278","doi":"","title":"Fast AutoAugment","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":104,"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; Generalization; Code (set theory); Matching (statistics); Image (mathematics); Artificial intelligence; Source code; Pattern recognition (psychology); Machine learning; Set (abstract data type)","authors":[{"name":"Sungbin Lim","is_ca":false},{"name":"Ildoo Kim","is_ca":false},{"name":"Taesup Kim","is_ca":true},{"name":"Chiheon Kim","is_ca":false},{"name":"Sungwoong Kim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01182337906363037,"gpt":0.2441420494707218,"spread":0.2323186704070914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001173933,0.001310923,0.001368944,0.001204218,0.0007477073,0.001121425,0.002032854,0.001430989,0.005671062],"category_scores_gemma":[0.006279128,0.0008870554,0.001133073,0.001185764,0.001264271,0.00266336,0.003024309,0.001907987,0.002171637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008611977,"about_ca_system_score_gemma":0.001709841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004783494,"about_ca_topic_score_gemma":0.005793049,"domain_scores_codex":[0.9991991,0.0001756174,0.00005454322,0.000235927,0.0002182921,0.0001165137],"domain_scores_gemma":[0.9982292,0.0007241578,0.0001696526,0.0005663048,0.0002436506,0.00006699862],"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":[0.0004887714,0.0002071379,0.003283427,0.0002172854,0.0001262446,0.0002055048,0.0002785496,0.2152196,0.01845102,0.01578606,0.02194301,0.7237935],"study_design_scores_gemma":[0.00003187617,0.00008584632,0.0002577872,0.00002529861,0.00001687022,0.0001435224,0.00003382765,0.9721654,0.01105871,0.01115784,0.005005264,0.00001780978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0476151,0.0009739094,0.9307452,0.0004649103,0.0001612711,0.0002072611,0.0003897336,0.0151927,0.004249961],"genre_scores_gemma":[0.4429951,0.00043701,0.5472218,0.0007349953,0.00008819535,0.0004681986,0.001406101,0.001544867,0.005103742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005671062,"threshold_uncertainty_score":0.01897156,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963582321","doi":"","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":103,"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":"Regret; Reinforcement learning; Computer science; Bridge (graph theory); State (computer science); Mathematical optimization; Algorithm; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Christoph Dann","is_ca":false},{"name":"Tor Lattimore","is_ca":true},{"name":"Emma Brunskill","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1348757675199226,"gpt":0.4272213443219531,"spread":0.2923455768020305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01294393,0.002299588,0.0024161,0.001442923,0.001011621,0.004188729,0.003220331,0.002530761,0.003264911],"category_scores_gemma":[0.08591015,0.0009516589,0.001255024,0.001388084,0.00545291,0.01021006,0.004247387,0.005985639,0.0004688753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003091693,"about_ca_system_score_gemma":0.002774602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002032767,"about_ca_topic_score_gemma":0.001396243,"domain_scores_codex":[0.9904659,0.003769127,0.0004711986,0.00161483,0.002811109,0.0008678396],"domain_scores_gemma":[0.9264156,0.05962985,0.00407852,0.005861727,0.00291434,0.001099981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002116735,0.0001109223,0.001386446,0.0002055274,0.0001124877,0.00009542967,0.000139257,0.6219187,0.0009638459,0.3346011,0.001608242,0.03864648],"study_design_scores_gemma":[0.00001390119,0.00008531291,0.0003079187,0.00005590195,0.00001972351,0.00004476952,0.00001783077,0.8218678,0.00108898,0.1757448,0.0007338598,0.00001929725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007185695,0.0008937417,0.9867079,0.0004496643,0.00007076332,0.00004638979,0.00006451534,0.0002299015,0.004351404],"genre_scores_gemma":[0.7538124,0.001631089,0.2392943,0.0008435114,0.0005349756,0.0004809819,0.0002589545,0.0004568239,0.00268703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01294393,"threshold_uncertainty_score":0.0684548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970783931","doi":"","title":"Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":95,"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":"Computer science; MNIST database; Recurrent neural network; Backpropagation; Artificial neural network; Algorithm; Artificial intelligence","authors":[{"name":"Aaron R. Voelker","is_ca":true},{"name":"Ivana Kajić","is_ca":true},{"name":"Chris Eliasmith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01482531169994164,"gpt":0.2382913086173716,"spread":0.22346599691743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004789944,0.0005621827,0.0004277494,0.0002773067,0.00020316,0.0009428028,0.002152647,0.0008791165,0.002385772],"category_scores_gemma":[0.001792503,0.0003152003,0.0004024842,0.0004222085,0.0006869366,0.001648699,0.0007536199,0.00109533,0.0007521226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005291462,"about_ca_system_score_gemma":0.0004582629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002562745,"about_ca_topic_score_gemma":0.003405563,"domain_scores_codex":[0.9998162,0.00003586885,0.00001422155,0.00005185795,0.00005114349,0.00003076792],"domain_scores_gemma":[0.9996704,0.0001095037,0.00005061692,0.00008496333,0.00006012175,0.00002433859],"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":[0.0003366657,0.0001511145,0.001870359,0.0002165748,0.0001229104,0.0004056876,0.0002610931,0.4303284,0.07213345,0.1368625,0.005857066,0.3514541],"study_design_scores_gemma":[0.000006205836,0.00003564573,0.00008965586,0.000006633781,0.000008898296,0.00003793025,0.000007848264,0.9817629,0.009156579,0.007366968,0.001510569,0.00001020677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04209001,0.0006017012,0.9511522,0.0002988984,0.0001356048,0.00003298335,0.0001086042,0.002238514,0.003341463],"genre_scores_gemma":[0.737292,0.0005967774,0.2548204,0.0002572479,0.00008961343,0.0001154462,0.0002345962,0.0002266909,0.00636728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002562745,"threshold_uncertainty_score":0.007981181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963313316","doi":"","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":92,"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":"Kronecker delta; Reinforcement learning; Scalability; Computer science; Trust region; Curvature; Mathematical optimization; Artificial intelligence; Theoretical computer science; Mathematics","authors":[{"name":"Yuhuai Wu","is_ca":true},{"name":"Elman Mansimov","is_ca":true},{"name":"Roger Grosse","is_ca":true},{"name":"S. Matthew Liao","is_ca":false},{"name":"Jimmy Ba","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05248858218001681,"gpt":0.315826014867957,"spread":0.2633374326879402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001628899,0.001177549,0.00143103,0.0004756112,0.0003162548,0.000889598,0.001461519,0.001307144,0.003410135],"category_scores_gemma":[0.00479552,0.0005657082,0.0007660139,0.0003927632,0.001125491,0.001361799,0.001221726,0.002232142,0.0009275754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001507571,"about_ca_system_score_gemma":0.001727517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006236748,"about_ca_topic_score_gemma":0.004733259,"domain_scores_codex":[0.9994174,0.0001935007,0.00003163057,0.0001267074,0.0001654074,0.00006543072],"domain_scores_gemma":[0.9985531,0.0007389919,0.0001284989,0.0001646719,0.000319976,0.0000948447],"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":[0.00009053696,0.00003326704,0.0003406002,0.00005352742,0.0000369873,0.00005488846,0.00004447921,0.9456026,0.002122253,0.01207195,0.001358944,0.03818994],"study_design_scores_gemma":[0.000003501562,0.000009075788,0.00001174852,0.00000196218,0.00000154009,0.000004154212,0.000001163436,0.9980832,0.0002339906,0.001488424,0.0001593773,0.000001851574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003209925,0.0001148044,0.9954531,0.00006285336,0.00002441818,0.00001922329,0.00001642285,0.0004716881,0.0006275103],"genre_scores_gemma":[0.6120471,0.0002544567,0.3808682,0.0002122441,0.00006415586,0.0002404913,0.0002084068,0.0005440684,0.005560957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006236748,"threshold_uncertainty_score":0.01240093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560977758","doi":"","title":"Learning Deep Parsimonious Representations","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":90,"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; University of Toronto","funders":"","keywords":"Interpretability; Cluster analysis; Conceptual clustering; Computer science; Artificial intelligence; Categorization; Machine learning; Generalization; Deep learning; Regularization (linguistics); Correlation clustering; Canopy clustering algorithm; Mathematics","authors":[{"name":"Renjie Liao","is_ca":true},{"name":"Alexander G. Schwing","is_ca":false},{"name":"Richard S. Zemel","is_ca":true},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0174282915545141,"gpt":0.2555935385113803,"spread":0.2381652469568663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009781884,0.001172544,0.0009653833,0.0007011771,0.0004331194,0.001093474,0.00177033,0.001685373,0.002168514],"category_scores_gemma":[0.004189286,0.0005603942,0.0007250333,0.0008227144,0.001167264,0.003566892,0.002200895,0.003569293,0.000679724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008893555,"about_ca_system_score_gemma":0.0006797973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001157846,"about_ca_topic_score_gemma":0.002951539,"domain_scores_codex":[0.9994311,0.0001681111,0.00002151824,0.0001993049,0.0001066036,0.00007324876],"domain_scores_gemma":[0.9988074,0.0005649392,0.0001237447,0.0003416342,0.00008808426,0.00007420834],"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":[0.000220045,0.0002333644,0.001727002,0.0002834492,0.0001665869,0.0002855475,0.0003667932,0.564895,0.0238469,0.1280596,0.006059898,0.2738557],"study_design_scores_gemma":[0.000008910661,0.00004644378,0.0001304562,0.00001520136,0.00001269959,0.00004069737,0.0000232723,0.9180493,0.001664284,0.07910993,0.0008909972,0.000007818681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04978753,0.0003044044,0.9469465,0.00049483,0.00003889693,0.00003335889,0.0001631658,0.0005729409,0.001658401],"genre_scores_gemma":[0.7629579,0.0004941889,0.2286166,0.0006550744,0.00009633833,0.0001351603,0.0007656937,0.0002351506,0.006043991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002168514,"threshold_uncertainty_score":0.007254362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119200797","doi":"","title":"An Accelerated Proximal Coordinate Gradient Method","year":2014,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematical optimization; Dual (grammatical number); Convergence (economics); Proximal Gradient Methods; Computer science; Convex optimization; Empirical risk minimization; Minification; Coordinate descent; Gradient method; Regular polygon; Stochastic gradient descent; Rate of convergence; Convex function; Applied mathematics; Mathematics; Artificial intelligence; Artificial neural network; Key (lock); Geometry","authors":[{"name":"Qihang Lin","is_ca":false},{"name":"Zhaosong Lu","is_ca":true},{"name":"Lin Xiao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02352433827712829,"gpt":0.2919534599160039,"spread":0.2684291216388756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001109182,0.001039888,0.001350894,0.0007559778,0.0004914731,0.001038844,0.001625627,0.001379034,0.006317773],"category_scores_gemma":[0.003141656,0.0005533271,0.0007742126,0.0007048079,0.0008674701,0.001114752,0.00176162,0.001784966,0.002578594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005461344,"about_ca_system_score_gemma":0.001892021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002489129,"about_ca_topic_score_gemma":0.002074386,"domain_scores_codex":[0.9991397,0.0002930387,0.00002715278,0.0001319856,0.0003444312,0.00006361179],"domain_scores_gemma":[0.9993516,0.0001993098,0.00004937617,0.00009397102,0.0002510104,0.00005483744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001936236,0.0001018076,0.0006079048,0.0002722,0.00009715436,0.0002207218,0.0001130162,0.6348212,0.01042102,0.142533,0.01733634,0.1932818],"study_design_scores_gemma":[0.00002632701,0.00003127433,0.00005091967,0.00000898933,0.000007785205,0.00004925208,0.000004959302,0.9852772,0.001152633,0.007804255,0.005576481,0.000009795914],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001291839,0.0001116293,0.9966087,0.0001015968,0.00006015408,0.00003241419,0.00002990792,0.0002711948,0.001492505],"genre_scores_gemma":[0.09746633,0.0003926658,0.8923697,0.0002428844,0.0001828807,0.0003531683,0.0002222107,0.0003611423,0.008408979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006317773,"threshold_uncertainty_score":0.02113503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146412174","doi":"","title":"Optimal Bayesian Recommendation Sets and Myopically Optimal Choice Query Sets","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":85,"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":"Computer science; Submodular set function; Query optimization; Mathematical optimization; Set (abstract data type); Multinomial logistic regression; Greedy algorithm; Bayesian probability; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics","authors":[{"name":"Paolo Viappiani","is_ca":true},{"name":"Craig Boutilier","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05953119479209398,"gpt":0.4010226266591596,"spread":0.3414914318670657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01786613,0.001567151,0.003755096,0.001926425,0.001241074,0.003467971,0.003129067,0.003661112,0.006483722],"category_scores_gemma":[0.07282828,0.001531624,0.001635575,0.002804098,0.00307438,0.007548738,0.003988513,0.003626079,0.001063686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003816084,"about_ca_system_score_gemma":0.002448062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002719689,"about_ca_topic_score_gemma":0.002723962,"domain_scores_codex":[0.9781187,0.01442005,0.000984942,0.002203534,0.003309565,0.0009631806],"domain_scores_gemma":[0.9381009,0.05201623,0.002558867,0.004058634,0.002211311,0.001053967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007112981,0.0003782245,0.00143177,0.0002894708,0.0002095782,0.0001443,0.0004543796,0.6066837,0.001181271,0.3232082,0.003817308,0.06149047],"study_design_scores_gemma":[0.00009438153,0.0001147086,0.0003331934,0.00004136327,0.00002509372,0.00004267514,0.00006852757,0.7912338,0.0007047048,0.2063505,0.0009546475,0.00003643764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05013814,0.0006230703,0.9390168,0.001473228,0.00002608127,0.0003205754,0.0004904186,0.0003388848,0.007572813],"genre_scores_gemma":[0.6596367,0.0006551821,0.3317707,0.0005854169,0.0001005506,0.001123427,0.0008597422,0.0002061283,0.005062092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01786613,"threshold_uncertainty_score":0.0944863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2528091958","doi":"","title":"The pigeon as particle filter","year":2007,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":81,"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":"Particle filter; Bayesian inference; Bayesian probability; Monte Carlo method; Inference; Computer science; Asymptote; Artificial intelligence; Sampling (signal processing); Ensemble learning; Machine learning; Posterior probability; Importance sampling; Filter (signal processing); Algorithm; Statistics; Mathematics; Kalman filter; Computer vision","authors":[{"name":"Nathaniel D. Daw","is_ca":false},{"name":"Aaron Courville","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0118451303110555,"gpt":0.2643726841054829,"spread":0.2525275537944274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140926,0.0003687907,0.000657206,0.0004892859,0.0006846544,0.001699978,0.000771387,0.001481681,0.008261774],"category_scores_gemma":[0.004592928,0.0003460959,0.0006735541,0.0002622658,0.002434385,0.002688451,0.001208862,0.001535658,0.0008663611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003806,"about_ca_system_score_gemma":0.0007126096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00437669,"about_ca_topic_score_gemma":0.002841442,"domain_scores_codex":[0.9994779,0.0001937021,0.00001605863,0.0001535642,0.0001094272,0.00004933003],"domain_scores_gemma":[0.9984397,0.0008685214,0.00009563507,0.0003366716,0.000141827,0.0001176178],"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":[0.0001176071,0.00003325737,0.001206093,0.00006850389,0.00008456939,0.0001180813,0.0001682198,0.04133698,0.002616484,0.9282944,0.006321383,0.01963444],"study_design_scores_gemma":[0.00004948051,0.00007787369,0.001045704,0.00003653722,0.0000301271,0.0001498296,0.00003655085,0.2980201,0.0009393436,0.6845153,0.01505876,0.00004051598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.066659,0.001906628,0.8304543,0.01161053,0.001311168,0.00009267611,0.0004258773,0.00153921,0.08600063],"genre_scores_gemma":[0.8364916,0.0008617697,0.1298685,0.001785643,0.0003309281,0.0001316258,0.0001759046,0.0001966041,0.03015734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008261774,"threshold_uncertainty_score":0.02763838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133552775","doi":"","title":"Learning from Limited Demonstrations","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Task (project management); Key (lock); Path (computing); Artificial intelligence; Machine learning; Mathematical optimization; Temporal difference learning; Mathematics","authors":[{"name":"Beomjoon Kim","is_ca":true},{"name":"Amir massoud Farahmand","is_ca":true},{"name":"Joëlle Pineau","is_ca":true},{"name":"Doina Precup","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01983794697850236,"gpt":0.2250760590633588,"spread":0.2052381120848564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002062479,0.0007929308,0.001347381,0.0005296243,0.0003809226,0.0009137292,0.001989214,0.001344207,0.002846328],"category_scores_gemma":[0.0151894,0.0008444638,0.0004761583,0.0004302526,0.00123449,0.002434259,0.002187565,0.001866285,0.0006318325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007423583,"about_ca_system_score_gemma":0.001444054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002491084,"about_ca_topic_score_gemma":0.002838331,"domain_scores_codex":[0.9988212,0.0004620682,0.00006321898,0.0002903489,0.0002743413,0.00008883359],"domain_scores_gemma":[0.9929302,0.004766246,0.0005714397,0.0008310479,0.0006179285,0.0002831974],"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":[0.0001764435,0.00007799525,0.001228516,0.0001357615,0.00004777823,0.0001108524,0.000115978,0.8797263,0.002370472,0.01530744,0.001412993,0.09928946],"study_design_scores_gemma":[0.00001400782,0.0000294227,0.00007562981,0.000008254283,0.000003087372,0.00001567558,0.000005449664,0.9926934,0.0005388372,0.00632985,0.0002811763,0.000005074377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02522689,0.0002013663,0.9721025,0.0002009107,0.00002147098,0.00004115995,0.00006336283,0.0006312011,0.001511161],"genre_scores_gemma":[0.7503097,0.000171668,0.246101,0.0001986033,0.00003952067,0.0002323111,0.000287163,0.0001194312,0.002540654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002846328,"threshold_uncertainty_score":0.01090759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162572398","doi":"","title":"Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings","year":2014,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Electroencephalography; Rhythm; Convolutional neural network; Pattern recognition (psychology); Computer science; Perception; Sensorimotor rhythm; Artificial intelligence; Speech recognition; Representation (politics); Psychology; Neuroscience; Brain–computer interface; Medicine","authors":[{"name":"Sebastian Stober","is_ca":true},{"name":"Daniel J. Cameron","is_ca":true},{"name":"Jessica A. Grahn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03641998959871662,"gpt":0.2740508930075762,"spread":0.2376309034088596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000428147,0.0005411549,0.0001688687,0.000342098,0.0001438142,0.0004731597,0.0002730823,0.0003347142,0.0006905546],"category_scores_gemma":[0.001685295,0.0001883761,0.0002285572,0.0002956768,0.0001676526,0.0004012773,0.000366216,0.0003854844,0.0003025237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003568868,"about_ca_system_score_gemma":0.0002978014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005702781,"about_ca_topic_score_gemma":0.009170255,"domain_scores_codex":[0.9998529,0.00002293872,0.000007588173,0.00004344005,0.00002897487,0.000044088],"domain_scores_gemma":[0.9997012,0.0001522675,0.00004297779,0.0000272398,0.00006228691,0.00001395834],"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":[0.0009742749,0.0004653911,0.04894728,0.0001982718,0.0003083655,0.0004384329,0.0002721135,0.1376119,0.2288328,0.001072175,0.002194769,0.5786843],"study_design_scores_gemma":[0.000015846,0.0002222498,0.04248447,0.00002832337,0.00007616974,0.0001328217,0.0001141449,0.8985764,0.05648528,0.0009147058,0.0009260225,0.00002346904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9092472,0.0002904558,0.08729548,0.0001688753,0.000072476,0.00005570001,0.0002928473,0.0005037135,0.002073148],"genre_scores_gemma":[0.9710423,0.0001780321,0.02697607,0.00003562343,0.00001367551,0.00002542522,0.0005331452,0.00001453317,0.001181225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005702781,"threshold_uncertainty_score":0.01133919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2553718801","doi":"","title":"Proximal Deep Structured Models","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":68,"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":"Computer science; ENCODE; Inference; Artificial intelligence; Image (mathematics); Deep learning; Artificial neural network; Noise reduction; Algorithm; Optical flow; Recurrent neural network; Pattern recognition (psychology)","authors":[{"name":"Shenlong Wang","is_ca":true},{"name":"Sanja Fidler","is_ca":true},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01742967120494543,"gpt":0.2527295355181506,"spread":0.2352998643132052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011659,0.0009754717,0.001189024,0.0005544879,0.0003014444,0.0009847014,0.001743769,0.0019829,0.003876013],"category_scores_gemma":[0.003729645,0.000747553,0.0008290325,0.0005847249,0.001328343,0.002348286,0.001805453,0.002606472,0.001000587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000841632,"about_ca_system_score_gemma":0.001052733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002267306,"about_ca_topic_score_gemma":0.003596968,"domain_scores_codex":[0.9995485,0.0001516208,0.00001596717,0.0001141652,0.0001154383,0.00005421953],"domain_scores_gemma":[0.9988832,0.0006323002,0.0001068374,0.0001491053,0.0001565488,0.00007199077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006810721,0.0000409447,0.0003383664,0.00008684566,0.0000515577,0.000065,0.00005704109,0.8261307,0.001631478,0.1361807,0.002245429,0.03310376],"study_design_scores_gemma":[0.00000448011,0.00001280071,0.00002619224,0.00000413254,0.000003523192,0.000007702693,0.000002455408,0.9662722,0.0001814864,0.03316142,0.0003203507,0.000003190049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004761373,0.0001736907,0.9936736,0.000167287,0.00002399544,0.00001319584,0.00007265406,0.0002042345,0.0009100641],"genre_scores_gemma":[0.6500562,0.001170661,0.3236466,0.0005790457,0.0002249717,0.0002973251,0.0009361312,0.0002507128,0.02283824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003876013,"threshold_uncertainty_score":0.01296651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970673985","doi":"","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":67,"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":"Reinforcement learning; Observable; Computer science; Set (abstract data type); Artificial intelligence; Task (project management); Function (biology); Optimization problem; Learning automata; Representation (politics); Decomposition; Automaton; Mathematical optimization; Mathematics; Algorithm","authors":[{"name":"Rodrigo Toro Icarte","is_ca":true},{"name":"Ethan Waldie","is_ca":false},{"name":"Toryn Q. Klassen","is_ca":true},{"name":"Richard Valenzano","is_ca":true},{"name":"Margarita P. Castro","is_ca":true},{"name":"Sheila A. McIlraith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02100086568913788,"gpt":0.2534669585508525,"spread":0.2324660928617146,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001945371,0.001081251,0.001263947,0.0004566692,0.0003914511,0.001193305,0.001308674,0.001370868,0.00357953],"category_scores_gemma":[0.009478923,0.0004866762,0.0006492151,0.0004970412,0.001473311,0.001651616,0.001168062,0.003176733,0.0006099307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200085,"about_ca_system_score_gemma":0.001264338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00144634,"about_ca_topic_score_gemma":0.001833881,"domain_scores_codex":[0.9988599,0.0005788087,0.00006771642,0.0002061294,0.0002050577,0.00008234437],"domain_scores_gemma":[0.995553,0.003353719,0.0002802691,0.0003624918,0.0003376862,0.0001128223],"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":[0.0000614399,0.00005809307,0.000379242,0.0001071988,0.0000361774,0.00004471012,0.00005370625,0.8422977,0.0007142099,0.1111339,0.001594227,0.04351942],"study_design_scores_gemma":[0.00001018239,0.00001230127,0.0000243857,0.000006967145,0.000002794348,0.000004916034,0.000002649256,0.9647503,0.000185866,0.03450331,0.0004927926,0.000003500462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003930284,0.000240439,0.9934905,0.0002404115,0.00003601919,0.00004475241,0.0000463026,0.0005224401,0.001448881],"genre_scores_gemma":[0.569917,0.0005914341,0.4243037,0.000365898,0.0001457614,0.0008673118,0.0002886441,0.000220695,0.0032997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00357953,"threshold_uncertainty_score":0.01197469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168345951","doi":"","title":"Slow, Decorrelated Features for Pretraining Complex Cell-like Networks","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":64,"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":"MNIST database; Computer science; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Layer (electronics); Algorithm; Function (biology); Word error rate","authors":[{"name":"Yoshua Bengio","is_ca":true},{"name":"James Bergstra","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02911092442670316,"gpt":0.2613746542383049,"spread":0.2322637298116018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007326883,0.0008325998,0.0005810158,0.000481072,0.0002733409,0.0004649739,0.001260906,0.0007431733,0.002775447],"category_scores_gemma":[0.004248275,0.0005877208,0.000427953,0.0005144224,0.0004373423,0.001113285,0.000819811,0.001473583,0.0008384555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005177191,"about_ca_system_score_gemma":0.0005741094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001569855,"about_ca_topic_score_gemma":0.004578052,"domain_scores_codex":[0.9997366,0.00004434002,0.00001721752,0.00006895343,0.0001003715,0.00003260517],"domain_scores_gemma":[0.9990067,0.0004814486,0.0001140963,0.0001689868,0.0001915633,0.00003719216],"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":[0.0001867544,0.0002004542,0.001512823,0.0001481352,0.00007211226,0.0001546572,0.00009071789,0.4913922,0.05242856,0.01628768,0.003619934,0.4339059],"study_design_scores_gemma":[0.0000139661,0.00004645819,0.0003566024,0.000007100236,0.000007229506,0.00003360617,0.00000382826,0.9841281,0.0106145,0.003755114,0.001024379,0.000009139719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0183473,0.0001157059,0.97966,0.00008677194,0.00002897736,0.00004417867,0.00005276881,0.0008679173,0.0007963552],"genre_scores_gemma":[0.3243618,0.0001635758,0.6720125,0.0001302891,0.00005530238,0.0002974994,0.0002939678,0.0003492296,0.002335745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002775447,"threshold_uncertainty_score":0.009284854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121331909","doi":"","title":"Generating more realistic images using gated MRF's","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":63,"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":"Artificial intelligence; Computer science; Inpainting; Pixel; Probabilistic logic; Pattern recognition (psychology); Set (abstract data type); Statistical model; Latent variable; Image (mathematics); Computer vision; Generative model; Image resolution; Generative grammar","authors":[{"name":"Marc’Aurelio Ranzato","is_ca":true},{"name":"Volodymyr Mnih","is_ca":true},{"name":"Geoffrey E. Hinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01859920218874686,"gpt":0.2607507749789137,"spread":0.2421515727901669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009216483,0.0006898436,0.0006433934,0.0003833263,0.0001575394,0.0006567824,0.0008013109,0.001009681,0.002031516],"category_scores_gemma":[0.002856978,0.000445554,0.0008369571,0.0002619202,0.0007569841,0.00107303,0.0006579589,0.001335274,0.0003925766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005475772,"about_ca_system_score_gemma":0.0003517897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001226236,"about_ca_topic_score_gemma":0.001424017,"domain_scores_codex":[0.9997715,0.0000693524,0.000009524953,0.00006206839,0.0000540605,0.0000333595],"domain_scores_gemma":[0.9991214,0.0004896593,0.00008470137,0.000199969,0.00005580965,0.0000484136],"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":[0.00008999759,0.00006007484,0.0004858603,0.0000606734,0.00003852541,0.0001547303,0.00006516399,0.9313452,0.02653379,0.0129166,0.0006875188,0.02756179],"study_design_scores_gemma":[0.000006839492,0.00002303394,0.0001210473,0.000004810945,0.000004311253,0.00005471179,0.000004305657,0.9924076,0.003611068,0.003496622,0.0002592916,0.000006484375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07893443,0.0001294822,0.9181778,0.0002799084,0.00004623452,0.00005633814,0.00009769067,0.0006920029,0.001586165],"genre_scores_gemma":[0.7445877,0.0001866849,0.2525886,0.0003078707,0.00003670208,0.00009328208,0.000264125,0.0002340623,0.001701038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002031516,"threshold_uncertainty_score":0.006796062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138972044","doi":"","title":"Better Approximation and Faster Algorithm Using the Proximal Average","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":57,"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":"Smoothing; Lasso (programming language); Overhead (engineering); Regular polygon; Algorithm; Computer science; Convex function; Approximation algorithm; Graph; Point (geometry); Proximal Gradient Methods; Mathematical optimization; Smoothness; Mathematics; Theoretical computer science; Geometry","authors":[{"name":"Yaoliang Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01477766485631066,"gpt":0.2135759926542853,"spread":0.1987983277979747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001651539,0.001019584,0.001531257,0.0007994099,0.0004996395,0.001198782,0.001168056,0.001561886,0.004112727],"category_scores_gemma":[0.005426655,0.0004502156,0.0009155117,0.001014722,0.0008251329,0.001830611,0.001895143,0.002572386,0.001705423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005367471,"about_ca_system_score_gemma":0.001403754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00324018,"about_ca_topic_score_gemma":0.002536267,"domain_scores_codex":[0.9989981,0.0002824784,0.00005024292,0.0001920806,0.0003837345,0.00009339343],"domain_scores_gemma":[0.9987093,0.0006146813,0.0000843288,0.0002627682,0.0002483755,0.00008057875],"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":[0.0003143923,0.0001406928,0.000892831,0.0002988911,0.0001153534,0.0002143287,0.0003483506,0.5956946,0.01880104,0.09875827,0.009353822,0.2750674],"study_design_scores_gemma":[0.00001910076,0.00003541426,0.00009358246,0.000009396043,0.000008926938,0.00005862808,0.00001642653,0.9846713,0.00182729,0.01118525,0.002062934,0.00001164078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002597537,0.0001187012,0.9961444,0.000114398,0.00004397028,0.00001706781,0.00001447215,0.0003055177,0.0006439768],"genre_scores_gemma":[0.1359801,0.0004013128,0.8586719,0.0002345331,0.0001915734,0.0001636734,0.0001861821,0.0002878216,0.003882801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004112727,"threshold_uncertainty_score":0.01375842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159008857","doi":"","title":"Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"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":"octopus (software); Gaussian process; Robotic arm; Reinforcement learning; Temporal difference learning; Computer science; Artificial intelligence; Process (computing); Domain (mathematical analysis); Bayesian optimization; Bayesian probability; State space; Trajectory; Machine learning; Computer vision; Gaussian; Mathematics","authors":[{"name":"Yaakov Engel","is_ca":true},{"name":"Peter Szabo","is_ca":false},{"name":"Dmitry Volkinshtein","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02016052612471637,"gpt":0.3137583755310238,"spread":0.2935978494063075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001248341,0.000428539,0.0005653368,0.0002421652,0.0002756261,0.0005227871,0.0005831323,0.0007515373,0.0009799373],"category_scores_gemma":[0.002968915,0.0002858739,0.0003760848,0.0002330721,0.0007122848,0.0004964898,0.0006865066,0.0009550925,0.0001240978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007421789,"about_ca_system_score_gemma":0.0009401019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008213351,"about_ca_topic_score_gemma":0.004601019,"domain_scores_codex":[0.9997544,0.00008929439,0.00001521902,0.00004316212,0.00006688849,0.00003105334],"domain_scores_gemma":[0.9987156,0.0009008456,0.0001332468,0.00004799545,0.0001512262,0.00005109732],"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":[0.00005754593,0.00003420778,0.0002554324,0.00002106418,0.00001626607,0.00002365763,0.00004016124,0.9739476,0.001106539,0.005065539,0.0002019837,0.01922991],"study_design_scores_gemma":[0.000004828745,0.000009906638,0.00001553211,8.678791e-7,0.00000109676,0.000001544579,8.879275e-7,0.9991431,0.0001373734,0.000635331,0.00004822995,0.000001282505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04019265,0.0001199111,0.9576647,0.0002162679,0.00003013316,0.00003405509,0.00001204543,0.0001935997,0.001536557],"genre_scores_gemma":[0.8975414,0.00008964018,0.1000891,0.0001051017,0.0000173276,0.0001030268,0.00002842933,0.00002519619,0.002000662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008213351,"threshold_uncertainty_score":0.01633108,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963779314","doi":"","title":"Satisfying real-world goals with dataset constraints","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Machine learning; Classifier (UML); Real world data; Data mining; Artificial intelligence; Training set; Set (abstract data type); Precision and recall; Data science","authors":[{"name":"Gabriel Goh","is_ca":false},{"name":"Andrew Cotter","is_ca":false},{"name":"Maya R. Gupta","is_ca":false},{"name":"Michael P. Friedlander","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02706035043457996,"gpt":0.2794520838944358,"spread":0.2523917334598558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01571284,0.001955402,0.00177304,0.0009890302,0.001136059,0.00414056,0.002824498,0.003290057,0.002010527],"category_scores_gemma":[0.05903835,0.00081514,0.0008800573,0.002189785,0.001677036,0.00731201,0.003346402,0.004358598,0.0007441555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001997081,"about_ca_system_score_gemma":0.002875018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001640387,"about_ca_topic_score_gemma":0.002661429,"domain_scores_codex":[0.9912409,0.00392525,0.0006775917,0.002013434,0.001597886,0.0005450291],"domain_scores_gemma":[0.9660587,0.02144728,0.002599593,0.005739658,0.003041131,0.001113762],"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":[0.0004415982,0.0006454972,0.01000688,0.0006500715,0.0002089012,0.000343297,0.0004093111,0.800877,0.005411304,0.05511559,0.01530514,0.1105854],"study_design_scores_gemma":[0.00005308184,0.0001817617,0.001854884,0.00007254832,0.00003274931,0.0001898082,0.0001815081,0.9184027,0.004134148,0.07056775,0.004294986,0.00003412658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0913453,0.0006708512,0.8949412,0.005282218,0.0001831445,0.0003818486,0.001335445,0.0007846203,0.005075307],"genre_scores_gemma":[0.5315704,0.0003914083,0.4596518,0.001805151,0.0002635305,0.001049114,0.002174913,0.0004054096,0.002688272],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01571284,"threshold_uncertainty_score":0.08309847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3104591796","doi":"","title":"Principal Neighbourhood Aggregation for Graph Nets","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Exploit; Theoretical computer science; Graph; Neighbourhood (mathematics); News aggregator; Graph isomorphism; Data mining; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Gabriele Corso","is_ca":false},{"name":"Luca Cavalleri","is_ca":false},{"name":"Dominique Beaini","is_ca":true},{"name":"Píetro Lió","is_ca":false},{"name":"Petar Veličković","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02632571881859675,"gpt":0.2520348910568238,"spread":0.225709172238227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001666789,0.0006548688,0.001082473,0.001431694,0.0007600489,0.001473582,0.001106365,0.001031897,0.001891809],"category_scores_gemma":[0.006721843,0.0003862276,0.001189914,0.001223667,0.001537113,0.003474958,0.002051507,0.001803979,0.0003319419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001655195,"about_ca_system_score_gemma":0.0007187072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004403214,"about_ca_topic_score_gemma":0.004598534,"domain_scores_codex":[0.9991717,0.0003070131,0.00004488346,0.000209738,0.0002007792,0.00006582804],"domain_scores_gemma":[0.997171,0.001527653,0.0003082001,0.0005115166,0.0002973957,0.0001841614],"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":[0.00008487032,0.00003539503,0.001167272,0.0001257544,0.00005794236,0.00007062403,0.0001353389,0.6073235,0.001193527,0.3437931,0.002595478,0.04341721],"study_design_scores_gemma":[0.000003951367,0.00001355082,0.0001585953,0.000007420813,0.000006487911,0.00001439531,0.000009067051,0.8201808,0.0002147871,0.1786579,0.0007277129,0.000005359794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04250198,0.000600305,0.9496232,0.0005752531,0.00008410386,0.00004743161,0.0002484509,0.0006840537,0.005635161],"genre_scores_gemma":[0.8135048,0.0008062745,0.1771314,0.0002238438,0.0001947506,0.0001720945,0.0006506376,0.0002742516,0.007041981],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004403214,"threshold_uncertainty_score":0.01200932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099351824","doi":"","title":"Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Computer science; Adaptation (eye); Artificial intelligence; Knowledge management; Machine learning; Psychology","authors":[{"name":"M. Caccia","is_ca":false},{"name":"Pau Rodríguez","is_ca":false},{"name":"Oleksiy Ostapenko","is_ca":false},{"name":"Fabrice Normandin","is_ca":false},{"name":"Min Lin","is_ca":false},{"name":"Lucas Page-Caccia","is_ca":false},{"name":"Issam Laradji","is_ca":false},{"name":"Irina Rish","is_ca":false},{"name":"Alexandre Lacoste","is_ca":false},{"name":"David Vázquez","is_ca":false},{"name":"Laurent Charlin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09874274633483145,"gpt":0.3030612532884616,"spread":0.2043185069536301,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002406667,0.000879532,0.001706076,0.001353866,0.0007203752,0.001447043,0.003538144,0.001578022,0.002560927],"category_scores_gemma":[0.006996414,0.0007355924,0.001127211,0.001536526,0.001839353,0.003936718,0.00410822,0.003178402,0.0004756167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008119347,"about_ca_system_score_gemma":0.00116492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003422109,"about_ca_topic_score_gemma":0.003302556,"domain_scores_codex":[0.9990605,0.0002659416,0.00006476603,0.0003055742,0.0002219247,0.00008141612],"domain_scores_gemma":[0.9964523,0.002229342,0.0002144645,0.0005169641,0.0004076904,0.00017928],"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":[0.0002600156,0.0004049744,0.0014109,0.0003588406,0.0003344952,0.0002189045,0.0003519907,0.3846909,0.004871072,0.1205794,0.004041112,0.4824773],"study_design_scores_gemma":[0.000006541083,0.00003109365,0.0001187146,0.00001094659,0.00001525778,0.00002627037,0.00001026696,0.9538743,0.0005282554,0.04472872,0.0006388621,0.00001080903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005248662,0.0004581224,0.9929066,0.0001706203,0.00007787059,0.00002875623,0.00002347342,0.0002265992,0.0008593986],"genre_scores_gemma":[0.4734519,0.00126183,0.5164025,0.0004225158,0.0005392457,0.0003221122,0.0002207345,0.000247381,0.007131772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003538144,"threshold_uncertainty_score":0.01272786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962705652","doi":"","title":"Stop wasting my gradients: practical SVRG","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Convergence (economics); Variance (accounting); Computation; Generalization; Rate of convergence; Selection (genetic algorithm); Mathematical optimization; Algorithm; Artificial intelligence; Applied mathematics; Mathematics; Channel (broadcasting)","authors":[{"name":"Reza Babanezhad","is_ca":true},{"name":"Mohamed Osama Ahmed","is_ca":true},{"name":"Alim Virani","is_ca":true},{"name":"Mark Schmidt","is_ca":true},{"name":"Jakub Konečný","is_ca":false},{"name":"Scott Sallinen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06114805913386867,"gpt":0.3037481648630557,"spread":0.2426001057291871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002435043,0.001066796,0.001197105,0.0004043201,0.0003374846,0.0007545779,0.001425605,0.001568382,0.003034511],"category_scores_gemma":[0.008626001,0.0005793168,0.0004319262,0.0004322841,0.001063473,0.001278639,0.001058344,0.001749974,0.0009639651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000471142,"about_ca_system_score_gemma":0.0009549641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002547445,"about_ca_topic_score_gemma":0.003399451,"domain_scores_codex":[0.9992125,0.0003559495,0.00003859109,0.0001420346,0.0001801499,0.00007078898],"domain_scores_gemma":[0.9980379,0.001211707,0.0001404345,0.0002428471,0.0003039444,0.0000631718],"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":[0.0002230251,0.0000819075,0.0007971236,0.0001498188,0.00006107706,0.0001906596,0.0001374432,0.792861,0.006773399,0.04079518,0.005463923,0.1524654],"study_design_scores_gemma":[0.000009002326,0.00002331881,0.00004363709,0.000005984913,0.00000293955,0.00001845564,0.000005194509,0.993395,0.0009294191,0.00478014,0.0007822517,0.000004683807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007528479,0.0001861935,0.990319,0.0002439424,0.00003720119,0.00003503454,0.0000211751,0.0004108235,0.001218171],"genre_scores_gemma":[0.3266668,0.0003134601,0.6672269,0.0003530164,0.00007796966,0.0001735196,0.0001656175,0.0003801031,0.004642684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003034511,"threshold_uncertainty_score":0.01287788,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3102998533","doi":"","title":"Information Maximization for Few-Shot Learning","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Shot (pellet); Maximization; Artificial intelligence; Machine learning; Mathematics; Mathematical optimization","authors":[{"name":"Malik Boudiaf","is_ca":false},{"name":"Imtiaz Masud Ziko","is_ca":true},{"name":"Jérôme Rony","is_ca":true},{"name":"José Dolz","is_ca":true},{"name":"Pablo Piantanida","is_ca":false},{"name":"Ismail Ben Ayed","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04073573737786874,"gpt":0.2550705761810338,"spread":0.2143348388031651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005955689,0.001588789,0.004133028,0.001834592,0.0009684713,0.002197137,0.004339493,0.003881476,0.003315923],"category_scores_gemma":[0.024743,0.00145345,0.001447089,0.002222483,0.003018717,0.005562915,0.003070923,0.003917059,0.0009312123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002445382,"about_ca_system_score_gemma":0.001893986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005512504,"about_ca_topic_score_gemma":0.004524612,"domain_scores_codex":[0.9976395,0.001131998,0.0001440203,0.0006052905,0.0003327101,0.0001464429],"domain_scores_gemma":[0.9853888,0.0124127,0.0004381673,0.0007232702,0.0008000185,0.0002370272],"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":[0.0003340284,0.0002950767,0.0009097336,0.000993126,0.0004274723,0.0001579938,0.0002247057,0.6676273,0.002940062,0.1598076,0.009637832,0.1566451],"study_design_scores_gemma":[0.00001051217,0.00002250769,0.000131268,0.0000200732,0.00001532148,0.0000213972,0.000008542135,0.9049987,0.0003839473,0.09396555,0.0004049216,0.00001726655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004331227,0.00160028,0.9924718,0.0004670933,0.00005169115,0.00004444665,0.0001143681,0.0001881669,0.0007308981],"genre_scores_gemma":[0.4929653,0.004519611,0.483533,0.001243939,0.0009664035,0.0008987321,0.001943256,0.0005220859,0.01340759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005955689,"threshold_uncertainty_score":0.031497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141742840","doi":"","title":"The Gaussian Process Density Sampler","year":2008,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":48,"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":"Density estimation; Gaussian process; Markov chain Monte Carlo; Probability density function; Prior probability; Gaussian; Computer science; Hyperparameter; Statistical physics; Mathematics; Bayesian probability; Algorithm; Artificial intelligence; Statistics; Physics","authors":[{"name":"Iain Murray","is_ca":true},{"name":"David Mackay","is_ca":false},{"name":"Ryan P. Adams","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.021284168092133,"gpt":0.2440894353219804,"spread":0.2228052672298474,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004664295,0.000895704,0.001567186,0.001426634,0.000860895,0.002482405,0.003276698,0.002170883,0.00664319],"category_scores_gemma":[0.02304054,0.0009397186,0.001289986,0.001784199,0.001961144,0.003342503,0.002455973,0.003321418,0.002218914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238547,"about_ca_system_score_gemma":0.002799155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006140114,"about_ca_topic_score_gemma":0.006150135,"domain_scores_codex":[0.9981444,0.0009754012,0.00005659218,0.0002903088,0.0004070259,0.0001262609],"domain_scores_gemma":[0.992673,0.00531579,0.000250849,0.0007615113,0.0008108936,0.0001879543],"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":[0.0001265897,0.00008549955,0.002424266,0.000168496,0.0001062998,0.000197866,0.0002139838,0.2704103,0.001208981,0.6190653,0.009649543,0.09634277],"study_design_scores_gemma":[0.00003712834,0.00001427631,0.0001688038,0.00003402208,0.00001982351,0.00008049904,0.0000170861,0.7849464,0.0004254348,0.2096521,0.004584349,0.0000201587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001545136,0.0001634632,0.9966467,0.0001661814,0.00003105886,0.00004179758,0.00009486507,0.0002384132,0.001072399],"genre_scores_gemma":[0.1484465,0.001083913,0.8421769,0.0004920888,0.0002602229,0.0007519784,0.001083005,0.0003980343,0.005307349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00664319,"threshold_uncertainty_score":0.0246675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963344792","doi":"","title":"Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":45,"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":"Diagonal; Kronecker delta; Leverage (statistics); Gradient descent; Computer science; Covariance; Stochastic gradient descent; Algorithm; Mathematics; Mathematical optimization; Artificial intelligence; Artificial neural network; Statistics; Physics; Geometry","authors":[{"name":"Thomas George","is_ca":false},{"name":"César Laurent","is_ca":true},{"name":"Xavier Bouthillier","is_ca":true},{"name":"Nicolas Ballas","is_ca":true},{"name":"Pascal Vincent","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01720553793103738,"gpt":0.2423449592092438,"spread":0.2251394212782065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001235811,0.0009464217,0.001092157,0.0004820971,0.0003843441,0.001172647,0.00097537,0.001268015,0.003689656],"category_scores_gemma":[0.005300466,0.0005737891,0.0005406461,0.0006023757,0.0008748181,0.001747174,0.0009394187,0.001564235,0.001774415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007713774,"about_ca_system_score_gemma":0.001638914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006117841,"about_ca_topic_score_gemma":0.01008113,"domain_scores_codex":[0.9995176,0.0001446242,0.00002917457,0.0001078391,0.000150727,0.00005011033],"domain_scores_gemma":[0.998995,0.0003381471,0.00006615913,0.0002356967,0.0003110487,0.00005383101],"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":[0.0001689771,0.0001089828,0.001104967,0.0001251505,0.0000721544,0.00008883585,0.0001369081,0.7415743,0.007732449,0.06457617,0.009242476,0.1750687],"study_design_scores_gemma":[0.000007561085,0.00001348488,0.00006706859,0.000005544558,0.000002439076,0.00001403598,0.000005658133,0.9910623,0.0004812407,0.007610166,0.0007260356,0.00000447284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006306186,0.00008472524,0.991864,0.00008073637,0.00004021765,0.00002349307,0.00003144857,0.00062038,0.0009488334],"genre_scores_gemma":[0.2293572,0.0001739565,0.7646148,0.0001975409,0.00005083096,0.0001664843,0.0002814615,0.0004138627,0.004743783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006117841,"threshold_uncertainty_score":0.01234311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889576094","doi":"","title":"Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization.","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":43,"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":"Mathematics; Variance reduction; Gradient descent; Combinatorics; Nabla symbol; Stationary point; Function (biology); Stochastic gradient descent; Applied mathematics; Mathematical analysis; Computer science; Physics; Statistics; Omega","authors":[{"name":"Dongruo Zhou","is_ca":false},{"name":"Pan Xu","is_ca":true},{"name":"Quanquan Gu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02298046378812457,"gpt":0.2619998012515888,"spread":0.2390193374634642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001373686,0.001649598,0.001542335,0.0005421338,0.0004383829,0.0009066197,0.001292051,0.001401556,0.001893755],"category_scores_gemma":[0.003731821,0.0007623142,0.001212968,0.0006235393,0.001184697,0.001137239,0.001356108,0.002117727,0.0007528597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207564,"about_ca_system_score_gemma":0.001890871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006597762,"about_ca_topic_score_gemma":0.008562855,"domain_scores_codex":[0.9992462,0.0003190605,0.00003118412,0.0001284372,0.0002058708,0.00006923774],"domain_scores_gemma":[0.9987977,0.0006911412,0.0001222485,0.00008997553,0.000225717,0.0000731613],"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":[0.00004631155,0.00004036,0.0004834513,0.0001517532,0.00007267822,0.00009201048,0.00004288955,0.9478576,0.001494524,0.02357722,0.003161846,0.02297935],"study_design_scores_gemma":[0.000003123154,0.000008384971,0.00002828029,0.000003813294,0.000002059909,0.000006642351,0.000001958264,0.9963439,0.0001274637,0.003110013,0.000362008,0.00000233578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003946965,0.0004103611,0.9937571,0.0002069781,0.00004283264,0.00003170019,0.00003941704,0.0002017182,0.00136282],"genre_scores_gemma":[0.3432059,0.001025295,0.6449481,0.0005405983,0.0001807753,0.0004282949,0.0006559243,0.00050307,0.008512152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006597762,"threshold_uncertainty_score":0.01311868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}