{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007053179,0.0001328927,0.0001466913,0.0002117094,0.0001871869,0.0009865295,0.000412975,0.0000882186,0.000001386368],"category_scores_gemma":[0.00004345785,0.0001097748,0.00003264619,0.0004698396,0.00001394493,0.005152111,0.00005973685,0.0001042796,0.00003551446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009314541,"about_ca_system_score_gemma":0.00004683565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005250415,"about_ca_topic_score_gemma":0.000001856491,"domain_scores_codex":[0.9985628,0.00003218838,0.0006671924,0.0001368752,0.0003500153,0.0002509527],"domain_scores_gemma":[0.9989583,0.00003473028,0.0003946498,0.0002590248,0.0002765818,0.00007671397],"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":[0.00001953026,0.00008102503,0.002829414,0.002665833,0.00002179144,0.000008837572,0.009678922,0.002511855,0.0008562928,0.2996488,0.006875142,0.6748026],"study_design_scores_gemma":[0.0004742012,0.0001575955,0.002509893,0.0002903258,0.000007227478,0.0002589018,0.0005144805,0.8761159,0.00189535,0.001483752,0.1156627,0.0006296663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002741568,0.0001135737,0.9892194,0.0001510164,0.001010003,0.0004127325,0.000001288179,0.0008554342,0.005495022],"genre_scores_gemma":[0.9963617,0.000001415923,0.003236957,0.0001029442,0.0001049736,0.00002720165,0.00001232245,0.000005704755,0.0001467365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9936202,"threshold_uncertainty_score":0.9513127,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0003320136,0.0001549336,0.0001203946,0.00043921,0.0003269362,0.001290516,0.0003438911,0.00008932085,0.00001043736],"category_scores_gemma":[0.00006334373,0.0001370308,0.0000484352,0.0006836528,0.00001707844,0.01628602,0.00002984177,0.0001313438,0.0005628651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216983,"about_ca_system_score_gemma":0.00006843275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001111813,"about_ca_topic_score_gemma":7.551297e-7,"domain_scores_codex":[0.9983321,0.00005953331,0.0006686162,0.0001238592,0.0005980868,0.0002177331],"domain_scores_gemma":[0.998874,0.00001709002,0.0004340386,0.0002570525,0.0003381376,0.00007968293],"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":[0.00001929973,0.00004565973,0.0001239605,0.0001937097,0.000002339017,2.103949e-7,0.00134124,0.3093445,0.00004909395,0.01026067,0.001493836,0.6771255],"study_design_scores_gemma":[0.0003898017,0.00009383802,0.0005923165,0.00005227889,0.000002164086,0.00001299243,0.00008889434,0.9617987,0.0003067447,0.0000231465,0.03647866,0.000160429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00465923,0.00001508643,0.9811482,0.001328901,0.0008936291,0.0003367606,0.000003087506,0.0007214727,0.01089367],"genre_scores_gemma":[0.9952655,0.000001455439,0.002049647,0.002402739,0.00008810643,0.00005016832,0.00005422576,0.000004390134,0.00008375895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9906063,"threshold_uncertainty_score":0.9997463,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001651346,0.0001767938,0.0001812941,0.0002423849,0.0005921056,0.001018532,0.0004278021,0.00006966793,0.000002477582],"category_scores_gemma":[0.00004286081,0.0001370011,0.00003596345,0.001055383,0.000105529,0.006705186,0.00009762873,0.000313997,0.00003131398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002900195,"about_ca_system_score_gemma":0.00003525498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001874307,"about_ca_topic_score_gemma":0.000001961984,"domain_scores_codex":[0.9983741,0.00008778108,0.0004565172,0.0002489161,0.0004756595,0.0003570017],"domain_scores_gemma":[0.998807,0.00005368688,0.0003993753,0.0002770845,0.0003608446,0.0001019986],"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":[0.0002776074,0.00008291481,0.01850492,0.0007891597,0.00007176631,0.00001929322,0.01337988,0.4461404,0.001943386,0.03035438,0.00157034,0.4868659],"study_design_scores_gemma":[0.0003673677,0.000193696,0.001300387,0.0001478849,0.000005570128,0.0001128967,0.0001888706,0.9946876,0.0006129457,0.0004838727,0.00167681,0.0002221476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09989683,0.00006930816,0.8968416,0.0001827826,0.0003858469,0.0002489224,4.558408e-7,0.0006126785,0.00176153],"genre_scores_gemma":[0.9933959,0.000003703287,0.006001749,0.0001964555,0.000187731,0.00003394411,0.00001583894,0.00001030895,0.0001543273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8934991,"threshold_uncertainty_score":0.9821725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100002341","doi":"","title":"Replicated Softmax: an Undirected Topic Model","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":442,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Latent Dirichlet allocation; Softmax function; Computer science; Graphical model; Inference; Artificial intelligence; Topic model; Latent variable; Undirected graph; Dirichlet distribution; Theoretical computer science; Data mining; Machine learning; Algorithm; Graph; Deep learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03266415990600878,"gpt":0.2715287157289674,"spread":0.2388645558229586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002458199,0.0001297607,0.0001482047,0.0001365825,0.0001994962,0.0008681432,0.0005798952,0.00008110482,8.156398e-7],"category_scores_gemma":[0.00003721239,0.0001163407,0.00002607995,0.0003528797,0.000009940114,0.006639922,0.00003627888,0.0001267453,0.00002065439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000605917,"about_ca_system_score_gemma":0.00009210513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002282958,"about_ca_topic_score_gemma":6.288028e-7,"domain_scores_codex":[0.9986908,0.0000341144,0.0005033295,0.0002048129,0.0003051104,0.0002618614],"domain_scores_gemma":[0.9989194,0.000008337716,0.0002426827,0.0004939411,0.0002319308,0.0001037573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008846892,0.00004689192,0.0001224538,0.0001649738,0.000004717107,0.000002045926,0.004878316,0.360736,0.001607439,0.02805504,0.0006336647,0.6037396],"study_design_scores_gemma":[0.0001511588,0.00003798939,0.0002501727,0.00002938705,0.000001919104,0.00002937775,0.00004052312,0.9978875,0.0002400599,0.0006462719,0.0005453687,0.0001402901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04927099,0.00006550938,0.9446685,0.0007851637,0.0002516204,0.0002264909,0.000001026517,0.001003862,0.003726852],"genre_scores_gemma":[0.987062,0.000001248079,0.01162013,0.00102461,0.00006098294,0.00001404779,0.00001623015,0.000003750854,0.0001970434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.937791,"threshold_uncertainty_score":0.8371525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001347647,0.00007732134,0.00008037536,0.0000656129,0.0009969203,0.002350276,0.0007988883,0.00004965023,0.000002018064],"category_scores_gemma":[0.00002392816,0.00006753228,0.00002729411,0.00008236348,0.00003050415,0.006075746,0.0001130603,0.00007933749,0.0001000089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002423978,"about_ca_system_score_gemma":0.00002499779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003353655,"about_ca_topic_score_gemma":0.000001001123,"domain_scores_codex":[0.9993306,0.00000994133,0.0002612354,0.00009863309,0.0001698872,0.0001296652],"domain_scores_gemma":[0.9988355,0.000006158542,0.0004160778,0.0005387019,0.0001530313,0.00005052209],"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":[0.000002055302,0.00001273319,0.000358017,0.00013837,0.000003887961,8.510228e-7,0.0007411142,0.0008659214,0.0001273661,0.06019487,0.001980593,0.9355742],"study_design_scores_gemma":[0.00008954961,0.00001722364,0.001361015,0.00002263748,0.000001435804,0.00004229907,0.00003779191,0.9630685,0.0004501232,0.0005382978,0.03426017,0.0001109576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001724631,0.00003673162,0.977272,0.0007905692,0.0002849587,0.0001895958,8.579348e-7,0.0005227535,0.01917789],"genre_scores_gemma":[0.9945038,0.000002895382,0.004980181,0.0001961218,0.00004218022,0.00007931956,0.000002761053,0.00000291371,0.0001898509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9927791,"threshold_uncertainty_score":0.9986854,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002245377,0.0001383861,0.0001314884,0.00009425206,0.0006425099,0.001131259,0.0002663654,0.00006748309,0.00001953025],"category_scores_gemma":[0.000009603209,0.0001220411,0.00004267348,0.0005127758,0.00002611959,0.004415872,0.00003281737,0.000119521,0.00009886877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004455158,"about_ca_system_score_gemma":0.00007906151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004985328,"about_ca_topic_score_gemma":0.000001930434,"domain_scores_codex":[0.9988805,0.00002518997,0.0005169565,0.00018179,0.0001769234,0.0002186457],"domain_scores_gemma":[0.9991256,0.00005248611,0.0002626168,0.0001893772,0.0003092377,0.00006070391],"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":[0.00001289712,0.0000343029,0.000105498,0.0004118385,0.00000856205,2.144472e-7,0.001126758,0.05418778,0.0005253128,0.01916197,0.006474182,0.9179507],"study_design_scores_gemma":[0.0002623188,0.00002818021,0.0003121129,0.00005638396,0.000003323207,0.00002803291,0.00003757791,0.9337291,0.0001238735,0.0004310753,0.06483363,0.0001544415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04901091,0.0001407902,0.944167,0.0008006782,0.0005188703,0.0006577048,0.000006009032,0.000376269,0.00432179],"genre_scores_gemma":[0.9889293,0.000001137114,0.008539972,0.0007566896,0.0003900887,0.0002970101,0.00006485956,0.000008680183,0.001012304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9399183,"threshold_uncertainty_score":0.9999056,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003246237,0.0001779939,0.0002566251,0.0005631961,0.0008733105,0.002153674,0.0008540953,0.0001304333,0.00009173872],"category_scores_gemma":[0.005069297,0.00009459903,0.00007962906,0.002472267,0.0001825837,0.004402479,0.0001226237,0.0006314017,0.0006446071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003561412,"about_ca_system_score_gemma":0.0001355263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134124,"about_ca_topic_score_gemma":0.00002064283,"domain_scores_codex":[0.9960746,0.0001934967,0.001139695,0.0002315069,0.001972346,0.0003883459],"domain_scores_gemma":[0.9964095,0.0008644827,0.0006324826,0.0006480583,0.001291725,0.0001537166],"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":[0.0001056898,0.00006157581,0.001311525,0.0001640537,0.00002478456,0.0002097258,0.00368672,0.1124968,0.0004732816,0.00131327,0.0204496,0.8597029],"study_design_scores_gemma":[0.0004229725,0.00003182846,0.0001848757,0.000009490534,0.000004553628,0.002480609,0.001724589,0.8686839,0.0002440734,0.0002895885,0.1257678,0.0001557158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8072849,0.0005909152,0.17741,0.002383584,0.005350001,0.001879979,0.00007737861,0.0004591566,0.00456406],"genre_scores_gemma":[0.9973146,0.000003452257,0.0008132784,0.0002541494,0.0004370875,0.0000809413,0.00001203165,0.00001079966,0.001073675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8595473,"threshold_uncertainty_score":0.9988822,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000266827,0.000165098,0.0002236525,0.0001706532,0.0003216586,0.001001675,0.0004973075,0.00009163102,0.00002095186],"category_scores_gemma":[0.0001119471,0.0001439055,0.0000626773,0.0002926242,0.00001802466,0.005243296,0.000111024,0.0001560738,0.000253486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007245071,"about_ca_system_score_gemma":0.0001158167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004807168,"about_ca_topic_score_gemma":9.081952e-7,"domain_scores_codex":[0.9984683,0.00008247521,0.0005813701,0.0001961792,0.0003700435,0.0003016198],"domain_scores_gemma":[0.9986369,0.0001161239,0.0004146524,0.0003496457,0.0004022633,0.00008040252],"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":[0.0004140709,0.000225146,0.01430225,0.02142612,0.000155075,0.00000508654,0.02951234,0.2303888,0.005029364,0.2313347,0.01110425,0.4561028],"study_design_scores_gemma":[0.0003608975,0.0001505281,0.001252589,0.0001058962,0.000004583545,0.00002551918,0.00005413944,0.9903576,0.00003850228,0.0001283825,0.007344218,0.0001771325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04746883,0.0001292724,0.9456148,0.001978373,0.001943091,0.001515075,0.00001933201,0.0007490476,0.0005822239],"genre_scores_gemma":[0.9929676,6.804805e-7,0.004423467,0.0001863417,0.0001248078,0.0001600309,0.0001422168,0.00001190433,0.001982921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9454988,"threshold_uncertainty_score":0.9659178,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001551716,0.0001333289,0.000161093,0.00008415165,0.0002683251,0.0002443716,0.0001210886,0.00006560201,0.00002772908],"category_scores_gemma":[0.00005351768,0.00007586898,0.00003067468,0.0002092687,0.00004030655,0.00136182,0.00001547426,0.0001124781,0.0000817624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000399409,"about_ca_system_score_gemma":0.00002321743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004396355,"about_ca_topic_score_gemma":7.81373e-7,"domain_scores_codex":[0.9990035,0.00004216063,0.0004173829,0.0001040777,0.0002296001,0.0002032601],"domain_scores_gemma":[0.9990889,0.0001102254,0.0002919359,0.0001566099,0.000277405,0.00007492276],"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":[0.0005784621,0.0003874547,0.01985731,0.003375005,0.0002052212,0.00001350836,0.009406214,0.03855144,0.008542766,0.2038516,0.03488109,0.6803499],"study_design_scores_gemma":[0.004883871,0.0003786591,0.003346145,0.001901266,0.0001113659,0.0006051345,0.003489473,0.8813927,0.0009205582,0.001762939,0.09984813,0.001359819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3188981,0.00008443402,0.6677238,0.00209285,0.0002263445,0.0009374184,0.00001167202,0.001463049,0.008562432],"genre_scores_gemma":[0.9971181,0.000003350365,0.001494639,0.0001522205,0.00009295138,0.0001060258,0.00001337823,0.00001603032,0.001003342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8428412,"threshold_uncertainty_score":0.3093847,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000763245,0.0001332696,0.0002556066,0.0004024435,0.0001186861,0.0004245667,0.0002246209,0.00008703562,0.000004729096],"category_scores_gemma":[0.0002113834,0.000123273,0.00004269633,0.0003022582,0.00003645549,0.003209876,0.00004246485,0.0001693522,0.00000484223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272735,"about_ca_system_score_gemma":0.0000696218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001503054,"about_ca_topic_score_gemma":0.000627518,"domain_scores_codex":[0.9986246,0.00004144628,0.0006912945,0.0001680928,0.000268557,0.000206017],"domain_scores_gemma":[0.998879,0.0001659506,0.0004416089,0.0001582487,0.0002912193,0.00006403793],"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":[0.00001615478,0.00001307343,0.0004046288,0.0003089892,0.000005102698,6.750821e-7,0.00350159,0.00003468509,0.001725116,0.0003881677,0.00003337425,0.9935684],"study_design_scores_gemma":[0.00165567,0.0001393284,0.003347272,0.000954856,0.00002043242,0.0001572047,0.003941684,0.9532833,0.03164655,0.00103197,0.003318684,0.00050308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9327809,0.0001477271,0.0603407,0.0002795796,0.0009138031,0.001014206,0.00003007015,0.0002641313,0.004228856],"genre_scores_gemma":[0.9893546,0.000006568281,0.01028796,0.00009001032,0.000059843,0.00008711599,0.00002071331,0.000007024084,0.000086209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9930654,"threshold_uncertainty_score":0.5026926,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000749336,0.0003092542,0.0003208689,0.0003472167,0.0005899309,0.002023931,0.0009897468,0.0001486513,0.000004992873],"category_scores_gemma":[0.0002797497,0.0002756691,0.00005492568,0.001489752,0.00004060818,0.006667704,0.0001301871,0.0001721619,0.00006112699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001365423,"about_ca_system_score_gemma":0.000387328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005054709,"about_ca_topic_score_gemma":0.00001700626,"domain_scores_codex":[0.9973454,0.00002389638,0.0009703413,0.0003835323,0.0005411431,0.0007356717],"domain_scores_gemma":[0.9976478,0.00009103277,0.0006152576,0.0003746953,0.0009925665,0.0002787045],"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":[0.0002465371,0.0002023414,0.001219562,0.01368079,0.00006156712,0.00003324947,0.02167593,0.08441807,0.002421032,0.1006892,0.002245301,0.7731065],"study_design_scores_gemma":[0.0008987463,0.0003237671,0.0009413256,0.0008189244,0.00002024228,0.0003334449,0.001000037,0.9454252,0.002966609,0.001136909,0.04513914,0.0009957175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002802102,0.0003089702,0.9920626,0.0006856932,0.0007284614,0.0008580205,0.000007198121,0.000378341,0.002168655],"genre_scores_gemma":[0.9316623,0.000003595088,0.06649751,0.00137652,0.0001815196,0.00008199659,0.00001289099,0.00001978218,0.0001638473],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9288602,"threshold_uncertainty_score":0.9999695,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006086789,0.0002028384,0.000244983,0.0001965169,0.0006990519,0.003048989,0.001214363,0.0001045212,7.907429e-7],"category_scores_gemma":[0.0002841445,0.0001769943,0.00003322319,0.0002360636,0.00007036065,0.01052667,0.0001965389,0.0003786645,0.000008833825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007466594,"about_ca_system_score_gemma":0.00005695038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000103772,"about_ca_topic_score_gemma":0.00001734681,"domain_scores_codex":[0.9983118,0.0001160437,0.0006100682,0.0002586684,0.0003444012,0.0003589827],"domain_scores_gemma":[0.9982266,0.00004947923,0.0008543229,0.0005851656,0.0001892288,0.00009523325],"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":[0.000009880215,0.00001821094,0.001296918,0.0001924239,0.000003105962,0.000004933349,0.008231872,0.3069628,0.00001615895,0.001916328,0.00004880345,0.6812985],"study_design_scores_gemma":[0.0004935086,0.00002501046,0.01094786,0.000140525,0.000003107405,0.0000215644,0.001082957,0.9866949,0.000005161824,0.00001324253,0.0003617607,0.0002104245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05892183,0.0001890202,0.932761,0.001877015,0.001246889,0.0003761209,0.000004161994,0.0003243214,0.004299708],"genre_scores_gemma":[0.998104,0.000007067553,0.001363933,0.0002121229,0.0001182733,0.00006036638,0.00007394577,0.000008929559,0.00005131482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391822,"threshold_uncertainty_score":0.997986,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003382379,0.0001626694,0.0001795096,0.0003575355,0.0003109568,0.0005038888,0.0004398424,0.0001064824,0.000001056869],"category_scores_gemma":[0.0000691809,0.0001498582,0.00004940466,0.001006254,0.00005224878,0.006686699,0.00007773079,0.0001504785,0.00002672463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006709254,"about_ca_system_score_gemma":0.00005089178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007569638,"about_ca_topic_score_gemma":0.000007739756,"domain_scores_codex":[0.9985301,0.00004079078,0.0006532276,0.0002180791,0.0001974543,0.0003602885],"domain_scores_gemma":[0.9988908,0.0000748382,0.0003206202,0.000251087,0.0003907993,0.00007185132],"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":[0.00009740683,0.00006952354,0.003545981,0.001556536,0.00001874737,0.000002030862,0.01340123,0.08046452,0.0008012298,0.06124602,0.01022983,0.828567],"study_design_scores_gemma":[0.0004187043,0.0001225259,0.000532401,0.0001265729,0.000002219791,0.00001783845,0.0001017201,0.983013,0.000222323,0.002052741,0.01324004,0.0001499333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02226669,0.0003883015,0.9722034,0.0001727736,0.002134607,0.0008684399,0.000009198498,0.0006227779,0.001333859],"genre_scores_gemma":[0.9957992,0.000003738752,0.0034264,0.0001812624,0.0003334615,0.0001521039,0.00002666869,0.000009648454,0.0000674784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9735326,"threshold_uncertainty_score":0.6111039,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002201637,0.0002265779,0.0002628099,0.0001569758,0.0002115878,0.0008607017,0.0009109073,0.00009758034,0.0000174856],"category_scores_gemma":[0.00001741534,0.0002013632,0.00006575987,0.0007221171,0.00003192507,0.008142939,0.0001809876,0.0002156813,0.002007201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008731932,"about_ca_system_score_gemma":0.00007151863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001065117,"about_ca_topic_score_gemma":6.553132e-7,"domain_scores_codex":[0.9980749,0.00004982296,0.0007123663,0.0002892051,0.0004708741,0.0004027605],"domain_scores_gemma":[0.9983163,0.00007131373,0.0005158592,0.0006758397,0.0002898217,0.0001308481],"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":[0.00005078074,0.0000790811,0.001189586,0.001508542,0.00003368526,0.000002678359,0.002314894,0.5254335,0.0007384669,0.05159757,0.02107513,0.395976],"study_design_scores_gemma":[0.0004528568,0.00004971702,0.00008723524,0.00008270462,0.00000335713,0.00005825325,0.0001024025,0.9085711,0.0001413025,0.00010265,0.09009764,0.0002507805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005609719,0.0002840712,0.975105,0.0007283797,0.001075949,0.0012055,0.000006607423,0.0006379221,0.01534689],"genre_scores_gemma":[0.9554285,0.00001493913,0.04007751,0.001266755,0.0001555213,0.000173432,0.00006036416,0.00002347871,0.002799504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9498188,"threshold_uncertainty_score":0.9987699,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003086166,0.0002223608,0.0002009777,0.0002202125,0.0003804546,0.001254692,0.000394027,0.00009119268,0.000002955897],"category_scores_gemma":[0.00003746253,0.0001781739,0.0000342085,0.0005714304,0.00002908029,0.005834027,0.00003667051,0.0003370327,0.00005803531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008591708,"about_ca_system_score_gemma":0.0001059508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001664588,"about_ca_topic_score_gemma":2.602174e-7,"domain_scores_codex":[0.9981189,0.00007744353,0.0006156633,0.0002124372,0.0006704886,0.0003050246],"domain_scores_gemma":[0.9985921,0.00002447851,0.0007143242,0.0002707612,0.0003032678,0.00009501889],"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":[0.00003811504,0.00002140727,0.002064663,0.0003278746,0.00001071911,0.000001978687,0.002588566,0.8960687,0.0002584095,0.007980965,0.000198037,0.09044057],"study_design_scores_gemma":[0.000384239,0.0004389012,0.004044361,0.0001566986,0.000007907748,0.0000324485,0.0002760931,0.9909536,0.0001483234,0.00005426573,0.003259605,0.0002435369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01403097,0.000066004,0.9802634,0.0002932832,0.0003826908,0.0003897695,2.952454e-7,0.0007391103,0.003834518],"genre_scores_gemma":[0.9948147,0.000003605885,0.004097127,0.0004879033,0.0000631717,0.00002462385,0.00005705701,0.000007337842,0.0004444992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9807837,"threshold_uncertainty_score":0.9997821,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001090873,0.0002667284,0.0004131178,0.0003369535,0.00084955,0.00724173,0.001484667,0.0001728054,0.000001845191],"category_scores_gemma":[0.00006598898,0.0002342978,0.00005782989,0.0002078969,0.00004781011,0.01228592,0.0002738418,0.0002946656,0.00003751385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839803,"about_ca_system_score_gemma":0.0001103578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001081485,"about_ca_topic_score_gemma":0.00001746478,"domain_scores_codex":[0.997522,0.0001409475,0.001088393,0.000292326,0.0004940561,0.0004622768],"domain_scores_gemma":[0.9973373,0.00004073627,0.001235227,0.001011711,0.0002559824,0.0001190643],"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":[0.00008898976,0.0004374054,0.05134796,0.01291977,0.0001535785,0.000146866,0.02821479,0.01035913,0.001751473,0.1890493,0.1190547,0.5864761],"study_design_scores_gemma":[0.0008026102,0.00007847313,0.001978395,0.001448859,0.000004782539,0.0001343122,0.0007747171,0.9053835,0.0004240778,0.0001161393,0.08827975,0.0005743564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03622263,0.002722729,0.8579081,0.00477258,0.0131899,0.003897647,0.00003036396,0.002771472,0.07848459],"genre_scores_gemma":[0.9981313,0.00001106715,0.001042102,0.000182353,0.0001445684,0.0001803676,0.000008007919,0.0000146902,0.0002854949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9619087,"threshold_uncertainty_score":0.9937888,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004016005,0.000207595,0.000177472,0.0002517067,0.0006406754,0.00149872,0.0005174543,0.00008672436,0.000006780497],"category_scores_gemma":[0.0000394292,0.0001705665,0.00002989026,0.0007844456,0.00009218224,0.009210839,0.00006725521,0.0001445603,0.0000649656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000837015,"about_ca_system_score_gemma":0.000216298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002413577,"about_ca_topic_score_gemma":0.000002144157,"domain_scores_codex":[0.9982439,0.00006432072,0.0005300539,0.0002457791,0.0005643739,0.0003516202],"domain_scores_gemma":[0.9985293,0.0000150762,0.0003765635,0.0003442078,0.0006203222,0.0001145766],"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":[0.0001292678,0.00004873337,0.002513209,0.001444653,0.00003322394,0.000003441547,0.03741369,0.4869042,0.004294893,0.01142484,0.0009114117,0.4548784],"study_design_scores_gemma":[0.0006156793,0.0001526041,0.0004427166,0.0001086949,0.000006000076,0.00004012974,0.0005243518,0.9951549,0.0005120579,0.000009982618,0.002183478,0.0002494638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05967303,0.00004343208,0.9354401,0.000275827,0.0003674131,0.0003103045,9.640265e-7,0.0006198575,0.00326904],"genre_scores_gemma":[0.9631218,0.000003028916,0.03551038,0.0008274703,0.0001152592,0.0000384442,0.00002863907,0.00001430307,0.0003406464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9034488,"threshold_uncertainty_score":0.9995378,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007655442,0.0002017736,0.0003359723,0.0001985464,0.001723723,0.003835507,0.0008595822,0.00008963855,0.000002966623],"category_scores_gemma":[0.0001642549,0.0001615338,0.0001471451,0.0001142777,0.00002931406,0.00659945,0.0001074704,0.0002007975,0.00002428156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509621,"about_ca_system_score_gemma":0.000067598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002634994,"about_ca_topic_score_gemma":0.00000510828,"domain_scores_codex":[0.9985552,0.00008251398,0.0005685384,0.000240993,0.0002846573,0.0002680692],"domain_scores_gemma":[0.9976212,0.00009736812,0.001033783,0.0005710344,0.0005966598,0.00007997434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004444088,0.000124661,0.0002771868,0.0009392287,0.0006640643,0.000002746775,0.018213,0.001867607,0.0002358909,0.7997376,0.06144097,0.1164526],"study_design_scores_gemma":[0.0006019119,0.0003472627,0.00008423983,0.0002024282,0.00008232411,0.00003299298,0.001794813,0.459179,0.0009792112,0.000970916,0.535298,0.0004268597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000516836,0.000307369,0.9523327,0.01600288,0.002118097,0.001823442,0.00002440175,0.001104005,0.02577022],"genre_scores_gemma":[0.9917522,0.000007601866,0.005808703,0.0004830857,0.0001486805,0.0007588282,0.000014681,0.00001271576,0.001013515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912354,"threshold_uncertainty_score":0.9995759,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386247,0.0001734521,0.0003984811,0.0003319068,0.0002493149,0.0001660767,0.0007375107,0.00008530613,4.279428e-7],"category_scores_gemma":[0.0002271104,0.0001636487,0.00008593741,0.00060126,0.00009067095,0.002898641,0.0002819751,0.0001393282,0.000001922514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008111746,"about_ca_system_score_gemma":0.0001247538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649262,"about_ca_topic_score_gemma":0.000008416559,"domain_scores_codex":[0.9974428,0.00007975425,0.001168286,0.0001965296,0.0007552009,0.0003574742],"domain_scores_gemma":[0.9978505,0.0001560175,0.0008673548,0.0003889989,0.0006587805,0.00007828181],"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":[0.0001488576,0.00003145933,0.0004628917,0.006787437,0.00004601148,0.000003248139,0.02657915,0.4381305,0.006244717,0.00076103,0.0000431736,0.5207615],"study_design_scores_gemma":[0.0005459254,0.00009163097,0.0002116209,0.0004234742,0.000002806586,0.00009897262,0.0007702357,0.9947432,0.002077488,0.00002247688,0.0008380746,0.000174065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01525176,0.0002266406,0.9830521,0.00007737976,0.0003999258,0.0004916431,0.000008060041,0.0001553961,0.0003370792],"genre_scores_gemma":[0.9776586,0.000009333461,0.02206568,0.00003010738,0.00007761201,0.00007759826,0.000007171937,0.00001254985,0.00006136399],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624068,"threshold_uncertainty_score":0.6673401,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006692196,0.0001504575,0.0001894879,0.0001197456,0.0002721427,0.001203386,0.001345998,0.0001258127,0.000001656245],"category_scores_gemma":[0.0001986914,0.0001186932,0.00003456381,0.000234063,0.0000387472,0.005284132,0.0002148401,0.0002882918,0.000005566268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003675,"about_ca_system_score_gemma":0.0001158998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650438,"about_ca_topic_score_gemma":0.000008229025,"domain_scores_codex":[0.9986669,0.00004531028,0.0004837115,0.0002485148,0.00027976,0.0002757923],"domain_scores_gemma":[0.998578,0.00009548951,0.0002866503,0.0007376051,0.0001970061,0.0001053108],"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":[0.000008552557,0.000006245245,0.00001664724,0.0002516727,0.000004628752,5.239289e-7,0.001000651,0.00005574284,0.001270003,0.04611196,0.001368679,0.9499047],"study_design_scores_gemma":[0.0002966162,0.00002248079,0.0001326442,0.00003402929,0.000006430737,0.0001056325,0.00001904734,0.9771347,0.0002319321,0.003097704,0.01875703,0.0001617232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001467369,0.00004410333,0.9944399,0.0005430471,0.001729994,0.0003699114,0.0000268501,0.0002313771,0.001147466],"genre_scores_gemma":[0.6035504,5.026927e-7,0.3956171,0.0003759789,0.0002877887,0.00003141219,0.00007129092,0.000007481575,0.00005799459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.977079,"threshold_uncertainty_score":0.9998335,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001527396,0.0001145019,0.000206439,0.0001240237,0.0001394778,0.00005402017,0.00005939464,0.00007640336,0.00002887897],"category_scores_gemma":[0.00008247363,0.00009758016,0.0000510524,0.0003289086,0.00005238119,0.0007814404,0.00002191063,0.0002170981,0.00001591574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001422258,"about_ca_system_score_gemma":0.0001141938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001179887,"about_ca_topic_score_gemma":0.00001018476,"domain_scores_codex":[0.9988066,0.00004534298,0.0004860518,0.0001119359,0.0003812505,0.0001687957],"domain_scores_gemma":[0.9988891,0.0000159651,0.0004444863,0.0001134198,0.0004540248,0.00008294755],"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":[0.006026106,0.0001742837,0.043152,0.002965988,0.0001206487,0.0000232448,0.03443636,0.00561081,0.01005416,0.0009976579,0.0004334557,0.8960053],"study_design_scores_gemma":[0.01313491,0.02643022,0.08461692,0.01320337,0.0007780534,0.003844702,0.08262518,0.4813409,0.2099677,0.0002887768,0.08035323,0.003416063],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9858212,0.0007081097,0.003357403,0.00005183858,0.0007260163,0.0003627269,0.00002809376,0.0001943224,0.008750288],"genre_scores_gemma":[0.9995033,0.0000350377,0.00005887977,0.00002050272,0.00004939834,0.00007736989,0.00005012524,0.000007625326,0.0001978057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8925892,"threshold_uncertainty_score":0.3979203,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032496,0.0001096463,0.0001570188,0.0002008943,0.0003151247,0.0005606598,0.0003405968,0.00003547519,0.000003149613],"category_scores_gemma":[0.00009258146,0.00008741608,0.00002968019,0.00115951,0.00006031063,0.003870303,0.00005247913,0.0001564457,0.00001436707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000196951,"about_ca_system_score_gemma":0.00002972325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002211069,"about_ca_topic_score_gemma":4.227972e-7,"domain_scores_codex":[0.9986729,0.0001278017,0.0004523955,0.0001491816,0.0004132648,0.0001844642],"domain_scores_gemma":[0.998689,0.00004533301,0.0003939019,0.0002710047,0.0005529312,0.00004785564],"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":[0.00009390456,0.0007752337,0.05597739,0.004069605,0.000215043,0.00005059624,0.09026983,0.1476826,0.008425799,0.03976189,0.005795775,0.6468823],"study_design_scores_gemma":[0.001845775,0.0005721407,0.01714455,0.0005223106,0.00005504596,0.0003936878,0.002251915,0.96265,0.007158199,0.0001326836,0.006644682,0.0006289851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0902554,0.0003815475,0.9041362,0.0005830526,0.0003273979,0.0004014742,0.000003632754,0.0003063394,0.003604894],"genre_scores_gemma":[0.9932848,0.000006324696,0.006279219,0.00003488234,0.00003702136,0.00002823849,0.00001279995,0.000004216376,0.0003125342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9030294,"threshold_uncertainty_score":0.5406455,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003493266,0.0001342787,0.0001456435,0.0001785849,0.0004471399,0.001061691,0.0003265833,0.00005998795,1.816347e-7],"category_scores_gemma":[0.00009078638,0.0001237195,0.00002794758,0.000298571,0.00002687774,0.00641197,0.0001803769,0.00018373,0.000005738258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000833964,"about_ca_system_score_gemma":0.00005685315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002690486,"about_ca_topic_score_gemma":0.000002185014,"domain_scores_codex":[0.9988008,0.00002386275,0.0003595758,0.0001900142,0.00030548,0.0003202414],"domain_scores_gemma":[0.9992769,0.0000367033,0.0002022141,0.0001629717,0.000230502,0.00009075604],"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":[0.00003994585,0.00002742818,0.000267574,0.003547616,0.00001678365,0.000005346623,0.007381186,0.4327811,0.0008751774,0.02505668,0.00002451578,0.5299767],"study_design_scores_gemma":[0.0006390283,0.0001092776,0.0001814589,0.000141773,0.000001856805,0.0001294433,0.0002708816,0.9956893,0.0002519228,0.0008621284,0.001555904,0.0001670463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01233472,0.0001402219,0.9858267,0.0002813896,0.0002473138,0.0005218023,0.000001375167,0.0003720966,0.0002743618],"genre_scores_gemma":[0.9677492,0.000006619242,0.03187799,0.00008369782,0.00004384931,0.000133897,0.000005556685,0.000009353646,0.00008986994],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9554144,"threshold_uncertainty_score":0.9999753,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001635978,0.0001445548,0.0001402429,0.0001188645,0.0003055825,0.001546235,0.0003685717,0.00006366338,0.0000120163],"category_scores_gemma":[0.00004442204,0.0001138572,0.00004085852,0.000292494,0.00002694879,0.01043058,0.00007506098,0.0001024707,0.0002655328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003355055,"about_ca_system_score_gemma":0.00002460227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001581087,"about_ca_topic_score_gemma":0.000002259847,"domain_scores_codex":[0.9988782,0.00006090992,0.000442048,0.0001470213,0.0002487774,0.0002230098],"domain_scores_gemma":[0.9991047,0.00002017955,0.0002458758,0.000221408,0.0003280779,0.00007975916],"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":[0.000004255506,0.00004303278,0.001313376,0.0002697997,0.0000219236,0.000001106307,0.003667204,0.1619812,0.002679079,0.000642927,0.008293755,0.8210823],"study_design_scores_gemma":[0.0001897343,0.00002103617,0.002780295,0.00002952075,0.000002990456,0.00001772703,0.0001304405,0.9933617,0.0001572169,0.00002598077,0.003163503,0.000119909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002899961,0.0002437762,0.9934216,0.0004444055,0.001189215,0.0003284115,0.000002263148,0.0003234783,0.001146892],"genre_scores_gemma":[0.9827088,0.000004570833,0.01638834,0.0003867002,0.0001972935,0.00008628227,0.00001627367,0.000005718877,0.0002060477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9798088,"threshold_uncertainty_score":0.9994903,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000319449,0.0001486222,0.000192298,0.0001149159,0.0002532199,0.0009929836,0.0003669242,0.00006753514,0.0000032004],"category_scores_gemma":[0.000044415,0.0001239094,0.00004989617,0.0002458624,0.000009116437,0.006098606,0.00006901435,0.00008360596,0.00006522751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004450973,"about_ca_system_score_gemma":0.00009587304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003064854,"about_ca_topic_score_gemma":0.000002134697,"domain_scores_codex":[0.9987963,0.00005100983,0.0004475906,0.0001918747,0.0002547091,0.0002585509],"domain_scores_gemma":[0.9990717,0.00003972145,0.0001995032,0.000234458,0.0003960702,0.00005858601],"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":[0.00001061425,0.000005576745,0.00002543953,0.0001384983,0.000008135023,1.246845e-7,0.001233025,0.9744765,0.001070937,0.002030375,0.00118018,0.01982064],"study_design_scores_gemma":[0.0003173068,0.0000569346,0.000004262528,0.00005114075,0.000003812327,0.000005275453,0.0002143301,0.9946348,0.001216102,0.0001405675,0.003190853,0.0001645974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01485177,0.0001675184,0.9817134,0.0004099669,0.001029753,0.0005957883,0.000004988368,0.0001451172,0.001081743],"genre_scores_gemma":[0.9733449,0.000002817032,0.02551266,0.0005150319,0.0002440192,0.00008050368,0.00002165848,0.000007781265,0.0002706502],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9584931,"threshold_uncertainty_score":0.9575363,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003875264,0.0001584826,0.0001602806,0.0001384535,0.0002395222,0.0008861122,0.0004036039,0.00005717866,0.000007168807],"category_scores_gemma":[0.0000592817,0.0001243911,0.0000422597,0.0003874329,0.00001709927,0.007782174,0.0001035684,0.00009913683,0.0001897702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003787953,"about_ca_system_score_gemma":0.00001482981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002546899,"about_ca_topic_score_gemma":0.000001580828,"domain_scores_codex":[0.9987293,0.00007484727,0.0003958625,0.0001245014,0.0002992432,0.0003761725],"domain_scores_gemma":[0.9992371,0.00002872373,0.0001781352,0.0002363306,0.0001563525,0.0001633443],"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":[0.00001080536,0.00003572588,0.001933107,0.000246032,0.0000186014,8.638789e-7,0.01469516,0.0267404,0.000852829,0.001867615,0.01154665,0.9420522],"study_design_scores_gemma":[0.0001294324,0.00003200135,0.002551678,0.00004806945,0.00000471633,0.00002585297,0.0001233496,0.9598376,0.0005000659,0.00002389307,0.03650178,0.0002215221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009534892,0.0002997389,0.9837146,0.001151753,0.001789619,0.0003028664,0.000002410527,0.0001976318,0.003006513],"genre_scores_gemma":[0.9853023,8.180151e-7,0.01199801,0.0018945,0.0006150115,0.0000525731,0.000007027254,0.000006757988,0.000122967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9757674,"threshold_uncertainty_score":0.85448,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001170087,0.0001247654,0.0001292392,0.00009879017,0.0001496264,0.0005533014,0.0005669701,0.00004541957,0.000005649905],"category_scores_gemma":[0.000007550845,0.000108658,0.00003028115,0.0004910835,0.00001476199,0.005532491,0.0001104786,0.0001191351,0.0008302818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006293745,"about_ca_system_score_gemma":0.00004002872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004893971,"about_ca_topic_score_gemma":1.881696e-7,"domain_scores_codex":[0.9988397,0.00002177777,0.0004119302,0.0001669329,0.0003250764,0.0002345872],"domain_scores_gemma":[0.9990656,0.00002534386,0.0002919704,0.0004015073,0.0001457706,0.00006975153],"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":[0.000007893113,0.000033056,0.0006640397,0.0004568484,0.000009377759,0.000001128467,0.001941817,0.3196185,0.001213231,0.1143279,0.003396445,0.5583298],"study_design_scores_gemma":[0.000194606,0.00002722979,0.0002927218,0.00004175811,0.000001318944,0.0000362739,0.00009364417,0.9596623,0.0002040199,0.0001621662,0.03913351,0.0001504468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01652284,0.0001965038,0.9679417,0.0008696473,0.001083089,0.0007850979,0.000002702142,0.0008879097,0.01171051],"genre_scores_gemma":[0.9936424,0.000002718844,0.004922453,0.0006175576,0.00006111387,0.00008859298,0.00001256837,0.000006104063,0.0006464952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771196,"threshold_uncertainty_score":0.9999477,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003263447,0.000222998,0.0003641992,0.0004068513,0.003243982,0.006460275,0.0007948293,0.0001296414,0.00001407121],"category_scores_gemma":[0.004696167,0.0001655907,0.00007012072,0.0002666835,0.0002491075,0.009944907,0.0002445624,0.0003219703,0.00005600717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128363,"about_ca_system_score_gemma":0.000144295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006792674,"about_ca_topic_score_gemma":0.000006990971,"domain_scores_codex":[0.9964268,0.00007328281,0.001137829,0.000298318,0.001547526,0.0005162232],"domain_scores_gemma":[0.9961886,0.0003914144,0.001526036,0.0005954858,0.001113852,0.0001846034],"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":[0.000178985,0.00001238203,0.004662934,0.0008027201,0.00002379052,0.000004207585,0.005301728,0.1096131,0.0001122893,0.001692256,0.00181715,0.8757784],"study_design_scores_gemma":[0.0008668543,0.0001652092,0.001114932,0.0001703778,0.0000067305,0.00004062248,0.003804845,0.9007249,0.0001508037,0.0009675877,0.09174553,0.0002415661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06905583,0.0008329116,0.9094979,0.002391006,0.001970556,0.002618249,0.00003095617,0.0003608538,0.0132417],"genre_scores_gemma":[0.9941895,0.00002170264,0.0005779187,0.00007812714,0.0001754356,0.0001094627,0.00002942583,0.00001574375,0.004802662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9251337,"threshold_uncertainty_score":0.9980537,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004787016,0.0002406926,0.0003484811,0.0002666252,0.000181969,0.001144103,0.0007468694,0.0001257117,0.000006660042],"category_scores_gemma":[0.00004048682,0.0002077735,0.00005628264,0.001383162,0.00002575515,0.005689695,0.000242538,0.0004095437,0.00008202035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008164347,"about_ca_system_score_gemma":0.00006106376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005955177,"about_ca_topic_score_gemma":0.000002891871,"domain_scores_codex":[0.9975729,0.0001964494,0.0009406795,0.0003246701,0.0004755877,0.0004897164],"domain_scores_gemma":[0.9984508,0.00009840877,0.0005875888,0.0004280627,0.0003328295,0.0001022872],"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":[0.00001957991,0.00001882241,0.002645027,0.0002055511,0.000005924666,0.000008183337,0.001041547,0.84356,0.00006902716,0.0004632515,0.001064938,0.1508981],"study_design_scores_gemma":[0.0005157195,0.00007154548,0.0007866047,0.0002400969,0.000002482729,0.00007233089,0.0003039824,0.9965152,0.00003579417,0.000009734009,0.001200058,0.0002464864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8872377,0.001635551,0.09444574,0.001325469,0.007153473,0.002154567,0.000004145735,0.00100767,0.005035741],"genre_scores_gemma":[0.9988245,0.000008044823,0.0001989183,0.000316854,0.0002198272,0.00002640723,0.00004247944,0.00001207765,0.0003508738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1529551,"threshold_uncertainty_score":0.9998928,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009493851,0.0002930807,0.0003414132,0.0002611706,0.002178416,0.004574608,0.001097786,0.000170013,0.000002295328],"category_scores_gemma":[0.0004749572,0.0002753902,0.0001023422,0.0001937076,0.00005320632,0.01248875,0.0002375589,0.0002700511,0.0000258228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002536259,"about_ca_system_score_gemma":0.0001275106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008821909,"about_ca_topic_score_gemma":5.932486e-7,"domain_scores_codex":[0.9974495,0.00009268441,0.000996241,0.0002987434,0.0006433509,0.0005195487],"domain_scores_gemma":[0.9963442,0.00007674344,0.00214865,0.0007243865,0.0005847944,0.0001212182],"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":[0.00001398555,0.000004738736,0.0003493462,0.0004647787,0.00001303959,4.8107e-7,0.001499256,0.9600219,0.0002023148,0.001997161,0.00006348728,0.03536959],"study_design_scores_gemma":[0.0007730199,0.000109847,0.0001218751,0.0001895573,0.00002014244,0.00004202838,0.0003055611,0.9927227,0.0008061146,0.00003936284,0.004550769,0.000318946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001576075,0.00003949447,0.9940802,0.0001779397,0.0009905299,0.0009904318,3.772995e-7,0.0002776186,0.001867259],"genre_scores_gemma":[0.8919091,0.000003522369,0.1070055,0.0001001906,0.0001489677,0.00009959544,0.00004535049,0.00002080489,0.0006668938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8903331,"threshold_uncertainty_score":0.9999698,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003326306,0.0001225411,0.0001239585,0.0001831873,0.0004207902,0.000870749,0.0003887669,0.00005743322,0.000007426233],"category_scores_gemma":[0.0002469468,0.00008787307,0.00004107613,0.0003883166,0.00003593175,0.006363098,0.00007433237,0.0001289589,0.000267893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005850805,"about_ca_system_score_gemma":0.0000689448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008544836,"about_ca_topic_score_gemma":7.61469e-7,"domain_scores_codex":[0.9986163,0.00008881558,0.000480676,0.0001702466,0.0003869082,0.0002570332],"domain_scores_gemma":[0.9989467,0.00009111809,0.0003853207,0.0002261966,0.0002520909,0.00009855645],"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":[0.000008146092,0.00001355139,0.001618662,0.0001001558,0.000009243411,0.000002853808,0.008694245,0.1211272,0.0008385965,0.02054755,0.0007999907,0.8462397],"study_design_scores_gemma":[0.0003560606,0.00003221573,0.0005638181,0.00006763408,0.000002569185,0.00003505976,0.0006905243,0.9792805,0.0001088534,0.0001550052,0.01854786,0.0001599455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004650016,0.00008021983,0.9825344,0.0010243,0.000387341,0.0001634815,6.822206e-7,0.0006457313,0.01051383],"genre_scores_gemma":[0.9939426,0.000007952332,0.004079036,0.0002944857,0.000049418,0.00003937252,0.000005715163,0.000007041763,0.001574365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9892926,"threshold_uncertainty_score":0.8396653,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076052,0.000189833,0.0002082965,0.000301076,0.0002847428,0.001492146,0.0007632442,0.00008770596,0.000002449939],"category_scores_gemma":[0.00009459895,0.0001647994,0.00003235304,0.0007069946,0.0000280059,0.007238344,0.0000719946,0.0001371274,0.00002364633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006400134,"about_ca_system_score_gemma":0.00005162963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002623025,"about_ca_topic_score_gemma":2.757803e-7,"domain_scores_codex":[0.9983026,0.0001588907,0.0006036137,0.0002393766,0.0003970419,0.0002984684],"domain_scores_gemma":[0.998418,0.00003922756,0.0004509957,0.00041588,0.0005394079,0.0001364464],"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":[0.00002795158,0.0001237305,0.0003372301,0.000615445,0.00001786205,0.000001717552,0.00711765,0.1616512,0.001279597,0.292634,0.00171432,0.5344793],"study_design_scores_gemma":[0.0002466856,0.0001659545,0.0001388558,0.00004923137,0.000003845661,0.00005569261,0.00006820211,0.9953638,0.001340981,0.0004187708,0.001944933,0.0002029996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002102811,0.00001995712,0.9935266,0.0002030271,0.0005048873,0.0004500813,0.000001735399,0.001381279,0.001809616],"genre_scores_gemma":[0.8801066,5.282484e-7,0.1192678,0.0003700078,0.0000561703,0.0001191704,0.00002803806,0.000009885726,0.00004181172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8780038,"threshold_uncertainty_score":0.9995444,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001939966,0.0002276366,0.0003118643,0.0004741333,0.0005561064,0.002511445,0.000515435,0.0001998202,0.0001187326],"category_scores_gemma":[0.00249093,0.0001764009,0.0000500529,0.0007114742,0.0001544467,0.008740244,0.0001702205,0.0006260595,0.0001554263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005295148,"about_ca_system_score_gemma":0.0001485167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004806507,"about_ca_topic_score_gemma":0.00001653298,"domain_scores_codex":[0.9964994,0.0001510917,0.001189553,0.0003578467,0.00136561,0.0004365507],"domain_scores_gemma":[0.9972197,0.0005730354,0.0006389269,0.000348937,0.000962247,0.0002571629],"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":[0.00007632629,0.000036168,0.002924249,0.000171176,0.00001108597,0.000003547457,0.002019982,0.0188143,0.0006889064,0.0001104018,0.004150956,0.9709929],"study_design_scores_gemma":[0.0005570308,0.0001018891,0.006399446,0.0000374614,0.000004586907,0.0001528346,0.001029208,0.9402477,0.0001829285,0.0001071204,0.0509233,0.000256515],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6994618,0.00008454847,0.2915715,0.003029553,0.00218457,0.0009544429,0.00006675567,0.0003172815,0.002329519],"genre_scores_gemma":[0.9910201,0.000004388096,0.008039988,0.0002424245,0.0002064451,0.00005797422,0.00007586862,0.00001550615,0.0003373378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9707364,"threshold_uncertainty_score":0.9985241,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002735858,0.00007242071,0.00006528804,0.00001460193,0.0003384216,0.0004331534,0.00009322573,0.00001780898,0.00003763293],"category_scores_gemma":[0.00001837053,0.00004624951,0.00002347323,0.0001026108,0.00001885085,0.0005536257,0.00001736804,0.00008071459,0.000220607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001319638,"about_ca_system_score_gemma":0.00001744893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009091875,"about_ca_topic_score_gemma":3.070266e-7,"domain_scores_codex":[0.9992087,0.0000121855,0.0003162,0.00005220013,0.0001767005,0.000233965],"domain_scores_gemma":[0.9995446,0.0000671928,0.0001320879,0.00009305411,0.00009865555,0.00006436039],"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":[0.00002341817,0.00001034607,0.001184797,0.00002810902,0.000007864114,3.992244e-7,0.0004676192,0.0001594914,0.00009918954,0.6800942,0.001373962,0.3165506],"study_design_scores_gemma":[0.0005509997,0.00008229187,0.001361959,0.00005583457,0.00001508163,0.000007780592,0.004087555,0.8430899,0.002494592,0.005470637,0.1425361,0.0002473476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2367752,0.0001501863,0.7179197,0.0005846095,0.001416807,0.0004210379,0.0000172455,0.0001255082,0.04258968],"genre_scores_gemma":[0.9991806,4.132422e-7,0.00004109402,0.0001251975,0.0001737908,0.00001538167,0.00001218542,0.000004428327,0.0004468933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8429304,"threshold_uncertainty_score":0.4176908,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001459124,0.0001446198,0.0001391362,0.0001593278,0.0003889188,0.002683664,0.0005030924,0.00008430407,0.00002014377],"category_scores_gemma":[0.0001226523,0.000130721,0.00003507361,0.0004300872,0.00002839782,0.009905141,0.00009446697,0.0002692464,0.0008233899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004886328,"about_ca_system_score_gemma":0.00006543627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001814177,"about_ca_topic_score_gemma":4.550466e-7,"domain_scores_codex":[0.9985517,0.00007156991,0.0005813006,0.0001402922,0.0004013169,0.000253846],"domain_scores_gemma":[0.9988053,0.00007767429,0.0004257515,0.0002544578,0.0003456596,0.00009114947],"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":[6.565448e-7,0.000004662277,0.001427216,0.00006763845,0.000007914984,4.025693e-7,0.00217378,0.9477512,0.0002316718,0.001235438,0.001628859,0.04547051],"study_design_scores_gemma":[0.0001566945,0.00004010701,0.00159925,0.00005535943,0.000003313193,0.000009655053,0.0003865198,0.9919913,0.00009237239,0.00003448457,0.005478017,0.0001528784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01333712,0.0000697689,0.9760004,0.0004689774,0.0005264495,0.0003285171,4.76155e-7,0.0007110412,0.008557254],"genre_scores_gemma":[0.9931545,0.000003623521,0.005782755,0.0002948731,0.00007321599,0.00006198107,0.00004926847,0.000006655679,0.0005730748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9798175,"threshold_uncertainty_score":0.9999546,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000314169,0.0002953212,0.0003238334,0.000291427,0.0004990395,0.001028848,0.0003920471,0.0001273159,0.00001507107],"category_scores_gemma":[0.000303878,0.0002658717,0.00009370412,0.0007627635,0.00008883888,0.002993619,0.00009019276,0.000331517,0.00004783583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007514923,"about_ca_system_score_gemma":0.00003641424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001440016,"about_ca_topic_score_gemma":0.000003151653,"domain_scores_codex":[0.9975809,0.0001973584,0.0008014678,0.0003966728,0.0004646998,0.0005588694],"domain_scores_gemma":[0.998604,0.0002617671,0.0004943825,0.0002165273,0.0002279848,0.0001953288],"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":[0.0003163863,0.00007334946,0.002755602,0.0003477554,0.00002660881,0.0000078251,0.003472475,0.7363548,0.05173459,0.000810713,0.00580189,0.1982981],"study_design_scores_gemma":[0.0003370545,0.0001322037,0.0003129187,0.0001680668,0.00001064607,0.0001474634,0.0001060209,0.9913836,0.003148346,0.0000849937,0.003857299,0.0003113513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7500029,0.00009501264,0.245465,0.0003533903,0.002492992,0.0004333411,0.00002344637,0.0003928397,0.000741137],"genre_scores_gemma":[0.9946826,0.000002511322,0.001149215,0.003419134,0.0006324193,0.00002721495,0.00002949188,0.00001995413,0.00003751869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2550289,"threshold_uncertainty_score":0.9999794,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001250372,0.0001222377,0.0001205633,0.0001239874,0.0001770451,0.0005779897,0.0004415875,0.00004083736,0.000002991176],"category_scores_gemma":[0.00003404549,0.00007398957,0.00002806521,0.0002425207,0.00002662564,0.015211,0.00008944084,0.00006672375,0.00004881812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004859952,"about_ca_system_score_gemma":0.00004451324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002775913,"about_ca_topic_score_gemma":2.164877e-7,"domain_scores_codex":[0.9988786,0.00002553157,0.0003918974,0.0001445957,0.0003241127,0.0002352937],"domain_scores_gemma":[0.9991835,0.0000190216,0.0002510412,0.0002448165,0.0002229277,0.00007863373],"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":[0.000004511118,0.000003469397,0.00003437901,0.00007197615,0.000001711118,6.849523e-7,0.0008591998,0.002705894,0.0008773889,0.01032778,0.0001744349,0.9849386],"study_design_scores_gemma":[0.0003092221,0.00001748449,0.00006564472,0.00009286308,9.692516e-7,0.00005100606,0.00007298282,0.9930926,0.0006308666,0.001701478,0.003830151,0.0001347511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001154797,0.0001274702,0.995007,0.0005855741,0.0004843226,0.0001783558,0.000001459175,0.0003853823,0.002075639],"genre_scores_gemma":[0.9789882,0.000002973994,0.02037339,0.0004020426,0.00005412797,0.00002081689,0.000001860876,0.000005285021,0.0001512942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9903867,"threshold_uncertainty_score":0.9985628,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008830244,0.0002789035,0.0003320725,0.0002138819,0.000553664,0.001821588,0.0007516076,0.0001257219,0.00001136617],"category_scores_gemma":[0.0002567891,0.0002555068,0.0001022013,0.0004376958,0.0000226888,0.006584779,0.0001951567,0.0004129688,0.0002929382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001217907,"about_ca_system_score_gemma":0.0001364991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003499133,"about_ca_topic_score_gemma":4.51405e-7,"domain_scores_codex":[0.9973937,0.0000944909,0.0009842963,0.0002811645,0.0006781304,0.0005682698],"domain_scores_gemma":[0.9979908,0.0001288381,0.0009218098,0.0003636054,0.0004833209,0.0001115762],"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":[0.00001514339,0.00000347514,0.002632578,0.0006796154,0.00001226162,3.498836e-7,0.001706493,0.9819648,0.0001934208,0.002982631,0.0002998197,0.009509437],"study_design_scores_gemma":[0.0006109511,0.0003706492,0.0001367024,0.0001764991,0.000008109301,0.00001517818,0.0003079328,0.9319536,0.0001907849,0.00001785652,0.0659144,0.0002973376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009366598,0.00008347839,0.9795047,0.0002750418,0.001395325,0.001058049,4.179181e-7,0.0008256857,0.0074907],"genre_scores_gemma":[0.9865053,0.000006601485,0.004238817,0.0003093034,0.0001232695,0.0001267489,0.00007649868,0.00002221604,0.008591196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9771388,"threshold_uncertainty_score":0.9999897,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002062831,0.0002138039,0.0002114101,0.0001480319,0.0005552014,0.0007679022,0.000221246,0.0001441091,0.000004210611],"category_scores_gemma":[0.0001344595,0.0001828614,0.00007746896,0.0004030388,0.00003453741,0.002088967,0.00001798184,0.0002444015,0.00001263999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005253331,"about_ca_system_score_gemma":0.00003169713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005375382,"about_ca_topic_score_gemma":5.257507e-7,"domain_scores_codex":[0.9984719,0.00005405644,0.0005620026,0.0002323481,0.0002942862,0.0003853728],"domain_scores_gemma":[0.9990301,0.0001203505,0.0004530476,0.0001563634,0.0001473636,0.00009275318],"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":[0.0005211474,0.0001331433,0.0001494601,0.0009330806,0.000009129609,0.000007353558,0.0028272,0.4132126,0.09962649,0.005403892,0.0428945,0.434282],"study_design_scores_gemma":[0.0005641793,0.0002047037,0.0006201948,0.00006721352,0.000009658266,0.00007546465,0.0001337429,0.9912744,0.0009020173,0.00006420803,0.00585658,0.0002276544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5094784,0.0005972636,0.4216293,0.003114754,0.01470118,0.007176787,0.0001433457,0.003493058,0.03966585],"genre_scores_gemma":[0.9954637,0.000006327044,0.0001768638,0.003348176,0.0001772844,0.00004160211,0.00009840679,0.00001371961,0.0006739427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5780618,"threshold_uncertainty_score":0.7456873,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003502482,0.0001844718,0.0001912383,0.0001345795,0.0005229588,0.001875377,0.0004395431,0.00009049612,0.000004993427],"category_scores_gemma":[0.0001423694,0.0001557925,0.00004416139,0.00042426,0.00005490374,0.005645065,0.00009699883,0.0002368217,0.00001670272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003002448,"about_ca_system_score_gemma":0.00009751999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001836609,"about_ca_topic_score_gemma":0.000003675462,"domain_scores_codex":[0.9985948,0.00006383815,0.0005340939,0.0001917118,0.0003209272,0.0002945889],"domain_scores_gemma":[0.9987279,0.00003760461,0.0004029278,0.0003091898,0.0004271744,0.00009516053],"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":[0.000008625717,0.00002744644,0.0002735159,0.000345516,0.00002261335,0.000009298166,0.003292385,0.6970004,0.1304008,0.002118555,0.002773506,0.1637274],"study_design_scores_gemma":[0.0001379374,0.00001220955,0.0000857714,0.00004649424,0.00000664547,0.00007323861,0.0001187904,0.9941469,0.003357136,0.00001799258,0.00180726,0.0001896612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04006451,0.00008330918,0.956621,0.000296908,0.001641173,0.0002251445,0.000006257279,0.0002808546,0.0007808462],"genre_scores_gemma":[0.9540377,0.000001302426,0.04515413,0.0003271814,0.0003799032,0.00001037448,0.00001757689,0.000009048377,0.00006273183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9139732,"threshold_uncertainty_score":0.9991608,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000853762,0.0001346361,0.0001141309,0.00007924357,0.0001622579,0.0007507665,0.00008789777,0.00006578114,0.000004422041],"category_scores_gemma":[0.00000556426,0.00009345568,0.00001856073,0.0001124172,0.00003395602,0.002536363,0.00002636306,0.0001357175,0.00001549184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002847032,"about_ca_system_score_gemma":0.00000673776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003548373,"about_ca_topic_score_gemma":1.617864e-7,"domain_scores_codex":[0.9992698,0.00002247501,0.0003055056,0.00006823236,0.0001663557,0.0001675742],"domain_scores_gemma":[0.999612,0.00001258848,0.00009646988,0.0001262415,0.0001208436,0.00003186697],"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":[0.000004239489,0.00001053228,0.0003724631,0.0006224651,0.00003682884,0.000001417268,0.005180342,0.07373077,0.01415579,0.0001239459,0.003501415,0.9022598],"study_design_scores_gemma":[0.00008803217,0.000008367141,0.0002157843,0.00009040521,0.000005958939,0.00006690754,0.0002471574,0.9955382,0.00242222,0.00006037812,0.001133953,0.000122608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5310788,0.0003225395,0.4648901,0.0001455844,0.0003777542,0.0008597362,0.000003398592,0.0008194866,0.001502653],"genre_scores_gemma":[0.9958667,0.0000033441,0.003710354,0.0002090488,0.000111453,0.00005692571,0.000009571407,0.00001393315,0.00001874111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9218075,"threshold_uncertainty_score":0.7239659,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007647283,0.0003056866,0.0003412709,0.0003061249,0.0004690663,0.002099717,0.0009455087,0.0001014065,0.000003811785],"category_scores_gemma":[0.0001206369,0.0002357616,0.00003447767,0.0007447276,0.00004275696,0.00714332,0.00007197191,0.000409253,0.00006452866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119151,"about_ca_system_score_gemma":0.0001716455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003021276,"about_ca_topic_score_gemma":0.000002809947,"domain_scores_codex":[0.9974496,0.0002220586,0.000782695,0.000317184,0.0007189612,0.0005094458],"domain_scores_gemma":[0.9981142,0.00006351039,0.0006660353,0.000412675,0.0004625477,0.0002810446],"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":[0.00002128273,0.00001652988,0.001275458,0.0001808963,0.00000758873,0.000001139311,0.007293384,0.8867991,0.0001062164,0.0005555853,0.00001897975,0.1037239],"study_design_scores_gemma":[0.0005886306,0.0006137023,0.0007643517,0.0001670066,0.000008962836,0.00008004194,0.000898967,0.9928893,0.0004335642,0.000008906447,0.003192978,0.000353557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02859114,0.00003006504,0.9676716,0.000600391,0.0002500227,0.0005865825,7.580139e-7,0.0006732757,0.001596166],"genre_scores_gemma":[0.9461588,5.590228e-7,0.05237215,0.0007577442,0.0001347629,0.00009679658,0.0000148356,0.00001683829,0.0004475728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9175676,"threshold_uncertainty_score":0.9989362,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003627354,0.0001558161,0.0001680606,0.0002383803,0.0001878587,0.0008020377,0.0006958469,0.0000469066,0.000008881848],"category_scores_gemma":[0.00004969992,0.00009566244,0.00001391082,0.0004529415,0.0001218554,0.01001219,0.00009591576,0.00008081862,0.0001154114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003115,"about_ca_system_score_gemma":0.0001218247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004615391,"about_ca_topic_score_gemma":0.000006941593,"domain_scores_codex":[0.9985244,0.00005517355,0.0005476813,0.0002106607,0.000406714,0.0002553384],"domain_scores_gemma":[0.9984782,0.00006819407,0.0005457851,0.0005983948,0.000227061,0.00008233493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002076201,0.00002218677,0.004045764,0.0004559448,0.00001647881,0.000006106784,0.0007226337,0.00007417647,0.003960692,0.07779823,0.03447925,0.8783978],"study_design_scores_gemma":[0.005507365,0.0005909478,0.02643886,0.005661537,0.00004651495,0.001094169,0.0008674861,0.3140905,0.0519212,0.001478539,0.5886478,0.003655024],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007911671,0.00001938239,0.9919694,0.0009584447,0.0001949639,0.0003909621,0.0004166131,0.0008964903,0.00436254],"genre_scores_gemma":[0.985028,0.00001065633,0.01394108,0.0004130705,0.00004144952,0.000095937,0.0002851987,0.000007943654,0.0001766456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9842368,"threshold_uncertainty_score":0.7734067,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000140242,0.0001919125,0.0002017039,0.0001121949,0.0002910189,0.0008025306,0.0005915472,0.00008802958,0.000001191182],"category_scores_gemma":[0.00009568107,0.0001728732,0.00007860142,0.0007520104,0.00002733142,0.007368418,0.00008603041,0.000160119,0.0000219962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002901301,"about_ca_system_score_gemma":0.00005182268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000038973,"about_ca_topic_score_gemma":4.998125e-7,"domain_scores_codex":[0.9984388,0.00003467708,0.0006045122,0.0002397134,0.0003497475,0.0003325721],"domain_scores_gemma":[0.9987556,0.00005358367,0.0005080537,0.0002161939,0.0002970423,0.000169482],"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":[0.00008456995,0.00002679195,0.0005057062,0.001177536,0.00002283234,0.000003522967,0.006044907,0.2278775,0.0005124125,0.05465707,0.003899651,0.7051874],"study_design_scores_gemma":[0.000488957,0.0001266226,0.0002177615,0.00006059597,0.000004506861,0.00002269547,0.0000765529,0.9854274,0.0003376109,0.0005492014,0.01247146,0.0002166172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004857511,0.0002479634,0.989597,0.002603788,0.0007072901,0.0007620985,0.000006129531,0.0006636003,0.0005546545],"genre_scores_gemma":[0.9886283,0.000004654992,0.008236647,0.002740101,0.0002054429,0.0001243034,0.0000315886,0.00001115079,0.00001779868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9837708,"threshold_uncertainty_score":0.7738821,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000271945,0.0001633846,0.0001906027,0.0001650456,0.0002742869,0.001204094,0.0002623893,0.00007216622,0.000001690037],"category_scores_gemma":[0.0002710305,0.0001591209,0.00002726082,0.0006583538,0.00001617777,0.004238347,0.0001067713,0.0002317123,0.00008065856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003636885,"about_ca_system_score_gemma":0.000159618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002150432,"about_ca_topic_score_gemma":0.00000166578,"domain_scores_codex":[0.9986235,0.00009229014,0.0005187087,0.0002473502,0.0003069762,0.0002111919],"domain_scores_gemma":[0.9990174,0.0000414251,0.0003279262,0.000105881,0.0002379031,0.0002695205],"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":[0.00001830708,0.00001797784,0.0000931292,0.0002011208,0.000004747821,2.280474e-7,0.06978073,0.5520461,0.0001752083,0.003223091,0.0007154844,0.3737239],"study_design_scores_gemma":[0.0004661393,0.00005701838,0.0004710378,0.00004796678,0.000004384364,0.00001229561,0.004032126,0.9747914,0.00001384046,0.000009507458,0.01991849,0.0001757965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007967669,0.0001057061,0.9858485,0.0009470997,0.0001388092,0.0003509354,0.000001685312,0.0004223309,0.004217263],"genre_scores_gemma":[0.9686509,0.000002212823,0.02958681,0.0009609794,0.000142588,0.00001537348,0.00006356456,0.000009820964,0.0005677311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9606832,"threshold_uncertainty_score":0.9998327,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006100062,0.0001676214,0.0001760611,0.0002552771,0.0001934714,0.00115394,0.000469384,0.00008381435,0.000001284031],"category_scores_gemma":[0.0006864557,0.0001489771,0.00003129127,0.000660646,0.00004203045,0.008841286,0.0001475634,0.0001758286,0.00007374894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388423,"about_ca_system_score_gemma":0.0001890759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001566351,"about_ca_topic_score_gemma":1.504029e-7,"domain_scores_codex":[0.9981592,0.00006812799,0.0006315282,0.0001916249,0.00064577,0.0003037684],"domain_scores_gemma":[0.9982119,0.00005878915,0.0005000603,0.0003121405,0.0007154971,0.000201624],"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":[0.00006956046,0.000311449,0.002837243,0.001675547,0.00005803497,0.00003725452,0.05330075,0.1468003,0.0001442708,0.5064913,0.05867814,0.2295962],"study_design_scores_gemma":[0.0003184941,0.00007770128,0.00003629442,0.0001110724,0.000004540357,0.0002226738,0.00064419,0.9930332,0.0001134675,0.0003524507,0.004895522,0.0001903843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001601855,0.00008462458,0.9902751,0.0006812838,0.00105101,0.0003439028,0.000001527997,0.001081457,0.004879282],"genre_scores_gemma":[0.9259959,0.000001468152,0.07315734,0.0004930396,0.0001119354,0.0000906589,0.00001872899,0.00001141229,0.0001195154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9243941,"threshold_uncertainty_score":0.9998829,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0003576505,0.0001680646,0.0001799879,0.0001711634,0.000471881,0.001933272,0.0004040986,0.00009190116,0.000004244584],"category_scores_gemma":[0.0004354772,0.0001636984,0.00005784905,0.000567029,0.00001903815,0.01467461,0.00006605362,0.0002029161,0.0001300854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005246994,"about_ca_system_score_gemma":0.0001153151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003921471,"about_ca_topic_score_gemma":1.243794e-7,"domain_scores_codex":[0.9984164,0.00005386982,0.0007231807,0.0001245669,0.0004169992,0.0002649517],"domain_scores_gemma":[0.9985322,0.00004946171,0.0006519157,0.0001290506,0.0004933123,0.0001440007],"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":[0.00003224464,0.000005851356,0.0001228071,0.0006401058,0.000006930029,1.809598e-7,0.0200637,0.7893195,0.0001387689,0.01521182,0.001804596,0.1726535],"study_design_scores_gemma":[0.0005008761,0.00007421202,0.00005856628,0.00003341616,0.000004167752,0.000008020353,0.001210879,0.9008181,0.00007834216,0.00003915511,0.09699608,0.0001781623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008406606,0.00004533067,0.9916036,0.001881879,0.0003310893,0.0005113322,0.00000360996,0.0007196766,0.004062844],"genre_scores_gemma":[0.9833435,0.000004397125,0.01283321,0.003319603,0.0001035181,0.00009778428,0.0001720094,0.000009730975,0.000116207],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825029,"threshold_uncertainty_score":0.9991066,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003021252,0.0002074536,0.0001849223,0.00009852849,0.001729969,0.00150032,0.001122488,0.0000856109,0.000002288318],"category_scores_gemma":[0.00009229948,0.0001321577,0.00004976018,0.0007000806,0.0001267661,0.006097407,0.0001075992,0.0002283698,0.0001161905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004533248,"about_ca_system_score_gemma":0.0002872272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004265708,"about_ca_topic_score_gemma":0.000004660129,"domain_scores_codex":[0.9980791,0.00004873165,0.0006195687,0.0002156429,0.0006030728,0.0004339308],"domain_scores_gemma":[0.9984139,0.00005654168,0.0004562385,0.000442871,0.0004995621,0.0001309322],"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":[0.00009689452,0.0001571057,0.01509216,0.00285505,0.00007225914,0.00006961192,0.03731124,0.004708397,0.0001720448,0.189522,0.02304991,0.7268934],"study_design_scores_gemma":[0.0008073,0.0001586723,0.01679069,0.000238591,0.0000123261,0.00247743,0.00162834,0.9181859,0.001029493,0.0032983,0.05439626,0.0009766953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05186611,0.0006437511,0.9309296,0.003776869,0.001491043,0.0006499708,0.000004243909,0.0009511632,0.009687223],"genre_scores_gemma":[0.9982122,0.00002359892,0.000820481,0.0005711128,0.00009467729,0.00005853979,0.000005474727,0.000007107933,0.0002067941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9463461,"threshold_uncertainty_score":0.9995697,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002259785,0.0001648017,0.0001691252,0.0002760588,0.0002076376,0.0007683281,0.0003727463,0.00007537618,0.000006161793],"category_scores_gemma":[0.00003122635,0.0001312535,0.00003868964,0.0005211565,0.00004483607,0.005067618,0.00009359163,0.0001541262,0.0001846289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009806466,"about_ca_system_score_gemma":0.00005175345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005893705,"about_ca_topic_score_gemma":0.000008784565,"domain_scores_codex":[0.9984928,0.00005438234,0.0005483054,0.0001970307,0.0003730869,0.0003343932],"domain_scores_gemma":[0.9991469,0.00001337651,0.0002788903,0.0002211099,0.000259645,0.00008003069],"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":[0.00008227142,0.0001408018,0.003040287,0.0009171539,0.00001692253,0.000007976911,0.032306,0.001509895,0.004231619,0.001170214,0.003340845,0.953236],"study_design_scores_gemma":[0.0004837467,0.0000622178,0.002110928,0.0003167462,0.000002504278,0.00003865222,0.0007267551,0.9884369,0.004372457,0.00004718592,0.003158721,0.0002431333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8139597,0.0002668162,0.1786825,0.0005074971,0.002950715,0.0008174248,0.000008814984,0.0004390919,0.002367465],"genre_scores_gemma":[0.99771,0.0000036231,0.00179163,0.0002733946,0.00007628586,0.00005185529,0.00002502871,0.000005504502,0.00006271309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.986927,"threshold_uncertainty_score":0.7409006,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003709342,0.0002352642,0.0002373253,0.0003205022,0.0004947213,0.000979458,0.0006885989,0.000108488,0.000004415297],"category_scores_gemma":[0.0002570219,0.0002210834,0.00005429094,0.0008300742,0.00009180659,0.004002894,0.00008882546,0.00009370263,0.00002295079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535031,"about_ca_system_score_gemma":0.0001620872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076733,"about_ca_topic_score_gemma":3.278502e-7,"domain_scores_codex":[0.9980615,0.0000441304,0.0008001485,0.0003009095,0.0004053446,0.0003879367],"domain_scores_gemma":[0.9973581,0.00007121187,0.0006432846,0.0004220182,0.001369808,0.0001355901],"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":[0.00004590099,0.00006301144,0.00001472189,0.000381942,0.00001885456,5.314538e-7,0.004302114,0.9316582,0.0001425887,0.04111437,0.002771439,0.01948634],"study_design_scores_gemma":[0.0004851334,0.0002013199,0.00002544153,0.0001614027,0.000009879445,0.00005136108,0.00008383003,0.9976058,0.000356826,0.0001957928,0.0005703549,0.0002528811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000326094,0.00005515337,0.9949181,0.0003720227,0.00169708,0.001303788,0.000007898361,0.0009371894,0.000382695],"genre_scores_gemma":[0.7961357,0.00000129975,0.2025311,0.000469617,0.0002290507,0.0004639179,0.00005106004,0.00001896998,0.00009930479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7958096,"threshold_uncertainty_score":0.9444937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}