{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":35,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":35,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"5648e54e999c","filters":{"venue":"Uncertainty in Artificial Intelligence"}},"results":[{"id":"W9932698","doi":"10.48550/arxiv.1205.2619","title":"Regret-based Reward Elicitation for Markov Decision Processes","year":2012,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":61,"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":"Regret; Markov decision process; Computer science; Preference elicitation; Function (biology); Minimax; Preference; Markov process; Markov chain; Mathematical optimization; Machine learning; Mathematics; Economics; Microeconomics","authors":[{"name":"Kevin Regan","is_ca":true},{"name":"Craig Boutilier","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06076316977610513,"gpt":0.3316740532104062,"spread":0.2709108834343011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01143313,0.001507925,0.001577027,0.0008216391,0.0006791665,0.002103598,0.001175678,0.001724571,0.002735811],"category_scores_gemma":[0.04198601,0.0009217853,0.001249803,0.0009218327,0.001741206,0.002667736,0.00255353,0.003180852,0.0004062632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003154615,"about_ca_system_score_gemma":0.002566503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002232675,"about_ca_topic_score_gemma":0.002337337,"domain_scores_codex":[0.9872334,0.008725257,0.0006006183,0.0009218833,0.001995203,0.000523652],"domain_scores_gemma":[0.9661788,0.02893035,0.001899513,0.001341015,0.0009995678,0.0006508022],"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":[0.0003249433,0.0001318848,0.0007171255,0.0002034964,0.00006373184,0.0001045988,0.0002231917,0.8742864,0.001652185,0.09275765,0.0008459125,0.02868896],"study_design_scores_gemma":[0.00003686524,0.00006065554,0.0001073743,0.00002378733,0.000009743308,0.00001861084,0.00001595092,0.9283013,0.0008517997,0.07011199,0.000448158,0.00001375172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01866696,0.0003169711,0.9776177,0.0004422876,0.00001983315,0.0001288502,0.0001125647,0.00027109,0.002423646],"genre_scores_gemma":[0.7222089,0.0005815595,0.2736367,0.0003022779,0.00006794183,0.0005904814,0.0003568036,0.0001388138,0.002116654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01143313,"threshold_uncertainty_score":0.06046492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161202741","doi":"10.5555/1036843.1036873","title":"From fields to trees","year":2004,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","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":"University of British Columbia","funders":"","keywords":"Gibbs sampling; Markov chain Monte Carlo; Graphical model; Tree (set theory); Sampling (signal processing); Computer science; Focus (optics); Markov chain; Importance sampling; Posterior probability; Algorithm; Mathematics; Belief propagation; Statistics; Artificial intelligence; Bayesian probability; Monte Carlo method; Machine learning; Combinatorics","authors":[{"name":"Firas Hamze","is_ca":true},{"name":"Nando de Freitas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04739542792282484,"gpt":0.3219355585509258,"spread":0.274540130628101,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002693632,0.0007473407,0.001036635,0.002170071,0.001076214,0.002397758,0.001693661,0.001870382,0.007348331],"category_scores_gemma":[0.01956465,0.0009683582,0.001390755,0.002193641,0.00269904,0.005321384,0.002590512,0.002929278,0.001258716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001865375,"about_ca_system_score_gemma":0.001572107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004923123,"about_ca_topic_score_gemma":0.004238567,"domain_scores_codex":[0.9981632,0.0008307121,0.00008022545,0.0003352838,0.0004549392,0.0001358049],"domain_scores_gemma":[0.9922454,0.005948545,0.0004185723,0.0007719699,0.0004263971,0.0001890645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003769356,0.00002478751,0.0004909578,0.0001062798,0.00002931686,0.00004037778,0.0001769958,0.1683224,0.0004923986,0.7614397,0.003711224,0.06512783],"study_design_scores_gemma":[0.00001558681,0.00001071666,0.00009722353,0.00003249622,0.000007287635,0.00002691294,0.00001268314,0.2511586,0.0002536615,0.7420385,0.006334193,0.00001210202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002222463,0.0003716046,0.9952621,0.0002668574,0.0000326703,0.00002289415,0.00007841922,0.0001790145,0.001563916],"genre_scores_gemma":[0.1355969,0.001893766,0.8548822,0.0007715953,0.0002940032,0.0003550288,0.0005620466,0.0004264167,0.0052181],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007348331,"threshold_uncertainty_score":0.02458262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964434332","doi":"","title":"Low Frequency Adversarial Perturbation","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":18,"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":"Adversarial system; Computer science; Black box; Image (mathematics); Perturbation (astronomy); Cloud computing; Frequency domain; Transformation (genetics); Artificial intelligence; Theoretical computer science; Computer vision; Algorithm","authors":[{"name":"Chuan Guo","is_ca":true},{"name":"Jared S. Frank","is_ca":false},{"name":"Kilian Q. Weinberger","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02908829838875739,"gpt":0.2972562858240615,"spread":0.2681679874353041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001036286,0.001059746,0.00102145,0.0004652585,0.0004791015,0.0009486263,0.001240976,0.001347545,0.004262742],"category_scores_gemma":[0.005389767,0.0003161495,0.0005862114,0.0003918103,0.001496274,0.00195184,0.00244135,0.002203305,0.0008310216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007488971,"about_ca_system_score_gemma":0.0005245146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008388974,"about_ca_topic_score_gemma":0.0008412664,"domain_scores_codex":[0.9989737,0.0003389625,0.00003159431,0.0001978068,0.0003156021,0.0001424314],"domain_scores_gemma":[0.9972752,0.001753393,0.0001995141,0.0005524317,0.0001392575,0.00008031921],"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":[0.0003517515,0.0001636604,0.0009163631,0.0001405031,0.0001036632,0.0003086327,0.00008596657,0.7764242,0.02569561,0.09586233,0.008232464,0.09171478],"study_design_scores_gemma":[0.00001501319,0.00006758884,0.0001582724,0.00000989516,0.000009810321,0.0001108028,0.00001839585,0.9594311,0.004797505,0.03334489,0.002023892,0.00001290663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02403047,0.0003207396,0.9673485,0.0004913312,0.00007220988,0.0001025613,0.0001174013,0.0007847078,0.006732159],"genre_scores_gemma":[0.8682178,0.0003183878,0.1238668,0.0005415473,0.0001069012,0.000172038,0.0002660237,0.0001545536,0.006356018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004262742,"threshold_uncertainty_score":0.01426029,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2401533533","doi":"","title":"Off-policy TD(λ) with a true online equivalence","year":2014,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Stability and Control of Uncertain Systems","field":"Engineering","cited_by":17,"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":"Online algorithm; Computer science; Equivalence (formal languages); Generalization; TRACE (psycholinguistics); Function approximation; Online learning; Algorithm; Function (biology); Artificial intelligence; Machine learning; Mathematics; Discrete mathematics; Artificial neural network","authors":[{"name":"Hado van Hasselt","is_ca":true},{"name":"A. Rupam Mahmood","is_ca":true},{"name":"Richard S. Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02643517356787296,"gpt":0.2660537146128079,"spread":0.2396185410449349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002824217,0.0009890335,0.001344173,0.0005971142,0.0005562269,0.001918986,0.002507384,0.002296295,0.005900078],"category_scores_gemma":[0.01437617,0.0005575622,0.0009044041,0.0005795219,0.001674892,0.003153305,0.003358632,0.004012543,0.0009393892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00166384,"about_ca_system_score_gemma":0.002955783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004038473,"about_ca_topic_score_gemma":0.002759242,"domain_scores_codex":[0.9978834,0.0005427739,0.0001329873,0.0005879776,0.0006117551,0.0002411006],"domain_scores_gemma":[0.9942638,0.003274362,0.0003209987,0.001065788,0.0008210267,0.0002539687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004935339,0.0004319995,0.001775199,0.0002037191,0.00007596559,0.0001562832,0.0002672194,0.454337,0.005010171,0.1320229,0.004937098,0.4002889],"study_design_scores_gemma":[0.00003825256,0.0001125214,0.0001069807,0.0000104769,0.000008723946,0.00004693538,0.00001402645,0.970332,0.001840178,0.02624157,0.001237448,0.00001092155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009696391,0.00008326022,0.9866533,0.0001968172,0.00007352125,0.00007356165,0.0000479349,0.0005924188,0.002582791],"genre_scores_gemma":[0.5007933,0.0001121333,0.4912491,0.0006614611,0.0001204393,0.0002631058,0.0002715546,0.0003525582,0.006176333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005900078,"threshold_uncertainty_score":0.01973778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2772489041","doi":"","title":"Triply Stochastic Gradients on Multiple Kernel Learning.","year":2017,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Kernel (algebra); Artificial intelligence; Multiple kernel learning; Kernel method; Mathematics; Support vector machine; Combinatorics","authors":[{"name":"Xiang Li","is_ca":false},{"name":"Bin Gu","is_ca":false},{"name":"Shuang Ao","is_ca":true},{"name":"Huaimin Wang","is_ca":false},{"name":"Charles X. Ling","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04788244141461452,"gpt":0.3144047320931431,"spread":0.2665222906785286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00239912,0.0006293347,0.001099578,0.0007629135,0.0004261715,0.001194475,0.001621389,0.001330958,0.003361021],"category_scores_gemma":[0.01113712,0.000430258,0.0004883524,0.0009186088,0.001336458,0.002974645,0.00214,0.001935455,0.0007585634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00124129,"about_ca_system_score_gemma":0.0009457565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003091289,"about_ca_topic_score_gemma":0.003012759,"domain_scores_codex":[0.9990112,0.0005190019,0.00005212845,0.0001168341,0.0002014623,0.00009931309],"domain_scores_gemma":[0.9965469,0.002073532,0.0001993478,0.0003618571,0.0006338074,0.0001846312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002936061,0.0001262624,0.001138783,0.0001766723,0.0001318179,0.00009438039,0.0001085938,0.4986131,0.00140468,0.3248687,0.01052109,0.1625224],"study_design_scores_gemma":[0.000008574297,0.00002054647,0.0001126547,0.000009716729,0.000006968215,0.00001401382,0.000006873543,0.9387878,0.0003377506,0.0597325,0.000955962,0.000006661596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01870979,0.00159279,0.9747083,0.0008557499,0.0001508916,0.00003290533,0.00006587725,0.0002515776,0.003632034],"genre_scores_gemma":[0.6895099,0.001255504,0.2908941,0.000350175,0.0003254329,0.0001403929,0.0003854793,0.000243761,0.01689534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003361021,"threshold_uncertainty_score":0.01268792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914852071","doi":"","title":"Subsampled Stochastic Variance-Reduced Gradient Langevin Dynamics.","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Langevin dynamics; Variance (accounting); Dynamics (music); Statistical physics; Computer science; Stochastic process; Langevin equation; Stochastic dynamics; Physics; Mathematics; Statistics; Economics","authors":[{"name":"Difan Zou","is_ca":false},{"name":"Pan Xu","is_ca":true},{"name":"Quanquan Gu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1252566851254776,"gpt":0.383399165742813,"spread":0.2581424806173354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167225,0.0005421837,0.001065908,0.0005402507,0.0003562407,0.00095097,0.001500978,0.001352326,0.002829257],"category_scores_gemma":[0.007852943,0.0004775551,0.0006574619,0.0004394741,0.001292459,0.001879145,0.001342761,0.001741342,0.0003733551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009499146,"about_ca_system_score_gemma":0.001043256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004875422,"about_ca_topic_score_gemma":0.004856917,"domain_scores_codex":[0.9995139,0.000197915,0.00001796022,0.00007232423,0.0001462677,0.00005154278],"domain_scores_gemma":[0.9980896,0.00122872,0.0001708283,0.0001935685,0.0002088964,0.0001082961],"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":[0.0001137398,0.00005878827,0.0007320279,0.0001078889,0.00007821915,0.00008147432,0.00008702333,0.6139422,0.001316015,0.3682118,0.002961413,0.01230943],"study_design_scores_gemma":[0.000006306149,0.000006749232,0.00007971343,0.000005489359,0.00000425081,0.00000796018,0.000004316724,0.9584132,0.0001413559,0.04087219,0.0004520883,0.000006273572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04199002,0.001186865,0.9453146,0.001162789,0.0003070191,0.00006545104,0.0003194865,0.0003844516,0.009269261],"genre_scores_gemma":[0.8637325,0.0006039414,0.1244899,0.0003287566,0.0001490739,0.0002104063,0.0004854945,0.0002451819,0.009754793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004875422,"threshold_uncertainty_score":0.009694099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2398850217","doi":"","title":"Off-policy learning based on weighted importance sampling with linear computational complexity","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":15,"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":"Component (thermodynamics); Computational complexity theory; Computer science; Sampling (signal processing); Measure (data warehouse); Stochastic gradient descent; Importance sampling; Algorithm; Function (biology); Mathematical optimization; Artificial intelligence; Mathematics; Machine learning; Data mining; Artificial neural network; Statistics; Monte Carlo method","authors":[{"name":"A. Rupam Mahmood","is_ca":true},{"name":"Richard S. Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09631687283916708,"gpt":0.3443424134911935,"spread":0.2480255406520264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004682454,0.00129556,0.002108846,0.00109197,0.0007243711,0.001505434,0.002783478,0.00145849,0.002817134],"category_scores_gemma":[0.02049113,0.0007692131,0.000810058,0.001062797,0.001685241,0.002680792,0.002435138,0.002984647,0.00051095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001732054,"about_ca_system_score_gemma":0.002594558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004443224,"about_ca_topic_score_gemma":0.004288202,"domain_scores_codex":[0.9976214,0.001054281,0.0001242273,0.0003342401,0.0006559124,0.0002099986],"domain_scores_gemma":[0.9882956,0.008901855,0.0005006,0.001080917,0.0009074148,0.0003136755],"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":[0.0002859172,0.0002579346,0.001630259,0.0001226053,0.00007240824,0.00009131889,0.0001133905,0.7394483,0.001688914,0.05577455,0.001360337,0.1991539],"study_design_scores_gemma":[0.00001173488,0.00002410743,0.00003851313,0.000004607623,0.000003760725,0.00001001865,0.000004015702,0.9899906,0.0004075667,0.009362892,0.000139167,0.000003017482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01053765,0.00009537349,0.987799,0.0001002615,0.00002469382,0.00008851296,0.00001549372,0.0004069948,0.000931919],"genre_scores_gemma":[0.5699551,0.0002078738,0.4259922,0.0003197989,0.00008961504,0.0004555048,0.0002085196,0.0002144437,0.002556933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004682454,"threshold_uncertainty_score":0.02476346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3090054376","doi":"","title":"Amortized Bayesian Optimization over Discrete Spaces","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Bayesian probability; Amortized analysis; Computer science; Bayesian optimization; Mathematical optimization; Mathematics; Artificial intelligence; Data structure; Programming language","authors":[{"name":"Kevin Swersky","is_ca":false},{"name":"Yulia Rubanova","is_ca":true},{"name":"David Dohan","is_ca":false},{"name":"Kevin J. Murphy","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02776626218202575,"gpt":0.2920423037285984,"spread":0.2642760415465726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009830501,0.001876873,0.003384587,0.001636761,0.001067482,0.004275983,0.003680432,0.004555513,0.00754812],"category_scores_gemma":[0.02594683,0.002183906,0.001709588,0.002795308,0.003676764,0.007016312,0.005191907,0.00486866,0.0007881859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003008708,"about_ca_system_score_gemma":0.002611737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005267889,"about_ca_topic_score_gemma":0.004103299,"domain_scores_codex":[0.9947732,0.003185573,0.0002588711,0.0005834644,0.0009118874,0.0002869503],"domain_scores_gemma":[0.9810141,0.01573984,0.0005677806,0.001237122,0.0009683618,0.0004729271],"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":[0.0002460523,0.0001063653,0.000430682,0.0002142709,0.0001578629,0.00005622429,0.00008412115,0.7030598,0.0003798947,0.2592361,0.004349361,0.03167925],"study_design_scores_gemma":[0.00002200898,0.00001678481,0.00004819322,0.0000172391,0.00001306574,0.00001233874,0.000006271638,0.8703195,0.0001268638,0.128844,0.0005646448,0.000009010305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008720832,0.0007761082,0.9860394,0.001242371,0.000118429,0.00004530296,0.0001926299,0.0002256552,0.002639277],"genre_scores_gemma":[0.4044394,0.001354343,0.5769988,0.0009622893,0.0007902881,0.0005696761,0.001099945,0.0005909433,0.01319434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009830501,"threshold_uncertainty_score":0.05198932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963001956","doi":"","title":"Bayesian hyperparameter optimization for ensemble learning","year":2016,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université Laval","funders":"","keywords":"Hyperparameter; Bayesian optimization; Hyperparameter optimization; Ensemble learning; Computer science; Machine learning; Artificial intelligence; Bayesian probability; Greedy algorithm; Mathematical optimization; Algorithm; Mathematics; Support vector machine","authors":[{"name":"Julien-Charles Lévesque","is_ca":true},{"name":"Christian Gagné","is_ca":true},{"name":"Robert Sabourin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04312508995708945,"gpt":0.3025274425148194,"spread":0.25940235255773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005252288,0.001999753,0.00270278,0.001681189,0.000861116,0.001674791,0.00217045,0.002095991,0.001814405],"category_scores_gemma":[0.01302146,0.001169326,0.001764512,0.001478098,0.001198164,0.002510317,0.002302411,0.003016171,0.0008090656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128818,"about_ca_system_score_gemma":0.001320785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003372898,"about_ca_topic_score_gemma":0.002925391,"domain_scores_codex":[0.9966883,0.001927488,0.0001416053,0.0004653924,0.0006256897,0.0001515699],"domain_scores_gemma":[0.9956175,0.00288471,0.0002896675,0.0005171195,0.0005691745,0.0001217671],"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":[0.00004077263,0.00003078108,0.0005023312,0.00004550564,0.0001409307,0.00002471127,0.0000479306,0.9349021,0.0008301379,0.01290267,0.001048248,0.04948386],"study_design_scores_gemma":[0.000004131307,0.00001200555,0.00005442247,0.000009124602,0.00001177094,0.000008313886,0.000004634007,0.9872247,0.000304242,0.0119297,0.0004290683,0.000007986889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003127737,0.0002993081,0.9958047,0.0000824569,0.00001482454,0.00001720131,0.00002676738,0.0001813852,0.000445681],"genre_scores_gemma":[0.3390102,0.0009718343,0.655434,0.0003517224,0.00026488,0.0005452828,0.0007600691,0.0004952514,0.002166789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005252288,"threshold_uncertainty_score":0.02777708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809487708","doi":"","title":"Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"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":"Variance (accounting); Temporal difference learning; Computer science; Reinforcement learning; Mean squared error; Lookup table; Function (biology); Algorithm; Artificial intelligence; Statistics; Mathematics","authors":[{"name":"Craig Sherstan","is_ca":true},{"name":"Brendan Bennett","is_ca":true},{"name":"Dylan R. Ashley","is_ca":true},{"name":"Kenny Young","is_ca":true},{"name":"Adam White","is_ca":true},{"name":"Martha White","is_ca":false},{"name":"Richard S. Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1008153029018901,"gpt":0.3667202816540406,"spread":0.2659049787521505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053409,0.001083667,0.001183979,0.0009732767,0.0003456267,0.001517429,0.002033551,0.001379444,0.002254158],"category_scores_gemma":[0.03270878,0.0004434911,0.0006960768,0.0006670312,0.00102828,0.002932574,0.002642686,0.002474428,0.0005250929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005549,"about_ca_system_score_gemma":0.001726382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004060122,"about_ca_topic_score_gemma":0.004204431,"domain_scores_codex":[0.9980801,0.0007154863,0.0001229269,0.0003858857,0.0006004137,0.00009517009],"domain_scores_gemma":[0.9808225,0.01506727,0.000829485,0.001277659,0.001632865,0.0003703152],"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":[0.0007883848,0.0003066375,0.009143627,0.0003544764,0.0003107862,0.00007392641,0.0002900859,0.5213302,0.003762903,0.03273578,0.002100214,0.4288029],"study_design_scores_gemma":[0.00003501793,0.00007112028,0.0006451336,0.00002509493,0.00002082086,0.00004418971,0.00002344178,0.9880095,0.001599989,0.008978442,0.0005303762,0.00001681413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02806111,0.0008519277,0.9682406,0.0002671437,0.00007629362,0.00007144466,0.00005078772,0.0004688063,0.001911915],"genre_scores_gemma":[0.4526277,0.0005982309,0.5415729,0.0002866102,0.0001343039,0.0002345518,0.0003310948,0.0003559807,0.003858601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0053409,"threshold_uncertainty_score":0.02824575,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089723243","doi":"","title":"Learning Intrinsic Rewards as a Bi-Level Optimization Problem","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Intrinsic motivation; Mathematical optimization; Mathematics; Psychology; Social psychology","authors":[{"name":"Bradly C. Stadie","is_ca":false},{"name":"Lunjun Zhang","is_ca":true},{"name":"Jimmy Ba","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06927971827994504,"gpt":0.2923596390382754,"spread":0.2230799207583304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003017681,0.0009159143,0.002488755,0.0007877587,0.0005763099,0.003176725,0.002646972,0.004620814,0.006954757],"category_scores_gemma":[0.007924285,0.001120555,0.0009335757,0.001117602,0.002049184,0.003477801,0.003594024,0.003670876,0.0008517234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002264591,"about_ca_system_score_gemma":0.001886153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002897034,"about_ca_topic_score_gemma":0.00262548,"domain_scores_codex":[0.9984745,0.0005902721,0.00006842547,0.0003062119,0.0003546251,0.0002059469],"domain_scores_gemma":[0.9959875,0.0029453,0.0002623317,0.0001900053,0.000333149,0.0002817982],"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":[0.00008281993,0.00007457232,0.0003800557,0.000106733,0.00006118634,0.00006493591,0.00006034744,0.8974233,0.0005939419,0.08479225,0.001334747,0.0150251],"study_design_scores_gemma":[0.00001248088,0.00001771422,0.00004535299,0.000007193823,0.000005565926,0.000005525615,0.000004455778,0.9801939,0.00007962537,0.01940156,0.0002222576,0.000004391628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02136815,0.000311094,0.9715674,0.001010004,0.00005280093,0.00005524568,0.00009724905,0.0001831777,0.005354892],"genre_scores_gemma":[0.7245764,0.0004193947,0.256562,0.000497216,0.0001665414,0.0005575037,0.0002569318,0.0002182181,0.01674581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006954757,"threshold_uncertainty_score":0.02326602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3090466896","doi":"","title":"Differentially Private Small Dataset Release Using Random Projections","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"","keywords":"Computer science","authors":[{"name":"Lovedeep Gondara","is_ca":true},{"name":"Ke Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1354467866766076,"gpt":0.3239428926810161,"spread":0.1884961060044085,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01031636,0.001228003,0.003395276,0.0009825367,0.00153884,0.004550034,0.00327099,0.002571796,0.004692514],"category_scores_gemma":[0.03706693,0.001170583,0.002113286,0.002201716,0.003208675,0.008926692,0.008948136,0.004317061,0.00115146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002049011,"about_ca_system_score_gemma":0.002779937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007831346,"about_ca_topic_score_gemma":0.0008495463,"domain_scores_codex":[0.9883456,0.0052532,0.0005823766,0.001696757,0.003127524,0.00099452],"domain_scores_gemma":[0.9606337,0.02388534,0.001235195,0.012232,0.001186834,0.0008269676],"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":[0.00597604,0.0004599479,0.002477617,0.000645083,0.0005576378,0.000945129,0.0007319438,0.3286254,0.01742518,0.4606521,0.0204345,0.1610695],"study_design_scores_gemma":[0.0002082248,0.0001769315,0.0004495004,0.00004124,0.0000737675,0.0002830617,0.00008786882,0.6799432,0.007931264,0.3077073,0.003048862,0.00004874427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03635912,0.000795395,0.954354,0.002714912,0.0001963904,0.00019226,0.0009665557,0.001281203,0.003140111],"genre_scores_gemma":[0.834903,0.0006348884,0.1536198,0.0009085505,0.0004165165,0.0004790709,0.001613987,0.000356997,0.007067122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01031636,"threshold_uncertainty_score":0.05455875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966820259","doi":"","title":"Problem-dependent Regret Bounds for Online Learning with Feedback Graphs.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Computer science; Online learning; Theoretical computer science; Artificial intelligence; Machine learning; World Wide Web","authors":[{"name":"Bingshan Hu","is_ca":true},{"name":"Nishant A. Mehta","is_ca":true},{"name":"Jianping Pan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1217124348623598,"gpt":0.4182077194194262,"spread":0.2964952845570664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01182457,0.003051182,0.002704576,0.001869493,0.001219166,0.003549234,0.004140805,0.003241432,0.007954157],"category_scores_gemma":[0.07505142,0.0009415954,0.001227369,0.00246355,0.003121562,0.006683354,0.003867263,0.00670093,0.001252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004561233,"about_ca_system_score_gemma":0.003221956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003590128,"about_ca_topic_score_gemma":0.003621013,"domain_scores_codex":[0.9929463,0.003497269,0.0002135618,0.0007915404,0.001644657,0.0009067183],"domain_scores_gemma":[0.9180083,0.07217471,0.002207767,0.00312473,0.002892061,0.001592552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009193343,0.0004447864,0.001209143,0.0007956593,0.0002409338,0.0001172802,0.0001978672,0.7302799,0.001045647,0.1888976,0.01814136,0.05771051],"study_design_scores_gemma":[0.0000448684,0.00008416099,0.0002971035,0.0001221628,0.00004916536,0.00004469194,0.00003055627,0.8679879,0.0004225148,0.1295671,0.001332116,0.00001767778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02373433,0.009264614,0.9388962,0.00377538,0.0005817445,0.0002615108,0.0009438162,0.0007456971,0.02179665],"genre_scores_gemma":[0.7842795,0.00693384,0.189327,0.002300392,0.001289621,0.0009891106,0.001806625,0.0007143121,0.01235958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01182457,"threshold_uncertainty_score":0.06253499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2402930259","doi":"","title":"Intelligent affect: rational decision making for socially aligned agents","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Evolutionary Game Theory and Cooperation","field":"Social Sciences","cited_by":5,"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":"Affect (linguistics); Computer science; Probabilistic logic; Planner; Deception; Action (physics); Encoding (memory); Cognition; Monte Carlo tree search; Function (biology); Range (aeronautics); Artificial intelligence; Human–computer interaction; Monte Carlo method; Social psychology; Psychology; Mathematics; Engineering","authors":[{"name":"Nabiha Asghar","is_ca":true},{"name":"Jesse Hoey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1292949818094062,"gpt":0.4102366722908574,"spread":0.2809416904814511,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002264136,0.0006698942,0.0004500448,0.0004316198,0.0008562551,0.003162262,0.001200324,0.001746937,0.004427741],"category_scores_gemma":[0.008207993,0.0003228158,0.0006350042,0.0004090852,0.003141133,0.00280913,0.00201015,0.001293435,0.0005280924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00128152,"about_ca_system_score_gemma":0.001315721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002120927,"about_ca_topic_score_gemma":0.001555164,"domain_scores_codex":[0.9987367,0.0007205669,0.00005174187,0.0001813459,0.0002177589,0.00009181945],"domain_scores_gemma":[0.9976596,0.0014843,0.0002883018,0.0002110211,0.0001704163,0.000186409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009295675,0.00004219087,0.0009786494,0.00009782626,0.00005565171,0.0002268472,0.0007672909,0.1971786,0.001337391,0.7741951,0.002076177,0.02295127],"study_design_scores_gemma":[0.00003027962,0.0000320701,0.0002453752,0.00002489489,0.00001582058,0.00004994103,0.0001584509,0.3779166,0.0004002454,0.6150615,0.006045255,0.00001967332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04377419,0.0004863434,0.9115193,0.003831797,0.0001397458,0.0001353483,0.0001326893,0.0003388737,0.03964165],"genre_scores_gemma":[0.8080266,0.0004090542,0.1845642,0.0003081272,0.0000878903,0.00029014,0.0001042887,0.0000631804,0.006146511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004427741,"threshold_uncertainty_score":0.01481223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089673743","doi":"","title":"C-MI-GAN : Estimation of Conditional Mutual Information using MinMax formulation","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"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":"Mutual information; Estimator; Minimax; Conditional independence; Conditional mutual information; Computer science; Mathematical optimization; Focus (optics); Independence (probability theory); Estimation; Conditional expectation; Artificial intelligence; Machine learning; Mathematics; Statistics; Engineering","authors":[{"name":"Arnab Kumar Mondal","is_ca":true},{"name":"Arnab Bhattacharjee","is_ca":false},{"name":"Sudipto Mukherjee","is_ca":false},{"name":"Himanshu Asnani","is_ca":false},{"name":"Sreeram Kannan","is_ca":false},{"name":"Prathosh AP","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05566346586866754,"gpt":0.3117709213048471,"spread":0.2561074554361796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005197969,0.00177247,0.001938103,0.001146589,0.0005007295,0.001546479,0.003441525,0.001788372,0.003761086],"category_scores_gemma":[0.01399243,0.0008128185,0.001079043,0.001035537,0.001864325,0.002508892,0.003002052,0.003904469,0.001037518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00132547,"about_ca_system_score_gemma":0.001769511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00286888,"about_ca_topic_score_gemma":0.003502125,"domain_scores_codex":[0.9976166,0.001196746,0.00008272992,0.0004734421,0.0004756322,0.0001548282],"domain_scores_gemma":[0.993536,0.00462317,0.0004358116,0.0006957903,0.0005358711,0.000173347],"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":[0.000275939,0.0001409755,0.002724814,0.000247803,0.0002623437,0.0001633772,0.0001314209,0.766364,0.003665231,0.09171764,0.009724064,0.1245824],"study_design_scores_gemma":[0.000005428009,0.00002240446,0.0001939324,0.0000153425,0.000008027987,0.0000355866,0.000005510849,0.9818482,0.000918959,0.01621634,0.0007186317,0.00001152664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005913701,0.0004489921,0.9903011,0.0002781805,0.00003360998,0.00006957438,0.0002041853,0.0007438862,0.00200673],"genre_scores_gemma":[0.5025173,0.0009197189,0.4843141,0.001152638,0.0003094614,0.0007570469,0.002411194,0.0009997346,0.006618893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005197969,"threshold_uncertainty_score":0.02748984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2772322972","doi":"","title":"Holographic Feature Representations of Deep Networks.","year":2017,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Holography; Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Computer vision; Computer graphics (images); Optics; Physics","authors":[{"name":"Martin Zinkevich","is_ca":false},{"name":"Alex Davies","is_ca":false},{"name":"Dale Schuurmans","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04953838544420267,"gpt":0.3293500301314125,"spread":0.2798116446872098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003278071,0.0004268499,0.0004732916,0.0005513508,0.0002105397,0.0009853992,0.001083155,0.0008291882,0.004121102],"category_scores_gemma":[0.002040293,0.0003195918,0.0003425571,0.0005896543,0.0006669002,0.002494247,0.001109827,0.001255098,0.0006965545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007507084,"about_ca_system_score_gemma":0.0005006162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003384846,"about_ca_topic_score_gemma":0.004652044,"domain_scores_codex":[0.9998245,0.00004635482,0.00001092965,0.00004322739,0.000042306,0.0000327252],"domain_scores_gemma":[0.9996108,0.0001479489,0.00006306823,0.00008593399,0.00006202096,0.00003032425],"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":[0.0002509998,0.0000998157,0.001396764,0.000246084,0.0001214124,0.0001024982,0.0001138591,0.3328041,0.008121789,0.3344093,0.01652787,0.3058055],"study_design_scores_gemma":[0.00000993388,0.00002957137,0.0004395217,0.00002175861,0.00001348507,0.00002813302,0.00001751149,0.849765,0.001992259,0.1455249,0.002149043,0.000008857945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0462372,0.002029468,0.9373625,0.001355238,0.0002757614,0.00003177951,0.001330026,0.001002661,0.01037524],"genre_scores_gemma":[0.9119088,0.0009830644,0.07408943,0.0003100763,0.0001725964,0.00007506916,0.001246929,0.0001295604,0.01108446],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004121102,"threshold_uncertainty_score":0.01378644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2572140284","doi":"","title":"On hyper-parameter estimation in empirical Bayes: a revisit of the MacKay algorithm","year":2016,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Bayes' theorem; Algorithm; Heuristic; Computer science; Gaussian; Estimation theory; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Bayesian probability","authors":[{"name":"Chun’e Li","is_ca":false},{"name":"Yongyi Mao","is_ca":true},{"name":"Richong Zhang","is_ca":false},{"name":"Jinpeng Huai","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05027605717255774,"gpt":0.3362111732541033,"spread":0.2859351160815455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03854187,0.002120476,0.003378378,0.005676022,0.001921744,0.006180434,0.004972821,0.003779652,0.004794792],"category_scores_gemma":[0.1052475,0.00190247,0.002451268,0.004899037,0.009955585,0.01324595,0.006491765,0.008230183,0.001913859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003149527,"about_ca_system_score_gemma":0.003884164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005043895,"about_ca_topic_score_gemma":0.003826197,"domain_scores_codex":[0.9803126,0.01311099,0.001007973,0.001791749,0.003340324,0.0004363731],"domain_scores_gemma":[0.9415511,0.05010981,0.001750077,0.003158314,0.003001443,0.0004291523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003931598,0.0000259044,0.0004954264,0.0002565622,0.0001096397,0.00007675417,0.0003455887,0.03278334,0.0003028301,0.9040094,0.001959725,0.05959554],"study_design_scores_gemma":[0.00001698078,0.00002348468,0.0002077765,0.0001696764,0.00003121084,0.00007280063,0.00003410207,0.09999746,0.0002487452,0.8919688,0.007173588,0.00005527342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001011516,0.001975044,0.9930769,0.0008821125,0.0001209417,0.00003621916,0.00003117229,0.00008303379,0.002783113],"genre_scores_gemma":[0.07923907,0.004997353,0.9089992,0.001018344,0.001435204,0.0003508613,0.0001047163,0.000410158,0.003445195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03854187,"threshold_uncertainty_score":0.2038313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2401728283","doi":"","title":"State sequence analysis in hidden Markov models","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Hidden Markov model; Viterbi algorithm; Sequence (biology); Inference; Forward algorithm; Computer science; State (computer science); Markov chain; Markov model; Hidden semi-Markov model; Sequence labeling; Artificial intelligence; Algorithm; Machine learning; Markov property; Variable-order Markov model","authors":[{"name":"Yuri Grinberg","is_ca":true},{"name":"Theodore J. Perkins","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1614388410284468,"gpt":0.3358911258933971,"spread":0.1744522848649503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00433939,0.001064934,0.001245868,0.001706949,0.0007694305,0.001427604,0.002102386,0.001904638,0.002058961],"category_scores_gemma":[0.02532049,0.001076736,0.00120315,0.001828449,0.001898919,0.003609794,0.001720979,0.003161209,0.0007606579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002134803,"about_ca_system_score_gemma":0.002452324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007881377,"about_ca_topic_score_gemma":0.005129063,"domain_scores_codex":[0.9968849,0.00156096,0.0001916333,0.0006180304,0.0006005727,0.0001437681],"domain_scores_gemma":[0.981557,0.01606059,0.0007986201,0.0007703762,0.0006884989,0.0001249923],"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":[0.0001177944,0.00004842097,0.001528767,0.0002983565,0.00009672855,0.0001555243,0.0002709877,0.7187942,0.001142453,0.1743246,0.001618238,0.1016039],"study_design_scores_gemma":[0.000007129811,0.00001303953,0.00009460723,0.00002503975,0.00001051927,0.00002213272,0.00001304357,0.8698025,0.0005638704,0.1285816,0.0008551511,0.00001140578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001895444,0.0003405632,0.996808,0.0001436036,0.0000220691,0.00002010896,0.00006623108,0.000332817,0.0003711387],"genre_scores_gemma":[0.2996757,0.001714808,0.6942759,0.0003242823,0.000266266,0.0003690096,0.0009143685,0.000299827,0.0021598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007881377,"threshold_uncertainty_score":0.0229491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965108857","doi":"","title":"Probability Distillation: A Caveat and Alternatives.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Distillation; Reliability engineering; Environmental science; Engineering; Chemistry; Chromatography","authors":[{"name":"Chin-Wei Huang","is_ca":true},{"name":"Faruk Ahmed","is_ca":false},{"name":"Kundan Kumar","is_ca":false},{"name":"Alexandre Lacoste","is_ca":false},{"name":"Aaron Courville","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04868565856059613,"gpt":0.2873961231225094,"spread":0.2387104645619132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02135887,0.001200518,0.001815034,0.001830407,0.002272769,0.005487385,0.006765414,0.004771383,0.01172567],"category_scores_gemma":[0.1154267,0.0007659391,0.001168091,0.003567869,0.01385086,0.02107219,0.007137232,0.01628284,0.002984247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001243388,"about_ca_system_score_gemma":0.002632578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002518913,"about_ca_topic_score_gemma":0.003815609,"domain_scores_codex":[0.9874358,0.006229853,0.0006505628,0.001637476,0.003711167,0.0003351022],"domain_scores_gemma":[0.9313373,0.05073001,0.001219201,0.01212299,0.004072158,0.0005184327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009204546,0.00002655831,0.0002308853,0.0002696853,0.00005972258,0.00005158828,0.0001245004,0.002038816,0.000140725,0.9412077,0.02347176,0.03228589],"study_design_scores_gemma":[0.00002326611,0.00001439773,0.00007429691,0.0001045419,0.00001235853,0.00008354574,0.00003887028,0.005423089,0.0003268017,0.9770442,0.01683395,0.00002067656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006894329,0.04171226,0.7151399,0.1646682,0.008953167,0.0001586182,0.001662384,0.0006738988,0.06013713],"genre_scores_gemma":[0.3500238,0.02961421,0.5321565,0.04409225,0.01477605,0.001015688,0.001004978,0.0009668753,0.02634967],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02135887,"threshold_uncertainty_score":0.1129578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2771250101","doi":"","title":"Why Rules are Complex: Real-Valued Probabilistic Logic Programs are not Fully Expressive.","year":2017,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Probabilistic logic; Programming language; Probabilistic argumentation; Theoretical computer science; Logic program; Probabilistic logic network; Description logic; Logic programming; Artificial intelligence; Multimodal logic; Autoepistemic logic","authors":[{"name":"David Buchman","is_ca":true},{"name":"David Poole","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1345770587479101,"gpt":0.3333605007034456,"spread":0.1987834419555355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006639971,0.0005135943,0.001010106,0.001304695,0.00129893,0.009373823,0.0025238,0.003144892,0.006128637],"category_scores_gemma":[0.04450101,0.001004159,0.001690489,0.001438048,0.007057454,0.02296343,0.003493684,0.005523348,0.001264785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011751,"about_ca_system_score_gemma":0.001698074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002841504,"about_ca_topic_score_gemma":0.002407858,"domain_scores_codex":[0.9944448,0.001959086,0.0005035811,0.001127537,0.001531103,0.0004338716],"domain_scores_gemma":[0.9646045,0.02593311,0.00232307,0.004415453,0.00204561,0.000678284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006649075,0.0000302789,0.001106179,0.0002105992,0.00008357085,0.0002164901,0.0006083101,0.008001926,0.0008463708,0.9594779,0.003897108,0.02545468],"study_design_scores_gemma":[0.000009047198,0.000003182186,0.0001305058,0.00002931035,0.00001316681,0.00007968306,0.0001002087,0.00850206,0.0002905923,0.9883768,0.002455195,0.00001029773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0688198,0.002830093,0.8456652,0.02781332,0.0003698274,0.0001223087,0.001343111,0.001318425,0.05171788],"genre_scores_gemma":[0.8292481,0.001743337,0.160328,0.002803623,0.0002720758,0.0001806796,0.0009621225,0.0003409306,0.004121154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009373823,"threshold_uncertainty_score":0.03511596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2406813038","doi":"","title":"Learning and planning with timing information in Markov decision processes","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"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":"Computer science; Markov decision process; Representation (politics); Artificial intelligence; Machine learning; Markov chain; Markov process; Set (abstract data type); State (computer science); Robot; Duration (music); Algorithm; Mathematics","authors":[{"name":"Pierre‐Luc Bacon","is_ca":true},{"name":"Borja Balle","is_ca":true},{"name":"Doina Precup","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05173460047726749,"gpt":0.3098116824769045,"spread":0.258077081999637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002363086,0.0007817065,0.001115172,0.00056274,0.0005331376,0.00111546,0.001204165,0.001305346,0.001628481],"category_scores_gemma":[0.009541492,0.0006235167,0.0008021451,0.0008138585,0.002051098,0.002978705,0.001339638,0.001574499,0.0001769299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376833,"about_ca_system_score_gemma":0.001251975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006218723,"about_ca_topic_score_gemma":0.004011709,"domain_scores_codex":[0.9988616,0.0005912927,0.00005668914,0.0002165679,0.0001565185,0.0001174919],"domain_scores_gemma":[0.9933261,0.005645429,0.0004212467,0.0002202384,0.0002130069,0.0001740321],"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":[0.00008156322,0.00002095852,0.0002885111,0.00002708643,0.00001504891,0.00004895794,0.00004490525,0.9554352,0.000341535,0.0361472,0.0001047474,0.007444264],"study_design_scores_gemma":[0.00001196453,0.00001170616,0.0000320744,0.000002804264,0.000002897046,0.000004453295,0.00000383819,0.9674666,0.000173841,0.032222,0.00006387462,0.000004009566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08509644,0.0002491462,0.9126031,0.0004296591,0.00002643832,0.00002866551,0.00007334019,0.0001810184,0.0013123],"genre_scores_gemma":[0.9035395,0.0002567582,0.09464844,0.00007725677,0.00003789809,0.0001027452,0.0001404814,0.00004696741,0.001149959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006218723,"threshold_uncertainty_score":0.01249737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089522502","doi":"","title":"Differentially Private Top-k Selection via Stability on Unknown Domain","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Selection (genetic algorithm); Stability (learning theory); Computer science; Domain (mathematical analysis); Mathematics; Artificial intelligence; Machine learning","authors":[{"name":"Ricardo Silva Carvalho","is_ca":false},{"name":"Ke Wang","is_ca":true},{"name":"Lovedeep Gondara","is_ca":true},{"name":"Chunyan Miao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06484861329735347,"gpt":0.2932797702087032,"spread":0.2284311569113497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005638526,0.00125233,0.003694213,0.001606178,0.00243866,0.004203555,0.00300941,0.00245289,0.004624838],"category_scores_gemma":[0.03536738,0.0008966962,0.001199127,0.003000841,0.003612143,0.006847827,0.007021779,0.00372237,0.001508142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002564497,"about_ca_system_score_gemma":0.0030039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001197828,"about_ca_topic_score_gemma":0.001171281,"domain_scores_codex":[0.9933838,0.002828277,0.000280354,0.00132545,0.001398441,0.0007837576],"domain_scores_gemma":[0.9683977,0.02388734,0.001145439,0.004395224,0.001306332,0.000867924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002153221,0.0002450774,0.002012902,0.0003174878,0.0002158456,0.00040567,0.0005548802,0.3128506,0.006940632,0.5490453,0.0127384,0.1125199],"study_design_scores_gemma":[0.00009628896,0.00006326062,0.0001770998,0.00001649505,0.00002582489,0.00009904723,0.00004252183,0.5700039,0.001831316,0.426888,0.0007240637,0.00003223081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06311905,0.0006126682,0.9261762,0.002534442,0.0001112353,0.0001434922,0.0006229638,0.001203748,0.005476208],"genre_scores_gemma":[0.9274425,0.0004181157,0.06491515,0.0005002668,0.0002396768,0.0001889332,0.0004773088,0.0001888065,0.005629258],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005638526,"threshold_uncertainty_score":0.02981973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3183287321","doi":"","title":"PROVIDE: A Probabilistic Framework for Unsupervised Video Decomposition","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"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; Inference; Leverage (statistics); Artificial intelligence; Probabilistic logic; Unsupervised learning; Benchmark (surveying); Machine learning; Decomposition; Pattern recognition (psychology)","authors":[{"name":"Polina Zablotskaia","is_ca":false},{"name":"Edoardo Alberto Dominici","is_ca":true},{"name":"Leonid Sigal","is_ca":true},{"name":"Andreas Lehrmann","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04810708885814038,"gpt":0.3203977335676425,"spread":0.2722906447095021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001422262,0.001158837,0.0008650832,0.001494889,0.0004936417,0.001192468,0.002385556,0.00136687,0.003604295],"category_scores_gemma":[0.004761787,0.0009331137,0.001616441,0.001222231,0.001051898,0.002307833,0.0020472,0.002629275,0.001378002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239339,"about_ca_system_score_gemma":0.001233754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006338528,"about_ca_topic_score_gemma":0.01081533,"domain_scores_codex":[0.9992624,0.0002147041,0.00003398735,0.0002066868,0.0002107526,0.00007149991],"domain_scores_gemma":[0.9988474,0.0005233302,0.0001507862,0.0002170021,0.0001835807,0.0000779403],"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":[0.0001470862,0.0000855898,0.00100483,0.0001527265,0.0001162173,0.0001380709,0.0001458288,0.6756638,0.00639934,0.1316883,0.009947472,0.1745108],"study_design_scores_gemma":[0.000005520464,0.000009174526,0.00008493474,0.000008220511,0.000006302801,0.00003745733,0.000004346628,0.9691662,0.0005943452,0.0281473,0.001929237,0.000006983553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009494965,0.00009290121,0.9976585,0.00008292851,0.0000140607,0.00001794467,0.0001689025,0.0005759323,0.0004392848],"genre_scores_gemma":[0.2251618,0.0008228251,0.7628142,0.0002982961,0.0001977736,0.0003300718,0.002503707,0.0007226929,0.007148671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006338528,"threshold_uncertainty_score":0.01260328,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965103194","doi":"","title":"Differentiable Probabilistic Models of Scientific Imaging with the Fourier Slice Theorem.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Iterative reconstruction; Artificial intelligence; Algorithm; Inference; Fourier transform; Projection (relational algebra); Probabilistic logic; Computer vision; Mathematics","authors":[{"name":"Karen Ullrich","is_ca":false},{"name":"Rianne van den Berg","is_ca":false},{"name":"Marcus A. Brubaker","is_ca":true},{"name":"David J. Fleet","is_ca":true},{"name":"Max Welling","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01385795714457307,"gpt":0.2940716380388189,"spread":0.2802136808942459,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00415759,0.001417349,0.001093993,0.001621377,0.0006353435,0.002421938,0.002307639,0.002491769,0.002434923],"category_scores_gemma":[0.01121757,0.000962554,0.0021907,0.001320627,0.0030188,0.003768746,0.002224433,0.003049633,0.0008191933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002139735,"about_ca_system_score_gemma":0.00132068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005487689,"about_ca_topic_score_gemma":0.003779085,"domain_scores_codex":[0.9984701,0.0007417703,0.00006474603,0.0002341841,0.0003908869,0.00009824053],"domain_scores_gemma":[0.994979,0.003352504,0.0005999545,0.0005118389,0.0004039807,0.0001527339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003501026,0.00002420169,0.0005744477,0.00008421441,0.00005958861,0.000107018,0.0001024938,0.426256,0.0008444329,0.5545405,0.001853618,0.01551844],"study_design_scores_gemma":[0.000005659917,0.00001061155,0.0001291607,0.00001282426,0.000008128104,0.00004126308,0.000007013596,0.7993835,0.0001853754,0.1985665,0.00163764,0.00001240244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002224034,0.0004919016,0.9948877,0.000412952,0.00004048517,0.00001554404,0.00009846836,0.0001106769,0.001718358],"genre_scores_gemma":[0.4424421,0.0032225,0.5396914,0.000594425,0.0005680407,0.0004346806,0.000886253,0.0003371375,0.01182338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005487689,"threshold_uncertainty_score":0.02198768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3090786554","doi":"","title":"Non Parametric Graph Learning for Bayesian Graph Neural Networks","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science; Adjacency matrix; Inference; Graph; Theoretical computer science; Artificial intelligence; Machine learning; Statistical relational learning; Data mining; Relational database","authors":[{"name":"Soumyasundar Pal","is_ca":true},{"name":"Saber Malekmohammadi","is_ca":false},{"name":"Florence Regol","is_ca":true},{"name":"Yingxue Zhang","is_ca":false},{"name":"Yishi Xu","is_ca":true},{"name":"Mark Coates","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04336867985110546,"gpt":0.2901535011615251,"spread":0.2467848213104196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003905918,0.001164629,0.001523049,0.001951567,0.0007609443,0.001561522,0.003470254,0.002868399,0.003454399],"category_scores_gemma":[0.02386569,0.001019625,0.001020942,0.002402878,0.00198196,0.003947454,0.001878358,0.003725016,0.0008127422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003089213,"about_ca_system_score_gemma":0.001717121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01233532,"about_ca_topic_score_gemma":0.0164596,"domain_scores_codex":[0.9980166,0.001090538,0.00007013516,0.0003786411,0.0003276592,0.0001163447],"domain_scores_gemma":[0.989532,0.00856991,0.0005827227,0.0004933825,0.0006448738,0.0001770797],"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":[0.00004869678,0.00003783708,0.0007447907,0.0001073591,0.00006049418,0.0000515007,0.00006373726,0.8213999,0.0002469507,0.1371282,0.002474076,0.03763642],"study_design_scores_gemma":[0.000003495015,0.000003920601,0.0000654992,0.000006862374,0.000003969548,0.000006645408,0.000003598912,0.9331776,0.00004500857,0.06634862,0.0003299072,0.000004935031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004124463,0.0004444446,0.9933561,0.000557737,0.00003508155,0.00003841536,0.0001594278,0.0002430873,0.001041374],"genre_scores_gemma":[0.5413926,0.002721469,0.4415625,0.000995956,0.000384921,0.0009275047,0.002182872,0.0004078451,0.009424348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01233532,"threshold_uncertainty_score":0.02452701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091221243","doi":"","title":"Semi-supervised Sequential Generative Models","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"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":"MNIST database; Computer science; Estimator; Latent variable; Generative model; Generative grammar; Machine learning; Artificial intelligence; Trajectory; Forcing (mathematics); Variance (accounting); Variable (mathematics); Deep learning; Mathematics; Statistics","authors":[{"name":"Michael N. Teng","is_ca":false},{"name":"Tuan Anh Lê","is_ca":false},{"name":"Adam Ścibior","is_ca":true},{"name":"Frank Wood","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09722466294154446,"gpt":0.2841124223971038,"spread":0.1868877594555593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001262979,0.0009828527,0.00105762,0.0005774359,0.0003219871,0.0008079034,0.002082197,0.001140947,0.003535292],"category_scores_gemma":[0.004312427,0.0007109244,0.0009965568,0.000573729,0.001359139,0.001395427,0.001539143,0.002001533,0.0007949909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007822459,"about_ca_system_score_gemma":0.0007889125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002529284,"about_ca_topic_score_gemma":0.006007788,"domain_scores_codex":[0.9993423,0.0002387869,0.00002695691,0.0002155261,0.0001141086,0.00006238152],"domain_scores_gemma":[0.9976588,0.001420633,0.0002708221,0.0003600513,0.0001864951,0.0001031828],"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":[0.00009259264,0.0000482416,0.001104864,0.00008037311,0.000066206,0.0001046768,0.0001179221,0.9064991,0.002556028,0.04182544,0.002347028,0.0451575],"study_design_scores_gemma":[0.000003518337,0.000008768184,0.00007260042,0.000004118031,0.000003666134,0.00001602863,0.000003243309,0.9889755,0.0003312003,0.01021741,0.0003601503,0.000003806922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009587938,0.0001328053,0.9885352,0.0001745007,0.00002515386,0.00002695382,0.0001622948,0.0004157251,0.0009394343],"genre_scores_gemma":[0.7548983,0.0003306209,0.2322157,0.0003413368,0.0001610746,0.000302959,0.001268878,0.0003505554,0.01013064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003535292,"threshold_uncertainty_score":0.01182675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963437270","doi":"","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates.","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Control variates; Temporal difference learning; Reinforcement learning; Variance (accounting); Computer science; Control (management); Variance reduction; Monte Carlo method; Artificial intelligence; Machine learning; Statistics; Mathematics; Hybrid Monte Carlo; Bayesian probability; Markov chain Monte Carlo","authors":[{"name":"Kristopher De Asis","is_ca":true},{"name":"Richard S. Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04175902341515242,"gpt":0.2973694407687176,"spread":0.2556104173535652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003154112,0.0008672708,0.001187087,0.0003521859,0.0003894872,0.001001372,0.002029981,0.001520178,0.003852058],"category_scores_gemma":[0.01196722,0.0004273488,0.0005111022,0.000434234,0.001222565,0.001681435,0.001663144,0.002394638,0.0005230919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009492963,"about_ca_system_score_gemma":0.001642459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002833761,"about_ca_topic_score_gemma":0.002731928,"domain_scores_codex":[0.9990398,0.000354413,0.00006389794,0.0001917184,0.0002497193,0.0001003037],"domain_scores_gemma":[0.9945697,0.003975049,0.000328714,0.0004161902,0.0004405694,0.0002696925],"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":[0.0005693145,0.0002901345,0.001371624,0.0001654119,0.00008388401,0.00008796369,0.00008131689,0.848229,0.001765087,0.02162638,0.001368462,0.1243614],"study_design_scores_gemma":[0.00001291764,0.00004162999,0.00004136499,0.000004391926,0.000003931925,0.000009207711,0.000001963711,0.9969494,0.0004561492,0.00225368,0.0002215333,0.000003865067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0150369,0.0004085802,0.9818672,0.0002004279,0.0001219127,0.00008404034,0.00003525648,0.0004402206,0.001805525],"genre_scores_gemma":[0.8143498,0.0001428201,0.1825303,0.0002726714,0.00006013165,0.0001909391,0.0001151771,0.00007669919,0.002261473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003852058,"threshold_uncertainty_score":0.01668078,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2774018923","doi":"","title":"Stochastic Segmentation Trees for Multiple Ground Truths.","year":2017,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence","authors":[{"name":"Jake Snell","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07325594585640749,"gpt":0.3439437889214061,"spread":0.2706878430649986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002944692,0.0007898923,0.00151627,0.003007204,0.0009122773,0.002347723,0.002369192,0.003202153,0.004686705],"category_scores_gemma":[0.01557769,0.001091022,0.001556048,0.002760368,0.001183983,0.003665181,0.001967081,0.002057565,0.00173231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001810912,"about_ca_system_score_gemma":0.001762653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00639862,"about_ca_topic_score_gemma":0.009841499,"domain_scores_codex":[0.9979364,0.0004798566,0.0001323066,0.0006018227,0.0006544447,0.0001952834],"domain_scores_gemma":[0.9928416,0.004617696,0.0005514589,0.000828126,0.0009555564,0.0002055515],"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":[0.0004016871,0.0001041955,0.002807647,0.0003389389,0.0001743159,0.0002963746,0.000290047,0.5657175,0.005162113,0.09664396,0.01516412,0.3128991],"study_design_scores_gemma":[0.000008914954,0.00001449238,0.0003262849,0.00002612259,0.00001130682,0.00005243223,0.0000195856,0.9399235,0.0008800188,0.05711762,0.00161212,0.000007745883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01335094,0.0006337296,0.9813119,0.0003883792,0.0000808564,0.00005567221,0.0008344642,0.001852576,0.001491577],"genre_scores_gemma":[0.3979031,0.000510083,0.5916106,0.0002196935,0.000213662,0.0001772111,0.005478259,0.0005895038,0.003297894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00639862,"threshold_uncertainty_score":0.01567864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966236725","doi":"","title":"On the Relationship Between Satisfiability and Markov Decision Processes.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Satisfiability; Markov process; Markov chain; Markov decision process; Boolean satisfiability problem; Theoretical computer science; Algorithm; Mathematics; Machine learning; Statistics","authors":[{"name":"Ricardo Salmon","is_ca":false},{"name":"Pascal Poupart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0628719743448886,"gpt":0.3038967491543022,"spread":0.2410247748094136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008772957,0.001208526,0.001617196,0.002817507,0.001880435,0.003584576,0.002206313,0.003384005,0.007546131],"category_scores_gemma":[0.06889155,0.00115621,0.002016388,0.003030855,0.007513254,0.01217932,0.002916126,0.00657312,0.0006447457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003493934,"about_ca_system_score_gemma":0.002647605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009600471,"about_ca_topic_score_gemma":0.007417194,"domain_scores_codex":[0.99386,0.003277583,0.0005116569,0.0006933392,0.001094262,0.0005630919],"domain_scores_gemma":[0.8536227,0.1375387,0.003093553,0.002330023,0.002361009,0.001053852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005477062,0.00004124178,0.0006498409,0.0001580971,0.00009242943,0.0001442514,0.0002307775,0.02423026,0.0001262928,0.9624414,0.002461104,0.009369564],"study_design_scores_gemma":[0.000008072237,0.000009217122,0.00008639553,0.00003234782,0.00001222135,0.00002170816,0.0000220679,0.02204961,0.00004627508,0.9770228,0.0006806769,0.00000874847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03102062,0.01567416,0.8847622,0.017142,0.0007247548,0.0001719183,0.0008980588,0.0002106176,0.04939575],"genre_scores_gemma":[0.7568874,0.0143995,0.2140318,0.003109745,0.001831227,0.0004363429,0.0009882154,0.0001441977,0.008171448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009600471,"threshold_uncertainty_score":0.04639637,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3090228367","doi":"","title":"Batch norm with entropic regularization turns deterministic autoencoders into generative models","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"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":"Autoencoder; Computer science; Generative model; Regularization (linguistics); Generative grammar; Encoder; Algorithm; Artificial neural network; Artificial intelligence; Encoding (memory); Matrix norm; Source code; Normalization (sociology); Theoretical computer science; Eigenvalues and eigenvectors","authors":[{"name":"Amur Ghose","is_ca":true},{"name":"Abdullah Rashwan","is_ca":true},{"name":"Pascal Poupart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04116235678626784,"gpt":0.2522136720768242,"spread":0.2110513152905563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001685646,0.001042328,0.0006586974,0.0004770183,0.0003121414,0.0009561722,0.001099365,0.001101708,0.002160199],"category_scores_gemma":[0.005250606,0.0006791723,0.000854335,0.0004092769,0.002198111,0.001735711,0.001778811,0.002595612,0.0004676661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001271451,"about_ca_system_score_gemma":0.0008420793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002581399,"about_ca_topic_score_gemma":0.002848032,"domain_scores_codex":[0.9992996,0.0002953725,0.00002529453,0.0001587998,0.0001717825,0.00004914305],"domain_scores_gemma":[0.9984018,0.00116843,0.0001046003,0.0001723942,0.00009851356,0.00005418161],"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":[0.00003728399,0.00002549941,0.0002442059,0.00004698731,0.00004207861,0.00007046235,0.00008121165,0.6238079,0.003995813,0.3477976,0.001364858,0.02248615],"study_design_scores_gemma":[0.00000259188,0.00001021932,0.00004102222,0.000007021595,0.000004025278,0.00001487908,0.000003502716,0.92858,0.0009333208,0.06968754,0.0007095595,0.000006386903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004153128,0.0001158534,0.9931405,0.0001913317,0.00002530901,0.0000110215,0.00002749248,0.0001380307,0.002197322],"genre_scores_gemma":[0.6541507,0.0008517821,0.3280889,0.0005574668,0.0002154149,0.0001782857,0.0002485776,0.0005019425,0.01520693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002581399,"threshold_uncertainty_score":0.00922513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3184302936","doi":"","title":"Identifying Regions of Trusted Predictions","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science; Pointwise; Machine learning; Artificial intelligence; Process (computing); Domain (mathematical analysis); Data mining; Confidence interval; Sample complexity; Sample (material); Statistics; Mathematics","authors":[{"name":"Nivasini Ananthakrishnan","is_ca":true},{"name":"Shai Ben-David","is_ca":true},{"name":"Tosca Lechner","is_ca":true},{"name":"Ruth Urner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05836014756836001,"gpt":0.3227540973834027,"spread":0.2643939498150427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01279355,0.001090809,0.001905015,0.002139059,0.001538817,0.005358974,0.003552448,0.002890103,0.003989433],"category_scores_gemma":[0.123256,0.001233248,0.001620713,0.001525692,0.0044438,0.007848712,0.007319223,0.003681789,0.001088714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002084403,"about_ca_system_score_gemma":0.002311049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002629122,"about_ca_topic_score_gemma":0.001651844,"domain_scores_codex":[0.990298,0.002624153,0.0005413129,0.002222119,0.003441052,0.0008735273],"domain_scores_gemma":[0.8608825,0.1047,0.01027596,0.0132707,0.009048479,0.001822308],"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":[0.001830271,0.0001746472,0.03449829,0.000674856,0.0002085506,0.001242734,0.002733451,0.4785439,0.01420157,0.3409552,0.006424603,0.118512],"study_design_scores_gemma":[0.00005055386,0.0001278672,0.002665058,0.0001233579,0.00004492971,0.0003723094,0.0002623736,0.7213654,0.01574913,0.2562139,0.002967632,0.00005760787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08944411,0.0006533541,0.9039595,0.0009463128,0.00003906128,0.00009026998,0.0005708079,0.001060808,0.003235813],"genre_scores_gemma":[0.8567128,0.0003534605,0.1394808,0.0003330635,0.0001209564,0.0002146455,0.001261294,0.0004577344,0.001065181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01279355,"threshold_uncertainty_score":0.06765962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963763058","doi":"","title":"Convex-constrained Sparse Additive Modeling and Its Extensions.","year":2017,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"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":"Overfitting; Convexity; Additive model; Mathematical optimization; Mathematics; Regularization (linguistics); A priori and a posteriori; Computer science; Algorithm; Convex optimization; Regular polygon; Convex function; Artificial intelligence; Machine learning; Artificial neural network","authors":[{"name":"Junming Yin","is_ca":false},{"name":"Yaoliang Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2580744315264659,"gpt":0.4199282445267047,"spread":0.1618538130002388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003174268,0.001260068,0.001010343,0.001053547,0.0004229138,0.001430013,0.002018862,0.001309472,0.0019548],"category_scores_gemma":[0.01152328,0.0008125954,0.001419427,0.001521004,0.001490462,0.002003627,0.00255456,0.002894946,0.0008036481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005624273,"about_ca_system_score_gemma":0.001064717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002098363,"about_ca_topic_score_gemma":0.002319407,"domain_scores_codex":[0.9981488,0.0008430329,0.00007914521,0.000243286,0.0006119086,0.00007383106],"domain_scores_gemma":[0.9959878,0.0025409,0.0003885064,0.0005672599,0.0004067706,0.0001087539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009141616,0.00006844325,0.0009202413,0.0003186507,0.0001662481,0.0001818211,0.0002053045,0.5484309,0.005116542,0.2845592,0.005191807,0.1547493],"study_design_scores_gemma":[0.000003836864,0.00001704659,0.00009440441,0.00001246706,0.00001248252,0.00005370554,0.000009232537,0.956102,0.0007900503,0.04058154,0.002312242,0.00001113351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009246703,0.0001781477,0.9982003,0.000109671,0.00001709992,0.00001056247,0.00003411025,0.00006601854,0.000459427],"genre_scores_gemma":[0.2183194,0.00209803,0.7729466,0.0005157907,0.0003588231,0.0002882241,0.0006126543,0.0002292273,0.004631244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003174268,"threshold_uncertainty_score":0.01678735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3185541071","doi":"","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"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; Computer science; Robustness (evolution); Machine learning; Artificial intelligence; Transfer of learning; Reuse; Context (archaeology); Task (project management); Bayesian probability; Engineering","authors":[{"name":"Mike Gimelfarb","is_ca":true},{"name":"Scott Sanner","is_ca":true},{"name":"Chi-Guhn Lee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03181191723208893,"gpt":0.2972237819968313,"spread":0.2654118647647424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00352456,0.001447765,0.001741789,0.0006059097,0.0004881209,0.001026695,0.002157267,0.001858052,0.002147847],"category_scores_gemma":[0.01088927,0.0008842503,0.0008115894,0.0005226043,0.001693613,0.002167935,0.002774528,0.003175586,0.0004400747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001701917,"about_ca_system_score_gemma":0.001600064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007612758,"about_ca_topic_score_gemma":0.006177522,"domain_scores_codex":[0.9986381,0.0005989851,0.00006409166,0.000296518,0.0002271971,0.0001751829],"domain_scores_gemma":[0.9960001,0.002854253,0.0002896045,0.0003019958,0.000317488,0.0002366002],"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":[0.0001535168,0.00009070586,0.0005535864,0.00004942336,0.00004284756,0.00004710373,0.0001004657,0.9580431,0.0007348411,0.006849368,0.0005253716,0.03280957],"study_design_scores_gemma":[0.00001191632,0.00002408943,0.00004034377,0.000004832873,0.000004040332,0.000004863537,0.0000046085,0.9940261,0.0002988031,0.005446339,0.0001294931,0.000004597972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04928366,0.0005257522,0.9467129,0.0003251756,0.00005135998,0.00008450114,0.00005910325,0.001131472,0.001826148],"genre_scores_gemma":[0.8996539,0.0001831456,0.09770652,0.0002376732,0.00003973391,0.0001477966,0.000114701,0.0001124933,0.001804061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007612758,"threshold_uncertainty_score":0.01863986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3183593932","doi":"","title":"Efficient Greedy Coordinate Descent via Variable Partitioning","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"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":"Coordinate descent; Greedy algorithm; Partition (number theory); Convergence (economics); Algorithm; Computer science; Descent (aeronautics); Mathematical optimization; Mathematics; Variable (mathematics); Rate of convergence; Key (lock); Combinatorics","authors":[{"name":"Fang Huang","is_ca":true},{"name":"Guanhua Fang","is_ca":false},{"name":"Tan Yu","is_ca":false},{"name":"Ping Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03679210610531011,"gpt":0.2756887765513355,"spread":0.2388966704460254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001031308,0.001342683,0.001916237,0.0008291912,0.0006041365,0.001199509,0.001573692,0.001020814,0.002707433],"category_scores_gemma":[0.004809435,0.0007093793,0.0008681501,0.001422948,0.0008527819,0.001004132,0.001630647,0.001260979,0.001374588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008068567,"about_ca_system_score_gemma":0.001678958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005922697,"about_ca_topic_score_gemma":0.005265528,"domain_scores_codex":[0.999056,0.000309174,0.00004496532,0.000214285,0.0002556074,0.0001198663],"domain_scores_gemma":[0.9988488,0.0005591948,0.00007885478,0.0001727702,0.0002758662,0.00006450497],"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":[0.0002093612,0.00006509649,0.0009879543,0.0001503097,0.00008011199,0.0001208605,0.0001049223,0.6985815,0.00473766,0.03130374,0.01222533,0.2514332],"study_design_scores_gemma":[0.00001621182,0.00002195209,0.00007547929,0.000003426747,0.000004293662,0.00002011211,0.000006630523,0.9940699,0.000577644,0.004196431,0.001003196,0.000004699879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004605682,0.0001570609,0.9936507,0.00006935608,0.00003850056,0.0000328546,0.00004955167,0.0005655123,0.0008307873],"genre_scores_gemma":[0.2016646,0.0002830529,0.7919242,0.0001862308,0.0001079107,0.0003795311,0.0008758756,0.0004185957,0.004159969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005922697,"threshold_uncertainty_score":0.01177645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089548822","doi":"","title":"Stable Policy Optimization via Off-Policy Divergence Regularization.","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Reinforcement learning; Benchmark (surveying); Regularization (linguistics); Computer science; Divergence (linguistics); Stability (learning theory); Trust region; Mathematical optimization; Adversarial system; Optimization problem; Range (aeronautics); Term (time); Artificial intelligence; Machine learning; Algorithm; Mathematics; Engineering","authors":[{"name":"Abdelaziz Touati","is_ca":true},{"name":"Amy Zhang","is_ca":true},{"name":"Joëlle Pineau","is_ca":true},{"name":"Pascal Vincent","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03451898926511433,"gpt":0.2957511071451971,"spread":0.2612321178800828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002232498,0.00100669,0.001154027,0.0005718041,0.0004594787,0.000936463,0.001201261,0.001405468,0.001693182],"category_scores_gemma":[0.0114123,0.0005459858,0.0006003701,0.0004570087,0.001853207,0.001432103,0.002070164,0.002493246,0.0004611632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001072405,"about_ca_system_score_gemma":0.001705835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002708417,"about_ca_topic_score_gemma":0.002241723,"domain_scores_codex":[0.999162,0.0003334235,0.00004215943,0.000172026,0.0002085713,0.00008183489],"domain_scores_gemma":[0.9963697,0.002504192,0.0003725966,0.0002939764,0.0002965688,0.0001629683],"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":[0.000105592,0.00006238483,0.0005791443,0.00005605361,0.00003992294,0.00004767982,0.00006378171,0.9411291,0.001460084,0.02118924,0.001164668,0.03410234],"study_design_scores_gemma":[0.000005127191,0.00001626491,0.00002907492,0.000003798218,0.000001961901,0.000006969516,0.000002787388,0.9945575,0.000266269,0.004969096,0.0001389619,0.000002279067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01402742,0.0002084649,0.9835998,0.0001967545,0.00003768924,0.00004380046,0.00002625428,0.000342609,0.001517311],"genre_scores_gemma":[0.8231747,0.0001956484,0.1725574,0.0002789431,0.00005643956,0.0001921453,0.0001694598,0.0002083231,0.003166912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002708417,"threshold_uncertainty_score":0.01180667,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}