{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":27,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":27,"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":"1592200117c9","filters":{"venue":"Conference on Learning Theory"}},"results":[{"id":"W1589919686","doi":"","title":"Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.","year":2008,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":108,"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":"Sample complexity; Computer science; Semi-supervised learning; Homogeneous; Distribution (mathematics); Artificial intelligence; Conjecture; Sample (material); Class (philosophy); Labeled data; Supervised learning; Machine learning; Pattern recognition (psychology); Mathematics; Artificial neural network; Discrete mathematics; Combinatorics","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Tyler Lu","is_ca":true},{"name":"Dávid Pál","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1094726326608954,"gpt":0.3005835196592879,"spread":0.1911108869983926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04909202,0.002055194,0.003230908,0.001854699,0.002274829,0.006628438,0.004759783,0.004406094,0.005380261],"category_scores_gemma":[0.2437087,0.001662931,0.002425974,0.002347252,0.006966659,0.01762641,0.006678529,0.008449861,0.0006740681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005287651,"about_ca_system_score_gemma":0.003938376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001770247,"about_ca_topic_score_gemma":0.002176097,"domain_scores_codex":[0.9686936,0.02026018,0.001149181,0.003399631,0.004714407,0.001783043],"domain_scores_gemma":[0.5536621,0.4099721,0.008232041,0.01941536,0.00544474,0.003273695],"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":[0.002027699,0.0005622571,0.01044493,0.0009811625,0.0006080166,0.000640019,0.0008329389,0.4680459,0.002348514,0.4380042,0.01347208,0.06203231],"study_design_scores_gemma":[0.00007958779,0.000131083,0.0005890534,0.00006714119,0.00005694027,0.0001891417,0.00009221874,0.6213314,0.001031848,0.3752761,0.001127078,0.00002841321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07923751,0.002680105,0.8899365,0.01374921,0.0002869549,0.0003119658,0.00108923,0.0006963228,0.01201226],"genre_scores_gemma":[0.7826052,0.001618824,0.2047564,0.002528409,0.001282519,0.0008575924,0.001588077,0.0005946105,0.004168412],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04909202,"threshold_uncertainty_score":0.2596266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965944281","doi":"","title":"Tight analyses for non-smooth stochastic gradient descent","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":41,"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":"Mathematics; Lipschitz continuity; Stochastic gradient descent; Differentiable function; Combinatorics; Convex function; Gradient descent; Upper and lower bounds; Regular polygon; Discrete mathematics; Applied mathematics; Mathematical analysis; Computer science","authors":[{"name":"Nicholas J. A. Harvey","is_ca":true},{"name":"Christopher Liaw","is_ca":true},{"name":"Yaniv Plan","is_ca":true},{"name":"Sikander Randhawa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04690993015189428,"gpt":0.3102476221312967,"spread":0.2633376919794024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02689398,0.005478594,0.005683759,0.004258015,0.003440413,0.005118314,0.006526676,0.00547856,0.01155368],"category_scores_gemma":[0.1309287,0.002581611,0.005286602,0.002817784,0.007728141,0.01225153,0.01086107,0.0144837,0.002261876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007805124,"about_ca_system_score_gemma":0.005633266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008286189,"about_ca_topic_score_gemma":0.006163376,"domain_scores_codex":[0.9879396,0.004328775,0.0006049093,0.002113406,0.003738483,0.001274775],"domain_scores_gemma":[0.9178297,0.05936402,0.005036654,0.007683893,0.007581455,0.002504308],"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":[0.0004304193,0.000189938,0.003074142,0.0008487701,0.0003434249,0.0003481624,0.0005948542,0.3736889,0.003638049,0.5788928,0.009510169,0.02844047],"study_design_scores_gemma":[0.00002887607,0.0001121183,0.0006552244,0.0001649774,0.00007747229,0.00007474286,0.00004978207,0.7913679,0.001172443,0.2033768,0.002871656,0.00004804743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01173335,0.003163206,0.9712432,0.002678832,0.0002855611,0.0001271436,0.0002373122,0.0006427363,0.009888599],"genre_scores_gemma":[0.5875375,0.006520189,0.3614404,0.00516221,0.001881202,0.001473719,0.001625798,0.003211356,0.0311477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02689398,"threshold_uncertainty_score":0.1422306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966286942","doi":"","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Minimax; Mathematics; Bayesian probability; Mathematical economics; Degenerate energy levels; Mathematical optimization; Computer science; Discrete mathematics; Statistics","authors":[{"name":"Tor Lattimore","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09132089929786394,"gpt":0.4067404308935916,"spread":0.3154195315957277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01028208,0.002522769,0.00225429,0.001788299,0.00130313,0.004363826,0.004623093,0.003070693,0.01100635],"category_scores_gemma":[0.04984009,0.001296808,0.002601558,0.002161507,0.005559481,0.01081544,0.006637167,0.01003828,0.001637809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003946359,"about_ca_system_score_gemma":0.002001774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009086961,"about_ca_topic_score_gemma":0.0007904171,"domain_scores_codex":[0.9926571,0.003393273,0.000259703,0.001180878,0.001890404,0.0006186304],"domain_scores_gemma":[0.9707834,0.02228632,0.002127802,0.003226193,0.000984717,0.000591629],"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":[0.0001424325,0.000105546,0.0006884271,0.0003075268,0.0001520849,0.0001275041,0.0002120599,0.1349184,0.001344937,0.8335251,0.005708786,0.02276736],"study_design_scores_gemma":[0.00002427975,0.00008641195,0.0003347366,0.0001056577,0.0000380294,0.0001195427,0.0000284268,0.2918641,0.0008436472,0.7035046,0.003017335,0.00003329057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006148201,0.001196633,0.977047,0.001833401,0.0001553934,0.00009107051,0.0002688926,0.0002015878,0.01305771],"genre_scores_gemma":[0.6866193,0.003651601,0.2862615,0.002686225,0.001222953,0.0009365972,0.0006300685,0.0005164686,0.01747532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01100635,"threshold_uncertainty_score":0.0543775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W43025842","doi":"","title":"PLAL: Cluster-based active learning","year":2013,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":29,"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":"Sample complexity; Complement (music); Computer science; Preprocessor; Probabilistic logic; Smoothness; Sample (material); Simple (philosophy); Active learning (machine learning); Artificial intelligence; Machine learning; Semi-supervised learning; Process (computing); Cluster (spacecraft); Mathematics","authors":[{"name":"Ruth Urner","is_ca":true},{"name":"Sharon Wulff","is_ca":false},{"name":"Shai Ben-David","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01420798321609177,"gpt":0.247912240700798,"spread":0.2337042574847062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009972543,0.00143533,0.001455775,0.001253172,0.001437399,0.00350535,0.007877616,0.002984,0.005772384],"category_scores_gemma":[0.03487288,0.0009054465,0.001120703,0.001292721,0.003476877,0.007040379,0.00670777,0.006079498,0.001765859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002270981,"about_ca_system_score_gemma":0.00197183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001787247,"about_ca_topic_score_gemma":0.002197281,"domain_scores_codex":[0.994197,0.002524935,0.0001943595,0.001193028,0.001562893,0.000327792],"domain_scores_gemma":[0.9516176,0.03529862,0.0017157,0.00750119,0.002938021,0.0009288652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001533066,0.0008602491,0.003845443,0.000726983,0.0002173468,0.0001952047,0.001060841,0.3167236,0.01479042,0.296129,0.01342085,0.3504971],"study_design_scores_gemma":[0.00005800222,0.0001120047,0.000117343,0.00001560827,0.00001545725,0.00004071419,0.00003650077,0.9149256,0.005154592,0.077808,0.001701317,0.00001498234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005177842,0.00007281072,0.9922858,0.0003499919,0.00002364301,0.00009033098,0.0000810253,0.0008761305,0.001042338],"genre_scores_gemma":[0.3161701,0.0001832573,0.6748466,0.000631121,0.0001767857,0.0008616758,0.000722921,0.0005863931,0.00582122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009972543,"threshold_uncertainty_score":0.05274045,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W9422450","doi":"","title":"Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Minimax; Outcome (game theory); Action (physics); Logarithm; Computer science; Mathematical optimization; Mathematics; Mathematical economics; Statistics; Psychology","authors":[{"name":"Gábor Bartók","is_ca":true},{"name":"Dávid Pál","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2434593967789235,"gpt":0.4046804874307592,"spread":0.1612210906518357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007462511,0.002260839,0.003761568,0.001224324,0.0009213511,0.002774599,0.002336947,0.002484523,0.005473551],"category_scores_gemma":[0.01802961,0.000959537,0.001147616,0.001068393,0.002709601,0.002902279,0.002874147,0.003095847,0.0004939888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003643493,"about_ca_system_score_gemma":0.002674126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006353855,"about_ca_topic_score_gemma":0.004698441,"domain_scores_codex":[0.9963741,0.002042047,0.0001582965,0.0004624279,0.0003228584,0.0006402315],"domain_scores_gemma":[0.9651681,0.03069644,0.001592549,0.0006301739,0.0007188516,0.001193848],"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":[0.0003829376,0.00008164937,0.001218957,0.0001660844,0.0001099868,0.0001318972,0.0000741394,0.9502456,0.0002041817,0.03941593,0.001846213,0.006122521],"study_design_scores_gemma":[0.0000446522,0.00005736206,0.0001765725,0.00001669244,0.00001015418,0.00001937818,0.00001586252,0.9690173,0.00006308209,0.03040867,0.0001587818,0.00001148368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2229928,0.002170077,0.7477323,0.004551829,0.0002496656,0.0002909016,0.001531277,0.0006289764,0.01985209],"genre_scores_gemma":[0.9594843,0.0008539588,0.02796356,0.0004897846,0.0001946744,0.0004301085,0.0007240456,0.000140038,0.009719467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007462511,"threshold_uncertainty_score":0.03946602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046729600","doi":"","title":"Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Regret; Gradient descent; Bounded function; Descent (aeronautics); Mathematical optimization; Computer science; Property (philosophy); Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis; Engineering; Machine learning","authors":[{"name":"James P. Bailey","is_ca":false},{"name":"Gauthier Gidel","is_ca":true},{"name":"Georgios Piliouras","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1225592921582373,"gpt":0.372425274325463,"spread":0.2498659821672256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002796015,0.001321757,0.001128459,0.000608912,0.0006604515,0.001109194,0.001951899,0.00142189,0.002160787],"category_scores_gemma":[0.01620615,0.0006290858,0.0006841613,0.0004967009,0.002330139,0.001793851,0.002124902,0.002387411,0.0005145133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234837,"about_ca_system_score_gemma":0.001634605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003267907,"about_ca_topic_score_gemma":0.003031882,"domain_scores_codex":[0.9982221,0.0008541986,0.00007044216,0.0002993582,0.0003656888,0.0001882116],"domain_scores_gemma":[0.9945276,0.00386709,0.0004303988,0.0005679922,0.0003131335,0.0002937611],"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":[0.000218289,0.0001133828,0.001209774,0.00007167867,0.00007129532,0.0001701287,0.0001489881,0.8189125,0.002035975,0.141028,0.001868438,0.0341516],"study_design_scores_gemma":[0.00001512586,0.00003259957,0.00006509796,0.000007539603,0.000005572339,0.00001587151,0.000004127668,0.962427,0.000468382,0.0366516,0.0003010533,0.000006089068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03351995,0.0002044144,0.9610369,0.0003377463,0.00003566395,0.00005334594,0.00003339861,0.0004986679,0.004279772],"genre_scores_gemma":[0.8188206,0.0001997656,0.1749959,0.000274092,0.00003828464,0.0003289862,0.0001150116,0.0002764603,0.004950889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003267907,"threshold_uncertainty_score":0.0147869,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046526692","doi":"","title":"Private Mean Estimation of Heavy-Tailed Distributions","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"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":"Univariate; Sample complexity; Bounded function; Minimax; Combinatorics; Mathematics; Differential privacy; Sample mean and sample covariance; Upper and lower bounds; Multivariate statistics; Sample (material); Estimation; Discrete mathematics; Statistics; Mathematical analysis; Computer science; Mathematical optimization; Physics; Estimator; Artificial intelligence","authors":[{"name":"Gautam Kamath","is_ca":true},{"name":"Vikrant Singhal","is_ca":false},{"name":"Jonathan Ullman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04420529321116277,"gpt":0.2818828961734084,"spread":0.2376776029622457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007449574,0.001538797,0.00239672,0.001182331,0.00110378,0.003459032,0.003541989,0.002188558,0.003940695],"category_scores_gemma":[0.05355184,0.001135062,0.001723915,0.001648744,0.003495635,0.008018523,0.006207213,0.005951859,0.0008529632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003317193,"about_ca_system_score_gemma":0.00243405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009758092,"about_ca_topic_score_gemma":0.001389229,"domain_scores_codex":[0.994115,0.002269058,0.0002685657,0.001085872,0.00158352,0.0006780596],"domain_scores_gemma":[0.9507005,0.03622848,0.002762417,0.008068228,0.001437021,0.0008033209],"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":[0.001331492,0.0002611215,0.004965645,0.0004395609,0.0002555361,0.0003927381,0.000480901,0.5049692,0.01082209,0.387958,0.006294684,0.08182904],"study_design_scores_gemma":[0.00002694896,0.00004540351,0.0004714406,0.00002790094,0.00002186051,0.0001290195,0.00002664328,0.8625364,0.003423349,0.1325117,0.0007534868,0.00002582853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02036745,0.0004175529,0.9753522,0.000924656,0.00004306914,0.00005630146,0.0002130104,0.000385991,0.002239731],"genre_scores_gemma":[0.6770836,0.0009575564,0.3142954,0.0007224669,0.0003807675,0.0004011635,0.0007862133,0.0003057776,0.005067191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007449574,"threshold_uncertainty_score":0.03939754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W75140964","doi":"","title":"Agnostic KWIK learning and efficient approximate reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"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":"Reinforcement learning; Computer science; Simple (philosophy); Artificial intelligence; Algorithm; Theoretical computer science; Machine learning","authors":[{"name":"István Szita","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03446888166875992,"gpt":0.247999907469349,"spread":0.2135310258005891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001860294,0.0008768067,0.001381903,0.0004678743,0.0003741589,0.001017998,0.001933067,0.001330218,0.002672602],"category_scores_gemma":[0.009071812,0.000592013,0.0004464098,0.0005466783,0.001569277,0.002378393,0.002060032,0.002584088,0.0006149946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039835,"about_ca_system_score_gemma":0.001168304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002373248,"about_ca_topic_score_gemma":0.002285784,"domain_scores_codex":[0.9985847,0.0005723143,0.00007579694,0.0002244502,0.000380422,0.0001622024],"domain_scores_gemma":[0.997453,0.001362525,0.0002675944,0.000496868,0.0003151932,0.0001047711],"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":[0.0001534725,0.000127022,0.0007214198,0.0001103225,0.00005612589,0.00008379658,0.00009197497,0.8176853,0.001736016,0.1252333,0.001486861,0.05251442],"study_design_scores_gemma":[0.00001087032,0.00001922954,0.00003401297,0.000003815441,0.000003934866,0.00001402536,0.000003655421,0.9684824,0.0002943736,0.03080655,0.0003233275,0.000003849695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01018046,0.0001510358,0.9876179,0.000153561,0.00002335543,0.00002352155,0.00001520471,0.0002682369,0.001566832],"genre_scores_gemma":[0.8092794,0.0002704483,0.1827669,0.0002323637,0.00005829943,0.0001744431,0.000125358,0.0001303064,0.006962366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002672602,"threshold_uncertainty_score":0.009838283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1877234769","doi":"","title":"Open Problem: Recursive Teaching Dimension Versus VC Dimension","year":2015,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Concept class; Dimension (graph theory); Conjecture; Mathematics; Class (philosophy); VC dimension; Bounded function; Upper and lower bounds; Exponential function; Discrete mathematics; Function (biology); Combinatorics; Kolmogorov complexity; Algebra over a field; Pure mathematics; Computer science; Artificial intelligence; Mathematical analysis","authors":[{"name":"Hans Ulrich Simon","is_ca":false},{"name":"Sandra Zilles","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06272562214348579,"gpt":0.3247416508144249,"spread":0.2620160286709391,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009538388,0.001460084,0.003924368,0.00176492,0.002633878,0.007852738,0.006190754,0.005595141,0.01440016],"category_scores_gemma":[0.1229985,0.001174317,0.002153119,0.002713294,0.008274892,0.02301578,0.006275609,0.01061029,0.002409345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005056231,"about_ca_system_score_gemma":0.003296008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001940776,"about_ca_topic_score_gemma":0.001092972,"domain_scores_codex":[0.9884416,0.003264446,0.0005599306,0.003667941,0.002568932,0.001497123],"domain_scores_gemma":[0.7265533,0.2443959,0.005278309,0.01360288,0.005294489,0.004875196],"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":[0.001008401,0.0003970526,0.00534264,0.001171995,0.0001753208,0.0001941478,0.0007875143,0.03978992,0.002477741,0.7699898,0.0378364,0.140829],"study_design_scores_gemma":[0.00009344932,0.0001060792,0.001322267,0.000166873,0.00003979596,0.0003267125,0.0002018993,0.109088,0.001442592,0.8800422,0.00709113,0.00007902711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1737038,0.01554842,0.674739,0.07627191,0.001332339,0.0003257169,0.003968795,0.003113901,0.05099608],"genre_scores_gemma":[0.8442106,0.006198663,0.1237406,0.007108111,0.005666343,0.0008211492,0.001960471,0.001176575,0.009117487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01440016,"threshold_uncertainty_score":0.05044436,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966312692","doi":"","title":"Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":10,"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":"Mathematics; Martingale (probability theory); Martingale difference sequence; Central limit theorem; Applied mathematics; Stochastic gradient descent; Rate of convergence; Multivariate random variable; Weak convergence; Mathematical analysis; Random variable; Statistics; Computer science","authors":[{"name":"Andreas Anastasiou","is_ca":false},{"name":"Krishnakumar Balasubramanian","is_ca":false},{"name":"Murat A. Erdogdu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05635044454367171,"gpt":0.3348542065146358,"spread":0.278503761970964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01918491,0.001971575,0.002046724,0.00330836,0.0008111699,0.002340034,0.003037557,0.001955783,0.004485499],"category_scores_gemma":[0.08012067,0.0009018084,0.002311732,0.001442717,0.00488939,0.004796594,0.004458407,0.005467314,0.0008278421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003232388,"about_ca_system_score_gemma":0.002412873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003627175,"about_ca_topic_score_gemma":0.002608439,"domain_scores_codex":[0.9947425,0.002917537,0.0002316536,0.0005952699,0.001155854,0.0003570772],"domain_scores_gemma":[0.9553038,0.03328168,0.002354759,0.002515396,0.004931005,0.001613319],"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":[0.0001198965,0.00007124269,0.002050213,0.0002593969,0.00008876423,0.0002160148,0.0002396051,0.1538798,0.002052334,0.8218493,0.001375466,0.01779811],"study_design_scores_gemma":[0.00001304437,0.00004547257,0.0003290665,0.00004293922,0.00001550761,0.00005920382,0.00001519474,0.850823,0.0009122188,0.1469517,0.0007665451,0.00002610067],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01042259,0.0005532646,0.985599,0.0004536083,0.0000936785,0.0000576621,0.0000515263,0.0002080397,0.002560546],"genre_scores_gemma":[0.6049209,0.001970904,0.3763709,0.0008891462,0.0004638174,0.00100657,0.0004715222,0.0007497591,0.01315641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01918491,"threshold_uncertainty_score":0.1014607,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963004847","doi":"","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Thompson sampling; Asymptotically optimal algorithm; Index (typography); Frequentist inference; Gaussian; Mathematical optimization; Computer science; Mathematics; Mathematical economics; Bayesian probability; Statistics; Artificial intelligence; Bayesian inference","authors":[{"name":"Tor Lattimore","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2738514103519363,"gpt":0.459272651460563,"spread":0.1854212411086267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006262658,0.001752922,0.001956349,0.0008353637,0.0009905315,0.003138911,0.002848126,0.002332077,0.005086148],"category_scores_gemma":[0.03448705,0.0008251545,0.001066117,0.001123942,0.002679692,0.003705124,0.002134305,0.00453853,0.0007702297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003715884,"about_ca_system_score_gemma":0.002778605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003164848,"about_ca_topic_score_gemma":0.002919307,"domain_scores_codex":[0.9972795,0.001235446,0.00008970468,0.0003938606,0.0006071026,0.0003943029],"domain_scores_gemma":[0.9700551,0.02480128,0.001869818,0.001520952,0.0008404811,0.0009123874],"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":[0.0004428278,0.0001674261,0.00105431,0.0001237854,0.0000848457,0.0001099913,0.0001423077,0.7868656,0.001585216,0.1829065,0.003356966,0.02316013],"study_design_scores_gemma":[0.00001909211,0.00003834487,0.0001273065,0.00001406645,0.000009513215,0.00001777325,0.00001216911,0.9539686,0.000384003,0.04514504,0.0002535439,0.00001053611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06562682,0.0009926417,0.917113,0.001542477,0.0001326301,0.0001034739,0.0001916948,0.0006233411,0.01367398],"genre_scores_gemma":[0.8792983,0.0008725304,0.1113256,0.0005221107,0.0002306691,0.0002587755,0.0002875244,0.0002914123,0.006913028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006262658,"threshold_uncertainty_score":0.03312051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W593234165","doi":"","title":"The sample complexity of agnostic learning under deterministic labels","year":2014,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","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 Waterloo","funders":"","keywords":"Sample complexity; Dimension (graph theory); Computer science; Class (philosophy); Sample (material); Function (biology); Set (abstract data type); VC dimension; Binary number; Artificial intelligence; Probably approximately correct learning; Computational complexity theory; Machine learning; Theoretical computer science; Algorithm; Mathematics; Computational learning theory; Active learning (machine learning); Combinatorics","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Ruth Urner","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03920515464262433,"gpt":0.2815507529389313,"spread":0.2423455982963069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01270111,0.001178077,0.00243888,0.00123934,0.001231807,0.00430878,0.003245408,0.002873197,0.003021201],"category_scores_gemma":[0.0841739,0.001065373,0.001502542,0.001479054,0.003795999,0.009947721,0.004130658,0.005550552,0.0005991508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004227178,"about_ca_system_score_gemma":0.002657169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002063595,"about_ca_topic_score_gemma":0.00203125,"domain_scores_codex":[0.9896106,0.004722027,0.0006573863,0.002248214,0.002072667,0.0006892927],"domain_scores_gemma":[0.8608232,0.1192978,0.004333327,0.01135711,0.00286265,0.001325789],"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":[0.002207357,0.0004125736,0.01248381,0.0007282103,0.0002822425,0.0002674691,0.0006557585,0.5908399,0.005420724,0.2741611,0.007389394,0.1051514],"study_design_scores_gemma":[0.00007522441,0.0001163119,0.001347692,0.0000448899,0.0000325524,0.0001346361,0.00005715348,0.7880032,0.001769722,0.2077252,0.0006607745,0.00003262799],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2493138,0.001701293,0.7330968,0.005574825,0.00009699439,0.0002364311,0.001046163,0.001416733,0.007516889],"genre_scores_gemma":[0.8216256,0.000926794,0.1691489,0.001153412,0.0002782125,0.0005483532,0.002177966,0.0003951072,0.003745581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01270111,"threshold_uncertainty_score":0.06717068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2475351935","doi":"","title":"Learning and Testing Junta Distributions","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"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":"Hypercube; Uniform distribution (continuous); Distribution (mathematics); Mathematics; Boolean function; Property testing; Domain (mathematical analysis); Combinatorics; Discrete mathematics; Set (abstract data type); Algorithm; Computer science; Statistics; Mathematical analysis","authors":[{"name":"Maryam Aliakbarpour","is_ca":false},{"name":"Eric Blais","is_ca":true},{"name":"Ronitt Rubinfeld","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02196962589253052,"gpt":0.2657186468250975,"spread":0.243749020932567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01185183,0.001300069,0.002412288,0.002192788,0.001998957,0.002937544,0.004802602,0.003304148,0.002421263],"category_scores_gemma":[0.1087831,0.001151615,0.002192261,0.002225598,0.005043691,0.01172979,0.00455224,0.004854247,0.0006047837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00210759,"about_ca_system_score_gemma":0.001989709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001710429,"about_ca_topic_score_gemma":0.001390546,"domain_scores_codex":[0.9861891,0.004287927,0.0009721044,0.004986236,0.002581268,0.0009834544],"domain_scores_gemma":[0.8912845,0.08912706,0.004853243,0.008752119,0.004022405,0.001960768],"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":[0.003271665,0.001084265,0.04890498,0.0006300967,0.0007066466,0.001062742,0.001165999,0.4599885,0.007819266,0.2187465,0.005111931,0.2515074],"study_design_scores_gemma":[0.00009410142,0.0002283882,0.001549645,0.00003625733,0.00003802324,0.0002802259,0.0001633232,0.7899922,0.003140656,0.2036086,0.0008284404,0.000040081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2088155,0.0002956979,0.7857292,0.001540007,0.00008081682,0.000153506,0.000417178,0.0008121886,0.002155951],"genre_scores_gemma":[0.8196247,0.0001984499,0.1756098,0.0006983551,0.0002911194,0.0003527589,0.001566447,0.0001789654,0.001479411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01185183,"threshold_uncertainty_score":0.06267923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046684513","doi":"","title":"Locally Private Hypothesis Selection","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Differential privacy; Combinatorics; Mathematics; Omega; Distribution (mathematics); Discrete mathematics; Generalization; Probability distribution; Upper and lower bounds; Algorithm; Statistics; Physics","authors":[{"name":"Sivakanth Gopi","is_ca":false},{"name":"Gautam Kamath","is_ca":true},{"name":"Janardhan Kulkarni","is_ca":false},{"name":"Aleksandar Nikolov","is_ca":true},{"name":"Zhiwei Steven Wu","is_ca":false},{"name":"Huanyu Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05567489988836302,"gpt":0.2571248751803857,"spread":0.2014499752920227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01123178,0.001017374,0.00258769,0.001045158,0.001439834,0.003527164,0.004292418,0.002561408,0.01331001],"category_scores_gemma":[0.0453612,0.0007366408,0.001511026,0.00218704,0.003585703,0.008326879,0.006962378,0.004044465,0.002683722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00268945,"about_ca_system_score_gemma":0.002517399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007806047,"about_ca_topic_score_gemma":0.0008055327,"domain_scores_codex":[0.9855096,0.007844562,0.0004765583,0.002954623,0.002182747,0.001032036],"domain_scores_gemma":[0.943781,0.03938086,0.002272722,0.01206114,0.001412435,0.00109183],"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":[0.003467026,0.0006491307,0.01026646,0.0008439203,0.0005118334,0.001715771,0.001440242,0.1591052,0.0138806,0.4611973,0.01868,0.3282425],"study_design_scores_gemma":[0.0002936055,0.0003600707,0.001377686,0.00005023415,0.0000826575,0.0005993317,0.0002049082,0.5400621,0.008230841,0.442461,0.006218483,0.00005898866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03742661,0.0006430765,0.9486169,0.002773075,0.0001186665,0.0003214293,0.0007376999,0.001706721,0.007655891],"genre_scores_gemma":[0.773031,0.0004051385,0.2146023,0.001563968,0.0004890441,0.0006263825,0.001374992,0.0002705935,0.007636533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01331001,"threshold_uncertainty_score":0.05940002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963800416","doi":"","title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematical proof; Markov decision process; Contraction (grammar); Property (philosophy); Computer science; Mathematics; Applied mathematics; Mathematical optimization; Measure (data warehouse); Class (philosophy); Markov process; Linear model; Artificial intelligence; Machine learning; Statistics","authors":[{"name":"Bernardo Ávila Pires","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0519210604033747,"gpt":0.2934808180844667,"spread":0.2415597576810921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01071265,0.002455215,0.002485827,0.001451945,0.0007072944,0.002737503,0.002495757,0.002037426,0.003513793],"category_scores_gemma":[0.05358884,0.001047204,0.001562213,0.0009388541,0.003517204,0.005631635,0.004145496,0.005475139,0.0005184544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004202228,"about_ca_system_score_gemma":0.003320546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003676258,"about_ca_topic_score_gemma":0.002052895,"domain_scores_codex":[0.994065,0.00239491,0.0002551861,0.0008922321,0.001869509,0.0005233228],"domain_scores_gemma":[0.9556433,0.03736877,0.002347472,0.001690443,0.002174469,0.0007756434],"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":[0.00008267196,0.00004476897,0.0003499541,0.0001185088,0.00004612098,0.0000312561,0.00006980357,0.9275808,0.0005475566,0.06156372,0.0003396934,0.00922502],"study_design_scores_gemma":[0.000003741375,0.00002639396,0.00002461703,0.00001769848,0.000005568214,0.000007766376,0.000004903412,0.9742284,0.000243049,0.0253048,0.0001273805,0.000005658668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006360601,0.0004550281,0.9913431,0.0002550637,0.00003344291,0.00002645032,0.00003235727,0.0001884765,0.001305478],"genre_scores_gemma":[0.7997343,0.001261194,0.1945091,0.000401108,0.0001837455,0.0003439819,0.0002864185,0.0004472861,0.002832884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01071265,"threshold_uncertainty_score":0.05665463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153773643","doi":"","title":"Sample Compression for Multi-label Concept Classes","year":2014,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","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 Regina","funders":"","keywords":"Dimension (graph theory); Sample (material); Compression (physics); VC dimension; Class (philosophy); Mathematics; Extension (predicate logic); Binary number; Sample size determination; Data compression; Computer science; Artificial intelligence; Algorithm; Combinatorics; Arithmetic; Statistics","authors":[{"name":"Rahim Samei","is_ca":true},{"name":"Pavel Semukhin","is_ca":true},{"name":"Boting Yang","is_ca":true},{"name":"Sandra Zilles","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05949915847716699,"gpt":0.3286035096503646,"spread":0.2691043511731976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004799524,0.0007622713,0.001304615,0.002288156,0.001278688,0.002261064,0.001776544,0.001358524,0.003620094],"category_scores_gemma":[0.02767939,0.0004009689,0.0008521033,0.002813506,0.002621232,0.006711695,0.00367746,0.002855125,0.0004738175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002954307,"about_ca_system_score_gemma":0.001255151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008768222,"about_ca_topic_score_gemma":0.0005550441,"domain_scores_codex":[0.9924238,0.001564807,0.0003198368,0.001115171,0.003987876,0.0005885969],"domain_scores_gemma":[0.9729947,0.01738925,0.001492171,0.005399219,0.002213805,0.0005107704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001296916,0.0004895813,0.005847716,0.0006268914,0.0001551073,0.0002713973,0.0008688366,0.1476828,0.02553636,0.3580032,0.00717179,0.4520494],"study_design_scores_gemma":[0.00008315459,0.0003170153,0.001994368,0.00009147092,0.00003945466,0.0006232263,0.0001822233,0.7999318,0.02441863,0.164718,0.007546629,0.00005406489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1373966,0.002068716,0.850525,0.001625658,0.0001608018,0.0003609018,0.0005690417,0.000636111,0.006657218],"genre_scores_gemma":[0.7506407,0.0009816427,0.2414175,0.0006717686,0.0004595443,0.0004296958,0.001285568,0.0001685106,0.003945155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004799524,"threshold_uncertainty_score":0.02538264,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1956860503","doi":"","title":"Learnability of Solutions to Conjunctive Queries: The Full Dichotomy","year":2015,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","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":"McMaster University","funders":"","keywords":"Learnability; Property (philosophy); Theoretical computer science; Computer science; Conjunctive query; Mathematics; Discrete mathematics; Space (punctuation); Artificial intelligence; Algebra over a field; Relational database; Pure mathematics; Information retrieval","authors":[{"name":"Hubie Chen","is_ca":false},{"name":"Matthew Valeriote","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0490561778058568,"gpt":0.2872785683180127,"spread":0.2382223905121559,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00998201,0.0007715009,0.001335875,0.001716212,0.001687129,0.003904174,0.003185042,0.002572785,0.005599536],"category_scores_gemma":[0.05866417,0.0007957167,0.002163533,0.001469487,0.009063,0.01919488,0.007623987,0.005737208,0.0006172342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002235225,"about_ca_system_score_gemma":0.001377571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00127783,"about_ca_topic_score_gemma":0.0008760752,"domain_scores_codex":[0.9894721,0.003987099,0.0005619491,0.002306816,0.003039356,0.0006327274],"domain_scores_gemma":[0.9574124,0.03371097,0.001765096,0.004202364,0.002025316,0.0008839433],"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":[0.0001426579,0.00009684986,0.001474995,0.0002276574,0.00004535527,0.00009336229,0.0009819039,0.008629328,0.001026017,0.9520817,0.001592293,0.03360791],"study_design_scores_gemma":[0.00002403145,0.00002965304,0.0002430875,0.00002313018,0.00001437808,0.00006627188,0.0001084016,0.03193244,0.0006144522,0.9661687,0.0007655274,0.000009957447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1807553,0.001312733,0.7841576,0.01086913,0.0000790034,0.0001272476,0.0004840648,0.0007289844,0.02148599],"genre_scores_gemma":[0.9180982,0.0006997286,0.07452991,0.001068943,0.0003031948,0.0002281534,0.0006984681,0.000185714,0.004187717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00998201,"threshold_uncertainty_score":0.05279052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174935984","doi":"","title":"Size and Depth Separation in Approximating Natural Functions with Neural Networks","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","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 Toronto","funders":"","keywords":"Lipschitz continuity; Bounded function; Mathematics; Function (biology); Polynomial; Artificial neural network; Constant (computer programming); Computational complexity theory; Discrete mathematics; Algorithm; Computer science; Pure mathematics; Artificial intelligence; Mathematical analysis","authors":[{"name":"Gal Vardi","is_ca":false},{"name":"Daniel Reichman","is_ca":false},{"name":"Toniann Pitassi","is_ca":true},{"name":"Ohad Shamir","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01089248834608676,"gpt":0.2541372997461577,"spread":0.243244811400071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002249872,0.001300104,0.0009038605,0.0008891154,0.0007273795,0.002020515,0.002046663,0.001663028,0.003546507],"category_scores_gemma":[0.01962749,0.000798873,0.001455312,0.000688157,0.002534882,0.009179484,0.003690764,0.003530227,0.0005604406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003639001,"about_ca_system_score_gemma":0.001513928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004462123,"about_ca_topic_score_gemma":0.00626872,"domain_scores_codex":[0.9981706,0.000566676,0.0001045806,0.0004168603,0.0005097059,0.0002315154],"domain_scores_gemma":[0.9911142,0.00670441,0.0004523427,0.001048602,0.000410522,0.0002697904],"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":[0.001050649,0.000157652,0.006625864,0.0005000503,0.000123872,0.0002587798,0.000799568,0.5878466,0.01403047,0.2672983,0.003983139,0.1173251],"study_design_scores_gemma":[0.00002284693,0.00007575023,0.0004273724,0.00003908793,0.00002902606,0.00007999965,0.00005514075,0.858995,0.003753682,0.1343496,0.002156436,0.00001601969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1834853,0.001693191,0.79198,0.003640998,0.0000968615,0.0001153199,0.0004273904,0.001917666,0.01664326],"genre_scores_gemma":[0.7567539,0.0009423294,0.2338996,0.0007982903,0.0001149842,0.0001844053,0.0005477031,0.0004031052,0.006355707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004462123,"threshold_uncertainty_score":0.02640289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174263485","doi":"","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","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":"Regret; Randomness; Intuition; Computer science; Mathematical economics; Mathematical optimization; Fictitious play; Mathematics; Game theory; Machine learning; Statistics","authors":[{"name":"Mark Sellke","is_ca":false},{"name":"Sébastien Bubeck","is_ca":false},{"name":"Thomas Budzinski","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1626154911242037,"gpt":0.4264370049582369,"spread":0.2638215138340332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006025058,0.001639483,0.002389413,0.000774823,0.001064078,0.002874845,0.002633716,0.003043856,0.001676407],"category_scores_gemma":[0.02000481,0.0008338852,0.001360325,0.001233412,0.003425526,0.003011739,0.003084616,0.00276079,0.0004653943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002116095,"about_ca_system_score_gemma":0.001686862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002027609,"about_ca_topic_score_gemma":0.001240767,"domain_scores_codex":[0.9946764,0.00266699,0.0001800008,0.0007854932,0.0007421059,0.0009490511],"domain_scores_gemma":[0.9852809,0.01070429,0.001595228,0.001092647,0.0006343409,0.0006924905],"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":[0.0003580715,0.0001219727,0.0008491413,0.0001081458,0.0001111924,0.0002653758,0.0001323304,0.8836059,0.001488198,0.1061936,0.001163666,0.005602449],"study_design_scores_gemma":[0.00003664833,0.00007049189,0.0001337103,0.00001376077,0.00001592006,0.00005695644,0.00002825378,0.9452104,0.0003540688,0.05383158,0.0002349223,0.0000133044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1386164,0.0006513917,0.8448364,0.001832472,0.00009896597,0.0001054384,0.0002043953,0.0002512264,0.01340345],"genre_scores_gemma":[0.9608389,0.0002407937,0.03472192,0.0003796098,0.0001256341,0.0001741235,0.0000836412,0.00004891028,0.003386355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006025058,"threshold_uncertainty_score":0.03186393,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173288964","doi":"","title":"Nonparametric Regression with Shallow Overparametrized Neural Networks Trained by GD with Early Stopping","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","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","funders":"","keywords":"Early stopping; Lipschitz continuity; Artificial neural network; Nonparametric statistics; Noise (video); Kernel (algebra); Nonparametric regression; Kernel regression; Computer science; Regression; Mathematics; Stochastic gradient descent; Gradient descent; Artificial intelligence; Algorithm; Pattern recognition (psychology); Statistics; Discrete mathematics; Mathematical analysis","authors":[{"name":"Ilja Kuzborskij","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01753391270644775,"gpt":0.24806449918661,"spread":0.2305305864801622,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006484394,0.001626904,0.001946852,0.0007266862,0.0003570178,0.001239426,0.002110431,0.002618199,0.001205025],"category_scores_gemma":[0.02560729,0.0009077867,0.0009642228,0.0006715273,0.00257139,0.003118168,0.003699042,0.003602314,0.0003428084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001589715,"about_ca_system_score_gemma":0.001200841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003313972,"about_ca_topic_score_gemma":0.003314437,"domain_scores_codex":[0.998487,0.0008160195,0.00007469867,0.0002722134,0.0002077609,0.000142242],"domain_scores_gemma":[0.9892306,0.007743221,0.0007707548,0.00117545,0.0007894707,0.0002904727],"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":[0.000167453,0.00004230166,0.001666419,0.0001232606,0.00007129694,0.0001296922,0.0001312107,0.9205435,0.002978138,0.04801247,0.0005892423,0.02554509],"study_design_scores_gemma":[0.000007084474,0.00002529643,0.00005919179,0.000007218225,0.000003947156,0.000006712629,0.000002764814,0.9909254,0.0003926741,0.008494125,0.00007077002,0.00000487194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03533008,0.0003314222,0.9628295,0.0004153699,0.00002361581,0.00003245196,0.00005479511,0.0002981737,0.0006846035],"genre_scores_gemma":[0.6778373,0.0003449186,0.3165409,0.000600745,0.00006202004,0.0002080507,0.0002590594,0.0002275394,0.003919468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006484394,"threshold_uncertainty_score":0.03429312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964762712","doi":"","title":"On Mean Estimation for General Norms with Statistical Queries.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Complexity and Algorithms in Graphs","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 Toronto","funders":"","keywords":"Normed vector space; Combinatorics; Distribution (mathematics); Mathematics; Oracle; Norm (philosophy); Space (punctuation); Upper and lower bounds; Discrete mathematics; Computer science; Mathematical analysis","authors":[{"name":"Jerry Li","is_ca":false},{"name":"Aleksandar Nikolov","is_ca":true},{"name":"Ilya Razenshteyn","is_ca":false},{"name":"Erik Waingarten","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01814144913091369,"gpt":0.2612117571156775,"spread":0.2430703079847638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01847992,0.002515575,0.004567126,0.002347899,0.002095024,0.005899673,0.006954592,0.005145278,0.00535677],"category_scores_gemma":[0.1269139,0.001361207,0.002574609,0.004535113,0.00657119,0.02282172,0.008077897,0.008667697,0.001371247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005147864,"about_ca_system_score_gemma":0.003401132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004045252,"about_ca_topic_score_gemma":0.002233102,"domain_scores_codex":[0.9811878,0.009600726,0.0008153176,0.003344562,0.003750969,0.001300537],"domain_scores_gemma":[0.7761577,0.1982578,0.007528964,0.01151314,0.004139335,0.002403044],"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":[0.001475506,0.0005200987,0.006332729,0.0008513729,0.0003912614,0.000493318,0.001245244,0.2814725,0.003727806,0.6086988,0.01269905,0.08209223],"study_design_scores_gemma":[0.00005183742,0.0001062698,0.000504309,0.00003433283,0.00003499627,0.0002042512,0.0001261025,0.5628596,0.001001606,0.4338728,0.001165684,0.0000381115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03453717,0.002324935,0.9541986,0.004286863,0.0001228798,0.0001466439,0.0005859716,0.0007038707,0.003093123],"genre_scores_gemma":[0.6055234,0.003230072,0.3758132,0.002399247,0.001832699,0.0008405748,0.002917205,0.0008373401,0.006606228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01847992,"threshold_uncertainty_score":0.09773231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174325474","doi":"","title":"Asymptotically Optimal Information-Directed Sampling","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Asymptotically optimal algorithm; Frequentist inference; Regret; Thompson sampling; Mathematical optimization; Computer science; Simple (philosophy); Connection (principal bundle); Upper and lower bounds; Sampling (signal processing); Mathematics; Bayesian probability; Artificial intelligence; Bayesian inference; Machine learning","authors":[{"name":"Johannes Kirschner","is_ca":false},{"name":"Tor Lattimore","is_ca":false},{"name":"Claire Vernade","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1378188340422346,"gpt":0.4246927229571403,"spread":0.2868738889149057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003671037,0.0009870294,0.001638713,0.0009180969,0.0006688572,0.001738859,0.002337466,0.001678493,0.00370083],"category_scores_gemma":[0.02147311,0.0006957942,0.0007564368,0.001000353,0.001778953,0.002104714,0.002358869,0.002659004,0.001017038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002047173,"about_ca_system_score_gemma":0.002524137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001809786,"about_ca_topic_score_gemma":0.002628596,"domain_scores_codex":[0.9974957,0.001201585,0.00009696405,0.0003619257,0.0006131988,0.0002306451],"domain_scores_gemma":[0.9924948,0.005381795,0.0003848217,0.0008692683,0.0005387458,0.000330478],"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":[0.0004184564,0.0002629376,0.001495985,0.0002105374,0.0000863471,0.0001327045,0.0001741174,0.5031307,0.002536129,0.3548156,0.006423927,0.1303126],"study_design_scores_gemma":[0.00003706185,0.00003290403,0.00006656585,0.00001674664,0.000006940715,0.00002844583,0.000008898449,0.9254094,0.0006050318,0.07284599,0.000934264,0.000007710461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01081483,0.0001999061,0.9849606,0.0003605152,0.00004652952,0.00007954756,0.00007384305,0.0004573143,0.003006898],"genre_scores_gemma":[0.4950505,0.000335307,0.4984955,0.0005280424,0.0001481827,0.0004525995,0.0004352737,0.0002326711,0.004321934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00370083,"threshold_uncertainty_score":0.01941454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176194860","doi":"","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","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","funders":"","keywords":"Convergence (economics); Stochastic gradient descent; Applied mathematics; Mathematics; Criticality; Rate of convergence; Limit (mathematics); Statistical physics; Mathematical optimization; Computer science; Mathematical analysis; Physics; Artificial neural network","authors":[{"name":"Courtney Paquette","is_ca":true},{"name":"Ki‐Won Lee","is_ca":false},{"name":"Fabián Pedregosa","is_ca":false},{"name":"Elliot Paquette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01944880602390112,"gpt":0.2931511756311167,"spread":0.2737023696072156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003448596,0.0008762229,0.00104737,0.001477006,0.0007684032,0.00187325,0.001699476,0.001178409,0.003076253],"category_scores_gemma":[0.02688495,0.0005652046,0.0009547686,0.0007140791,0.003133572,0.004556122,0.002519175,0.002936778,0.000415959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001857923,"about_ca_system_score_gemma":0.001156239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002052843,"about_ca_topic_score_gemma":0.001665575,"domain_scores_codex":[0.9988205,0.0003885477,0.00005501478,0.0002402427,0.0003452382,0.0001504678],"domain_scores_gemma":[0.9875925,0.008959731,0.0009306864,0.001104321,0.0009091548,0.0005036161],"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":[0.00006742102,0.00006640222,0.001578533,0.0001637288,0.00006878712,0.0002704462,0.0001883573,0.3530551,0.003946422,0.6253328,0.002134021,0.01312799],"study_design_scores_gemma":[0.000004587479,0.00001478687,0.000178903,0.00001401557,0.000005753756,0.00003628068,0.00001205016,0.8652208,0.0007282647,0.133254,0.0005191955,0.0000113659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05393384,0.001071983,0.9358569,0.001202461,0.00007796931,0.000046843,0.00009183431,0.0004370124,0.007281103],"genre_scores_gemma":[0.865642,0.001242162,0.1268908,0.0004575547,0.0001985677,0.0002505286,0.000219785,0.0004419649,0.004656817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003448596,"threshold_uncertainty_score":0.01823813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174799275","doi":"","title":"Learning and testing junta distributions with sub cube conditioning","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","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":"University of Waterloo","funders":"","keywords":"Conditioning; Combinatorics; Distribution (mathematics); Mathematics; Logarithm; Bhattacharyya distance; Probability distribution; Discrete mathematics; Algorithm; Computer science; Statistics; Artificial intelligence; Mathematical analysis","authors":[{"name":"Xi Chen","is_ca":false},{"name":"Rajesh Jayaram","is_ca":false},{"name":"Amit Levi","is_ca":true},{"name":"Erik Waingarten","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01607629887651031,"gpt":0.2527456540907559,"spread":0.2366693552142456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007194861,0.002105433,0.002689458,0.001464314,0.001577578,0.003287988,0.005979499,0.002983042,0.00777153],"category_scores_gemma":[0.07238828,0.001030519,0.002795173,0.002341473,0.003438934,0.009807803,0.006473823,0.006532435,0.00211495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00206623,"about_ca_system_score_gemma":0.002812539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003965217,"about_ca_topic_score_gemma":0.0047672,"domain_scores_codex":[0.991583,0.002821504,0.0005723474,0.002502666,0.001892223,0.0006281614],"domain_scores_gemma":[0.9298368,0.05325544,0.002523942,0.00973039,0.003011523,0.001641891],"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":[0.00450004,0.001609259,0.05058598,0.000638981,0.0005961251,0.0008212796,0.0008896531,0.4183912,0.007445537,0.1925536,0.02697094,0.2949974],"study_design_scores_gemma":[0.0001024661,0.0001983339,0.001076902,0.00002848478,0.00002640755,0.0001716869,0.0001206942,0.8576603,0.002575392,0.1369483,0.001062283,0.00002872881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.230215,0.0007719811,0.7532955,0.002881724,0.0002157006,0.0003835358,0.001718258,0.005577236,0.004941028],"genre_scores_gemma":[0.7244607,0.000329905,0.2609221,0.001653109,0.0004299077,0.0007161081,0.006411941,0.0009361784,0.004139928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00777153,"threshold_uncertainty_score":0.03805053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175841314","doi":"","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture MDPs","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Mathematics; Minimax; Logarithm; Estimator; Bounded function; Combinatorics; Discrete mathematics; Regret; Mathematical optimization; Markov process; Computer science; Artificial intelligence; Statistics","authors":[{"name":"Dongruo Zhou","is_ca":false},{"name":"Quanquan Gu","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1281220911290732,"gpt":0.423888662028909,"spread":0.2957665708998357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004297545,0.001944089,0.002660741,0.0006502641,0.0005695617,0.001616885,0.002210754,0.002265602,0.003234463],"category_scores_gemma":[0.01923783,0.001187303,0.0009558189,0.0006457453,0.002643615,0.002936811,0.002687052,0.004106457,0.000481903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002921406,"about_ca_system_score_gemma":0.002061725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006532812,"about_ca_topic_score_gemma":0.003883637,"domain_scores_codex":[0.9983766,0.000770126,0.00006622304,0.0003562263,0.0002129473,0.0002179875],"domain_scores_gemma":[0.9869078,0.01099505,0.0008075689,0.0004361706,0.0004248671,0.0004286142],"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":[0.0001287683,0.00006390307,0.0005349607,0.00007854681,0.00005560245,0.00005733547,0.0000489436,0.9600255,0.0003948712,0.03024451,0.0005600091,0.007806947],"study_design_scores_gemma":[0.00001182887,0.00001627415,0.00003329765,0.00000484093,0.000003930892,0.000003476604,0.000002891682,0.9901966,0.0000870822,0.009557727,0.00007919826,0.000002889061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04323617,0.0009295819,0.9511062,0.0009550775,0.00006668054,0.00007623476,0.00009655034,0.0003575801,0.003175835],"genre_scores_gemma":[0.8814241,0.0006222217,0.1108362,0.0005068816,0.0001162499,0.0002732524,0.0002337445,0.0001928467,0.005794432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006532812,"threshold_uncertainty_score":0.02272785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196848038","doi":"","title":"Open Problem: Are all VC-classes CPAC learnable?","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science","authors":[{"name":"Sushant Agarwal","is_ca":true},{"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":0.04229467534172605,"gpt":0.3155514981952951,"spread":0.2732568228535691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002375958,0.001018874,0.001730632,0.001180314,0.003085383,0.008209666,0.003758373,0.005286409,0.02491465],"category_scores_gemma":[0.03073993,0.0008364489,0.001503516,0.002179039,0.004216923,0.0182739,0.003416859,0.009587871,0.002675443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002479883,"about_ca_system_score_gemma":0.003382986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003838206,"about_ca_topic_score_gemma":0.003478912,"domain_scores_codex":[0.9956664,0.0005621511,0.0001806147,0.00227108,0.0006235003,0.0006961694],"domain_scores_gemma":[0.9696998,0.02045724,0.00149813,0.003978292,0.002730152,0.00163635],"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":[0.0007471105,0.0006032599,0.01307667,0.001152018,0.0002627916,0.0001658851,0.0008034615,0.01711882,0.002137798,0.5724533,0.08667717,0.3048017],"study_design_scores_gemma":[0.00008549846,0.0001065058,0.002963713,0.0001636788,0.00005472371,0.0002039558,0.0005863958,0.04003898,0.002019198,0.9389706,0.01476299,0.00004373353],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4488122,0.004918632,0.3794135,0.0429256,0.001812675,0.0003674013,0.01432284,0.003742529,0.1036846],"genre_scores_gemma":[0.9430348,0.0011586,0.03279374,0.002452881,0.0009351522,0.0002851876,0.005823225,0.0004472785,0.0130691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02491465,"threshold_uncertainty_score":0.0833478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175907392","doi":"","title":"On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Markov Chains and Monte Carlo Methods","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 Toronto","funders":"","keywords":"Monte Carlo method; Smoothness; Lipschitz continuity; Rate of convergence; Physics; Combinatorics; BETA (programming language); Convex function; Distribution (mathematics); Mathematics; Regular polygon; Mathematical analysis; Statistics; Geometry","authors":[{"name":"Murat A. Erdogdu","is_ca":true},{"name":"Rasa Hosseinzadeh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06749056405776141,"gpt":0.3460512910546785,"spread":0.2785607269969171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01015665,0.001492449,0.001673994,0.001458789,0.001389655,0.001988206,0.003147403,0.00232315,0.003233605],"category_scores_gemma":[0.05688222,0.0008096877,0.001558801,0.0008644192,0.004968111,0.00476789,0.004015529,0.004295432,0.0004887366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002519513,"about_ca_system_score_gemma":0.00201696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005815599,"about_ca_topic_score_gemma":0.004626976,"domain_scores_codex":[0.9981244,0.001070088,0.00005344765,0.0002430477,0.0002992173,0.0002097283],"domain_scores_gemma":[0.9560564,0.0378729,0.001586466,0.001534428,0.001627023,0.001322809],"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":[0.0002864409,0.0001076071,0.003963514,0.0002791783,0.00009057664,0.0002367593,0.0003274229,0.5231228,0.002699964,0.4563288,0.002171536,0.01038545],"study_design_scores_gemma":[0.00001514682,0.00003103098,0.0001891594,0.00003765026,0.000009602818,0.00002499698,0.00002136941,0.9300367,0.0004941398,0.06878212,0.0003412224,0.00001691023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1116267,0.002080108,0.8689936,0.003075062,0.000159437,0.0001267669,0.0001762097,0.0005778085,0.01318421],"genre_scores_gemma":[0.8356552,0.002149785,0.1487513,0.00108847,0.0002389649,0.0005997261,0.0004542747,0.001047345,0.01001502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01015665,"threshold_uncertainty_score":0.0537141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}