{"meta":{"query_hash":"1592200117c9","filters":{"venue":"Conference on Learning Theory"},"cohort_total":27,"direct_labels_cover":0,"predictions_cover":27,"exported":27,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/1592200117c9","api":"https://metacan.xera.ac/api/v1/cohort?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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10947263266089535,"score_gpt":0.3005835196592879,"score_spread":0.19111088699839257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589919686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60353523,0.000062335515,0.3912469,0.0013244121,0.00022695119,0.00035587294,0.00011559616,0.00030445616,0.0028282048],"genre_scores_gemma":[0.99329215,0.000056849694,0.005183752,0.0000630356,0.000025813406,0.000008339051,0.00022925781,0.000014699273,0.0011260922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962797,0.0016518782,0.00052282016,0.00074815605,0.00049976434,0.00029765035],"domain_scores_gemma":[0.9950982,0.0013067942,0.00067249726,0.002539643,0.00029163982,0.00009123523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020334017,0.00023669821,0.0005220857,0.0003124982,0.00055214285,0.000068019384,0.0025889603,0.000101691956,0.00023507405],"category_scores_gemma":[0.0034434176,0.00014212269,0.00015433393,0.0016103238,0.00064816576,0.00033173995,0.0009704476,0.0007906125,0.000015297213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028441023,0.0006297041,0.26838067,0.00016717121,0.0010545278,0.00005502323,0.009647001,0.018214641,0.0054311864,0.6018642,0.0002038829,0.09406758],"study_design_scores_gemma":[0.00053434394,0.0002254615,0.067984015,0.0001015096,0.0002736543,0.00003210279,0.0008228603,0.9206918,0.0008382852,0.0056510908,0.002489695,0.00035519945],"about_ca_topic_score_codex":0.00037131627,"about_ca_topic_score_gemma":0.00006921801,"teacher_disagreement_score":0.90247715,"about_ca_system_score_codex":0.000026949649,"about_ca_system_score_gemma":0.00022255968,"threshold_uncertainty_score":0.57955956},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06272562214348579,"score_gpt":0.3247416508144249,"score_spread":0.2620160286709391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1877234769","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07354822,0.00022798055,0.4170951,0.006971203,0.0034449804,0.0010232847,0.000001715952,0.0016054065,0.4960821],"genre_scores_gemma":[0.9520539,0.000013181722,0.037853666,0.00032949616,0.00014323555,0.000026938387,0.000015095245,0.00003563509,0.009528859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661,0.0014062639,0.0002611984,0.00078592444,0.00047016476,0.00046648755],"domain_scores_gemma":[0.99797136,0.0005576753,0.00024993374,0.00071698194,0.00020233418,0.00030171798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034578163,0.00029129515,0.0003126099,0.00015190917,0.000540917,0.00062283996,0.0018920449,0.000119295204,0.000057531233],"category_scores_gemma":[0.0013502829,0.0002473911,0.000064314045,0.00021374619,0.000084148305,0.0006434807,0.001462295,0.0013433368,0.0006283189],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029057366,0.00008613978,0.00011007274,0.000006425611,0.000022104028,0.000029823139,0.0042195665,0.0039388402,0.00022160394,0.8096939,0.0012123216,0.18016863],"study_design_scores_gemma":[0.009279564,0.008050493,0.0005857079,0.0013078945,0.000070322385,0.000076274606,0.003997988,0.4342583,0.0012045079,0.41455472,0.12429395,0.0023202645],"about_ca_topic_score_codex":0.00008203436,"about_ca_topic_score_gemma":0.0000022022073,"teacher_disagreement_score":0.87850565,"about_ca_system_score_codex":0.00010030495,"about_ca_system_score_gemma":0.00024155376,"threshold_uncertainty_score":0.99999785},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0490561778058568,"score_gpt":0.28727856831801274,"score_spread":0.23822239051215593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1956860503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05022876,0.000067704525,0.8961589,0.005178922,0.00048758482,0.00030388992,0.0000023073396,0.00031554291,0.04725642],"genre_scores_gemma":[0.99346054,0.000004460808,0.0029271424,0.00028769983,0.000068300076,0.000033284985,0.0000016238238,0.00001079586,0.0032061555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976866,0.0009786251,0.00023321742,0.0004043425,0.000364002,0.00033321127],"domain_scores_gemma":[0.9979053,0.00065794046,0.00015520594,0.0007088979,0.00037728448,0.00019536633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028879263,0.00017157526,0.00022783756,0.000096009,0.00029228616,0.000108012224,0.0010221603,0.000061135856,0.000087086846],"category_scores_gemma":[0.002712515,0.000118905424,0.00007680151,0.00039031645,0.00027635804,0.00016021868,0.00037946735,0.00066112174,0.00024964518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104516155,0.00007317875,0.0005990961,0.000008027703,0.000023927842,0.0000027995334,0.009787045,0.0073990375,0.00029331562,0.9187286,0.0004949641,0.06248549],"study_design_scores_gemma":[0.0021750769,0.0062435116,0.013121102,0.0003729557,0.000057365793,0.000048201844,0.01512684,0.2973451,0.0013834533,0.5075107,0.15516384,0.0014518304],"about_ca_topic_score_codex":0.00006652935,"about_ca_topic_score_gemma":0.000005756354,"teacher_disagreement_score":0.94323176,"about_ca_system_score_codex":0.00005204059,"about_ca_system_score_gemma":0.0002949102,"threshold_uncertainty_score":0.48488224},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05949915847716699,"score_gpt":0.3286035096503646,"score_spread":0.26910435117319764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153773643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020654346,0.00004269485,0.9929924,0.0005139163,0.00043182832,0.00016439923,0.0000031709158,0.0004935473,0.0032925934],"genre_scores_gemma":[0.749171,0.000010179725,0.24509853,0.0005377235,0.00018923686,0.0000407511,0.000021933827,0.000026529628,0.0049041286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816453,0.0005359022,0.00020111729,0.000520967,0.00020378121,0.00037371242],"domain_scores_gemma":[0.9972623,0.0018531069,0.00016537016,0.0004555558,0.0001384051,0.00012525158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009713296,0.000212466,0.00025176178,0.00009057247,0.0004413685,0.00022197005,0.00084585603,0.00009570292,0.0000834905],"category_scores_gemma":[0.0018083588,0.00017878241,0.00007171061,0.0001208813,0.00010774081,0.00016957063,0.00017662195,0.0004893184,0.00009550877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001797275,0.000056964298,0.00015868722,0.000010384337,0.000007162917,4.725518e-7,0.00051280245,0.00081049296,0.00036811258,0.6062626,0.00018490726,0.39160943],"study_design_scores_gemma":[0.0010021793,0.00046722247,0.0003741981,0.000091563226,0.0000052559003,0.000001963055,0.00007886252,0.9411732,0.00051397213,0.029114349,0.026920654,0.0002565891],"about_ca_topic_score_codex":0.00001339414,"about_ca_topic_score_gemma":7.8315213e-7,"teacher_disagreement_score":0.9403627,"about_ca_system_score_codex":0.000018169383,"about_ca_system_score_gemma":0.00005505389,"threshold_uncertainty_score":0.72905356},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02196962589253052,"score_gpt":0.26571864682509755,"score_spread":0.24374902093256703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475351935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05432954,0.000065107975,0.9112205,0.0023206456,0.00020644582,0.00008345559,0.0000017047935,0.0008906107,0.030881984],"genre_scores_gemma":[0.983311,0.00003726901,0.006369432,0.00005805353,0.00008843831,0.000010048599,0.0000021842006,0.0000144014475,0.010109197],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830925,0.00045888926,0.00017273973,0.0004950803,0.00019179555,0.00037226154],"domain_scores_gemma":[0.99798334,0.0013702967,0.00012950593,0.00026363053,0.00010977722,0.00014346321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010054656,0.00018726804,0.00017236767,0.000100076424,0.0005770712,0.00021293196,0.00042716367,0.00006929474,0.00010689917],"category_scores_gemma":[0.0028634616,0.00013047234,0.000038126847,0.0002404083,0.00015118919,0.00023503948,0.00028227555,0.000575199,0.00022845433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059097165,0.000013901243,0.0059830365,0.0000046356276,0.000007148381,0.000008051718,0.00022493844,0.000045717377,0.0017867984,0.4179159,0.00002214906,0.5739818],"study_design_scores_gemma":[0.0039769015,0.0043560974,0.07113781,0.0024526413,0.000068282236,0.00035796195,0.0011202687,0.33380374,0.0040690713,0.44443896,0.13097136,0.003246917],"about_ca_topic_score_codex":0.0000068324543,"about_ca_topic_score_gemma":4.0025589e-7,"teacher_disagreement_score":0.9289814,"about_ca_system_score_codex":0.000029299114,"about_ca_system_score_gemma":0.00006653871,"threshold_uncertainty_score":0.5320507},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2738514103519363,"score_gpt":0.45927265146056295,"score_spread":0.18542124110862668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963004847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0753321,0.000037674796,0.92131346,0.0005330324,0.00024188489,0.00044418257,0.00009442045,0.000055432098,0.0019478335],"genre_scores_gemma":[0.97462237,0.000029716555,0.00037805794,0.000028148079,0.00005332951,0.00004372451,0.000004959138,0.000020184485,0.024819486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588895,0.0010593417,0.00062012405,0.00067865435,0.0012905984,0.00046234962],"domain_scores_gemma":[0.98563784,0.011719859,0.00055931014,0.0009901285,0.00096462975,0.00012820362],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051325406,0.00021431445,0.0005271848,0.0006949424,0.00031508514,0.00012213887,0.0015011723,0.00015200103,0.0014449119],"category_scores_gemma":[0.030114017,0.000102831495,0.00036620453,0.0017583502,0.00059653015,0.00022018285,0.00022083407,0.0003834568,0.00010473119],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009838894,0.00019100955,0.026225843,0.000011508776,0.0005148713,0.000004701164,0.00087605655,0.041100945,0.0030542715,0.055278964,0.0003487114,0.87140924],"study_design_scores_gemma":[0.0052628336,0.0023309344,0.20755823,0.00036542147,0.00042479415,0.0000021464714,0.005722305,0.47520635,0.01167509,0.27471787,0.015692653,0.0010413965],"about_ca_topic_score_codex":0.0000062992376,"about_ca_topic_score_gemma":0.000036728663,"teacher_disagreement_score":0.9209354,"about_ca_system_score_codex":0.000063679145,"about_ca_system_score_gemma":0.0002685223,"threshold_uncertainty_score":0.9994679},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0519210604033747,"score_gpt":0.29348081808446674,"score_spread":0.24155975768109206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963800416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016897339,0.0000071539666,0.9836047,0.0013604157,0.00010978968,0.00051982334,0.0000015381991,0.00071618106,0.011990612],"genre_scores_gemma":[0.94151676,0.00001674277,0.031600088,0.00044495251,0.00009973693,0.00012360954,0.000015704021,0.00007344195,0.026108969],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968311,0.00027278758,0.00047101834,0.00082397216,0.0006782445,0.0009228412],"domain_scores_gemma":[0.99710447,0.0008285419,0.00045325083,0.0009167666,0.00043448887,0.0002624787],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011423086,0.000488501,0.00042109878,0.00042121086,0.00060628064,0.00028518325,0.0013223019,0.00018584967,0.00005324014],"category_scores_gemma":[0.00084171497,0.00033597634,0.00015956546,0.00034338105,0.00025879996,0.00073659467,0.00022578202,0.00058698683,0.00009424819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018821444,0.0000152219845,0.000053024523,0.00001908062,0.000026958858,0.0000018179347,0.0004753046,0.59856814,0.0004307534,0.39399788,0.000015751752,0.00620784],"study_design_scores_gemma":[0.0017329222,0.0015715811,0.000016343882,0.0003082883,0.000018177772,0.0000023174125,0.00008121869,0.97203183,0.00097192335,0.021512104,0.0012055776,0.0005477313],"about_ca_topic_score_codex":0.0000069815433,"about_ca_topic_score_gemma":9.0650025e-7,"teacher_disagreement_score":0.9520047,"about_ca_system_score_codex":0.000254692,"about_ca_system_score_gemma":0.000971865,"threshold_uncertainty_score":0.9999092},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.018141449130913694,"score_gpt":0.26121175711567746,"score_spread":0.24307030798476376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964762712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0423775,0.000004035401,0.94824594,0.00021802823,0.00020070122,0.00022443186,0.0000046164923,0.00016534145,0.008559431],"genre_scores_gemma":[0.86948067,0.0000020783837,0.12786165,0.00027792333,0.000033908524,0.00002926502,0.000019863155,0.000013138168,0.0022815291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989041,0.00011156396,0.00012574387,0.00038348895,0.00022841289,0.00024665936],"domain_scores_gemma":[0.9987463,0.00066009536,0.00007757813,0.00035993184,0.000086445274,0.00006970174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045079147,0.00014842775,0.00016339937,0.00008456104,0.00017185493,0.00016253765,0.00041998952,0.000047016547,0.00017783814],"category_scores_gemma":[0.00014076638,0.00011434466,0.000034917768,0.00011650948,0.000103032384,0.00017212042,0.00006229209,0.000270363,0.00017172766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011124828,0.000030524167,0.000056114164,0.000012595682,0.0000093044455,0.0000020625605,0.00042389447,0.004311434,0.00004007486,0.8995537,0.000046485486,0.09540257],"study_design_scores_gemma":[0.00040978892,0.0011720941,0.00071096816,0.00006245098,0.0000036995007,0.0000036642998,0.000052914595,0.53743404,0.00017335513,0.4591208,0.0006741246,0.00018209194],"about_ca_topic_score_codex":0.000005341674,"about_ca_topic_score_gemma":0.0000030370188,"teacher_disagreement_score":0.82710314,"about_ca_system_score_codex":0.000027485366,"about_ca_system_score_gemma":0.0000845219,"threshold_uncertainty_score":0.46628398},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.046909930151894284,"score_gpt":0.3102476221312967,"score_spread":0.26333769197940243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965944281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060600974,0.000023284674,0.98706836,0.00017230009,0.0004085263,0.00064156717,0.000001672178,0.00045465736,0.0051695625],"genre_scores_gemma":[0.9603824,0.000005460807,0.03630149,0.00018377019,0.00003467724,0.000107962165,0.000009469995,0.00002459272,0.0029501542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837416,0.00011417377,0.0002524087,0.00058969716,0.00027565975,0.00039390562],"domain_scores_gemma":[0.99828565,0.00056103466,0.000192769,0.00062022917,0.00021812318,0.00012221323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059471664,0.00023545053,0.0002738703,0.00027811583,0.00016795647,0.00016645079,0.0008620302,0.00008204028,0.00012983945],"category_scores_gemma":[0.00031783176,0.00020784055,0.000116426876,0.0002920722,0.000072149865,0.00019566697,0.0001487141,0.0002522494,0.00019560958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052765852,0.00007526689,0.00007659453,0.000021953478,0.000028117021,0.0000013416072,0.0007526672,0.025002956,0.001196654,0.9558377,0.00020626909,0.016747704],"study_design_scores_gemma":[0.00071746396,0.0010969717,0.00058489945,0.00025072266,0.000026561313,0.0000045723223,0.00018635292,0.9044617,0.0023414257,0.08919884,0.00063734525,0.00049313245],"about_ca_topic_score_codex":0.0000020741409,"about_ca_topic_score_gemma":4.294957e-7,"teacher_disagreement_score":0.95432234,"about_ca_system_score_codex":0.00007927304,"about_ca_system_score_gemma":0.00010558959,"threshold_uncertainty_score":0.84754914},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09132089929786394,"score_gpt":0.4067404308935916,"score_spread":0.31541953159572766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966286942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.751332,0.00002024463,0.15902217,0.00031803927,0.0006108609,0.0008161677,0.0000073752362,0.00015623937,0.0877169],"genre_scores_gemma":[0.9940724,0.000006895964,0.002106013,0.000075362535,0.00009129308,0.000054286924,0.000008648612,0.000016230195,0.0035688875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961051,0.0008623823,0.0005390351,0.0005499312,0.00143089,0.0005126676],"domain_scores_gemma":[0.9969584,0.0013920957,0.0001682867,0.0008757473,0.000360361,0.00024512524],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005651754,0.00019832596,0.00032266075,0.0006974094,0.00012729094,0.00045347423,0.0012643468,0.00012172124,0.00091745646],"category_scores_gemma":[0.0055955853,0.00015602338,0.00005564732,0.00086981064,0.00015552808,0.0010498525,0.00016925987,0.0007193206,0.0056642494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014435031,0.00027789857,0.0342928,0.00002544627,0.000014397443,0.000010416449,0.017578963,0.14282376,0.00070270314,0.34510338,0.0002413623,0.45748538],"study_design_scores_gemma":[0.003543865,0.0034912026,0.07325065,0.0003675493,0.000011261017,0.000020894733,0.06064617,0.38872635,0.005190481,0.4181623,0.04473951,0.0018497626],"about_ca_topic_score_codex":0.000006495758,"about_ca_topic_score_gemma":5.162152e-7,"teacher_disagreement_score":0.4556356,"about_ca_system_score_codex":0.0000885672,"about_ca_system_score_gemma":0.00016375413,"threshold_uncertainty_score":0.9999958},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05635044454367171,"score_gpt":0.33485420651463577,"score_spread":0.27850376197096405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966312692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42231804,0.000013187369,0.57309145,0.000031301748,0.00019557873,0.0005926869,0.0000028694362,0.000041163028,0.0037137347],"genre_scores_gemma":[0.9816867,0.000002981856,0.015022209,0.000027375587,0.000048056387,0.00006639253,0.000012260746,0.00003456151,0.0030994697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986227,0.00026706437,0.00036185913,0.0002705721,0.00018370572,0.00029411117],"domain_scores_gemma":[0.9976437,0.0014247497,0.00035077037,0.00030025517,0.00020996737,0.00007057019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021150701,0.00018825982,0.0003563934,0.00010476204,0.000088808316,0.000025598663,0.00017775623,0.00009182743,0.00010866003],"category_scores_gemma":[0.0012895362,0.00016451532,0.00012651747,0.00008129331,0.00006528571,0.000062671614,0.000053305637,0.00024013405,0.0000029371583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010214641,0.00039401586,0.0013359461,0.0015122611,0.00011363756,0.0000013253414,0.0054167463,0.003198275,0.033048052,0.898644,0.00016568655,0.055148628],"study_design_scores_gemma":[0.004071291,0.003243958,0.0010333643,0.0018330923,0.00024524317,0.0000125960405,0.0053345007,0.6888132,0.036833808,0.25703052,0.0004389365,0.001109458],"about_ca_topic_score_codex":0.0000024598837,"about_ca_topic_score_gemma":0.0000014544619,"teacher_disagreement_score":0.68561494,"about_ca_system_score_codex":0.00004373513,"about_ca_system_score_gemma":0.000055574765,"threshold_uncertainty_score":0.670874},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.044205293211162774,"score_gpt":0.28188289617340845,"score_spread":0.23767760296224566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046526692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025529163,0.000023383005,0.9535194,0.01772859,0.000077743425,0.00012308682,0.000011994808,0.0009327625,0.0020538992],"genre_scores_gemma":[0.93039805,0.000019380977,0.069380455,0.00011482922,0.000013249265,0.000010531814,0.000028043001,0.000008376143,0.000027085296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986403,0.00022084315,0.000247012,0.00041282602,0.00024124865,0.0002377711],"domain_scores_gemma":[0.9968135,0.00032548342,0.0002019014,0.0024895547,0.00008699569,0.000082581],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005524044,0.00014342002,0.00020045409,0.00007203696,0.00014154232,0.000087982575,0.009504503,0.00009096718,0.00007449315],"category_scores_gemma":[0.029148737,0.00013655792,0.000049041675,0.00042989093,0.0001836414,0.0003402936,0.012396747,0.00046555843,0.00013789671],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035025016,0.000034022476,0.00023355459,0.000025758078,0.000016568169,0.000004483953,0.0003401276,0.0008820755,0.0016498619,0.92834806,0.0018524848,0.06657797],"study_design_scores_gemma":[0.00017085407,0.00019871551,0.00040905247,0.00007212271,0.0000056210456,0.0000014745541,0.000052259566,0.49057147,0.011875068,0.4959546,0.0005431651,0.00014559318],"about_ca_topic_score_codex":0.0000018835367,"about_ca_topic_score_gemma":2.2537508e-7,"teacher_disagreement_score":0.9048689,"about_ca_system_score_codex":0.000035914127,"about_ca_system_score_gemma":0.000078032164,"threshold_uncertainty_score":0.99585456},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05567489988836302,"score_gpt":0.2571248751803857,"score_spread":0.20144997529202266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046684513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011029532,0.000027039041,0.9429362,0.033135407,0.00011588026,0.00013342703,0.0000015915947,0.0026392601,0.009981676],"genre_scores_gemma":[0.8950283,0.00005178348,0.103430726,0.0012080132,0.00005296162,0.000015915179,0.000002000002,0.000019651685,0.00019062885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982672,0.00028378356,0.00019181943,0.0006369924,0.00027387057,0.00034638896],"domain_scores_gemma":[0.9970633,0.00044918075,0.00013464915,0.0021625897,0.0000784626,0.000111832385],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005821042,0.00019096278,0.0001888265,0.00009777068,0.00019434441,0.00022008242,0.013514065,0.00013102975,0.00016029582],"category_scores_gemma":[0.036565255,0.00018163366,0.000050390176,0.0005135627,0.00012210978,0.00038744585,0.015030071,0.00072327664,0.00062387023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006900795,0.000037524384,0.00057879585,0.000023310362,0.000032641474,0.000018665654,0.0002600806,0.00029545807,0.006704641,0.6248569,0.0110088475,0.35611412],"study_design_scores_gemma":[0.00023298424,0.00041592986,0.0007568116,0.000062906,0.0000063344864,0.0000067878645,0.00005686601,0.31108913,0.010894825,0.6673673,0.008775335,0.000334807],"about_ca_topic_score_codex":0.0000016320782,"about_ca_topic_score_gemma":2.7940752e-7,"teacher_disagreement_score":0.8839988,"about_ca_system_score_codex":0.00004736357,"about_ca_system_score_gemma":0.00008849005,"threshold_uncertainty_score":0.9929362},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12255929215823734,"score_gpt":0.37242527432546296,"score_spread":0.2498659821672256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046729600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29104814,0.00020223792,0.70094204,0.0032328703,0.00016337582,0.00047350486,0.000010070558,0.00022117698,0.0037065998],"genre_scores_gemma":[0.99340713,0.0000828188,0.0043368465,0.00035383727,0.00010847446,0.00001623166,0.000003187953,0.00003278395,0.001658682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598116,0.00078627164,0.0004193707,0.00087406515,0.0014303306,0.0005088309],"domain_scores_gemma":[0.9938733,0.004654675,0.0003015758,0.00042351516,0.00035193187,0.00039501954],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018585805,0.00026693227,0.0003802536,0.00014103313,0.0003727873,0.00039693603,0.0007438383,0.00007304096,0.0007353574],"category_scores_gemma":[0.010422448,0.0001854845,0.00006096055,0.00046313295,0.00040279803,0.00026273102,0.0003203344,0.00081938657,0.00030507895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001941601,0.0001154919,0.024885422,0.0000413012,0.00008392719,0.00025232031,0.0062602623,0.017319059,0.0019015326,0.013196773,0.00038051757,0.93362176],"study_design_scores_gemma":[0.0065039345,0.005742114,0.05327256,0.000967431,0.000065467066,0.00008653921,0.020548046,0.77997667,0.0062157097,0.09442037,0.030050732,0.002150409],"about_ca_topic_score_codex":0.0000077037475,"about_ca_topic_score_gemma":0.0000063500884,"teacher_disagreement_score":0.9314714,"about_ca_system_score_codex":0.00004765789,"about_ca_system_score_gemma":0.000094584975,"threshold_uncertainty_score":0.9979132},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.017533912706447753,"score_gpt":0.24806449918660997,"score_spread":0.23053058648016223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173288964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13718185,0.00023863188,0.8562986,0.00093197724,0.00011193474,0.00015424307,0.000001944588,0.00042343387,0.0046573533],"genre_scores_gemma":[0.9886162,0.00004860498,0.007759444,0.00029588817,0.000047370042,0.000023599494,0.00007957862,0.00003217488,0.0030971183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694747,0.00088262773,0.00025698385,0.0009101014,0.00052224664,0.00048057604],"domain_scores_gemma":[0.9974723,0.00090677454,0.00031837588,0.0008838845,0.00022739256,0.00019131311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087082817,0.0003284532,0.00035987244,0.00023703798,0.00038388334,0.00061571965,0.0007636517,0.00013880561,0.00008391469],"category_scores_gemma":[0.0007311957,0.0002351858,0.00006063877,0.0015025885,0.00012912652,0.00047502993,0.00014925796,0.0011757354,0.00002785183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015969224,0.00045505416,0.023918295,0.000061416074,0.00017133406,0.0002871182,0.0020258871,0.05412488,0.0031653806,0.24704354,0.00045426836,0.6666959],"study_design_scores_gemma":[0.0016439651,0.0011058701,0.013555924,0.0003169813,0.00002868756,0.00006177541,0.00022986555,0.9796097,0.00022942162,0.0008236279,0.0018203511,0.00057380064],"about_ca_topic_score_codex":0.000016887303,"about_ca_topic_score_gemma":0.000004592549,"teacher_disagreement_score":0.92548484,"about_ca_system_score_codex":0.00005226528,"about_ca_system_score_gemma":0.00016193494,"threshold_uncertainty_score":0.95905983},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1626154911242037,"score_gpt":0.42643700495823694,"score_spread":0.26382151383403324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174263485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120090514,0.00030776643,0.876941,0.00080064504,0.00007278096,0.00043739824,0.000036852376,0.00008756394,0.0012254708],"genre_scores_gemma":[0.95846975,0.000070755006,0.019476838,0.00011053532,0.000026441012,0.00006686257,0.00002513696,0.000037000245,0.021716705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578893,0.001689111,0.00039409506,0.0007850388,0.00092745567,0.0004153894],"domain_scores_gemma":[0.992115,0.005055907,0.00023232533,0.00090855744,0.0014547785,0.00023343587],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022726406,0.00027454132,0.00042239064,0.00021960367,0.000801171,0.00046652675,0.00065214414,0.0001324946,0.0014454967],"category_scores_gemma":[0.009764556,0.00019018949,0.000051326617,0.0006781371,0.0008184698,0.00028465458,0.0003726801,0.0009979575,0.00032595734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003524124,0.0013937902,0.0058526793,0.000026068175,0.00034348553,0.0003423078,0.026631506,0.7613249,0.006077575,0.06926664,0.00062684686,0.124590084],"study_design_scores_gemma":[0.0064720083,0.0010832503,0.018784447,0.00048501894,0.00004972678,0.000106921485,0.0342658,0.92626536,0.0023853448,0.0065031066,0.0026373784,0.00096163416],"about_ca_topic_score_codex":0.000007704017,"about_ca_topic_score_gemma":0.000054665725,"teacher_disagreement_score":0.8574642,"about_ca_system_score_codex":0.00006731567,"about_ca_system_score_gemma":0.0004030881,"threshold_uncertainty_score":0.9994673},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1378188340422346,"score_gpt":0.4246927229571403,"score_spread":0.2868738889149057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174325474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032292604,0.00005506676,0.9059206,0.0010785214,0.00036317614,0.00014121935,0.000008208945,0.00035244567,0.059788104],"genre_scores_gemma":[0.9637124,0.000040858915,0.018994521,0.00035116845,0.000115501134,0.000018571784,0.000035762052,0.000020019132,0.016711194],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962031,0.0007660618,0.0005478999,0.0004444576,0.0015817817,0.00045668537],"domain_scores_gemma":[0.9920865,0.0051508737,0.00018725551,0.0006041747,0.0017666036,0.00020455456],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0035358376,0.00017707981,0.00029167338,0.00029891514,0.00039254624,0.000753348,0.0007080177,0.00012124162,0.0057177152],"category_scores_gemma":[0.044458833,0.00014455894,0.00010119013,0.0008911118,0.00021811876,0.0007590629,0.0002976987,0.0008656105,0.00445378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037420014,0.00011497434,0.0021217603,0.000015419932,0.000058350117,0.00007218361,0.002539765,0.074776866,0.00086286996,0.36944446,0.000778159,0.548841],"study_design_scores_gemma":[0.0019517312,0.0006025491,0.021880012,0.00026898994,0.000023426612,0.000095817326,0.013581846,0.26563576,0.005231222,0.5396683,0.14985758,0.0012027237],"about_ca_topic_score_codex":0.0000010339377,"about_ca_topic_score_gemma":0.0000012212009,"teacher_disagreement_score":0.9314198,"about_ca_system_score_codex":0.00004742933,"about_ca_system_score_gemma":0.0004966563,"threshold_uncertainty_score":0.9963214},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016076298876510308,"score_gpt":0.2527456540907559,"score_spread":0.2366693552142456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174799275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22270454,0.00016785183,0.74918634,0.0011074655,0.0001552829,0.00009488367,0.0000029676632,0.0008151003,0.025765581],"genre_scores_gemma":[0.98593444,0.000029028912,0.010659431,0.0001309761,0.0000725207,0.000013714859,0.000035772708,0.000018808942,0.0031053144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798244,0.00059069204,0.00018499185,0.0006038086,0.00025032298,0.00038772754],"domain_scores_gemma":[0.9982083,0.0009534204,0.00015199087,0.00027583336,0.00024961703,0.00016085256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007277988,0.00022151165,0.00022572457,0.000089413785,0.0009823433,0.00052367884,0.00027748224,0.00007492203,0.00009167589],"category_scores_gemma":[0.002175063,0.00020040432,0.000036284084,0.0004950068,0.00016124707,0.00026225825,0.00023544463,0.0011970571,0.0000616066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019678087,0.00006426429,0.017233497,0.00003484018,0.000037487505,0.00020226768,0.0012289486,0.003984567,0.004067417,0.7620209,0.000037337857,0.2110688],"study_design_scores_gemma":[0.0034351815,0.00327109,0.05106119,0.0025160867,0.00013476938,0.0017387903,0.004742176,0.78203756,0.02031051,0.10722935,0.020568019,0.002955259],"about_ca_topic_score_codex":0.00000823212,"about_ca_topic_score_gemma":0.000001994898,"teacher_disagreement_score":0.778053,"about_ca_system_score_codex":0.000029782856,"about_ca_system_score_gemma":0.00023762384,"threshold_uncertainty_score":0.8172251},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010892488346086762,"score_gpt":0.25413729974615773,"score_spread":0.24324481140007098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174935984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20837925,0.00022368738,0.7813597,0.00072692387,0.00024198863,0.00008929834,1.650335e-7,0.00023564321,0.008743345],"genre_scores_gemma":[0.9895741,0.000008715325,0.0076486114,0.00017453152,0.000058552243,0.000010627096,0.0000058117043,0.000009315093,0.0025097318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986739,0.00042325954,0.00014627515,0.00038465793,0.00013988765,0.00023197851],"domain_scores_gemma":[0.9990638,0.0005121085,0.00008802529,0.00020971138,0.000071928844,0.000054458273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004989504,0.00013668396,0.00015152384,0.00005453868,0.00022227142,0.00026270354,0.00016680954,0.00004868591,0.00002571237],"category_scores_gemma":[0.00038971947,0.000113823706,0.000021965574,0.00031038982,0.00005263436,0.00023250973,0.00010202287,0.0008013946,0.0000069901866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007786448,0.00007214249,0.014391176,0.000025248935,0.000024409066,0.000105262625,0.0026252407,0.2248852,0.0004379823,0.22306022,0.00001760054,0.5342777],"study_design_scores_gemma":[0.00032162166,0.00011722194,0.014829961,0.000066270564,0.0000036970405,0.000050400395,0.0003600048,0.98227865,0.00002672965,0.0016844072,0.000102615115,0.00015845348],"about_ca_topic_score_codex":0.0000072963107,"about_ca_topic_score_gemma":0.000020479509,"teacher_disagreement_score":0.78119487,"about_ca_system_score_codex":0.000016858605,"about_ca_system_score_gemma":0.000055315526,"threshold_uncertainty_score":0.46415958},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12812209112907322,"score_gpt":0.42388866202890896,"score_spread":0.2957665708998357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175841314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023605369,0.00025679034,0.9585086,0.0013069413,0.00047041057,0.00044191518,0.000006517675,0.00019224573,0.015211196],"genre_scores_gemma":[0.7834133,0.000089690686,0.01105389,0.00024243518,0.00038781023,0.000090867055,0.000060687,0.00006121117,0.20460014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947803,0.00095329806,0.000679712,0.0010694737,0.001713616,0.00080360076],"domain_scores_gemma":[0.99164605,0.00530716,0.00033886707,0.00075519783,0.0016744662,0.0002782703],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005012404,0.00032667146,0.0005150852,0.0003043687,0.00078146125,0.0005602275,0.00096400786,0.0002190779,0.003917007],"category_scores_gemma":[0.028045539,0.00027040983,0.0002631378,0.00072539505,0.0002924948,0.00037757578,0.000385049,0.0014008351,0.0012192228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012290671,0.00012449885,0.0003676342,0.000033430762,0.00009495215,0.00014689316,0.003442448,0.6244938,0.0044542016,0.05522158,0.0022336529,0.30815786],"study_design_scores_gemma":[0.0022263383,0.0018669744,0.00055470475,0.00020049543,0.00003248378,0.000039545484,0.01101002,0.5287054,0.013861144,0.051441442,0.38917512,0.0008863292],"about_ca_topic_score_codex":0.000002503219,"about_ca_topic_score_gemma":0.0000019372328,"teacher_disagreement_score":0.94745475,"about_ca_system_score_codex":0.00009700968,"about_ca_system_score_gemma":0.00055369677,"threshold_uncertainty_score":0.9999748},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06749056405776141,"score_gpt":0.3460512910546785,"score_spread":0.27856072699691714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175907392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9574653,0.00021069283,0.0076209027,0.0016868068,0.00017852715,0.00020808254,0.000013692252,0.000050815615,0.032565206],"genre_scores_gemma":[0.9950996,0.000116662355,0.00029896037,0.00022840811,0.000053798496,0.000019674933,0.0000017883484,0.000022420621,0.0041587097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977325,0.0013764831,0.00023356963,0.00025257745,0.00021092645,0.0001939393],"domain_scores_gemma":[0.9928843,0.0062885378,0.00018025118,0.0004404575,0.00015432846,0.000052153362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020221607,0.0001741058,0.0002998108,0.00003460348,0.00016861974,0.00004612802,0.00031596964,0.00008299633,0.00016350695],"category_scores_gemma":[0.0047758967,0.00009722161,0.0000834925,0.00011919341,0.00026492562,0.00003113018,0.00015669389,0.00053715083,8.369356e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005867048,0.000026598667,0.0016557388,0.000084524545,0.000063407184,0.000008183723,0.0034778055,0.0000054532634,0.0009866132,0.9852289,0.0004054202,0.007998696],"study_design_scores_gemma":[0.0018845786,0.0012668383,0.006460828,0.003116296,0.0005088099,0.00003645274,0.047032636,0.004169766,0.06220546,0.8616377,0.010250692,0.0014299242],"about_ca_topic_score_codex":0.000015346388,"about_ca_topic_score_gemma":0.0000106265825,"teacher_disagreement_score":0.12359117,"about_ca_system_score_codex":0.00001311834,"about_ca_system_score_gemma":0.00006512149,"threshold_uncertainty_score":0.5717539},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01944880602390112,"score_gpt":0.2931511756311167,"score_spread":0.27370236960721556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176194860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31814012,0.00006564686,0.6567939,0.0010274746,0.00010201069,0.000117055366,0.00006473385,0.00002535072,0.023663722],"genre_scores_gemma":[0.99883306,0.0000071773798,0.0002559923,0.00023015212,0.000052087795,0.000008111019,0.000029771229,0.000006878025,0.0005767459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987053,0.0005345894,0.00015278066,0.00025226004,0.00011777902,0.00023724242],"domain_scores_gemma":[0.99870944,0.0009072955,0.000033789176,0.00021411643,0.00006965501,0.00006573159],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00073561823,0.00010951712,0.00019193641,0.000038174927,0.0001544124,0.00013070868,0.00008916233,0.000031178985,0.0024857759],"category_scores_gemma":[0.0002922751,0.00008311019,0.000063039064,0.00020352648,0.00005058536,0.000030171408,0.000057426743,0.000406191,0.000030907457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014280222,0.00009517917,0.006431082,0.0000053721537,0.00007167155,0.00016422765,0.0004074274,0.000061630555,0.00001459437,0.98456955,0.000023037363,0.008141951],"study_design_scores_gemma":[0.0009846438,0.00010049775,0.020154666,0.000050978237,0.00035803963,0.000023817332,0.012375678,0.10571266,0.000104244566,0.8574991,0.0022635793,0.00037207108],"about_ca_topic_score_codex":0.00001788713,"about_ca_topic_score_gemma":0.000004377133,"teacher_disagreement_score":0.680693,"about_ca_system_score_codex":0.0000074993673,"about_ca_system_score_gemma":0.000037006706,"threshold_uncertainty_score":0.9984261},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.042294675341726054,"score_gpt":0.3155514981952951,"score_spread":0.27325682285356906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196848038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004155093,0.003949798,0.7529562,0.013090442,0.0004613626,0.00067754835,0.0000036884503,0.0033287504,0.22137707],"genre_scores_gemma":[0.74806726,0.00016672903,0.21667688,0.0019410283,0.00007138734,0.00006145641,0.00001312322,0.00004113528,0.032960974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99763554,0.0005757588,0.00023690726,0.0007768332,0.00032716265,0.0004477687],"domain_scores_gemma":[0.9981326,0.00031120807,0.00025663286,0.0007959001,0.00037463862,0.00012904202],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011009086,0.00025156763,0.00031194545,0.00011053281,0.00028286685,0.0014900169,0.002786493,0.0001461072,0.00037109395],"category_scores_gemma":[0.0009534322,0.0002233708,0.00006640005,0.00041748752,0.000095179304,0.000852284,0.0017756909,0.0009154516,0.0002196908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021664491,0.000068323156,0.00018229343,0.00004006079,0.000023128292,0.00017914711,0.0006379247,0.000052356096,0.00350311,0.9110241,0.0011880279,0.08307987],"study_design_scores_gemma":[0.0004101206,0.0002448703,0.00018207976,0.00085332704,0.000017413817,0.00008661383,0.0005871481,0.0038925833,0.03276923,0.9123869,0.04788559,0.0006841127],"about_ca_topic_score_codex":0.000016259082,"about_ca_topic_score_gemma":0.000009768925,"teacher_disagreement_score":0.7439122,"about_ca_system_score_codex":0.00006831022,"about_ca_system_score_gemma":0.00039624984,"threshold_uncertainty_score":0.9995465},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014207983216091773,"score_gpt":0.24791224070079795,"score_spread":0.2337042574847062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W43025842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0648552,0.000033319335,0.84752446,0.0029277469,0.00048324213,0.0003303219,6.18893e-7,0.0015447194,0.08230037],"genre_scores_gemma":[0.9806794,0.0000072675807,0.006389363,0.00071366335,0.0001220753,0.00006180808,0.000009262502,0.000034383705,0.011982779],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710107,0.0010302861,0.00024611174,0.0006739831,0.0003880799,0.00056046783],"domain_scores_gemma":[0.99788845,0.00097343256,0.0002243348,0.0005236464,0.00018528008,0.00020488632],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008743241,0.0003140048,0.0002845686,0.00022465365,0.00051569263,0.00048334597,0.0010437096,0.00013652878,0.00097606523],"category_scores_gemma":[0.00084024854,0.00027689844,0.00011494911,0.0003086335,0.00012364876,0.00043898006,0.00023363675,0.001635897,0.0024911284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055542678,0.00010778712,0.0008501681,0.00002288152,0.000034349487,0.000014790154,0.0021703353,0.038633004,0.00073449156,0.24663976,0.00035245516,0.7103844],"study_design_scores_gemma":[0.0008908871,0.00076624623,0.0035955939,0.00015521537,0.000008727496,0.000009603684,0.0005341538,0.95841086,0.000902463,0.02234547,0.011784082,0.0005966782],"about_ca_topic_score_codex":0.000044842236,"about_ca_topic_score_gemma":7.409853e-7,"teacher_disagreement_score":0.91977787,"about_ca_system_score_codex":0.000052099807,"about_ca_system_score_gemma":0.00014285622,"threshold_uncertainty_score":0.9999683},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03920515464262433,"score_gpt":0.2815507529389313,"score_spread":0.24234559829630695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W593234165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02332056,0.000052276093,0.9605703,0.0009933242,0.00034787552,0.00010984483,0.000001077215,0.00032603712,0.0142787015],"genre_scores_gemma":[0.9930641,0.00002724412,0.004524777,0.00016732322,0.00008228744,0.000010071079,0.000004738235,0.00001975776,0.002099682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969442,0.0015030878,0.00032235892,0.0004324303,0.00036420661,0.00043370115],"domain_scores_gemma":[0.9918431,0.0069565764,0.0003166755,0.00061791536,0.00015228505,0.00011346047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002371976,0.00022596907,0.00029008283,0.000086679356,0.0008604725,0.00023603326,0.0012017387,0.00007541143,0.00008483312],"category_scores_gemma":[0.0054211416,0.00016535804,0.000093270464,0.00023061536,0.0005146993,0.00010195834,0.00029966343,0.00094479043,0.00013617083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016345517,0.000025789454,0.00058611744,0.000013016917,0.000014301167,0.0000013148203,0.000448426,0.0091813365,0.0001528226,0.84191126,0.000013693206,0.14763555],"study_design_scores_gemma":[0.00037907483,0.00072356925,0.006255157,0.00013144017,0.000014352298,0.000008807525,0.0002118629,0.57920194,0.00021610077,0.4048427,0.0077057346,0.00030927887],"about_ca_topic_score_codex":0.00003538209,"about_ca_topic_score_gemma":0.000005210585,"teacher_disagreement_score":0.96974355,"about_ca_system_score_codex":0.000022528706,"about_ca_system_score_gemma":0.00008706133,"threshold_uncertainty_score":0.6743105},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Simple (philosophy); Artificial intelligence; Algorithm; Theoretical computer science; Machine learning","score_opus":0.034468881668759915,"score_gpt":0.247999907469349,"score_spread":0.21353102580058908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75140964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017019885,0.00009492735,0.8758206,0.000076507,0.00031101788,0.0003280215,9.822605e-8,0.00089724554,0.10545173],"genre_scores_gemma":[0.98171395,0.00019023856,0.0056754756,0.00012803718,0.00005254315,0.00004115337,0.000008373858,0.00005470215,0.01213555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615914,0.0007645282,0.00057113275,0.00092906423,0.0006612925,0.00091486034],"domain_scores_gemma":[0.99765784,0.00075680215,0.00050134567,0.0005801079,0.00020414306,0.00029978508],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021377462,0.0005079146,0.00044418368,0.00036733935,0.0008935704,0.0003867545,0.0009923064,0.00018763426,0.00046184173],"category_scores_gemma":[0.0017786014,0.00048528158,0.00011213999,0.0003967939,0.00029837602,0.00032189363,0.0008197119,0.001859389,0.0005078994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006105223,0.000034288492,0.0015322778,0.00004390314,0.00003994525,0.000029814808,0.0059436164,0.6265475,0.00029458746,0.350251,0.000010193542,0.015211828],"study_design_scores_gemma":[0.0007592156,0.0013526543,0.0010371263,0.00031104253,0.00003470396,0.000030337871,0.0011588521,0.9881581,0.00081188773,0.0029925024,0.0026252882,0.00072827766],"about_ca_topic_score_codex":0.000012577679,"about_ca_topic_score_gemma":2.8962842e-7,"teacher_disagreement_score":0.964694,"about_ca_system_score_codex":0.00009725716,"about_ca_system_score_gemma":0.00011955744,"threshold_uncertainty_score":0.9997599},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.24345939677892353,"score_gpt":0.40468048743075924,"score_spread":0.1612210906518357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9422450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56400114,0.0002407765,0.41863665,0.00008062513,0.0005831943,0.00044511884,0.000009461096,0.00006780644,0.015935235],"genre_scores_gemma":[0.9931802,0.000036536974,0.0007948738,0.0000072851353,0.00004361662,0.000024787143,0.0000011772319,0.000018737072,0.0058927704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966552,0.0007230219,0.0005647541,0.0005432352,0.0010938084,0.0004199814],"domain_scores_gemma":[0.9958445,0.0030545879,0.00030609462,0.00058497005,0.000089238194,0.00012064248],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035437194,0.00018048492,0.00035779818,0.000448207,0.00008975132,0.00004456486,0.0008228477,0.0000986713,0.0016376945],"category_scores_gemma":[0.009388884,0.00014627312,0.000071759256,0.00040815133,0.00042233022,0.0002394648,0.0002185866,0.00057678006,0.00060295104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025282146,0.00072641496,0.06787108,0.000022029444,0.00007177454,0.00016582171,0.028487857,0.06851728,0.00688444,0.035576753,0.000051400508,0.78909695],"study_design_scores_gemma":[0.0034158016,0.0027275772,0.23075037,0.0010755978,0.000032790656,0.000010808361,0.026712727,0.06783741,0.051309265,0.61161965,0.0031130163,0.001394961],"about_ca_topic_score_codex":0.000010528344,"about_ca_topic_score_gemma":0.0000014552456,"teacher_disagreement_score":0.78770196,"about_ca_system_score_codex":0.00005067309,"about_ca_system_score_gemma":0.00007919039,"threshold_uncertainty_score":0.99927497},"labels":[],"label_agreement":null}]}