{"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07923751,0.002680105,0.8899365,0.013749213,0.0002869549,0.0003119658,0.0010892301,0.0006963228,0.012012256],"genre_scores_gemma":[0.78260523,0.0016188242,0.2047564,0.0025284085,0.001282519,0.00085759244,0.0015880774,0.0005946105,0.004168412],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96869355,0.020260181,0.0011491808,0.003399631,0.0047144075,0.0017830435],"domain_scores_gemma":[0.55366206,0.40997213,0.008232041,0.019415364,0.0054447404,0.0032736945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04909202,0.0020551935,0.0032309084,0.0018546989,0.0022748294,0.0066284384,0.004759783,0.0044060936,0.005380261],"category_scores_gemma":[0.24370874,0.0016629306,0.0024259745,0.0023472523,0.006966659,0.017626414,0.0066785286,0.008449861,0.0006740681],"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":[0.002027699,0.00056225713,0.010444927,0.0009811625,0.00060801656,0.00064001896,0.00083293894,0.46804595,0.002348514,0.43800417,0.013472081,0.06203231],"study_design_scores_gemma":[0.00007958779,0.00013108301,0.0005890534,0.00006714119,0.00005694027,0.00018914173,0.00009221874,0.6213314,0.0010318485,0.37527615,0.0011270777,0.000028413215],"about_ca_topic_score_codex":0.0017702465,"about_ca_topic_score_gemma":0.0021760967,"teacher_disagreement_score":0.04909202,"about_ca_system_score_codex":0.0052876505,"about_ca_system_score_gemma":0.0039383764,"threshold_uncertainty_score":0.25962657},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1737038,0.015548423,0.674739,0.076271914,0.0013323391,0.00032571686,0.0039687953,0.0031139012,0.050996076],"genre_scores_gemma":[0.8442106,0.0061986633,0.12374061,0.007108111,0.0056663426,0.00082114915,0.0019604713,0.001176575,0.009117487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9884416,0.003264446,0.00055993063,0.003667941,0.0025689323,0.0014971229],"domain_scores_gemma":[0.72655326,0.24439593,0.005278309,0.013602883,0.005294489,0.004875196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009538388,0.0014600841,0.0039243684,0.0017649201,0.0026338776,0.007852738,0.0061907535,0.005595141,0.014400157],"category_scores_gemma":[0.1229985,0.0011743171,0.0021531188,0.0027132935,0.008274892,0.023015784,0.006275609,0.01061029,0.002409345],"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":[0.0010084014,0.00039705264,0.00534264,0.0011719954,0.0001753208,0.00019414777,0.00078751426,0.039789915,0.002477741,0.76998985,0.0378364,0.14082901],"study_design_scores_gemma":[0.00009344932,0.00010607925,0.0013222675,0.00016687304,0.00003979596,0.0003267125,0.00020189925,0.10908803,0.0014425925,0.8800422,0.00709113,0.00007902711],"about_ca_topic_score_codex":0.0019407758,"about_ca_topic_score_gemma":0.0010929722,"teacher_disagreement_score":0.014400157,"about_ca_system_score_codex":0.0050562313,"about_ca_system_score_gemma":0.0032960079,"threshold_uncertainty_score":0.050444365},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18075533,0.0013127333,0.7841576,0.010869131,0.0000790034,0.00012724758,0.00048406483,0.00072898436,0.02148599],"genre_scores_gemma":[0.9180982,0.00069972855,0.07452991,0.0010689427,0.00030319477,0.00022815341,0.0006984681,0.00018571399,0.0041877166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894721,0.0039870986,0.0005619491,0.0023068162,0.0030393559,0.0006327274],"domain_scores_gemma":[0.95741236,0.03371097,0.0017650959,0.0042023635,0.0020253162,0.0008839433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00998201,0.00077150087,0.0013358752,0.0017162118,0.001687129,0.0039041743,0.0031850424,0.002572785,0.0055995365],"category_scores_gemma":[0.058664173,0.00079571665,0.0021635331,0.001469487,0.009063,0.019194882,0.0076239873,0.0057372083,0.0006172342],"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":[0.00014265787,0.000096849864,0.0014749946,0.00022765744,0.000045355275,0.000093362294,0.0009819039,0.008629328,0.0010260167,0.9520817,0.0015922931,0.033607908],"study_design_scores_gemma":[0.00002403145,0.000029653036,0.00024308753,0.000023130176,0.000014378079,0.00006627188,0.00010840157,0.03193244,0.00061445223,0.9661687,0.00076552737,0.000009957447],"about_ca_topic_score_codex":0.0012778303,"about_ca_topic_score_gemma":0.00087607524,"teacher_disagreement_score":0.00998201,"about_ca_system_score_codex":0.0022352247,"about_ca_system_score_gemma":0.0013775707,"threshold_uncertainty_score":0.052790523},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13739663,0.0020687156,0.85052496,0.0016256579,0.00016080176,0.00036090176,0.0005690417,0.00063611096,0.006657218],"genre_scores_gemma":[0.7506407,0.0009816427,0.24141745,0.0006717686,0.0004595443,0.00042969582,0.0012855676,0.00016851057,0.0039451546],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924238,0.0015648075,0.00031983684,0.0011151714,0.0039878758,0.0005885969],"domain_scores_gemma":[0.97299474,0.017389245,0.0014921712,0.005399219,0.0022138052,0.0005107704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047995243,0.00076227135,0.0013046153,0.0022881557,0.0012786875,0.0022610645,0.0017765437,0.001358524,0.0036200942],"category_scores_gemma":[0.027679387,0.00040096886,0.0008521033,0.0028135064,0.0026212316,0.0067116953,0.0036774604,0.0028551247,0.0004738175],"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":[0.0012969156,0.00048958126,0.0058477162,0.00062689144,0.00015510726,0.00027139726,0.0008688366,0.14768285,0.025536358,0.3580032,0.0071717896,0.45204943],"study_design_scores_gemma":[0.00008315459,0.0003170153,0.001994368,0.00009147092,0.00003945466,0.00062322634,0.00018222332,0.7999318,0.02441863,0.164718,0.007546629,0.000054064894],"about_ca_topic_score_codex":0.0008768222,"about_ca_topic_score_gemma":0.0005550441,"teacher_disagreement_score":0.0047995243,"about_ca_system_score_codex":0.0029543065,"about_ca_system_score_gemma":0.0012551509,"threshold_uncertainty_score":0.025382638},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2088155,0.00029569794,0.78572917,0.0015400071,0.00008081682,0.00015350603,0.00041717797,0.0008121886,0.0021559508],"genre_scores_gemma":[0.8196247,0.0001984499,0.17560977,0.00069835514,0.00029111942,0.00035275894,0.001566447,0.00017896545,0.0014794109],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98618907,0.004287927,0.00097210443,0.0049862363,0.002581268,0.0009834544],"domain_scores_gemma":[0.89128447,0.08912706,0.0048532425,0.008752119,0.004022405,0.0019607684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01185183,0.0013000693,0.0024122878,0.0021927883,0.0019989565,0.0029375441,0.0048026023,0.0033041479,0.0024212627],"category_scores_gemma":[0.10878314,0.001151615,0.0021922614,0.0022255979,0.005043691,0.011729795,0.00455224,0.0048542465,0.0006047837],"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":[0.0032716652,0.0010842648,0.048904978,0.0006300967,0.0007066466,0.0010627424,0.0011659992,0.4599885,0.007819266,0.21874651,0.005111931,0.25150737],"study_design_scores_gemma":[0.000094101415,0.00022838823,0.0015496447,0.00003625733,0.000038023238,0.00028022585,0.00016332325,0.7899922,0.0031406563,0.2036086,0.0008284404,0.000040081],"about_ca_topic_score_codex":0.0017104294,"about_ca_topic_score_gemma":0.001390546,"teacher_disagreement_score":0.01185183,"about_ca_system_score_codex":0.0021075897,"about_ca_system_score_gemma":0.0019897087,"threshold_uncertainty_score":0.06267923},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06562682,0.0009926417,0.917113,0.0015424774,0.00013263006,0.00010347392,0.00019169477,0.0006233411,0.013673976],"genre_scores_gemma":[0.8792983,0.0008725304,0.11132558,0.00052211067,0.00023066906,0.00025877552,0.00028752437,0.00029141232,0.0069130277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99727947,0.0012354463,0.000089704685,0.00039386062,0.0006071026,0.00039430294],"domain_scores_gemma":[0.9700551,0.024801282,0.0018698182,0.0015209519,0.0008404811,0.00091238745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062626577,0.0017529224,0.0019563492,0.0008353637,0.0009905315,0.0031389107,0.0028481255,0.0023320774,0.0050861477],"category_scores_gemma":[0.03448705,0.00082515454,0.0010661173,0.0011239417,0.002679692,0.0037051241,0.002134305,0.0045385305,0.0007702297],"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":[0.0004428278,0.00016742606,0.0010543104,0.0001237854,0.0000848457,0.00010999133,0.00014230775,0.7868656,0.0015852165,0.18290652,0.0033569657,0.023160134],"study_design_scores_gemma":[0.00001909211,0.00003834487,0.00012730653,0.000014066445,0.0000095132145,0.000017773245,0.000012169107,0.95396864,0.00038400298,0.045145042,0.00025354387,0.000010536106],"about_ca_topic_score_codex":0.0031648476,"about_ca_topic_score_gemma":0.0029193067,"teacher_disagreement_score":0.0062626577,"about_ca_system_score_codex":0.0037158837,"about_ca_system_score_gemma":0.0027786053,"threshold_uncertainty_score":0.033120513},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063606007,0.00045502812,0.99134314,0.00025506367,0.000033442913,0.000026450321,0.000032357275,0.00018847651,0.0013054783],"genre_scores_gemma":[0.7997343,0.0012611941,0.19450915,0.00040110797,0.00018374555,0.0003439819,0.00028641848,0.0004472861,0.0028328835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994065,0.0023949104,0.00025518608,0.0008922321,0.0018695086,0.0005233228],"domain_scores_gemma":[0.9556433,0.03736877,0.0023474721,0.0016904434,0.0021744694,0.00077564345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010712652,0.0024552154,0.002485827,0.0014519452,0.00070729444,0.0027375028,0.0024957566,0.0020374262,0.0035137935],"category_scores_gemma":[0.053588845,0.001047204,0.0015622132,0.0009388541,0.0035172044,0.005631635,0.0041454956,0.0054751392,0.0005184544],"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":[0.000082671955,0.000044768967,0.0003499541,0.00011850876,0.000046120982,0.000031256102,0.00006980357,0.92758083,0.0005475566,0.061563723,0.00033969342,0.00922502],"study_design_scores_gemma":[0.000003741375,0.000026393956,0.000024617033,0.00001769848,0.0000055682135,0.000007766376,0.0000049034124,0.9742284,0.00024304901,0.025304802,0.00012738045,0.0000056586678],"about_ca_topic_score_codex":0.0036762585,"about_ca_topic_score_gemma":0.0020528946,"teacher_disagreement_score":0.010712652,"about_ca_system_score_codex":0.004202228,"about_ca_system_score_gemma":0.0033205461,"threshold_uncertainty_score":0.056654632},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034537174,0.0023249353,0.9541986,0.0042868634,0.00012287979,0.00014664393,0.0005859716,0.0007038707,0.0030931232],"genre_scores_gemma":[0.6055234,0.003230072,0.3758132,0.002399247,0.0018326988,0.0008405748,0.0029172048,0.0008373401,0.006606228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98118776,0.009600726,0.0008153176,0.0033445621,0.003750969,0.0013005369],"domain_scores_gemma":[0.7761577,0.19825785,0.007528964,0.011513142,0.0041393354,0.002403044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018479917,0.002515575,0.0045671263,0.0023478991,0.0020950243,0.0058996733,0.006954592,0.0051452783,0.0053567705],"category_scores_gemma":[0.12691386,0.0013612069,0.0025746087,0.004535113,0.0065711904,0.022821717,0.008077897,0.008667697,0.0013712471],"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":[0.0014755065,0.0005200987,0.0063327285,0.0008513729,0.00039126142,0.000493318,0.0012452436,0.2814725,0.0037278056,0.6086988,0.012699053,0.082092226],"study_design_scores_gemma":[0.00005183742,0.00010626979,0.000504309,0.000034332832,0.00003499627,0.00020425118,0.00012610249,0.5628596,0.0010016062,0.43387285,0.0011656837,0.000038111502],"about_ca_topic_score_codex":0.004045252,"about_ca_topic_score_gemma":0.002233102,"teacher_disagreement_score":0.018479917,"about_ca_system_score_codex":0.0051478636,"about_ca_system_score_gemma":0.0034011318,"threshold_uncertainty_score":0.097732306},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011733351,0.0031632062,0.9712432,0.0026788316,0.00028556114,0.00012714356,0.00023731217,0.00064273627,0.009888599],"genre_scores_gemma":[0.5875375,0.006520189,0.36144036,0.0051622097,0.0018812021,0.0014737195,0.0016257981,0.0032113562,0.031147702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879396,0.0043287748,0.00060490926,0.0021134058,0.0037384832,0.0012747747],"domain_scores_gemma":[0.9178297,0.059364017,0.005036654,0.0076838927,0.0075814547,0.002504308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026893979,0.005478594,0.0056837588,0.0042580147,0.0034404134,0.0051183137,0.0065266755,0.00547856,0.011553679],"category_scores_gemma":[0.13092871,0.0025816113,0.0052866023,0.002817784,0.007728141,0.01225153,0.010861069,0.014483699,0.002261876],"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":[0.0004304193,0.00018993799,0.0030741417,0.00084877014,0.00034342488,0.00034816237,0.0005948542,0.3736889,0.0036380487,0.57889277,0.009510169,0.028440472],"study_design_scores_gemma":[0.000028876073,0.000112118345,0.0006552244,0.00016497738,0.000077472294,0.00007474286,0.00004978207,0.79136795,0.0011724426,0.20337677,0.0028716559,0.00004804743],"about_ca_topic_score_codex":0.008286189,"about_ca_topic_score_gemma":0.006163376,"teacher_disagreement_score":0.026893979,"about_ca_system_score_codex":0.0078051244,"about_ca_system_score_gemma":0.005633266,"threshold_uncertainty_score":0.14223063},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061482014,0.0011966331,0.977047,0.0018334013,0.00015539335,0.00009107051,0.0002688926,0.0002015878,0.013057709],"genre_scores_gemma":[0.6866193,0.0036516008,0.2862615,0.002686225,0.0012229534,0.0009365972,0.0006300685,0.0005164686,0.017475316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926571,0.0033932729,0.00025970297,0.0011808779,0.001890404,0.00061863044],"domain_scores_gemma":[0.97078335,0.022286324,0.0021278015,0.0032261931,0.000984717,0.00059162895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010282083,0.0025227692,0.0022542903,0.0017882992,0.0013031301,0.004363826,0.004623093,0.0030706935,0.011006349],"category_scores_gemma":[0.049840085,0.0012968077,0.0026015579,0.0021615073,0.0055594807,0.010815438,0.0066371667,0.010038276,0.0016378094],"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":[0.00014243246,0.00010554604,0.0006884271,0.00030752682,0.00015208487,0.00012750407,0.00021205988,0.13491836,0.001344937,0.83352506,0.0057087857,0.022767363],"study_design_scores_gemma":[0.000024279745,0.00008641195,0.0003347366,0.00010565768,0.000038029404,0.000119542725,0.000028426804,0.2918641,0.0008436472,0.70350456,0.0030173352,0.000033290573],"about_ca_topic_score_codex":0.0009086961,"about_ca_topic_score_gemma":0.00079041714,"teacher_disagreement_score":0.011006349,"about_ca_system_score_codex":0.003946359,"about_ca_system_score_gemma":0.0020017743,"threshold_uncertainty_score":0.054377496},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01042259,0.0005532646,0.98559904,0.00045360834,0.0000936785,0.000057662102,0.000051526302,0.0002080397,0.0025605457],"genre_scores_gemma":[0.60492086,0.0019709037,0.37637088,0.00088914623,0.00046381744,0.00100657,0.00047152225,0.0007497591,0.013156411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947425,0.0029175368,0.0002316536,0.0005952699,0.0011558536,0.0003570772],"domain_scores_gemma":[0.95530385,0.03328168,0.0023547593,0.0025153963,0.0049310047,0.0016133193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01918491,0.0019715747,0.002046724,0.0033083605,0.0008111699,0.0023400343,0.0030375565,0.0019557832,0.0044854986],"category_scores_gemma":[0.08012067,0.00090180844,0.002311732,0.0014427169,0.00488939,0.004796594,0.004458407,0.0054673143,0.0008278421],"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":[0.000119896475,0.00007124269,0.002050213,0.00025939685,0.00008876423,0.00021601483,0.00023960514,0.15387976,0.0020523337,0.8218493,0.0013754664,0.017798109],"study_design_scores_gemma":[0.000013044369,0.000045472567,0.0003290665,0.000042939224,0.000015507614,0.000059203823,0.000015194741,0.85082304,0.0009122188,0.14695169,0.00076654507,0.000026100672],"about_ca_topic_score_codex":0.0036271752,"about_ca_topic_score_gemma":0.0026084387,"teacher_disagreement_score":0.01918491,"about_ca_system_score_codex":0.0032323876,"about_ca_system_score_gemma":0.0024128729,"threshold_uncertainty_score":0.101460695},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02036745,0.0004175529,0.97535217,0.000924656,0.000043069136,0.000056301462,0.00021301044,0.000385991,0.0022397311],"genre_scores_gemma":[0.6770836,0.0009575564,0.31429535,0.00072246685,0.00038076745,0.00040116347,0.0007862133,0.00030577756,0.0050671906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994115,0.0022690578,0.00026856567,0.001085872,0.00158352,0.00067805964],"domain_scores_gemma":[0.9507005,0.036228478,0.0027624168,0.008068228,0.0014370208,0.0008033209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074495743,0.0015387968,0.0023967205,0.0011823311,0.0011037803,0.0034590322,0.0035419888,0.0021885578,0.003940695],"category_scores_gemma":[0.05355184,0.0011350617,0.001723915,0.0016487443,0.0034956348,0.0080185225,0.0062072133,0.0059518586,0.0008529632],"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":[0.0013314921,0.00026112146,0.0049656453,0.00043956086,0.00025553606,0.0003927381,0.000480901,0.5049692,0.010822093,0.38795796,0.006294684,0.08182904],"study_design_scores_gemma":[0.000026948963,0.000045403507,0.00047144055,0.000027900942,0.000021860513,0.00012901954,0.000026643276,0.8625364,0.0034233492,0.13251166,0.00075348676,0.000025828527],"about_ca_topic_score_codex":0.0009758092,"about_ca_topic_score_gemma":0.001389229,"teacher_disagreement_score":0.0074495743,"about_ca_system_score_codex":0.003317193,"about_ca_system_score_gemma":0.0024340497,"threshold_uncertainty_score":0.039397538},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037426606,0.00064307655,0.9486169,0.002773075,0.00011866646,0.0003214293,0.0007376999,0.0017067214,0.007655891],"genre_scores_gemma":[0.773031,0.00040513847,0.21460229,0.0015639685,0.0004890441,0.00062638253,0.0013749922,0.00027059353,0.007636533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9855096,0.007844562,0.00047655826,0.0029546227,0.0021827468,0.001032036],"domain_scores_gemma":[0.943781,0.03938086,0.002272722,0.012061141,0.0014124354,0.0010918297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011231775,0.0010173736,0.00258769,0.0010451584,0.0014398338,0.003527164,0.0042924182,0.0025614079,0.01331001],"category_scores_gemma":[0.045361202,0.0007366408,0.0015110257,0.00218704,0.0035857025,0.008326879,0.006962378,0.004044465,0.002683722],"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":[0.0034670262,0.0006491307,0.010266456,0.00084392034,0.00051183335,0.0017157714,0.0014402419,0.15910524,0.013880605,0.46119732,0.018679995,0.32824248],"study_design_scores_gemma":[0.00029360547,0.00036007067,0.0013776863,0.000050234146,0.0000826575,0.00059933175,0.0002049082,0.5400621,0.008230841,0.442461,0.006218483,0.000058988662],"about_ca_topic_score_codex":0.0007806047,"about_ca_topic_score_gemma":0.0008055327,"teacher_disagreement_score":0.01331001,"about_ca_system_score_codex":0.0026894496,"about_ca_system_score_gemma":0.0025173991,"threshold_uncertainty_score":0.059400022},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033519953,0.00020441436,0.9610369,0.00033774629,0.000035663947,0.000053345935,0.000033398606,0.00049866794,0.004279772],"genre_scores_gemma":[0.8188206,0.00019976556,0.17499593,0.00027409205,0.000038284637,0.0003289862,0.00011501158,0.00027646025,0.004950889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822205,0.00085419865,0.00007044216,0.00029935822,0.0003656888,0.00018821156],"domain_scores_gemma":[0.99452764,0.0038670897,0.00043039882,0.00056799216,0.00031313347,0.00029376106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027960155,0.0013217574,0.0011284595,0.00060891197,0.00066045154,0.001109194,0.0019518993,0.0014218898,0.0021607873],"category_scores_gemma":[0.016206147,0.0006290858,0.00068416126,0.00049670093,0.0023301388,0.0017938508,0.0021249016,0.0023874114,0.0005145133],"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":[0.00021828896,0.00011338277,0.0012097744,0.00007167867,0.00007129532,0.00017012865,0.0001489881,0.8189125,0.0020359755,0.14102805,0.0018684381,0.034151595],"study_design_scores_gemma":[0.000015125865,0.000032599568,0.00006509796,0.0000075396033,0.0000055723385,0.000015871512,0.000004127668,0.962427,0.000468382,0.036651596,0.00030105325,0.0000060890684],"about_ca_topic_score_codex":0.0032679073,"about_ca_topic_score_gemma":0.0030318825,"teacher_disagreement_score":0.0032679073,"about_ca_system_score_codex":0.0012348366,"about_ca_system_score_gemma":0.0016346049,"threshold_uncertainty_score":0.014786899},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035330083,0.00033142223,0.96282953,0.00041536987,0.000023615814,0.000032451964,0.000054795106,0.00029817375,0.0006846035],"genre_scores_gemma":[0.6778373,0.0003449186,0.31654087,0.00060074497,0.000062020044,0.00020805074,0.00025905942,0.00022753939,0.0039194683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998487,0.0008160195,0.00007469867,0.00027221342,0.00020776085,0.00014224202],"domain_scores_gemma":[0.9892306,0.007743221,0.00077075476,0.0011754496,0.00078947074,0.0002904727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064843944,0.0016269038,0.0019468516,0.0007266862,0.00035701777,0.0012394264,0.0021104307,0.002618199,0.0012050254],"category_scores_gemma":[0.025607288,0.00090778666,0.00096422277,0.00067152735,0.0025713902,0.003118168,0.0036990424,0.003602314,0.00034280843],"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":[0.000167453,0.00004230166,0.0016664189,0.00012326056,0.00007129694,0.00012969218,0.00013121069,0.9205435,0.0029781377,0.048012473,0.0005892423,0.025545094],"study_design_scores_gemma":[0.000007084474,0.000025296427,0.000059191785,0.000007218225,0.0000039471556,0.000006712629,0.000002764814,0.99092543,0.00039267406,0.008494125,0.000070770024,0.00000487194],"about_ca_topic_score_codex":0.0033139721,"about_ca_topic_score_gemma":0.0033144366,"teacher_disagreement_score":0.0064843944,"about_ca_system_score_codex":0.0015897147,"about_ca_system_score_gemma":0.0012008414,"threshold_uncertainty_score":0.034293115},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13861638,0.0006513917,0.8448364,0.0018324716,0.00009896597,0.000105438376,0.0002043953,0.00025122645,0.013403447],"genre_scores_gemma":[0.9608389,0.00024079374,0.03472192,0.00037960976,0.00012563409,0.00017412352,0.0000836412,0.000048910282,0.0033863548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467635,0.00266699,0.00018000079,0.0007854932,0.0007421059,0.00094905106],"domain_scores_gemma":[0.98528093,0.01070429,0.0015952281,0.0010926473,0.0006343409,0.00069249055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060250578,0.0016394827,0.0023894133,0.00077482295,0.0010640783,0.0028748452,0.002633716,0.0030438558,0.0016764068],"category_scores_gemma":[0.020004814,0.0008338852,0.0013603248,0.001233412,0.0034255257,0.0030117389,0.0030846158,0.0027607896,0.00046539426],"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":[0.00035807147,0.000121972706,0.0008491413,0.00010814575,0.00011119243,0.00026537577,0.00013233045,0.8836059,0.0014881981,0.1061936,0.0011636659,0.005602449],"study_design_scores_gemma":[0.000036648325,0.00007049189,0.00013371029,0.000013760775,0.000015920057,0.000056956436,0.000028253784,0.9452104,0.00035406885,0.053831577,0.00023492234,0.000013304397],"about_ca_topic_score_codex":0.0020276092,"about_ca_topic_score_gemma":0.0012407671,"teacher_disagreement_score":0.0060250578,"about_ca_system_score_codex":0.002116095,"about_ca_system_score_gemma":0.0016868623,"threshold_uncertainty_score":0.031863928},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010814827,0.0001999061,0.9849606,0.0003605152,0.00004652952,0.000079547564,0.000073843046,0.00045731434,0.0030068976],"genre_scores_gemma":[0.49505052,0.000335307,0.49849546,0.00052804244,0.00014818266,0.00045259946,0.00043527375,0.00023267105,0.004321934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974957,0.0012015849,0.000096964046,0.0003619257,0.00061319885,0.00023064514],"domain_scores_gemma":[0.9924948,0.0053817946,0.00038482167,0.0008692683,0.00053874584,0.00033047804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036710366,0.0009870294,0.0016387127,0.0009180969,0.00066885725,0.0017388593,0.0023374655,0.0016784926,0.00370083],"category_scores_gemma":[0.021473106,0.0006957942,0.0007564368,0.0010003529,0.0017789528,0.0021047136,0.0023588694,0.002659004,0.0010170378],"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":[0.0004184564,0.00026293762,0.0014959854,0.00021053744,0.0000863471,0.00013270447,0.00017411738,0.5031307,0.0025361294,0.35481563,0.006423927,0.13031259],"study_design_scores_gemma":[0.000037061847,0.000032904034,0.00006656585,0.000016746635,0.000006940715,0.000028445831,0.000008898449,0.92540944,0.00060503185,0.07284599,0.000934264,0.0000077104605],"about_ca_topic_score_codex":0.0018097862,"about_ca_topic_score_gemma":0.0026285956,"teacher_disagreement_score":0.00370083,"about_ca_system_score_codex":0.002047173,"about_ca_system_score_gemma":0.002524137,"threshold_uncertainty_score":0.019414544},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23021504,0.00077198114,0.7532955,0.0028817242,0.00021570061,0.00038353578,0.0017182578,0.0055772364,0.004941028],"genre_scores_gemma":[0.7244607,0.00032990504,0.26092213,0.0016531094,0.0004299077,0.00071610813,0.0064119413,0.0009361784,0.0041399277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99158305,0.0028215044,0.00057234743,0.002502666,0.0018922227,0.0006281614],"domain_scores_gemma":[0.92983675,0.053255435,0.0025239424,0.00973039,0.003011523,0.0016418908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007194861,0.0021054328,0.0026894584,0.0014643143,0.0015775776,0.0032879878,0.0059794993,0.0029830416,0.00777153],"category_scores_gemma":[0.07238828,0.0010305189,0.0027951726,0.002341473,0.003438934,0.009807803,0.006473823,0.006532435,0.0021149495],"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":[0.00450004,0.0016092586,0.05058598,0.000638981,0.0005961251,0.0008212796,0.0008896531,0.41839117,0.0074455375,0.19255364,0.026970938,0.2949974],"study_design_scores_gemma":[0.00010246607,0.00019833392,0.0010769021,0.000028484776,0.000026407548,0.00017168693,0.00012069424,0.8576603,0.0025753924,0.13694833,0.0010622831,0.000028728811],"about_ca_topic_score_codex":0.0039652167,"about_ca_topic_score_gemma":0.0047672,"teacher_disagreement_score":0.00777153,"about_ca_system_score_codex":0.0020662302,"about_ca_system_score_gemma":0.0028125395,"threshold_uncertainty_score":0.038050532},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18348527,0.0016931911,0.79198,0.0036409977,0.0000968615,0.0001153199,0.00042739045,0.0019176656,0.016643256],"genre_scores_gemma":[0.7567539,0.0009423294,0.23389958,0.0007982903,0.00011498417,0.00018440529,0.0005477031,0.00040310522,0.0063557066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981706,0.000566676,0.00010458063,0.00041686033,0.0005097059,0.00023151544],"domain_scores_gemma":[0.9911142,0.00670441,0.0004523427,0.001048602,0.00041052196,0.0002697904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022498716,0.001300104,0.00090386055,0.0008891154,0.00072737946,0.0020205153,0.0020466626,0.0016630279,0.0035465069],"category_scores_gemma":[0.019627495,0.000798873,0.0014553118,0.000688157,0.0025348824,0.009179484,0.0036907638,0.0035302273,0.00056044065],"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":[0.0010506494,0.00015765199,0.006625864,0.0005000503,0.00012387199,0.00025877976,0.00079956796,0.5878466,0.014030467,0.26729834,0.003983139,0.11732508],"study_design_scores_gemma":[0.000022846934,0.000075750235,0.00042737238,0.000039087932,0.00002902606,0.00007999965,0.00005514075,0.858995,0.0037536821,0.13434961,0.0021564362,0.000016019687],"about_ca_topic_score_codex":0.004462123,"about_ca_topic_score_gemma":0.0062687197,"teacher_disagreement_score":0.004462123,"about_ca_system_score_codex":0.0036390007,"about_ca_system_score_gemma":0.0015139277,"threshold_uncertainty_score":0.02640289},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043236166,0.00092958193,0.9511062,0.0009550775,0.00006668054,0.000076234755,0.00009655034,0.00035758005,0.0031758354],"genre_scores_gemma":[0.8814241,0.0006222217,0.1108362,0.00050688157,0.00011624992,0.00027325237,0.0002337445,0.00019284667,0.0057944315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983766,0.000770126,0.00006622304,0.00035622626,0.00021294734,0.00021798749],"domain_scores_gemma":[0.98690784,0.010995051,0.0008075689,0.00043617058,0.00042486706,0.00042861424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042975447,0.001944089,0.0026607406,0.0006502641,0.0005695617,0.0016168846,0.0022107542,0.0022656021,0.0032344626],"category_scores_gemma":[0.019237835,0.0011873025,0.0009558189,0.00064574525,0.0026436145,0.002936811,0.0026870524,0.004106457,0.000481903],"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":[0.00012876831,0.00006390307,0.0005349607,0.000078546815,0.00005560245,0.000057335466,0.000048943595,0.96002555,0.0003948712,0.030244514,0.0005600091,0.007806947],"study_design_scores_gemma":[0.000011828871,0.000016274147,0.000033297652,0.0000048409297,0.0000039308916,0.000003476604,0.0000028916822,0.9901966,0.000087082204,0.009557727,0.00007919826,0.0000028890609],"about_ca_topic_score_codex":0.0065328125,"about_ca_topic_score_gemma":0.003883637,"teacher_disagreement_score":0.0065328125,"about_ca_system_score_codex":0.002921406,"about_ca_system_score_gemma":0.002061725,"threshold_uncertainty_score":0.022727847},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11162674,0.0020801078,0.8689936,0.003075062,0.00015943698,0.00012676691,0.00017620972,0.00057780853,0.013184214],"genre_scores_gemma":[0.83565515,0.002149785,0.14875129,0.0010884703,0.00023896487,0.0005997261,0.0004542747,0.0010473452,0.01001502],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981244,0.0010700884,0.00005344765,0.00024304769,0.00029921732,0.00020972833],"domain_scores_gemma":[0.9560564,0.037872896,0.0015864659,0.0015344282,0.0016270232,0.001322809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010156654,0.0014924485,0.0016739937,0.0014587895,0.001389655,0.0019882056,0.0031474032,0.0023231504,0.0032336046],"category_scores_gemma":[0.05688222,0.00080968766,0.0015588009,0.00086441915,0.0049681114,0.00476789,0.0040155286,0.0042954315,0.0004887366],"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":[0.00028644086,0.000107607055,0.0039635138,0.0002791783,0.00009057664,0.00023675934,0.00032742287,0.5231228,0.0026999637,0.45632878,0.0021715355,0.010385448],"study_design_scores_gemma":[0.000015146822,0.000031030984,0.00018915941,0.000037650265,0.000009602818,0.000024996978,0.000021369407,0.93003666,0.0004941398,0.06878212,0.00034122242,0.000016910235],"about_ca_topic_score_codex":0.005815599,"about_ca_topic_score_gemma":0.0046269763,"teacher_disagreement_score":0.010156654,"about_ca_system_score_codex":0.0025195132,"about_ca_system_score_gemma":0.0020169597,"threshold_uncertainty_score":0.053714097},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05393384,0.0010719827,0.93585694,0.0012024611,0.000077969315,0.000046843,0.00009183431,0.0004370124,0.0072811027],"genre_scores_gemma":[0.86564195,0.0012421624,0.12689078,0.0004575547,0.00019856771,0.00025052857,0.000219785,0.00044196486,0.0046568173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988205,0.00038854766,0.00005501478,0.00024024268,0.00034523822,0.00015046781],"domain_scores_gemma":[0.9875925,0.008959731,0.0009306864,0.0011043207,0.0009091548,0.0005036161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034485955,0.0008762229,0.0010473697,0.0014770059,0.0007684032,0.0018732499,0.0016994762,0.0011784087,0.003076253],"category_scores_gemma":[0.026884945,0.0005652046,0.00095476856,0.00071407907,0.0031335722,0.0045561222,0.0025191752,0.0029367777,0.00041595905],"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":[0.000067421024,0.00006640222,0.0015785333,0.00016372884,0.00006878712,0.0002704462,0.00018835731,0.35305515,0.003946422,0.6253328,0.0021340207,0.013127993],"study_design_scores_gemma":[0.0000045874785,0.00001478687,0.00017890298,0.000014015571,0.0000057537563,0.000036280682,0.000012050164,0.8652208,0.00072826474,0.13325399,0.0005191955,0.000011365904],"about_ca_topic_score_codex":0.0020528426,"about_ca_topic_score_gemma":0.0016655751,"teacher_disagreement_score":0.0034485955,"about_ca_system_score_codex":0.0018579235,"about_ca_system_score_gemma":0.0011562394,"threshold_uncertainty_score":0.018238127},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44881222,0.0049186316,0.37941355,0.042925604,0.0018126754,0.00036740134,0.0143228425,0.0037425293,0.10368457],"genre_scores_gemma":[0.9430348,0.0011586003,0.032793738,0.0024528808,0.0009351522,0.0002851876,0.0058232252,0.00044727852,0.0130691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956664,0.0005621511,0.0001806147,0.0022710802,0.00062350027,0.0006961694],"domain_scores_gemma":[0.9696998,0.020457242,0.00149813,0.003978292,0.0027301519,0.0016363502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023759583,0.0010188736,0.0017306316,0.0011803135,0.0030853825,0.008209666,0.0037583727,0.005286409,0.02491465],"category_scores_gemma":[0.030739926,0.0008364489,0.0015035162,0.002179039,0.0042169234,0.018273905,0.0034168588,0.009587871,0.002675443],"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":[0.00074711046,0.00060325995,0.013076667,0.0011520179,0.00026279158,0.00016588513,0.00080346153,0.017118819,0.0021377981,0.5724533,0.08667717,0.3048017],"study_design_scores_gemma":[0.00008549846,0.00010650577,0.0029637127,0.00016367878,0.00005472371,0.00020395579,0.0005863958,0.04003898,0.002019198,0.93897057,0.014762993,0.000043733526],"about_ca_topic_score_codex":0.003838206,"about_ca_topic_score_gemma":0.003478912,"teacher_disagreement_score":0.02491465,"about_ca_system_score_codex":0.0024798834,"about_ca_system_score_gemma":0.003382986,"threshold_uncertainty_score":0.0833478},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051778415,0.00007281072,0.99228585,0.00034999193,0.000023643006,0.00009033098,0.000081025304,0.0008761305,0.0010423376],"genre_scores_gemma":[0.3161701,0.00018325729,0.6748466,0.00063112105,0.00017678573,0.00086167577,0.000722921,0.00058639306,0.0058212196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994197,0.002524935,0.00019435953,0.0011930283,0.001562893,0.00032779205],"domain_scores_gemma":[0.9516176,0.035298623,0.0017156997,0.0075011896,0.002938021,0.00092886516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009972543,0.0014353298,0.0014557746,0.001253172,0.0014373987,0.0035053503,0.007877616,0.0029840004,0.0057723843],"category_scores_gemma":[0.03487288,0.0009054465,0.0011207034,0.0012927208,0.0034768772,0.0070403786,0.00670777,0.006079498,0.0017658594],"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":[0.0015330656,0.0008602491,0.0038454433,0.000726983,0.0002173468,0.00019520475,0.0010608414,0.31672356,0.014790419,0.29612902,0.01342085,0.35049713],"study_design_scores_gemma":[0.00005800222,0.00011200466,0.000117343036,0.000015608273,0.000015457252,0.000040714185,0.000036500765,0.91492563,0.0051545925,0.077808,0.0017013174,0.000014982341],"about_ca_topic_score_codex":0.0017872468,"about_ca_topic_score_gemma":0.0021972812,"teacher_disagreement_score":0.009972543,"about_ca_system_score_codex":0.0022709807,"about_ca_system_score_gemma":0.00197183,"threshold_uncertainty_score":0.052740455},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2493138,0.0017012926,0.73309684,0.0055748248,0.00009699439,0.00023643108,0.0010461628,0.001416733,0.0075168894],"genre_scores_gemma":[0.82162565,0.000926794,0.1691489,0.0011534123,0.00027821248,0.0005483532,0.002177966,0.00039510717,0.0037455813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98961055,0.004722027,0.0006573863,0.0022482136,0.002072667,0.00068929273],"domain_scores_gemma":[0.8608232,0.11929782,0.0043333266,0.011357113,0.0028626495,0.0013257893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01270111,0.0011780766,0.0024388803,0.0012393396,0.001231807,0.0043087797,0.0032454082,0.0028731974,0.0030212007],"category_scores_gemma":[0.084173895,0.0010653732,0.0015025424,0.0014790545,0.0037959989,0.009947721,0.0041306578,0.0055505517,0.00059915084],"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":[0.0022073565,0.0004125736,0.01248381,0.0007282103,0.00028224254,0.00026746906,0.0006557585,0.5908399,0.005420724,0.27416113,0.007389394,0.105151415],"study_design_scores_gemma":[0.00007522441,0.0001163119,0.0013476921,0.000044889897,0.0000325524,0.00013463611,0.00005715348,0.7880032,0.0017697221,0.20772515,0.00066077453,0.00003262799],"about_ca_topic_score_codex":0.0020635948,"about_ca_topic_score_gemma":0.00203125,"teacher_disagreement_score":0.01270111,"about_ca_system_score_codex":0.0042271777,"about_ca_system_score_gemma":0.0026571695,"threshold_uncertainty_score":0.06717068},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0101804575,0.00015103583,0.98761785,0.00015356098,0.000023355427,0.00002352155,0.000015204711,0.00026823685,0.001566832],"genre_scores_gemma":[0.80927944,0.0002704483,0.18276688,0.00023236367,0.000058299425,0.0001744431,0.00012535797,0.00013030642,0.006962366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858475,0.00057231425,0.00007579694,0.00022445022,0.00038042196,0.00016220241],"domain_scores_gemma":[0.99745303,0.0013625252,0.00026759438,0.00049686804,0.0003151932,0.00010477109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001860294,0.00087680673,0.001381903,0.0004678743,0.00037415893,0.0010179984,0.0019330666,0.001330218,0.0026726017],"category_scores_gemma":[0.009071812,0.000592013,0.00044640983,0.0005466783,0.0015692769,0.002378393,0.0020600322,0.002584088,0.00061499455],"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":[0.0001534725,0.00012702198,0.0007214198,0.00011032251,0.000056125886,0.00008379658,0.00009197497,0.8176853,0.0017360165,0.12523326,0.0014868611,0.052514415],"study_design_scores_gemma":[0.000010870319,0.000019229541,0.000034012974,0.000003815441,0.000003934866,0.000014025362,0.0000036554213,0.9684824,0.00029437363,0.030806553,0.00032332746,0.0000038496946],"about_ca_topic_score_codex":0.0023732483,"about_ca_topic_score_gemma":0.0022857839,"teacher_disagreement_score":0.0026726017,"about_ca_system_score_codex":0.0010398349,"about_ca_system_score_gemma":0.0011683039,"threshold_uncertainty_score":0.009838283},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22299281,0.002170077,0.74773234,0.0045518293,0.0002496656,0.00029090157,0.0015312773,0.0006289764,0.019852092],"genre_scores_gemma":[0.9594843,0.00085395883,0.027963558,0.0004897846,0.00019467436,0.00043010854,0.00072404556,0.00014003801,0.009719467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963741,0.0020420474,0.00015829652,0.00046242785,0.00032285837,0.00064023153],"domain_scores_gemma":[0.9651681,0.030696437,0.0015925486,0.0006301739,0.0007188516,0.0011938476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074625113,0.0022608386,0.0037615683,0.0012243242,0.00092135114,0.0027745995,0.0023369472,0.0024845235,0.005473551],"category_scores_gemma":[0.01802961,0.000959537,0.0011476158,0.0010683932,0.0027096006,0.0029022787,0.002874147,0.0030958473,0.0004939888],"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":[0.00038293758,0.00008164937,0.001218957,0.00016608441,0.00010998677,0.00013189718,0.000074139396,0.95024556,0.00020418175,0.039415926,0.0018462132,0.006122521],"study_design_scores_gemma":[0.000044652195,0.000057362064,0.00017657255,0.000016692436,0.00001015418,0.000019378178,0.000015862517,0.96901727,0.00006308209,0.030408666,0.00015878175,0.000011483676],"about_ca_topic_score_codex":0.0063538547,"about_ca_topic_score_gemma":0.0046984414,"teacher_disagreement_score":0.0074625113,"about_ca_system_score_codex":0.0036434932,"about_ca_system_score_gemma":0.0026741263,"threshold_uncertainty_score":0.039466023},"labels":[],"label_agreement":null}]}