{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":27,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":27,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"1592200117c9","filters":{"venue":"Conference on Learning Theory"}},"results":[{"id":"W1589919686","doi":"","title":"Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.","year":2008,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Computer science; Semi-supervised learning; Homogeneous; Distribution (mathematics); Artificial intelligence; Conjecture; Sample (material); Class (philosophy); Labeled data; Supervised learning; Machine learning; Pattern recognition (psychology); Mathematics; Artificial neural network; Discrete mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.1094726326608954,"gpt":0.3005835196592879,"spread":0.1911108869983926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002033402,0.0002366982,0.0005220857,0.0003124982,0.0005521429,0.00006801938,0.00258896,0.000101692,0.0002350741],"category_scores_gemma":[0.003443418,0.0001421227,0.0001543339,0.001610324,0.0006481658,0.00033174,0.0009704476,0.0007906125,0.00001529721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002694965,"about_ca_system_score_gemma":0.0002225597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003713163,"about_ca_topic_score_gemma":0.00006921801,"domain_scores_codex":[0.9962797,0.001651878,0.0005228202,0.000748156,0.0004997643,0.0002976503],"domain_scores_gemma":[0.9950982,0.001306794,0.0006724973,0.002539643,0.0002916398,0.00009123523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002844102,0.0006297041,0.2683807,0.0001671712,0.001054528,0.00005502323,0.009647001,0.01821464,0.005431186,0.6018642,0.0002038829,0.09406758],"study_design_scores_gemma":[0.0005343439,0.0002254615,0.06798401,0.0001015096,0.0002736543,0.00003210279,0.0008228603,0.9206918,0.0008382852,0.005651091,0.002489695,0.0003551994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6035352,0.00006233552,0.3912469,0.001324412,0.0002269512,0.0003558729,0.0001155962,0.0003044562,0.002828205],"genre_scores_gemma":[0.9932922,0.00005684969,0.005183752,0.0000630356,0.00002581341,0.000008339051,0.0002292578,0.00001469927,0.001126092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9024771,"threshold_uncertainty_score":0.5795596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965944281","doi":"","title":"Tight analyses for non-smooth stochastic gradient descent","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Lipschitz continuity; Stochastic gradient descent; Differentiable function; Combinatorics; Convex function; Gradient descent; Upper and lower bounds; Regular polygon; Discrete mathematics; Applied mathematics; Mathematical analysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04690993015189428,"gpt":0.3102476221312967,"spread":0.2633376919794024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005947166,0.0002354505,0.0002738703,0.0002781158,0.0001679565,0.0001664508,0.0008620302,0.00008204028,0.0001298394],"category_scores_gemma":[0.0003178318,0.0002078406,0.0001164269,0.0002920722,0.00007214987,0.000195667,0.0001487141,0.0002522494,0.0001956096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007927304,"about_ca_system_score_gemma":0.0001055896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002074141,"about_ca_topic_score_gemma":4.294957e-7,"domain_scores_codex":[0.9983742,0.0001141738,0.0002524087,0.0005896972,0.0002756598,0.0003939056],"domain_scores_gemma":[0.9982857,0.0005610347,0.000192769,0.0006202292,0.0002181232,0.0001222132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005276585,0.00007526689,0.00007659453,0.00002195348,0.00002811702,0.000001341607,0.0007526672,0.02500296,0.001196654,0.9558377,0.0002062691,0.0167477],"study_design_scores_gemma":[0.000717464,0.001096972,0.0005848994,0.0002507227,0.00002656131,0.000004572322,0.0001863529,0.9044617,0.002341426,0.08919884,0.0006373452,0.0004931325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006060097,0.00002328467,0.9870684,0.0001723001,0.0004085263,0.0006415672,0.000001672178,0.0004546574,0.005169563],"genre_scores_gemma":[0.9603824,0.000005460807,0.03630149,0.0001837702,0.00003467724,0.0001079622,0.000009469995,0.00002459272,0.002950154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9543223,"threshold_uncertainty_score":0.8475491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966286942","doi":"","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Minimax; Mathematics; Bayesian probability; Mathematical economics; Degenerate energy levels; Mathematical optimization; Computer science; Discrete mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.09132089929786394,"gpt":0.4067404308935916,"spread":0.3154195315957277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005651754,0.000198326,0.0003226608,0.0006974094,0.0001272909,0.0004534742,0.001264347,0.0001217212,0.0009174565],"category_scores_gemma":[0.005595585,0.0001560234,0.00005564732,0.0008698106,0.0001555281,0.001049852,0.0001692599,0.0007193206,0.005664249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000885672,"about_ca_system_score_gemma":0.0001637541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006495758,"about_ca_topic_score_gemma":5.162152e-7,"domain_scores_codex":[0.9961051,0.0008623823,0.0005390351,0.0005499312,0.00143089,0.0005126676],"domain_scores_gemma":[0.9969584,0.001392096,0.0001682867,0.0008757473,0.000360361,0.0002451252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001443503,0.0002778986,0.0342928,0.00002544627,0.00001439744,0.00001041645,0.01757896,0.1428238,0.0007027031,0.3451034,0.0002413623,0.4574854],"study_design_scores_gemma":[0.003543865,0.003491203,0.07325065,0.0003675493,0.00001126102,0.00002089473,0.06064617,0.3887264,0.005190481,0.4181623,0.04473951,0.001849763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.751332,0.00002024463,0.1590222,0.0003180393,0.0006108609,0.0008161677,0.000007375236,0.0001562394,0.0877169],"genre_scores_gemma":[0.9940724,0.000006895964,0.002106013,0.00007536254,0.00009129308,0.00005428692,0.000008648612,0.00001623019,0.003568887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4556356,"threshold_uncertainty_score":0.9999958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W43025842","doi":"","title":"PLAL: Cluster-based active learning","year":2013,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Complement (music); Computer science; Preprocessor; Probabilistic logic; Smoothness; Sample (material); Simple (philosophy); Active learning (machine learning); Artificial intelligence; Machine learning; Semi-supervised learning; Process (computing); Cluster (spacecraft); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01420798321609177,"gpt":0.247912240700798,"spread":0.2337042574847062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008743241,0.0003140048,0.0002845686,0.0002246536,0.0005156926,0.000483346,0.00104371,0.0001365288,0.0009760652],"category_scores_gemma":[0.0008402485,0.0002768984,0.0001149491,0.0003086335,0.0001236488,0.0004389801,0.0002336367,0.001635897,0.002491128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005209981,"about_ca_system_score_gemma":0.0001428562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004484224,"about_ca_topic_score_gemma":7.409853e-7,"domain_scores_codex":[0.9971011,0.001030286,0.0002461117,0.0006739831,0.0003880799,0.0005604678],"domain_scores_gemma":[0.9978884,0.0009734326,0.0002243348,0.0005236464,0.0001852801,0.0002048863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005554268,0.0001077871,0.0008501681,0.00002288152,0.00003434949,0.00001479015,0.002170335,0.038633,0.0007344916,0.2466398,0.0003524552,0.7103844],"study_design_scores_gemma":[0.0008908871,0.0007662462,0.003595594,0.0001552154,0.000008727496,0.000009603684,0.0005341538,0.9584109,0.000902463,0.02234547,0.01178408,0.0005966782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0648552,0.00003331933,0.8475245,0.002927747,0.0004832421,0.0003303219,6.18893e-7,0.001544719,0.08230037],"genre_scores_gemma":[0.9806794,0.000007267581,0.006389363,0.0007136634,0.0001220753,0.00006180808,0.000009262502,0.00003438371,0.01198278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9197779,"threshold_uncertainty_score":0.9999683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W9422450","doi":"","title":"Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Minimax; Outcome (game theory); Action (physics); Logarithm; Computer science; Mathematical optimization; Mathematics; Mathematical economics; Statistics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2434593967789235,"gpt":0.4046804874307592,"spread":0.1612210906518357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003543719,0.0001804849,0.0003577982,0.000448207,0.00008975132,0.00004456486,0.0008228477,0.0000986713,0.001637695],"category_scores_gemma":[0.009388884,0.0001462731,0.00007175926,0.0004081513,0.0004223302,0.0002394648,0.0002185866,0.0005767801,0.000602951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005067309,"about_ca_system_score_gemma":0.00007919039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001052834,"about_ca_topic_score_gemma":0.000001455246,"domain_scores_codex":[0.9966552,0.0007230219,0.0005647541,0.0005432352,0.001093808,0.0004199814],"domain_scores_gemma":[0.9958445,0.003054588,0.0003060946,0.0005849701,0.00008923819,0.0001206425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002528215,0.000726415,0.06787108,0.00002202944,0.00007177454,0.0001658217,0.02848786,0.06851728,0.00688444,0.03557675,0.00005140051,0.789097],"study_design_scores_gemma":[0.003415802,0.002727577,0.2307504,0.001075598,0.00003279066,0.00001080836,0.02671273,0.06783741,0.05130927,0.6116197,0.003113016,0.001394961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5640011,0.0002407765,0.4186366,0.00008062513,0.0005831943,0.0004451188,0.000009461096,0.00006780644,0.01593523],"genre_scores_gemma":[0.9931802,0.00003653697,0.0007948738,0.000007285135,0.00004361662,0.00002478714,0.000001177232,0.00001873707,0.00589277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.787702,"threshold_uncertainty_score":0.999275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046729600","doi":"","title":"Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Regret; Gradient descent; Bounded function; Descent (aeronautics); Mathematical optimization; Computer science; Property (philosophy); Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis; Engineering; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1225592921582373,"gpt":0.372425274325463,"spread":0.2498659821672256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001858581,0.0002669323,0.0003802536,0.0001410331,0.0003727873,0.000396936,0.0007438383,0.00007304096,0.0007353574],"category_scores_gemma":[0.01042245,0.0001854845,0.00006096055,0.000463133,0.000402798,0.000262731,0.0003203344,0.0008193866,0.000305079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004765789,"about_ca_system_score_gemma":0.00009458498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007703748,"about_ca_topic_score_gemma":0.000006350088,"domain_scores_codex":[0.9959812,0.0007862716,0.0004193707,0.0008740652,0.001430331,0.0005088309],"domain_scores_gemma":[0.9938733,0.004654675,0.0003015758,0.0004235152,0.0003519319,0.0003950195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001941601,0.0001154919,0.02488542,0.0000413012,0.00008392719,0.0002523203,0.006260262,0.01731906,0.001901533,0.01319677,0.0003805176,0.9336218],"study_design_scores_gemma":[0.006503935,0.005742114,0.05327256,0.000967431,0.00006546707,0.00008653921,0.02054805,0.7799767,0.00621571,0.09442037,0.03005073,0.002150409],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2910481,0.0002022379,0.700942,0.00323287,0.0001633758,0.0004735049,0.00001007056,0.000221177,0.0037066],"genre_scores_gemma":[0.9934071,0.0000828188,0.004336847,0.0003538373,0.0001084745,0.00001623166,0.000003187953,0.00003278395,0.001658682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9314714,"threshold_uncertainty_score":0.9979132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046526692","doi":"","title":"Private Mean Estimation of Heavy-Tailed Distributions","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Univariate; Sample complexity; Bounded function; Minimax; Combinatorics; Mathematics; Differential privacy; Sample mean and sample covariance; Upper and lower bounds; Multivariate statistics; Sample (material); Estimation; Discrete mathematics; Statistics; Mathematical analysis; Computer science; Mathematical optimization; Physics; Estimator; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04420529321116277,"gpt":0.2818828961734084,"spread":0.2376776029622457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005524044,0.00014342,0.0002004541,0.00007203696,0.0001415423,0.00008798257,0.009504503,0.00009096718,0.00007449315],"category_scores_gemma":[0.02914874,0.0001365579,0.00004904168,0.0004298909,0.0001836414,0.0003402936,0.01239675,0.0004655584,0.0001378967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003591413,"about_ca_system_score_gemma":0.00007803216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001883537,"about_ca_topic_score_gemma":2.253751e-7,"domain_scores_codex":[0.9986403,0.0002208432,0.000247012,0.000412826,0.0002412487,0.0002377711],"domain_scores_gemma":[0.9968135,0.0003254834,0.0002019014,0.002489555,0.00008699569,0.000082581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003502502,0.00003402248,0.0002335546,0.00002575808,0.00001656817,0.000004483953,0.0003401276,0.0008820755,0.001649862,0.9283481,0.001852485,0.06657797],"study_design_scores_gemma":[0.0001708541,0.0001987155,0.0004090525,0.00007212271,0.000005621046,0.000001474554,0.00005225957,0.4905715,0.01187507,0.4959546,0.0005431651,0.0001455932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02552916,0.00002338301,0.9535194,0.01772859,0.00007774343,0.0001230868,0.00001199481,0.0009327625,0.002053899],"genre_scores_gemma":[0.930398,0.00001938098,0.06938045,0.0001148292,0.00001324927,0.00001053181,0.000028043,0.000008376143,0.0000270853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9048689,"threshold_uncertainty_score":0.9958546,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W75140964","doi":"","title":"Agnostic KWIK learning and efficient approximate reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Simple (philosophy); Artificial intelligence; Algorithm; Theoretical computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03446888166875992,"gpt":0.247999907469349,"spread":0.2135310258005891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002137746,0.0005079146,0.0004441837,0.0003673394,0.0008935704,0.0003867545,0.0009923064,0.0001876343,0.0004618417],"category_scores_gemma":[0.001778601,0.0004852816,0.00011214,0.0003967939,0.000298376,0.0003218936,0.0008197119,0.001859389,0.0005078994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009725716,"about_ca_system_score_gemma":0.0001195574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001257768,"about_ca_topic_score_gemma":2.896284e-7,"domain_scores_codex":[0.9961591,0.0007645282,0.0005711328,0.0009290642,0.0006612925,0.0009148603],"domain_scores_gemma":[0.9976578,0.0007568022,0.0005013457,0.0005801079,0.0002041431,0.0002997851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006105223,0.00003428849,0.001532278,0.00004390314,0.00003994525,0.00002981481,0.005943616,0.6265475,0.0002945875,0.350251,0.00001019354,0.01521183],"study_design_scores_gemma":[0.0007592156,0.001352654,0.001037126,0.0003110425,0.00003470396,0.00003033787,0.001158852,0.9881581,0.0008118877,0.002992502,0.002625288,0.0007282777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01701988,0.00009492735,0.8758206,0.000076507,0.0003110179,0.0003280215,9.822605e-8,0.0008972455,0.1054517],"genre_scores_gemma":[0.981714,0.0001902386,0.005675476,0.0001280372,0.00005254315,0.00004115337,0.000008373858,0.00005470215,0.01213555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.964694,"threshold_uncertainty_score":0.9997599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1877234769","doi":"","title":"Open Problem: Recursive Teaching Dimension Versus VC Dimension","year":2015,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Concept class; Dimension (graph theory); Conjecture; Mathematics; Class (philosophy); VC dimension; Bounded function; Upper and lower bounds; Exponential function; Discrete mathematics; Function (biology); Combinatorics; Kolmogorov complexity; Algebra over a field; Pure mathematics; Computer science; Artificial intelligence; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.06272562214348579,"gpt":0.3247416508144249,"spread":0.2620160286709391,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003457816,0.0002912951,0.0003126099,0.0001519092,0.000540917,0.00062284,0.001892045,0.0001192952,0.00005753123],"category_scores_gemma":[0.001350283,0.0002473911,0.00006431404,0.0002137462,0.00008414831,0.0006434807,0.001462295,0.001343337,0.0006283189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003049,"about_ca_system_score_gemma":0.0002415538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008203436,"about_ca_topic_score_gemma":0.000002202207,"domain_scores_codex":[0.99661,0.001406264,0.0002611984,0.0007859244,0.0004701648,0.0004664875],"domain_scores_gemma":[0.9979714,0.0005576753,0.0002499337,0.0007169819,0.0002023342,0.000301718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002905737,0.00008613978,0.0001100727,0.000006425611,0.00002210403,0.00002982314,0.004219566,0.00393884,0.0002216039,0.8096939,0.001212322,0.1801686],"study_design_scores_gemma":[0.009279564,0.008050493,0.0005857079,0.001307894,0.00007032238,0.00007627461,0.003997988,0.4342583,0.001204508,0.4145547,0.124294,0.002320264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07354822,0.0002279805,0.4170951,0.006971203,0.00344498,0.001023285,0.000001715952,0.001605407,0.4960821],"genre_scores_gemma":[0.9520539,0.00001318172,0.03785367,0.0003294962,0.0001432355,0.00002693839,0.00001509524,0.00003563509,0.009528859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8785056,"threshold_uncertainty_score":0.9999979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966312692","doi":"","title":"Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Martingale (probability theory); Martingale difference sequence; Central limit theorem; Applied mathematics; Stochastic gradient descent; Rate of convergence; Multivariate random variable; Weak convergence; Mathematical analysis; Random variable; Statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05635044454367171,"gpt":0.3348542065146358,"spread":0.278503761970964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00211507,0.0001882598,0.0003563934,0.000104762,0.00008880832,0.00002559866,0.0001777562,0.00009182743,0.00010866],"category_scores_gemma":[0.001289536,0.0001645153,0.0001265175,0.00008129331,0.00006528571,0.00006267161,0.00005330564,0.000240134,0.000002937158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004373513,"about_ca_system_score_gemma":0.00005557476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002459884,"about_ca_topic_score_gemma":0.000001454462,"domain_scores_codex":[0.9986227,0.0002670644,0.0003618591,0.0002705721,0.0001837057,0.0002941112],"domain_scores_gemma":[0.9976437,0.00142475,0.0003507704,0.0003002552,0.0002099674,0.00007057019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001021464,0.0003940159,0.001335946,0.001512261,0.0001136376,0.000001325341,0.005416746,0.003198275,0.03304805,0.898644,0.0001656865,0.05514863],"study_design_scores_gemma":[0.004071291,0.003243958,0.001033364,0.001833092,0.0002452432,0.00001259604,0.005334501,0.6888132,0.03683381,0.2570305,0.0004389365,0.001109458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.422318,0.00001318737,0.5730914,0.00003130175,0.0001955787,0.0005926869,0.000002869436,0.00004116303,0.003713735],"genre_scores_gemma":[0.9816867,0.000002981856,0.01502221,0.00002737559,0.00004805639,0.00006639253,0.00001226075,0.00003456151,0.00309947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6856149,"threshold_uncertainty_score":0.670874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963004847","doi":"","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Thompson sampling; Asymptotically optimal algorithm; Index (typography); Frequentist inference; Gaussian; Mathematical optimization; Computer science; Mathematics; Mathematical economics; Bayesian probability; Statistics; Artificial intelligence; Bayesian inference","retraction":null,"screen_n_in":null,"score":{"opus":0.2738514103519363,"gpt":0.459272651460563,"spread":0.1854212411086267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005132541,0.0002143145,0.0005271848,0.0006949424,0.0003150851,0.0001221389,0.001501172,0.000152001,0.001444912],"category_scores_gemma":[0.03011402,0.0001028315,0.0003662045,0.00175835,0.0005965302,0.0002201828,0.0002208341,0.0003834568,0.0001047312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006367914,"about_ca_system_score_gemma":0.0002685223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006299238,"about_ca_topic_score_gemma":0.00003672866,"domain_scores_codex":[0.9958889,0.001059342,0.000620124,0.0006786544,0.001290598,0.0004623496],"domain_scores_gemma":[0.9856378,0.01171986,0.0005593101,0.0009901285,0.0009646298,0.0001282036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009838894,0.0001910095,0.02622584,0.00001150878,0.0005148713,0.000004701164,0.0008760566,0.04110095,0.003054271,0.05527896,0.0003487114,0.8714092],"study_design_scores_gemma":[0.005262834,0.002330934,0.2075582,0.0003654215,0.0004247942,0.000002146471,0.005722305,0.4752063,0.01167509,0.2747179,0.01569265,0.001041397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0753321,0.0000376748,0.9213135,0.0005330324,0.0002418849,0.0004441826,0.00009442045,0.0000554321,0.001947833],"genre_scores_gemma":[0.9746224,0.00002971656,0.0003780579,0.00002814808,0.00005332951,0.00004372451,0.000004959138,0.00002018449,0.02481949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9209354,"threshold_uncertainty_score":0.9994679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W593234165","doi":"","title":"The sample complexity of agnostic learning under deterministic labels","year":2014,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Dimension (graph theory); Computer science; Class (philosophy); Sample (material); Function (biology); Set (abstract data type); VC dimension; Binary number; Artificial intelligence; Probably approximately correct learning; Computational complexity theory; Machine learning; Theoretical computer science; Algorithm; Mathematics; Computational learning theory; Active learning (machine learning); Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.03920515464262433,"gpt":0.2815507529389313,"spread":0.2423455982963069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002371976,0.0002259691,0.0002900828,0.00008667936,0.0008604725,0.0002360333,0.001201739,0.00007541143,0.00008483312],"category_scores_gemma":[0.005421142,0.000165358,0.00009327046,0.0002306154,0.0005146993,0.0001019583,0.0002996634,0.0009447904,0.0001361708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002252871,"about_ca_system_score_gemma":0.00008706133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003538209,"about_ca_topic_score_gemma":0.000005210585,"domain_scores_codex":[0.9969442,0.001503088,0.0003223589,0.0004324303,0.0003642066,0.0004337011],"domain_scores_gemma":[0.9918431,0.006956576,0.0003166755,0.0006179154,0.0001522851,0.0001134605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001634552,0.00002578945,0.0005861174,0.00001301692,0.00001430117,0.00000131482,0.000448426,0.009181336,0.0001528226,0.8419113,0.00001369321,0.1476355],"study_design_scores_gemma":[0.0003790748,0.0007235692,0.006255157,0.0001314402,0.0000143523,0.000008807525,0.0002118629,0.5792019,0.0002161008,0.4048427,0.007705735,0.0003092789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02332056,0.00005227609,0.9605703,0.0009933242,0.0003478755,0.0001098448,0.000001077215,0.0003260371,0.0142787],"genre_scores_gemma":[0.9930641,0.00002724412,0.004524777,0.0001673232,0.00008228744,0.00001007108,0.000004738235,0.00001975776,0.002099682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9697435,"threshold_uncertainty_score":0.6743105,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2475351935","doi":"","title":"Learning and Testing Junta Distributions","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Hypercube; Uniform distribution (continuous); Distribution (mathematics); Mathematics; Boolean function; Property testing; Domain (mathematical analysis); Combinatorics; Discrete mathematics; Set (abstract data type); Algorithm; Computer science; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.02196962589253052,"gpt":0.2657186468250975,"spread":0.243749020932567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001005466,0.000187268,0.0001723677,0.0001000764,0.0005770712,0.000212932,0.0004271637,0.00006929474,0.0001068992],"category_scores_gemma":[0.002863462,0.0001304723,0.00003812685,0.0002404083,0.0001511892,0.0002350395,0.0002822755,0.000575199,0.0002284543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002929911,"about_ca_system_score_gemma":0.00006653871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006832454,"about_ca_topic_score_gemma":4.002559e-7,"domain_scores_codex":[0.9983093,0.0004588893,0.0001727397,0.0004950803,0.0001917956,0.0003722615],"domain_scores_gemma":[0.9979833,0.001370297,0.0001295059,0.0002636305,0.0001097772,0.0001434632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005909716,0.00001390124,0.005983036,0.000004635628,0.000007148381,0.000008051718,0.0002249384,0.00004571738,0.001786798,0.4179159,0.00002214906,0.5739818],"study_design_scores_gemma":[0.003976902,0.004356097,0.07113781,0.002452641,0.00006828224,0.000357962,0.001120269,0.3338037,0.004069071,0.444439,0.1309714,0.003246917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05432954,0.00006510798,0.9112205,0.002320646,0.0002064458,0.00008345559,0.000001704793,0.0008906107,0.03088198],"genre_scores_gemma":[0.983311,0.00003726901,0.006369432,0.00005805353,0.00008843831,0.0000100486,0.000002184201,0.00001440145,0.0101092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9289814,"threshold_uncertainty_score":0.5320507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3046684513","doi":"","title":"Locally Private Hypothesis Selection","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Differential privacy; Combinatorics; Mathematics; Omega; Distribution (mathematics); Discrete mathematics; Generalization; Probability distribution; Upper and lower bounds; Algorithm; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.05567489988836302,"gpt":0.2571248751803857,"spread":0.2014499752920227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005821042,0.0001909628,0.0001888265,0.00009777068,0.0001943444,0.0002200824,0.01351407,0.0001310298,0.0001602958],"category_scores_gemma":[0.03656526,0.0001816337,0.00005039018,0.0005135627,0.0001221098,0.0003874458,0.01503007,0.0007232766,0.0006238702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004736357,"about_ca_system_score_gemma":0.00008849005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001632078,"about_ca_topic_score_gemma":2.794075e-7,"domain_scores_codex":[0.9982672,0.0002837836,0.0001918194,0.0006369924,0.0002738706,0.000346389],"domain_scores_gemma":[0.9970633,0.0004491807,0.0001346491,0.00216259,0.0000784626,0.0001118324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006900795,0.00003752438,0.0005787959,0.00002331036,0.00003264147,0.00001866565,0.0002600806,0.0002954581,0.006704641,0.6248569,0.01100885,0.3561141],"study_design_scores_gemma":[0.0002329842,0.0004159299,0.0007568116,0.000062906,0.000006334486,0.000006787865,0.00005686601,0.3110891,0.01089482,0.6673673,0.008775335,0.000334807],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01102953,0.00002703904,0.9429362,0.03313541,0.0001158803,0.000133427,0.000001591595,0.00263926,0.009981676],"genre_scores_gemma":[0.8950283,0.00005178348,0.1034307,0.001208013,0.00005296162,0.00001591518,0.000002000002,0.00001965168,0.0001906289],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8839988,"threshold_uncertainty_score":0.9929362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963800416","doi":"","title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematical proof; Markov decision process; Contraction (grammar); Property (philosophy); Computer science; Mathematics; Applied mathematics; Mathematical optimization; Measure (data warehouse); Class (philosophy); Markov process; Linear model; Artificial intelligence; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0519210604033747,"gpt":0.2934808180844667,"spread":0.2415597576810921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001142309,0.000488501,0.0004210988,0.0004212109,0.0006062806,0.0002851833,0.001322302,0.0001858497,0.00005324014],"category_scores_gemma":[0.000841715,0.0003359763,0.0001595655,0.000343381,0.0002588,0.0007365947,0.000225782,0.0005869868,0.00009424819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000254692,"about_ca_system_score_gemma":0.000971865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006981543,"about_ca_topic_score_gemma":9.065002e-7,"domain_scores_codex":[0.9968311,0.0002727876,0.0004710183,0.0008239722,0.0006782445,0.0009228412],"domain_scores_gemma":[0.9971045,0.0008285419,0.0004532508,0.0009167666,0.0004344889,0.0002624787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001882144,0.00001522198,0.00005302452,0.00001908062,0.00002695886,0.000001817935,0.0004753046,0.5985681,0.0004307534,0.3939979,0.00001575175,0.00620784],"study_design_scores_gemma":[0.001732922,0.001571581,0.00001634388,0.0003082883,0.00001817777,0.000002317413,0.00008121869,0.9720318,0.0009719233,0.0215121,0.001205578,0.0005477313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001689734,0.000007153967,0.9836047,0.001360416,0.0001097897,0.0005198233,0.000001538199,0.0007161811,0.01199061],"genre_scores_gemma":[0.9415168,0.00001674277,0.03160009,0.0004449525,0.00009973693,0.0001236095,0.00001570402,0.00007344195,0.02610897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9520047,"threshold_uncertainty_score":0.9999092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153773643","doi":"","title":"Sample Compression for Multi-label Concept Classes","year":2014,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Dimension (graph theory); Sample (material); Compression (physics); VC dimension; Class (philosophy); Mathematics; Extension (predicate logic); Binary number; Sample size determination; Data compression; Computer science; Artificial intelligence; Algorithm; Combinatorics; Arithmetic; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05949915847716699,"gpt":0.3286035096503646,"spread":0.2691043511731976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009713296,0.000212466,0.0002517618,0.00009057247,0.0004413685,0.0002219701,0.000845856,0.00009570292,0.0000834905],"category_scores_gemma":[0.001808359,0.0001787824,0.00007171061,0.0001208813,0.0001077408,0.0001695706,0.000176622,0.0004893184,0.00009550877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001816938,"about_ca_system_score_gemma":0.00005505389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001339414,"about_ca_topic_score_gemma":7.831521e-7,"domain_scores_codex":[0.9981645,0.0005359022,0.0002011173,0.000520967,0.0002037812,0.0003737124],"domain_scores_gemma":[0.9972623,0.001853107,0.0001653702,0.0004555558,0.0001384051,0.0001252516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001797275,0.0000569643,0.0001586872,0.00001038434,0.000007162917,4.725518e-7,0.0005128024,0.000810493,0.0003681126,0.6062626,0.0001849073,0.3916094],"study_design_scores_gemma":[0.001002179,0.0004672225,0.0003741981,0.00009156323,0.0000052559,0.000001963055,0.00007886252,0.9411732,0.0005139721,0.02911435,0.02692065,0.0002565891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002065435,0.00004269485,0.9929924,0.0005139163,0.0004318283,0.0001643992,0.000003170916,0.0004935473,0.003292593],"genre_scores_gemma":[0.749171,0.00001017972,0.2450985,0.0005377235,0.0001892369,0.0000407511,0.00002193383,0.00002652963,0.004904129],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9403627,"threshold_uncertainty_score":0.7290536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1956860503","doi":"","title":"Learnability of Solutions to Conjunctive Queries: The Full Dichotomy","year":2015,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Learnability; Property (philosophy); Theoretical computer science; Computer science; Conjunctive query; Mathematics; Discrete mathematics; Space (punctuation); Artificial intelligence; Algebra over a field; Relational database; Pure mathematics; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.0490561778058568,"gpt":0.2872785683180127,"spread":0.2382223905121559,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002887926,0.0001715753,0.0002278376,0.000096009,0.0002922862,0.0001080122,0.00102216,0.00006113586,0.00008708685],"category_scores_gemma":[0.002712515,0.0001189054,0.00007680151,0.0003903164,0.000276358,0.0001602187,0.0003794674,0.0006611217,0.0002496452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005204059,"about_ca_system_score_gemma":0.0002949102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006652935,"about_ca_topic_score_gemma":0.000005756354,"domain_scores_codex":[0.9976866,0.0009786251,0.0002332174,0.0004043425,0.000364002,0.0003332113],"domain_scores_gemma":[0.9979053,0.0006579405,0.0001552059,0.0007088979,0.0003772845,0.0001953663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001045162,0.00007317875,0.0005990961,0.000008027703,0.00002392784,0.000002799533,0.009787045,0.007399037,0.0002933156,0.9187286,0.0004949641,0.06248549],"study_design_scores_gemma":[0.002175077,0.006243512,0.0131211,0.0003729557,0.00005736579,0.00004820184,0.01512684,0.2973451,0.001383453,0.5075107,0.1551638,0.00145183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05022876,0.00006770452,0.8961589,0.005178922,0.0004875848,0.0003038899,0.00000230734,0.0003155429,0.04725642],"genre_scores_gemma":[0.9934605,0.000004460808,0.002927142,0.0002876998,0.00006830008,0.00003328498,0.000001623824,0.00001079586,0.003206155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9432318,"threshold_uncertainty_score":0.4848822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174935984","doi":"","title":"Size and Depth Separation in Approximating Natural Functions with Neural Networks","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Lipschitz continuity; Bounded function; Mathematics; Function (biology); Polynomial; Artificial neural network; Constant (computer programming); Computational complexity theory; Discrete mathematics; Algorithm; Computer science; Pure mathematics; Artificial intelligence; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01089248834608676,"gpt":0.2541372997461577,"spread":0.243244811400071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004989504,0.000136684,0.0001515238,0.00005453868,0.0002222714,0.0002627035,0.0001668095,0.00004868591,0.00002571237],"category_scores_gemma":[0.0003897195,0.0001138237,0.00002196557,0.0003103898,0.00005263436,0.0002325097,0.0001020229,0.0008013946,0.000006990187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000168586,"about_ca_system_score_gemma":0.00005531553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007296311,"about_ca_topic_score_gemma":0.00002047951,"domain_scores_codex":[0.9986739,0.0004232595,0.0001462752,0.0003846579,0.0001398876,0.0002319785],"domain_scores_gemma":[0.9990638,0.0005121085,0.00008802529,0.0002097114,0.00007192884,0.00005445827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007786448,0.00007214249,0.01439118,0.00002524894,0.00002440907,0.0001052626,0.002625241,0.2248852,0.0004379823,0.2230602,0.00001760054,0.5342777],"study_design_scores_gemma":[0.0003216217,0.0001172219,0.01482996,0.00006627056,0.00000369704,0.00005040039,0.0003600048,0.9822786,0.00002672965,0.001684407,0.0001026151,0.0001584535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2083793,0.0002236874,0.7813597,0.0007269239,0.0002419886,0.00008929834,1.650335e-7,0.0002356432,0.008743345],"genre_scores_gemma":[0.9895741,0.000008715325,0.007648611,0.0001745315,0.00005855224,0.0000106271,0.000005811704,0.000009315093,0.002509732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7811949,"threshold_uncertainty_score":0.4641596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174263485","doi":"","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Randomness; Intuition; Computer science; Mathematical economics; Mathematical optimization; Fictitious play; Mathematics; Game theory; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1626154911242037,"gpt":0.4264370049582369,"spread":0.2638215138340332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002272641,0.0002745413,0.0004223906,0.0002196037,0.000801171,0.0004665267,0.0006521441,0.0001324946,0.001445497],"category_scores_gemma":[0.009764556,0.0001901895,0.00005132662,0.0006781371,0.0008184698,0.0002846546,0.0003726801,0.0009979575,0.0003259573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006731567,"about_ca_system_score_gemma":0.0004030881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007704017,"about_ca_topic_score_gemma":0.00005466572,"domain_scores_codex":[0.9957889,0.001689111,0.0003940951,0.0007850388,0.0009274557,0.0004153894],"domain_scores_gemma":[0.992115,0.005055907,0.0002323253,0.0009085574,0.001454778,0.0002334359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003524124,0.00139379,0.005852679,0.00002606818,0.0003434855,0.0003423078,0.02663151,0.7613249,0.006077575,0.06926664,0.0006268469,0.1245901],"study_design_scores_gemma":[0.006472008,0.00108325,0.01878445,0.0004850189,0.00004972678,0.0001069215,0.0342658,0.9262654,0.002385345,0.006503107,0.002637378,0.0009616342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1200905,0.0003077664,0.876941,0.000800645,0.00007278096,0.0004373982,0.00003685238,0.00008756394,0.001225471],"genre_scores_gemma":[0.9584697,0.00007075501,0.01947684,0.0001105353,0.00002644101,0.00006686257,0.00002513696,0.00003700025,0.0217167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8574642,"threshold_uncertainty_score":0.9994673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173288964","doi":"","title":"Nonparametric Regression with Shallow Overparametrized Neural Networks Trained by GD with Early Stopping","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Early stopping; Lipschitz continuity; Artificial neural network; Nonparametric statistics; Noise (video); Kernel (algebra); Nonparametric regression; Kernel regression; Computer science; Regression; Mathematics; Stochastic gradient descent; Gradient descent; Artificial intelligence; Algorithm; Pattern recognition (psychology); Statistics; Discrete mathematics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01753391270644775,"gpt":0.24806449918661,"spread":0.2305305864801622,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008708282,0.0003284532,0.0003598724,0.000237038,0.0003838833,0.0006157196,0.0007636517,0.0001388056,0.00008391469],"category_scores_gemma":[0.0007311957,0.0002351858,0.00006063877,0.001502589,0.0001291265,0.0004750299,0.000149258,0.001175735,0.00002785183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005226528,"about_ca_system_score_gemma":0.0001619349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000168873,"about_ca_topic_score_gemma":0.000004592549,"domain_scores_codex":[0.9969475,0.0008826277,0.0002569839,0.0009101014,0.0005222466,0.000480576],"domain_scores_gemma":[0.9974723,0.0009067745,0.0003183759,0.0008838845,0.0002273926,0.0001913131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001596922,0.0004550542,0.0239183,0.00006141607,0.0001713341,0.0002871182,0.002025887,0.05412488,0.003165381,0.2470435,0.0004542684,0.6666959],"study_design_scores_gemma":[0.001643965,0.00110587,0.01355592,0.0003169813,0.00002868756,0.00006177541,0.0002298655,0.9796097,0.0002294216,0.0008236279,0.001820351,0.0005738006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1371818,0.0002386319,0.8562986,0.0009319772,0.0001119347,0.0001542431,0.000001944588,0.0004234339,0.004657353],"genre_scores_gemma":[0.9886162,0.00004860498,0.007759444,0.0002958882,0.00004737004,0.00002359949,0.00007957862,0.00003217488,0.003097118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254848,"threshold_uncertainty_score":0.9590598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964762712","doi":"","title":"On Mean Estimation for General Norms with Statistical Queries.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Normed vector space; Combinatorics; Distribution (mathematics); Mathematics; Oracle; Norm (philosophy); Space (punctuation); Upper and lower bounds; Discrete mathematics; Computer science; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01814144913091369,"gpt":0.2612117571156775,"spread":0.2430703079847638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004507915,0.0001484277,0.0001633994,0.00008456104,0.0001718549,0.0001625376,0.0004199895,0.00004701655,0.0001778381],"category_scores_gemma":[0.0001407664,0.0001143447,0.00003491777,0.0001165095,0.0001030324,0.0001721204,0.00006229209,0.000270363,0.0001717277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002748537,"about_ca_system_score_gemma":0.0000845219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005341674,"about_ca_topic_score_gemma":0.000003037019,"domain_scores_codex":[0.9989041,0.000111564,0.0001257439,0.000383489,0.0002284129,0.0002466594],"domain_scores_gemma":[0.9987463,0.0006600954,0.00007757813,0.0003599318,0.00008644527,0.00006970174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001112483,0.00003052417,0.00005611416,0.00001259568,0.000009304445,0.00000206256,0.0004238945,0.004311434,0.00004007486,0.8995537,0.00004648549,0.09540257],"study_design_scores_gemma":[0.0004097889,0.001172094,0.0007109682,0.00006245098,0.000003699501,0.0000036643,0.00005291459,0.537434,0.0001733551,0.4591208,0.0006741246,0.0001820919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0423775,0.000004035401,0.9482459,0.0002180282,0.0002007012,0.0002244319,0.000004616492,0.0001653415,0.008559431],"genre_scores_gemma":[0.8694807,0.000002078384,0.1278616,0.0002779233,0.00003390852,0.00002926502,0.00001986316,0.00001313817,0.002281529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8271031,"threshold_uncertainty_score":0.466284,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174325474","doi":"","title":"Asymptotically Optimal Information-Directed Sampling","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Asymptotically optimal algorithm; Frequentist inference; Regret; Thompson sampling; Mathematical optimization; Computer science; Simple (philosophy); Connection (principal bundle); Upper and lower bounds; Sampling (signal processing); Mathematics; Bayesian probability; Artificial intelligence; Bayesian inference; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1378188340422346,"gpt":0.4246927229571403,"spread":0.2868738889149057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003535838,0.0001770798,0.0002916734,0.0002989151,0.0003925462,0.000753348,0.0007080177,0.0001212416,0.005717715],"category_scores_gemma":[0.04445883,0.0001445589,0.0001011901,0.0008911118,0.0002181188,0.0007590629,0.0002976987,0.0008656105,0.00445378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004742933,"about_ca_system_score_gemma":0.0004966563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001033938,"about_ca_topic_score_gemma":0.000001221201,"domain_scores_codex":[0.9962031,0.0007660618,0.0005478999,0.0004444576,0.001581782,0.0004566854],"domain_scores_gemma":[0.9920865,0.005150874,0.0001872555,0.0006041747,0.001766604,0.0002045546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003742001,0.0001149743,0.00212176,0.00001541993,0.00005835012,0.00007218361,0.002539765,0.07477687,0.00086287,0.3694445,0.000778159,0.548841],"study_design_scores_gemma":[0.001951731,0.0006025491,0.02188001,0.0002689899,0.00002342661,0.00009581733,0.01358185,0.2656358,0.005231222,0.5396683,0.1498576,0.001202724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0322926,0.00005506676,0.9059206,0.001078521,0.0003631761,0.0001412194,0.000008208945,0.0003524457,0.0597881],"genre_scores_gemma":[0.9637124,0.00004085891,0.01899452,0.0003511684,0.0001155011,0.00001857178,0.00003576205,0.00002001913,0.01671119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9314198,"threshold_uncertainty_score":0.9963214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176194860","doi":"","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Statistical Mechanics and Entropy","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Convergence (economics); Stochastic gradient descent; Applied mathematics; Mathematics; Criticality; Rate of convergence; Limit (mathematics); Statistical physics; Mathematical optimization; Computer science; Mathematical analysis; Physics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01944880602390112,"gpt":0.2931511756311167,"spread":0.2737023696072156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007356182,0.0001095171,0.0001919364,0.00003817493,0.0001544124,0.0001307087,0.00008916233,0.00003117898,0.002485776],"category_scores_gemma":[0.0002922751,0.00008311019,0.00006303906,0.0002035265,0.00005058536,0.00003017141,0.00005742674,0.000406191,0.00003090746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007499367,"about_ca_system_score_gemma":0.00003700671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001788713,"about_ca_topic_score_gemma":0.000004377133,"domain_scores_codex":[0.9987053,0.0005345894,0.0001527807,0.00025226,0.000117779,0.0002372424],"domain_scores_gemma":[0.9987094,0.0009072955,0.00003378918,0.0002141164,0.00006965501,0.00006573159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001428022,0.00009517917,0.006431082,0.000005372154,0.00007167155,0.0001642276,0.0004074274,0.00006163056,0.00001459437,0.9845695,0.00002303736,0.008141951],"study_design_scores_gemma":[0.0009846438,0.0001004978,0.02015467,0.00005097824,0.0003580396,0.00002381733,0.01237568,0.1057127,0.0001042446,0.8574991,0.002263579,0.0003720711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3181401,0.00006564686,0.6567939,0.001027475,0.0001020107,0.0001170554,0.00006473385,0.00002535072,0.02366372],"genre_scores_gemma":[0.9988331,0.00000717738,0.0002559923,0.0002301521,0.00005208779,0.000008111019,0.00002977123,0.000006878025,0.0005767459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.680693,"threshold_uncertainty_score":0.9984261,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174799275","doi":"","title":"Learning and testing junta distributions with sub cube conditioning","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Conditioning; Combinatorics; Distribution (mathematics); Mathematics; Logarithm; Bhattacharyya distance; Probability distribution; Discrete mathematics; Algorithm; Computer science; Statistics; Artificial intelligence; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01607629887651031,"gpt":0.2527456540907559,"spread":0.2366693552142456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007277988,0.0002215117,0.0002257246,0.00008941378,0.0009823433,0.0005236788,0.0002774822,0.00007492203,0.00009167589],"category_scores_gemma":[0.002175063,0.0002004043,0.00003628408,0.0004950068,0.0001612471,0.0002622583,0.0002354446,0.001197057,0.0000616066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002978286,"about_ca_system_score_gemma":0.0002376238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000823212,"about_ca_topic_score_gemma":0.000001994898,"domain_scores_codex":[0.9979824,0.000590692,0.0001849918,0.0006038086,0.000250323,0.0003877275],"domain_scores_gemma":[0.9982083,0.0009534204,0.0001519909,0.0002758334,0.000249617,0.0001608526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001967809,0.00006426429,0.0172335,0.00003484018,0.00003748751,0.0002022677,0.001228949,0.003984567,0.004067417,0.7620209,0.00003733786,0.2110688],"study_design_scores_gemma":[0.003435181,0.00327109,0.05106119,0.002516087,0.0001347694,0.00173879,0.004742176,0.7820376,0.02031051,0.1072294,0.02056802,0.002955259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2227045,0.0001678518,0.7491863,0.001107465,0.0001552829,0.00009488367,0.000002967663,0.0008151003,0.02576558],"genre_scores_gemma":[0.9859344,0.00002902891,0.01065943,0.0001309761,0.0000725207,0.00001371486,0.00003577271,0.00001880894,0.003105314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.778053,"threshold_uncertainty_score":0.8172251,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175841314","doi":"","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture MDPs","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Mathematics; Minimax; Logarithm; Estimator; Bounded function; Combinatorics; Discrete mathematics; Regret; Mathematical optimization; Markov process; Computer science; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1281220911290732,"gpt":0.423888662028909,"spread":0.2957665708998357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005012404,0.0003266715,0.0005150852,0.0003043687,0.0007814612,0.0005602275,0.0009640079,0.0002190779,0.003917007],"category_scores_gemma":[0.02804554,0.0002704098,0.0002631378,0.000725395,0.0002924948,0.0003775758,0.000385049,0.001400835,0.001219223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009700968,"about_ca_system_score_gemma":0.0005536968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002503219,"about_ca_topic_score_gemma":0.000001937233,"domain_scores_codex":[0.9947803,0.0009532981,0.000679712,0.001069474,0.001713616,0.0008036008],"domain_scores_gemma":[0.9916461,0.00530716,0.0003388671,0.0007551978,0.001674466,0.0002782703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001229067,0.0001244989,0.0003676342,0.00003343076,0.00009495215,0.0001468932,0.003442448,0.6244938,0.004454202,0.05522158,0.002233653,0.3081579],"study_design_scores_gemma":[0.002226338,0.001866974,0.0005547047,0.0002004954,0.00003248378,0.00003954548,0.01101002,0.5287054,0.01386114,0.05144144,0.3891751,0.0008863292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02360537,0.0002567903,0.9585086,0.001306941,0.0004704106,0.0004419152,0.000006517675,0.0001922457,0.0152112],"genre_scores_gemma":[0.7834133,0.00008969069,0.01105389,0.0002424352,0.0003878102,0.00009086706,0.000060687,0.00006121117,0.2046001],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9474548,"threshold_uncertainty_score":0.9999748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196848038","doi":"","title":"Open Problem: Are all VC-classes CPAC learnable?","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04229467534172605,"gpt":0.3155514981952951,"spread":0.2732568228535691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001100909,0.0002515676,0.0003119454,0.0001105328,0.0002828669,0.001490017,0.002786493,0.0001461072,0.0003710939],"category_scores_gemma":[0.0009534322,0.0002233708,0.00006640005,0.0004174875,0.0000951793,0.000852284,0.001775691,0.0009154516,0.0002196908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006831022,"about_ca_system_score_gemma":0.0003962498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001625908,"about_ca_topic_score_gemma":0.000009768925,"domain_scores_codex":[0.9976355,0.0005757588,0.0002369073,0.0007768332,0.0003271626,0.0004477687],"domain_scores_gemma":[0.9981326,0.0003112081,0.0002566329,0.0007959001,0.0003746386,0.000129042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002166449,0.00006832316,0.0001822934,0.00004006079,0.00002312829,0.0001791471,0.0006379247,0.0000523561,0.00350311,0.9110241,0.001188028,0.08307987],"study_design_scores_gemma":[0.0004101206,0.0002448703,0.0001820798,0.000853327,0.00001741382,0.00008661383,0.0005871481,0.003892583,0.03276923,0.9123869,0.04788559,0.0006841127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004155093,0.003949798,0.7529562,0.01309044,0.0004613626,0.0006775483,0.00000368845,0.00332875,0.2213771],"genre_scores_gemma":[0.7480673,0.000166729,0.2166769,0.001941028,0.00007138734,0.00006145641,0.00001312322,0.00004113528,0.03296097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7439122,"threshold_uncertainty_score":0.9995465,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175907392","doi":"","title":"On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Monte Carlo method; Smoothness; Lipschitz continuity; Rate of convergence; Physics; Combinatorics; BETA (programming language); Convex function; Distribution (mathematics); Mathematics; Regular polygon; Mathematical analysis; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.06749056405776141,"gpt":0.3460512910546785,"spread":0.2785607269969171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022161,0.0001741058,0.0002998108,0.00003460348,0.0001686197,0.00004612802,0.0003159696,0.00008299633,0.0001635069],"category_scores_gemma":[0.004775897,0.00009722161,0.0000834925,0.0001191934,0.0002649256,0.00003113018,0.0001566939,0.0005371508,8.369356e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001311834,"about_ca_system_score_gemma":0.00006512149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001534639,"about_ca_topic_score_gemma":0.00001062658,"domain_scores_codex":[0.9977325,0.001376483,0.0002335696,0.0002525774,0.0002109264,0.0001939393],"domain_scores_gemma":[0.9928843,0.006288538,0.0001802512,0.0004404575,0.0001543285,0.00005215336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005867048,0.00002659867,0.001655739,0.00008452454,0.00006340718,0.000008183723,0.003477806,0.000005453263,0.0009866132,0.9852289,0.0004054202,0.007998696],"study_design_scores_gemma":[0.001884579,0.001266838,0.006460828,0.003116296,0.0005088099,0.00003645274,0.04703264,0.004169766,0.06220546,0.8616377,0.01025069,0.001429924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574653,0.0002106928,0.007620903,0.001686807,0.0001785271,0.0002080825,0.00001369225,0.00005081562,0.03256521],"genre_scores_gemma":[0.9950996,0.0001166624,0.0002989604,0.0002284081,0.0000537985,0.00001967493,0.000001788348,0.00002242062,0.00415871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1235912,"threshold_uncertainty_score":0.5717539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}