{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":436,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":436,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"a2addb5837d6","filters":{"topic":"Advanced Bandit Algorithms Research"}},"results":[{"id":"W2192203593","doi":"10.1109/jproc.2015.2494218","title":"Taking the Human Out of the Loop: A Review of Bayesian Optimization","year":2015,"lang":"en","type":"review","venue":"Proceedings of the IEEE","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5868,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Bayesian optimization; Loop (graph theory); Bayesian probability; Human-in-the-loop; Computer science; Artificial intelligence; Mathematics","authors":[{"name":"Bobak Shahriari","is_ca":true},{"name":"Kevin Swersky","is_ca":false},{"name":"Ziyu Wang","is_ca":false},{"name":"Ryan P. Adams","is_ca":false},{"name":"Nando de Freitas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2723421006942705,"gpt":0.4942171047619189,"spread":0.2218750040676484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002967358,0.001261882,0.001942474,0.002567687,0.0005110762,0.002180117,0.00167849,0.002072366,0.003535488],"category_scores_gemma":[0.007534511,0.0006432518,0.0008398872,0.004857996,0.001746293,0.00268935,0.0009331733,0.002082363,0.001867485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001730642,"about_ca_system_score_gemma":0.003297863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005024743,"about_ca_topic_score_gemma":0.005790241,"domain_scores_codex":[0.9987852,0.0004425001,0.0001239195,0.0001805149,0.0004145407,0.00005326462],"domain_scores_gemma":[0.9946561,0.00419041,0.0002357587,0.0001089386,0.000711973,0.00009681055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005894478,0.00009953,0.0006638317,0.01271232,0.0001766701,0.0001049832,0.0001473682,0.008060265,0.0003140194,0.09130342,0.03700556,0.8493531],"study_design_scores_gemma":[0.00003114086,0.0001498794,0.001619144,0.01185276,0.0002398957,0.0006263572,0.0002276969,0.006925553,0.0006901898,0.1154576,0.8620602,0.0001194136],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002337059,0.9822565,0.01080326,0.002335164,0.0002547638,0.000009733281,0.00003359842,0.00001992009,0.004053332],"genre_scores_gemma":[0.004164895,0.988736,0.005193294,0.00051817,0.0005973272,0.0000196829,0.00004214359,0.00001403222,0.0007145717],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005024743,"threshold_uncertainty_score":0.01569307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119738618","doi":"","title":"Improved Algorithms for Linear Stochastic Bandits","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":916,"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; Logarithm; Computer science; Constant (computer programming); Simple (philosophy); Algorithm; Mathematical optimization; Multi-armed bandit; Mathematics; Machine learning","authors":[{"name":"Yasin Abbasi-Yadkori","is_ca":true},{"name":"Dávid Pál","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3179026584292263,"gpt":0.4621502314159748,"spread":0.1442475729867485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008746492,0.002299319,0.002995717,0.002032754,0.0009861181,0.003264652,0.004659482,0.003298637,0.008169985],"category_scores_gemma":[0.04489249,0.001170912,0.001900964,0.002924328,0.002438478,0.005900263,0.004277546,0.006200713,0.003284171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002812113,"about_ca_system_score_gemma":0.002999307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003043824,"about_ca_topic_score_gemma":0.002925608,"domain_scores_codex":[0.9920875,0.003554884,0.0004014049,0.001103707,0.002134805,0.000717635],"domain_scores_gemma":[0.9774994,0.01567248,0.001422823,0.002937819,0.001998257,0.0004692464],"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":[0.0004438064,0.0002952042,0.001232905,0.0003538644,0.0001571091,0.0001126171,0.0002191129,0.5721544,0.002765167,0.2561734,0.009038774,0.1570536],"study_design_scores_gemma":[0.00003933125,0.00003787705,0.0001130125,0.00002958227,0.0000139385,0.00003229071,0.000006844414,0.9459243,0.0005808895,0.05186597,0.001342466,0.0000134817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00468228,0.0006533609,0.9902884,0.0004119279,0.00009552488,0.0000800382,0.000101554,0.0007733071,0.0029136],"genre_scores_gemma":[0.2585602,0.001282696,0.7272025,0.001005207,0.0006581399,0.0006956131,0.0007621157,0.0008566319,0.008976917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008746492,"threshold_uncertainty_score":0.04625642,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206530644","doi":"10.1017/9781108571401","title":"Bandit Algorithms","year":2020,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":851,"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":"Computer science; Markov decision process; Intuition; Mathematical proof; Bayesian probability; Thompson sampling; Artificial intelligence; Focus (optics); Machine learning; Operations research; Markov process; Management science; Mathematical optimization; Mathematics; Engineering","authors":[{"name":"Tor Lattimore","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1148289934412215,"gpt":0.330816909380413,"spread":0.2159879159391914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00237404,0.002028273,0.002544644,0.001326196,0.001219177,0.004599835,0.002734886,0.002845929,0.02660274],"category_scores_gemma":[0.01250982,0.0007751642,0.001316275,0.00270307,0.001527657,0.003189528,0.002703371,0.00341242,0.011547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001766057,"about_ca_system_score_gemma":0.001823009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00268368,"about_ca_topic_score_gemma":0.002809577,"domain_scores_codex":[0.9978431,0.000880294,0.0001354788,0.0004009207,0.0005304456,0.000209685],"domain_scores_gemma":[0.995665,0.003020458,0.0002306295,0.0005434608,0.0004289734,0.0001114773],"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":[0.0001656871,0.000130587,0.0006630686,0.0004299123,0.0001824412,0.00008686222,0.0001206394,0.2127413,0.0006515872,0.425747,0.04053511,0.3185458],"study_design_scores_gemma":[0.00005611701,0.00005667646,0.0001780738,0.0001882982,0.00004929845,0.0001078681,0.00004729583,0.5465144,0.0005025584,0.4187463,0.03352221,0.00003102887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003189385,0.006442642,0.936176,0.001613355,0.0005806654,0.0001671609,0.000487539,0.001035741,0.05030755],"genre_scores_gemma":[0.2023543,0.01442132,0.6748054,0.002450048,0.001267659,0.001253412,0.002198085,0.001134496,0.1001153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02660274,"threshold_uncertainty_score":0.08899504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1931877416","doi":"10.1184/r1/6550949","title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":846,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Multidisciplinary University Research Initiative","keywords":"Regret; Computer science; Benchmark (surveying); Artificial intelligence; Imitation; Online learning; Reduction (mathematics); Machine learning; Sequence (biology); Iterative learning control; Online machine learning; Convergence (economics); Mathematical optimization; Active learning (machine learning); Mathematics; Economics; Psychology","authors":[{"name":"Stéphane Ross","is_ca":false},{"name":"Geoffrey J. Gordon","is_ca":false},{"name":"J. Andrew Bagnell","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1356271737258775,"gpt":0.3110003567384468,"spread":0.1753731830125693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002931319,0.001367687,0.00193232,0.000632973,0.0005669019,0.001064072,0.002934896,0.002079901,0.00244464],"category_scores_gemma":[0.01589996,0.0007369491,0.001039364,0.0007185147,0.002182313,0.002346724,0.002802889,0.003679124,0.0006362479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001367724,"about_ca_system_score_gemma":0.00188769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002323702,"about_ca_topic_score_gemma":0.001771048,"domain_scores_codex":[0.9976894,0.0009253963,0.00008111751,0.0005142363,0.0006217405,0.000168072],"domain_scores_gemma":[0.9933974,0.005004345,0.0003969873,0.0006606079,0.0003367552,0.0002038774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001251149,0.0001738742,0.000651872,0.0001451807,0.00007401779,0.0001220534,0.0001323818,0.813426,0.001304635,0.1132639,0.002845851,0.06773507],"study_design_scores_gemma":[0.00001177922,0.00004040041,0.0000675025,0.000007808499,0.000005565972,0.00002388833,0.000004055294,0.9664181,0.0003595644,0.03254486,0.0005103293,0.000006139363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00525936,0.0001684598,0.9916065,0.0002916976,0.00004475705,0.00005826696,0.00002541655,0.000269988,0.002275534],"genre_scores_gemma":[0.553184,0.0003842257,0.4371679,0.0005073092,0.0003375725,0.0005328431,0.0002730712,0.0003226741,0.007290335],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002934896,"threshold_uncertainty_score":0.01550245,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073384958","doi":"10.1007/978-3-031-01551-9","title":"Algorithms for Reinforcement Learning","year":2010,"lang":"en","type":"book","venue":"Synthesis lectures on artificial intelligence and machine learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":750,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Learning classifier system; Hyper-heuristic; Instance-based learning; Active learning (machine learning); Term (time); Unsupervised learning; Core (optical fiber); Robot learning; Robot","authors":[{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1604075222470484,"gpt":0.4127314576545998,"spread":0.2523239354075514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000523601,0.001322646,0.001110132,0.0005523246,0.0004457257,0.001485027,0.001113923,0.001164806,0.02105755],"category_scores_gemma":[0.002201933,0.0004421466,0.0005456653,0.0009108802,0.0009849702,0.001681204,0.001075604,0.002461988,0.006246857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009265375,"about_ca_system_score_gemma":0.0005173201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001292076,"about_ca_topic_score_gemma":0.001412686,"domain_scores_codex":[0.9996834,0.000083503,0.00001548262,0.00007871607,0.0001115687,0.00002733831],"domain_scores_gemma":[0.9995756,0.0002282543,0.00001960386,0.0000903739,0.00006854667,0.00001767255],"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":[0.00004085949,0.0000548857,0.0001756495,0.0001424175,0.00004752535,0.0000453638,0.00006346054,0.147449,0.000719836,0.3975665,0.04332735,0.4103672],"study_design_scores_gemma":[0.0000294695,0.00002252364,0.0001195374,0.00005496201,0.00001612069,0.00005780324,0.00001809724,0.42947,0.0006275054,0.520232,0.04933888,0.00001313114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001586803,0.003964288,0.9395554,0.0006565573,0.0006556123,0.00004091419,0.0001163267,0.001006599,0.05241738],"genre_scores_gemma":[0.2061871,0.005526741,0.6102038,0.0007931858,0.001227043,0.0006069793,0.0008349484,0.0009225525,0.1736977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02105755,"threshold_uncertainty_score":0.07044452,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142971854","doi":"10.1016/j.tcs.2009.01.016","title":"Exploration–exploitation tradeoff using variance estimates in multi-armed bandits","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":566,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Variance (accounting); Stochastic game; Upper and lower bounds; Logarithm; Mathematical optimization; Computer science; Multi-armed bandit; Interval (graph theory); Mathematics; Mathematical economics; Machine learning; Economics","authors":[{"name":"Jean-Yves Audibert","is_ca":false},{"name":"Rémi Munos","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2025090972907981,"gpt":0.4631392662511002,"spread":0.2606301689603022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01741206,0.001801049,0.003292357,0.001939547,0.001008865,0.004078803,0.00246353,0.004149533,0.002009197],"category_scores_gemma":[0.08031216,0.001942511,0.001007089,0.001705955,0.002668021,0.006750336,0.003856997,0.003234298,0.0004377603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378395,"about_ca_system_score_gemma":0.001663079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001100996,"about_ca_topic_score_gemma":0.0008045105,"domain_scores_codex":[0.9900691,0.007260599,0.0004701544,0.0006379086,0.001006346,0.0005558263],"domain_scores_gemma":[0.9136565,0.07833941,0.002657933,0.00258174,0.002190966,0.0005735562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005399436,0.00009468298,0.00171695,0.0002333121,0.0002439849,0.00007355642,0.0001621639,0.8388136,0.001278294,0.111198,0.0009046881,0.04474088],"study_design_scores_gemma":[0.0000448597,0.0000698111,0.0002316226,0.00003990339,0.00002981559,0.00003173484,0.00001833976,0.9476445,0.0004835272,0.05120246,0.0001807996,0.00002271905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03525495,0.001214849,0.959457,0.0008320826,0.00005525736,0.0000427771,0.00005216048,0.000178787,0.002912093],"genre_scores_gemma":[0.8497404,0.0009737169,0.1452886,0.000284409,0.0002174992,0.0003045098,0.0001220478,0.0002014138,0.002867379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01741206,"threshold_uncertainty_score":0.09208488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160163723","doi":"","title":"Parametric Bandits: The Generalized Linear Case","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":261,"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; Parameterized complexity; Generalized linear model; Parametric statistics; Computer science; Mathematical optimization; Linear model; Applied mathematics; Mathematics; Algorithm; Machine learning; Statistics","authors":[{"name":"Sarah Filippi","is_ca":false},{"name":"Olivier Cappé","is_ca":false},{"name":"Aurélien Garivier","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1076079387823779,"gpt":0.4263062865630172,"spread":0.3186983477806393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004796262,0.001375101,0.002314568,0.000966577,0.0007434839,0.003075278,0.002419904,0.00298553,0.003788901],"category_scores_gemma":[0.02690956,0.0007497104,0.001091223,0.001786333,0.002917579,0.004336558,0.002557728,0.003919819,0.0007395204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001358666,"about_ca_system_score_gemma":0.0009697663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002793439,"about_ca_topic_score_gemma":0.002219034,"domain_scores_codex":[0.9964722,0.002164506,0.0001014215,0.0005368181,0.0003780416,0.0003469819],"domain_scores_gemma":[0.9866454,0.009924301,0.001724435,0.001047793,0.0003924641,0.0002656093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009152276,0.00006761034,0.0008007946,0.0001004922,0.00007614135,0.0003103268,0.0001117949,0.753856,0.0003980112,0.2226601,0.001387056,0.02014021],"study_design_scores_gemma":[0.0000157395,0.00002467084,0.0001114829,0.00001317716,0.000009080822,0.00005095188,0.00002360749,0.9104796,0.000113674,0.0886912,0.0004545712,0.00001219739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03773119,0.0009692831,0.9541205,0.001410819,0.00006093159,0.00008029519,0.0001475637,0.0002199762,0.005259498],"genre_scores_gemma":[0.8931358,0.001010096,0.09912643,0.0005110618,0.0002034904,0.0002823549,0.0001407428,0.00008648523,0.005503578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004796262,"threshold_uncertainty_score":0.02536541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W53582479","doi":"","title":"Regret Bounds for the Adaptive Control of Linear Quadratic Systems","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":213,"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; Logarithm; Mathematical optimization; Set (abstract data type); Upper and lower bounds; Quadratic equation; Mathematics; Control (management); Computer science; Control theory (sociology); Artificial intelligence; Statistics","authors":[{"name":"Yasin Abbasi-Yadkori","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3701429153791539,"gpt":0.4472209630766811,"spread":0.07707804769752713,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006223999,0.002396354,0.001513216,0.0009329995,0.0008851725,0.002120143,0.001625557,0.001692309,0.003532653],"category_scores_gemma":[0.03278783,0.0004974154,0.0009714391,0.001052651,0.002836154,0.002780412,0.002674602,0.003946481,0.0006041747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002177451,"about_ca_system_score_gemma":0.001336038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002248909,"about_ca_topic_score_gemma":0.001113548,"domain_scores_codex":[0.9970715,0.001240365,0.00009718142,0.0003754386,0.0008737957,0.0003416665],"domain_scores_gemma":[0.9752907,0.02091259,0.001152196,0.0007967445,0.001449068,0.0003986655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002247526,0.00006016467,0.0006526296,0.0002587005,0.00007278224,0.0000741876,0.000104097,0.8723424,0.001229037,0.09986562,0.002335878,0.02277979],"study_design_scores_gemma":[0.00001163407,0.00004231839,0.0001323519,0.00002728203,0.00001092349,0.00001525023,0.000008515063,0.9632583,0.0003204503,0.03575386,0.0004118598,0.000007220262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009631106,0.001948194,0.9809704,0.0008153509,0.0001093863,0.00004141013,0.0000673018,0.0002132942,0.006203474],"genre_scores_gemma":[0.8464805,0.003199201,0.1408727,0.0008235305,0.0007091725,0.0004690141,0.0003971138,0.0003802813,0.006668543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006223999,"threshold_uncertainty_score":0.03291607,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160367301","doi":"10.1145/1566374.1566412","title":"A unified framework for dynamic pari-mutuel information market design","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Mathematical optimization; Computer science; Function (biology); Logarithm; Popularity; Convex optimization; Mechanism design; Simple (philosophy); Regular polygon; Minification; Mathematical economics; Economics; Mathematics","authors":[{"name":"Shipra Agrawal","is_ca":false},{"name":"Erick Delage","is_ca":true},{"name":"Mark Peters","is_ca":false},{"name":"Zizhuo Wang","is_ca":false},{"name":"Yinyu Ye","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1202788275421259,"gpt":0.4558329411854775,"spread":0.3355541136433516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005783459,0.001394412,0.001502236,0.001242538,0.0008537011,0.003394227,0.003140367,0.002160599,0.007143293],"category_scores_gemma":[0.007833187,0.0008027393,0.001256987,0.001318397,0.002576042,0.0053193,0.002577791,0.00362331,0.001144894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001935912,"about_ca_system_score_gemma":0.002478814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008465125,"about_ca_topic_score_gemma":0.001006749,"domain_scores_codex":[0.997481,0.001214109,0.0001124036,0.0003088651,0.0006758804,0.0002077668],"domain_scores_gemma":[0.9978557,0.0009698897,0.0002622583,0.0003561932,0.0003985374,0.0001573303],"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":[0.00001496948,0.00002938372,0.00006377677,0.00003215417,0.00001282297,0.00004059968,0.00003253406,0.07278082,0.0003864825,0.9157636,0.000946796,0.009896081],"study_design_scores_gemma":[0.00002433913,0.0000466433,0.00004319679,0.00001712635,0.00000931402,0.00004236694,0.00001472102,0.4676294,0.0002841972,0.5279047,0.003968151,0.00001568202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001272287,0.0001174736,0.9949192,0.0002889335,0.00002095148,0.00003976514,0.00003599322,0.00003707431,0.003268378],"genre_scores_gemma":[0.3220578,0.001386229,0.6625615,0.0004318824,0.0003704408,0.0009255136,0.0002151724,0.0001268542,0.01192458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007143293,"threshold_uncertainty_score":0.03058618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1917528016","doi":"","title":"Contextual Multi-Armed Bandits","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Regret; Stochastic game; Multi-armed bandit; Context (archaeology); Metric space; Metric (unit); Computer science; Space (punctuation); Lipschitz continuity; Action (physics); Mathematics; Thompson sampling; Function (biology); Theoretical computer science; Mathematical optimization; Combinatorics; Discrete mathematics; Mathematical economics; Machine learning","authors":[{"name":"Tyler Lu","is_ca":true},{"name":"Dávid Pál","is_ca":true},{"name":"Martin Pál","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2128862204345478,"gpt":0.5039623446227086,"spread":0.2910761241881608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004043092,0.002874101,0.00411194,0.001001208,0.0008940903,0.003124847,0.002599478,0.003549905,0.00499654],"category_scores_gemma":[0.01791564,0.001250066,0.001445401,0.001489424,0.002327514,0.003655832,0.002702119,0.003669628,0.001090113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185789,"about_ca_system_score_gemma":0.001237818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004075886,"about_ca_topic_score_gemma":0.003937348,"domain_scores_codex":[0.996253,0.001801887,0.0001738286,0.0008987352,0.0004207453,0.0004516354],"domain_scores_gemma":[0.9856469,0.01100053,0.001524853,0.0007587839,0.0005427259,0.0005261911],"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":[0.0004506129,0.0001539501,0.001342839,0.0002772719,0.0001491485,0.0001519984,0.00008571783,0.9167882,0.0005399465,0.06296613,0.002144656,0.01494963],"study_design_scores_gemma":[0.00003307086,0.00006225899,0.0001281324,0.00002670605,0.00002029145,0.00001656197,0.00001309289,0.9772296,0.0001283587,0.02181174,0.0005194857,0.00001086111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06995278,0.006140204,0.9068397,0.002240302,0.0003125595,0.0002665212,0.0008018083,0.001032833,0.0124134],"genre_scores_gemma":[0.8961424,0.001797979,0.0923494,0.0008404812,0.000470331,0.0004366832,0.0007244437,0.0001217503,0.00711659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00499654,"threshold_uncertainty_score":0.02138215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2193897973","doi":"10.1109/mwc.2016.7498076","title":"Multi-armed bandits with application to 5G small cells","year":2016,"lang":"en","type":"article","venue":"IEEE Wireless Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Selfishness; Cellular network; Wireless; Resource allocation; Wireless network; Distributed computing; Computer network; Next-generation network; Resource (disambiguation); Small cell; Mobile computing; Telecommunications; The Internet; World Wide Web","authors":[{"name":"Setareh Maghsudi","is_ca":true},{"name":"Ekram Hossain","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1564926192755867,"gpt":0.4209362025593321,"spread":0.2644435832837454,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001259214,0.001093763,0.001021141,0.000490322,0.0005591609,0.001561456,0.000678119,0.001714193,0.003638985],"category_scores_gemma":[0.004882861,0.0003006705,0.0005712509,0.0009778109,0.001105492,0.0008749532,0.0009880851,0.001924529,0.0004379135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103131,"about_ca_system_score_gemma":0.0005948951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003574114,"about_ca_topic_score_gemma":0.002647175,"domain_scores_codex":[0.9994752,0.0003118902,0.00001717157,0.00004504437,0.00007854686,0.00007228172],"domain_scores_gemma":[0.9975968,0.00187288,0.000201231,0.00005882868,0.000187517,0.00008267196],"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":[0.00009368896,0.00005044639,0.0007082959,0.0001282253,0.00004639692,0.0001957559,0.00008766383,0.8070167,0.0006745097,0.1702498,0.002567405,0.01818122],"study_design_scores_gemma":[0.00001063671,0.00003260431,0.0001047826,0.0000193136,0.000009601431,0.00002508404,0.00002507404,0.9653009,0.0001186882,0.03281875,0.001527713,0.00000685143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03306862,0.00755549,0.9330885,0.002185282,0.0003378612,0.00007458657,0.0001160851,0.0001512335,0.02342243],"genre_scores_gemma":[0.9064641,0.006958277,0.06974643,0.0005242592,0.0004731983,0.0002116349,0.0001187535,0.00004898716,0.01545433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003638985,"threshold_uncertainty_score":0.01217359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963110737","doi":"","title":"Portfolio allocation for Bayesian optimization","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":124,"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":"Bayesian optimization; Computer science; Bayesian probability; Gaussian process; Machine learning; Portfolio; Function (biology); Parameterized complexity; Mathematical optimization; Portfolio optimization; Artificial intelligence; Gaussian; Algorithm; Mathematics","authors":[{"name":"Matthew D. Hoffman","is_ca":true},{"name":"Eric Brochu","is_ca":true},{"name":"Nando de Freitas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2496469089177329,"gpt":0.4408040778022478,"spread":0.1911571688845149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005782521,0.002200402,0.002752897,0.001229691,0.0008575896,0.002719453,0.001790914,0.003067315,0.009673085],"category_scores_gemma":[0.02035212,0.00105293,0.001179031,0.002028276,0.001951796,0.003016354,0.002933116,0.003536758,0.001939417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002289889,"about_ca_system_score_gemma":0.002024622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002665006,"about_ca_topic_score_gemma":0.001851318,"domain_scores_codex":[0.9962491,0.002445769,0.0001287018,0.0003835335,0.0005851381,0.0002076543],"domain_scores_gemma":[0.9939229,0.004820882,0.0003216933,0.0003221323,0.0004603024,0.0001520459],"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":[0.00009109772,0.00008062211,0.0005055281,0.0002635953,0.0001237731,0.00006471092,0.00007034883,0.5121517,0.0004354696,0.408732,0.005631474,0.07184963],"study_design_scores_gemma":[0.00002590356,0.00002594126,0.0001085284,0.0000497193,0.00001620612,0.00002613363,0.000008403248,0.7755895,0.0001847906,0.2207345,0.003216978,0.00001338575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001893502,0.001247584,0.9908394,0.0004571909,0.00005828411,0.00005178386,0.0000512973,0.0001147243,0.00528619],"genre_scores_gemma":[0.3135795,0.006027003,0.6603411,0.0009683505,0.0006668183,0.001253596,0.000542348,0.0003650732,0.01625621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009673085,"threshold_uncertainty_score":0.03235972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987292194","doi":"10.1287/moor.2014.0663","title":"Partial Monitoring—Classification, Regret Bounds, and Algorithms","year":2014,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":123,"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; Logarithm; Minimax; Mathematics; Outcome (game theory); Action (physics); Mathematical optimization; Mathematical economics; Statistics; Psychology","authors":[{"name":"Gábor Bartók","is_ca":false},{"name":"Dean P. Foster","is_ca":false},{"name":"Dávid Pál","is_ca":false},{"name":"Alexander Rakhlin","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4399227455027039,"gpt":0.5509132329952277,"spread":0.1109904874925237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01144437,0.002626846,0.003425036,0.001593988,0.001433202,0.004851421,0.004305751,0.003217822,0.004965133],"category_scores_gemma":[0.05788539,0.001160502,0.001654604,0.002680063,0.004002137,0.009273909,0.004386414,0.006341457,0.0009465159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004487347,"about_ca_system_score_gemma":0.002555125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002241248,"about_ca_topic_score_gemma":0.001667708,"domain_scores_codex":[0.9913235,0.003989917,0.0003719211,0.001624162,0.001770831,0.0009197365],"domain_scores_gemma":[0.9554811,0.03509465,0.003069885,0.003795486,0.001488003,0.001070839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005835444,0.0003523251,0.003884411,0.0004577454,0.000198518,0.00009932669,0.0002214512,0.5541915,0.001001572,0.322349,0.01039577,0.1062649],"study_design_scores_gemma":[0.0000329094,0.00006994815,0.0003950181,0.0000537208,0.00002469091,0.00005182118,0.00001835097,0.7526504,0.0003491156,0.245223,0.001114662,0.00001638289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02582207,0.005017256,0.9523138,0.003723375,0.0001844925,0.0001641444,0.0004506696,0.0006333352,0.01169079],"genre_scores_gemma":[0.6856772,0.005026856,0.2909489,0.001717209,0.001498941,0.001140311,0.001206586,0.0004835647,0.01230048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01144437,"threshold_uncertainty_score":0.06052428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103581319","doi":"","title":"Online Optimization in X-Armed Bandits","year":2008,"lang":"en","type":"article","venue":"RePEc: Research Papers in Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":122,"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":"Mathematics; Stochastic game; Regret; Mathematical optimization; Bounded function; Lipschitz continuity; Euclidean space; Function (biology); Combinatorics; Hypercube; Dimension (graph theory); Discrete mathematics; Mathematical economics; Pure mathematics; Mathematical analysis","authors":[{"name":"Sébastien Bubeck","is_ca":false},{"name":"Rémi Munos","is_ca":false},{"name":"Gilles Stoltz","is_ca":true},{"name":"Csaba Szepesvári","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1316744920066128,"gpt":0.431294036276807,"spread":0.2996195442701942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005467576,0.001486341,0.00269045,0.0006625784,0.000656341,0.003096433,0.001353212,0.002743809,0.004495615],"category_scores_gemma":[0.01708871,0.001022811,0.0009644313,0.001175013,0.002791026,0.003202803,0.001879146,0.00256441,0.000593962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001676318,"about_ca_system_score_gemma":0.0008686681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002197474,"about_ca_topic_score_gemma":0.001523355,"domain_scores_codex":[0.997005,0.001980805,0.0001401362,0.0003951426,0.0002349586,0.0002439083],"domain_scores_gemma":[0.9835128,0.01435328,0.001100705,0.0004339838,0.00033251,0.0002667014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002071458,0.00005579844,0.000667663,0.0001473591,0.00007876951,0.00009927891,0.00008959211,0.8252283,0.0003983639,0.1615392,0.0008011849,0.01068725],"study_design_scores_gemma":[0.00003906639,0.00003556591,0.0001027266,0.00002592627,0.000009091176,0.00001033106,0.00001722696,0.9095952,0.0001293247,0.08962586,0.0003997196,0.000009983617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05454898,0.001759601,0.9311532,0.001355744,0.00009291145,0.00007444352,0.0001322174,0.0002406137,0.0106423],"genre_scores_gemma":[0.9145412,0.001281628,0.07071834,0.0004248476,0.0002191628,0.0004720428,0.0001718667,0.0001118369,0.01205912],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005467576,"threshold_uncertainty_score":0.02891564,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964007796","doi":"","title":"{Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":122,"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; Stochastic game; Upper and lower bounds; Combinatorics; Mathematics; Constant (computer programming); Combinatorial optimization; Discrete mathematics; Mathematical optimization; Computer science; Mathematical economics","authors":[{"name":"Branislav Kveton","is_ca":false},{"name":"Zheng Wen","is_ca":false},{"name":"Azin Ashkan","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2749472121146019,"gpt":0.4837384434734039,"spread":0.208791231358802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009540077,0.00456734,0.004106344,0.002197482,0.002536799,0.006383576,0.005043263,0.003927981,0.01298903],"category_scores_gemma":[0.04832378,0.001774244,0.002575816,0.00367975,0.005823462,0.009620172,0.006080936,0.009687247,0.003379777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005708992,"about_ca_system_score_gemma":0.003560702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002842087,"about_ca_topic_score_gemma":0.00319392,"domain_scores_codex":[0.9919903,0.003348846,0.0003231246,0.001184438,0.001900203,0.00125311],"domain_scores_gemma":[0.9654019,0.02652139,0.001886202,0.003144485,0.001777515,0.001268475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001298868,0.0006103542,0.002057911,0.000901163,0.0002493796,0.0002349162,0.0002956161,0.6143597,0.002856811,0.3023814,0.01973652,0.05501743],"study_design_scores_gemma":[0.00005666449,0.00009401536,0.000304802,0.000136456,0.0000374086,0.0000791679,0.00004632785,0.8345243,0.0008208686,0.1619931,0.001883946,0.0000228215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0323622,0.004578339,0.9213657,0.004112655,0.0003418189,0.0003373802,0.001369073,0.001458434,0.03407437],"genre_scores_gemma":[0.7233104,0.005314615,0.2438423,0.003914214,0.001171249,0.001897943,0.002675794,0.001724919,0.01614844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01298903,"threshold_uncertainty_score":0.05045336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963582321","doi":"","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":103,"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; Reinforcement learning; Computer science; Bridge (graph theory); State (computer science); Mathematical optimization; Algorithm; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Christoph Dann","is_ca":false},{"name":"Tor Lattimore","is_ca":true},{"name":"Emma Brunskill","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1348757675199226,"gpt":0.4272213443219531,"spread":0.2923455768020305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01294393,0.002299588,0.0024161,0.001442923,0.001011621,0.004188729,0.003220331,0.002530761,0.003264911],"category_scores_gemma":[0.08591015,0.0009516589,0.001255024,0.001388084,0.00545291,0.01021006,0.004247387,0.005985639,0.0004688753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003091693,"about_ca_system_score_gemma":0.002774602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002032767,"about_ca_topic_score_gemma":0.001396243,"domain_scores_codex":[0.9904659,0.003769127,0.0004711986,0.00161483,0.002811109,0.0008678396],"domain_scores_gemma":[0.9264156,0.05962985,0.00407852,0.005861727,0.00291434,0.001099981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002116735,0.0001109223,0.001386446,0.0002055274,0.0001124877,0.00009542967,0.000139257,0.6219187,0.0009638459,0.3346011,0.001608242,0.03864648],"study_design_scores_gemma":[0.00001390119,0.00008531291,0.0003079187,0.00005590195,0.00001972351,0.00004476952,0.00001783077,0.8218678,0.00108898,0.1757448,0.0007338598,0.00001929725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007185695,0.0008937417,0.9867079,0.0004496643,0.00007076332,0.00004638979,0.00006451534,0.0002299015,0.004351404],"genre_scores_gemma":[0.7538124,0.001631089,0.2392943,0.0008435114,0.0005349756,0.0004809819,0.0002589545,0.0004568239,0.00268703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01294393,"threshold_uncertainty_score":0.0684548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000850397","doi":"10.1109/tac.2013.2292137","title":"Online Markov Decision Processes Under Bandit Feedback","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"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; Markov decision process; Markov chain; State (computer science); Computer science; Markov process; Function (biology); Mathematical economics; Discrete mathematics; Combinatorics; Mathematical optimization; Mathematics; Artificial intelligence; Algorithm; Machine learning; Statistics; Psychology","authors":[{"name":"Gergely Neu","is_ca":false},{"name":"András György","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true},{"name":"András Antos","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04329478899436651,"gpt":0.3667983632348631,"spread":0.3235035742404966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004397803,0.00190747,0.00277837,0.0008937691,0.001040906,0.002715235,0.001928173,0.003183634,0.004407706],"category_scores_gemma":[0.01779657,0.001039889,0.0009970801,0.001320215,0.002756916,0.003490251,0.002438064,0.003358298,0.0008395383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003941219,"about_ca_system_score_gemma":0.002285632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01091907,"about_ca_topic_score_gemma":0.006695867,"domain_scores_codex":[0.9967272,0.001263439,0.000118306,0.0006525886,0.0004548281,0.0007835754],"domain_scores_gemma":[0.982404,0.01397566,0.001636015,0.0005467908,0.0007030012,0.0007345224],"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":[0.0003541121,0.0001027392,0.0008616457,0.0001098055,0.00005170634,0.0002383124,0.0001082417,0.8623846,0.0003596117,0.1268949,0.001400076,0.007134311],"study_design_scores_gemma":[0.00003176618,0.00002254175,0.00008265184,0.000008102666,0.000007741083,0.00001402501,0.00000776558,0.9598926,0.00008974151,0.0396424,0.0001924286,0.000008260498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228584,0.002057088,0.8580876,0.003381191,0.0002157423,0.0001473744,0.0006287743,0.0009229982,0.01170077],"genre_scores_gemma":[0.9591931,0.0009523226,0.02889504,0.00040305,0.0002016841,0.0002656374,0.00031108,0.00009605486,0.009681872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01091907,"threshold_uncertainty_score":0.02859569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156211713","doi":"10.1287/moor.1090.0397","title":"Markov Decision Processes with Arbitrary Reward Processes","year":2009,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Regret; Hindsight bias; Reinforcement learning; Mathematical optimization; Mathematics; Q-learning; Markov process; Realization (probability); Function (biology); Trajectory; Markov chain; Process (computing); Computer science; Artificial intelligence","authors":[{"name":"Jia Yuan Yu","is_ca":true},{"name":"Shie Mannor","is_ca":true},{"name":"Nahum Shimkin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.205043330395209,"gpt":0.5069362652545172,"spread":0.3018929348593081,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003637383,0.001621886,0.00203265,0.0006343289,0.0008739592,0.002313668,0.002828449,0.003166989,0.003607593],"category_scores_gemma":[0.01320907,0.0007958619,0.001187256,0.001074193,0.002702849,0.003141533,0.001995221,0.003448496,0.0006649224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037786,"about_ca_system_score_gemma":0.001622648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005793126,"about_ca_topic_score_gemma":0.003610947,"domain_scores_codex":[0.9971005,0.001156378,0.0001116188,0.0007027158,0.0003938816,0.0005347928],"domain_scores_gemma":[0.9923379,0.005422144,0.0009176061,0.0005052942,0.0003689965,0.0004481119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001892638,0.0001048275,0.0009082179,0.00006004055,0.00005464649,0.0003183068,0.0000916631,0.7284779,0.0005521195,0.2625099,0.0006348015,0.00609842],"study_design_scores_gemma":[0.00004260061,0.00002976945,0.00007822416,0.000005410485,0.00001090739,0.00001737089,0.00000825331,0.9334944,0.0001798146,0.06578854,0.0003328132,0.00001173107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07089176,0.0003431204,0.920385,0.001506747,0.0001054802,0.0001167682,0.0002498372,0.0002135221,0.006187846],"genre_scores_gemma":[0.9053814,0.0005168088,0.08349757,0.0002303442,0.0001621045,0.0003366682,0.0002438345,0.00003944586,0.009591855],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005793126,"threshold_uncertainty_score":0.01923656,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964072175","doi":"10.14288/1.0044651","title":"Online learning under delayed feedback","year":2015,"lang":"en","type":"article","venue":"Open Collections","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":98,"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; Computer science; Online learning; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Multimedia","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.2615616721285479,"gpt":0.4801871304299516,"spread":0.2186254583014037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002851072,0.001095385,0.001439335,0.0004804369,0.0004936462,0.001549078,0.001369619,0.001666501,0.001952905],"category_scores_gemma":[0.01728046,0.0004428048,0.0004736886,0.0006349812,0.001550764,0.002487736,0.001438605,0.002047843,0.0003438327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001904469,"about_ca_system_score_gemma":0.00136327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001635288,"about_ca_topic_score_gemma":0.00104948,"domain_scores_codex":[0.9983501,0.0006396045,0.00007026507,0.0003667228,0.000313738,0.0002595758],"domain_scores_gemma":[0.9896495,0.008020634,0.0008192835,0.000595984,0.000604357,0.0003101197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003484336,0.00007997084,0.0005944065,0.0002208837,0.00005694367,0.00009542183,0.00006039538,0.8727888,0.001398167,0.09774462,0.001691498,0.0249204],"study_design_scores_gemma":[0.00004051899,0.0000666117,0.00008984261,0.00001826674,0.00001395136,0.00002357293,0.000007385056,0.9454207,0.0006466676,0.05318409,0.0004812438,0.000007095653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05209151,0.001592718,0.9404638,0.0009728308,0.0001509231,0.00005948878,0.0001464279,0.0003915255,0.004130785],"genre_scores_gemma":[0.9507481,0.0009133728,0.04358191,0.0002771584,0.0001834405,0.0001508169,0.00009779445,0.0000655221,0.003981859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002851072,"threshold_uncertainty_score":0.01507807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157016390","doi":"","title":"Online Markov Decision Processes under Bandit Feedback","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":97,"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; Markov decision process; Computer science; Markov process; State (computer science); Markov chain; Mathematical optimization; Online learning; Reinforcement learning; Adversary; Function (biology); Action (physics); Artificial intelligence; Mathematics; Algorithm; Machine learning","authors":[{"name":"Gergely Neu","is_ca":false},{"name":"András Antos","is_ca":false},{"name":"András György","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08846169459235069,"gpt":0.4450109408182472,"spread":0.3565492462258965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005270173,0.001357324,0.002608962,0.0008460726,0.001053839,0.002496416,0.001560786,0.002503314,0.004531298],"category_scores_gemma":[0.01990811,0.00083786,0.0007849715,0.001101158,0.002874091,0.002767249,0.002007205,0.002782475,0.0006980966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003331646,"about_ca_system_score_gemma":0.00164178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009546356,"about_ca_topic_score_gemma":0.005395324,"domain_scores_codex":[0.9969409,0.001393981,0.0001214936,0.0005448079,0.0003733161,0.0006255726],"domain_scores_gemma":[0.9782282,0.0171166,0.002261235,0.000668951,0.0009330076,0.0007919405],"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":[0.0003509131,0.00009438556,0.001217469,0.00007194692,0.00004932843,0.0002103478,0.0001057972,0.8608178,0.00036792,0.1307816,0.001034717,0.004897768],"study_design_scores_gemma":[0.00002735916,0.00001819691,0.00009603863,0.000009112238,0.000006748399,0.00001152188,0.000008856048,0.969237,0.0001058857,0.03035391,0.0001178143,0.000007515199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2090917,0.0009927668,0.7764356,0.002874156,0.0001496875,0.0001598002,0.0005195177,0.0005569358,0.009219809],"genre_scores_gemma":[0.9780146,0.0003472011,0.01567182,0.000225461,0.00008952453,0.0001968936,0.0001698783,0.00004351152,0.005241133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009546356,"threshold_uncertainty_score":0.02787167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161571887","doi":"10.1145/1553374.1553524","title":"Piecewise-stationary bandit problems with side observations","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Israel Science Foundation; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Regret; Piecewise; Baseline (sea); Mathematics; Piecewise linear function; Contrast (vision); Adversarial system; Distribution (mathematics); Computer science; Mathematical optimization; Artificial intelligence; Statistics; Mathematical analysis","authors":[{"name":"Jia Yuan Yu","is_ca":true},{"name":"Shie Mannor","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2241001579878948,"gpt":0.4240967083286237,"spread":0.1999965503407289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003214831,0.001592875,0.002669506,0.0006127923,0.0007070387,0.001812933,0.002372097,0.002881935,0.00450966],"category_scores_gemma":[0.0112284,0.000965749,0.001037949,0.001582754,0.001503662,0.00315174,0.00178428,0.003533601,0.0009411909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314895,"about_ca_system_score_gemma":0.001020892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002871885,"about_ca_topic_score_gemma":0.001702254,"domain_scores_codex":[0.9986379,0.0005737803,0.00007577104,0.0003316026,0.0001606708,0.0002202719],"domain_scores_gemma":[0.9896399,0.008080059,0.001167415,0.0004879439,0.0002473749,0.0003773236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006364397,0.0001201348,0.0009556047,0.0001576024,0.00009059777,0.000240299,0.00009367694,0.9267729,0.0008139276,0.04149261,0.001647927,0.02697835],"study_design_scores_gemma":[0.00004297071,0.00007288507,0.0001419681,0.00001354326,0.00001739779,0.00003996569,0.00001663903,0.9668846,0.0002703282,0.0321991,0.0002901111,0.00001049931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07267887,0.001006234,0.9211646,0.001253673,0.0000792776,0.0001080124,0.0003828691,0.0005200697,0.00280624],"genre_scores_gemma":[0.8647495,0.0009564731,0.12388,0.0003394552,0.0002082215,0.0003193715,0.000650094,0.0001100671,0.008786843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00450966,"threshold_uncertainty_score":0.01700187,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146412174","doi":"","title":"Optimal Bayesian Recommendation Sets and Myopically Optimal Choice Query Sets","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":85,"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":"Computer science; Submodular set function; Query optimization; Mathematical optimization; Set (abstract data type); Multinomial logistic regression; Greedy algorithm; Bayesian probability; Data mining; Algorithm; Machine learning; Artificial intelligence; Mathematics","authors":[{"name":"Paolo Viappiani","is_ca":true},{"name":"Craig Boutilier","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05953119479209398,"gpt":0.4010226266591596,"spread":0.3414914318670657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01786613,0.001567151,0.003755096,0.001926425,0.001241074,0.003467971,0.003129067,0.003661112,0.006483722],"category_scores_gemma":[0.07282828,0.001531624,0.001635575,0.002804098,0.00307438,0.007548738,0.003988513,0.003626079,0.001063686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003816084,"about_ca_system_score_gemma":0.002448062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002719689,"about_ca_topic_score_gemma":0.002723962,"domain_scores_codex":[0.9781187,0.01442005,0.000984942,0.002203534,0.003309565,0.0009631806],"domain_scores_gemma":[0.9381009,0.05201623,0.002558867,0.004058634,0.002211311,0.001053967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007112981,0.0003782245,0.00143177,0.0002894708,0.0002095782,0.0001443,0.0004543796,0.6066837,0.001181271,0.3232082,0.003817308,0.06149047],"study_design_scores_gemma":[0.00009438153,0.0001147086,0.0003331934,0.00004136327,0.00002509372,0.00004267514,0.00006852757,0.7912338,0.0007047048,0.2063505,0.0009546475,0.00003643764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05013814,0.0006230703,0.9390168,0.001473228,0.00002608127,0.0003205754,0.0004904186,0.0003388848,0.007572813],"genre_scores_gemma":[0.6596367,0.0006551821,0.3317707,0.0005854169,0.0001005506,0.001123427,0.0008597422,0.0002061283,0.005062092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01786613,"threshold_uncertainty_score":0.0944863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170307371","doi":"","title":"On correlation and budget constraints in model-based bandit optimization with application to automatic machine learning","year":2014,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":84,"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":"Frequentist inference; Bayesian optimization; Computer science; Machine learning; Bayesian probability; Artificial intelligence; Constraint (computer-aided design); Feature (linguistics); Function (biology); Mathematical optimization; Bayesian inference; Mathematics","authors":[{"name":"Matthew D. Hoffman","is_ca":false},{"name":"Bobak Shahriari","is_ca":true},{"name":"Nando de Freitas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.100663809997761,"gpt":0.4084052332996377,"spread":0.3077414233018767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01258978,0.001871037,0.003283414,0.001245615,0.001063086,0.002910195,0.001951497,0.002683786,0.0031896],"category_scores_gemma":[0.0478168,0.001658477,0.001154536,0.002468247,0.002825283,0.004776639,0.0029524,0.003264846,0.0005186292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002441917,"about_ca_system_score_gemma":0.003459275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00769961,"about_ca_topic_score_gemma":0.005589286,"domain_scores_codex":[0.9943281,0.004127205,0.0001795834,0.0003612915,0.0006885232,0.0003152719],"domain_scores_gemma":[0.9677492,0.02836379,0.001769658,0.000922508,0.0008928834,0.0003019053],"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":[0.0000637394,0.00003502236,0.0002828123,0.0000772104,0.00003900244,0.00004635853,0.00006248183,0.9014193,0.0002117823,0.08611374,0.0007518136,0.01089662],"study_design_scores_gemma":[0.000009216778,0.00001404231,0.00005504857,0.00002189401,0.000006086471,0.000009310244,0.000006818202,0.9684592,0.00009840572,0.03103287,0.0002779002,0.000009125981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007337685,0.0006491969,0.9889731,0.0005743331,0.00003121223,0.00003784584,0.00004369155,0.0001244671,0.002228393],"genre_scores_gemma":[0.6324829,0.002475647,0.3567643,0.000776708,0.000333898,0.0008702309,0.0002905663,0.0003961169,0.005609708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01258978,"threshold_uncertainty_score":0.0665819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952908320","doi":"","title":"Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations","year":2012,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Institute for Computing, Information and Cognitive Systems","keywords":"Regret; Mathematics; Complement (music); Exponential function; Dimension (graph theory); Gaussian; Combinatorics; Function (biology); Constant (computer programming); Gaussian process; Space (punctuation); Exponential family; Discrete mathematics; Applied mathematics; Mathematical analysis; Statistics; Computer science; Physics","authors":[{"name":"Nando de Freitas","is_ca":true},{"name":"Alex Smola","is_ca":false},{"name":"Masrour Zoghi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1870917374975287,"gpt":0.3866931792783039,"spread":0.1996014417807752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01506853,0.002722263,0.002912836,0.002005511,0.001822224,0.00371148,0.003234386,0.002792062,0.004569695],"category_scores_gemma":[0.07016343,0.001276706,0.001698345,0.002560572,0.004971283,0.007310618,0.004495109,0.006228617,0.0009444454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004814098,"about_ca_system_score_gemma":0.00235508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003224212,"about_ca_topic_score_gemma":0.002464138,"domain_scores_codex":[0.9948044,0.002254411,0.0001722264,0.0007359271,0.001210187,0.0008228288],"domain_scores_gemma":[0.9400284,0.05109711,0.002829038,0.002917286,0.00216804,0.0009602146],"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":[0.0006230156,0.0001579395,0.002054987,0.000346751,0.0001991233,0.0001949054,0.0002094898,0.6880626,0.001303826,0.2795323,0.004852164,0.02246295],"study_design_scores_gemma":[0.00004140024,0.00005447644,0.0004001889,0.00008016879,0.00003765866,0.00005519008,0.00002467676,0.8838313,0.0004846019,0.1141352,0.0008333934,0.00002168786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04335701,0.008060028,0.9288399,0.003440864,0.0002705702,0.0001120991,0.0003727955,0.0006469121,0.01489974],"genre_scores_gemma":[0.8417225,0.007828468,0.1319301,0.002108127,0.001240288,0.0008620789,0.0009111362,0.0007060308,0.01269125],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01506853,"threshold_uncertainty_score":0.07969093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2602868127","doi":"10.24963/ijcai.2017/278","title":"Bernoulli Rank-1 Bandits for Click Feedback","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":75,"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; Bernoulli's principle; Rank (graph theory); Position (finance); Computer science; Bounded function; Product (mathematics); Mathematics; Algorithm; Combinatorics; Machine learning","authors":[{"name":"Sumeet Katariya","is_ca":false},{"name":"Branislav Kveton","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true},{"name":"Claire Vernade","is_ca":false},{"name":"Zheng Wen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3279068753148421,"gpt":0.5299592419994449,"spread":0.2020523666846028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00706894,0.001460133,0.002947365,0.001199744,0.0009093207,0.001883465,0.002690433,0.002192078,0.005526266],"category_scores_gemma":[0.02516245,0.0007208627,0.0007404425,0.001413922,0.001831603,0.00324169,0.001446969,0.002690859,0.001342608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00239898,"about_ca_system_score_gemma":0.001684846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004536739,"about_ca_topic_score_gemma":0.004024408,"domain_scores_codex":[0.9961072,0.002094489,0.0001508366,0.0005176138,0.000696348,0.0004335696],"domain_scores_gemma":[0.9808591,0.01499246,0.001736532,0.001044139,0.0008932279,0.0004745976],"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":[0.0006181797,0.0002368822,0.001186115,0.000135209,0.00005329035,0.00009222854,0.0001021862,0.8687528,0.0008300941,0.0610763,0.003837085,0.0630797],"study_design_scores_gemma":[0.00002662621,0.00003952837,0.0001055411,0.000008424081,0.000004594001,0.0000125943,0.000005117173,0.9785775,0.0001843072,0.0207609,0.0002662084,0.000008758798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0815473,0.001567141,0.9074329,0.001290981,0.0001269848,0.0002065275,0.0003171449,0.001764424,0.00574658],"genre_scores_gemma":[0.8795918,0.0005492297,0.1107885,0.0004990288,0.0002052744,0.0003422857,0.0003386568,0.0001666306,0.007518432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00706894,"threshold_uncertainty_score":0.03738463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095762034","doi":"10.5555/1577069.1577089","title":"Online Learning with Sample Path Constraints","year":2009,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":74,"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":"Hindsight bias; Path (computing); Heuristic; Mathematical optimization; Convex hull; Sample (material); Constraint (computer-aided design); Computer science; Decision maker; Function (biology); Measure (data warehouse); Term (time); Mathematics; Regular polygon; Operations research; Data mining; Psychology","authors":[{"name":"Shie Mannor","is_ca":true},{"name":"John N. Tsitsiklis","is_ca":false},{"name":"Jia Yuan Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04860125274093496,"gpt":0.3624277436117635,"spread":0.3138264908708285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004534392,0.001852994,0.002424423,0.0005842015,0.0004876326,0.001508069,0.002057778,0.002837921,0.003761911],"category_scores_gemma":[0.0315681,0.0008956911,0.0005601368,0.001208807,0.00168204,0.004291687,0.001308203,0.003291416,0.000437685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001676166,"about_ca_system_score_gemma":0.001717078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005581359,"about_ca_topic_score_gemma":0.003724544,"domain_scores_codex":[0.9980667,0.0009694414,0.000070897,0.0003896813,0.0002226725,0.0002805403],"domain_scores_gemma":[0.9617221,0.03310905,0.002759579,0.000961307,0.0007240068,0.0007239943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002141357,0.000124357,0.0008233084,0.00006343774,0.00003909434,0.0000833665,0.00003392017,0.9760616,0.0002398396,0.01176893,0.0006717594,0.009876291],"study_design_scores_gemma":[0.00003138508,0.00005263306,0.0001057875,0.000006259615,0.000006008554,0.000009686681,0.000005823035,0.9888617,0.0001531815,0.01064427,0.0001181008,0.000005127991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1617806,0.001261142,0.8276334,0.001818432,0.0001130764,0.000183282,0.000349904,0.0005971617,0.006262835],"genre_scores_gemma":[0.9405903,0.0005676697,0.05427165,0.0002944629,0.0001293996,0.0002154359,0.0002902852,0.00007505305,0.003565639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005581359,"threshold_uncertainty_score":0.02398044,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105336508","doi":"","title":"A Convergent Form of Approximate Policy Iteration","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":73,"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":"Lipschitz continuity; Convergence (economics); Operator (biology); Action (physics); Mathematics; Constant (computer programming); Mathematical optimization; Function (biology); Applied mathematics; Bellman equation; State (computer science); Computer science; Algorithm; Mathematical analysis","authors":[{"name":"Theodore J. Perkins","is_ca":false},{"name":"Doina Precup","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1833628301305216,"gpt":0.4441139764675269,"spread":0.2607511463370052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003669835,0.001091723,0.001678396,0.0006342681,0.0004953208,0.001364725,0.002247252,0.002165484,0.004323912],"category_scores_gemma":[0.01626253,0.0006654125,0.000848236,0.0006272251,0.002181003,0.00280658,0.002266575,0.00269569,0.0008592313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001065626,"about_ca_system_score_gemma":0.001958293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001563452,"about_ca_topic_score_gemma":0.001383555,"domain_scores_codex":[0.9977587,0.0007772394,0.0001021704,0.0003815333,0.0008363911,0.0001439383],"domain_scores_gemma":[0.9937909,0.003937752,0.0003856168,0.0007976196,0.0009061482,0.0001818905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001090265,0.0000890744,0.0004330273,0.0001107791,0.00005973839,0.00008219263,0.000147784,0.8188213,0.001802066,0.1340393,0.001246864,0.04305878],"study_design_scores_gemma":[0.00001043652,0.00003010967,0.00001824394,0.000007143502,0.000003982234,0.00002001306,0.000004942556,0.9838551,0.0004216123,0.01509764,0.0005265219,0.000004222382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005081657,0.00008733581,0.9914243,0.0001209609,0.00003769861,0.00003818819,0.0000183371,0.0001546293,0.003036822],"genre_scores_gemma":[0.4638347,0.0003038725,0.5257694,0.000328819,0.0001312216,0.0005312125,0.0001412151,0.0001946108,0.00876492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004323912,"threshold_uncertainty_score":0.01940817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1577851669","doi":"10.1007/978-3-642-34106-9_25","title":"Partial Monitoring with Side Information","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","authors":[{"name":"Gábor Bartók","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07038242003984675,"gpt":0.3665795994389151,"spread":0.2961971793990684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483065,0.0009542878,0.00115635,0.0004936808,0.0004264592,0.001777184,0.0009943462,0.0009314842,0.004983244],"category_scores_gemma":[0.005173446,0.0004245947,0.0004583251,0.0006869929,0.0008754348,0.002844942,0.001527182,0.001517557,0.001288983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005329654,"about_ca_system_score_gemma":0.0005500378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002722112,"about_ca_topic_score_gemma":0.000326763,"domain_scores_codex":[0.9987142,0.0004116414,0.00006903364,0.0002906278,0.0003616507,0.0001527326],"domain_scores_gemma":[0.9960461,0.001926235,0.0002811285,0.001278021,0.0003514377,0.0001169711],"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":[0.001358812,0.0001308041,0.001814558,0.0004534155,0.0001523722,0.0004410667,0.0001936265,0.1229429,0.0230342,0.3514568,0.01705937,0.4809622],"study_design_scores_gemma":[0.00004803776,0.0001878523,0.0006321073,0.0000643512,0.00008555772,0.0005259472,0.00002466945,0.6662532,0.01645656,0.3063781,0.009312445,0.00003120724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02336988,0.001222867,0.9512867,0.0005648054,0.0001798201,0.0000556784,0.0002591988,0.001151107,0.02190982],"genre_scores_gemma":[0.8388509,0.001113096,0.1309347,0.0003736688,0.0004862245,0.0001384095,0.0004996423,0.0002933718,0.02730996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004983244,"threshold_uncertainty_score":0.01667064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2561282814","doi":"10.1016/j.tcs.2012.10.008","title":"Toward a classification of finite partial-monitoring games","year":2012,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":67,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Computer science; Algebra over a field; Calculus (dental); Mathematical economics; Pure mathematics; Medicine","authors":[{"name":"András Antos","is_ca":false},{"name":"Gábor Bartók","is_ca":true},{"name":"Dávid Pál","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1886192829944454,"gpt":0.4452306175989132,"spread":0.2566113346044678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00346876,0.001343439,0.0022489,0.002353773,0.001481974,0.006151097,0.003416583,0.002902827,0.00640657],"category_scores_gemma":[0.01798695,0.0007724241,0.001771059,0.001888042,0.003347277,0.007490125,0.002771928,0.005380976,0.0006157561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002584717,"about_ca_system_score_gemma":0.002418015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001745313,"about_ca_topic_score_gemma":0.00150421,"domain_scores_codex":[0.9973766,0.0008922277,0.000224396,0.0005379003,0.0005310164,0.0004380242],"domain_scores_gemma":[0.9820806,0.01252218,0.001502474,0.00130933,0.001069442,0.001515931],"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":[0.00009889488,0.0001165358,0.001386543,0.00008430033,0.00002942495,0.00004448658,0.0002347841,0.01217722,0.0006283492,0.9686148,0.002527335,0.01405747],"study_design_scores_gemma":[0.00005120857,0.00005585105,0.0005005774,0.00004885266,0.00002104193,0.00007383879,0.00007972777,0.1345226,0.0002542253,0.8627899,0.001582185,0.00002015418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2455775,0.000835944,0.7179958,0.002860869,0.000133047,0.0003210841,0.0008289933,0.0004933768,0.0309534],"genre_scores_gemma":[0.8587171,0.001014778,0.1254204,0.0007529499,0.0003526206,0.0005162153,0.001375585,0.0001714669,0.01167892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00640657,"threshold_uncertainty_score":0.0214321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2293140407","doi":"10.1145/1993636.1993666","title":"Dueling algorithms","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":66,"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":"Minimax; Computer science; Mathematical optimization; Binary search algorithm; Algorithm; Ranking (information retrieval); Binary number; Mathematics; Search algorithm; Artificial intelligence","authors":[{"name":"Nicole Immorlica","is_ca":false},{"name":"Adam Tauman Kalai","is_ca":false},{"name":"Brendan Lucier","is_ca":true},{"name":"Ankur Moitra","is_ca":false},{"name":"Andrew Postlewaite","is_ca":false},{"name":"Moshe Tennenholtz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5436472135121365,"gpt":0.4912489599546517,"spread":0.05239825355748484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003280154,0.001447523,0.002052258,0.002045193,0.001869328,0.003964712,0.003461836,0.002938139,0.02539049],"category_scores_gemma":[0.01777936,0.0005833296,0.001606838,0.002801316,0.001965649,0.007220988,0.004742604,0.003623544,0.006282753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001980918,"about_ca_system_score_gemma":0.001620084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001347194,"about_ca_topic_score_gemma":0.00147326,"domain_scores_codex":[0.9969469,0.001084637,0.0002191636,0.0005623032,0.0007669613,0.0004201331],"domain_scores_gemma":[0.995047,0.002922886,0.0002825084,0.001068847,0.0004375826,0.0002412027],"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":[0.00009167876,0.0001511893,0.000426381,0.0002788069,0.00004166769,0.00006178274,0.0001454594,0.06888677,0.0006014083,0.7137786,0.0236369,0.1918994],"study_design_scores_gemma":[0.00006464904,0.000079868,0.0001087696,0.00006658162,0.00001623293,0.0001303632,0.00004255529,0.2718155,0.0006547792,0.7055073,0.02148884,0.00002447594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008716062,0.002059185,0.9418197,0.001759905,0.0005041088,0.0003603636,0.0003810737,0.0009275125,0.04347205],"genre_scores_gemma":[0.2868859,0.00331953,0.6419319,0.002295743,0.0009273676,0.001140964,0.001887125,0.0009129069,0.06069863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02539049,"threshold_uncertainty_score":0.0849396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963246254","doi":"","title":"Optimum Statistical Estimation with Strategic Data Sources","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":64,"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":"Estimator; Polynomial regression; Computer science; Regression; Regression analysis; Kernel (algebra); Linear regression; Range (aeronautics); Proper linear model; Mathematical optimization; Econometrics; Statistics; Mathematics; Machine learning; Engineering","authors":[{"name":"Yang Cai","is_ca":true},{"name":"Constantinos Daskalakis","is_ca":false},{"name":"Christos H. Papadimitriou","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5456077650671064,"gpt":0.5258773785639367,"spread":0.01973038650316972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01628684,0.001306173,0.002367329,0.001544676,0.0007837999,0.003067768,0.002328544,0.003278067,0.006894847],"category_scores_gemma":[0.06377346,0.001666942,0.001140958,0.002575081,0.002636977,0.005681439,0.00438347,0.003032479,0.001659809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002048034,"about_ca_system_score_gemma":0.001984528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001009908,"about_ca_topic_score_gemma":0.0009244609,"domain_scores_codex":[0.9844081,0.0111724,0.0005317514,0.001903413,0.001506191,0.0004781743],"domain_scores_gemma":[0.9574677,0.03070718,0.004582565,0.004996953,0.00164006,0.0006055965],"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":[0.0008974327,0.0002260681,0.002918294,0.0003988753,0.0002436943,0.0003060756,0.0003071524,0.257663,0.001688825,0.6029422,0.006935411,0.1254732],"study_design_scores_gemma":[0.0002577321,0.0001726697,0.0006760545,0.0001359329,0.00005735231,0.0001284924,0.00007130671,0.5753233,0.001143456,0.4168264,0.005159469,0.00004770571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01737016,0.0007398649,0.9752746,0.001873543,0.00006118252,0.0001753304,0.0001939258,0.0002212152,0.00409023],"genre_scores_gemma":[0.6142945,0.0009082834,0.3722328,0.0008143749,0.0002157706,0.00101941,0.0004526307,0.0001101832,0.009952162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01628684,"threshold_uncertainty_score":0.08613402,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W191658262","doi":"","title":"{Toward Minimax Off-policy Value Estimation}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":62,"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":"Estimator; Minimax; Markov decision process; Multiplicative function; Mathematical optimization; Oracle; Computer science; Time horizon; Limit (mathematics); Sample size determination; Upper and lower bounds; Mathematics; Sample (material); Value (mathematics); Markov process; Statistics","authors":[{"name":"Lihong Li","is_ca":false},{"name":"Rémi Munos","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3651976247050544,"gpt":0.5253249721812989,"spread":0.1601273474762445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01404385,0.002073983,0.00355676,0.001524877,0.0009100023,0.003433095,0.002280192,0.003091802,0.004431943],"category_scores_gemma":[0.06357222,0.001100549,0.0008072635,0.001487048,0.003861881,0.004603599,0.003134237,0.00454172,0.0008970991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002563876,"about_ca_system_score_gemma":0.002528696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002247085,"about_ca_topic_score_gemma":0.001244083,"domain_scores_codex":[0.9928017,0.004987385,0.0002057915,0.0009208334,0.0007448291,0.0003394835],"domain_scores_gemma":[0.9558498,0.03919687,0.001821924,0.001410954,0.001265087,0.0004553628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006246804,0.0002605694,0.003637786,0.0004295434,0.0002362888,0.0002082736,0.0002065483,0.6809061,0.0008545367,0.2302415,0.004810543,0.07758363],"study_design_scores_gemma":[0.00003833509,0.0000758372,0.0002647117,0.00009280194,0.00001453421,0.00003449669,0.0000240798,0.8847965,0.0006087038,0.1133566,0.0006750371,0.00001825027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02885048,0.001123403,0.9618438,0.001956147,0.00007894573,0.0001917523,0.0002126094,0.0003580898,0.005384862],"genre_scores_gemma":[0.748836,0.001104621,0.2413628,0.001127627,0.0003069067,0.0007523631,0.0005857764,0.0002903809,0.005633518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01404385,"threshold_uncertainty_score":0.07427186,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964315724","doi":"10.48550/arxiv.1605.08988","title":"On Explore-Then-Commit Strategies","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":59,"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; Commit; Minimax; Mathematical optimization; Asymptotically optimal algorithm; Simple (philosophy); Gaussian; Computer science; Order (exchange); Time horizon; Empirical evidence; Horizon; Mathematical economics; Mathematics; Economics; Machine learning","authors":[{"name":"Aurélien Garivier","is_ca":false},{"name":"Emilie Kaufmann","is_ca":false},{"name":"Tor Lattimore","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3686539785191696,"gpt":0.3317025144979235,"spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005306371,0.002034727,0.002228245,0.0008652667,0.0007143329,0.002322169,0.001875162,0.003043824,0.005952096],"category_scores_gemma":[0.03012438,0.0007913276,0.0008671416,0.001229445,0.002662672,0.003597163,0.002056234,0.003664624,0.0009548941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001993087,"about_ca_system_score_gemma":0.001967602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002494968,"about_ca_topic_score_gemma":0.001610584,"domain_scores_codex":[0.9969211,0.001784322,0.0001188599,0.0004298641,0.0003680033,0.0003779364],"domain_scores_gemma":[0.9776837,0.01907209,0.001365751,0.0006212232,0.0006267966,0.0006304365],"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":[0.0004704898,0.0001794254,0.001534613,0.0002912633,0.0001449363,0.0002405366,0.0003088309,0.6108882,0.001253225,0.3562648,0.002804756,0.02561899],"study_design_scores_gemma":[0.0000868604,0.0001536206,0.0002063315,0.00006326687,0.00002385856,0.00004521173,0.00004259743,0.8230346,0.0003693431,0.1749098,0.0010441,0.0000202923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09339536,0.002078403,0.8740434,0.002984012,0.0001519063,0.0002267457,0.000286347,0.0002800411,0.02655386],"genre_scores_gemma":[0.8967816,0.001492861,0.08550455,0.0008178829,0.0002002976,0.0005284835,0.0002314148,0.0001961929,0.01424662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005952096,"threshold_uncertainty_score":0.02806312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2206616202","doi":"","title":"Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":57,"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; Computer science; Lasso (programming language); Online algorithm; Algorithm; Set (abstract data type); Online learning; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","authors":[{"name":"Yasin Abbasi-Yadkori","is_ca":true},{"name":"Dávid Pál","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1421157769493659,"gpt":0.4560052028147418,"spread":0.3138894258653759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006510065,0.001435911,0.001956837,0.001321219,0.0007602079,0.00287948,0.002764589,0.00198781,0.004598004],"category_scores_gemma":[0.04932374,0.0009153507,0.001263779,0.001620665,0.002912255,0.004002615,0.00472884,0.00624052,0.0009461738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386053,"about_ca_system_score_gemma":0.001406984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001155835,"about_ca_topic_score_gemma":0.0007999177,"domain_scores_codex":[0.9951138,0.001812078,0.0003067733,0.0006742358,0.001776587,0.000316579],"domain_scores_gemma":[0.9783247,0.01572522,0.001417428,0.002657933,0.001422875,0.0004518354],"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":[0.0002171533,0.000202705,0.001110313,0.0001605408,0.00007607191,0.0001722384,0.0002102078,0.5635912,0.00234762,0.3106093,0.002004319,0.1192984],"study_design_scores_gemma":[0.00002148892,0.00003684523,0.0001040743,0.00002403989,0.000007988609,0.00004738394,0.000007859058,0.9216999,0.001400595,0.07591629,0.0007151805,0.0000183428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006022713,0.0001431488,0.9912463,0.0001953474,0.0000301587,0.00004444904,0.00005168368,0.0003516559,0.001914541],"genre_scores_gemma":[0.5456915,0.000507416,0.4475973,0.0004718607,0.0002554483,0.0005569026,0.0004018605,0.0004151291,0.004102627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006510065,"threshold_uncertainty_score":0.03442889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009482316","doi":"10.1080/07474940600596695","title":"Sequential Generalized Likelihood Ratios and Adaptive Treatment Allocation for Optimal Sequential Selection","year":2006,"lang":"en","type":"article","venue":"Sequential Analysis","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National University of Singapore; University of Lethbridge; National Science Foundation","keywords":"Mathematics; Selection (genetic algorithm); Mathematical optimization; Sequential estimation; Sampling (signal processing); Exponential family; Constraint (computer-aided design); Population; Sequential analysis; Stopping rule; Statistics; Computer science; Artificial intelligence","authors":[{"name":"Hock Peng Chan","is_ca":false},{"name":"Tze-Leung Lai","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08329802728424093,"gpt":0.3970339346573362,"spread":0.3137359073730952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02911002,0.0013322,0.002673616,0.001608742,0.0005171684,0.001574632,0.002734544,0.00169151,0.005862962],"category_scores_gemma":[0.09817887,0.0008513648,0.001133023,0.001493141,0.003581876,0.002457362,0.002523921,0.001855613,0.0007060522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001984487,"about_ca_system_score_gemma":0.002753127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001593942,"about_ca_topic_score_gemma":0.0009541265,"domain_scores_codex":[0.971068,0.02444647,0.0005181691,0.001587206,0.001824817,0.0005552687],"domain_scores_gemma":[0.9534027,0.03993395,0.002776095,0.001873601,0.001586308,0.0004273952],"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":[0.0007247279,0.0002424403,0.001519756,0.0002133912,0.0002580211,0.0001700179,0.0001970325,0.6068093,0.001175754,0.2798638,0.001357481,0.1074682],"study_design_scores_gemma":[0.0001657556,0.000143434,0.0003371528,0.00002682537,0.00002780656,0.00005033975,0.00001980878,0.8867072,0.000733173,0.1111879,0.0005791203,0.00002135354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009507146,0.0001174535,0.9890881,0.0002513666,0.00001698299,0.0001498663,0.0000182891,0.0001022564,0.0007486765],"genre_scores_gemma":[0.4242173,0.000215816,0.571871,0.0002679021,0.00008884975,0.001249252,0.00009286011,0.0001121738,0.001884744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02911002,"threshold_uncertainty_score":0.1539504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1675620121","doi":"10.48550/arxiv.1402.7005","title":"Bayesian Multi-Scale Optimistic Optimization","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":53,"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":"Bayesian optimization; Regret; Computer science; Mathematical optimization; Global optimization; Optimization problem; Convergence (economics); Gaussian process; Bayesian probability; Test functions for optimization; Derivative-free optimization; Function (biology); Continuous optimization; Random optimization; Gaussian; Algorithm; Multi-swarm optimization; Mathematics; Artificial intelligence; Machine learning","authors":[{"name":"Ziyu Wang","is_ca":true},{"name":"Babak Shakibi","is_ca":true},{"name":"Nando de Freitas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2206405619657407,"gpt":0.3089465051702611,"spread":0.08830594320452045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004668181,0.00141071,0.001839193,0.0008274572,0.0008278622,0.002357116,0.00185628,0.001429144,0.004889645],"category_scores_gemma":[0.01223001,0.0009651336,0.001120709,0.001168408,0.001739512,0.002361612,0.003057052,0.003007397,0.001100029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002082041,"about_ca_system_score_gemma":0.002446675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003064139,"about_ca_topic_score_gemma":0.003793041,"domain_scores_codex":[0.997587,0.001040575,0.00009419631,0.0003491839,0.0006604984,0.0002685825],"domain_scores_gemma":[0.9954032,0.003074361,0.000332704,0.0005963479,0.0004285871,0.0001647361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000131222,0.00003531847,0.0003880379,0.0001090585,0.00005853738,0.00004399555,0.00006759183,0.8506765,0.0007775985,0.1051393,0.003231887,0.03934089],"study_design_scores_gemma":[0.00000726661,0.00001290081,0.00005145906,0.00001101394,0.000006925296,0.000009889208,0.000007166557,0.970004,0.0003542507,0.0288736,0.0006553138,0.000006386749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005954545,0.0003564241,0.9877844,0.0003603591,0.00002860172,0.00003453222,0.00006245415,0.0003878042,0.005030935],"genre_scores_gemma":[0.5788509,0.0007865237,0.409456,0.0004941901,0.0001282057,0.0003226431,0.0003628276,0.0005076286,0.009091083],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004889645,"threshold_uncertainty_score":0.02468795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964240248","doi":"","title":"Combinatorial cascading bandits","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"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":"Computer science; Observability; Regret; Mathematical proof; Routing (electronic design automation); Theoretical computer science; Mathematical optimization; Mathematics; Machine learning","authors":[{"name":"Branislav Kveton","is_ca":false},{"name":"Zheng Wen","is_ca":false},{"name":"Azin Ashkan","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3963383477905725,"gpt":0.5102858031466518,"spread":0.1139474553560793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002429809,0.001195118,0.001919668,0.0008129769,0.0007413749,0.001838211,0.00198342,0.001615894,0.004717187],"category_scores_gemma":[0.0104268,0.0005756625,0.0007849513,0.001357473,0.001463881,0.002179816,0.001969431,0.001991479,0.0006855629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134692,"about_ca_system_score_gemma":0.000973145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002057913,"about_ca_topic_score_gemma":0.002150314,"domain_scores_codex":[0.998221,0.0007681129,0.00009726043,0.0003748009,0.0003092779,0.0002296158],"domain_scores_gemma":[0.9940645,0.00401212,0.000578167,0.0006271662,0.0004145899,0.0003034718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001930901,0.00009501815,0.00133087,0.0001335149,0.00007499506,0.0001247445,0.0000674672,0.8562378,0.0009239847,0.1063848,0.003198321,0.03123543],"study_design_scores_gemma":[0.0000179304,0.00002947827,0.00008052762,0.00001075365,0.000008055047,0.00002604623,0.000008550847,0.9581525,0.0001893797,0.04088238,0.0005882476,0.000006132674],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06520214,0.0006695099,0.9234725,0.0007867347,0.00009067739,0.0001159733,0.0002918289,0.0006360684,0.008734496],"genre_scores_gemma":[0.8777393,0.000444754,0.1149592,0.000396576,0.00008269094,0.0003196217,0.0003620989,0.0001236543,0.005572228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004717187,"threshold_uncertainty_score":0.01578063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1838526237","doi":"10.1287/mnsc.2015.2153","title":"Robust Multiarmed Bandit Problems","year":2015,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"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":"Mathematical optimization; Computer science; Bellman equation; Robust optimization; Dynamic programming; Dynamic pricing; Decision maker; Multi-armed bandit; Regret; Mathematics; Operations research; Economics","authors":[{"name":"Michael Jong Kim","is_ca":true},{"name":"Andrew E. B. Lim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3788463044400635,"gpt":0.4460406049573264,"spread":0.06719430051726294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007608545,0.00297251,0.004515287,0.001244626,0.0008917429,0.004898388,0.003233871,0.005656354,0.008723812],"category_scores_gemma":[0.02364395,0.001474137,0.001723929,0.001988665,0.002946409,0.003443465,0.00223937,0.004219184,0.001662008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002793477,"about_ca_system_score_gemma":0.00186046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004811341,"about_ca_topic_score_gemma":0.002622425,"domain_scores_codex":[0.9943896,0.00261189,0.0003345935,0.001207378,0.0007679558,0.0006886446],"domain_scores_gemma":[0.9790853,0.01671571,0.002102536,0.0007310982,0.0009920828,0.0003732542],"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":[0.0001645413,0.00007961082,0.0005363059,0.0001667429,0.0001072336,0.0001737753,0.00007453511,0.8656985,0.0004680108,0.1181354,0.001709201,0.0126861],"study_design_scores_gemma":[0.00002934363,0.00003186399,0.00009695516,0.00002354811,0.00001907842,0.00002197285,0.00001759824,0.9519767,0.0001737521,0.04699599,0.0005962992,0.00001681903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01345697,0.001288051,0.9745821,0.001133578,0.0001122169,0.0001690388,0.0004297222,0.0003012716,0.00852709],"genre_scores_gemma":[0.8114837,0.002597184,0.1618967,0.0009412997,0.0003819363,0.000884904,0.0008787171,0.0002267878,0.02070879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008723812,"threshold_uncertainty_score":0.04023832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154806059","doi":"","title":"Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"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; Markov decision process; Adversarial system; Mathematical optimization; Computer science; Shortest path problem; Path (computing); Mathematics; Graph; Markov process; Theoretical computer science; Artificial intelligence; Machine learning","authors":[{"name":"Yasin Abbasi","is_ca":false},{"name":"Peter L. Bartlett","is_ca":false},{"name":"Varun Kanade","is_ca":false},{"name":"Yevgeny Seldin","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09547229580583252,"gpt":0.270794819568804,"spread":0.1753225237629715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005563384,0.001846935,0.002523211,0.0007986809,0.0009791711,0.002166846,0.002406219,0.002641973,0.003624765],"category_scores_gemma":[0.02008713,0.001275614,0.001544895,0.001222978,0.003011391,0.004338257,0.002902901,0.004920834,0.0004543044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003360484,"about_ca_system_score_gemma":0.002477696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006291115,"about_ca_topic_score_gemma":0.004276509,"domain_scores_codex":[0.996435,0.001682246,0.0001232201,0.0009166147,0.000332439,0.0005104079],"domain_scores_gemma":[0.9691498,0.02725654,0.001602985,0.0008671125,0.0004707725,0.0006527393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001644416,0.0000799242,0.0005573628,0.00006642406,0.00005219928,0.00009459272,0.00005433791,0.9614204,0.0002465429,0.02994444,0.0004558732,0.006863462],"study_design_scores_gemma":[0.00002331244,0.0000275584,0.0000534651,0.000005022957,0.000006567874,0.00001004379,0.000006468935,0.9662714,0.0001461462,0.03331891,0.000126213,0.000004886037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05293016,0.000587395,0.9416018,0.001345783,0.00006902346,0.0001168315,0.0001843134,0.000466921,0.00269776],"genre_scores_gemma":[0.8832706,0.0006921391,0.109276,0.000432838,0.000150185,0.0004234495,0.000375275,0.0001527412,0.005226795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006291115,"threshold_uncertainty_score":0.02942228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2241126168","doi":"","title":"The adversarial stochastic shortest path problem with unknown transition probabilities","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":49,"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; Markov decision process; Reinforcement learning; Shortest path problem; Computer science; Logarithm; State space; Mathematical optimization; Mathematics; Graph; Markov process; Artificial intelligence; Theoretical computer science; Machine learning","authors":[{"name":"Gergely Neu","is_ca":false},{"name":"András György","is_ca":true},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06434972756859121,"gpt":0.3637676920026717,"spread":0.2994179644340805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001669297,0.001025662,0.001479176,0.000522365,0.0005229615,0.001082528,0.001665679,0.00192458,0.002106568],"category_scores_gemma":[0.006066394,0.0005004141,0.0006960881,0.0006602083,0.001672554,0.002259821,0.001324469,0.001782609,0.0002611676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001193734,"about_ca_system_score_gemma":0.001315853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003203357,"about_ca_topic_score_gemma":0.001964786,"domain_scores_codex":[0.9988499,0.0004604275,0.00004313652,0.0003585505,0.0001426813,0.0001454029],"domain_scores_gemma":[0.9959689,0.002974952,0.0004867878,0.0002217527,0.0001352033,0.0002123471],"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":[0.00005957072,0.00003108042,0.0002858558,0.00003476649,0.00002919198,0.00007847462,0.00002687581,0.966005,0.0002870288,0.02720506,0.000386792,0.005570294],"study_design_scores_gemma":[0.000009935879,0.00001485112,0.0000407769,0.000002716243,0.000004061915,0.00001190139,0.000003677359,0.9778431,0.0001357234,0.02172738,0.0002022558,0.000003626207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03639945,0.0002310515,0.9605227,0.0005289506,0.00004484212,0.00005479519,0.0001272511,0.0001566988,0.001934334],"genre_scores_gemma":[0.874408,0.0004059827,0.1198192,0.0001799158,0.0001116233,0.0001863863,0.0002767055,0.00007819774,0.004534002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003203357,"threshold_uncertainty_score":0.008828223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106233414","doi":"10.48550/arxiv.1205.0622","title":"No-Regret Learning in Extensive-Form Games with Imperfect Recall","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":47,"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; Recall; Computer science; Imperfect; Perfect information; Class (philosophy); Counterfactual thinking; Mathematical economics; Mathematics; Artificial intelligence; Psychology; Machine learning; Cognitive psychology; Social psychology","authors":[{"name":"Marc Lanctot","is_ca":true},{"name":"Richard G. Gibson","is_ca":true},{"name":"Neil Burch","is_ca":false},{"name":"Martin Zinkevich","is_ca":true},{"name":"Michael Bowling","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1408962463293117,"gpt":0.2858046201333195,"spread":0.1449083738040078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00559251,0.001460492,0.001721995,0.0005257564,0.0005992003,0.001932459,0.001973984,0.001591009,0.001355353],"category_scores_gemma":[0.02613381,0.0007268501,0.00074733,0.0006389009,0.002826079,0.003705072,0.001844425,0.00261928,0.0003042603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002019896,"about_ca_system_score_gemma":0.00150756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002140303,"about_ca_topic_score_gemma":0.002116714,"domain_scores_codex":[0.9960497,0.00248759,0.0001345367,0.0005665453,0.0004568058,0.0003048234],"domain_scores_gemma":[0.9813416,0.01503399,0.001224471,0.00162363,0.000386803,0.0003895388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000482093,0.0001894822,0.001097066,0.0001361293,0.0001110533,0.0001033628,0.0001531007,0.7829096,0.0006060654,0.1791557,0.001518859,0.03353768],"study_design_scores_gemma":[0.00003805129,0.00005699867,0.0001487025,0.00001430121,0.00001322154,0.00001974885,0.00001009113,0.8706061,0.0004087782,0.1283253,0.0003484854,0.00001022865],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1038829,0.0006241637,0.8851712,0.001435575,0.00005199812,0.0001248642,0.0001169808,0.0004699409,0.008122267],"genre_scores_gemma":[0.9115955,0.0003727403,0.08329768,0.0003057009,0.0000871486,0.0002090204,0.0001403216,0.0000598019,0.003932046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00559251,"threshold_uncertainty_score":0.02957636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110582581","doi":"10.48550/arxiv.1206.6457","title":"Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":46,"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; Exponential function; Mathematical economics; Applied mathematics; Mathematics; Gaussian; Process (computing); Gaussian process; Econometrics; Mathematical optimization; Statistical physics; Economics; Computer science; Statistics; Physics; Mathematical analysis","authors":[{"name":"Nando de Freitas","is_ca":true},{"name":"Alex Smola","is_ca":true},{"name":"Masrour Zoghi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4019517217496925,"gpt":0.3403438641409024,"spread":0.06160785760879012,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01530934,0.002839986,0.003079991,0.002025674,0.001915243,0.003835692,0.003450891,0.002929377,0.004655411],"category_scores_gemma":[0.06876258,0.001334388,0.00170991,0.002597503,0.005162863,0.007740323,0.004456697,0.006642771,0.0009941207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005303404,"about_ca_system_score_gemma":0.002600416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003375302,"about_ca_topic_score_gemma":0.002725111,"domain_scores_codex":[0.9947482,0.00236419,0.0001684279,0.0007581585,0.001161517,0.0007995903],"domain_scores_gemma":[0.9427685,0.04844327,0.002767635,0.002970985,0.002060281,0.0009893166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000633823,0.0001707328,0.002157699,0.000345717,0.0002078447,0.0001916747,0.000220153,0.65076,0.001276704,0.3168642,0.005431793,0.02173965],"study_design_scores_gemma":[0.00004333803,0.00005494068,0.0004018878,0.00008350532,0.00003795286,0.00005218304,0.00002579538,0.8660918,0.0004627504,0.1318604,0.0008630933,0.00002236033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04630912,0.008116768,0.9231952,0.004236092,0.0002902895,0.0001243302,0.000430469,0.0006977557,0.01659997],"genre_scores_gemma":[0.848596,0.007826025,0.1244288,0.00237055,0.001274643,0.0008609431,0.0009365224,0.0006951239,0.01301133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01530934,"threshold_uncertainty_score":0.08096457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569559301","doi":"10.1007/978-3-540-27819-1_46","title":"The Budgeted Multi-armed Bandit Problem","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Abstraction; Set (abstract data type); Mathematical optimization; Multi-armed bandit; Artificial intelligence; Operations research; Machine learning; Mathematics; Programming language","authors":[{"name":"Omid Madani","is_ca":false},{"name":"Daniel J. Lizotte","is_ca":true},{"name":"Russell Greiner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07238701070652422,"gpt":0.3767942946054017,"spread":0.3044072838988775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004700442,0.001715522,0.003939035,0.0009772601,0.001024728,0.005303391,0.00299025,0.005443001,0.01182006],"category_scores_gemma":[0.01961314,0.001469899,0.0009585078,0.002515733,0.002521617,0.005158297,0.002415786,0.004058734,0.001912905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001839942,"about_ca_system_score_gemma":0.001786224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002562028,"about_ca_topic_score_gemma":0.001770064,"domain_scores_codex":[0.996908,0.001771925,0.0001157347,0.0005320534,0.0003205154,0.0003517242],"domain_scores_gemma":[0.9905612,0.007725172,0.0005496742,0.0004374557,0.000365629,0.0003609378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006679017,0.0001778655,0.0007590573,0.0004793596,0.0001741217,0.0001999567,0.0001229819,0.5955771,0.0005989898,0.3205072,0.0206424,0.06009301],"study_design_scores_gemma":[0.0001296692,0.00006778799,0.0001970785,0.00007036195,0.00003851188,0.00006783429,0.00004565267,0.687049,0.0002100828,0.3078627,0.004230171,0.0000311538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02904451,0.003939719,0.928767,0.004748536,0.0005413152,0.0001732182,0.0009256622,0.0003132194,0.03154671],"genre_scores_gemma":[0.7191,0.006860525,0.2050313,0.00128809,0.001456803,0.001024687,0.001541207,0.000396917,0.06330045],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01182006,"threshold_uncertainty_score":0.03954208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969276875","doi":"10.1016/j.tcs.2014.09.029","title":"Near-optimal PAC bounds for discounted MDPs","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Upper and lower bounds; Markov decision process; Logarithm; Sample complexity; Mathematics; Reinforcement learning; State space; Stochastic matrix; Markov chain; Matrix (chemical analysis); Space (punctuation); Markov process; Mathematical optimization; Applied mathematics; Combinatorics; Computer science; Statistics; Mathematical analysis","authors":[{"name":"Tor Lattimore","is_ca":true},{"name":"Marcus Hütter","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04680964409173786,"gpt":0.418173190851378,"spread":0.3713635467596401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008327335,0.003738836,0.005303547,0.003462454,0.002481854,0.009079892,0.004883167,0.004728241,0.01447466],"category_scores_gemma":[0.05770148,0.002196721,0.002211889,0.003913435,0.003878361,0.01391465,0.007141346,0.01102645,0.001756873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008643851,"about_ca_system_score_gemma":0.008258153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004809622,"about_ca_topic_score_gemma":0.006839177,"domain_scores_codex":[0.9934277,0.002098758,0.0002991857,0.0009537127,0.001801049,0.001419635],"domain_scores_gemma":[0.9427331,0.0491838,0.00143941,0.002520512,0.002055771,0.002067425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006423899,0.0003353945,0.0007585368,0.0006907861,0.0001357891,0.0001115667,0.0002401594,0.6149774,0.000930909,0.3300956,0.01056138,0.04052016],"study_design_scores_gemma":[0.00003980904,0.0000644892,0.0001258658,0.0001324424,0.00003926275,0.00005885847,0.00005098038,0.6909906,0.0005458053,0.3062524,0.001675011,0.00002452096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0450282,0.007226659,0.8873165,0.006335709,0.0005198327,0.0003280487,0.001620838,0.001164661,0.05045956],"genre_scores_gemma":[0.7585099,0.006883887,0.2051786,0.00250922,0.001295738,0.001191945,0.001872576,0.00102127,0.02153686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01447466,"threshold_uncertainty_score":0.06271583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951455820","doi":"","title":"Online Learning to Rank in Stochastic Click Models","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Computer science; Learning to rank; Rank (graph theory); Regret; Machine learning; Online learning; Convergence (economics); Artificial intelligence; Range (aeronautics); Class (philosophy); Theoretical computer science; Ranking (information retrieval); Mathematics; World Wide Web","authors":[{"name":"Masrour Zoghi","is_ca":false},{"name":"Tomáš Tunys","is_ca":false},{"name":"Mohammad Ghavamzadeh","is_ca":false},{"name":"Branislav Kveton","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true},{"name":"Zheng Wen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3577127700268318,"gpt":0.3531140666372869,"spread":0.004598703389544934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008085603,0.001691065,0.003582695,0.00145508,0.0010392,0.002510096,0.002955415,0.00262958,0.004908773],"category_scores_gemma":[0.03015659,0.001008543,0.001221659,0.002266727,0.002442546,0.005657933,0.001953273,0.003128888,0.001504699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002106332,"about_ca_system_score_gemma":0.002019815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006251622,"about_ca_topic_score_gemma":0.007504487,"domain_scores_codex":[0.9953739,0.002275707,0.000215464,0.0008402813,0.0007459357,0.0005487474],"domain_scores_gemma":[0.9734834,0.02152549,0.00179677,0.001599328,0.001023722,0.0005712477],"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":[0.0005367937,0.0003255756,0.00285461,0.0003450686,0.00009559991,0.0002037915,0.0001222748,0.7880096,0.0008856006,0.1310596,0.009214957,0.06634647],"study_design_scores_gemma":[0.00002862075,0.00004877425,0.0001809253,0.000009236844,0.000009653384,0.00003701735,0.00001258892,0.9571877,0.0002473913,0.04187647,0.0003496778,0.00001200444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05917595,0.001371398,0.9333305,0.001266218,0.00009339803,0.0001189209,0.0004960888,0.001134524,0.003013096],"genre_scores_gemma":[0.8144631,0.00165807,0.1705179,0.0007524757,0.0005484193,0.000410364,0.001480129,0.0003064914,0.009863093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008085603,"threshold_uncertainty_score":0.04276127,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146807381","doi":"","title":"PAC-Bayesian Analysis of Contextual Bandits","year":2011,"lang":"la","type":"article","venue":"MPG.PuRe (Max Planck Society)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Regret; Logarithm; Upper and lower bounds; Scaling; Bayesian probability; Computer science; Task (project management); Combinatorics; Mathematics; Algorithm; Artificial intelligence; Machine learning","authors":[{"name":"Yevgeny Seldin","is_ca":false},{"name":"Peter Auer","is_ca":false},{"name":"John Shawe‐Taylor","is_ca":true},{"name":"Ronald Ortner","is_ca":false},{"name":"François Laviolette","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1328243330302454,"gpt":0.3771460626394505,"spread":0.2443217296092051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006679031,0.001941812,0.002694138,0.001194171,0.001104097,0.003010621,0.002640774,0.001971231,0.007131402],"category_scores_gemma":[0.03366702,0.001285792,0.001386412,0.001511278,0.00316429,0.004328297,0.003139897,0.004102545,0.0009986812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003577112,"about_ca_system_score_gemma":0.003272152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005460722,"about_ca_topic_score_gemma":0.005206991,"domain_scores_codex":[0.9958156,0.00175936,0.0001499474,0.0006466042,0.0009794119,0.0006491559],"domain_scores_gemma":[0.9811064,0.01487734,0.001192898,0.001075923,0.001212374,0.000535136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002341692,0.0000556588,0.0008256343,0.0001725227,0.00008751483,0.00008613339,0.00009616117,0.7194259,0.0008728487,0.2595012,0.002140646,0.01650166],"study_design_scores_gemma":[0.00001632375,0.00002224109,0.0001643675,0.00002783617,0.00001880473,0.00001578267,0.000009443929,0.9217166,0.0002806791,0.077158,0.0005569874,0.00001290296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02103971,0.001320891,0.9653597,0.001165191,0.00008805001,0.00008607926,0.0003104617,0.000349191,0.01028079],"genre_scores_gemma":[0.8234022,0.002248896,0.1587724,0.0008247865,0.0004868369,0.0006165871,0.0006734385,0.0004124119,0.01256233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007131402,"threshold_uncertainty_score":0.03532249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135829225","doi":"10.1109/gamenets.2009.5137416","title":"Online learning in Markov decision processes with arbitrarily changing rewards and transitions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":37,"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":"Markov decision process; Regret; Computer science; Markov chain; Transition (genetics); Decision maker; Markov process; Range (aeronautics); Trajectory; Control (management); Online learning; Mathematical optimization; Artificial intelligence; Machine learning; Mathematics; Operations research; Statistics; Engineering","authors":[{"name":"Jia Yuan Yu","is_ca":true},{"name":"Shie Mannor","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04799188361605175,"gpt":0.3932287474444243,"spread":0.3452368638283726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005256236,0.00149611,0.002239828,0.0007441349,0.0008591863,0.002075865,0.001943744,0.002452667,0.001896577],"category_scores_gemma":[0.01948992,0.0009187549,0.001016281,0.001265351,0.0027229,0.003233079,0.002601748,0.002935517,0.0002780464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002115194,"about_ca_system_score_gemma":0.001916098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006427636,"about_ca_topic_score_gemma":0.00402363,"domain_scores_codex":[0.9975031,0.001155098,0.0001109674,0.0005600703,0.0002716722,0.0003991389],"domain_scores_gemma":[0.979482,0.01782464,0.001353912,0.000511584,0.000426832,0.0004010142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001563925,0.00006552084,0.0005663609,0.00006985647,0.00004533227,0.0001006544,0.00006706944,0.9406334,0.0002752533,0.04501916,0.0002916052,0.0127094],"study_design_scores_gemma":[0.00001871125,0.00002173302,0.00005674295,0.000007401469,0.000008029638,0.00001010939,0.000005425254,0.9697318,0.0001748661,0.02985314,0.0001061305,0.000005921248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04028909,0.0007114891,0.9562605,0.000636676,0.00004194318,0.00005477533,0.00005599845,0.0002303296,0.001719193],"genre_scores_gemma":[0.8895679,0.0008772737,0.106114,0.0002380586,0.0001113609,0.0002192478,0.0001317565,0.00005584404,0.00268447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006427636,"threshold_uncertainty_score":0.02779794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810504435","doi":"10.1109/access.2018.2850879","title":"A Multi-Domain Anti-Jamming Defense Scheme in Heterogeneous Wireless Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Jamming; Computer science; Power domains; Stackelberg competition; Channel (broadcasting); Wireless; Frequency domain; Computer network; Logarithm; Domain (mathematical analysis); Power (physics); Mathematical optimization; Telecommunications; Mathematics","authors":[{"name":"Luliang Jia","is_ca":false},{"name":"Yuhua Xu","is_ca":false},{"name":"Youming Sun","is_ca":false},{"name":"Shuo Feng","is_ca":false},{"name":"Long Yu","is_ca":false},{"name":"Alagan Anpalagan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1625277235217346,"gpt":0.4640437230106479,"spread":0.3015159994889133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001182339,0.0008232166,0.0007225633,0.0006200139,0.0006810095,0.0008491493,0.001307265,0.0008926739,0.0006805164],"category_scores_gemma":[0.002525144,0.0002052504,0.0005874383,0.0008051278,0.0007426083,0.001374214,0.001457291,0.0008655876,0.0001320882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007203165,"about_ca_system_score_gemma":0.0006271217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000670817,"about_ca_topic_score_gemma":0.0006528165,"domain_scores_codex":[0.9990382,0.000356951,0.00003551065,0.000169765,0.0002002359,0.0001994547],"domain_scores_gemma":[0.9988517,0.0005068533,0.0002139878,0.0001402945,0.0001744713,0.0001128026],"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":[0.0003609076,0.0001627196,0.001544854,0.0001768799,0.0002004927,0.0005472489,0.0002421995,0.7866535,0.02866531,0.0944589,0.00186964,0.08511732],"study_design_scores_gemma":[0.00001389681,0.0001413879,0.0001720236,0.000006383027,0.00003187648,0.0001514571,0.0000371959,0.9878372,0.001993704,0.008928769,0.0006735827,0.00001244117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04760728,0.00033678,0.9492155,0.0002148459,0.00004511351,0.00004661135,0.00002303428,0.00006983912,0.002440932],"genre_scores_gemma":[0.9525275,0.0002138686,0.04577354,0.0001106548,0.00003966312,0.00005339078,0.00002390331,0.000008987467,0.001248465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001307265,"threshold_uncertainty_score":0.006252825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W659523800","doi":"","title":"Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":34,"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; Computer science; Algorithm; Logarithm; Stochastic process; Adversarial system; Artificial intelligence; Mathematical optimization; Mathematics; Machine learning; Statistics","authors":[{"name":"Yevgeny Seldin","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true},{"name":"Peter Auer","is_ca":false},{"name":"Yasin Abbasi-Yadkori","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07402534430139121,"gpt":0.3945074600203065,"spread":0.3204821157189153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01026909,0.00155171,0.001244796,0.0008826749,0.0006800538,0.0013738,0.001889548,0.002222068,0.002757838],"category_scores_gemma":[0.03298193,0.0003439085,0.0006252611,0.001315371,0.001726,0.002098849,0.001907797,0.002156527,0.0005766826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001847797,"about_ca_system_score_gemma":0.002238027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003432089,"about_ca_topic_score_gemma":0.002739959,"domain_scores_codex":[0.9947895,0.002594729,0.0002630248,0.0005125222,0.001413637,0.0004265629],"domain_scores_gemma":[0.9642159,0.02827828,0.001608182,0.002736732,0.00240576,0.0007551306],"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":[0.001116034,0.0003004372,0.002889509,0.0002061182,0.00007697667,0.00008083899,0.00004407711,0.9534169,0.001580961,0.00909309,0.002317841,0.02887719],"study_design_scores_gemma":[0.00006035991,0.0002365098,0.0005890162,0.0000151521,0.000009098317,0.00005870946,0.00001715534,0.9940808,0.001074546,0.003541507,0.0003058386,0.00001129467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4795412,0.00477376,0.4927114,0.001888169,0.0003042861,0.0004832513,0.001149701,0.001775728,0.01737246],"genre_scores_gemma":[0.8696679,0.0006238166,0.126195,0.0002699381,0.00007436733,0.000168897,0.001068969,0.0002197161,0.001711538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01026909,"threshold_uncertainty_score":0.05430877,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2187589363","doi":"10.1609/aaai.v28i1.8891","title":"Online (Budgeted) Social Choice","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":33,"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":"Cardinality (data modeling); Regret; Set (abstract data type); Decision maker; Combinatorics; Social choice theory; Matching (statistics); Contrast (vision); Selection (genetic algorithm); Order (exchange); Mathematics; Computer science; Binary logarithm; Mathematical optimization; Mathematical economics; Discrete mathematics; Artificial intelligence; Data mining; Operations research; Machine learning; Statistics; Economics","authors":[{"name":"Joel Oren","is_ca":true},{"name":"Brendan Lucier","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2875956122926702,"gpt":0.4538000765792046,"spread":0.1662044642865344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005245316,0.001937247,0.002822947,0.0008521411,0.001678167,0.003162747,0.004663469,0.00384637,0.02024667],"category_scores_gemma":[0.01484422,0.001043021,0.00109558,0.002451545,0.002062843,0.00787784,0.003018651,0.002803609,0.001893164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003602584,"about_ca_system_score_gemma":0.002404795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004684212,"about_ca_topic_score_gemma":0.007004426,"domain_scores_codex":[0.9950438,0.002157991,0.0001810279,0.001268607,0.0006657424,0.000682926],"domain_scores_gemma":[0.9908499,0.006055888,0.0005885656,0.001440328,0.0003503242,0.0007150516],"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":[0.001941968,0.0009998715,0.002260066,0.000415155,0.0002085388,0.0004947177,0.0003387102,0.6778135,0.001474517,0.20059,0.01535551,0.09810754],"study_design_scores_gemma":[0.0002163292,0.00009520914,0.0002723622,0.00002326763,0.00002638877,0.00009031663,0.00006494161,0.8623123,0.0006969288,0.132285,0.003895319,0.00002166061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09907216,0.0006999891,0.8687998,0.003961768,0.0002613295,0.0007404839,0.002123511,0.001063773,0.02327723],"genre_scores_gemma":[0.7472185,0.0004804579,0.2313121,0.0005060484,0.0002896482,0.0006998843,0.00124455,0.0001430117,0.01810562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02024667,"threshold_uncertainty_score":0.0677318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}