{"meta":{"query_hash":"a2addb5837d6","filters":{"topic":"Advanced Bandit Algorithms Research"},"cohort_total":436,"direct_labels_cover":1,"predictions_cover":436,"exported":436,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/a2addb5837d6","api":"https://metacan.xera.ac/api/v1/cohort?topic=Advanced+Bandit+Algorithms+Research"},"results":[{"id":"W100039866","doi":"","title":"The Online Loop-free Stochastic Shortest-Path Problem.","year":2010,"lang":"en","type":"article","venue":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Shortest path problem; Regret; Mathematics; Asymptotically optimal algorithm; Path (computing); Graph; Action (physics); State (computer science); Combinatorics; Mathematical optimization; Hindsight bias; Discrete mathematics; Computer science; Algorithm","score_opus":0.07004419195070641,"score_gpt":0.3992770809796929,"score_spread":0.3292328890289865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W100039866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046328828,0.00076418184,0.94558233,0.0010345672,0.00011145102,0.0002076393,0.00053814764,0.00036066837,0.005072156],"genre_scores_gemma":[0.7866092,0.0008222404,0.20383532,0.00030373398,0.00017906031,0.00040033227,0.0010956328,0.00013644683,0.0066179927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985195,0.00061849295,0.00007263267,0.00037511738,0.0001866412,0.00022770243],"domain_scores_gemma":[0.99573046,0.0030900387,0.0005017905,0.0002450689,0.00017193686,0.00026076156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017521074,0.0010448581,0.0015902088,0.0006388507,0.0006682395,0.0011947829,0.0018536132,0.001943236,0.0031159902],"category_scores_gemma":[0.006062218,0.0005614809,0.0007706331,0.0010455955,0.0013023863,0.0027474195,0.0014682197,0.0015544151,0.000443048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016323336,0.00012015511,0.00060651737,0.00013011193,0.00008310702,0.0001273686,0.000062369596,0.94057906,0.00041551373,0.036763787,0.001960418,0.01898849],"study_design_scores_gemma":[0.0000450342,0.000051851843,0.00013076967,0.000011437875,0.000015319265,0.0000443402,0.000016498365,0.94189423,0.00024144817,0.056439646,0.0011008728,0.000008539053],"about_ca_topic_score_codex":0.004395472,"about_ca_topic_score_gemma":0.004051424,"teacher_disagreement_score":0.004395472,"about_ca_system_score_codex":0.0014953755,"about_ca_system_score_gemma":0.0020264515,"threshold_uncertainty_score":0.010849774},"labels":[],"label_agreement":null},{"id":"W1506389236","doi":"10.1109/ccece.2015.7129466","title":"An estimation based allocation rule with super-linear regret and finite lock-on time for time-dependent multi-armed bandit processes","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Mathematical optimization; Index (typography); Markov decision process; Multi-armed bandit; Computer science; Upper and lower bounds; Process (computing); Moving average; Markov chain; Markov process; Mathematics; Statistics; Machine learning","score_opus":0.12708405197254166,"score_gpt":0.4245114426048841,"score_spread":0.29742739063234247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506389236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016670762,0.0007148829,0.9791399,0.00043323878,0.00006698737,0.00007028723,0.000055677072,0.00024872168,0.0025995604],"genre_scores_gemma":[0.83466095,0.0009798912,0.1568794,0.0005590087,0.00023661117,0.00031788528,0.00020400638,0.00018153428,0.0059807105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960134,0.0015921613,0.00025238612,0.0008399095,0.00081635383,0.00048578784],"domain_scores_gemma":[0.9822713,0.013420332,0.0016795706,0.0007300761,0.0013055266,0.0005931846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006882399,0.0014594656,0.0035797395,0.0009662837,0.0008219296,0.0031866038,0.0026426003,0.002735135,0.0032966123],"category_scores_gemma":[0.022393193,0.00090396724,0.0010287723,0.0011352878,0.0023197378,0.0028069909,0.0021903347,0.0041737827,0.00088015787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030814618,0.00016323822,0.0009272219,0.00016559979,0.00010047276,0.00019318341,0.00016468554,0.8769278,0.0014016444,0.06944644,0.001865944,0.048335757],"study_design_scores_gemma":[0.000018682382,0.000042099797,0.00008562204,0.000020764352,0.000013362384,0.000024825122,0.000006594383,0.98703706,0.00030667114,0.012183839,0.00024776458,0.000012620295],"about_ca_topic_score_codex":0.0031667736,"about_ca_topic_score_gemma":0.0023172738,"teacher_disagreement_score":0.006882399,"about_ca_system_score_codex":0.0017342295,"about_ca_system_score_gemma":0.0022317881,"threshold_uncertainty_score":0.036398053},"labels":[],"label_agreement":null},{"id":"W1540112079","doi":"10.5555/1402821.1402866","title":"Using adaptive consultation of experts to improve convergence rates in multiagent learning","year":2008,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regret; Computer science; Outcome (game theory); Convergence (economics); Advice (programming); Multi-agent system; Set (abstract data type); Class (philosophy); Nash equilibrium; Process (computing); Frame (networking); Order (exchange); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics","score_opus":0.367641049994208,"score_gpt":0.4650858587974098,"score_spread":0.09744480880320183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540112079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031096574,0.00039992697,0.96445125,0.0004497471,0.00004596952,0.000084128216,0.000013344177,0.00043656072,0.003022467],"genre_scores_gemma":[0.8285431,0.00023609813,0.16747111,0.00036189958,0.00010738085,0.00023762672,0.00004522069,0.000109443834,0.0028881645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583745,0.0024896264,0.00013140577,0.00046597788,0.0007129547,0.00036260023],"domain_scores_gemma":[0.9789094,0.016339006,0.0013206587,0.001009814,0.0018103648,0.00061079947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007607407,0.0014976591,0.0016205142,0.000985935,0.0008360433,0.0009937638,0.002524609,0.002917725,0.0020892604],"category_scores_gemma":[0.03539832,0.0005424902,0.0005965087,0.00061028573,0.0016332499,0.002151028,0.0022077342,0.0020484505,0.0006305589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043567095,0.00019793774,0.0014854402,0.0001096203,0.000082783,0.00019662283,0.0003064837,0.91146815,0.002233562,0.025052205,0.0017885693,0.056642827],"study_design_scores_gemma":[0.000035571607,0.000069496935,0.00007946176,0.000009472387,0.00000817959,0.000023446732,0.000011080289,0.9928461,0.00055864896,0.00606815,0.00028282765,0.000007720306],"about_ca_topic_score_codex":0.0030718162,"about_ca_topic_score_gemma":0.001947578,"teacher_disagreement_score":0.007607407,"about_ca_system_score_codex":0.0012997815,"about_ca_system_score_gemma":0.0012953621,"threshold_uncertainty_score":0.04023224},"labels":[],"label_agreement":null},{"id":"W1545471058","doi":"10.1007/11776420_39","title":"Online Learning with Constraints","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hindsight bias; Convex hull; Computer science; Path (computing); Decision maker; Mathematical optimization; Constraint (computer-aided design); Term (time); Function (biology); Online learning; Regular polygon; Artificial intelligence; Operations research; Mathematics","score_opus":0.05701351581155001,"score_gpt":0.3661818562238235,"score_spread":0.3091683404122735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1545471058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0132522825,0.0019894126,0.9198312,0.0023383538,0.00042432162,0.00009437047,0.0004407896,0.00090708386,0.060722128],"genre_scores_gemma":[0.5463246,0.003028154,0.31988722,0.0011915328,0.0015074587,0.00058851007,0.0021711546,0.0006849204,0.12461648],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990933,0.00029673407,0.000041331772,0.00023859083,0.00024379622,0.00008626679],"domain_scores_gemma":[0.9948177,0.0038155443,0.00015761548,0.0007832924,0.00025864283,0.00016723476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012021317,0.0009909029,0.0012827049,0.0005880326,0.00058133487,0.0018517757,0.0016843781,0.0012706255,0.024856137],"category_scores_gemma":[0.008969364,0.00051182206,0.0005585933,0.0015041886,0.0008693786,0.0041698264,0.0022278458,0.0032150918,0.0033564013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002524607,0.00037217423,0.00071347435,0.0003360533,0.00006948294,0.000103758095,0.00007837572,0.11182284,0.00084346614,0.28833556,0.052713457,0.54435897],"study_design_scores_gemma":[0.000045400167,0.00006581106,0.0002066413,0.00005778452,0.000018105395,0.00007714547,0.000024045485,0.53552467,0.0009890359,0.44946107,0.013516296,0.000013952297],"about_ca_topic_score_codex":0.0009767984,"about_ca_topic_score_gemma":0.0014650535,"teacher_disagreement_score":0.024856137,"about_ca_system_score_codex":0.0008340247,"about_ca_system_score_gemma":0.00097281544,"threshold_uncertainty_score":0.083152115},"labels":[],"label_agreement":null},{"id":"W1564634725","doi":"10.1007/11776420_31","title":"Online Learning with Variable Stage Duration","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic game; Hindsight bias; Regret; Repeated game; Computer science; Minimax; Mathematical economics; Variable (mathematics); Duration (music); Term (time); Game theory; Mathematics; Machine learning; Psychology","score_opus":0.048767061172971984,"score_gpt":0.3533309066974802,"score_spread":0.3045638455245082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564634725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03115441,0.0007100815,0.9611899,0.0005264779,0.00012823388,0.00007693574,0.00014886202,0.0005940954,0.0054710065],"genre_scores_gemma":[0.7549266,0.0007935175,0.2041131,0.00037149887,0.00051464065,0.00042718463,0.00045887378,0.00021848167,0.03817601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986731,0.0004941798,0.000079162615,0.00031896055,0.000218161,0.00021654584],"domain_scores_gemma":[0.9843776,0.012832772,0.00040971275,0.001523027,0.00047792998,0.00037893842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040118727,0.00084800395,0.0020930464,0.00056143996,0.0006130113,0.0012645032,0.0032839538,0.0019973153,0.013737462],"category_scores_gemma":[0.013087016,0.00081673305,0.000911062,0.001262485,0.0011330502,0.005044631,0.002542355,0.0028947638,0.0015783114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001479693,0.00069202826,0.0019251409,0.0003532341,0.00012716038,0.00015012684,0.00020065095,0.3704389,0.002328018,0.19807912,0.00960673,0.41461915],"study_design_scores_gemma":[0.00011260342,0.00017773689,0.00025229726,0.000024612433,0.00003476806,0.000038946815,0.000013981623,0.89552104,0.0009192282,0.10130216,0.0015878923,0.000014643982],"about_ca_topic_score_codex":0.0013832045,"about_ca_topic_score_gemma":0.0018999078,"teacher_disagreement_score":0.013737462,"about_ca_system_score_codex":0.0009860467,"about_ca_system_score_gemma":0.0012951696,"threshold_uncertainty_score":0.045956433},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07238701070652422,"score_gpt":0.3767942946054017,"score_spread":0.3044072838988775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569559301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029044507,0.003939719,0.928767,0.004748536,0.00054131524,0.00017321821,0.0009256622,0.00031321944,0.03154671],"genre_scores_gemma":[0.7191,0.006860525,0.20503126,0.0012880898,0.0014568031,0.0010246874,0.001541207,0.000396917,0.06330045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996908,0.0017719248,0.00011573468,0.0005320534,0.00032051542,0.0003517242],"domain_scores_gemma":[0.9905612,0.007725172,0.00054967415,0.0004374557,0.00036562904,0.0003609378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047004423,0.0017155218,0.003939035,0.0009772601,0.0010247281,0.0053033913,0.0029902502,0.005443001,0.011820064],"category_scores_gemma":[0.019613141,0.0014698985,0.0009585078,0.0025157328,0.0025216173,0.005158297,0.0024157856,0.004058734,0.0019129051],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066790165,0.00017786547,0.0007590573,0.00047935962,0.00017412174,0.00019995673,0.00012298195,0.5955771,0.0005989898,0.3205072,0.020642402,0.060093008],"study_design_scores_gemma":[0.00012966919,0.00006778799,0.00019707845,0.00007036195,0.00003851188,0.00006783429,0.000045652672,0.68704903,0.00021008281,0.30786273,0.0042301705,0.000031153802],"about_ca_topic_score_codex":0.0025620281,"about_ca_topic_score_gemma":0.0017700638,"teacher_disagreement_score":0.011820064,"about_ca_system_score_codex":0.0018399417,"about_ca_system_score_gemma":0.0017862243,"threshold_uncertainty_score":0.03954208},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.07038242003984675,"score_gpt":0.3665795994389151,"score_spread":0.29619717939906837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577851669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023369879,0.0012228672,0.95128673,0.0005648054,0.00017982005,0.000055678403,0.0002591988,0.0011511073,0.021909816],"genre_scores_gemma":[0.8388509,0.0011130956,0.1309347,0.00037366882,0.00048622445,0.00013840945,0.0004996423,0.00029337185,0.027309956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987142,0.00041164143,0.00006903364,0.0002906278,0.00036165075,0.00015273264],"domain_scores_gemma":[0.9960461,0.001926235,0.00028112845,0.001278021,0.00035143772,0.00011697113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483065,0.0009542878,0.0011563496,0.00049368077,0.00042645924,0.0017771841,0.0009943462,0.00093148416,0.0049832435],"category_scores_gemma":[0.005173446,0.00042459473,0.00045832514,0.00068699295,0.0008754348,0.0028449423,0.0015271817,0.001517557,0.0012889827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013588119,0.00013080414,0.001814558,0.0004534155,0.0001523722,0.00044106675,0.0001936265,0.12294293,0.023034202,0.35145676,0.017059373,0.48096216],"study_design_scores_gemma":[0.000048037764,0.0001878523,0.0006321073,0.000064351196,0.000085557724,0.0005259472,0.00002466945,0.6662532,0.016456556,0.3063781,0.009312445,0.00003120724],"about_ca_topic_score_codex":0.00027221118,"about_ca_topic_score_gemma":0.00032676302,"teacher_disagreement_score":0.0049832435,"about_ca_system_score_codex":0.0005329654,"about_ca_system_score_gemma":0.0005500378,"threshold_uncertainty_score":0.016670644},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.22064056196574067,"score_gpt":0.3089465051702611,"score_spread":0.08830594320452045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1675620121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059545455,0.0003564241,0.9877844,0.0003603591,0.00002860172,0.000034532222,0.00006245415,0.0003878042,0.0050309347],"genre_scores_gemma":[0.5788509,0.00078652374,0.40945598,0.00049419014,0.00012820572,0.0003226431,0.00036282765,0.0005076286,0.009091083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99758697,0.0010405754,0.00009419631,0.00034918395,0.0006604984,0.00026858252],"domain_scores_gemma":[0.9954032,0.0030743608,0.00033270405,0.0005963479,0.00042858708,0.0001647361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046681813,0.0014107098,0.0018391932,0.0008274572,0.0008278622,0.0023571162,0.0018562797,0.0014291437,0.004889645],"category_scores_gemma":[0.012230008,0.0009651336,0.0011207088,0.0011684084,0.0017395117,0.0023616124,0.0030570521,0.0030073966,0.0011000292],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013122201,0.000035318466,0.00038803788,0.00010905851,0.00005853738,0.000043995555,0.00006759183,0.85067654,0.0007775985,0.10513931,0.0032318872,0.03934089],"study_design_scores_gemma":[0.0000072666103,0.000012900812,0.00005145906,0.000011013937,0.0000069252965,0.000009889208,0.000007166557,0.97000396,0.00035425072,0.028873602,0.0006553138,0.0000063867487],"about_ca_topic_score_codex":0.0030641393,"about_ca_topic_score_gemma":0.0037930408,"teacher_disagreement_score":0.004889645,"about_ca_system_score_codex":0.0020820412,"about_ca_system_score_gemma":0.0024466745,"threshold_uncertainty_score":0.024687946},"labels":[],"label_agreement":null},{"id":"W169239147","doi":"10.5220/0002712500360044","title":"A GENERIC SOLUTION TO MULTI-ARMED BERNOULLI BANDIT PROBLEMS BASED ON RANDOM SAMPLING FROM SIBLING CONJUGATE PRIORS","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Conjugate prior; Bernoulli's principle; Conjugate; Prior probability; Computer science; Thompson sampling; Sampling (signal processing); Mathematics; Mathematical optimization; Algorithm; Bayesian probability; Artificial intelligence; Engineering; Telecommunications","score_opus":0.20640621805017811,"score_gpt":0.43735276582573485,"score_spread":0.23094654777555673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W169239147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033392862,0.0001274674,0.99390805,0.00025167785,0.000036156736,0.000044662425,0.0000484471,0.00007151849,0.002172663],"genre_scores_gemma":[0.2156515,0.00069822784,0.76959896,0.00040550833,0.00021704126,0.0005197704,0.0003112022,0.00018225082,0.012415455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998357,0.0008854264,0.00007235932,0.00022386445,0.00029462876,0.00016668416],"domain_scores_gemma":[0.9970018,0.0020343256,0.000249098,0.0002510701,0.00029552606,0.000168052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003919045,0.0011231963,0.0018256606,0.0008625992,0.0008245328,0.0018885343,0.0029417833,0.00374816,0.005721272],"category_scores_gemma":[0.013595771,0.0009637484,0.0014291077,0.0016360935,0.0020968544,0.0022671323,0.003208198,0.0025755947,0.0012631094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008793561,0.00006089728,0.00047009822,0.000115459065,0.00007222274,0.000105249164,0.00013779713,0.5782159,0.0007820085,0.3819775,0.003044157,0.034930885],"study_design_scores_gemma":[0.000021641426,0.000015356802,0.000057543508,0.000016172424,0.0000119976785,0.000030986525,0.00001138594,0.9137113,0.00014339738,0.085098684,0.0008703643,0.000011193116],"about_ca_topic_score_codex":0.0020975291,"about_ca_topic_score_gemma":0.0030060988,"teacher_disagreement_score":0.005721272,"about_ca_system_score_codex":0.0010623797,"about_ca_system_score_gemma":0.0023607418,"threshold_uncertainty_score":0.020726144},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3788463044400635,"score_gpt":0.44604060495732645,"score_spread":0.06719430051726294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1838526237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013456968,0.0012880508,0.9745821,0.0011335781,0.00011221691,0.00016903882,0.00042972222,0.00030127156,0.00852709],"genre_scores_gemma":[0.8114837,0.0025971844,0.16189672,0.0009412997,0.00038193635,0.000884904,0.00087871705,0.00022678777,0.020708786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943896,0.0026118902,0.00033459353,0.0012073781,0.00076795585,0.00068864465],"domain_scores_gemma":[0.9790853,0.016715713,0.0021025357,0.0007310982,0.0009920828,0.0003732542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076085445,0.0029725104,0.004515287,0.0012446264,0.00089174294,0.0048983884,0.0032338707,0.0056563537,0.008723812],"category_scores_gemma":[0.023643954,0.0014741373,0.001723929,0.0019886645,0.0029464092,0.003443465,0.0022393698,0.004219184,0.0016620085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016454127,0.00007961082,0.00053630595,0.00016674286,0.000107233565,0.00017377529,0.00007453511,0.8656985,0.0004680108,0.11813543,0.0017092014,0.012686095],"study_design_scores_gemma":[0.000029343626,0.00003186399,0.00009695516,0.00002354811,0.000019078425,0.000021972854,0.000017598242,0.95197666,0.00017375205,0.04699599,0.00059629924,0.000016819029],"about_ca_topic_score_codex":0.0048113414,"about_ca_topic_score_gemma":0.0026224249,"teacher_disagreement_score":0.008723812,"about_ca_system_score_codex":0.0027934771,"about_ca_system_score_gemma":0.0018604596,"threshold_uncertainty_score":0.04023832},"labels":[],"label_agreement":null},{"id":"W1844882231","doi":"10.1007/978-3-540-72606-7_71","title":"Reinforcement Learning-Based Load Shared Sequential Routing","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Learning automata; Reinforcement learning; Static routing; Distributed computing; Destination-Sequenced Distance Vector routing; Routing (electronic design automation); Link-state routing protocol; Dynamic Source Routing; Blocking (statistics); Artificial intelligence; Automaton; Computer network; Routing protocol","score_opus":0.10729862514666907,"score_gpt":0.39573778242917695,"score_spread":0.2884391572825079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1844882231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04556249,0.00025595815,0.9459722,0.0002848196,0.00013543188,0.000085457694,0.000056063127,0.0013119783,0.0063355933],"genre_scores_gemma":[0.9217363,0.00009340254,0.07270938,0.000120035125,0.000057983227,0.00009410862,0.00007735179,0.0001181613,0.0049932143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922633,0.00021245323,0.000037274167,0.00015033442,0.00019916627,0.00017448932],"domain_scores_gemma":[0.99756634,0.0013472629,0.0001980689,0.00027066667,0.0004419298,0.00017573338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015432686,0.0008018604,0.0015687504,0.0005696127,0.0006971981,0.0010593503,0.0024745127,0.00091274333,0.00456534],"category_scores_gemma":[0.0040137838,0.00052154803,0.00038762152,0.00065712584,0.0009396023,0.0012747719,0.0014258545,0.0012973103,0.00056228606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019253328,0.00010005771,0.0002678996,0.000029838298,0.000021147993,0.000025097534,0.000032430955,0.93814903,0.0012680158,0.005276889,0.0015973455,0.05303971],"study_design_scores_gemma":[0.000007900977,0.000013950449,0.000023143819,0.000001191224,0.000002479064,0.0000044031162,0.0000023416353,0.9980094,0.00014965398,0.0017018482,0.00008191772,0.0000018150906],"about_ca_topic_score_codex":0.0064478857,"about_ca_topic_score_gemma":0.0074924426,"teacher_disagreement_score":0.0064478857,"about_ca_system_score_codex":0.0014509285,"about_ca_system_score_gemma":0.0015677746,"threshold_uncertainty_score":0.015272558},"labels":[],"label_agreement":null},{"id":"W1868011046","doi":"","title":"On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oracle; Set (abstract data type); Exploit; Computer science; Quality (philosophy); Mathematical optimization; Identification (biology); Mathematics; Theoretical computer science","score_opus":0.2028115132751566,"score_gpt":0.4445514399849025,"score_spread":0.2417399267097459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1868011046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07247603,0.0006217445,0.92270803,0.0010011034,0.000037630394,0.00016296977,0.00024649486,0.00034048487,0.0024055105],"genre_scores_gemma":[0.83127415,0.00079944823,0.16165744,0.0005667134,0.00018587727,0.0005910154,0.0006009268,0.00018010862,0.004144302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923844,0.004328335,0.000274729,0.0013077664,0.0009382515,0.0007666632],"domain_scores_gemma":[0.8807267,0.10905267,0.0048013497,0.002482181,0.0014280471,0.0015090579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014410293,0.0023800342,0.00456069,0.0017432875,0.001440451,0.0034769813,0.0036947622,0.0043117125,0.0034609379],"category_scores_gemma":[0.06181924,0.0013749099,0.001539405,0.0021270057,0.0072618118,0.008366873,0.0047448506,0.0039112293,0.0004893955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007704703,0.00017807215,0.0017908984,0.00022231249,0.00011105712,0.0002445342,0.00026079977,0.89398086,0.0010266311,0.08331958,0.00072890054,0.017365796],"study_design_scores_gemma":[0.00006115592,0.000096475465,0.0002747851,0.00003524992,0.000019143403,0.000047281435,0.000042410178,0.9000157,0.0005797727,0.098640576,0.0001523201,0.00003513403],"about_ca_topic_score_codex":0.002485255,"about_ca_topic_score_gemma":0.0014075682,"teacher_disagreement_score":0.014410293,"about_ca_system_score_codex":0.002346432,"about_ca_system_score_gemma":0.0019301753,"threshold_uncertainty_score":0.07620978},"labels":[],"label_agreement":null},{"id":"W189728362","doi":"10.1007/978-3-642-40988-2_16","title":"Greedy Confidence Pursuit: A Pragmatic Approach to Multi-bandit Optimization","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Greedy algorithm; Selection (genetic algorithm); Set (abstract data type); Thompson sampling; Mathematical optimization; Baseline (sea); Artificial intelligence; Machine learning; Algorithm; Bayesian probability; Mathematics","score_opus":0.08883393490227826,"score_gpt":0.3708055884183275,"score_spread":0.28197165351604925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W189728362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000675179,0.00017714742,0.99449027,0.00035466976,0.00004858957,0.00001529875,0.000017285585,0.000072256014,0.0041493834],"genre_scores_gemma":[0.13127643,0.0010264545,0.85089874,0.0006852577,0.00043295434,0.0003354761,0.00010712223,0.0003750837,0.0148624955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976822,0.0012636094,0.000082009035,0.00017481166,0.0006956887,0.000101684345],"domain_scores_gemma":[0.9969266,0.0022846276,0.00012981692,0.0002536672,0.00030823596,0.00009708857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003563872,0.001316448,0.0015534748,0.0007855278,0.00087191095,0.0032799528,0.0022209033,0.0025485002,0.0055746413],"category_scores_gemma":[0.01357139,0.0008795086,0.00107754,0.0017501567,0.002710705,0.0023804484,0.0044282856,0.0040170182,0.0014854982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080943304,0.000035842204,0.00015000654,0.00014250362,0.000050071303,0.00007559236,0.00011768277,0.08271133,0.0014186287,0.8536153,0.0066309855,0.05497118],"study_design_scores_gemma":[0.000023776605,0.00003038097,0.00004950586,0.000035221507,0.000015315605,0.000045673743,0.000021371117,0.49872598,0.0005445367,0.4950497,0.0054380912,0.000020449212],"about_ca_topic_score_codex":0.0010290336,"about_ca_topic_score_gemma":0.0012802857,"teacher_disagreement_score":0.0055746413,"about_ca_system_score_codex":0.0010811482,"about_ca_system_score_gemma":0.001445179,"threshold_uncertainty_score":0.018847764},"labels":[],"label_agreement":null},{"id":"W1915057100","doi":"10.1007/978-3-319-11662-4_13","title":"Bayesian Reinforcement Learning with Exploration","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Reinforcement learning; Computer science; Minimax; Sample complexity; Bayesian probability; Class (philosophy); Artificial intelligence; Sample (material); Machine learning; Mathematical optimization; Mathematics","score_opus":0.06435445389814211,"score_gpt":0.3528636545911634,"score_spread":0.28850920069302133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1915057100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042221104,0.0015142598,0.96379495,0.00055694446,0.0001866429,0.000028366063,0.000051383468,0.00035906985,0.029286385],"genre_scores_gemma":[0.54834276,0.0026029465,0.35728094,0.0004719336,0.00050807244,0.00032770232,0.00026751714,0.0003742274,0.089823924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999549,0.00018184354,0.000015924887,0.00007941557,0.00013807973,0.00003569174],"domain_scores_gemma":[0.9991364,0.0006099384,0.000042298663,0.00008407466,0.00008450045,0.000042897624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009557473,0.0007787569,0.0008052648,0.00033086454,0.00026060228,0.00095956813,0.0009706297,0.0010327101,0.009379435],"category_scores_gemma":[0.003842843,0.00041436433,0.00040961336,0.00048770758,0.0008005434,0.0011884477,0.0013165433,0.0019487935,0.0017200534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010415587,0.00008819831,0.00028883954,0.00015230758,0.00005774084,0.000055909502,0.00007004421,0.44475418,0.001306476,0.2554016,0.012653881,0.28506672],"study_design_scores_gemma":[0.000019415635,0.00003479699,0.0000894896,0.000030948526,0.000010927723,0.000035051984,0.000006277957,0.80561745,0.00048638834,0.18758094,0.006076556,0.000011702244],"about_ca_topic_score_codex":0.00094886584,"about_ca_topic_score_gemma":0.0011346423,"teacher_disagreement_score":0.009379435,"about_ca_system_score_codex":0.0006083237,"about_ca_system_score_gemma":0.00061425474,"threshold_uncertainty_score":0.031377375},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3651976247050544,"score_gpt":0.5253249721812989,"score_spread":0.16012734747624452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191658262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02885048,0.0011234034,0.9618438,0.0019561474,0.00007894573,0.00019175229,0.0002126094,0.00035808978,0.005384862],"genre_scores_gemma":[0.748836,0.0011046209,0.24136284,0.0011276269,0.00030690673,0.00075236306,0.0005857764,0.00029038094,0.005633518],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99280167,0.0049873847,0.00020579153,0.00092083344,0.0007448291,0.00033948352],"domain_scores_gemma":[0.9558498,0.03919687,0.001821924,0.0014109544,0.0012650873,0.0004553628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014043852,0.0020739834,0.0035567605,0.001524877,0.00091000233,0.003433095,0.0022801915,0.0030918017,0.004431943],"category_scores_gemma":[0.06357222,0.0011005491,0.00080726354,0.0014870479,0.003861881,0.0046035987,0.0031342367,0.0045417203,0.00089709915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062468037,0.00026056936,0.0036377858,0.00042954338,0.00023628885,0.00020827357,0.00020654834,0.68090606,0.00085453666,0.23024154,0.004810543,0.077583626],"study_design_scores_gemma":[0.00003833509,0.0000758372,0.00026471174,0.000092801936,0.000014534215,0.000034496694,0.000024079796,0.8847965,0.00060870376,0.11335665,0.0006750371,0.000018250272],"about_ca_topic_score_codex":0.0022470849,"about_ca_topic_score_gemma":0.0012440829,"teacher_disagreement_score":0.014043852,"about_ca_system_score_codex":0.002563876,"about_ca_system_score_gemma":0.0025286963,"threshold_uncertainty_score":0.07427186},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2128862204345478,"score_gpt":0.5039623446227086,"score_spread":0.2910761241881608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1917528016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06995278,0.0061402037,0.90683967,0.0022403018,0.00031255945,0.0002665212,0.00080180826,0.0010328331,0.012413398],"genre_scores_gemma":[0.8961424,0.0017979785,0.0923494,0.0008404812,0.000470331,0.0004366832,0.0007244437,0.00012175034,0.00711659],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996253,0.0018018874,0.00017382862,0.00089873525,0.00042074535,0.00045163542],"domain_scores_gemma":[0.9856469,0.0110005345,0.0015248527,0.0007587839,0.0005427259,0.0005261911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040430916,0.0028741006,0.00411194,0.0010012081,0.00089409034,0.0031248468,0.0025994775,0.0035499055,0.0049965396],"category_scores_gemma":[0.017915642,0.0012500659,0.0014454005,0.0014894245,0.0023275143,0.0036558323,0.0027021193,0.0036696277,0.0010901127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045061292,0.00015395008,0.0013428392,0.00027727193,0.00014914852,0.00015199842,0.00008571783,0.91678816,0.00053994654,0.06296613,0.0021446561,0.014949627],"study_design_scores_gemma":[0.000033070864,0.000062258994,0.00012813236,0.000026706055,0.000020291453,0.00001656197,0.000013092889,0.9772296,0.00012835875,0.021811742,0.0005194857,0.000010861107],"about_ca_topic_score_codex":0.004075886,"about_ca_topic_score_gemma":0.003937348,"teacher_disagreement_score":0.0049965396,"about_ca_system_score_codex":0.00185789,"about_ca_system_score_gemma":0.0012378184,"threshold_uncertainty_score":0.021382153},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.13562717372587746,"score_gpt":0.3110003567384468,"score_spread":0.17537318301256932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1931877416","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052593597,0.00016845975,0.9916065,0.00029169762,0.000044757046,0.00005826696,0.00002541655,0.000269988,0.0022755335],"genre_scores_gemma":[0.55318403,0.00038422566,0.4371679,0.0005073092,0.00033757248,0.00053284306,0.0002730712,0.00032267408,0.007290335],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768937,0.00092539634,0.00008111751,0.0005142363,0.00062174053,0.00016807202],"domain_scores_gemma":[0.99339736,0.0050043454,0.00039698728,0.00066060794,0.0003367552,0.00020387735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029313192,0.0013676865,0.0019323197,0.00063297304,0.0005669019,0.0010640718,0.0029348962,0.0020799013,0.00244464],"category_scores_gemma":[0.015899958,0.0007369491,0.0010393636,0.0007185147,0.0021823135,0.0023467243,0.0028028893,0.003679124,0.00063624786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012511492,0.00017387424,0.000651872,0.0001451807,0.00007401779,0.00012205345,0.0001323818,0.813426,0.0013046353,0.11326386,0.0028458515,0.06773507],"study_design_scores_gemma":[0.000011779221,0.000040400413,0.0000675025,0.000007808499,0.000005565972,0.000023888333,0.0000040552936,0.96641815,0.00035956435,0.032544855,0.0005103293,0.0000061393625],"about_ca_topic_score_codex":0.0023237017,"about_ca_topic_score_gemma":0.0017710482,"teacher_disagreement_score":0.0029348962,"about_ca_system_score_codex":0.0013677237,"about_ca_system_score_gemma":0.0018876896,"threshold_uncertainty_score":0.015502453},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04680964409173786,"score_gpt":0.418173190851378,"score_spread":0.3713635467596401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969276875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045028202,0.007226659,0.8873165,0.0063357092,0.00051983265,0.0003280487,0.0016208381,0.0011646614,0.05045956],"genre_scores_gemma":[0.7585099,0.0068838866,0.20517865,0.00250922,0.0012957379,0.0011919447,0.0018725761,0.0010212702,0.021536862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934277,0.0020987585,0.00029918572,0.00095371273,0.0018010491,0.0014196353],"domain_scores_gemma":[0.9427331,0.049183797,0.0014394098,0.0025205119,0.0020557707,0.0020674246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008327335,0.003738836,0.0053035473,0.0034624543,0.002481854,0.009079892,0.004883167,0.0047282414,0.014474662],"category_scores_gemma":[0.05770148,0.002196721,0.0022118895,0.0039134347,0.0038783613,0.013914649,0.0071413456,0.011026454,0.0017568733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006423899,0.0003353945,0.0007585368,0.00069078605,0.00013578912,0.00011156667,0.00024015944,0.6149774,0.00093090895,0.33009556,0.010561384,0.040520158],"study_design_scores_gemma":[0.000039809038,0.0000644892,0.00012586577,0.00013244241,0.000039262748,0.000058858466,0.00005098038,0.69099057,0.0005458053,0.30625242,0.0016750109,0.000024520958],"about_ca_topic_score_codex":0.004809622,"about_ca_topic_score_gemma":0.0068391766,"teacher_disagreement_score":0.014474662,"about_ca_system_score_codex":0.008643851,"about_ca_system_score_gemma":0.008258153,"threshold_uncertainty_score":0.06271583},"labels":[],"label_agreement":null},{"id":"W1978605753","doi":"10.1023/b:josh.0000031422.02125.97","title":"Predictive, Stochastic and Dynamic Extensions to Aversion Dynamics Scheduling","year":2004,"lang":"en","type":"article","venue":"Journal of Scheduling","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Risk aversion (psychology); Computer science; Heuristic; Loss aversion; Schedule; Scheduling (production processes); Operations research; Economics; Microeconomics; Expected utility hypothesis; Operations management; Mathematical economics; Mathematics; Artificial intelligence","score_opus":0.04847535851588778,"score_gpt":0.3939548206699781,"score_spread":0.3454794621540903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978605753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13936995,0.00048785392,0.8431922,0.0018667852,0.00032060107,0.00006225104,0.0001982612,0.00031304924,0.014189129],"genre_scores_gemma":[0.9708694,0.00028795353,0.02191888,0.000112825444,0.00015857298,0.000049009253,0.000085980944,0.00004484938,0.00647244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911326,0.00036596137,0.000029308252,0.0001168252,0.00019877602,0.00017581916],"domain_scores_gemma":[0.9950277,0.003236458,0.00048516135,0.00043179217,0.000492703,0.00032612475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026426744,0.0008163066,0.0010962042,0.00069749483,0.00072147785,0.0019166323,0.0017374454,0.0010294734,0.0044342917],"category_scores_gemma":[0.011751598,0.00059887255,0.0007180383,0.0009441615,0.0013616794,0.00247383,0.00159082,0.0024240897,0.00027193362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086954315,0.00005144528,0.00027305514,0.000019735937,0.000015205398,0.000036407113,0.000042102612,0.89395994,0.0003125751,0.09617038,0.00070349255,0.008328713],"study_design_scores_gemma":[0.0000060552056,0.000011311588,0.00004426635,0.0000018353229,0.0000034880327,0.0000040416808,0.000003964082,0.9803591,0.000047851423,0.019365862,0.00014860644,0.0000036485658],"about_ca_topic_score_codex":0.00694995,"about_ca_topic_score_gemma":0.006387864,"teacher_disagreement_score":0.00694995,"about_ca_system_score_codex":0.0018527595,"about_ca_system_score_gemma":0.0024780768,"threshold_uncertainty_score":0.014834166},"labels":[],"label_agreement":null},{"id":"W1982615629","doi":"10.1109/icassp.2013.6638679","title":"Learning-stage based decentralized adaptive access policy for dynamic spectrum access","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Stage (stratigraphy); Access control; Computer network; Distributed computing","score_opus":0.16316195378576367,"score_gpt":0.5125284662488282,"score_spread":0.3493665124630645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982615629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05111109,0.00021101897,0.9455119,0.0005157828,0.000054325585,0.000108071894,0.00007063136,0.00015856313,0.0022585043],"genre_scores_gemma":[0.96119726,0.00012983716,0.03595635,0.00013204165,0.00007432536,0.0001471989,0.000052347867,0.000022763426,0.0022877587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781513,0.00087765895,0.000060954146,0.00044910712,0.00037537006,0.0004218333],"domain_scores_gemma":[0.99428576,0.0036398706,0.0007216342,0.00029847363,0.0006517827,0.0004024889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002868297,0.000905127,0.0015638906,0.00051108544,0.00063736405,0.0011146123,0.0023275432,0.0017849717,0.0021458534],"category_scores_gemma":[0.008866317,0.00042081502,0.00054569595,0.0007955468,0.0014808353,0.0015828905,0.0014292827,0.0019924946,0.00027659346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026198468,0.00011638379,0.0008389801,0.00006235507,0.000043052274,0.00009485932,0.00007784972,0.9670058,0.0012859234,0.0181234,0.0007992265,0.011290168],"study_design_scores_gemma":[0.000027839746,0.000051446837,0.000101946476,0.0000021974704,0.0000060688394,0.000017175355,0.0000074149493,0.994269,0.00019459358,0.005188373,0.00012865616,0.0000053122094],"about_ca_topic_score_codex":0.00334993,"about_ca_topic_score_gemma":0.002464466,"teacher_disagreement_score":0.00334993,"about_ca_system_score_codex":0.0016891893,"about_ca_system_score_gemma":0.0019227793,"threshold_uncertainty_score":0.015169203},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Logarithm; Minimax; Mathematics; Outcome (game theory); Action (physics); Mathematical optimization; Mathematical economics; Statistics; Psychology","score_opus":0.43992274550270394,"score_gpt":0.5509132329952277,"score_spread":0.11099048749252372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987292194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02582207,0.0050172564,0.95231384,0.0037233755,0.00018449254,0.00016414443,0.00045066964,0.0006333352,0.011690786],"genre_scores_gemma":[0.6856772,0.0050268555,0.29094887,0.0017172091,0.0014989409,0.0011403108,0.0012065856,0.00048356465,0.012300485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913235,0.003989917,0.00037192105,0.0016241622,0.001770831,0.00091973646],"domain_scores_gemma":[0.9554811,0.035094652,0.003069885,0.0037954864,0.0014880032,0.0010708388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011444367,0.002626846,0.0034250356,0.0015939882,0.0014332017,0.0048514213,0.004305751,0.0032178222,0.0049651326],"category_scores_gemma":[0.05788539,0.001160502,0.0016546038,0.0026800628,0.0040021366,0.009273909,0.004386414,0.006341457,0.00094651594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005835444,0.0003523251,0.003884411,0.00045774542,0.00019851797,0.000099326695,0.00022145119,0.55419147,0.0010015725,0.322349,0.010395774,0.10626486],"study_design_scores_gemma":[0.000032909404,0.00006994815,0.00039501814,0.000053720796,0.000024690915,0.00005182118,0.000018350971,0.75265044,0.0003491156,0.245223,0.0011146622,0.000016382886],"about_ca_topic_score_codex":0.0022412476,"about_ca_topic_score_gemma":0.0016677076,"teacher_disagreement_score":0.011444367,"about_ca_system_score_codex":0.0044873473,"about_ca_system_score_gemma":0.0025551247,"threshold_uncertainty_score":0.060524285},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; 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","score_opus":0.043294788994366507,"score_gpt":0.3667983632348631,"score_spread":0.3235035742404966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000850397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12285841,0.0020570876,0.8580876,0.0033811913,0.00021574227,0.00014737439,0.00062877435,0.00092299824,0.011700769],"genre_scores_gemma":[0.9591931,0.0009523226,0.028895041,0.00040305,0.00020168412,0.00026563744,0.00031108005,0.00009605486,0.009681872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967272,0.0012634386,0.00011830602,0.00065258855,0.00045482814,0.0007835754],"domain_scores_gemma":[0.982404,0.013975657,0.0016360146,0.00054679083,0.00070300116,0.00073452236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004397803,0.0019074704,0.0027783702,0.00089376915,0.0010409064,0.0027152346,0.001928173,0.0031836336,0.004407706],"category_scores_gemma":[0.017796569,0.0010398894,0.0009970801,0.0013202148,0.0027569158,0.0034902506,0.0024380635,0.0033582984,0.00083953835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003541121,0.00010273917,0.0008616457,0.00010980547,0.000051706338,0.00023831235,0.000108241744,0.86238456,0.00035961173,0.12689488,0.0014000763,0.0071343114],"study_design_scores_gemma":[0.000031766176,0.000022541753,0.00008265184,0.0000081026665,0.000007741083,0.000014025007,0.00000776558,0.95989263,0.00008974151,0.0396424,0.00019242856,0.000008260498],"about_ca_topic_score_codex":0.010919067,"about_ca_topic_score_gemma":0.0066958666,"teacher_disagreement_score":0.010919067,"about_ca_system_score_codex":0.003941219,"about_ca_system_score_gemma":0.0022856318,"threshold_uncertainty_score":0.028595686},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08329802728424093,"score_gpt":0.39703393465733616,"score_spread":0.3137359073730952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009482316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009507146,0.00011745351,0.98908806,0.0002513666,0.000016982991,0.00014986629,0.000018289098,0.00010225639,0.0007486765],"genre_scores_gemma":[0.42421728,0.00021581605,0.57187104,0.0002679021,0.000088849745,0.001249252,0.000092860115,0.00011217381,0.0018847443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.971068,0.024446465,0.00051816914,0.0015872065,0.0018248166,0.00055526866],"domain_scores_gemma":[0.9534027,0.039933946,0.0027760947,0.0018736013,0.0015863077,0.00042739516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029110024,0.0013322002,0.0026736162,0.001608742,0.00051716843,0.0015746325,0.0027345445,0.0016915101,0.005862962],"category_scores_gemma":[0.09817887,0.0008513648,0.0011330227,0.0014931408,0.0035818762,0.002457362,0.0025239212,0.0018556126,0.00070605223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072472787,0.00024244028,0.0015197563,0.00021339119,0.0002580211,0.0001700179,0.00019703245,0.6068093,0.0011757544,0.27986377,0.0013574808,0.10746817],"study_design_scores_gemma":[0.00016575555,0.00014343401,0.00033715277,0.000026825373,0.000027806562,0.000050339753,0.000019808784,0.88670725,0.000733173,0.11118791,0.0005791203,0.000021353544],"about_ca_topic_score_codex":0.0015939418,"about_ca_topic_score_gemma":0.0009541265,"teacher_disagreement_score":0.029110024,"about_ca_system_score_codex":0.0019844868,"about_ca_system_score_gemma":0.002753127,"threshold_uncertainty_score":0.1539504},"labels":[],"label_agreement":null},{"id":"W2015102477","doi":"10.1109/spawc.2013.6612026","title":"Decentralized spectrum learning and access adaptive to channel availability distribution in primary network","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Channel (broadcasting); Computer science; Closeness; Distribution (mathematics); Range (aeronautics); Computer network; Distributed computing; Artificial intelligence; Mathematics; Engineering","score_opus":0.07890080798694213,"score_gpt":0.3996474952581169,"score_spread":0.3207466872711747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015102477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06795345,0.00019532134,0.9299109,0.00021020992,0.000033588552,0.000051865434,0.000027698365,0.00026814893,0.0013487756],"genre_scores_gemma":[0.97264785,0.000076432865,0.026329644,0.000059446724,0.000043635024,0.000041415256,0.000015497684,0.000015690059,0.00077050086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742824,0.0007754096,0.0000977103,0.0006935953,0.00060716446,0.0003978515],"domain_scores_gemma":[0.9917848,0.0046953904,0.0011201338,0.00094679947,0.0010647132,0.00038821218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026436637,0.00056569773,0.0012741267,0.0005093718,0.00074452616,0.0011159574,0.0017239494,0.00080375804,0.0009981095],"category_scores_gemma":[0.010021288,0.0004118375,0.00034202874,0.00075199973,0.0015882909,0.0017174965,0.0014192543,0.0012540282,0.00021194294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002165767,0.000109082146,0.0014306118,0.00006684064,0.000034824043,0.0001219318,0.00014290947,0.94127667,0.005445086,0.013878547,0.00053212204,0.036744736],"study_design_scores_gemma":[0.000012812196,0.000041751635,0.00015452433,0.000001836578,0.000004707917,0.00003453129,0.000009077698,0.99415296,0.0007872556,0.004654633,0.00014005756,0.000005873083],"about_ca_topic_score_codex":0.0025731556,"about_ca_topic_score_gemma":0.0019962995,"teacher_disagreement_score":0.0026436637,"about_ca_system_score_codex":0.0012886506,"about_ca_system_score_gemma":0.0017064713,"threshold_uncertainty_score":0.0139811635},"labels":[],"label_agreement":null},{"id":"W2020216268","doi":"10.1109/spawc.2014.6941869","title":"Distributed stochastic learning for dynamic spectrum access adaptive to primary network conditions","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Cognitive radio; Learning automata; Channel (broadcasting); Set (abstract data type); Collision; Distributed computing; Computer network; Adaptive learning; Selection (genetic algorithm); Automaton; Machine learning; Artificial intelligence; Computer security; Telecommunications; Wireless","score_opus":0.08252314095925892,"score_gpt":0.44043246196883157,"score_spread":0.3579093210095726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020216268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042670347,0.00017547421,0.95493627,0.0003983798,0.00004741191,0.000058150592,0.00004875253,0.000225899,0.0014394169],"genre_scores_gemma":[0.9745394,0.0001387032,0.02328751,0.00011211049,0.00004503579,0.00014094968,0.00004897749,0.000026096079,0.0016611931],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864346,0.00039115618,0.000065407236,0.0003638519,0.00027389178,0.0002622297],"domain_scores_gemma":[0.993471,0.0046829237,0.0007218692,0.00026010512,0.000622243,0.0002418592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002341747,0.00089307915,0.0015605956,0.000588987,0.0006290876,0.0012175802,0.0015175742,0.0011956242,0.001816899],"category_scores_gemma":[0.010698577,0.00055346056,0.00060153916,0.00058621535,0.0017831052,0.00129138,0.001356834,0.0015946233,0.00023026904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050404822,0.000034716315,0.0005316889,0.000025691948,0.000023655848,0.00004594934,0.00004289874,0.9824923,0.00053978554,0.0097953575,0.00019069461,0.0062268428],"study_design_scores_gemma":[0.0000073804677,0.000011840126,0.000048787195,0.00000147376,0.0000032199612,0.0000055427645,0.000003448099,0.99599576,0.00009599712,0.0037774465,0.000046260353,0.000002894801],"about_ca_topic_score_codex":0.006047485,"about_ca_topic_score_gemma":0.004772628,"teacher_disagreement_score":0.006047485,"about_ca_system_score_codex":0.0018263002,"about_ca_system_score_gemma":0.0017662194,"threshold_uncertainty_score":0.013250828},"labels":[],"label_agreement":null},{"id":"W2022938204","doi":"10.1142/s0218488508005364","title":"PORTFOLIO SELECTION AND ONLINE LEARNING","year":2008,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Portfolio; Universalization; Computer science; Selection (genetic algorithm); Markov chain; Investment strategy; Econometrics; Stock market; Mathematical optimization; Work (physics); Cover (algebra); Economics; Financial economics; Artificial intelligence; Mathematics; Machine learning; Microeconomics; Engineering","score_opus":0.09085081597946684,"score_gpt":0.40544625715843874,"score_spread":0.31459544117897187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022938204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020676946,0.0023595556,0.96881247,0.0010435848,0.0000924232,0.00004418708,0.000060216913,0.00015651733,0.0067541474],"genre_scores_gemma":[0.870512,0.0025752548,0.117355816,0.00057503616,0.0005823477,0.00018593353,0.0001680287,0.00006604302,0.007979388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973757,0.0011438965,0.00011532634,0.00056936947,0.0005868999,0.00020876809],"domain_scores_gemma":[0.99007297,0.00775305,0.00072103005,0.00068861264,0.0005371217,0.00022721704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034898838,0.0011242095,0.0015041664,0.0009362913,0.00048004868,0.0019419731,0.0014789215,0.0016608387,0.0030755629],"category_scores_gemma":[0.017702669,0.0003758076,0.0005500427,0.0013689988,0.0021131258,0.0039254627,0.0016394397,0.0015880278,0.0004327614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117827425,0.00014237607,0.0021404522,0.00019645986,0.00013743115,0.00011696088,0.000116689705,0.32338947,0.0009604398,0.51460814,0.0024182028,0.15565553],"study_design_scores_gemma":[0.000026866537,0.00008111065,0.00027690642,0.000032183445,0.0000184058,0.00006057726,0.00001846931,0.73033625,0.00071675744,0.2661508,0.00226726,0.000014356245],"about_ca_topic_score_codex":0.0011925646,"about_ca_topic_score_gemma":0.0007844951,"teacher_disagreement_score":0.0034898838,"about_ca_system_score_codex":0.0014071133,"about_ca_system_score_gemma":0.00093079,"threshold_uncertainty_score":0.018456459},"labels":[],"label_agreement":null},{"id":"W2024490033","doi":"10.1007/s001860300295","title":"One-armed bandit models with continuous and delayed responses","year":2003,"lang":"en","type":"article","venue":"Mathematical Methods of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Manitoba","funders":"","keywords":"Multi-armed bandit; Monotonic function; Markov decision process; Sequence (biology); Optimal stopping; Markov process; Mathematical optimization; Limit (mathematics); Index (typography); Bayesian probability; Markov chain; Mathematics; Time horizon; Computer science; Statistics","score_opus":0.5018446804662678,"score_gpt":0.6032521031918505,"score_spread":0.10140742272558267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024490033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12206946,0.0025874553,0.86217684,0.0031730642,0.00039218785,0.00028424017,0.0012395935,0.0005759908,0.007501136],"genre_scores_gemma":[0.9274741,0.0021327597,0.040588442,0.00060439203,0.0005329564,0.0008393444,0.0008126536,0.00008760778,0.026927834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920358,0.0046268594,0.00037597324,0.0014069763,0.0004922775,0.001062166],"domain_scores_gemma":[0.9318902,0.05793292,0.005233355,0.0022040487,0.0019335699,0.0008060219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013348294,0.0038201115,0.0076362775,0.0018231441,0.0013606178,0.0072531197,0.0053880727,0.009102272,0.008731729],"category_scores_gemma":[0.04281554,0.0024309717,0.002286056,0.0029629446,0.005125827,0.0070604347,0.0032557454,0.005994548,0.002449199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007072025,0.00018765502,0.0016448487,0.00023604785,0.00028707852,0.00029934442,0.00020640361,0.8491155,0.00028369023,0.13739851,0.001573299,0.008060481],"study_design_scores_gemma":[0.00012978545,0.00009363299,0.0002462106,0.000034330475,0.00009309856,0.00003867071,0.000054967408,0.9436342,0.00014227023,0.055105515,0.00037875897,0.000048506947],"about_ca_topic_score_codex":0.0058991946,"about_ca_topic_score_gemma":0.003891337,"teacher_disagreement_score":0.013348294,"about_ca_system_score_codex":0.0024225484,"about_ca_system_score_gemma":0.001336567,"threshold_uncertainty_score":0.07059336},"labels":[],"label_agreement":null},{"id":"W2030136720","doi":"10.1016/j.jspi.2004.01.022","title":"Evaluation of asymptotic approximations for a two-stage Bernoulli bandit","year":2004,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Bernoulli's principle; Bayes' theorem; Applied mathematics; Bernoulli trial; Bayesian probability; Optimal stopping; Mathematical optimization; Approximations of π; Stage (stratigraphy); Mathematical economics; Statistics","score_opus":0.27833213208247826,"score_gpt":0.5350748650473813,"score_spread":0.2567427329649031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030136720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03180876,0.0011920496,0.96063226,0.0006201023,0.000086972796,0.00013670912,0.00015722912,0.0005642471,0.0048017157],"genre_scores_gemma":[0.55248255,0.0014948956,0.43704608,0.00041073438,0.00023174094,0.0006718205,0.0008561444,0.0005578739,0.0062481356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932422,0.0042393096,0.00023175178,0.00046046267,0.0012824121,0.00054384937],"domain_scores_gemma":[0.8657174,0.12344533,0.00209616,0.003526527,0.0043742945,0.0008402274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024949357,0.0015664413,0.0029149018,0.0018317193,0.001133494,0.0038924075,0.00398539,0.0034795746,0.007501281],"category_scores_gemma":[0.12302243,0.0014992559,0.0013079017,0.0023784293,0.002965164,0.0046566324,0.0033652163,0.0040028533,0.0011791498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079219457,0.00014409045,0.0024553672,0.00028085292,0.00013320902,0.00013721973,0.00022859522,0.8475604,0.0006072755,0.1066747,0.0016060807,0.039379984],"study_design_scores_gemma":[0.00003596288,0.000047380905,0.00024838632,0.000052047475,0.000026459897,0.00004005534,0.000034163855,0.98139876,0.00028745743,0.017478203,0.00033779314,0.000013370416],"about_ca_topic_score_codex":0.009604538,"about_ca_topic_score_gemma":0.0071599577,"teacher_disagreement_score":0.024949357,"about_ca_system_score_codex":0.0036736887,"about_ca_system_score_gemma":0.004906991,"threshold_uncertainty_score":0.13194638},"labels":[],"label_agreement":null},{"id":"W2037905382","doi":"10.1007/s10994-006-0219-y","title":"Online calibrated forecasts: Memory efficiency versus universality for learning in games","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Army Research Office; Air Force Office of Scientific Research; Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Fictitious play; Regret; Repeated game; Computer science; Nash equilibrium; Best response; Universality (dynamical systems); Artificial intelligence; Mathematics; Mathematical optimization; Game theory; Mathematical economics; Machine learning","score_opus":0.08089650883186325,"score_gpt":0.4011498157716262,"score_spread":0.32025330693976295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037905382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16151768,0.00071509735,0.8291195,0.00199173,0.000117498676,0.00008976673,0.00020089417,0.00052274374,0.00572511],"genre_scores_gemma":[0.9607141,0.000454222,0.036517113,0.00022264107,0.00015673437,0.000085384934,0.00013867118,0.0000855535,0.0016254226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964271,0.0014994782,0.0002643893,0.00089993665,0.00045841583,0.0004506722],"domain_scores_gemma":[0.92169386,0.06099594,0.0045007393,0.009595219,0.00228202,0.00093222986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011310367,0.0013631339,0.0027936897,0.0012533165,0.00081471825,0.0034688509,0.0030593579,0.0026742318,0.0047833556],"category_scores_gemma":[0.10501842,0.000962733,0.00095942325,0.0010568625,0.0027800049,0.012651963,0.0032715,0.0042154198,0.00047404587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008053826,0.00029713003,0.007166443,0.00029131758,0.0002905363,0.00015430957,0.00043036893,0.50280744,0.001290538,0.3799181,0.0030063295,0.10354208],"study_design_scores_gemma":[0.000055396227,0.00007852103,0.001136813,0.000043981498,0.000043619635,0.000043455046,0.000052605938,0.6946536,0.0009178139,0.3025563,0.00038623466,0.00003162806],"about_ca_topic_score_codex":0.0022553597,"about_ca_topic_score_gemma":0.0023923784,"teacher_disagreement_score":0.011310367,"about_ca_system_score_codex":0.0016331271,"about_ca_system_score_gemma":0.001630426,"threshold_uncertainty_score":0.059815645},"labels":[],"label_agreement":null},{"id":"W2038683608","doi":"10.1287/opre.1110.0922","title":"A Unified Framework for Dynamic Prediction Market Design","year":2011,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Computer science; Mathematical optimization; Bidding; Function (biology); Mechanism design; Bounded function; Convex optimization; Bellman equation; Regular polygon; Mathematical economics; Economics; Mathematics; Microeconomics","score_opus":0.558322727140912,"score_gpt":0.5555112619072152,"score_spread":0.002811465233696797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038683608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010685488,0.0001509713,0.99525744,0.00024164704,0.000024611192,0.00004661906,0.00003212863,0.000053541815,0.003124522],"genre_scores_gemma":[0.2904593,0.0014967732,0.69497216,0.00041017274,0.00029703917,0.0008205947,0.00023707247,0.00013951758,0.011167215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975171,0.0010123639,0.00013694957,0.00039238099,0.00070996495,0.00023126989],"domain_scores_gemma":[0.9983797,0.0006756514,0.00017520419,0.00028011517,0.00037266943,0.00011664204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045108483,0.001424085,0.0013142658,0.0008390353,0.0006788051,0.003289316,0.002974119,0.0018359876,0.00700053],"category_scores_gemma":[0.0053158877,0.00082058244,0.0013810378,0.0010620838,0.002135337,0.003970348,0.002304076,0.0031894054,0.000908704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022007554,0.000041362546,0.0001051168,0.00006292274,0.000022605293,0.00006350982,0.000049070735,0.1715633,0.000795726,0.8086826,0.0015069246,0.01708479],"study_design_scores_gemma":[0.000029125522,0.000054809665,0.000044991655,0.0000238186,0.000013214573,0.000045582296,0.000018411592,0.65563196,0.00037693273,0.33771497,0.0060294834,0.000016790264],"about_ca_topic_score_codex":0.0016916436,"about_ca_topic_score_gemma":0.0018754944,"teacher_disagreement_score":0.00700053,"about_ca_system_score_codex":0.0020439823,"about_ca_system_score_gemma":0.0032148932,"threshold_uncertainty_score":0.023855925},"labels":[],"label_agreement":null},{"id":"W2038708756","doi":"10.1016/j.orl.2010.09.006","title":"Weak aggregating algorithm for the distribution-free perishable inventory problem","year":2010,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical optimization; Class (philosophy); Parametric statistics; Computer science; Distribution (mathematics); Mathematics; Algorithm; Artificial intelligence; Statistics","score_opus":0.1251349721004983,"score_gpt":0.4507296444040477,"score_spread":0.32559467230354944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038708756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019519677,0.0001755217,0.9767513,0.0003937822,0.000065140775,0.000071940936,0.00007248644,0.00020923461,0.0027409068],"genre_scores_gemma":[0.38364545,0.00048505812,0.6029009,0.0003824346,0.00023519379,0.0005928287,0.0005151145,0.00020169117,0.011041256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783915,0.0010260064,0.00014202697,0.00027762962,0.0004126568,0.00030256034],"domain_scores_gemma":[0.9921407,0.005305879,0.00043555087,0.0008884085,0.00084726134,0.00038209354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006519095,0.001500407,0.002865981,0.0015190438,0.0013419962,0.0029304412,0.0035656637,0.002332781,0.004628923],"category_scores_gemma":[0.01260618,0.00077461003,0.0011153118,0.002712616,0.0014666364,0.004497154,0.0035747457,0.0032874357,0.0009981024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095838134,0.0004407753,0.0016380649,0.00034088487,0.00017539572,0.00012707399,0.000409008,0.5117975,0.002753992,0.22702682,0.007862621,0.24646954],"study_design_scores_gemma":[0.00006079722,0.00008223331,0.0001395945,0.000017410095,0.00002720335,0.00003162751,0.000027988373,0.9018146,0.00063352403,0.09628325,0.00086959323,0.000012294215],"about_ca_topic_score_codex":0.001547847,"about_ca_topic_score_gemma":0.0013936774,"teacher_disagreement_score":0.006519095,"about_ca_system_score_codex":0.0014501839,"about_ca_system_score_gemma":0.002466869,"threshold_uncertainty_score":0.034476697},"labels":[],"label_agreement":null},{"id":"W204541363","doi":"","title":"Online Learning with Global Cost Functions","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Mathematical optimization; Job shop scheduling; Computer science; Scheduling (production processes); Function (biology); Decision maker; Norm (philosophy); Operations research; Mathematics; Machine learning; Schedule","score_opus":0.11747433322981686,"score_gpt":0.4665678340823299,"score_spread":0.349093500852513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W204541363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022507342,0.00037162163,0.9732891,0.00049304904,0.00004320888,0.000056063174,0.00008494392,0.00026876185,0.0028859787],"genre_scores_gemma":[0.8225779,0.0005621068,0.16782135,0.0003523912,0.00016985045,0.00040742167,0.0003184945,0.00012891913,0.0076615736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983746,0.0006954297,0.00006877509,0.00035372833,0.00025584135,0.0002515806],"domain_scores_gemma":[0.9937411,0.0045599206,0.00045945466,0.0005050268,0.00046825036,0.0002662916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034077521,0.0021526825,0.0021815526,0.00064258196,0.00047982222,0.0019592266,0.001986303,0.0019698134,0.0043214],"category_scores_gemma":[0.011046163,0.0005256139,0.0006895689,0.00097342173,0.0017287453,0.00372266,0.002159218,0.0024245405,0.00063661335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013954392,0.00008198632,0.0004059947,0.00006912393,0.000033969896,0.000057807283,0.000024675306,0.9574476,0.00027993778,0.019064827,0.0007426528,0.021651886],"study_design_scores_gemma":[0.00001445573,0.000037651684,0.000040520412,0.000005478217,0.000006336301,0.000009382244,0.000005962062,0.98699147,0.0001868864,0.012518645,0.00017912457,0.000004014046],"about_ca_topic_score_codex":0.0023434935,"about_ca_topic_score_gemma":0.0018222011,"teacher_disagreement_score":0.0043214,"about_ca_system_score_codex":0.001580827,"about_ca_system_score_gemma":0.0013981028,"threshold_uncertainty_score":0.01802212},"labels":[],"label_agreement":null},{"id":"W2059995471","doi":"10.3182/20140824-6-za-1003.01866","title":"Fast Distributed Strategic Learning for Global Optima in Queueing Access Games","year":2014,"lang":"en","type":"article","venue":"IFAC Proceedings Volumes","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Stochastic game; Computer science; Queueing theory; Queue; Convergence (economics); Mathematical optimization; Stochastic approximation; Graph; Q-learning; Reinforcement learning; Theoretical computer science; Artificial intelligence; Mathematics; Asynchronous communication; Mathematical economics","score_opus":0.10372407585180725,"score_gpt":0.4312016915104807,"score_spread":0.32747761565867345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059995471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04941371,0.0005426056,0.9404758,0.0014012004,0.00016527914,0.00016483429,0.00011833153,0.00036777626,0.007350504],"genre_scores_gemma":[0.883385,0.00060084544,0.10265983,0.00063817884,0.00027103876,0.00056073227,0.00026682043,0.00029675552,0.011320834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974394,0.0012171755,0.00010036414,0.00033466023,0.00036576364,0.000542713],"domain_scores_gemma":[0.95704114,0.038259886,0.001002866,0.0010909408,0.0013288287,0.0012764063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008669077,0.002570977,0.004513984,0.0021869307,0.0018561453,0.0031923887,0.0039011494,0.0036515237,0.009191371],"category_scores_gemma":[0.04175086,0.0017489234,0.0016257052,0.0017208454,0.0049882443,0.0060359393,0.0064317947,0.0065667,0.0008092892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041208774,0.00014415622,0.00047998852,0.00015241999,0.000065467124,0.00005957962,0.00014282856,0.88120025,0.00043904476,0.098440476,0.0025060165,0.01595763],"study_design_scores_gemma":[0.00004600308,0.000024212623,0.000036705576,0.000009143043,0.00000873885,0.000005930362,0.000014229414,0.94241095,0.00007949438,0.057268906,0.00008929069,0.000006357746],"about_ca_topic_score_codex":0.0074558784,"about_ca_topic_score_gemma":0.007685102,"teacher_disagreement_score":0.009191371,"about_ca_system_score_codex":0.0034739063,"about_ca_system_score_gemma":0.0049625863,"threshold_uncertainty_score":0.045847},"labels":[],"label_agreement":null},{"id":"W2066996533","doi":"10.1007/s10463-013-0401-5","title":"One-armed bandit process with a covariate","year":2013,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Manitoba","funders":"","keywords":"Covariate; Mathematics; Conjugate prior; Bayesian probability; Statistics; Sequence (biology); Econometrics; Variance (accounting); Stochastic game; Monotonic function; Prior probability; Regression; Mathematical economics","score_opus":0.26697745204278833,"score_gpt":0.46407051248974257,"score_spread":0.19709306044695424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066996533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067853965,0.0010027654,0.9201416,0.0039220257,0.0003715384,0.0003080714,0.0015523656,0.000926959,0.0039207903],"genre_scores_gemma":[0.84565324,0.0018100959,0.11506613,0.001039512,0.0012062542,0.0012867203,0.0017319163,0.00015011553,0.03205598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901951,0.0057099117,0.00040327545,0.0022310535,0.0006302324,0.00083047355],"domain_scores_gemma":[0.9518454,0.034902778,0.0043783565,0.0059864903,0.002144009,0.00074300496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017860763,0.0026093842,0.006971971,0.0018961484,0.0017610624,0.0057594436,0.005115889,0.009027106,0.010271981],"category_scores_gemma":[0.046741907,0.0020740347,0.002708051,0.0028440766,0.005098258,0.0068839793,0.0036349192,0.006613651,0.0044352324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026147624,0.00068144745,0.008877424,0.000563985,0.00058994215,0.00078348443,0.0004982487,0.42050672,0.0018442209,0.5100072,0.0076302807,0.045402277],"study_design_scores_gemma":[0.00032303715,0.00024909488,0.0013165011,0.00008870823,0.00024081476,0.000120587734,0.00006619792,0.8700044,0.0006723654,0.12474043,0.0020853814,0.000092435606],"about_ca_topic_score_codex":0.0030080331,"about_ca_topic_score_gemma":0.0023476991,"teacher_disagreement_score":0.017860763,"about_ca_system_score_codex":0.0017409166,"about_ca_system_score_gemma":0.0018143015,"threshold_uncertainty_score":0.094457805},"labels":[],"label_agreement":null},{"id":"W2068420430","doi":"10.1002/asmb.823","title":"Optimal investment and consumption with stochastic dividends","year":2009,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Dividend; Consumption (sociology); Economics; Poisson distribution; Investment (military); Econometrics; Investment strategy; Rate of return; Financial market; Mathematical economics; Microeconomics; Actuarial science; Mathematics; Finance; Statistics","score_opus":0.10484829443400571,"score_gpt":0.35823646907277057,"score_spread":0.25338817463876484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068420430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46449816,0.0009805114,0.5113976,0.0034053524,0.00008553612,0.00011715922,0.00028765082,0.00016251419,0.01906554],"genre_scores_gemma":[0.97363585,0.000359405,0.018941743,0.000108228334,0.000040110415,0.00008402826,0.00010460319,0.000029413462,0.006696622],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992304,0.0003553564,0.00003588491,0.00011140522,0.00012074507,0.00014618978],"domain_scores_gemma":[0.99763584,0.0016791369,0.000285797,0.00010185237,0.00014889584,0.00014848406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022314633,0.0006280877,0.0011862993,0.0006119273,0.0003219343,0.0019513208,0.0006536193,0.0013196669,0.0033696955],"category_scores_gemma":[0.009715604,0.0006622678,0.00048684046,0.0006805933,0.0014245693,0.0020756214,0.0007555773,0.00085493724,0.00025982896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001980597,0.00008420604,0.0011453539,0.00006718076,0.000049304577,0.0001179563,0.0000652923,0.73985595,0.0005871612,0.24761195,0.0010814884,0.009136061],"study_design_scores_gemma":[0.00003737838,0.000030605257,0.00031915383,0.000013434636,0.000013377793,0.000014603255,0.00002999361,0.913328,0.00031695538,0.08551799,0.0003691693,0.000009318279],"about_ca_topic_score_codex":0.0038198938,"about_ca_topic_score_gemma":0.0021180331,"teacher_disagreement_score":0.0038198938,"about_ca_system_score_codex":0.0021597422,"about_ca_system_score_gemma":0.0012515074,"threshold_uncertainty_score":0.01567012},"labels":[],"label_agreement":null},{"id":"W2069281427","doi":"10.1109/iccchina.2012.6356916","title":"Distributed opportunistic spectrum access with unknown population","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Cognitive radio; Regret; Population; Channel (broadcasting); Online learning; Computer network; Bernoulli's principle; Throughput; Distributed computing; Machine learning; Telecommunications; Wireless; Engineering","score_opus":0.2369926352547683,"score_gpt":0.4832749232261946,"score_spread":0.2462822879714263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069281427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12875861,0.00017559092,0.8672857,0.0005900759,0.00004168089,0.00008900068,0.00008989165,0.0002160147,0.0027534522],"genre_scores_gemma":[0.9753523,0.00008131051,0.022539318,0.00008747386,0.000042775155,0.00010851533,0.000042056403,0.000011384891,0.0017349261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832755,0.0006251441,0.000042500957,0.0003671969,0.00031779893,0.0003198882],"domain_scores_gemma":[0.99490994,0.0032876797,0.0007905141,0.00043144205,0.00034865265,0.0002317443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022898535,0.00067451183,0.0014152102,0.0004544036,0.0006706106,0.0012242566,0.0019974967,0.0011715523,0.00096620497],"category_scores_gemma":[0.008253222,0.0005414864,0.0005646319,0.00067125354,0.001386518,0.0016389661,0.001707674,0.0010947733,0.0001678815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013126891,0.00006451859,0.0014880422,0.000026581474,0.000039091396,0.00020541385,0.000069198206,0.97296685,0.0009066738,0.014625488,0.00038178233,0.009095066],"study_design_scores_gemma":[0.000016490378,0.000019732295,0.00015147026,0.0000014751791,0.0000048394545,0.0000270547,0.000010035379,0.99423933,0.00013387117,0.0052751196,0.00011618225,0.000004482299],"about_ca_topic_score_codex":0.004141885,"about_ca_topic_score_gemma":0.0032561691,"teacher_disagreement_score":0.004141885,"about_ca_system_score_codex":0.0013805677,"about_ca_system_score_gemma":0.0010041584,"threshold_uncertainty_score":0.012109995},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; 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","score_opus":0.16040752224704838,"score_gpt":0.4127314576545998,"score_spread":0.2523239354075514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073384958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015868027,0.0039642877,0.9395554,0.0006565573,0.00065561227,0.000040914187,0.00011632669,0.0010065988,0.05241738],"genre_scores_gemma":[0.20618711,0.005526741,0.6102038,0.0007931858,0.0012270431,0.0006069793,0.00083494844,0.00092255254,0.1736977],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996834,0.000083503,0.00001548262,0.00007871607,0.00011156867,0.000027338314],"domain_scores_gemma":[0.99957556,0.00022825433,0.000019603864,0.0000903739,0.00006854667,0.000017672552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052360096,0.0013226464,0.0011101316,0.00055232464,0.00044572566,0.0014850271,0.0011139229,0.0011648062,0.021057546],"category_scores_gemma":[0.0022019332,0.0004421466,0.0005456653,0.00091088016,0.0009849702,0.0016812043,0.0010756038,0.0024619878,0.006246857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040859493,0.000054885702,0.00017564949,0.00014241754,0.00004752535,0.0000453638,0.00006346054,0.14744902,0.000719836,0.39756647,0.04332735,0.4103672],"study_design_scores_gemma":[0.0000294695,0.000022523644,0.00011953739,0.000054962005,0.000016120688,0.000057803238,0.000018097238,0.42946997,0.00062750536,0.52023196,0.049338877,0.000013131135],"about_ca_topic_score_codex":0.0012920764,"about_ca_topic_score_gemma":0.0014126861,"teacher_disagreement_score":0.021057546,"about_ca_system_score_codex":0.0009265375,"about_ca_system_score_gemma":0.00051732006,"threshold_uncertainty_score":0.070444524},"labels":[],"label_agreement":null},{"id":"W2079808644","doi":"10.1109/icassp.2014.6855022","title":"Channel-aware distributed dynamic spectrum access via learning-based heterogeneous multi-channel auction","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Channel (broadcasting); Throughput; Overhead (engineering); Diversity gain; Auction algorithm; Computer network; Spectrum auction; Auction theory; Wireless; Common value auction; Telecommunications; Revenue equivalence; Fading; Mathematics","score_opus":0.07850233049752461,"score_gpt":0.41138927468019487,"score_spread":0.3328869441826703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079808644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019113563,0.00014238014,0.97876155,0.00011353202,0.000025136214,0.000049293092,0.00001963118,0.000120367666,0.0016545963],"genre_scores_gemma":[0.94963527,0.000118875345,0.048912432,0.000052235235,0.000042634332,0.00008556775,0.000021443942,0.000018005367,0.0011135204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998028,0.0006743681,0.0000688803,0.00030444993,0.0006072225,0.0003170238],"domain_scores_gemma":[0.9977325,0.0011302716,0.00032816533,0.00024782534,0.0003730969,0.00018808735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022008826,0.0008705225,0.001977712,0.0004942978,0.0005921501,0.0015992168,0.0023453895,0.0010300011,0.0012401273],"category_scores_gemma":[0.00409636,0.00043068785,0.0006239928,0.0009090638,0.0012238048,0.0018539203,0.0014695807,0.0012529895,0.0002277897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104360915,0.00010271718,0.0003483654,0.00004467134,0.000037703056,0.00010859997,0.000033935645,0.96386003,0.00197692,0.017970804,0.00048897933,0.014922846],"study_design_scores_gemma":[0.00001253883,0.000018814166,0.000025338506,8.753493e-7,0.0000035268504,0.000015380825,0.0000028848247,0.99655366,0.00016898115,0.003097595,0.00009675005,0.0000036051474],"about_ca_topic_score_codex":0.0016309463,"about_ca_topic_score_gemma":0.0011251105,"teacher_disagreement_score":0.0023453895,"about_ca_system_score_codex":0.0012713888,"about_ca_system_score_gemma":0.0013563095,"threshold_uncertainty_score":0.011639535},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2081804334","doi":"10.1109/glocom.2012.6503147","title":"Rank-optimal channel selection strategy in cognitive networks","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quality of service; Channel (broadcasting); Computer science; Selection (genetic algorithm); Cognitive radio; Throughput; Rank (graph theory); Convergence (economics); Quality (philosophy); Provisioning; Computer network; Mathematical optimization; Artificial intelligence; Mathematics; Wireless; Telecommunications; Combinatorics","score_opus":0.16538516075825044,"score_gpt":0.4570105232673575,"score_spread":0.2916253625091071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081804334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043189876,0.000583229,0.95048326,0.00037370645,0.000047377423,0.000048471444,0.000047632755,0.00030302515,0.0049234293],"genre_scores_gemma":[0.9471958,0.00029688198,0.049281165,0.00013512632,0.000049732334,0.00008774023,0.000043308537,0.00002203511,0.0028882467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987256,0.0005282652,0.000043878525,0.00017476299,0.00026641437,0.00026098656],"domain_scores_gemma":[0.9979227,0.0011613657,0.00027335138,0.00016654652,0.0003378927,0.00013812025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015347617,0.0007825926,0.00090431276,0.00058010913,0.00052505155,0.0011214766,0.0012266139,0.0009518412,0.0011176553],"category_scores_gemma":[0.0043219663,0.00033278062,0.00030874577,0.0005723128,0.0013948393,0.0010107115,0.0008796444,0.00071463216,0.00035947404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019331943,0.00008088859,0.0005327336,0.00006928262,0.000048206814,0.00012917248,0.00010931249,0.8881436,0.002664818,0.049696624,0.0019078387,0.056424163],"study_design_scores_gemma":[0.000021731626,0.000046846355,0.0000758776,0.0000043281048,0.000008252974,0.000029572773,0.000011688915,0.98605925,0.00059001776,0.012836753,0.0003057159,0.00001001516],"about_ca_topic_score_codex":0.0036047124,"about_ca_topic_score_gemma":0.0030748786,"teacher_disagreement_score":0.0036047124,"about_ca_system_score_codex":0.0011811047,"about_ca_system_score_gemma":0.0014556915,"threshold_uncertainty_score":0.008569598},"labels":[],"label_agreement":null},{"id":"W2084056659","doi":"10.1109/pimrc.2013.6666540","title":"Channel selection in Cognitive Radio Networks: A Switchable Bayesian Learning Automata approach","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Learning automata; Cognitive radio; Computer science; Channel (broadcasting); Probabilistic logic; Automaton; Bayesian probability; Bayesian network; Action selection; Selection (genetic algorithm); Theoretical computer science; Artificial intelligence; Computer network; Wireless; Telecommunications","score_opus":0.07435939515523153,"score_gpt":0.377254372149669,"score_spread":0.30289497699443746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084056659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030583266,0.0004435065,0.96309716,0.00060419814,0.000055738394,0.00004208165,0.000077874305,0.00017580017,0.0049204635],"genre_scores_gemma":[0.92870307,0.00053404795,0.06542878,0.00016964121,0.00008479613,0.00015958474,0.0000859571,0.000037223028,0.004796884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989889,0.00041746933,0.000038488743,0.00022078157,0.0001772758,0.00015703472],"domain_scores_gemma":[0.9976851,0.0017524441,0.00017512921,0.00009251836,0.00017888946,0.000115965704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011734773,0.0007536673,0.0011287406,0.00048152258,0.00056340435,0.0014088047,0.0017705433,0.0018475736,0.0019840808],"category_scores_gemma":[0.004114989,0.00047662944,0.00079847925,0.00056385587,0.0018260282,0.0015244596,0.0012625464,0.0018676441,0.00028359986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007109842,0.00004835114,0.00079872494,0.000054384793,0.00003906218,0.00010586291,0.00017582685,0.8888508,0.0009638013,0.094395705,0.0005251093,0.01397124],"study_design_scores_gemma":[0.0000067073456,0.000018722872,0.00005629789,0.0000043809832,0.000006507104,0.00001175863,0.000012080858,0.9751452,0.00011459135,0.024340952,0.00027631255,0.000006424324],"about_ca_topic_score_codex":0.0072896536,"about_ca_topic_score_gemma":0.0062873424,"teacher_disagreement_score":0.0072896536,"about_ca_system_score_codex":0.0014148046,"about_ca_system_score_gemma":0.0012126149,"threshold_uncertainty_score":0.014494419},"labels":[],"label_agreement":null},{"id":"W2086587356","doi":"10.1007/s10994-013-5364-5","title":"BoostingTree: parallel selection of weak learners in boosting, with application to ranking","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Magyarország Kormánya; Alberta Innovates; Nemzeti Kutatási és Technológiai Hivatal; Hungarian Scientific Research Fund","keywords":"Boosting (machine learning); Gradient boosting; Machine learning; Artificial intelligence; Ranking (information retrieval); Decision tree; Computer science; Mathematics; Feature selection; Pattern recognition (psychology); Random forest","score_opus":0.03175220600398684,"score_gpt":0.3621694942332327,"score_spread":0.3304172882292459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086587356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028178312,0.00037084456,0.9909965,0.00011915227,0.00019680255,0.00012278132,0.000110562905,0.0040774154,0.0011880348],"genre_scores_gemma":[0.06584315,0.00035377406,0.92770886,0.00017583944,0.00024411538,0.0003810736,0.000555741,0.0011862582,0.0035512517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963206,0.0016562954,0.00020686374,0.00034127472,0.0011838342,0.00029118764],"domain_scores_gemma":[0.9947955,0.0021466664,0.00017660356,0.0010753683,0.0015213606,0.00028446983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008926756,0.0015656308,0.0032927007,0.0023037097,0.0012749339,0.002503374,0.0041630287,0.0023234112,0.008224647],"category_scores_gemma":[0.016174627,0.0014285755,0.0018874139,0.0033142916,0.0008529132,0.002781876,0.0027098171,0.0037649737,0.005379838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006727901,0.0003252656,0.0013783413,0.00033161492,0.00025884103,0.000111523266,0.000166542,0.12775578,0.0034272056,0.027296346,0.02955534,0.80872035],"study_design_scores_gemma":[0.00015419407,0.0001171771,0.0003371009,0.000033247066,0.00007608704,0.00008317123,0.000021165351,0.95603985,0.0031195611,0.030489704,0.009500555,0.000028204744],"about_ca_topic_score_codex":0.002686291,"about_ca_topic_score_gemma":0.0042766044,"teacher_disagreement_score":0.008926756,"about_ca_system_score_codex":0.00077468087,"about_ca_system_score_gemma":0.0023246473,"threshold_uncertainty_score":0.04720974},"labels":[],"label_agreement":null},{"id":"W2094589420","doi":"10.1016/j.jet.2006.09.003","title":"Good news and bad news in two-armed bandits","year":2006,"lang":"en","type":"article","venue":"Journal of Economic Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"News media; Economics; Advertising; Computer science; Business","score_opus":0.04525898535024124,"score_gpt":0.4004500211495165,"score_spread":0.35519103579927525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094589420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38096943,0.0063075083,0.5798444,0.011117739,0.0006238514,0.00012906165,0.00041831884,0.00044686638,0.020142786],"genre_scores_gemma":[0.9789348,0.0015100678,0.0107212225,0.00037700517,0.00049766153,0.00010997916,0.00011784502,0.00006764244,0.0076636644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918596,0.005384802,0.00044110796,0.0009382921,0.0006037793,0.00077243475],"domain_scores_gemma":[0.7535843,0.23294075,0.0073237,0.0027457485,0.002149833,0.0012556671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021910679,0.0017813093,0.0051251613,0.0018244662,0.0016974233,0.009619859,0.002711828,0.006247882,0.006131821],"category_scores_gemma":[0.11440584,0.0023236144,0.0013364041,0.0021030158,0.0073808143,0.0098733185,0.0030076068,0.0059586614,0.00066870014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016799803,0.00024370447,0.005724004,0.0003772852,0.00044875374,0.00039629824,0.0007319084,0.44078347,0.0006324072,0.5232513,0.0038485788,0.021882426],"study_design_scores_gemma":[0.0001348769,0.000062522435,0.00089674554,0.000050643077,0.000093893104,0.000046350673,0.00013535378,0.6325305,0.00019940604,0.3653854,0.00040399464,0.00006035733],"about_ca_topic_score_codex":0.003385585,"about_ca_topic_score_gemma":0.0018917342,"teacher_disagreement_score":0.021910679,"about_ca_system_score_codex":0.0021047124,"about_ca_system_score_gemma":0.0012927166,"threshold_uncertainty_score":0.11587614},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.048601252740934964,"score_gpt":0.3624277436117635,"score_spread":0.31382649087082853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095762034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1617806,0.0012611418,0.82763344,0.0018184325,0.00011307638,0.00018328204,0.000349904,0.0005971617,0.0062628346],"genre_scores_gemma":[0.9405903,0.00056766975,0.054271646,0.00029446286,0.00012939963,0.0002154359,0.00029028524,0.00007505305,0.003565639],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980667,0.0009694414,0.000070897004,0.0003896813,0.00022267253,0.0002805403],"domain_scores_gemma":[0.96172214,0.033109054,0.0027595793,0.000961307,0.0007240068,0.00072399434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004534392,0.0018529941,0.002424423,0.0005842015,0.00048763258,0.0015080688,0.002057778,0.002837921,0.0037619113],"category_scores_gemma":[0.0315681,0.0008956911,0.0005601368,0.001208807,0.00168204,0.0042916867,0.0013082025,0.0032914162,0.00043768497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021413565,0.00012435699,0.0008233084,0.000063437736,0.000039094335,0.000083366496,0.00003392017,0.9760616,0.00023983956,0.011768934,0.00067175936,0.009876291],"study_design_scores_gemma":[0.000031385083,0.00005263306,0.000105787476,0.000006259615,0.000006008554,0.000009686681,0.0000058230353,0.98886174,0.00015318154,0.010644275,0.000118100805,0.0000051279912],"about_ca_topic_score_codex":0.0055813594,"about_ca_topic_score_gemma":0.0037245438,"teacher_disagreement_score":0.0055813594,"about_ca_system_score_codex":0.0016761658,"about_ca_system_score_gemma":0.001717078,"threshold_uncertainty_score":0.023980439},"labels":[],"label_agreement":null},{"id":"W2096871811","doi":"10.2139/ssrn.1133118","title":"Strategic Manipulation of Empirical Tests","year":2008,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Business; Political science; Psychology","score_opus":0.2411058581692617,"score_gpt":0.47160472181368035,"score_spread":0.23049886364441866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096871811","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3280555,0.002067024,0.3077125,0.013532809,0.0009866703,0.000517604,0.00033851195,0.0010610865,0.34572837],"genre_scores_gemma":[0.9766291,0.00019355684,0.017101536,0.001136611,0.00022207237,0.00021278627,0.00007171405,0.00009310689,0.0043395567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95342547,0.030469993,0.0021510937,0.0038054397,0.008007472,0.0021405055],"domain_scores_gemma":[0.7477788,0.1891876,0.019175712,0.033070877,0.008108036,0.0026789187],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028962802,0.0012273788,0.0010792763,0.0028833286,0.0014520647,0.0068657384,0.0015636323,0.0029896747,0.012923453],"category_scores_gemma":[0.19737977,0.0008665039,0.0007404481,0.0021807172,0.0036189456,0.00501387,0.0043933373,0.0038982783,0.0020234787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011398554,0.00055368635,0.022137145,0.0004409843,0.00041850872,0.0005607529,0.003649583,0.006466576,0.015210969,0.7570931,0.00689953,0.18542935],"study_design_scores_gemma":[0.00034360652,0.0005742622,0.018393928,0.00024801385,0.00038405386,0.0004503126,0.0020501926,0.048869062,0.017929507,0.87879723,0.031835053,0.00012474202],"about_ca_topic_score_codex":0.00056077354,"about_ca_topic_score_gemma":0.0008800694,"teacher_disagreement_score":0.99701035,"about_ca_system_score_codex":0.0019049984,"about_ca_system_score_gemma":0.0031162228,"threshold_uncertainty_score":0.15317178},"labels":[],"label_agreement":null},{"id":"W2102933744","doi":"10.5555/2025816.2025869","title":"The Bayesian pursuit algorithm: a new family of estimator learning automata","year":2011,"lang":"en","type":"article","venue":"Duo Research Archive (University of Oslo)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Learning automata; Prior probability; Bayesian probability; Conjugate prior; Estimator; Computer science; Algorithm; Artificial intelligence; Machine learning; Mathematics; Automaton; Statistics","score_opus":0.14377433902124603,"score_gpt":0.3747589294397711,"score_spread":0.2309845904185251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102933744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097596383,0.00025588402,0.9979861,0.00008176775,0.000033051714,0.000015397249,0.000030503394,0.00016333949,0.00045796018],"genre_scores_gemma":[0.06893643,0.0011970288,0.92525655,0.00022683023,0.00026404846,0.00034660785,0.00020697748,0.00036147705,0.00320395],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954781,0.001812015,0.00032910274,0.0007944267,0.0014243464,0.00016202596],"domain_scores_gemma":[0.9878131,0.008301854,0.00054768415,0.001524266,0.0015257094,0.00028744322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006723439,0.0012595569,0.0024911608,0.0020986064,0.0008769961,0.003256109,0.0040103067,0.0031255884,0.003323325],"category_scores_gemma":[0.027381836,0.0012404149,0.0018934573,0.002037242,0.002114243,0.005556964,0.004175392,0.004580012,0.0015633962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022473313,0.00009205573,0.0014344839,0.00024632807,0.00019224103,0.000076146396,0.00020466889,0.2559364,0.002573804,0.37989986,0.0045061777,0.3546131],"study_design_scores_gemma":[0.000020556201,0.000045713394,0.00007955939,0.000027746568,0.000023473298,0.000052118878,0.000006919814,0.8947126,0.0007334148,0.10045023,0.0038256487,0.000022106711],"about_ca_topic_score_codex":0.0016758147,"about_ca_topic_score_gemma":0.0016299876,"teacher_disagreement_score":0.006723439,"about_ca_system_score_codex":0.001127799,"about_ca_system_score_gemma":0.0016871612,"threshold_uncertainty_score":0.03555733},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1316744920066128,"score_gpt":0.431294036276807,"score_spread":0.2996195442701942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103581319","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054548983,0.0017596011,0.9311532,0.0013557444,0.000092911454,0.00007444352,0.00013221736,0.00024061368,0.010642304],"genre_scores_gemma":[0.9145412,0.0012816277,0.07071834,0.00042484765,0.00021916282,0.0004720428,0.00017186673,0.00011183689,0.012059119],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99700505,0.0019808048,0.00014013624,0.00039514256,0.00023495858,0.00024390832],"domain_scores_gemma":[0.9835128,0.014353276,0.0011007049,0.00043398378,0.00033250995,0.0002667014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005467576,0.0014863407,0.0026904498,0.0006625784,0.00065634097,0.0030964334,0.0013532122,0.0027438095,0.004495615],"category_scores_gemma":[0.017088706,0.0010228106,0.0009644313,0.001175013,0.0027910261,0.003202803,0.0018791462,0.0025644104,0.00059396203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020714583,0.00005579844,0.000667663,0.00014735911,0.00007876951,0.00009927891,0.00008959211,0.82522833,0.00039836395,0.16153923,0.0008011849,0.010687249],"study_design_scores_gemma":[0.000039066388,0.00003556591,0.00010272656,0.000025926272,0.000009091176,0.000010331059,0.000017226963,0.9095952,0.00012932466,0.08962586,0.00039971963,0.000009983617],"about_ca_topic_score_codex":0.0021974738,"about_ca_topic_score_gemma":0.0015233546,"teacher_disagreement_score":0.005467576,"about_ca_system_score_codex":0.0016763181,"about_ca_system_score_gemma":0.00086866814,"threshold_uncertainty_score":0.028915644},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.18336283013052163,"score_gpt":0.44411397646752687,"score_spread":0.26075114633700525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105336508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005081657,0.00008733581,0.9914243,0.00012096086,0.000037698606,0.00003818819,0.000018337105,0.00015462929,0.0030368217],"genre_scores_gemma":[0.46383467,0.00030387245,0.5257694,0.00032881898,0.00013122158,0.00053121254,0.00014121506,0.00019461075,0.00876492],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99775875,0.0007772394,0.000102170416,0.00038153332,0.0008363911,0.00014393835],"domain_scores_gemma":[0.9937909,0.003937752,0.00038561682,0.0007976196,0.0009061482,0.00018189054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036698354,0.0010917234,0.0016783958,0.0006342681,0.0004953208,0.0013647253,0.0022472516,0.0021654838,0.004323912],"category_scores_gemma":[0.016262533,0.00066541246,0.00084823597,0.0006272251,0.0021810033,0.0028065797,0.0022665747,0.0026956904,0.00085923134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010902647,0.0000890744,0.00043302728,0.000110779096,0.00005973839,0.00008219263,0.00014778401,0.8188213,0.0018020663,0.13403934,0.0012468642,0.04305878],"study_design_scores_gemma":[0.000010436524,0.000030109673,0.000018243936,0.0000071435015,0.000003982234,0.00002001306,0.000004942556,0.98385507,0.00042161235,0.015097641,0.0005265219,0.0000042223824],"about_ca_topic_score_codex":0.0015634521,"about_ca_topic_score_gemma":0.0013835549,"teacher_disagreement_score":0.004323912,"about_ca_system_score_codex":0.0010656264,"about_ca_system_score_gemma":0.0019582934,"threshold_uncertainty_score":0.019408166},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14089624632931172,"score_gpt":0.28580462013331953,"score_spread":0.1449083738040078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106233414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1038829,0.0006241637,0.8851712,0.0014355753,0.00005199812,0.00012486424,0.00011698083,0.0004699409,0.008122267],"genre_scores_gemma":[0.9115955,0.0003727403,0.08329768,0.00030570093,0.000087148605,0.00020902036,0.0001403216,0.000059801903,0.003932046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960497,0.00248759,0.00013453666,0.0005665453,0.0004568058,0.0003048234],"domain_scores_gemma":[0.9813416,0.015033989,0.0012244714,0.0016236297,0.00038680297,0.00038953882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055925096,0.0014604917,0.001721995,0.00052575645,0.00059920026,0.0019324586,0.0019739838,0.0015910085,0.0013553526],"category_scores_gemma":[0.026133813,0.00072685006,0.00074733,0.0006389009,0.0028260788,0.0037050715,0.0018444249,0.00261928,0.00030426035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000482093,0.00018948225,0.0010970664,0.00013612927,0.000111053254,0.00010336277,0.00015310067,0.7829096,0.0006060654,0.17915568,0.0015188592,0.033537682],"study_design_scores_gemma":[0.000038051294,0.000056998673,0.00014870247,0.00001430121,0.000013221539,0.000019748848,0.000010091131,0.87060606,0.00040877817,0.12832531,0.0003484854,0.000010228649],"about_ca_topic_score_codex":0.0021403031,"about_ca_topic_score_gemma":0.0021167144,"teacher_disagreement_score":0.0055925096,"about_ca_system_score_codex":0.002019896,"about_ca_system_score_gemma":0.0015075605,"threshold_uncertainty_score":0.029576361},"labels":[],"label_agreement":null},{"id":"W2107105626","doi":"","title":"Optimal unbiased estimators for evaluating agent performance","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Variance (accounting); Outcome (game theory); Computer science; Minimum-variance unbiased estimator; Set (abstract data type); Bias of an estimator; Mathematical optimization; Mathematics; Statistics; Mathematical economics; Economics","score_opus":0.25992983276054066,"score_gpt":0.5149763499626402,"score_spread":0.25504651720209953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107105626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011167467,0.0005874933,0.98579305,0.00019631418,0.000038160415,0.00006312709,0.000061999745,0.00026765672,0.0018245946],"genre_scores_gemma":[0.57606435,0.0011329302,0.41785055,0.00033204723,0.00021496724,0.0006385103,0.00044586745,0.00027898466,0.0030418616],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881363,0.0071507096,0.00056811323,0.0012024273,0.0023173415,0.0006250298],"domain_scores_gemma":[0.96623766,0.025821017,0.0022432692,0.0024542306,0.0028469302,0.0003968868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013931055,0.0017028489,0.0022715835,0.0031663703,0.0007281149,0.0030390644,0.0014366173,0.0023126262,0.0024163243],"category_scores_gemma":[0.09291584,0.00090697734,0.00073670543,0.0016899994,0.002181459,0.004436279,0.0020639119,0.0018798036,0.00096012506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000326989,0.00010140762,0.004327588,0.00020262625,0.00025479874,0.00008448604,0.00019703519,0.75735706,0.0019551623,0.14032406,0.002035306,0.09283353],"study_design_scores_gemma":[0.000027308604,0.00007546672,0.0006389005,0.00006763768,0.000031397496,0.00003490769,0.000037341317,0.924674,0.0017558499,0.07172813,0.00089982245,0.00002927367],"about_ca_topic_score_codex":0.0022261676,"about_ca_topic_score_gemma":0.0015683972,"teacher_disagreement_score":0.013931055,"about_ca_system_score_codex":0.0018459888,"about_ca_system_score_gemma":0.0019255375,"threshold_uncertainty_score":0.073675334},"labels":[],"label_agreement":null},{"id":"W2110454495","doi":"10.48550/arxiv.1405.3318","title":"Adaptive Monte Carlo via Bandit Allocation","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Monte Carlo method; Estimator; Mathematical optimization; Computer science; Set (abstract data type); Mean squared error; Mathematics; Statistics","score_opus":0.1881229664939298,"score_gpt":0.2733599798044529,"score_spread":0.08523701331052314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110454495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010697914,0.00045062648,0.9849759,0.0004524765,0.00004875304,0.00008874546,0.000041360625,0.00013242873,0.0031118176],"genre_scores_gemma":[0.6817255,0.00080038066,0.30879644,0.000499875,0.00022042533,0.00079373555,0.00017506492,0.00009064572,0.0068979426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953819,0.0030213436,0.00014391133,0.00059189287,0.000574818,0.00028610634],"domain_scores_gemma":[0.9869473,0.010863451,0.0009095982,0.00059049844,0.00046344244,0.00022577186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006170714,0.0013829976,0.0019888396,0.0010298779,0.00073715276,0.0021410713,0.0021596383,0.002420603,0.003093472],"category_scores_gemma":[0.025583427,0.0008315718,0.0006562343,0.0016933751,0.0025741728,0.0024476163,0.002119829,0.00231988,0.0006777847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012945998,0.00006411345,0.0006782341,0.00005937678,0.00008341086,0.00006114638,0.00006301576,0.8374181,0.00036559717,0.13889632,0.0007317782,0.021449482],"study_design_scores_gemma":[0.000024684594,0.000025453475,0.000069805574,0.0000137822735,0.000012243206,0.000013259251,0.0000058712517,0.9372734,0.00022236718,0.061803423,0.0005262194,0.00000950688],"about_ca_topic_score_codex":0.0027278387,"about_ca_topic_score_gemma":0.0025326612,"teacher_disagreement_score":0.006170714,"about_ca_system_score_codex":0.0016171586,"about_ca_system_score_gemma":0.0014280044,"threshold_uncertainty_score":0.03263426},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Exponential function; Mathematical economics; Applied mathematics; Mathematics; Gaussian; Process (computing); Gaussian process; Econometrics; Mathematical optimization; Statistical physics; Economics; Computer science; Statistics; Physics; Mathematical analysis","score_opus":0.4019517217496925,"score_gpt":0.3403438641409024,"score_spread":0.06160785760879012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110582581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04630912,0.008116768,0.92319524,0.004236092,0.0002902895,0.00012433021,0.00043046902,0.00069775566,0.01659997],"genre_scores_gemma":[0.84859604,0.007826025,0.124428846,0.00237055,0.001274643,0.0008609431,0.0009365224,0.0006951239,0.013011325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947482,0.0023641898,0.00016842794,0.0007581585,0.0011615168,0.0007995903],"domain_scores_gemma":[0.9427685,0.048443273,0.0027676346,0.0029709847,0.0020602806,0.0009893166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015309343,0.002839986,0.0030799913,0.0020256736,0.0019152425,0.0038356923,0.0034508905,0.0029293771,0.0046554105],"category_scores_gemma":[0.06876258,0.0013343882,0.00170991,0.0025975027,0.0051628626,0.007740323,0.004456697,0.0066427714,0.0009941207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000633823,0.0001707328,0.002157699,0.00034571698,0.00020784474,0.00019167468,0.000220153,0.65076,0.001276704,0.31686422,0.005431793,0.021739654],"study_design_scores_gemma":[0.000043338026,0.00005494068,0.00040188775,0.00008350532,0.000037952857,0.00005218304,0.00002579538,0.86609185,0.00046275044,0.1318604,0.0008630933,0.000022360327],"about_ca_topic_score_codex":0.0033753018,"about_ca_topic_score_gemma":0.0027251109,"teacher_disagreement_score":0.015309343,"about_ca_system_score_codex":0.0053034043,"about_ca_system_score_gemma":0.0026004158,"threshold_uncertainty_score":0.080964565},"labels":[],"label_agreement":null},{"id":"W2110722897","doi":"10.1109/icassp.2006.1660926","title":"Transmission Scheduling for Sensor Network Lifetime Maximization: A Shortest Path Bandit Formulation","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wireless sensor network; Scheduling (production processes); Maximization; Mathematical optimization; Shortest path problem; Computer science; Independent and identically distributed random variables; Job shop scheduling; Dynamic priority scheduling; Fading; Fair-share scheduling; Channel (broadcasting); Computer network; Mathematics; Random variable; Theoretical computer science; Quality of service; Routing (electronic design automation)","score_opus":0.06525706696555161,"score_gpt":0.37955171465594856,"score_spread":0.31429464769039694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110722897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008349205,0.0007273582,0.9850101,0.0009636151,0.00006737393,0.00008017954,0.00014600075,0.000083420215,0.0045728236],"genre_scores_gemma":[0.7663706,0.0031381315,0.2124719,0.00072219706,0.00055389246,0.0010280223,0.0004133884,0.00022235127,0.015079523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984774,0.0007164315,0.00006250641,0.0002747776,0.00029115053,0.00017770573],"domain_scores_gemma":[0.9968342,0.0022553771,0.00046446986,0.00009738798,0.0002683632,0.00008023969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027948073,0.0014054652,0.0015961925,0.0006810254,0.00056010985,0.0018185162,0.0015490648,0.0019690597,0.0038903374],"category_scores_gemma":[0.006538001,0.0006417579,0.0006800324,0.0017463373,0.0013183936,0.0026406755,0.0011533058,0.0018773939,0.00060994324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005381277,0.000040739076,0.00020225867,0.00011719047,0.000037515994,0.00006965823,0.000066179484,0.9210932,0.00065682165,0.06589729,0.001520976,0.010244411],"study_design_scores_gemma":[0.000011607699,0.0000296717,0.00006634978,0.000014037269,0.0000102978665,0.000018882167,0.000016719949,0.97303796,0.00019609937,0.025823385,0.0007679919,0.000007077444],"about_ca_topic_score_codex":0.003269371,"about_ca_topic_score_gemma":0.0027633102,"teacher_disagreement_score":0.0038903374,"about_ca_system_score_codex":0.0021823228,"about_ca_system_score_gemma":0.0014693919,"threshold_uncertainty_score":0.015833914},"labels":[],"label_agreement":null},{"id":"W2111440138","doi":"","title":"Online learning with expert advice and finite-horizon constraints","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Sublinear function; Novelty; Mathematical optimization; Time horizon; Adversary; Artificial intelligence; Online learning; Quality (philosophy); Machine learning; Mathematics","score_opus":0.10906569035608918,"score_gpt":0.4113532463015598,"score_spread":0.30228755594547063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111440138","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08302164,0.00054264144,0.9104915,0.0007611428,0.00005589152,0.00007995127,0.000071145,0.0002472035,0.004728895],"genre_scores_gemma":[0.9360236,0.00026764182,0.059485897,0.0002411559,0.00011462429,0.00013625712,0.00008241461,0.000029430345,0.0036190138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982468,0.0007718403,0.00006581278,0.00031309552,0.0003300722,0.00027233775],"domain_scores_gemma":[0.98492396,0.012695207,0.0010147926,0.00042514212,0.0005434234,0.00039754595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033758567,0.0014153307,0.0018440104,0.00040515105,0.0004260194,0.0010497705,0.0015342137,0.0024247828,0.0025595594],"category_scores_gemma":[0.015062276,0.0005668379,0.00035550335,0.0006199695,0.0013864957,0.0020816827,0.0008543464,0.0020357855,0.0003182716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022524658,0.00013759412,0.0006305159,0.00008582063,0.0000471665,0.00013726357,0.000040286053,0.9649241,0.00045158638,0.015172365,0.0006807263,0.01746734],"study_design_scores_gemma":[0.000042423235,0.000042642314,0.000085011976,0.000006437811,0.000005377705,0.000017612027,0.000006130735,0.99191004,0.00020412344,0.007544239,0.00013136785,0.0000046507685],"about_ca_topic_score_codex":0.0041560447,"about_ca_topic_score_gemma":0.0035096486,"teacher_disagreement_score":0.0041560447,"about_ca_system_score_codex":0.001042824,"about_ca_system_score_gemma":0.0014678675,"threshold_uncertainty_score":0.017853439},"labels":[],"label_agreement":null},{"id":"W2116497114","doi":"10.1007/978-3-540-72927-3_19","title":"Strategies for Prediction Under Imperfect Monitoring","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imperfect; Computer science; Constructive; Logarithm; Consistency (knowledge bases); Convergence (economics); Simple (philosophy); Asymptotically optimal algorithm; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics","score_opus":0.14308238564303533,"score_gpt":0.4279685929098571,"score_spread":0.2848862072668218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116497114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037836604,0.0013766977,0.9406677,0.0029485791,0.00020402553,0.00007472083,0.0002214165,0.00040257297,0.016267668],"genre_scores_gemma":[0.9237632,0.0012970525,0.058553237,0.00035701718,0.00040082872,0.00019579279,0.0001736134,0.00008726783,0.015171928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895537,0.00047364016,0.000056390072,0.00019665538,0.00016983484,0.00014801382],"domain_scores_gemma":[0.9911754,0.0071895192,0.00046490703,0.00063652673,0.0003421019,0.00019149491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031801458,0.0012298832,0.0015195003,0.0006810387,0.00049072824,0.0024910849,0.0019018773,0.0022558803,0.004196842],"category_scores_gemma":[0.015129009,0.0005797819,0.0005514538,0.000999437,0.0014455671,0.0036830625,0.0015101654,0.002080034,0.00063928345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015519225,0.000057559904,0.0007595314,0.00012985298,0.00008665307,0.00015080975,0.00015475655,0.2703404,0.0006803174,0.6650471,0.0065301717,0.055907693],"study_design_scores_gemma":[0.000022108337,0.000022384178,0.00011219479,0.000016878748,0.000014372976,0.000029031526,0.00001567333,0.528026,0.00023015401,0.47079024,0.00070983014,0.000011261656],"about_ca_topic_score_codex":0.0013601338,"about_ca_topic_score_gemma":0.00084851886,"teacher_disagreement_score":0.004196842,"about_ca_system_score_codex":0.0012769714,"about_ca_system_score_gemma":0.00083596486,"threshold_uncertainty_score":0.016818404},"labels":[],"label_agreement":null},{"id":"W2116541203","doi":"10.1109/itw.2008.4578656","title":"Streaming algorithms for estimating entropy","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Defense Science and Engineering Graduate; National Science Foundation","keywords":"Rényi entropy; Shannon's source coding theorem; Entropy (arrow of time); Computation; Computer science; Maximum entropy probability distribution; Algorithm; Entropy power inequality; Information theory; Entropy rate; Rate of convergence; Mathematics; Joint entropy; Principle of maximum entropy; Applied mathematics; Mathematical optimization; Maximum entropy thermodynamics; Joint quantum entropy; Statistics; Artificial intelligence","score_opus":0.23567286712257887,"score_gpt":0.4722105377626748,"score_spread":0.23653767064009593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116541203","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010154864,0.00018951042,0.99791497,0.0000803407,0.00003751274,0.000022902317,0.000039282393,0.00012782795,0.0005722386],"genre_scores_gemma":[0.10917601,0.00126854,0.88351923,0.00023279092,0.0006274138,0.00045736087,0.00043162846,0.00037293392,0.0039140135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973326,0.0010192643,0.00018137388,0.00043093346,0.0008851238,0.00015068047],"domain_scores_gemma":[0.98813254,0.007804313,0.0006190853,0.0020628688,0.0011404706,0.0002406573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004108105,0.001135788,0.0015857302,0.0029660282,0.0009071892,0.0020359666,0.002332438,0.0018429338,0.004841608],"category_scores_gemma":[0.02694619,0.0006919875,0.0013729185,0.00253121,0.001947895,0.006384447,0.0030102432,0.0035499595,0.0014111224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015701725,0.00007561915,0.00106857,0.0002838807,0.00011858502,0.00013023446,0.00023459872,0.21243086,0.0067820656,0.5999428,0.004284965,0.1744908],"study_design_scores_gemma":[0.000012789279,0.00003717233,0.00018611812,0.00003497343,0.000017286013,0.00009845748,0.000016804699,0.71979755,0.0022272028,0.27395847,0.003583416,0.000029686604],"about_ca_topic_score_codex":0.001270216,"about_ca_topic_score_gemma":0.0008891044,"teacher_disagreement_score":0.004841608,"about_ca_system_score_codex":0.0011316916,"about_ca_system_score_gemma":0.0008541014,"threshold_uncertainty_score":0.021725953},"labels":[],"label_agreement":null},{"id":"W2118191986","doi":"10.1613/jair.1336","title":"Can We Learn to Beat the Best Stock","year":2004,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Algorithmic trading; Technical analysis; Computer science; Smoothing; Heuristics; Stock market; Trading strategy; Stock (firearms); Pairs trade; Econometrics; Financial economics; Empirical evidence; Artificial intelligence; Machine learning; Context (archaeology); Alternative trading system; Economics; Engineering","score_opus":0.5013709025139251,"score_gpt":0.568274054729651,"score_spread":0.06690315221572585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118191986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09296086,0.0012956898,0.8946701,0.0024148617,0.0002946137,0.00009322297,0.00014204941,0.0016443231,0.006484263],"genre_scores_gemma":[0.7328204,0.00041038918,0.25925183,0.0010325294,0.00023330883,0.00011476817,0.0003403554,0.00017893783,0.0056175278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994522,0.00012141929,0.00004017654,0.0001760404,0.00012887365,0.000081344806],"domain_scores_gemma":[0.9976126,0.0014087205,0.0003109476,0.00019072159,0.00030072525,0.0001762027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016821591,0.00071125646,0.00091836555,0.00085689867,0.00048447648,0.001311887,0.0014053568,0.0019484181,0.004053406],"category_scores_gemma":[0.010272257,0.00032657117,0.00033954546,0.0005808826,0.0010500981,0.0028774708,0.00094348035,0.00126527,0.0011326295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000676846,0.0002873026,0.009524322,0.00016134224,0.00020317311,0.00013488621,0.00025118145,0.17270334,0.003927195,0.0386159,0.017888105,0.75562644],"study_design_scores_gemma":[0.00008599567,0.00014585284,0.00062599435,0.000032909797,0.000038360777,0.00009514088,0.00004986963,0.93272597,0.0023479941,0.06087775,0.0029501843,0.000023985469],"about_ca_topic_score_codex":0.0017205414,"about_ca_topic_score_gemma":0.0019390575,"teacher_disagreement_score":0.004053406,"about_ca_system_score_codex":0.0005319397,"about_ca_system_score_gemma":0.0009249102,"threshold_uncertainty_score":0.013559997},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3179026584292263,"score_gpt":0.46215023141597483,"score_spread":0.1442475729867485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119738618","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00468228,0.00065336085,0.9902884,0.0004119279,0.00009552488,0.000080038204,0.000101554004,0.0007733071,0.0029136003],"genre_scores_gemma":[0.25856018,0.0012826957,0.7272025,0.0010052073,0.00065813994,0.0006956131,0.0007621157,0.0008566319,0.008976917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99208754,0.003554884,0.00040140492,0.0011037068,0.0021348046,0.000717635],"domain_scores_gemma":[0.9774994,0.015672484,0.0014228234,0.0029378189,0.001998257,0.00046924636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008746492,0.0022993193,0.0029957173,0.0020327535,0.0009861181,0.0032646523,0.0046594823,0.0032986372,0.008169985],"category_scores_gemma":[0.044892494,0.001170912,0.0019009636,0.0029243284,0.0024384777,0.0059002633,0.0042775464,0.006200713,0.0032841708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044380644,0.00029520423,0.001232905,0.00035386437,0.00015710905,0.00011261708,0.00021911287,0.5721544,0.002765167,0.25617343,0.009038774,0.1570536],"study_design_scores_gemma":[0.000039331255,0.000037877053,0.00011301251,0.000029582267,0.000013938496,0.00003229071,0.0000068444137,0.9459243,0.0005808895,0.051865965,0.0013424658,0.000013481698],"about_ca_topic_score_codex":0.003043824,"about_ca_topic_score_gemma":0.0029256076,"teacher_disagreement_score":0.008746492,"about_ca_system_score_codex":0.0028121127,"about_ca_system_score_gemma":0.002999307,"threshold_uncertainty_score":0.046256423},"labels":[],"label_agreement":null},{"id":"W2133081350","doi":"10.1109/cdc.2010.5717262","title":"Online Convex Programming and regularization in adaptive control","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Convex optimization; Generalization; Sequence (biology); Mathematical optimization; Computer science; Regular polygon; Dynamic programming; Regularization (linguistics); Adaptive control; Convex function; Convex analysis; Control theory (sociology); Control (management); Algorithm; Mathematics; Artificial intelligence","score_opus":0.07039671897197886,"score_gpt":0.41335475547406814,"score_spread":0.3429580365020893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133081350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005591468,0.0018733949,0.98665977,0.0009775106,0.0000764411,0.000016988119,0.000027233178,0.00007881504,0.0046983287],"genre_scores_gemma":[0.75600857,0.005231466,0.22626716,0.0006057424,0.0008464721,0.00030958882,0.00013273057,0.00013486294,0.010463496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891555,0.0005233443,0.000038806786,0.00018091331,0.00027233624,0.000068990754],"domain_scores_gemma":[0.99788886,0.0016102488,0.0001612131,0.00013163366,0.0001605189,0.000047640915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016528575,0.00088492373,0.00092829065,0.00043512112,0.00034975272,0.0010740586,0.00079217134,0.0013472178,0.0013665381],"category_scores_gemma":[0.004773337,0.00034170705,0.00058490544,0.0008004565,0.0021399742,0.0014022173,0.0011439137,0.0025601927,0.00023818469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046497073,0.00004282964,0.000315673,0.00013238635,0.000045453035,0.000076658514,0.00008869829,0.5191024,0.0011175512,0.4344472,0.0020105336,0.0425741],"study_design_scores_gemma":[0.000007081171,0.000020901332,0.000078564895,0.0000110508645,0.0000035556823,0.000012266454,0.000007097377,0.8894559,0.00027915312,0.108624265,0.0014938693,0.0000063660655],"about_ca_topic_score_codex":0.0023988476,"about_ca_topic_score_gemma":0.0014644001,"teacher_disagreement_score":0.0023988476,"about_ca_system_score_codex":0.0012292789,"about_ca_system_score_gemma":0.00088908157,"threshold_uncertainty_score":0.00891912},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04799188361605175,"score_gpt":0.3932287474444243,"score_spread":0.3452368638283726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135829225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040289093,0.0007114891,0.9562605,0.00063667604,0.00004194318,0.000054775326,0.000055998455,0.00023032965,0.0017191933],"genre_scores_gemma":[0.88956785,0.00087727373,0.10611401,0.00023805861,0.00011136088,0.00021924776,0.0001317565,0.000055844044,0.0026844705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975031,0.0011550976,0.00011096739,0.0005600703,0.00027167224,0.00039913892],"domain_scores_gemma":[0.979482,0.017824639,0.0013539123,0.00051158405,0.000426832,0.00040101417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052562356,0.0014961098,0.0022398278,0.00074413494,0.0008591863,0.0020758654,0.0019437437,0.0024526673,0.0018965771],"category_scores_gemma":[0.019489916,0.0009187549,0.0010162808,0.0012653514,0.0027229,0.003233079,0.0026017483,0.0029355169,0.00027804635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015639252,0.000065520835,0.0005663609,0.00006985647,0.00004533227,0.00010065435,0.000067069435,0.94063336,0.00027525335,0.04501916,0.00029160516,0.012709399],"study_design_scores_gemma":[0.000018711246,0.000021733016,0.000056742945,0.000007401469,0.000008029638,0.000010109394,0.000005425254,0.9697318,0.00017486609,0.029853135,0.00010613045,0.000005921248],"about_ca_topic_score_codex":0.0064276364,"about_ca_topic_score_gemma":0.00402363,"teacher_disagreement_score":0.0064276364,"about_ca_system_score_codex":0.002115194,"about_ca_system_score_gemma":0.001916098,"threshold_uncertainty_score":0.027797937},"labels":[],"label_agreement":null},{"id":"W2136723863","doi":"","title":"An Empirical Analysis of Off-policy Learning in Discrete MDPs","year":2012,"lang":"en","type":"article","venue":"European Workshop on Reinforcement Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Dynamic programming; Variance (accounting); Sampling (signal processing); Population; Mathematical optimization; Monte Carlo method; Policy analysis; Artificial intelligence; Algorithm; Statistics; Mathematics; Economics","score_opus":0.10710063990214132,"score_gpt":0.45902569817125777,"score_spread":0.35192505826911646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136723863","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8413725,0.002146841,0.15015802,0.0016039048,0.000078376375,0.00019488567,0.0004879375,0.00028962127,0.003668006],"genre_scores_gemma":[0.98661685,0.0003115764,0.011997653,0.00007410561,0.000021493153,0.000093805385,0.0003558908,0.0000361062,0.0004924193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961015,0.002500788,0.00016503871,0.00036813616,0.000607675,0.00025686546],"domain_scores_gemma":[0.8200043,0.1644182,0.0050822166,0.005882434,0.0033793636,0.0012334244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015754698,0.0008845141,0.0012162519,0.001139401,0.0006288991,0.0009969634,0.0017471621,0.001598429,0.0022085526],"category_scores_gemma":[0.10932687,0.00043899572,0.00065302814,0.000979577,0.002007967,0.0032508685,0.0013081932,0.002991931,0.0001467476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038296345,0.00032754114,0.012259377,0.00017737856,0.00008875811,0.00007429843,0.00008956291,0.94886714,0.00034021086,0.01752843,0.0011545249,0.01870978],"study_design_scores_gemma":[0.000026479227,0.00013384326,0.0024930981,0.000033489676,0.000013324474,0.000030442838,0.000039681094,0.98876476,0.00038131452,0.007846,0.00022508178,0.000012432005],"about_ca_topic_score_codex":0.004121312,"about_ca_topic_score_gemma":0.0024582609,"teacher_disagreement_score":0.015754698,"about_ca_system_score_codex":0.0021194818,"about_ca_system_score_gemma":0.0012917516,"threshold_uncertainty_score":0.08331978},"labels":[],"label_agreement":null},{"id":"W2142115504","doi":"10.48550/arxiv.1503.05087","title":"Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Weighting; Computer science; Algorithm; Mathematical optimization; Mathematics","score_opus":0.1796660741256431,"score_gpt":0.3228558868453828,"score_spread":0.1431898127197397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142115504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005195007,0.00009701655,0.992949,0.0002047174,0.000031498766,0.000080420185,0.000033629694,0.00037040023,0.0010383041],"genre_scores_gemma":[0.30621505,0.00019182256,0.6884559,0.00039933607,0.00015910219,0.0005798095,0.00029759787,0.00032928376,0.0033720986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997615,0.0011416008,0.00010971335,0.0003338694,0.0005705982,0.00022914121],"domain_scores_gemma":[0.9946326,0.003635821,0.00033353543,0.0008094302,0.000391085,0.00019759718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037410231,0.0012721289,0.0020332073,0.0010136111,0.00069686724,0.0019268106,0.002743956,0.0018414424,0.0045619067],"category_scores_gemma":[0.0150174415,0.0007245654,0.0008796678,0.0012870143,0.0015541153,0.0027277297,0.0028460585,0.0030611777,0.001403554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044903002,0.00031072256,0.0013174657,0.0002247377,0.00009211332,0.00018606905,0.00024836443,0.56941944,0.0043365764,0.14733864,0.005468788,0.27060804],"study_design_scores_gemma":[0.00003268787,0.000031199015,0.000047670826,0.000009430694,0.000005991245,0.000025264266,0.000010591168,0.9653018,0.0005979755,0.033381265,0.00054984057,0.0000061943038],"about_ca_topic_score_codex":0.0017655359,"about_ca_topic_score_gemma":0.0021298544,"teacher_disagreement_score":0.0045619067,"about_ca_system_score_codex":0.001358654,"about_ca_system_score_gemma":0.0019962406,"threshold_uncertainty_score":0.019784689},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.20250909729079805,"score_gpt":0.46313926625110025,"score_spread":0.2606301689603022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142971854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035254948,0.0012148488,0.959457,0.0008320826,0.00005525736,0.000042777097,0.000052160478,0.00017878696,0.002912093],"genre_scores_gemma":[0.8497404,0.0009737169,0.14528857,0.00028440903,0.00021749924,0.0003045098,0.0001220478,0.00020141384,0.0028673785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9900691,0.007260599,0.00047015442,0.00063790864,0.0010063457,0.0005558263],"domain_scores_gemma":[0.9136565,0.07833941,0.0026579332,0.00258174,0.002190966,0.00057355623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01741206,0.0018010485,0.0032923566,0.0019395467,0.0010088648,0.0040788027,0.0024635296,0.0041495333,0.0020091971],"category_scores_gemma":[0.08031216,0.001942511,0.0010070892,0.0017059548,0.0026680212,0.0067503364,0.0038569972,0.0032342982,0.0004377603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005399436,0.000094682975,0.0017169504,0.00023331214,0.00024398493,0.00007355642,0.00016216392,0.8388136,0.0012782945,0.11119803,0.00090468815,0.044740878],"study_design_scores_gemma":[0.000044859702,0.000069811096,0.00023162256,0.000039903385,0.000029815594,0.000031734842,0.000018339764,0.94764453,0.00048352723,0.051202465,0.00018079963,0.000022719052],"about_ca_topic_score_codex":0.0011009963,"about_ca_topic_score_gemma":0.00080451055,"teacher_disagreement_score":0.01741206,"about_ca_system_score_codex":0.0013783948,"about_ca_system_score_gemma":0.0016630786,"threshold_uncertainty_score":0.092084885},"labels":[],"label_agreement":null},{"id":"W2142975476","doi":"10.1287/ijoc.2013.0553","title":"Online Sequential Optimization with Biased Gradients: Theory and Applications to Censored Demand","year":2013,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convexity; Mathematical optimization; Convex optimization; Generalization; Convex function; Computer science; Regular polygon; Gradient descent; Mathematics; Artificial intelligence","score_opus":0.05892505650074767,"score_gpt":0.39245925833899264,"score_spread":0.333534201838245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142975476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014487648,0.00071847107,0.9821138,0.00069441466,0.000045807617,0.00004067552,0.00004618578,0.00010881222,0.0017441997],"genre_scores_gemma":[0.735594,0.002301543,0.2549113,0.0004841691,0.00026615945,0.00037503388,0.00020216055,0.00019194574,0.0056737084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981628,0.001014139,0.000070392045,0.00022324405,0.0003848342,0.0001445492],"domain_scores_gemma":[0.9863853,0.010884069,0.0011083264,0.00057156634,0.0008059194,0.000244795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005311024,0.0011896658,0.0016881966,0.00094802765,0.00055415946,0.0013017122,0.0016170624,0.0017448989,0.0020813162],"category_scores_gemma":[0.016377863,0.00088762864,0.0010202918,0.0013048253,0.0023968369,0.0024903978,0.0016827055,0.0022026636,0.00024390935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078223755,0.000060239057,0.0012511456,0.00012306253,0.00008181439,0.00016102508,0.00007411403,0.8435483,0.00066693884,0.13356306,0.0011071272,0.019284846],"study_design_scores_gemma":[0.000009073915,0.000015275135,0.00013235366,0.000008906034,0.000005647786,0.000015616839,0.0000061545143,0.9688588,0.00014657131,0.03049754,0.00029823143,0.0000058467604],"about_ca_topic_score_codex":0.0049410886,"about_ca_topic_score_gemma":0.0034023635,"teacher_disagreement_score":0.005311024,"about_ca_system_score_codex":0.001975571,"about_ca_system_score_gemma":0.0015934281,"threshold_uncertainty_score":0.028087735},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.059531194792093976,"score_gpt":0.4010226266591596,"score_spread":0.34149143186706565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146412174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05013814,0.0006230703,0.9390168,0.001473228,0.00002608127,0.00032057543,0.00049041864,0.00033888477,0.007572813],"genre_scores_gemma":[0.6596367,0.0006551821,0.3317707,0.0005854169,0.00010055062,0.0011234271,0.0008597422,0.00020612826,0.005062092],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97811866,0.014420047,0.000984942,0.0022035337,0.003309565,0.0009631806],"domain_scores_gemma":[0.9381009,0.052016232,0.0025588665,0.0040586344,0.0022113107,0.0010539673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017866135,0.0015671506,0.0037550963,0.0019264248,0.0012410737,0.0034679705,0.0031290667,0.0036611124,0.0064837215],"category_scores_gemma":[0.07282828,0.0015316242,0.0016355749,0.0028040984,0.0030743803,0.0075487383,0.003988513,0.003626079,0.0010636856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071129814,0.00037822447,0.0014317698,0.00028947077,0.00020957818,0.0001443,0.0004543796,0.6066837,0.0011812709,0.32320815,0.0038173082,0.061490472],"study_design_scores_gemma":[0.00009438153,0.000114708564,0.00033319343,0.00004136327,0.000025093716,0.00004267514,0.000068527566,0.7912338,0.00070470484,0.20635054,0.0009546475,0.00003643764],"about_ca_topic_score_codex":0.0027196892,"about_ca_topic_score_gemma":0.0027239616,"teacher_disagreement_score":0.017866135,"about_ca_system_score_codex":0.0038160835,"about_ca_system_score_gemma":0.0024480624,"threshold_uncertainty_score":0.094486296},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13282433303024543,"score_gpt":0.3771460626394505,"score_spread":0.24432172960920506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146807381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021039713,0.0013208907,0.9653597,0.0011651906,0.00008805001,0.000086079264,0.00031046174,0.00034919102,0.010280786],"genre_scores_gemma":[0.8234022,0.0022488963,0.15877241,0.00082478655,0.00048683686,0.00061658706,0.00067343854,0.0004124119,0.012562329],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958156,0.0017593604,0.00014994736,0.0006466042,0.0009794119,0.00064915593],"domain_scores_gemma":[0.9811064,0.014877344,0.0011928976,0.0010759232,0.0012123742,0.00053513603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006679031,0.0019418122,0.0026941383,0.0011941714,0.0011040968,0.003010621,0.0026407735,0.0019712313,0.007131402],"category_scores_gemma":[0.033667017,0.0012857922,0.0013864117,0.0015112781,0.0031642895,0.004328297,0.0031398972,0.004102545,0.0009986812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023416923,0.000055658802,0.0008256343,0.00017252269,0.00008751483,0.00008613339,0.000096161166,0.7194259,0.0008728487,0.25950125,0.0021406463,0.01650166],"study_design_scores_gemma":[0.00001632375,0.00002224109,0.00016436748,0.000027836171,0.000018804725,0.00001578267,0.000009443929,0.9217166,0.00028067915,0.077158,0.00055698736,0.000012902956],"about_ca_topic_score_codex":0.0054607224,"about_ca_topic_score_gemma":0.0052069915,"teacher_disagreement_score":0.007131402,"about_ca_system_score_codex":0.0035771125,"about_ca_system_score_gemma":0.0032721518,"threshold_uncertainty_score":0.035322487},"labels":[],"label_agreement":null},{"id":"W2151101070","doi":"10.2139/ssrn.789464","title":"Evaluating Search and Matching Models Using Experimental Data","year":2005,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Matching (statistics); Computer science; Data mining; Econometrics; Mathematics; Statistics","score_opus":0.46222288934752004,"score_gpt":0.568678542894699,"score_spread":0.10645565354717895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151101070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92020893,0.001520539,0.071006246,0.0012901418,0.00013758907,0.0003833534,0.0013618278,0.0004567646,0.0036345762],"genre_scores_gemma":[0.9701605,0.0003035942,0.025677705,0.00016105248,0.000064481865,0.00034072658,0.0022558484,0.00007840789,0.00095761055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98275083,0.013546009,0.0010075658,0.0013185393,0.0010406503,0.0003363888],"domain_scores_gemma":[0.48766527,0.48441595,0.0074557965,0.01436469,0.005066705,0.0010316265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033193868,0.0015940275,0.0016586825,0.0029826544,0.0009161326,0.0030216172,0.0025269936,0.004884963,0.0058869035],"category_scores_gemma":[0.2606556,0.00088137225,0.0012207197,0.003074117,0.0017930783,0.0061596846,0.0013655156,0.0019593672,0.0017351601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009979248,0.004061622,0.04224704,0.0011847639,0.0013382323,0.00015510691,0.00036788126,0.80677587,0.0018395582,0.024176622,0.005198864,0.10267516],"study_design_scores_gemma":[0.00070498616,0.0011120476,0.0025168792,0.00004540744,0.00020258361,0.00005769053,0.00010957003,0.9731599,0.0017742368,0.019716717,0.0005629526,0.000037009824],"about_ca_topic_score_codex":0.0050690877,"about_ca_topic_score_gemma":0.0037445882,"teacher_disagreement_score":0.033193868,"about_ca_system_score_codex":0.0032811859,"about_ca_system_score_gemma":0.002476987,"threshold_uncertainty_score":0.17554808},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09547229580583252,"score_gpt":0.270794819568804,"score_spread":0.1753225237629715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154806059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052930158,0.00058739504,0.9416018,0.0013457832,0.00006902346,0.00011683149,0.0001843134,0.000466921,0.0026977595],"genre_scores_gemma":[0.88327056,0.0006921391,0.109276004,0.00043283802,0.00015018502,0.00042344953,0.000375275,0.00015274124,0.005226795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99643505,0.0016822458,0.00012322013,0.0009166147,0.00033243903,0.0005104079],"domain_scores_gemma":[0.9691498,0.027256545,0.0016029852,0.0008671125,0.00047077253,0.00065273925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005563384,0.0018469355,0.0025232106,0.0007986809,0.0009791711,0.0021668463,0.0024062193,0.0026419733,0.0036247652],"category_scores_gemma":[0.020087134,0.0012756141,0.0015448953,0.0012229781,0.003011391,0.0043382565,0.002902901,0.0049208337,0.00045430442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016444158,0.000079924204,0.0005573628,0.00006642406,0.000052199277,0.000094592724,0.000054337906,0.96142036,0.00024654288,0.029944438,0.00045587323,0.006863462],"study_design_scores_gemma":[0.000023312443,0.000027558403,0.000053465104,0.0000050229573,0.000006567874,0.000010043794,0.000006468935,0.9662714,0.00014614617,0.03331891,0.00012621304,0.0000048860365],"about_ca_topic_score_codex":0.006291115,"about_ca_topic_score_gemma":0.004276509,"teacher_disagreement_score":0.006291115,"about_ca_system_score_codex":0.003360484,"about_ca_system_score_gemma":0.0024776964,"threshold_uncertainty_score":0.029422283},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.20504333039520903,"score_gpt":0.5069362652545172,"score_spread":0.3018929348593081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156211713","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07089176,0.00034312037,0.920385,0.0015067472,0.000105480176,0.00011676818,0.00024983723,0.0002135221,0.0061878464],"genre_scores_gemma":[0.90538144,0.00051680877,0.08349757,0.00023034416,0.00016210446,0.0003366682,0.00024383454,0.00003944586,0.009591855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99710053,0.0011563782,0.000111618836,0.0007027158,0.00039388158,0.0005347928],"domain_scores_gemma":[0.9923379,0.005422144,0.0009176061,0.00050529424,0.00036899647,0.00044811185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036373828,0.0016218864,0.0020326502,0.00063432887,0.00087395916,0.0023136684,0.0028284492,0.0031669892,0.0036075928],"category_scores_gemma":[0.013209074,0.0007958619,0.0011872556,0.0010741932,0.0027028492,0.0031415334,0.0019952215,0.0034484959,0.0006649224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018926384,0.00010482749,0.00090821786,0.00006004055,0.000054646487,0.0003183068,0.000091663096,0.7284779,0.0005521195,0.26250985,0.0006348015,0.00609842],"study_design_scores_gemma":[0.00004260061,0.00002976945,0.00007822416,0.000005410485,0.000010907394,0.000017370892,0.00000825331,0.93349445,0.00017981461,0.065788545,0.0003328132,0.000011731067],"about_ca_topic_score_codex":0.0057931263,"about_ca_topic_score_gemma":0.003610947,"teacher_disagreement_score":0.0057931263,"about_ca_system_score_codex":0.002037786,"about_ca_system_score_gemma":0.001622648,"threshold_uncertainty_score":0.019236565},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08846169459235069,"score_gpt":0.44501094081824716,"score_spread":0.35654924622589645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157016390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20909174,0.0009927668,0.77643555,0.0028741555,0.00014968752,0.00015980021,0.0005195177,0.0005569358,0.009219809],"genre_scores_gemma":[0.9780146,0.00034720113,0.01567182,0.000225461,0.00008952453,0.00019689361,0.00016987832,0.000043511518,0.0052411333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969409,0.0013939807,0.00012149365,0.0005448079,0.00037331606,0.0006255726],"domain_scores_gemma":[0.9782282,0.017116597,0.0022612347,0.00066895096,0.0009330076,0.00079194055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052701733,0.0013573238,0.0026089624,0.0008460726,0.0010538388,0.0024964155,0.0015607858,0.0025033143,0.004531298],"category_scores_gemma":[0.019908108,0.00083786005,0.00078497146,0.0011011583,0.002874091,0.0027672485,0.0020072048,0.0027824752,0.00069809664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003509131,0.00009438556,0.0012174685,0.000071946924,0.000049328428,0.00021034785,0.000105797175,0.8608178,0.00036792003,0.13078159,0.0010347174,0.004897768],"study_design_scores_gemma":[0.000027359158,0.000018196906,0.00009603863,0.000009112238,0.0000067483993,0.000011521882,0.000008856048,0.969237,0.00010588568,0.030353906,0.000117814285,0.0000075151993],"about_ca_topic_score_codex":0.009546356,"about_ca_topic_score_gemma":0.0053953244,"teacher_disagreement_score":0.009546356,"about_ca_system_score_codex":0.0033316463,"about_ca_system_score_gemma":0.0016417799,"threshold_uncertainty_score":0.027871668},"labels":[],"label_agreement":null},{"id":"W2157140780","doi":"10.1007/978-3-642-16108-7_20","title":"Toward a Classification of Finite Partial-Monitoring Games","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.1545661084896942,"score_gpt":0.40540969760175927,"score_spread":0.25084358911206506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157140780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19289507,0.0013383658,0.74190587,0.0022431288,0.00018599037,0.00032837188,0.0010731973,0.00063254515,0.05939753],"genre_scores_gemma":[0.81303555,0.0015144582,0.15643129,0.00076577853,0.00052569085,0.0006599006,0.0021405506,0.0002580834,0.024668682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998058,0.00053938164,0.00016985892,0.00042969984,0.00045798448,0.0003450796],"domain_scores_gemma":[0.99152094,0.0056442833,0.00069922616,0.0007045383,0.0005898582,0.0008411971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00245328,0.0013724283,0.0021430075,0.0021995616,0.0014348454,0.006085284,0.0032270763,0.0023629665,0.0073269703],"category_scores_gemma":[0.009946678,0.00080143724,0.0018838492,0.0021315091,0.0028583098,0.00662261,0.0024173993,0.005589872,0.0008378772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005197865,0.00006539504,0.0007436402,0.0000640089,0.000018234776,0.000033828124,0.00015793389,0.0062717125,0.0005081056,0.9758779,0.0026290503,0.013578226],"study_design_scores_gemma":[0.000028146611,0.000035510682,0.00038803468,0.000040858948,0.000015416983,0.000070307135,0.00005179789,0.07408147,0.00020978927,0.9229431,0.0021185933,0.000016955157],"about_ca_topic_score_codex":0.0016066242,"about_ca_topic_score_gemma":0.0014315248,"teacher_disagreement_score":0.0073269703,"about_ca_system_score_codex":0.0025819943,"about_ca_system_score_gemma":0.0019617195,"threshold_uncertainty_score":0.024511099},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1076079387823779,"score_gpt":0.4263062865630172,"score_spread":0.3186983477806393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160163723","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037731186,0.0009692831,0.95412046,0.0014108187,0.000060931587,0.00008029519,0.00014756367,0.0002199762,0.005259498],"genre_scores_gemma":[0.89313585,0.0010100964,0.09912643,0.0005110618,0.00020349037,0.00028235491,0.00014074279,0.000086485226,0.0055035776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99647224,0.002164506,0.00010142146,0.0005368181,0.0003780416,0.00034698195],"domain_scores_gemma":[0.9866454,0.009924301,0.0017244352,0.0010477927,0.00039246408,0.00026560933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004796262,0.0013751012,0.0023145678,0.000966577,0.0007434839,0.0030752777,0.002419904,0.00298553,0.003788901],"category_scores_gemma":[0.026909564,0.00074971037,0.0010912233,0.0017863333,0.0029175791,0.004336558,0.002557728,0.0039198194,0.0007395204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009152276,0.00006761034,0.0008007946,0.00010049221,0.000076141354,0.00031032684,0.00011179488,0.753856,0.00039801124,0.2226601,0.0013870557,0.020140214],"study_design_scores_gemma":[0.000015739499,0.00002467084,0.0001114829,0.000013177158,0.000009080822,0.000050951883,0.000023607492,0.9104796,0.00011367402,0.088691205,0.0004545712,0.00001219739],"about_ca_topic_score_codex":0.0027934387,"about_ca_topic_score_gemma":0.002219034,"teacher_disagreement_score":0.004796262,"about_ca_system_score_codex":0.0013586663,"about_ca_system_score_gemma":0.0009697663,"threshold_uncertainty_score":0.025365412},"labels":[],"label_agreement":null},{"id":"W2160262323","doi":"10.48550/arxiv.1306.0686","title":"Online Learning under Delayed Feedback","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Online learning; Computer science; Multiplicative function; Feedback loop; Adversarial system; Black box; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Multimedia; World Wide Web","score_opus":0.2569419831242067,"score_gpt":0.3170267194651759,"score_spread":0.060084736340969225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160262323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058907688,0.0014520548,0.93333375,0.001122851,0.00014881339,0.000058467715,0.0001546861,0.00039829046,0.004423437],"genre_scores_gemma":[0.95116526,0.0008245999,0.04341134,0.00027711954,0.00017600718,0.00013823278,0.00009999602,0.000064246706,0.0038432414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842584,0.0006215355,0.00006581825,0.00036358566,0.0002918004,0.00023142339],"domain_scores_gemma":[0.99077153,0.0071059153,0.0007309522,0.00060029223,0.0005193117,0.0002720038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025814038,0.0010138415,0.0013105932,0.0004577789,0.00048773157,0.001521799,0.0012794056,0.0016036121,0.0018587656],"category_scores_gemma":[0.01641861,0.0004202592,0.00044818825,0.00061237917,0.0014889423,0.002427549,0.0014070382,0.002005178,0.00032752776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038359367,0.00008576029,0.0007067217,0.00021997995,0.00005962134,0.00009111931,0.00006499452,0.84457296,0.0016071646,0.12279936,0.0018608212,0.027547901],"study_design_scores_gemma":[0.00003927886,0.00006162743,0.00009318207,0.000016936958,0.000012994552,0.000022243199,0.000007441031,0.9322973,0.0007163723,0.06623557,0.00049034384,0.000006727676],"about_ca_topic_score_codex":0.001509497,"about_ca_topic_score_gemma":0.0009661043,"teacher_disagreement_score":0.0025814038,"about_ca_system_score_codex":0.0018915226,"about_ca_system_score_gemma":0.0012813604,"threshold_uncertainty_score":0.013724029},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12027882754212588,"score_gpt":0.45583294118547746,"score_spread":0.3355541136433516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160367301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012722873,0.00011747364,0.99491924,0.00028893346,0.000020951478,0.00003976514,0.000035993224,0.000037074307,0.003268378],"genre_scores_gemma":[0.32205784,0.001386229,0.6625615,0.0004318824,0.00037044083,0.0009255136,0.00021517245,0.0001268542,0.011924576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99748105,0.0012141089,0.000112403555,0.00030886507,0.00067588035,0.0002077668],"domain_scores_gemma":[0.9978557,0.0009698897,0.00026225834,0.00035619322,0.00039853744,0.00015733032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005783459,0.0013944115,0.0015022355,0.0012425381,0.00085370115,0.0033942275,0.0031403673,0.0021605992,0.007143293],"category_scores_gemma":[0.0078331875,0.0008027393,0.0012569873,0.0013183972,0.0025760417,0.0053193,0.0025777908,0.0036233102,0.0011448943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014969484,0.000029383722,0.00006377677,0.00003215417,0.000012822971,0.000040599683,0.000032534062,0.07278082,0.00038648254,0.9157636,0.00094679603,0.009896081],"study_design_scores_gemma":[0.000024339128,0.0000466433,0.00004319679,0.00001712635,0.00000931402,0.000042366944,0.000014721025,0.46762943,0.00028419716,0.52790475,0.0039681513,0.00001568202],"about_ca_topic_score_codex":0.0008465125,"about_ca_topic_score_gemma":0.0010067486,"teacher_disagreement_score":0.007143293,"about_ca_system_score_codex":0.0019359124,"about_ca_system_score_gemma":0.0024788138,"threshold_uncertainty_score":0.030586183},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2241001579878948,"score_gpt":0.4240967083286237,"score_spread":0.19999655034072888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161571887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07267887,0.001006234,0.92116463,0.0012536728,0.0000792776,0.00010801245,0.0003828691,0.0005200697,0.00280624],"genre_scores_gemma":[0.8647495,0.00095647306,0.12387999,0.0003394552,0.00020822152,0.0003193715,0.000650094,0.000110067114,0.008786843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863786,0.00057378033,0.000075771044,0.00033160264,0.00016067081,0.00022027188],"domain_scores_gemma":[0.9896399,0.008080059,0.0011674147,0.00048794394,0.0002473749,0.00037732362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032148305,0.0015928751,0.0026695062,0.00061279227,0.0007070387,0.001812933,0.002372097,0.0028819346,0.00450966],"category_scores_gemma":[0.011228403,0.00096574903,0.001037949,0.0015827542,0.0015036623,0.0031517402,0.0017842801,0.0035336006,0.00094119087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063643965,0.00012013477,0.00095560466,0.00015760244,0.00009059777,0.00024029899,0.00009367694,0.9267729,0.00081392756,0.04149261,0.0016479266,0.02697835],"study_design_scores_gemma":[0.00004297071,0.00007288507,0.00014196808,0.00001354326,0.000017397786,0.00003996569,0.00001663903,0.96688455,0.00027032816,0.0321991,0.00029011111,0.000010499309],"about_ca_topic_score_codex":0.0028718847,"about_ca_topic_score_gemma":0.001702254,"teacher_disagreement_score":0.00450966,"about_ca_system_score_codex":0.0013148955,"about_ca_system_score_gemma":0.0010208917,"threshold_uncertainty_score":0.017001867},"labels":[],"label_agreement":null},{"id":"W2161790782","doi":"10.1145/1553374.1553500","title":"A simpler unified analysis of budget perceptrons","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perceptron; Computer science; Regret; Mathematical proof; Regularization (linguistics); Algorithm; Set (abstract data type); Mathematical optimization; Artificial intelligence; Machine learning; Artificial neural network; Mathematics","score_opus":0.13430457853375094,"score_gpt":0.4873831615531908,"score_spread":0.35307858301943984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161790782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007507497,0.0022765682,0.968789,0.0022193803,0.00020708096,0.00006807783,0.00020228335,0.00035982,0.018370317],"genre_scores_gemma":[0.62025243,0.0077741407,0.3156947,0.003339953,0.0022491126,0.0007510019,0.0008585115,0.0011279008,0.04795228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960188,0.0015000335,0.00014952637,0.000610379,0.0011732292,0.00054801244],"domain_scores_gemma":[0.9928767,0.0043129288,0.0007020652,0.0009337977,0.00089421973,0.0002802459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00733724,0.002361245,0.0024815423,0.0018858202,0.0010351589,0.004411575,0.0036178916,0.0029747966,0.012854147],"category_scores_gemma":[0.026231492,0.0011790443,0.0019839683,0.0019920971,0.0030881371,0.010626035,0.003729569,0.0066597364,0.0021429444],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012271495,0.00006224832,0.00042570615,0.00019624594,0.00006661101,0.00006953353,0.000094630195,0.13297865,0.0009867122,0.8378745,0.005649989,0.021472566],"study_design_scores_gemma":[0.000020553784,0.00005121799,0.00028379142,0.00008525255,0.000027124785,0.000047386566,0.000017947821,0.5463308,0.0004361504,0.44935766,0.0033155584,0.000026519445],"about_ca_topic_score_codex":0.003392225,"about_ca_topic_score_gemma":0.0024341955,"teacher_disagreement_score":0.012854147,"about_ca_system_score_codex":0.003429648,"about_ca_system_score_gemma":0.0022163307,"threshold_uncertainty_score":0.043001473},"labels":[],"label_agreement":null},{"id":"W2168337246","doi":"10.1109/cdc.2007.4434388","title":"Decentralized adaptation in sensor networks: Analysis and application of regret-based algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Wireless sensor network; Computer science; Overhead (engineering); Class (philosophy); Correlated equilibrium; Matching (statistics); Set (abstract data type); Distributed computing; Scheme (mathematics); Adaptation (eye); Game theory; Algorithm; Real-time computing; Computer network; Repeated game; Artificial intelligence; Mathematics; Machine learning; Equilibrium selection","score_opus":0.06504570463724091,"score_gpt":0.4214379622264054,"score_spread":0.3563922575891645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168337246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072277905,0.0010064541,0.98668903,0.00053116813,0.00007117257,0.00005352402,0.000026492675,0.00012619508,0.0042682476],"genre_scores_gemma":[0.8292336,0.0031163706,0.15989378,0.00040305473,0.0006072668,0.00045830425,0.0001092246,0.00020104315,0.00597742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731195,0.0013672784,0.00009239472,0.00032298142,0.00067945704,0.00022597013],"domain_scores_gemma":[0.9896197,0.007894771,0.0010427518,0.00049176184,0.00077757536,0.00017352139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006000014,0.0011725684,0.0014089006,0.0009439308,0.00067193294,0.0015255067,0.0023543066,0.0017870101,0.0017401933],"category_scores_gemma":[0.020873703,0.00060366077,0.0010202753,0.0013624681,0.0021249228,0.0024410274,0.0016266761,0.0021513966,0.00026809226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022675194,0.000026808362,0.00034254836,0.00006231912,0.000045008648,0.000035666046,0.000044869834,0.90004826,0.00032844458,0.08736377,0.0007597057,0.010920025],"study_design_scores_gemma":[0.0000049264977,0.00001246085,0.00009030424,0.0000061938977,0.000005783669,0.000016643526,0.000005292584,0.97428244,0.000074964795,0.025145937,0.00035038672,0.0000046320347],"about_ca_topic_score_codex":0.0029044265,"about_ca_topic_score_gemma":0.0015584424,"teacher_disagreement_score":0.006000014,"about_ca_system_score_codex":0.001995121,"about_ca_system_score_gemma":0.0014550401,"threshold_uncertainty_score":0.031731486},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.100663809997761,"score_gpt":0.4084052332996377,"score_spread":0.3077414233018767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170307371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073376847,0.00064919685,0.9889731,0.00057433307,0.000031212232,0.000037845835,0.000043691554,0.0001244671,0.0022283928],"genre_scores_gemma":[0.6324829,0.0024756468,0.35676435,0.00077670795,0.00033389803,0.0008702309,0.00029056633,0.0003961169,0.005609708],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943281,0.0041272053,0.00017958341,0.00036129146,0.0006885232,0.0003152719],"domain_scores_gemma":[0.96774924,0.02836379,0.0017696576,0.00092250796,0.0008928834,0.00030190533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012589779,0.0018710366,0.0032834138,0.0012456154,0.0010630863,0.002910195,0.001951497,0.0026837857,0.0031895996],"category_scores_gemma":[0.047816798,0.0016584774,0.0011545361,0.0024682472,0.0028252834,0.004776639,0.0029523997,0.0032648458,0.00051862915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000637394,0.000035022364,0.0002828123,0.0000772104,0.00003900244,0.000046358527,0.00006248183,0.9014193,0.0002117823,0.08611374,0.00075181364,0.010896625],"study_design_scores_gemma":[0.000009216778,0.000014042305,0.00005504857,0.000021894011,0.0000060864713,0.000009310244,0.0000068182017,0.96845925,0.00009840572,0.031032866,0.00027790022,0.000009125981],"about_ca_topic_score_codex":0.0076996097,"about_ca_topic_score_gemma":0.005589286,"teacher_disagreement_score":0.012589779,"about_ca_system_score_codex":0.002441917,"about_ca_system_score_gemma":0.0034592755,"threshold_uncertainty_score":0.066581905},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.28759561229267017,"score_gpt":0.45380007657920457,"score_spread":0.1662044642865344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187589363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09907216,0.0006999891,0.8687998,0.0039617675,0.00026132946,0.0007404839,0.0021235107,0.0010637727,0.023277234],"genre_scores_gemma":[0.74721855,0.00048045788,0.23131214,0.0005060484,0.0002896482,0.00069988426,0.0012445495,0.00014301165,0.018105617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504375,0.002157991,0.00018102788,0.0012686067,0.00066574244,0.00068292604],"domain_scores_gemma":[0.99084985,0.0060558883,0.0005885656,0.0014403276,0.0003503242,0.0007150516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052453163,0.0019372469,0.002822947,0.0008521411,0.0016781674,0.0031627466,0.004663469,0.0038463697,0.020246668],"category_scores_gemma":[0.014844216,0.0010430207,0.0010955804,0.0024515453,0.0020628427,0.00787784,0.003018651,0.0028036092,0.0018931635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019419678,0.0009998715,0.0022600663,0.00041515497,0.00020853881,0.0004947177,0.00033871023,0.6778135,0.0014745166,0.20058998,0.015355512,0.09810754],"study_design_scores_gemma":[0.00021632921,0.00009520914,0.00027236223,0.000023267632,0.000026388772,0.00009031663,0.00006494161,0.86231226,0.0006969288,0.13228501,0.0038953188,0.000021660615],"about_ca_topic_score_codex":0.0046842117,"about_ca_topic_score_gemma":0.007004426,"teacher_disagreement_score":0.020246668,"about_ca_system_score_codex":0.0036025841,"about_ca_system_score_gemma":0.0024047948,"threshold_uncertainty_score":0.0677318},"labels":[],"label_agreement":null},{"id":"W2189148180","doi":"","title":"Linear multi-resource allocation with semi-bandit feedback","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Task (project management); Resource allocation; Mathematical optimization; Resource (disambiguation); Hypercube; Noise (video); Resource management (computing); Distributed computing; Artificial intelligence; Machine learning; Mathematics; Engineering","score_opus":0.17021817587683175,"score_gpt":0.40578447418840363,"score_spread":0.2355662983115719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189148180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050141692,0.0011793529,0.9411966,0.0014052001,0.00014052168,0.000109054985,0.00016502247,0.0003427577,0.005319718],"genre_scores_gemma":[0.9106666,0.0005999363,0.08011164,0.0005231929,0.00020478175,0.00031363041,0.00017475184,0.00009434422,0.007311143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712604,0.0016080446,0.000117151234,0.00042004875,0.0003733291,0.00035528655],"domain_scores_gemma":[0.9859555,0.0116011845,0.0010433964,0.00044747946,0.0005864671,0.00036594135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046566236,0.0016679371,0.0028075809,0.0006033864,0.00057715335,0.0020746093,0.0017977408,0.0026419156,0.0039855186],"category_scores_gemma":[0.01796605,0.00101398,0.00074205274,0.0012913948,0.0023932252,0.002698834,0.0018570033,0.0024936919,0.00072970736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020835077,0.00007624349,0.00027939954,0.00009157399,0.000047484307,0.00008223055,0.00004810502,0.9669283,0.00034359194,0.023920663,0.00074560964,0.0072284746],"study_design_scores_gemma":[0.000021291044,0.000025948675,0.00003960929,0.000006844064,0.0000059464755,0.000010030473,0.000006032451,0.9871996,0.00010655334,0.012449367,0.0001238216,0.0000049000655],"about_ca_topic_score_codex":0.0038174414,"about_ca_topic_score_gemma":0.002716131,"teacher_disagreement_score":0.0046566236,"about_ca_system_score_codex":0.0017667986,"about_ca_system_score_gemma":0.0014921409,"threshold_uncertainty_score":0.02462691},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2723421006942705,"score_gpt":0.49421710476191894,"score_spread":0.22187500406764843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2192203593","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023370594,0.9822565,0.010803259,0.0023351645,0.00025476379,0.000009733281,0.000033598415,0.000019920095,0.0040533324],"genre_scores_gemma":[0.004164895,0.988736,0.0051932936,0.00051816995,0.00059732725,0.000019682899,0.00004214359,0.000014032218,0.00071457174],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987852,0.00044250008,0.00012391945,0.0001805149,0.00041454073,0.00005326462],"domain_scores_gemma":[0.9946561,0.0041904105,0.00023575868,0.00010893862,0.000711973,0.000096810545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029673583,0.0012618816,0.0019424742,0.0025676873,0.0005110762,0.0021801174,0.0016784902,0.0020723664,0.0035354882],"category_scores_gemma":[0.0075345114,0.00064325175,0.0008398872,0.004857996,0.0017462932,0.0026893497,0.0009331733,0.0020823632,0.0018674851],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058944777,0.00009953,0.0006638317,0.01271232,0.00017667007,0.00010498317,0.00014736819,0.008060265,0.00031401945,0.091303416,0.037005562,0.84935313],"study_design_scores_gemma":[0.000031140862,0.00014987939,0.0016191445,0.011852763,0.00023989566,0.0006263572,0.00022769686,0.006925553,0.00069018983,0.11545762,0.86206025,0.000119413606],"about_ca_topic_score_codex":0.0050247433,"about_ca_topic_score_gemma":0.0057902406,"teacher_disagreement_score":0.0050247433,"about_ca_system_score_codex":0.0017306422,"about_ca_system_score_gemma":0.0032978628,"threshold_uncertainty_score":0.015693069},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15649261927558675,"score_gpt":0.4209362025593321,"score_spread":0.2644435832837454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2193897973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033068616,0.00755549,0.9330885,0.002185282,0.00033786116,0.00007458657,0.00011608507,0.00015123349,0.02342243],"genre_scores_gemma":[0.9064641,0.0069582774,0.069746435,0.00052425923,0.00047319828,0.00021163492,0.00011875345,0.000048987156,0.015454327],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994752,0.0003118902,0.000017171573,0.000045044366,0.00007854686,0.00007228172],"domain_scores_gemma":[0.9975968,0.0018728802,0.00020123101,0.000058828682,0.00018751695,0.000082671955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012592144,0.0010937627,0.0010211413,0.00049032195,0.0005591609,0.0015614555,0.000678119,0.0017141929,0.0036389853],"category_scores_gemma":[0.0048828614,0.00030067054,0.0005712509,0.0009778109,0.0011054919,0.00087495317,0.000988085,0.0019245287,0.00043791346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009368896,0.000050446393,0.0007082959,0.00012822529,0.000046396923,0.00019575589,0.00008766383,0.8070167,0.00067450973,0.17024979,0.0025674046,0.018181222],"study_design_scores_gemma":[0.000010636708,0.00003260431,0.00010478259,0.0000193136,0.000009601431,0.000025084038,0.000025074041,0.9653009,0.000118688164,0.032818746,0.0015277128,0.0000068514296],"about_ca_topic_score_codex":0.003574114,"about_ca_topic_score_gemma":0.002647175,"teacher_disagreement_score":0.0036389853,"about_ca_system_score_codex":0.0011031312,"about_ca_system_score_gemma":0.0005948951,"threshold_uncertainty_score":0.012173593},"labels":[],"label_agreement":null},{"id":"W2203325308","doi":"10.48550/arxiv.1206.6487","title":"An Adaptive Algorithm for Finite Stochastic Partial Monitoring","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Algorithm","score_opus":0.3480788863386984,"score_gpt":0.3467574326496035,"score_spread":0.0013214536890948647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2203325308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017283738,0.00010267054,0.9781723,0.0003750307,0.0000559352,0.00008644267,0.000077193894,0.0008980009,0.002948748],"genre_scores_gemma":[0.46624452,0.00010691005,0.5274273,0.0003492608,0.000086590524,0.00032598464,0.00026918997,0.00021162155,0.0049786572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984067,0.00039108156,0.000091845686,0.0005120601,0.00037601247,0.00022226752],"domain_scores_gemma":[0.99756515,0.0011693125,0.00027996566,0.00059748563,0.000203478,0.00018471663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001593957,0.00078804244,0.0010859289,0.000513127,0.0005916435,0.00149506,0.0030251935,0.001525888,0.0041022506],"category_scores_gemma":[0.0072394805,0.0003602157,0.0007925123,0.0007485532,0.0011375904,0.0028327773,0.0021576365,0.0021815493,0.0008218184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007036824,0.00035707344,0.002595569,0.00019794362,0.00012674555,0.00017369994,0.00031091154,0.44917703,0.009013494,0.23028228,0.009274846,0.29778683],"study_design_scores_gemma":[0.00006276979,0.000046936333,0.0001226266,0.000009250927,0.000013966673,0.00005754309,0.000012473998,0.94689864,0.0015417536,0.049882285,0.001338935,0.000012828132],"about_ca_topic_score_codex":0.001607289,"about_ca_topic_score_gemma":0.0022384578,"teacher_disagreement_score":0.0041022506,"about_ca_system_score_codex":0.0014498526,"about_ca_system_score_gemma":0.0019052958,"threshold_uncertainty_score":0.013723433},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14211577694936595,"score_gpt":0.45600520281474183,"score_spread":0.3138894258653759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206616202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006022713,0.0001431488,0.9912463,0.00019534744,0.000030158702,0.00004444904,0.000051683684,0.00035165588,0.001914541],"genre_scores_gemma":[0.54569155,0.000507416,0.4475973,0.00047186067,0.0002554483,0.00055690255,0.00040186048,0.0004151291,0.0041026273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951138,0.0018120776,0.00030677332,0.0006742358,0.0017765866,0.00031657895],"domain_scores_gemma":[0.9783247,0.015725221,0.0014174278,0.002657933,0.0014228749,0.00045183543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065100654,0.0014359108,0.0019568373,0.0013212193,0.0007602079,0.0028794801,0.0027645892,0.00198781,0.0045980043],"category_scores_gemma":[0.049323738,0.00091535074,0.001263779,0.0016206654,0.0029122545,0.0040026153,0.00472884,0.00624052,0.0009461738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021715331,0.00020270499,0.0011103133,0.00016054083,0.00007607191,0.00017223845,0.00021020781,0.5635912,0.00234762,0.31060928,0.0020043189,0.11929844],"study_design_scores_gemma":[0.000021488924,0.000036845227,0.00010407427,0.000024039891,0.0000079886095,0.000047383943,0.000007859058,0.9216999,0.0014005947,0.07591629,0.0007151805,0.000018342802],"about_ca_topic_score_codex":0.0011558348,"about_ca_topic_score_gemma":0.00079991773,"teacher_disagreement_score":0.0065100654,"about_ca_system_score_codex":0.0013860526,"about_ca_system_score_gemma":0.0014069839,"threshold_uncertainty_score":0.034428895},"labels":[],"label_agreement":null},{"id":"W2222041227","doi":"10.6084/m9.figshare.1448973.v1","title":"Human behavior in contextual multi-armed bandit problems - Poster presented at Reinforcement learning and decision making conference in 2015","year":2015,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Computer science; Machine learning; Psychology; Social psychology","score_opus":0.33005442763166004,"score_gpt":0.4855699151820237,"score_spread":0.15551548755036365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222041227","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7106415,0.0025963075,0.2568624,0.005819944,0.00036508765,0.00022042847,0.0004866895,0.00042604888,0.022581482],"genre_scores_gemma":[0.9706778,0.00041035688,0.02647131,0.00021342194,0.000040921317,0.000090210524,0.00015631103,0.000025827047,0.0019139379],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99864477,0.0009219439,0.000034470264,0.00020622558,0.00009615087,0.00009639979],"domain_scores_gemma":[0.9968876,0.0021858755,0.0002610285,0.0002635765,0.00016933773,0.00023253293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002713972,0.00048238927,0.00056892715,0.00025433407,0.00052325,0.0015723761,0.00043602253,0.0011531399,0.0039881393],"category_scores_gemma":[0.010057756,0.0002424269,0.00035565472,0.00029000375,0.00095891836,0.0011816173,0.0008874091,0.0014076615,0.0004923266],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021849992,0.0011882881,0.02557132,0.00048491446,0.00047979504,0.00030030392,0.0012497338,0.6630471,0.011372279,0.068991475,0.017144961,0.20798476],"study_design_scores_gemma":[0.0001148184,0.0006562255,0.013606492,0.000088342225,0.000061626015,0.000095939584,0.00046150005,0.87347007,0.0023076853,0.10439705,0.004668346,0.00007189011],"about_ca_topic_score_codex":0.002310472,"about_ca_topic_score_gemma":0.0030605276,"teacher_disagreement_score":0.0039881393,"about_ca_system_score_codex":0.0006872323,"about_ca_system_score_gemma":0.00047401854,"threshold_uncertainty_score":0.014353037},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06434972756859121,"score_gpt":0.36376769200267167,"score_spread":0.2994179644340805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2241126168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036399446,0.00023105154,0.9605227,0.0005289506,0.000044842116,0.000054795193,0.0001272511,0.00015669882,0.0019343339],"genre_scores_gemma":[0.874408,0.00040598275,0.11981918,0.00017991579,0.00011162333,0.00018638633,0.00027670545,0.000078197736,0.0045340024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884987,0.00046042752,0.000043136522,0.00035855052,0.00014268128,0.00014540288],"domain_scores_gemma":[0.99596894,0.002974952,0.00048678782,0.00022175274,0.00013520329,0.0002123471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001669297,0.0010256617,0.0014791765,0.000522365,0.00052296155,0.0010825281,0.001665679,0.0019245801,0.002106568],"category_scores_gemma":[0.006066394,0.0005004141,0.0006960881,0.0006602083,0.0016725536,0.0022598214,0.0013244691,0.0017826088,0.00026116765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059570724,0.000031080424,0.0002858558,0.00003476649,0.000029191984,0.000078474615,0.000026875814,0.966005,0.0002870288,0.027205065,0.000386792,0.005570294],"study_design_scores_gemma":[0.0000099358795,0.0000148511235,0.0000407769,0.0000027162432,0.000004061915,0.00001190139,0.000003677359,0.9778431,0.00013572341,0.021727378,0.00020225583,0.0000036262072],"about_ca_topic_score_codex":0.0032033569,"about_ca_topic_score_gemma":0.0019647859,"teacher_disagreement_score":0.0032033569,"about_ca_system_score_codex":0.0011937341,"about_ca_system_score_gemma":0.0013158526,"threshold_uncertainty_score":0.008828223},"labels":[],"label_agreement":null},{"id":"W2266817871","doi":"","title":"An expectation-maximization algorithm to compute a stochastic factorization from data","year":2015,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Stochastic matrix; Markov chain; Factorization; Algorithm; Matrix (chemical analysis); Computer science; Matrix decomposition; Matrix multiplication; Probabilistic logic; Mathematical optimization; Markov decision process; Markov process; Mathematics; Artificial intelligence; Machine learning","score_opus":0.6099591275582319,"score_gpt":0.5389729520319333,"score_spread":0.0709861755262986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266817871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077395706,0.000038540533,0.9984156,0.00007393684,0.0000163764,0.000036522724,0.00003506934,0.0003914983,0.00021844092],"genre_scores_gemma":[0.04158413,0.00012861706,0.9561656,0.0001446832,0.00005665957,0.00040608904,0.00037567073,0.0001416548,0.000996871],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887735,0.000456531,0.00008552792,0.00026606765,0.00023415805,0.000080475795],"domain_scores_gemma":[0.996799,0.002450673,0.00016585445,0.0002103859,0.00029202117,0.00008199381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029349087,0.0018317744,0.0015332156,0.0012290078,0.0006820237,0.0011823925,0.0019402438,0.0014285967,0.006992678],"category_scores_gemma":[0.009147091,0.0010884544,0.0013795531,0.0015795038,0.0010427808,0.0017289304,0.0018244227,0.0032821766,0.0023853884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019194486,0.00025252244,0.0013303622,0.0003402938,0.0002807191,0.00016113433,0.00015892087,0.5769126,0.0049337023,0.049574934,0.009350187,0.3565127],"study_design_scores_gemma":[0.000024525396,0.00002761217,0.000086260676,0.000011746559,0.000013413174,0.000032002004,0.000009426876,0.9802202,0.00073728187,0.017618168,0.0012094091,0.000009943177],"about_ca_topic_score_codex":0.006458485,"about_ca_topic_score_gemma":0.008442705,"teacher_disagreement_score":0.006992678,"about_ca_system_score_codex":0.0012265916,"about_ca_system_score_gemma":0.003184216,"threshold_uncertainty_score":0.023392797},"labels":[],"label_agreement":null},{"id":"W2275726605","doi":"10.1007/bfb0009401","title":"On the bandit problem","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in control and information sciences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science","score_opus":0.04962082229917428,"score_gpt":0.3466692124861482,"score_spread":0.29704839018697393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2275726605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05310294,0.0095958095,0.63038445,0.017788418,0.0013078288,0.00007259396,0.0003637606,0.00020145325,0.28718272],"genre_scores_gemma":[0.73632383,0.011313001,0.07841022,0.004104055,0.0038114071,0.00048420785,0.0009300333,0.00046934214,0.1641539],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987134,0.00063576864,0.00004752108,0.00018418209,0.00027131452,0.00014790263],"domain_scores_gemma":[0.99465984,0.0041840607,0.00030704454,0.0003512382,0.0003115388,0.00018621789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002040003,0.0011358914,0.0017870247,0.0011581013,0.00173545,0.004624509,0.0013353855,0.0032466594,0.01529427],"category_scores_gemma":[0.01420247,0.0006382138,0.00087120873,0.0021199258,0.0038521674,0.006498602,0.003028081,0.0057946453,0.0020853342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024700621,0.000012413561,0.00006820854,0.000036161116,0.000009183456,0.000019686724,0.00004420474,0.0051950878,0.00007965606,0.9846538,0.0042303605,0.0056265336],"study_design_scores_gemma":[0.000009438696,0.000005269065,0.000050554787,0.000020348287,0.000004451913,0.00001545109,0.000020039313,0.019451823,0.00004095641,0.9781545,0.002222321,0.000004839156],"about_ca_topic_score_codex":0.0016608561,"about_ca_topic_score_gemma":0.0010485841,"teacher_disagreement_score":0.01529427,"about_ca_system_score_codex":0.0015456966,"about_ca_system_score_gemma":0.0009285587,"threshold_uncertainty_score":0.05116445},"labels":[],"label_agreement":null},{"id":"W2281341692","doi":"10.48550/arxiv.1602.07905","title":"Thompson Sampling is Asymptotically Optimal in General Environments","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Asymptotically optimal algorithm; Mathematics; Mathematical economics; Applied mathematics; Computer science; Geography; Environmental science; Statistics; Mathematical optimization; Telecommunications","score_opus":0.2727705402762734,"score_gpt":0.3244993651873518,"score_spread":0.051728824911078386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281341692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07111488,0.0005683696,0.9198048,0.0010902366,0.00006138285,0.00011172216,0.00014151642,0.0003618721,0.00674516],"genre_scores_gemma":[0.90898925,0.0005355234,0.08503556,0.0004048998,0.0001263878,0.00020429175,0.00024020036,0.00014432013,0.004319634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99712306,0.0014272117,0.00010672112,0.00063333166,0.0004100867,0.00029956037],"domain_scores_gemma":[0.9830102,0.013522312,0.0010064208,0.0014345858,0.0005274759,0.00049908704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004568403,0.0010874097,0.0022102862,0.0008148017,0.0009377613,0.0018805893,0.0020108207,0.002144305,0.0025981562],"category_scores_gemma":[0.03465958,0.00071622524,0.0010404597,0.00091125997,0.0033576076,0.004209038,0.002491636,0.0025933662,0.00032136057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025950823,0.0001083314,0.002243702,0.00014819423,0.00014772054,0.00020910172,0.00016647426,0.54538167,0.0015807032,0.4292785,0.0017626779,0.018713366],"study_design_scores_gemma":[0.000023539258,0.000042406922,0.00026740626,0.000016467784,0.000014949342,0.000036541544,0.000015020279,0.78758764,0.00035528088,0.21112595,0.00050141785,0.000013333462],"about_ca_topic_score_codex":0.0040368023,"about_ca_topic_score_gemma":0.003925485,"teacher_disagreement_score":0.004568403,"about_ca_system_score_codex":0.002322358,"about_ca_system_score_gemma":0.0015726861,"threshold_uncertainty_score":0.024160266},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5436472135121365,"score_gpt":0.4912489599546517,"score_spread":0.05239825355748484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293140407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008716062,0.002059185,0.94181967,0.0017599053,0.0005041088,0.00036036363,0.00038107365,0.0009275125,0.04347205],"genre_scores_gemma":[0.28688592,0.00331953,0.6419319,0.0022957427,0.0009273676,0.001140964,0.0018871246,0.0009129069,0.06069863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969469,0.0010846365,0.00021916362,0.0005623032,0.0007669613,0.0004201331],"domain_scores_gemma":[0.995047,0.0029228863,0.0002825084,0.001068847,0.00043758264,0.00024120274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003280154,0.0014475232,0.0020522578,0.0020451935,0.0018693284,0.003964712,0.003461836,0.0029381393,0.025390489],"category_scores_gemma":[0.017779358,0.00058332965,0.0016068384,0.0028013159,0.001965649,0.007220988,0.0047426037,0.0036235442,0.006282753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009167876,0.00015118935,0.00042638104,0.00027880693,0.000041667692,0.00006178274,0.00014545936,0.06888677,0.0006014083,0.71377856,0.023636904,0.19189943],"study_design_scores_gemma":[0.000064649044,0.000079868,0.00010876963,0.00006658162,0.000016232932,0.0001303632,0.000042555293,0.27181548,0.0006547792,0.7055073,0.021488843,0.000024475936],"about_ca_topic_score_codex":0.0013471942,"about_ca_topic_score_gemma":0.0014732603,"teacher_disagreement_score":0.025390489,"about_ca_system_score_codex":0.0019809182,"about_ca_system_score_gemma":0.0016200838,"threshold_uncertainty_score":0.0849396},"labels":[],"label_agreement":null},{"id":"W2293196265","doi":"10.5220/0005458706300636","title":"Improving Online Marketing Experiments with Drifting Multi-armed Bandits","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Marketing; Business","score_opus":0.30746654149901387,"score_gpt":0.4815174979023776,"score_spread":0.1740509564033637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293196265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85466397,0.00096950284,0.13362594,0.0008311037,0.00022007295,0.00030967852,0.00039350617,0.0017970451,0.0071891746],"genre_scores_gemma":[0.9496533,0.00014143517,0.047577884,0.00020315858,0.00005317235,0.00015692785,0.00037438975,0.00011424107,0.0017253984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765897,0.0014807789,0.000128852,0.00029904585,0.00024627664,0.00018606821],"domain_scores_gemma":[0.9850221,0.01190845,0.0006848851,0.0013971761,0.000617612,0.0003696907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057529137,0.0012057367,0.0015211927,0.0005634769,0.0006981309,0.0014704703,0.0015707413,0.0019602561,0.0036127488],"category_scores_gemma":[0.023075238,0.00048456862,0.0006505529,0.00075691345,0.0009217484,0.003385374,0.0013510069,0.0024400929,0.0008759087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041817524,0.003649564,0.0070561594,0.0003837739,0.0003025299,0.0002126711,0.0003159335,0.8586728,0.0067367405,0.01190459,0.004629374,0.1019541],"study_design_scores_gemma":[0.0001574907,0.00047769275,0.00076711626,0.000013818458,0.00002067667,0.000018599485,0.00003775914,0.99145496,0.0022562016,0.0042944527,0.00048658517,0.000014637213],"about_ca_topic_score_codex":0.0024171316,"about_ca_topic_score_gemma":0.0020509143,"teacher_disagreement_score":0.0057529137,"about_ca_system_score_codex":0.00079356425,"about_ca_system_score_gemma":0.00060982053,"threshold_uncertainty_score":0.030424654},"labels":[],"label_agreement":null},{"id":"W2333014926","doi":"10.3982/te992","title":"Expressible inspections","year":2013,"lang":"en","type":"article","venue":"Theoretical Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computability; Probabilistic logic; Test (biology); Outcome (game theory); Computer science; Realization (probability); Process (computing); Computable analysis; Conditional probability; Mathematical economics; Artificial intelligence; Mathematics; Theoretical computer science; Statistics; Programming language","score_opus":0.06724342768532615,"score_gpt":0.38675485028641815,"score_spread":0.319511422601092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333014926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055270568,0.0004185192,0.8036865,0.005141194,0.00018746007,0.00033497534,0.0022130862,0.001892332,0.13085549],"genre_scores_gemma":[0.7422763,0.00055375515,0.21818052,0.0009668332,0.00023819256,0.0006144839,0.0017702699,0.00038519633,0.03501442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920805,0.0024759567,0.0008154566,0.0016002572,0.0020643244,0.0009635377],"domain_scores_gemma":[0.9766643,0.012483448,0.0016362208,0.0056488826,0.003091926,0.00047506817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076422747,0.0009784148,0.0010904538,0.0015936762,0.0016343863,0.005385163,0.003053199,0.0030522079,0.019876158],"category_scores_gemma":[0.044782687,0.0008276847,0.0019666362,0.0019248208,0.0057368437,0.011389659,0.0038347342,0.0037021893,0.0026611302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049528004,0.000035183504,0.000554484,0.00006654686,0.000014661367,0.00013612042,0.0002556689,0.0045081405,0.0003801446,0.98207825,0.0019019961,0.01001914],"study_design_scores_gemma":[0.000017938748,0.000017273274,0.00018987803,0.00003638836,0.000017383267,0.00008814305,0.00008037128,0.02140792,0.0006697693,0.9702528,0.0072052707,0.000016841468],"about_ca_topic_score_codex":0.004061696,"about_ca_topic_score_gemma":0.003159988,"teacher_disagreement_score":0.019876158,"about_ca_system_score_codex":0.0037873136,"about_ca_system_score_gemma":0.0025397397,"threshold_uncertainty_score":0.06649238},"labels":[],"label_agreement":null},{"id":"W2395778028","doi":"10.7939/r3-dc54-6x83","title":"New representations and approximations for sequential decision making under uncertainty","year":2007,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Key (lock); Artificial intelligence; Exploit; Observability; Dual (grammatical number); Function (biology); Machine learning; Mathematical optimization; Mathematics","score_opus":0.19214727774047474,"score_gpt":0.5278730889014068,"score_spread":0.3357258111609321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395778028","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048402934,0.00025695527,0.99174654,0.00033465808,0.000032960637,0.000023547731,0.000056120145,0.00005774812,0.0026510786],"genre_scores_gemma":[0.40105984,0.0012663043,0.58815414,0.00028667224,0.00019269825,0.00046481332,0.0004614711,0.00013453135,0.007979557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980111,0.00089073816,0.00009965529,0.00027373977,0.0005581717,0.0001664517],"domain_scores_gemma":[0.99509865,0.0032615873,0.00047635852,0.00051808625,0.00043885646,0.00020636368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035634483,0.0009900886,0.0012430582,0.0010365137,0.0004756931,0.0025700647,0.001683905,0.001396488,0.0041918107],"category_scores_gemma":[0.014931095,0.0007784023,0.0011559344,0.0014444537,0.0018253495,0.004099468,0.0026617304,0.0043696016,0.0006547394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005519471,0.000041549396,0.00037236628,0.00008589659,0.000026012527,0.0000339777,0.00012643078,0.45260763,0.00028386142,0.5187844,0.0013113971,0.026271287],"study_design_scores_gemma":[0.0000061465707,0.000011143363,0.000025519772,0.000016333184,0.000003650412,0.0000074796735,0.000011629631,0.8873152,0.00008501846,0.11156177,0.0009517618,0.000004432646],"about_ca_topic_score_codex":0.0023843583,"about_ca_topic_score_gemma":0.0023079661,"teacher_disagreement_score":0.0041918107,"about_ca_system_score_codex":0.0021611063,"about_ca_system_score_gemma":0.0017014042,"threshold_uncertainty_score":0.018845558},"labels":[],"label_agreement":null},{"id":"W2396828995","doi":"","title":"A Lazy Approach to Online Learning with Constraints.","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Artificial intelligence; Novelty; Mathematical optimization; Bounded function; Online learning; Machine learning; Mathematics","score_opus":0.21612609913797645,"score_gpt":0.43081793676658786,"score_spread":0.2146918376286114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396828995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055588307,0.0002858986,0.99064904,0.0003015607,0.000039355527,0.00005439014,0.00003158619,0.00017287176,0.0029065697],"genre_scores_gemma":[0.6120327,0.0006704443,0.37401685,0.0007052963,0.00032148458,0.00040512552,0.00017283903,0.0001765203,0.011498696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99827874,0.0007636805,0.000067290624,0.00036548503,0.00037984393,0.00014497244],"domain_scores_gemma":[0.99469924,0.0038328208,0.00044455347,0.00052023306,0.00029849212,0.00020466327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028757625,0.0012010273,0.0012150604,0.0005055806,0.00055169436,0.0013204098,0.0021052875,0.001721123,0.004622771],"category_scores_gemma":[0.0091924425,0.0005693962,0.00058565685,0.00078955817,0.0018918935,0.0027021526,0.0014631881,0.002725904,0.00072363135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021298703,0.0002354792,0.0007093639,0.00028096142,0.0001432552,0.00017348367,0.00012652286,0.74557155,0.0021836841,0.17581306,0.0047890902,0.06976064],"study_design_scores_gemma":[0.00003716894,0.00006081065,0.00006471957,0.000015012298,0.000013335912,0.00003408336,0.000008625713,0.9341457,0.0005090739,0.063865334,0.0012376391,0.00000851081],"about_ca_topic_score_codex":0.0015668187,"about_ca_topic_score_gemma":0.0022020978,"teacher_disagreement_score":0.004622771,"about_ca_system_score_codex":0.001043466,"about_ca_system_score_gemma":0.0015835032,"threshold_uncertainty_score":0.0154646635},"labels":[],"label_agreement":null},{"id":"W2398037065","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":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Commit; Computer science; Database","score_opus":0.3686539785191696,"score_gpt":0.33170251449792354,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398037065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09863366,0.0023287893,0.8609076,0.0031972502,0.00017632761,0.00024127826,0.0003449569,0.00032808274,0.033842105],"genre_scores_gemma":[0.89686805,0.0016288379,0.080962144,0.0008128527,0.00022621045,0.0005373115,0.00028132054,0.00020531428,0.018477952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974068,0.0014272543,0.000105063285,0.00039724694,0.00032531432,0.00033825115],"domain_scores_gemma":[0.9820992,0.015101918,0.0011370573,0.0005558624,0.0005219643,0.0005840969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043874388,0.0020194415,0.0019755636,0.0008414745,0.0007316811,0.0023193052,0.0018020184,0.0028784315,0.006821215],"category_scores_gemma":[0.025244324,0.0007279529,0.00082301354,0.0012111143,0.0024895486,0.0035101005,0.0020175185,0.0036092522,0.0010784741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005077136,0.00019769877,0.0015550057,0.00031736275,0.00013900225,0.0002534551,0.00031980412,0.58731335,0.001270864,0.37237954,0.0038241176,0.03192205],"study_design_scores_gemma":[0.00008126208,0.00015025603,0.00018742817,0.00005941061,0.000020709747,0.00004420562,0.000044742144,0.8399481,0.00037347808,0.15788743,0.0011843588,0.000018628689],"about_ca_topic_score_codex":0.0025179079,"about_ca_topic_score_gemma":0.0016704196,"teacher_disagreement_score":0.006821215,"about_ca_system_score_codex":0.0018318493,"about_ca_system_score_gemma":0.0019046448,"threshold_uncertainty_score":0.023203254},"labels":[],"label_agreement":null},{"id":"W2402248766","doi":"10.1609/aaai.v25i1.7954","title":"Recommendation Sets and Choice Queries: There Is No Exploration/Exploitation Tradeoff!","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Recommender system; Computer science; Set (abstract data type); Preference elicitation; Bayesian probability; Component (thermodynamics); Function (biology); Query optimization; Information retrieval; Data mining; Artificial intelligence; Machine learning; Preference; Mathematics","score_opus":0.46823225723104683,"score_gpt":0.4411107119125127,"score_spread":0.027121545318534113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402248766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04231053,0.002468155,0.9052324,0.022210397,0.00015040608,0.00029492768,0.00043445802,0.00029898016,0.02659971],"genre_scores_gemma":[0.70884126,0.0021971213,0.27445802,0.0033236945,0.00079776044,0.0010141705,0.00064564386,0.00036290346,0.008359426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96547914,0.024392748,0.0011620028,0.0026132436,0.0053403545,0.0010124875],"domain_scores_gemma":[0.83248556,0.14718631,0.0044347676,0.010825048,0.0030041311,0.0020643089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0287375,0.0013060624,0.0028764834,0.0012512052,0.0017646049,0.00811733,0.0031459522,0.0073940107,0.012550054],"category_scores_gemma":[0.15877013,0.0015741833,0.0016150645,0.0026590277,0.005890809,0.023276687,0.0052534086,0.008563961,0.0016335081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074419647,0.00028175942,0.0021412405,0.0003933386,0.00022790911,0.00013788679,0.00084853446,0.05238029,0.00080723077,0.8668938,0.0052929316,0.06985091],"study_design_scores_gemma":[0.00010616014,0.00010088166,0.000462345,0.00007501373,0.000032297357,0.00014101162,0.00013098617,0.09661156,0.0004208533,0.8990959,0.0027922862,0.000030738458],"about_ca_topic_score_codex":0.001215561,"about_ca_topic_score_gemma":0.0010345313,"teacher_disagreement_score":0.0287375,"about_ca_system_score_codex":0.002961618,"about_ca_system_score_gemma":0.0022042182,"threshold_uncertainty_score":0.15198022},"labels":[],"label_agreement":null},{"id":"W2403303158","doi":"","title":"Bayesian optimal control of smoothly parameterized systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Parameterized complexity; Markov decision process; Mathematical optimization; Computer science; Thompson sampling; Bayesian probability; Mathematics; Algorithm; Markov process; Artificial intelligence; Machine learning","score_opus":0.18254699853885475,"score_gpt":0.4346419930056865,"score_spread":0.25209499446683176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403303158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03166996,0.00062455586,0.96101373,0.0006023578,0.000039889524,0.00005200511,0.00009918901,0.000152116,0.005746256],"genre_scores_gemma":[0.93827856,0.0008607085,0.054987025,0.00016386273,0.00008538984,0.00018225325,0.00014627934,0.000075629854,0.005220359],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881727,0.0004735715,0.000039307342,0.00026378193,0.00022911147,0.00017700682],"domain_scores_gemma":[0.9966037,0.0024817316,0.0003848206,0.00016086537,0.00019267462,0.00017612072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002068276,0.001364115,0.0014296112,0.0005867788,0.00046689078,0.0017413162,0.0014779423,0.0015407101,0.0029601988],"category_scores_gemma":[0.008810697,0.00068836764,0.0009817212,0.000691301,0.0022446273,0.0019866186,0.001799823,0.0023530629,0.0002598582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003967703,0.00001794668,0.0001933281,0.000043915832,0.00002394789,0.000043360677,0.000043074764,0.9347686,0.00038092205,0.0597968,0.00030135957,0.0043470855],"study_design_scores_gemma":[0.000008597126,0.000012527486,0.000053821837,0.000004888946,0.0000033825231,0.0000034771058,0.0000054580614,0.97705954,0.00007009202,0.022553457,0.00022043458,0.0000043594832],"about_ca_topic_score_codex":0.008104663,"about_ca_topic_score_gemma":0.0038102565,"teacher_disagreement_score":0.008104663,"about_ca_system_score_codex":0.0020996262,"about_ca_system_score_gemma":0.0013231352,"threshold_uncertainty_score":0.01611495},"labels":[],"label_agreement":null},{"id":"W2465908909","doi":"","title":"Shifting regret, mirror descent, and matrices","year":2016,"lang":"en","type":"article","venue":"Spiral (Imperial College London)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Base (topology); Computer science; Class (philosophy); Simplex; Matrix (chemical analysis); Gradient descent; Mathematical optimization; Algorithm; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics; Combinatorics; Artificial neural network","score_opus":0.08209789988066338,"score_gpt":0.381714209005795,"score_spread":0.2996163091251316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465908909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027125653,0.0022057998,0.9600291,0.0014838926,0.00019792462,0.000043632914,0.00014723974,0.00028921905,0.00847746],"genre_scores_gemma":[0.80351144,0.0033128948,0.17871758,0.00097225053,0.00072305667,0.00022668713,0.0004210753,0.0002670266,0.011847922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983175,0.0007361955,0.00004808543,0.00028755225,0.00040375497,0.00020687093],"domain_scores_gemma":[0.99188554,0.0057266923,0.0006867226,0.0008779965,0.0005041287,0.00031881157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036188045,0.002206002,0.001610266,0.0007687064,0.0007362577,0.0016987101,0.0021040377,0.0022077353,0.0028995133],"category_scores_gemma":[0.020632904,0.00050712633,0.00074090686,0.0013037435,0.0031231483,0.0038381075,0.0025334407,0.0034485266,0.0006864043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018887474,0.00010145588,0.0014905194,0.00017816,0.000089253255,0.0002210099,0.000108450455,0.6999199,0.0013917848,0.24664359,0.005336648,0.04433037],"study_design_scores_gemma":[0.000011784692,0.00005797493,0.00017924179,0.000026015075,0.000009572604,0.00004077272,0.00001100926,0.86371535,0.00041449533,0.13486539,0.00065685366,0.000011582817],"about_ca_topic_score_codex":0.0038479907,"about_ca_topic_score_gemma":0.00235718,"teacher_disagreement_score":0.0038479907,"about_ca_system_score_codex":0.0017520948,"about_ca_system_score_gemma":0.0014472613,"threshold_uncertainty_score":0.019138336},"labels":[],"label_agreement":null},{"id":"W2483372187","doi":"10.4018/978-1-59140-702-7.ch021","title":"Online Methods for Portfolio Selection","year":2006,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Portfolio; Selection (genetic algorithm); Portfolio optimization; Computer science; Econometrics; Investment strategy; Post-modern portfolio theory; Investment portfolio; Investment (military); Stock (firearms); Stock market; Economics; Financial economics; Replicating portfolio; Artificial intelligence; Finance; Engineering; Geography","score_opus":0.12451742203920636,"score_gpt":0.4819105692302763,"score_spread":0.35739314719106996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483372187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047076918,0.0033140841,0.9914833,0.00022960104,0.00019938633,0.00005350109,0.00010344095,0.00042608785,0.0037197482],"genre_scores_gemma":[0.08519894,0.013573854,0.86922026,0.0007519435,0.0019450501,0.001192811,0.0014536644,0.00063390017,0.026029669],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975794,0.0009151705,0.00013449728,0.0003480579,0.0009174237,0.00010542728],"domain_scores_gemma":[0.9959643,0.0029150492,0.00018947794,0.00046741663,0.00039191387,0.000071765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002928767,0.0020121646,0.0020270613,0.001986891,0.0005777951,0.0025620905,0.0019993475,0.0018436996,0.01583436],"category_scores_gemma":[0.01197155,0.00072521233,0.001223197,0.002910048,0.0010117418,0.0026753168,0.002128176,0.0029810045,0.008305038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087634464,0.0001603406,0.00064502406,0.00054904906,0.00020261336,0.000092812894,0.00005804992,0.123711675,0.0013286537,0.19473922,0.023026826,0.6553981],"study_design_scores_gemma":[0.000053326534,0.000051511703,0.00027779245,0.00011179944,0.000034757402,0.00016129055,0.000018675793,0.6583681,0.00090692897,0.3066855,0.03330155,0.000028707376],"about_ca_topic_score_codex":0.001348244,"about_ca_topic_score_gemma":0.0010881528,"teacher_disagreement_score":0.01583436,"about_ca_system_score_codex":0.0009234674,"about_ca_system_score_gemma":0.0010311258,"threshold_uncertainty_score":0.052971244},"labels":[],"label_agreement":null},{"id":"W2509437949","doi":"","title":"Deep learning games","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Nash equilibrium; Computer science; Deep learning; Artificial intelligence; Regret; Karush–Kuhn–Tucker conditions; Artificial neural network; Game theory; Differentiable function; Equivalence (formal languages); Bijection; Mathematical optimization; Machine learning; Mathematics; Mathematical economics; Discrete mathematics","score_opus":0.07726177950359157,"score_gpt":0.39242078176238665,"score_spread":0.31515900225879506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509437949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033333905,0.00025939356,0.9026901,0.004227566,0.00015690761,0.00027141525,0.00030779082,0.00018859914,0.058564335],"genre_scores_gemma":[0.8316366,0.0005612513,0.13757774,0.0012224024,0.00023096123,0.00077148917,0.00023752492,0.00008469293,0.027677272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978479,0.0010288687,0.00009955246,0.00036144664,0.0004240786,0.00023814349],"domain_scores_gemma":[0.9973985,0.0018452127,0.00016731402,0.0002379865,0.00015361418,0.0001974568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001872421,0.00092004536,0.00082926947,0.00049338693,0.0007206766,0.0025056303,0.0018944679,0.0019948615,0.009315164],"category_scores_gemma":[0.0088555375,0.00040522616,0.000789504,0.0004470034,0.002414679,0.0038298955,0.0026424723,0.0030527448,0.00069071323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000223096,0.00004084093,0.0001341651,0.000039347306,0.000017712975,0.000037029455,0.00007685124,0.037474673,0.0003344014,0.95220643,0.0017063417,0.007909953],"study_design_scores_gemma":[0.000023468629,0.000027965025,0.00005092268,0.00001314842,0.000006269564,0.000021137856,0.000024681567,0.2325472,0.00020659632,0.7637894,0.003281743,0.000007566368],"about_ca_topic_score_codex":0.001833345,"about_ca_topic_score_gemma":0.001875316,"teacher_disagreement_score":0.009315164,"about_ca_system_score_codex":0.0019584498,"about_ca_system_score_gemma":0.001558196,"threshold_uncertainty_score":0.031162322},"labels":[],"label_agreement":null},{"id":"W2545509292","doi":"10.1109/globalsip.2013.6737014","title":"Consensus-based distributed online prediction and optimization","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Computer science; Lipschitz continuity; Point (geometry); Gradient descent; Stochastic gradient descent; Optimization problem; Function (biology); Node (physics); Data stream; Distributed computing; Mathematical optimization; Algorithm; Artificial intelligence; Machine learning; Artificial neural network; Mathematics","score_opus":0.08648565861720116,"score_gpt":0.39760601744012514,"score_spread":0.311120358822924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545509292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016930146,0.00027632155,0.9799652,0.00043934316,0.00005962148,0.000033190143,0.000053090484,0.00029944378,0.0019436032],"genre_scores_gemma":[0.9150349,0.0002850141,0.07975309,0.00020341533,0.00013192947,0.00018376045,0.00017949576,0.00009756512,0.0041309074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820006,0.0005472945,0.000071633316,0.00050220004,0.0004249774,0.00025385927],"domain_scores_gemma":[0.9953467,0.0030377815,0.00046256158,0.000357953,0.00061279983,0.00018222013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023911474,0.0011729705,0.0022628412,0.00053025875,0.0007497125,0.0011991692,0.0022125356,0.0015226441,0.0016604943],"category_scores_gemma":[0.0078400355,0.00054680026,0.0005152399,0.0009786871,0.0013857075,0.0020797658,0.0018359149,0.001816899,0.0003966164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007587081,0.000026858743,0.00020988937,0.000028377226,0.000020077974,0.000033363314,0.00002671329,0.9809467,0.00025576307,0.0066422764,0.00069055014,0.01104355],"study_design_scores_gemma":[0.000007764634,0.000009298891,0.000025157822,0.0000014414256,0.0000020924354,0.0000040952536,0.0000041560334,0.99530077,0.00010884416,0.004430651,0.000103629296,0.0000021378926],"about_ca_topic_score_codex":0.0069155814,"about_ca_topic_score_gemma":0.0035022201,"teacher_disagreement_score":0.0069155814,"about_ca_system_score_codex":0.0013761086,"about_ca_system_score_gemma":0.001862711,"threshold_uncertainty_score":0.013750613},"labels":[],"label_agreement":null},{"id":"W2550845292","doi":"10.1007/s10898-018-0688-0","title":"A Bayesian optimization approach to find Nash equilibria","year":2018,"lang":"en","type":"article","venue":"Journal of Global Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"Universiteit Leiden; National Science Foundation","keywords":"Bayesian probability; Nash equilibrium; Mathematical economics; Computer science; Economics; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.06602853053884729,"score_gpt":0.4121978716972752,"score_spread":0.3461693411584279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550845292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024934611,0.00019854016,0.99245065,0.00040358948,0.00003393669,0.000053797972,0.00003753892,0.00006088922,0.004267524],"genre_scores_gemma":[0.22581048,0.0011365094,0.75398713,0.00048727062,0.0003505394,0.0010372143,0.00027648432,0.00024716364,0.016667219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761593,0.0013464096,0.000095054726,0.00026409,0.00052415143,0.00015445099],"domain_scores_gemma":[0.9910136,0.0075731124,0.0002893194,0.0002291334,0.00072547904,0.0001693505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005773939,0.001856277,0.00313621,0.0030879562,0.0016525931,0.0031779518,0.0036153242,0.0038865895,0.009240688],"category_scores_gemma":[0.023406113,0.0021316055,0.0018533125,0.0028961569,0.0027733173,0.005179546,0.0035883358,0.003635106,0.0012023544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006596505,0.00013157958,0.00039716242,0.00014678456,0.00011654971,0.000046974394,0.000116128205,0.61520976,0.000340839,0.34173056,0.0036030654,0.038094673],"study_design_scores_gemma":[0.000024582594,0.000014330506,0.000044963832,0.000027426508,0.000018199442,0.000008910114,0.000013079246,0.9048113,0.00008446622,0.0943205,0.0006209638,0.00001115529],"about_ca_topic_score_codex":0.009825086,"about_ca_topic_score_gemma":0.010621212,"teacher_disagreement_score":0.009825086,"about_ca_system_score_codex":0.002708132,"about_ca_system_score_gemma":0.003752088,"threshold_uncertainty_score":0.030913174},"labels":[],"label_agreement":null},{"id":"W2552858844","doi":"10.48550/arxiv.1702.03040","title":"Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta","keywords":"Sublinear function; Regret; Bounded function; Logarithm; Boundary (topology); Domain (mathematical analysis); Constraint (computer-aided design); Regular polygon; Curvature; Computer science; Algorithm; Mathematical optimization; Mathematics; Upper and lower bounds; Discrete mathematics; Geometry; Mathematical analysis","score_opus":0.25291467637716164,"score_gpt":0.32576508533834175,"score_spread":0.07285040896118011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552858844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07460631,0.0007482905,0.91701245,0.0019670394,0.000072476156,0.00009170192,0.00019279093,0.00073977304,0.004569196],"genre_scores_gemma":[0.78583413,0.00058874855,0.20589781,0.0007721883,0.00017150905,0.00028924426,0.00040657388,0.0004276221,0.0056122206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774843,0.0011736043,0.00006661913,0.00040839188,0.00034213526,0.0002607817],"domain_scores_gemma":[0.9822869,0.013301942,0.0012701009,0.0017184555,0.00066669355,0.0007559182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005710018,0.0012033548,0.0019843122,0.00066026964,0.0011168639,0.0022825936,0.0023814295,0.002466483,0.003212008],"category_scores_gemma":[0.030733915,0.0008021898,0.0010221725,0.0013476061,0.0033892356,0.0058988146,0.0030691815,0.004913235,0.00091122184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006235631,0.00020942994,0.0018817346,0.00015141763,0.00007603076,0.00021701328,0.00030218603,0.7600062,0.0014306167,0.18294244,0.006070379,0.046088874],"study_design_scores_gemma":[0.000039001494,0.00007790303,0.00012597343,0.000020240404,0.0000079871725,0.000037872083,0.00002660688,0.9163042,0.0007363717,0.0821323,0.00047606818,0.000015516564],"about_ca_topic_score_codex":0.001822469,"about_ca_topic_score_gemma":0.0014975151,"teacher_disagreement_score":0.005710018,"about_ca_system_score_codex":0.0016441176,"about_ca_system_score_gemma":0.0015480422,"threshold_uncertainty_score":0.030197859},"labels":[],"label_agreement":null},{"id":"W2553665199","doi":"","title":"The Forget-me-not Process","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Piecewise; Computer science; Logarithm; Probabilistic logic; Sequence (biology); Task (project management); Partition (number theory); Range (aeronautics); Process (computing); Data mining; Parametric statistics; Bayesian probability; Algorithm; Identification (biology); Artificial intelligence; Machine learning; Mathematics; Statistics; Engineering","score_opus":0.09964141962034775,"score_gpt":0.4246329324623445,"score_spread":0.3249915128419968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553665199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024484948,0.00019282581,0.99618226,0.00022388353,0.00004748385,0.00003028377,0.000052183437,0.00041960514,0.000403009],"genre_scores_gemma":[0.37800494,0.0007731017,0.6106711,0.00086953957,0.00046391122,0.00051722664,0.00074295764,0.00040697173,0.007550268],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976973,0.00083393237,0.00011809186,0.00059348106,0.0005466624,0.0002105508],"domain_scores_gemma":[0.9917515,0.0051289564,0.00052607333,0.0014828471,0.0008601735,0.0002503558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004907061,0.0021166771,0.0028034414,0.001119912,0.0009003609,0.001945464,0.005128734,0.0028864394,0.004645112],"category_scores_gemma":[0.021966113,0.0011309157,0.0013937477,0.0012373114,0.0018501785,0.0053983754,0.0031721655,0.004708969,0.0018598913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007733768,0.00015916457,0.0022828698,0.00025044198,0.00024454625,0.0002681413,0.00022900841,0.6102133,0.0038281882,0.12288475,0.005809211,0.253057],"study_design_scores_gemma":[0.000025103009,0.000055592474,0.00009431011,0.000015411688,0.000018978331,0.00005141184,0.0000051980255,0.95954764,0.0013332032,0.037800398,0.0010365015,0.000016241931],"about_ca_topic_score_codex":0.0021693811,"about_ca_topic_score_gemma":0.002469458,"teacher_disagreement_score":0.005128734,"about_ca_system_score_codex":0.0010432514,"about_ca_system_score_gemma":0.002555222,"threshold_uncertainty_score":0.025951326},"labels":[],"label_agreement":null},{"id":"W2559019597","doi":"10.1109/cec.2016.7744386","title":"Contextual bandit algorithm for risk-aware recommender systems","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Recommender system; Computer science; Reinforcement learning; Context (archaeology); Machine learning; Artificial intelligence; Risk analysis (engineering)","score_opus":0.17491537736588925,"score_gpt":0.44714640914436493,"score_spread":0.2722310317784757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559019597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020605698,0.0012153607,0.9739382,0.00048161685,0.00006374791,0.00009401432,0.000059872713,0.00048265344,0.0030587951],"genre_scores_gemma":[0.7081009,0.00083786587,0.28485852,0.00046735368,0.00014786629,0.00046570034,0.00022502922,0.00012416372,0.0047726207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981541,0.00095708476,0.00010404361,0.00027923234,0.00030962014,0.00019599458],"domain_scores_gemma":[0.9942836,0.004228103,0.00039196358,0.00036436514,0.0005546625,0.0001771846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003932806,0.0012051155,0.0024752484,0.00093162793,0.0009708743,0.0015703398,0.0021070915,0.002053045,0.0034965351],"category_scores_gemma":[0.012178748,0.0005975005,0.0006469588,0.00096216716,0.0013063337,0.0020539537,0.0017805955,0.002238263,0.0010588105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004176341,0.00017256133,0.0013438701,0.0001800106,0.000121039455,0.000058265647,0.00019980158,0.82930744,0.0010324996,0.038385794,0.0027860745,0.125995],"study_design_scores_gemma":[0.000021480695,0.000038128328,0.000101992526,0.00001745945,0.000012660503,0.000013780433,0.000012341314,0.9898768,0.00019799334,0.009309901,0.0003906376,0.00000675563],"about_ca_topic_score_codex":0.0068508307,"about_ca_topic_score_gemma":0.0049484693,"teacher_disagreement_score":0.0068508307,"about_ca_system_score_codex":0.0013946646,"about_ca_system_score_gemma":0.0014490121,"threshold_uncertainty_score":0.020798922},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Computer science; Algebra over a field; Calculus (dental); Mathematical economics; Pure mathematics; Medicine","score_opus":0.18861928299444541,"score_gpt":0.44523061759891325,"score_spread":0.25661133460446783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561282814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24557751,0.000835944,0.71799576,0.002860869,0.00013304701,0.00032108408,0.00082899333,0.0004933768,0.030953398],"genre_scores_gemma":[0.8587171,0.0010147776,0.12542038,0.0007529499,0.0003526206,0.0005162153,0.0013755846,0.00017146689,0.011678917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737656,0.00089222775,0.00022439599,0.00053790025,0.0005310164,0.0004380242],"domain_scores_gemma":[0.9820806,0.012522177,0.0015024741,0.00130933,0.0010694418,0.0015159305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034687598,0.0013434393,0.0022488998,0.0023537725,0.0014819736,0.006151097,0.0034165827,0.0029028265,0.0064065703],"category_scores_gemma":[0.017986951,0.0007724241,0.001771059,0.001888042,0.0033472772,0.0074901246,0.0027719277,0.0053809755,0.00061575614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009889488,0.00011653577,0.0013865432,0.00008430033,0.000029424953,0.000044486576,0.00023478406,0.0121772215,0.0006283492,0.9686148,0.0025273354,0.014057473],"study_design_scores_gemma":[0.000051208568,0.000055851055,0.0005005774,0.000048852657,0.000021041928,0.00007383879,0.00007972777,0.13452259,0.00025422534,0.86278987,0.0015821848,0.00002015418],"about_ca_topic_score_codex":0.0017453134,"about_ca_topic_score_gemma":0.00150421,"teacher_disagreement_score":0.0064065703,"about_ca_system_score_codex":0.0025847172,"about_ca_system_score_gemma":0.0024180147,"threshold_uncertainty_score":0.021432102},"labels":[],"label_agreement":null},{"id":"W2561826351","doi":"10.1109/isit.2005.1523524","title":"Tracking the best quantizer","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Quantization (signal processing); Sequence (biology); Algorithm; Lossy compression; Quadratic equation; Mathematics; Piecewise; Scalar (mathematics); Computer science; Monotone polygon; Computational complexity theory; Piecewise linear function; Mathematical optimization; Artificial intelligence","score_opus":0.3106148670222755,"score_gpt":0.516547703061707,"score_spread":0.20593283603943158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561826351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02254801,0.00030745938,0.9751236,0.00020832708,0.00005342063,0.000033752753,0.000038246737,0.00020382206,0.0014833568],"genre_scores_gemma":[0.7154134,0.00041707465,0.2793273,0.0002000608,0.000087254426,0.000086299755,0.000098839984,0.00010462905,0.0042652357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882954,0.00022627621,0.00005852438,0.00043282588,0.0003294504,0.00012335896],"domain_scores_gemma":[0.9975394,0.0012016238,0.00040386122,0.00040048914,0.00038209584,0.000072523464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019266236,0.00055415573,0.0009425244,0.00049233227,0.00061311416,0.001381001,0.0011888512,0.0010805055,0.0016039289],"category_scores_gemma":[0.009172677,0.00036236667,0.0002764698,0.00048139517,0.0013208104,0.0027108958,0.0011015582,0.0011584399,0.00072591484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054004695,0.000103269886,0.0018604728,0.0002293051,0.00008507186,0.00009580351,0.00022555584,0.5706871,0.035985667,0.14374304,0.0023835432,0.2440611],"study_design_scores_gemma":[0.00004228855,0.00013681786,0.00028522612,0.000033342123,0.000025032447,0.00010842906,0.000060378647,0.9364142,0.021883069,0.038274936,0.0027065526,0.000029808838],"about_ca_topic_score_codex":0.0014971936,"about_ca_topic_score_gemma":0.0010746466,"teacher_disagreement_score":0.0019266236,"about_ca_system_score_codex":0.0009614525,"about_ca_system_score_gemma":0.001361927,"threshold_uncertainty_score":0.010189116},"labels":[],"label_agreement":null},{"id":"W2568832377","doi":"10.1109/isit.2012.6284689","title":"Efficient tracking of large classes of experts","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Base (topology); Computer science; Binary number; Class (philosophy); Sequence (biology); Upper and lower bounds; Algorithm; Set (abstract data type); Block (permutation group theory); Artificial intelligence; Theoretical computer science; Mathematics; Machine learning; Combinatorics; Arithmetic","score_opus":0.19343292246344623,"score_gpt":0.5014377617839864,"score_spread":0.3080048393205401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568832377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063325666,0.00022735538,0.93197984,0.0005048619,0.00003899724,0.00011316708,0.000110701185,0.00085614657,0.002843291],"genre_scores_gemma":[0.74704885,0.00023367847,0.24256726,0.00054691127,0.00015705766,0.00032685307,0.00046875476,0.00015728745,0.00849328],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971967,0.0007828373,0.000102780745,0.0009146776,0.0005585996,0.00044440574],"domain_scores_gemma":[0.9872385,0.009147767,0.0010035845,0.0012480166,0.0007655939,0.00059660064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004997381,0.001222295,0.0019055033,0.00077880034,0.0009644907,0.0017288695,0.003427284,0.0029264635,0.002568954],"category_scores_gemma":[0.01918268,0.00085309404,0.0010676902,0.0008107268,0.001641622,0.00314086,0.0023146428,0.0029421092,0.0007545872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053250475,0.00017586003,0.003731664,0.00012691549,0.00008180552,0.00014204835,0.0002590943,0.8402053,0.0029169186,0.042020146,0.0045434427,0.10526438],"study_design_scores_gemma":[0.000022206961,0.000031069245,0.00015958028,0.0000054034344,0.0000066460275,0.00001939654,0.000012376313,0.9836447,0.0006404116,0.015112273,0.0003399962,0.000005873685],"about_ca_topic_score_codex":0.005803462,"about_ca_topic_score_gemma":0.0038930746,"teacher_disagreement_score":0.005803462,"about_ca_system_score_codex":0.0019302691,"about_ca_system_score_gemma":0.0022841198,"threshold_uncertainty_score":0.026428998},"labels":[],"label_agreement":null},{"id":"W2569695769","doi":"10.1007/978-3-319-50502-2_3","title":"Markov Multi-armed Bandit","year":2016,"lang":"en","type":"book-chapter","venue":"Wireless networks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Markov chain; Computer science; Markov model; Variable-order Markov model; Markov process; Markov property; Markov decision process; Markov kernel; Mathematical optimization; Markov renewal process; Examples of Markov chains; Mathematics; Machine learning; Statistics","score_opus":0.10221312763472323,"score_gpt":0.3813151395114032,"score_spread":0.27910201187668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569695769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024101404,0.013742419,0.83392346,0.0019753068,0.0010770691,0.00003939622,0.0002224614,0.0004129803,0.14619677],"genre_scores_gemma":[0.27834523,0.05435797,0.32244977,0.0023485178,0.004037116,0.000576729,0.0011989536,0.0007333423,0.33595234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954396,0.00015328317,0.000022317132,0.000076135904,0.00016388601,0.000040409028],"domain_scores_gemma":[0.99893576,0.000800323,0.000046727364,0.000098337725,0.00009201221,0.000026847501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082764804,0.0012740404,0.0010165311,0.0005054727,0.00041086637,0.0029311,0.0010092629,0.0015774297,0.011639679],"category_scores_gemma":[0.0030787631,0.00052959507,0.00051146775,0.0015052761,0.0010656376,0.0019890298,0.0009196544,0.0023170211,0.004853975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004723358,0.00005831801,0.00015773247,0.0002549547,0.000055095457,0.000061051855,0.00008445034,0.097014695,0.00080893724,0.7016353,0.044349257,0.15547301],"study_design_scores_gemma":[0.000015443815,0.000025633146,0.00013647413,0.00013901993,0.000020928706,0.00008331358,0.000030601776,0.26732996,0.00047509617,0.67291725,0.058797177,0.000029098142],"about_ca_topic_score_codex":0.0011232177,"about_ca_topic_score_gemma":0.0014825489,"teacher_disagreement_score":0.011639679,"about_ca_system_score_codex":0.0009889416,"about_ca_system_score_gemma":0.00078501744,"threshold_uncertainty_score":0.03893864},"labels":[],"label_agreement":null},{"id":"W2596047044","doi":"","title":"An Economic Model of Induction","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Incentive; Test (biology); Political science; Operations research; Management; Economics; Engineering; Medicine","score_opus":0.22913483422267705,"score_gpt":0.4730171926103604,"score_spread":0.24388235838768335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596047044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024138905,0.0033150692,0.5222272,0.038859483,0.00061608054,0.00034018978,0.0011820046,0.0005444908,0.40877655],"genre_scores_gemma":[0.6883956,0.0037881439,0.14229716,0.0044718115,0.0013247075,0.0011303744,0.0008103607,0.0003444444,0.15743732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99564266,0.0017155885,0.00017905147,0.0009409197,0.0010558141,0.00046582322],"domain_scores_gemma":[0.99028134,0.005919615,0.000697708,0.0014540657,0.0011458286,0.00050143123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048178574,0.00078642694,0.00092528213,0.0016548621,0.0020801579,0.004589237,0.0027631696,0.0033833715,0.020874891],"category_scores_gemma":[0.012793096,0.00051379605,0.0018742149,0.0014423564,0.0076275053,0.00750388,0.0033529992,0.0036902695,0.003105939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009396332,0.00000866526,0.00011524737,0.000018560166,0.000006171486,0.00004313636,0.000043722655,0.0043420363,0.00005690189,0.9913935,0.0016829505,0.0022797722],"study_design_scores_gemma":[0.000015888987,0.000008254528,0.00007354572,0.000013209041,0.0000041279472,0.00004343002,0.000014387919,0.017859861,0.0000472387,0.9716077,0.01030615,0.000006343984],"about_ca_topic_score_codex":0.00473567,"about_ca_topic_score_gemma":0.0027953107,"teacher_disagreement_score":0.020874891,"about_ca_system_score_codex":0.0065085944,"about_ca_system_score_gemma":0.003403932,"threshold_uncertainty_score":0.06983346},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3279068753148421,"score_gpt":0.5299592419994449,"score_spread":0.2020523666846028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602868127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0815473,0.0015671414,0.90743285,0.0012909814,0.00012698477,0.00020652746,0.00031714494,0.0017644236,0.00574658],"genre_scores_gemma":[0.8795918,0.0005492297,0.11078853,0.0004990288,0.00020527441,0.00034228573,0.00033865677,0.00016663056,0.007518432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99610716,0.002094489,0.00015083657,0.0005176138,0.000696348,0.00043356957],"domain_scores_gemma":[0.9808591,0.014992464,0.0017365318,0.0010441393,0.0008932279,0.00047459765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070689404,0.0014601328,0.0029473647,0.0011997443,0.00090932066,0.0018834645,0.002690433,0.002192078,0.005526266],"category_scores_gemma":[0.02516245,0.0007208627,0.0007404425,0.0014139223,0.0018316025,0.0032416899,0.0014469691,0.0026908591,0.001342608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061817974,0.00023688225,0.0011861146,0.00013520902,0.000053290347,0.00009222854,0.00010218616,0.8687528,0.0008300941,0.061076302,0.0038370846,0.0630797],"study_design_scores_gemma":[0.00002662621,0.00003952837,0.000105541054,0.000008424081,0.0000045940005,0.000012594303,0.0000051171733,0.9785775,0.00018430718,0.020760898,0.00026620843,0.000008758798],"about_ca_topic_score_codex":0.0045367386,"about_ca_topic_score_gemma":0.004024408,"teacher_disagreement_score":0.0070689404,"about_ca_system_score_codex":0.0023989803,"about_ca_system_score_gemma":0.0016848457,"threshold_uncertainty_score":0.03738463},"labels":[],"label_agreement":null},{"id":"W2604713477","doi":"10.48550/arxiv.1703.02626","title":"Horde of Bandits using Gaussian Markov Random Fields","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Thompson sampling; Computer science; Scalability; Cluster analysis; Regret; Markov chain; Graph; Gaussian; Recommender system; Theoretical computer science; Mathematical optimization; Artificial intelligence; Algorithm; Machine learning; Mathematics","score_opus":0.2722265457874038,"score_gpt":0.3314936328505302,"score_spread":0.05926708706312639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604713477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033934817,0.00097260915,0.9575313,0.0013127167,0.00013717308,0.000106318854,0.00016060023,0.0005997582,0.005244709],"genre_scores_gemma":[0.7248514,0.0012049603,0.2622168,0.0009807985,0.00030739867,0.00045116388,0.00041696598,0.0003416497,0.009228836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752253,0.001555879,0.000060031954,0.0003432782,0.000340026,0.00017821263],"domain_scores_gemma":[0.9902715,0.007506056,0.0005206654,0.00091911276,0.00044124626,0.00034126177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004464697,0.00129547,0.0021346544,0.0011981782,0.0011349292,0.0018868633,0.0024368335,0.0022133663,0.0038246654],"category_scores_gemma":[0.018817738,0.0008315694,0.0010885539,0.0012593302,0.0025928754,0.003099775,0.0020504303,0.0033129707,0.00082058046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027639986,0.00009780913,0.0009281501,0.00009462391,0.00007755304,0.000095320494,0.00008966333,0.79266447,0.0007931842,0.17157453,0.0041321903,0.029176202],"study_design_scores_gemma":[0.000017752429,0.00001937445,0.00006113422,0.0000100027255,0.0000063096627,0.000012788264,0.000006905189,0.9568261,0.00015660391,0.042384837,0.0004918024,0.000006467552],"about_ca_topic_score_codex":0.0061607417,"about_ca_topic_score_gemma":0.006726993,"teacher_disagreement_score":0.0061607417,"about_ca_system_score_codex":0.002262726,"about_ca_system_score_gemma":0.0017764007,"threshold_uncertainty_score":0.023611903},"labels":[],"label_agreement":null},{"id":"W2611974834","doi":"","title":"Rewards and errors in multi-arm bandits for interactive education","year":2016,"lang":"en","type":"preprint","venue":"LillOA (Université de Lille (University Of Lille))","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Maximization; Utility maximization; Estimation; Artificial intelligence; Machine learning; Mathematical optimization; Engineering","score_opus":0.07773655344355909,"score_gpt":0.3737362547816234,"score_spread":0.2959997013380643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611974834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22172973,0.0036660593,0.754338,0.0039893133,0.00033145223,0.0001485084,0.00061956537,0.0009551702,0.014222158],"genre_scores_gemma":[0.9254067,0.0015024942,0.049169116,0.00023971671,0.00024931398,0.00024636896,0.00044721895,0.00028250462,0.022456568],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952429,0.0023225714,0.00028274223,0.00079916057,0.0007181064,0.0006345247],"domain_scores_gemma":[0.92255324,0.06674058,0.004412398,0.003094138,0.0017500579,0.0014495738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011395937,0.0016482876,0.0025737884,0.0018000192,0.0012730525,0.0042393645,0.002226625,0.0031108707,0.0087195905],"category_scores_gemma":[0.06378179,0.0010920147,0.00081462355,0.0019970292,0.0030698502,0.004892272,0.0032263878,0.0041066282,0.0014459967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011073315,0.0001497986,0.003179238,0.00024981494,0.0000927221,0.00017832693,0.00023345195,0.7755258,0.0008394341,0.16124815,0.0037214635,0.05347449],"study_design_scores_gemma":[0.000056212953,0.00010422074,0.0007606653,0.00007433312,0.000025187937,0.00003225343,0.000029587363,0.8840758,0.0004648236,0.11371195,0.00064095506,0.000023966244],"about_ca_topic_score_codex":0.004216645,"about_ca_topic_score_gemma":0.0053759324,"teacher_disagreement_score":0.011395937,"about_ca_system_score_codex":0.0036805873,"about_ca_system_score_gemma":0.0023034655,"threshold_uncertainty_score":0.060268164},"labels":[],"label_agreement":null},{"id":"W2613496886","doi":"10.23919/date.2017.7927235","title":"Multi-armed bandits for efficient lifetime estimation in MPSoC design","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"MPSoC; Computer science; Estimation; System on a chip; Embedded system; Engineering; Systems engineering","score_opus":0.28522129695402665,"score_gpt":0.5120190131924317,"score_spread":0.22679771623840506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613496886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03535514,0.0011188037,0.9602764,0.00040091167,0.000046566925,0.00009384645,0.00006687423,0.0005974598,0.002043902],"genre_scores_gemma":[0.74556744,0.0006122476,0.25026983,0.00032908694,0.0000817969,0.0004476773,0.00017075485,0.000097997734,0.002423206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984193,0.0009912074,0.00007276597,0.00012898391,0.00025130503,0.0001365276],"domain_scores_gemma":[0.9948715,0.0039301347,0.0004565891,0.00022711667,0.00039386124,0.00012084598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031025098,0.001209786,0.0014315622,0.00095959747,0.0006893579,0.0012379745,0.00084725086,0.0012271111,0.0021461963],"category_scores_gemma":[0.009634052,0.00062760606,0.0006233429,0.00069916894,0.000805347,0.001037262,0.0009216061,0.0014782259,0.00053094333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010567227,0.000037646176,0.0005544379,0.000047905374,0.000036463396,0.000021565727,0.0000296615,0.96854633,0.000536883,0.0055215177,0.00047522443,0.024086677],"study_design_scores_gemma":[0.000006277021,0.000021434034,0.000039864808,0.000007663757,0.0000040868267,0.00000417378,0.0000044894937,0.9972779,0.00020173556,0.002263477,0.00016648797,0.0000022841414],"about_ca_topic_score_codex":0.003411394,"about_ca_topic_score_gemma":0.0034395715,"teacher_disagreement_score":0.003411394,"about_ca_system_score_codex":0.0010044747,"about_ca_system_score_gemma":0.0013042514,"threshold_uncertainty_score":0.016407847},"labels":[],"label_agreement":null},{"id":"W2740079300","doi":"10.24963/ijcai.2017/281","title":"Efficiency Through Procrastination: Approximately Optimal Algorithm Configuration with Runtime Guarantees","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Procrastination; Computer science; Algorithm; Asymptotically optimal algorithm; Algorithm design; Distributed computing","score_opus":0.11211907534675045,"score_gpt":0.42880950455152594,"score_spread":0.3166904292047755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740079300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049358387,0.00087309664,0.9341007,0.0010624735,0.00009143323,0.00025698481,0.00012372578,0.0040795417,0.010053687],"genre_scores_gemma":[0.68152297,0.0005174147,0.3103106,0.0006420128,0.00020575341,0.0007462239,0.00049063563,0.0017359328,0.0038283635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9827017,0.0071494766,0.0009872692,0.002539045,0.0044405446,0.0021819232],"domain_scores_gemma":[0.92959666,0.03625013,0.004151967,0.02444953,0.0036268185,0.0019248291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0120542785,0.0024966162,0.0029485757,0.0017988374,0.0016910221,0.0039661243,0.0053017163,0.0026438788,0.0058888434],"category_scores_gemma":[0.08520626,0.0013512128,0.001400711,0.00231531,0.004661358,0.00747971,0.0058305115,0.0050353683,0.002895576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019447565,0.0005645656,0.0047404664,0.0004370279,0.00016714155,0.0003713389,0.00048535824,0.56081927,0.009708712,0.1290108,0.013907684,0.27784297],"study_design_scores_gemma":[0.0001555862,0.00030630792,0.00037491677,0.000058679572,0.000042705648,0.0002737274,0.00006208767,0.8892301,0.0060479627,0.10082282,0.0025895212,0.000035646775],"about_ca_topic_score_codex":0.0010679476,"about_ca_topic_score_gemma":0.0012540395,"teacher_disagreement_score":0.0120542785,"about_ca_system_score_codex":0.0021701097,"about_ca_system_score_gemma":0.0043386044,"threshold_uncertainty_score":0.06374991},"labels":[],"label_agreement":null},{"id":"W2765574662","doi":"10.1109/tac.2017.2765501","title":"The Multi-Armed Bandit With Stochastic Plays","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Sublinear function; Mathematical optimization; Upper and lower bounds; Stochastic process; Process (computing); Computer science; Power (physics); Work (physics); Demand response; Mathematics; Engineering; Machine learning; Statistics; Discrete mathematics","score_opus":0.07040009105956221,"score_gpt":0.3874683501386741,"score_spread":0.31706825907911185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765574662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016377775,0.00069792947,0.9742624,0.001366455,0.00013571543,0.00008893357,0.00013299097,0.00032763783,0.0066101267],"genre_scores_gemma":[0.80358416,0.0010807337,0.17898406,0.0012056996,0.0004501524,0.00052976265,0.0003262119,0.00021916522,0.013620055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614185,0.0023110802,0.000150182,0.00052432617,0.00048183222,0.0003906861],"domain_scores_gemma":[0.9900815,0.007438758,0.00085400214,0.00074720255,0.00053749274,0.00034098796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005229055,0.0022562365,0.0027770875,0.00076123665,0.0011131427,0.0027292622,0.002554866,0.0028094463,0.005271066],"category_scores_gemma":[0.016360128,0.0009715182,0.0014820541,0.0013150094,0.002714704,0.0032025273,0.0023601209,0.0042686374,0.0012291138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031197956,0.00012722332,0.0008045924,0.00016438334,0.0001076508,0.000166841,0.000110200825,0.8359472,0.0007844983,0.13472904,0.003285493,0.02346092],"study_design_scores_gemma":[0.000025549,0.000038439273,0.000060292823,0.000014374986,0.0000114437435,0.000019607003,0.000005923849,0.96756506,0.00021127655,0.031452876,0.0005862718,0.00000895626],"about_ca_topic_score_codex":0.0026761144,"about_ca_topic_score_gemma":0.0022675898,"teacher_disagreement_score":0.005271066,"about_ca_system_score_codex":0.001634384,"about_ca_system_score_gemma":0.0018818373,"threshold_uncertainty_score":0.02765423},"labels":[],"label_agreement":null},{"id":"W2768553781","doi":"10.3386/w24046","title":"Fast and Slow Learning From Reviews","year":2017,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Army Research Office; Multidisciplinary University Research Initiative","keywords":"Computer science; Psychology","score_opus":0.7586984365747184,"score_gpt":0.6545416765619062,"score_spread":0.10415676001281216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768553781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19936626,0.0017437723,0.77475065,0.003909347,0.00017043902,0.0002891531,0.0010628987,0.00096124865,0.017746164],"genre_scores_gemma":[0.92348784,0.0012524106,0.045485772,0.0005436896,0.00024371833,0.00032017843,0.0006279716,0.00020688486,0.027831387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620146,0.0012644351,0.00017853387,0.0011063098,0.00084860536,0.00040065902],"domain_scores_gemma":[0.9605447,0.028404849,0.004141519,0.0028792655,0.0031908369,0.0008387464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064543583,0.0008053132,0.002089167,0.0013611964,0.0006336201,0.0029281655,0.0028678211,0.0027757846,0.0070683286],"category_scores_gemma":[0.05746717,0.0012434633,0.0012421896,0.0011039753,0.0017819699,0.00750567,0.0015400978,0.002581442,0.0023125338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006947715,0.0003086385,0.013231082,0.0006201774,0.00020502807,0.00091361534,0.0013829282,0.38297442,0.005985622,0.4439409,0.010454602,0.13928822],"study_design_scores_gemma":[0.00007392562,0.00010347369,0.003156257,0.000054410346,0.00004136649,0.00034920374,0.00007440666,0.865494,0.0009929888,0.12659371,0.0029951143,0.00007103895],"about_ca_topic_score_codex":0.0068587963,"about_ca_topic_score_gemma":0.004255569,"teacher_disagreement_score":0.0070683286,"about_ca_system_score_codex":0.0018387213,"about_ca_system_score_gemma":0.00089568517,"threshold_uncertainty_score":0.03413433},"labels":[],"label_agreement":null},{"id":"W2770008080","doi":"","title":"Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation","year":2017,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Regret; Sublinear function; Computer science; Algorithm; Linear regression; Constraint (computer-aided design); Task (project management); Exponential function; Mathematical optimization; Mathematics; Machine learning; Discrete mathematics","score_opus":0.25850632172385657,"score_gpt":0.4470429972754272,"score_spread":0.1885366755515706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770008080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067636166,0.0009622475,0.9870401,0.00085430755,0.000104127794,0.00013244103,0.00021144305,0.0014779466,0.0024537628],"genre_scores_gemma":[0.26060548,0.0012524232,0.7270392,0.0012022413,0.0005542599,0.0008837296,0.0017490388,0.0007104936,0.006003232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99668306,0.0011457772,0.00018979252,0.00069213065,0.0008159478,0.00047342977],"domain_scores_gemma":[0.9847705,0.01151758,0.0010507292,0.0013616937,0.0009540385,0.00034543645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047884085,0.002609702,0.0027247495,0.0009935412,0.000985996,0.0021764257,0.0041655283,0.0024154615,0.0061996877],"category_scores_gemma":[0.021376278,0.0010426209,0.0015574034,0.0020324432,0.0014526242,0.0041323015,0.0028696968,0.0057563265,0.0030164346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006542719,0.0006742729,0.0012973155,0.0004103185,0.00012798575,0.00011578747,0.00016997872,0.7161039,0.0019342004,0.04373357,0.021211153,0.21356724],"study_design_scores_gemma":[0.000046295256,0.000036868423,0.00009719327,0.00001195195,0.000011464913,0.000028864544,0.000014428522,0.9830344,0.0005305242,0.015552668,0.0006278062,0.0000075371727],"about_ca_topic_score_codex":0.0046594026,"about_ca_topic_score_gemma":0.007428977,"teacher_disagreement_score":0.0061996877,"about_ca_system_score_codex":0.0024343173,"about_ca_system_score_gemma":0.0039597643,"threshold_uncertainty_score":0.025323868},"labels":[],"label_agreement":null},{"id":"W2788451989","doi":"10.1088/1742-5468/ab3988","title":"Online learning of quantum states*","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Noise (video); State (computer science); Quantum state; Quantum; Quantum measurement; Quantum error correction; Quantum information; Quantum algorithm","score_opus":0.05046056171250354,"score_gpt":0.4264589322504994,"score_spread":0.3759983705379959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788451989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18235302,0.00023071433,0.8087892,0.002101729,0.000076104516,0.00014005187,0.00022121746,0.0008649065,0.0052230456],"genre_scores_gemma":[0.9480562,0.00006243993,0.049248066,0.00024581465,0.00006176418,0.00009934793,0.00020645806,0.00006051181,0.0019593213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99590886,0.0020997936,0.00015779752,0.0007975522,0.00059333286,0.0004426807],"domain_scores_gemma":[0.97101146,0.02179578,0.0015349321,0.0039485577,0.0009427228,0.000766634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005113715,0.0008947593,0.0019066309,0.00056360976,0.0009484699,0.0015158224,0.0031212084,0.0017837979,0.003218428],"category_scores_gemma":[0.027770469,0.00069787743,0.0007584384,0.00071522256,0.0039079664,0.0063845324,0.0030965628,0.0037740595,0.0003630863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012003916,0.0005271618,0.0028966083,0.00021079674,0.000107318774,0.00016647812,0.00022947724,0.74340254,0.0023874799,0.17303279,0.0027816854,0.07305713],"study_design_scores_gemma":[0.000024590574,0.00005122267,0.00015760564,0.000007842354,0.0000054265183,0.000011650689,0.000008849222,0.93083525,0.0010492498,0.067702845,0.0001376844,0.000007778363],"about_ca_topic_score_codex":0.002028411,"about_ca_topic_score_gemma":0.0018506574,"teacher_disagreement_score":0.005113715,"about_ca_system_score_codex":0.0022639914,"about_ca_system_score_gemma":0.0018653913,"threshold_uncertainty_score":0.027044237},"labels":[],"label_agreement":null},{"id":"W2796264871","doi":"10.1007/978-3-319-89656-4_3","title":"A Novel Evaluation Methodology for Assessing Off-Policy Learning Methods in Contextual Bandits","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Robustness (evolution); Outcome (game theory); Observational study; Machine learning; Artificial intelligence; Evaluation function; Policy learning; Quality (philosophy)","score_opus":0.42374252120565437,"score_gpt":0.5813126106282402,"score_spread":0.15757008942258588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796264871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02111815,0.000797162,0.973078,0.00023763244,0.00018220101,0.0003021133,0.00021878346,0.0005396727,0.00352627],"genre_scores_gemma":[0.3333215,0.0005626922,0.660527,0.00023800509,0.00029359703,0.001047666,0.0008802205,0.0004614474,0.0026678958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.970902,0.01982263,0.001394619,0.0020601475,0.005116874,0.0007036873],"domain_scores_gemma":[0.8993618,0.077452816,0.0037277488,0.008456172,0.009306684,0.0016948262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03642529,0.0024181528,0.0027784123,0.0039012895,0.0012608598,0.0043482804,0.0032692805,0.004122772,0.005741042],"category_scores_gemma":[0.12449286,0.00067894644,0.0012751428,0.0030311877,0.002933996,0.0060366313,0.0048396396,0.004399035,0.0008020607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016085566,0.0008110956,0.010355621,0.0009027868,0.00075110927,0.00010689254,0.00035740092,0.4267126,0.0033494518,0.12869832,0.0053544003,0.4209918],"study_design_scores_gemma":[0.000082253566,0.0006683888,0.0011053534,0.00013983426,0.0001044871,0.000059344435,0.00007077257,0.953698,0.0020269142,0.04017356,0.0018304188,0.000040740455],"about_ca_topic_score_codex":0.0021595757,"about_ca_topic_score_gemma":0.002192104,"teacher_disagreement_score":0.03642529,"about_ca_system_score_codex":0.0022519887,"about_ca_system_score_gemma":0.0026789808,"threshold_uncertainty_score":0.19263768},"labels":[],"label_agreement":null},{"id":"W2798538355","doi":"","title":"Online Regression with Partial Information: Generalization and Linear Projection","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Generalization; Computer science; Artificial intelligence; Projection (relational algebra); Regression; Mathematics; Statistics; Algorithm","score_opus":0.10514613752246296,"score_gpt":0.4469563311111556,"score_spread":0.3418101935886927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798538355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01319864,0.0010353365,0.98288107,0.0009906639,0.00006671951,0.000056809313,0.00018212714,0.00031821724,0.00127043],"genre_scores_gemma":[0.5922339,0.005108745,0.38578147,0.0010911119,0.0015809062,0.00078079675,0.0019112154,0.00045261596,0.01105924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935707,0.0039409497,0.00029373486,0.0011037788,0.0007470429,0.0003438877],"domain_scores_gemma":[0.9634696,0.028085241,0.0014142586,0.0049627568,0.0016709961,0.00039718204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01463254,0.0025416769,0.0047325986,0.001705534,0.00095405965,0.002370564,0.0035060681,0.0027005982,0.004224039],"category_scores_gemma":[0.05139198,0.002169116,0.0025697837,0.002954104,0.0038316771,0.008689784,0.0043869806,0.006408589,0.001092176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005461114,0.00041823278,0.00224199,0.0006247759,0.0005622509,0.00017844667,0.0002841024,0.6365001,0.0012690363,0.16225451,0.008328403,0.18679203],"study_design_scores_gemma":[0.00003091886,0.000054546657,0.00023944242,0.00003738547,0.000044678414,0.000034576402,0.0000141710325,0.91842103,0.00027247044,0.0802562,0.0005761822,0.000018491766],"about_ca_topic_score_codex":0.005336757,"about_ca_topic_score_gemma":0.0042629726,"teacher_disagreement_score":0.01463254,"about_ca_system_score_codex":0.0013512239,"about_ca_system_score_gemma":0.0025958081,"threshold_uncertainty_score":0.07738519},"labels":[],"label_agreement":null},{"id":"W2803847628","doi":"10.48550/arxiv.1805.09247","title":"Cleaning up the neighborhood: A full classification for adversarial partial monitoring","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Generalization; Adversarial system; Bartok; Computer science; Class (philosophy); Mathematical optimization; Artificial intelligence; Algorithm; Mathematics; Mathematical economics; Machine learning","score_opus":0.41563477076657585,"score_gpt":0.3521115529404013,"score_spread":0.06352321782617454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803847628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01501332,0.0004002374,0.97864896,0.0012425606,0.00008410171,0.00014757368,0.0002721727,0.00045067072,0.0037404122],"genre_scores_gemma":[0.5167581,0.0007021698,0.46698594,0.0013444034,0.00045948633,0.0008194819,0.0012209557,0.00056671497,0.011142823],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970522,0.0011386262,0.00011157808,0.00081412675,0.0005578495,0.0003256664],"domain_scores_gemma":[0.9914585,0.00500389,0.00055386085,0.002007623,0.0004709076,0.0005053113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039747814,0.0017846785,0.003179928,0.00091423205,0.0016031151,0.0030584913,0.0054287245,0.0041084504,0.0060720462],"category_scores_gemma":[0.019472023,0.0010440428,0.002200733,0.0010884186,0.0029195247,0.008330896,0.006885408,0.0075147054,0.0013695804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067005475,0.00040740977,0.0043154582,0.0003228905,0.00019429685,0.00026132984,0.00044909067,0.50380224,0.0024789996,0.3154619,0.018887844,0.15274853],"study_design_scores_gemma":[0.000028047707,0.00005375362,0.00020845383,0.000040558567,0.00002027676,0.000062524756,0.00002880837,0.8480587,0.00061037304,0.14910494,0.001767536,0.000016061362],"about_ca_topic_score_codex":0.0020465087,"about_ca_topic_score_gemma":0.002560011,"teacher_disagreement_score":0.0060720462,"about_ca_system_score_codex":0.0019809683,"about_ca_system_score_gemma":0.0017079316,"threshold_uncertainty_score":0.02102089},"labels":[],"label_agreement":null},{"id":"W2806928859","doi":"10.1609/aaai.v32i1.12183","title":"Imitation Upper Confidence Bound for Bandits on a Graph","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données","keywords":"Graph; Upper and lower bounds; Computer science; Imitation; Extension (predicate logic); Theoretical computer science; Mathematics; Mathematical optimization; Artificial intelligence; Psychology","score_opus":0.31198128436934186,"score_gpt":0.4631698758885268,"score_spread":0.15118859151918496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806928859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035173167,0.0005070027,0.9585033,0.00068624876,0.00004841862,0.000058945265,0.00012294426,0.0006358347,0.0042640786],"genre_scores_gemma":[0.8291359,0.0005760312,0.16343294,0.00040304183,0.00012592642,0.00034407352,0.00045782086,0.00031969917,0.0052046985],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962831,0.0015504229,0.00017975386,0.00066988514,0.00085631706,0.00046051227],"domain_scores_gemma":[0.9571231,0.034559548,0.0024175453,0.0027435413,0.0021018626,0.0010543877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059141433,0.0015847131,0.0029628105,0.0016765959,0.0010724759,0.002972663,0.0034738039,0.003036309,0.0039495486],"category_scores_gemma":[0.04979809,0.0007949152,0.0007839137,0.0018607405,0.0027724023,0.0048773843,0.0033268633,0.0037331462,0.00081939594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021996605,0.00006798191,0.00078437227,0.00009808731,0.00005003984,0.00006762757,0.000093450624,0.9106744,0.00071424607,0.058645703,0.0015360214,0.027048066],"study_design_scores_gemma":[0.000008986494,0.000014141907,0.00004946911,0.000009686093,0.000004518784,0.000011156422,0.000005517559,0.97782636,0.00022441613,0.021679446,0.00016155042,0.000004824766],"about_ca_topic_score_codex":0.0053483522,"about_ca_topic_score_gemma":0.0031742502,"teacher_disagreement_score":0.0059141433,"about_ca_system_score_codex":0.0029990189,"about_ca_system_score_gemma":0.0020821572,"threshold_uncertainty_score":0.0312773},"labels":[],"label_agreement":null},{"id":"W2809048072","doi":"10.1002/asmb.2355","title":"A Bayesian two‐armed bandit model","year":2018,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Stochastic game; Monotonic function; Mathematical optimization; Multi-armed bandit; Dynamic programming; Computer science; Bayesian probability; Outcome (game theory); Value (mathematics); Term (time); Sequence (biology); Stochastic programming; Mathematical economics; Economics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.1201796460493762,"score_gpt":0.3928292364248337,"score_spread":0.2726495903754575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809048072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053506814,0.0013111795,0.9160859,0.00433571,0.0001548999,0.00013385169,0.0008043803,0.00025555925,0.02341165],"genre_scores_gemma":[0.92460907,0.0013298555,0.04688695,0.0007168339,0.0002333484,0.0003810956,0.00040053975,0.00005200811,0.02539044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975981,0.001197447,0.00009826619,0.00044103168,0.00034950834,0.00031572286],"domain_scores_gemma":[0.994249,0.0040625357,0.0008797068,0.00019333643,0.00042441633,0.00019103626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041143503,0.0011818081,0.0026218859,0.0010101772,0.000835029,0.003498212,0.0020310741,0.004447841,0.0060139084],"category_scores_gemma":[0.010024538,0.0008528791,0.0008720185,0.0016404877,0.0025069986,0.0023481515,0.001425655,0.0025135214,0.0012495291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011638439,0.00006624701,0.0010499809,0.00009439281,0.00007543765,0.00024204826,0.00011071066,0.6975746,0.0003658003,0.28997248,0.0024689345,0.007863052],"study_design_scores_gemma":[0.000028043423,0.000028447226,0.00020734253,0.000028862954,0.00001940519,0.000033684217,0.00002365584,0.9273287,0.00007021987,0.07128379,0.0009264796,0.00002132463],"about_ca_topic_score_codex":0.010058488,"about_ca_topic_score_gemma":0.0055245026,"teacher_disagreement_score":0.010058488,"about_ca_system_score_codex":0.0019084585,"about_ca_system_score_gemma":0.0012685076,"threshold_uncertainty_score":0.021758974},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16252772352173464,"score_gpt":0.46404372301064795,"score_spread":0.3015159994889133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810504435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04760728,0.00033678,0.94921553,0.00021484595,0.000045113506,0.000046611352,0.000023034278,0.00006983912,0.002440932],"genre_scores_gemma":[0.9525275,0.00021386864,0.045773536,0.00011065476,0.00003966312,0.000053390784,0.000023903307,0.0000089874675,0.0012484649],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990382,0.000356951,0.000035510646,0.00016976504,0.00020023594,0.00019945472],"domain_scores_gemma":[0.99885166,0.00050685334,0.00021398779,0.00014029446,0.0001744713,0.000112802576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011823389,0.00082321663,0.0007225633,0.00062001386,0.0006810095,0.0008491493,0.0013072654,0.00089267385,0.0006805164],"category_scores_gemma":[0.0025251445,0.0002052504,0.0005874383,0.00080512784,0.00074260833,0.0013742142,0.0014572907,0.00086558756,0.0001320882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036090758,0.00016271956,0.0015448536,0.00017687988,0.00020049272,0.00054724887,0.00024219953,0.78665346,0.028665312,0.0944589,0.0018696401,0.08511732],"study_design_scores_gemma":[0.000013896812,0.00014138794,0.00017202357,0.0000063830266,0.000031876476,0.00015145713,0.000037195896,0.9878372,0.0019937044,0.008928769,0.0006735827,0.000012441172],"about_ca_topic_score_codex":0.00067081704,"about_ca_topic_score_gemma":0.0006528165,"teacher_disagreement_score":0.0013072654,"about_ca_system_score_codex":0.0007203165,"about_ca_system_score_gemma":0.0006271217,"threshold_uncertainty_score":0.0062528253},"labels":[],"label_agreement":null},{"id":"W2884790233","doi":"10.1007/978-3-319-92988-0_4","title":"Learning in a Game of Strategic Experimentation with Three-Armed Exponential Bandits","year":2018,"lang":"en","type":"book-chapter","venue":"Static & dynamic game theory: foundations & applications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Exponential function; Mathematical economics; Computer science; Operations research; Mathematics; Mathematical analysis","score_opus":0.09269191808257796,"score_gpt":0.41238929095090215,"score_spread":0.3196973728683242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884790233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1493896,0.00045999893,0.8021298,0.0018969332,0.000063505075,0.0001592225,0.00009404427,0.00023020522,0.045576606],"genre_scores_gemma":[0.9267648,0.00042781376,0.054785013,0.00019456941,0.00005807736,0.00024254188,0.000065188004,0.00004158629,0.017420435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704283,0.0019371524,0.00010119415,0.0003146507,0.00031246452,0.0002917574],"domain_scores_gemma":[0.98874366,0.009833796,0.00043481114,0.000411828,0.00022294963,0.0003529492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038297174,0.0009992712,0.0013946082,0.00044772195,0.00076984224,0.003333086,0.0019874875,0.00289639,0.006295612],"category_scores_gemma":[0.01719135,0.00053732935,0.0011054755,0.00075909885,0.0039527724,0.004732745,0.0024489893,0.0028057313,0.00058617734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024850972,0.00011618152,0.0006490293,0.000119708886,0.000061282946,0.00009513673,0.00035016425,0.3035999,0.00081186596,0.6750608,0.000925299,0.017962117],"study_design_scores_gemma":[0.000065240616,0.000073130155,0.00014021633,0.00002864968,0.000012434241,0.000030225427,0.00007051381,0.55487514,0.00023003043,0.4434008,0.0010538322,0.000019779432],"about_ca_topic_score_codex":0.0019249235,"about_ca_topic_score_gemma":0.0014328811,"teacher_disagreement_score":0.006295612,"about_ca_system_score_codex":0.0018720663,"about_ca_system_score_gemma":0.0013595562,"threshold_uncertainty_score":0.021060944},"labels":[],"label_agreement":null},{"id":"W2885586573","doi":"","title":"MRG_UWaterloo and WaterlooCormack Participation in the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Core (optical fiber); Telecommunications; Operating system","score_opus":0.354013297376704,"score_gpt":0.5097599940313238,"score_spread":0.15574669665461977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885586573","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016787477,0.008997363,0.019325377,0.17298892,0.07243968,0.0044178437,0.143698,0.01088666,0.5504586],"genre_scores_gemma":[0.021117322,0.00094166846,0.0093009,0.0071869153,0.0033437784,0.00046926845,0.048586708,0.0015856111,0.90746784],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9900663,0.0013192487,0.00021962664,0.001231911,0.004837827,0.0023250342],"domain_scores_gemma":[0.9700944,0.0011322276,0.00038823942,0.0015996415,0.016583864,0.010201625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010414007,0.002055707,0.0033712843,0.0049538137,0.0064205695,0.0055835014,0.0031141036,0.0037382606,0.24904913],"category_scores_gemma":[0.014557877,0.00073358056,0.0010069904,0.0049235197,0.0014440962,0.0039081634,0.0052282265,0.002663233,0.10711842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014292657,0.000062894804,0.00021804469,0.000039755076,0.000007518736,0.00005030178,0.000065823035,0.00007563177,0.0010095278,0.0010183644,0.9819577,0.015351561],"study_design_scores_gemma":[0.00009848219,0.00005607997,0.0013250036,0.00003136766,0.000013501385,0.00003487731,0.00029066106,0.0010116273,0.0014886308,0.0010851907,0.99453026,0.000034242443],"about_ca_topic_score_codex":0.28343266,"about_ca_topic_score_gemma":0.5706774,"teacher_disagreement_score":0.28343266,"about_ca_system_score_codex":0.013200108,"about_ca_system_score_gemma":0.021515965,"threshold_uncertainty_score":0.8331523},"labels":[],"label_agreement":null},{"id":"W2888696679","doi":"10.1287/moor.2021.1168","title":"Multiplayer Bandits Without Observing Collision Information","year":2021,"lang":"en","type":"preprint","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données; Université de Montréal; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; Canada First Research Excellence Fund; Centre de Recherches Mathématiques; Fundación BBVA","keywords":"Regret; Logarithm; Collision; Square root; Computer science; Nash equilibrium; Square (algebra); Mathematical optimization; Root (linguistics); Mathematical economics; Mathematics; Computer security; Mathematical analysis; Machine learning; Geometry","score_opus":0.45722932184973136,"score_gpt":0.5586788726154809,"score_spread":0.10144955076574952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888696679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16851711,0.0005498976,0.82175344,0.0008257016,0.00011417186,0.00015833456,0.00020644261,0.00033575768,0.007539157],"genre_scores_gemma":[0.93604165,0.0002932678,0.05633627,0.00027286136,0.00010478829,0.00023016399,0.00020098439,0.000071994735,0.00644807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968292,0.00134923,0.00014420939,0.00057186245,0.0004941959,0.0006112284],"domain_scores_gemma":[0.98199534,0.013552348,0.0023122511,0.000879266,0.00053320976,0.0007275308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034665172,0.0022316459,0.0024725078,0.00074335217,0.001166744,0.0022813776,0.002551194,0.0023352713,0.0035717767],"category_scores_gemma":[0.01812477,0.0009529482,0.0010909485,0.001223302,0.0022980114,0.004001099,0.0031025007,0.0031986893,0.0006866055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073169405,0.00019936328,0.0010489903,0.00012327054,0.000102989114,0.00020522639,0.00015849412,0.8984149,0.0014122432,0.0857178,0.0009305925,0.010954482],"study_design_scores_gemma":[0.00003993954,0.00008290342,0.000082660736,0.000008427198,0.000011866733,0.00003182649,0.000022361874,0.96463513,0.00039901832,0.034454025,0.00022138275,0.000010402419],"about_ca_topic_score_codex":0.0027014036,"about_ca_topic_score_gemma":0.0019384586,"teacher_disagreement_score":0.0035717767,"about_ca_system_score_codex":0.0017804538,"about_ca_system_score_gemma":0.0010881465,"threshold_uncertainty_score":0.018332899},"labels":[],"label_agreement":null},{"id":"W2895703110","doi":"10.1007/s10107-018-1336-7","title":"Faster algorithms for extensive-form game solving via improved smoothing functions","year":2018,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Army Research Laboratory; Directorate for Engineering; Directorate for Computer and Information Science and Engineering; Facebook","keywords":"Regret; Game tree; Mathematics; Smoothing; Weighting; Rate of convergence; Mathematical optimization; Logarithm; Entropy (arrow of time); Algorithm; Function (biology); Computer science; Game theory; Mathematical economics; Sequential game; Statistics","score_opus":0.1317707157070351,"score_gpt":0.4261131786377163,"score_spread":0.2943424629306812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895703110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069574295,0.0001384856,0.98888564,0.00023501767,0.00006778172,0.00007744009,0.000045950706,0.0007874888,0.0028047643],"genre_scores_gemma":[0.20343558,0.0002663368,0.7857937,0.00033780545,0.0001396965,0.00069605437,0.00029421586,0.0005729878,0.008463573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976738,0.0009087695,0.00011966626,0.00034655604,0.0005835813,0.00036759514],"domain_scores_gemma":[0.98874134,0.0077976044,0.00045505606,0.0016397954,0.0009908173,0.0003753892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042703343,0.0022502248,0.002758168,0.0017191342,0.0010870949,0.0028022446,0.00310365,0.002738365,0.017049888],"category_scores_gemma":[0.019698437,0.0010511867,0.001828378,0.0022834234,0.0016572997,0.0057528587,0.003008994,0.0057324967,0.0038019703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046703848,0.0005564832,0.00094824383,0.00026913697,0.0001144657,0.00006389887,0.00029831685,0.54673964,0.0022075353,0.17820857,0.008359377,0.2617672],"study_design_scores_gemma":[0.00006896718,0.000037613565,0.000108074404,0.000017041297,0.000015531437,0.000012793052,0.000021099017,0.92824453,0.0005557345,0.069971845,0.00093640434,0.000010255017],"about_ca_topic_score_codex":0.0061817653,"about_ca_topic_score_gemma":0.008816078,"teacher_disagreement_score":0.017049888,"about_ca_system_score_codex":0.002312149,"about_ca_system_score_gemma":0.004292877,"threshold_uncertainty_score":0.057037532},"labels":[],"label_agreement":null},{"id":"W2897984390","doi":"10.1007/s10994-019-05833-y","title":"Combining Bayesian optimization and Lipschitz optimization","year":2019,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institute for Advanced Research","keywords":"Lipschitz continuity; Bayesian optimization; Heuristics; Regret; Mathematical optimization; Computer science; Bayesian probability; Constant (computer programming); Optimization problem; Function (biology); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.05627383965606547,"score_gpt":0.3841076774584195,"score_spread":0.32783383780235403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897984390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002792356,0.001014012,0.9918087,0.0007915226,0.000072770505,0.000014703698,0.000040665946,0.00011123693,0.003354053],"genre_scores_gemma":[0.31524825,0.005729934,0.654867,0.0011189565,0.001471627,0.0003466896,0.0005791829,0.0006739746,0.019964444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960594,0.0023885586,0.00015740577,0.00036731313,0.00087648485,0.00015071475],"domain_scores_gemma":[0.9849641,0.012008377,0.0006582759,0.0009274949,0.0011693987,0.00027247853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008655819,0.0017767475,0.0034895309,0.0024395264,0.0007747743,0.0041216817,0.0019422236,0.0034224067,0.003922801],"category_scores_gemma":[0.03479904,0.0015279046,0.0011370357,0.0029726913,0.0025844602,0.006171033,0.0037259206,0.0035831924,0.0010037089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012360253,0.000090621026,0.00053857267,0.00033669797,0.00020599607,0.000056527657,0.000089443194,0.30017808,0.0007503249,0.62174153,0.0055414177,0.07034717],"study_design_scores_gemma":[0.000012624669,0.00001660349,0.000112328824,0.00003565568,0.000020441737,0.0000125516435,0.000009032448,0.6856382,0.0002624806,0.31246898,0.0013954738,0.000015566062],"about_ca_topic_score_codex":0.0037938084,"about_ca_topic_score_gemma":0.003519239,"teacher_disagreement_score":0.008655819,"about_ca_system_score_codex":0.0020551065,"about_ca_system_score_gemma":0.002355595,"threshold_uncertainty_score":0.045776904},"labels":[],"label_agreement":null},{"id":"W2903574704","doi":"10.1609/aaai.v33i01.33013943","title":"Meta-Descent for Online, Continual Prediction","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stochastic gradient descent; Computer science; Gradient descent; Range (aeronautics); Mathematical optimization; Descent (aeronautics); Hessian matrix; Artificial intelligence; Algorithm; Mathematics; Applied mathematics; Artificial neural network","score_opus":0.5329035804286594,"score_gpt":0.47185202673754284,"score_spread":0.061051553691116534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903574704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009488334,0.0008161665,0.9871884,0.00031716021,0.00007351693,0.00003309499,0.000047780984,0.0006671224,0.00136845],"genre_scores_gemma":[0.48159516,0.00075664214,0.5114313,0.00043454074,0.0001996819,0.00032176188,0.00034987475,0.00040614099,0.004504925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992767,0.00026957574,0.000043704895,0.00014220203,0.00020088766,0.000067002824],"domain_scores_gemma":[0.9969445,0.0020865118,0.0002373081,0.00029676443,0.00032919357,0.00010569188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027318394,0.0012122223,0.0016360078,0.0008865416,0.00045625112,0.0013431387,0.002007972,0.0017386392,0.001988339],"category_scores_gemma":[0.00738201,0.00082984427,0.00089930417,0.0008858863,0.0011236827,0.0017181948,0.0012234179,0.00240502,0.00065548706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007237403,0.000057935904,0.0005648008,0.00009359905,0.000082981904,0.00004816802,0.000040153074,0.9378581,0.0008599885,0.015648142,0.0016741846,0.042999562],"study_design_scores_gemma":[0.0000053497306,0.000010339627,0.000031798092,0.0000057311863,0.0000035349042,0.0000055992614,0.0000020311252,0.99601376,0.00018863507,0.0034086506,0.00032221817,0.0000023715259],"about_ca_topic_score_codex":0.003579758,"about_ca_topic_score_gemma":0.004206594,"teacher_disagreement_score":0.003579758,"about_ca_system_score_codex":0.0011300585,"about_ca_system_score_gemma":0.0016317206,"threshold_uncertainty_score":0.01444757},"labels":[],"label_agreement":null},{"id":"W2904232271","doi":"10.1609/aaai.v33i01.33016112","title":"Leveraging Observations in Bandits: Between Risks and Benefits","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Multi-armed bandit; Leverage (statistics); Computer science; Optimism; Context (archaeology); Thompson sampling; Order (exchange); Task (project management); Artificial intelligence; Machine learning; Dependency (UML); Economics; Psychology","score_opus":0.534976651882224,"score_gpt":0.4463792313613104,"score_spread":0.08859742052091357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904232271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12502432,0.0010209879,0.86860657,0.0015073654,0.000045747773,0.00008811346,0.000050303595,0.00050524395,0.003151346],"genre_scores_gemma":[0.9427553,0.00039839523,0.055065952,0.00023712931,0.000060879058,0.00013442563,0.00003592786,0.00007910468,0.0012329064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99424356,0.0033743882,0.0002542742,0.0007499805,0.000978374,0.00039938162],"domain_scores_gemma":[0.9244561,0.06376859,0.0048958897,0.005063485,0.0010247291,0.00079128053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0123988865,0.002015115,0.0019938215,0.00071863836,0.0009622455,0.002383128,0.0020500936,0.0027935887,0.0014435655],"category_scores_gemma":[0.07663623,0.0011353819,0.0008565105,0.0005897645,0.004392011,0.0055657616,0.004619733,0.0050078123,0.00034852186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005430088,0.00014479177,0.0040040123,0.00013331238,0.00012389019,0.00017711383,0.0002506721,0.87307596,0.0019804407,0.08216585,0.000460153,0.03694078],"study_design_scores_gemma":[0.000040113562,0.00015126824,0.00051037694,0.000037999445,0.000026706923,0.000055098582,0.000024821878,0.937046,0.0010612415,0.06074887,0.00027494464,0.000022618562],"about_ca_topic_score_codex":0.0017360937,"about_ca_topic_score_gemma":0.0013634105,"teacher_disagreement_score":0.0123988865,"about_ca_system_score_codex":0.0014685881,"about_ca_system_score_gemma":0.0013504049,"threshold_uncertainty_score":0.06557232},"labels":[],"label_agreement":null},{"id":"W2906115048","doi":"10.1287/moor.2021.1220","title":"A Primal–Dual Learning Algorithm for Personalized Dynamic Pricing with an Inventory Constraint","year":2022,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematical optimization; Curse of dimensionality; Regret; Dual (grammatical number); Dynamic pricing; Computer science; Revenue management; Constraint (computer-aided design); Revenue; Mathematics; Artificial intelligence; Machine learning; Economics; Microeconomics","score_opus":0.21645571140289932,"score_gpt":0.49928447950654015,"score_spread":0.2828287681036408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906115048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011865746,0.0004033759,0.9829947,0.0005673583,0.00007252019,0.000078158875,0.000077593984,0.00022902478,0.0037116262],"genre_scores_gemma":[0.3860553,0.00047982403,0.60460335,0.00060053443,0.00023524041,0.00045614372,0.000365845,0.00017150145,0.0070322333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992353,0.00030021954,0.000031381875,0.00017127476,0.00014064997,0.0001211993],"domain_scores_gemma":[0.9983171,0.0011681351,0.00011949041,0.000098284225,0.00019328862,0.00010367606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022893036,0.0012363113,0.0018403718,0.00065762515,0.0006304354,0.001491802,0.002070862,0.0022699686,0.004532402],"category_scores_gemma":[0.0050874003,0.00080192846,0.0005959802,0.0012645862,0.0010882393,0.0018877318,0.0016294477,0.0026559732,0.0008825845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013517837,0.00023769272,0.000601831,0.00010101362,0.000044405722,0.00006913407,0.000053237545,0.8912637,0.00048423826,0.03203675,0.005173841,0.06979893],"study_design_scores_gemma":[0.000022678294,0.000017242144,0.000025260122,0.0000051429975,0.0000032090209,0.000011942191,0.000004710325,0.9909462,0.000078854704,0.008513169,0.00036865385,0.000002981297],"about_ca_topic_score_codex":0.002991462,"about_ca_topic_score_gemma":0.0024987522,"teacher_disagreement_score":0.004532402,"about_ca_system_score_codex":0.0016151359,"about_ca_system_score_gemma":0.0022385707,"threshold_uncertainty_score":0.015162349},"labels":[],"label_agreement":null},{"id":"W2909800602","doi":"10.3929/ethz-b-000337731","title":"No-Regret Bayesian Optimization with Unknown Hyperparameters","year":2019,"lang":"en","type":"article","venue":"Repository for Publications and Research Data (ETH Zurich)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Hyperparameter; Bayesian optimization; Computer science; Regret; Benchmark (surveying); Gaussian process; Hyperparameter optimization; Mathematical optimization; Convergence (economics); Machine learning; Kernel (algebra); Black box; Artificial intelligence; Function (biology); Bayesian probability; Algorithm; Gaussian; Mathematics; Support vector machine","score_opus":0.2288060053411779,"score_gpt":0.4751225414535335,"score_spread":0.2463165361123556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909800602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011697164,0.0007680561,0.9823453,0.00089664524,0.000049745573,0.0000840803,0.0001325346,0.00081227324,0.0032141046],"genre_scores_gemma":[0.46242538,0.0008378966,0.5257748,0.0010563881,0.00022251578,0.0005568993,0.00088924053,0.00077125715,0.007465585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703133,0.0016304455,0.000117139985,0.0004991216,0.00043544377,0.00028643728],"domain_scores_gemma":[0.9870472,0.01029695,0.0007704608,0.00086517044,0.00068862084,0.00033165497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056008827,0.0025038193,0.0030139834,0.00091821724,0.0009337163,0.0021012973,0.002678205,0.0033136413,0.0037137629],"category_scores_gemma":[0.022709703,0.0011516776,0.0011621636,0.0014632054,0.002405806,0.0026761324,0.0025361099,0.004253664,0.0013917749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023539503,0.00011472566,0.0007621924,0.00017391173,0.000069678994,0.000050464485,0.000057325447,0.91895187,0.00048014286,0.031822108,0.004537834,0.042744357],"study_design_scores_gemma":[0.000027020333,0.000017555405,0.00008093937,0.000016502287,0.0000070210467,0.000011384391,0.0000073737297,0.983528,0.00022481958,0.015662892,0.00041009492,0.0000063972616],"about_ca_topic_score_codex":0.009218817,"about_ca_topic_score_gemma":0.009719875,"teacher_disagreement_score":0.009218817,"about_ca_system_score_codex":0.0022954796,"about_ca_system_score_gemma":0.0035373631,"threshold_uncertainty_score":0.029620647},"labels":[],"label_agreement":null},{"id":"W2910547178","doi":"10.1609/icaps.v29i1.3505","title":"Robust and Adaptive Planning under Model Uncertainty","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Robustness (evolution); Computation; Mathematical optimization; Computer science; Adversary; Monte Carlo method; Tree (set theory); Decision tree; Monte Carlo tree search; Bayesian probability; Artificial intelligence; Algorithm; Mathematics","score_opus":0.2897143656682048,"score_gpt":0.4215858200438864,"score_spread":0.1318714543756816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910547178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016926346,0.0002465859,0.9803098,0.00038306933,0.000018721244,0.000040629504,0.0000468272,0.00028371124,0.0017443015],"genre_scores_gemma":[0.79371476,0.00030996156,0.20392357,0.00021380566,0.000050386996,0.0001788701,0.0001437947,0.00011302432,0.0013517059],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752635,0.0011766846,0.00009014459,0.00046879015,0.00050527946,0.00023272741],"domain_scores_gemma":[0.99229187,0.0061224164,0.0006181364,0.0004836604,0.00030974846,0.00017404601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037799107,0.0010193994,0.0013112088,0.0006441492,0.00060471543,0.0015408259,0.0015288418,0.0014758426,0.001630049],"category_scores_gemma":[0.015412479,0.00089016097,0.00086706923,0.00072609476,0.0021302213,0.0020743161,0.0019636343,0.00240529,0.00024261513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038616457,0.000012582888,0.00027542422,0.000021197842,0.00002409443,0.000025556072,0.000030178448,0.9756209,0.00021708618,0.014992732,0.00024717656,0.008494418],"study_design_scores_gemma":[0.0000067960036,0.000014128822,0.00004932036,0.000006470633,0.0000040722334,0.000009727318,0.0000061241694,0.97691786,0.00017462374,0.022632165,0.00017404565,0.000004662316],"about_ca_topic_score_codex":0.006579984,"about_ca_topic_score_gemma":0.004842952,"teacher_disagreement_score":0.006579984,"about_ca_system_score_codex":0.0015454429,"about_ca_system_score_gemma":0.0024748459,"threshold_uncertainty_score":0.019990385},"labels":[],"label_agreement":null},{"id":"W2911952628","doi":"10.1109/tac.2019.2895253","title":"Thompson Sampling for Stochastic Control: The Continuous Parameter Case","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Regret; Stochastic control; Mathematics; Control (management); Mathematical optimization; State (computer science); Class (philosophy); Thompson sampling; Computer science; Applied mathematics; Control theory (sociology); Optimal control; Statistics; Algorithm; Artificial intelligence","score_opus":0.07199831115677265,"score_gpt":0.3889426739652809,"score_spread":0.3169443628085083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911952628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02649026,0.0009437471,0.96902597,0.0004924192,0.000049878035,0.00007093439,0.00006266724,0.000126114,0.0027380292],"genre_scores_gemma":[0.8892894,0.001052685,0.10637762,0.00030277454,0.00015418706,0.00021422622,0.00016483513,0.000107347754,0.0023370525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956169,0.0023720318,0.00017754306,0.0006863436,0.00083638646,0.00031072888],"domain_scores_gemma":[0.9748871,0.02114069,0.0011232742,0.0014391278,0.0009076902,0.00050224655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076376363,0.0014246072,0.0024905708,0.00081903994,0.0007381939,0.0019051589,0.0019075748,0.002304407,0.0023976557],"category_scores_gemma":[0.036966655,0.0005569089,0.00090450066,0.0011522126,0.0029548106,0.0029062873,0.0019295509,0.0025320589,0.00025597276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002851101,0.000056063876,0.0010671556,0.00015406683,0.0000968635,0.00017761978,0.00011242043,0.7799892,0.0013236294,0.19737141,0.0007649519,0.018601624],"study_design_scores_gemma":[0.000019062023,0.00006122652,0.00017813493,0.000020315467,0.000009871363,0.000030449639,0.0000113352025,0.93927574,0.0004385706,0.059600055,0.00034304117,0.0000121526655],"about_ca_topic_score_codex":0.0044267783,"about_ca_topic_score_gemma":0.00210349,"teacher_disagreement_score":0.0076376363,"about_ca_system_score_codex":0.0019608233,"about_ca_system_score_gemma":0.0016645272,"threshold_uncertainty_score":0.04039216},"labels":[],"label_agreement":null},{"id":"W2913189977","doi":"10.48550/arxiv.1902.05454","title":"Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Procrastination; Computer science; Parameterized complexity; Property (philosophy); Heuristic; Algorithm; Work (physics); Running time; Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.17310895493980513,"score_gpt":0.29484459573338645,"score_spread":0.12173564079358132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913189977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0672893,0.00038436995,0.9227868,0.00059598446,0.000066661334,0.0002484254,0.00012396152,0.0037633593,0.00474111],"genre_scores_gemma":[0.56878346,0.00016481821,0.42676663,0.0003747696,0.00008568068,0.0004221779,0.0005059701,0.0008599232,0.0020365585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938976,0.0020691273,0.0004066388,0.0013284346,0.0016130686,0.0006852015],"domain_scores_gemma":[0.9738168,0.013601185,0.0024218042,0.007750021,0.001517824,0.0008922508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051860805,0.001689048,0.0018146243,0.0012626275,0.0009946915,0.0022136865,0.004300507,0.0019568559,0.0031318718],"category_scores_gemma":[0.039460175,0.0010870954,0.001131662,0.002017699,0.0022261157,0.0047115223,0.003208732,0.004056389,0.0010416921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010856867,0.0005230471,0.004364281,0.00020624182,0.00014938491,0.00017577017,0.00035074953,0.6566838,0.007288088,0.041560903,0.008114156,0.27949798],"study_design_scores_gemma":[0.00008876908,0.00018250068,0.0002945492,0.000020747864,0.00002337397,0.000094391246,0.000031776504,0.9728592,0.0037681283,0.021383839,0.0012270033,0.000025681395],"about_ca_topic_score_codex":0.002144955,"about_ca_topic_score_gemma":0.0028427108,"teacher_disagreement_score":0.0051860805,"about_ca_system_score_codex":0.0017726263,"about_ca_system_score_gemma":0.0029361811,"threshold_uncertainty_score":0.027426958},"labels":[],"label_agreement":null},{"id":"W2913530954","doi":"","title":"New Algorithms for Multiplayer Bandits when Arm Means Vary Among Players","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Constant (computer programming); Combinatorics; Mathematics; Zero (linguistics); Computer science; Algorithm; Kappa; Statistics; Geometry; Programming language","score_opus":0.1970939867519552,"score_gpt":0.2941718692337994,"score_spread":0.09707788248184421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913530954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016235834,0.00074484496,0.97281975,0.00089141034,0.00015184571,0.00021727468,0.00016124139,0.000620478,0.008157434],"genre_scores_gemma":[0.36518484,0.0009182827,0.61410975,0.0012019606,0.0005465868,0.001290607,0.0006991402,0.00049846095,0.015550294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996779,0.0013771976,0.00015297305,0.0006372444,0.00055188884,0.0005017071],"domain_scores_gemma":[0.9924126,0.005127307,0.0008841919,0.0006999875,0.00045696183,0.00041889888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004367592,0.0026688501,0.0023939882,0.0011004704,0.0015361813,0.0030099284,0.0046513597,0.0036039657,0.0063888687],"category_scores_gemma":[0.017055761,0.0011140932,0.0014242656,0.0017474056,0.0021444927,0.0044443184,0.004153038,0.004932995,0.0021329243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090509426,0.0005298912,0.0017435055,0.00036343807,0.00021532325,0.0001568549,0.0004303162,0.69225365,0.0026759412,0.16578102,0.010772249,0.12417272],"study_design_scores_gemma":[0.00008800273,0.00009081079,0.00010169754,0.000039590017,0.000027721357,0.000054488577,0.000035234054,0.92019194,0.00054066995,0.076653555,0.0021587852,0.000017463495],"about_ca_topic_score_codex":0.0019097069,"about_ca_topic_score_gemma":0.0029844276,"teacher_disagreement_score":0.0063888687,"about_ca_system_score_codex":0.00237872,"about_ca_system_score_gemma":0.002255512,"threshold_uncertainty_score":0.02309829},"labels":[],"label_agreement":null},{"id":"W2914526782","doi":"10.48550/arxiv.1602.04282","title":"Conservative Bandits","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Mathematical optimization; Constraint (computer-aided design); Complement (music); Computer science; Revenue; Baseline (sea); Adversarial system; Upper and lower bounds; Mathematical economics; Mathematics; Economics; Artificial intelligence; Machine learning; Finance","score_opus":0.33433048380332875,"score_gpt":0.30347587737871823,"score_spread":0.03085460642461052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914526782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08008899,0.001155301,0.89462644,0.0018856705,0.00020394938,0.00016855834,0.00044632575,0.0003855705,0.021039203],"genre_scores_gemma":[0.8962048,0.00086900254,0.08592413,0.00068498676,0.00025847903,0.00042354688,0.000440066,0.00013954379,0.015055418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771726,0.0010701399,0.00009505911,0.00045616672,0.00035505876,0.000306361],"domain_scores_gemma":[0.9908337,0.0069974153,0.0009568077,0.0005802568,0.0003029745,0.00032882867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003059483,0.001363121,0.0021803074,0.000787251,0.0009808943,0.0027354625,0.0022524034,0.0030442276,0.006186027],"category_scores_gemma":[0.015859585,0.000701408,0.000980634,0.0012707489,0.0023867732,0.0034141352,0.0019811275,0.0029764161,0.001015242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035293968,0.00014816814,0.0012134536,0.00019997255,0.0000956994,0.00025919234,0.00016598872,0.71979624,0.0013619164,0.2501385,0.0047005564,0.02156737],"study_design_scores_gemma":[0.000049966726,0.000066430985,0.00012559032,0.00003186971,0.000016222933,0.000052766067,0.000025113155,0.89049006,0.00027616453,0.10732486,0.001528008,0.000012974411],"about_ca_topic_score_codex":0.0016245246,"about_ca_topic_score_gemma":0.0015283528,"teacher_disagreement_score":0.006186027,"about_ca_system_score_codex":0.0015719406,"about_ca_system_score_gemma":0.0010247964,"threshold_uncertainty_score":0.020694375},"labels":[],"label_agreement":null},{"id":"W2916603395","doi":"10.24963/ijcai.2019/386","title":"Perturbed-History Exploration in Stochastic Multi-Armed Bandits","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Bernoulli's principle; Offset (computer science); Argument (complex analysis); Computer science; Optimism; Mathematical optimization; Mathematics; Psychology; Machine learning; Engineering; Social psychology","score_opus":0.40352070611907126,"score_gpt":0.4707663724538747,"score_spread":0.06724566633480344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916603395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04889896,0.0013556494,0.9442977,0.00078728725,0.000079003745,0.0000942383,0.0001251492,0.0007590289,0.0036029844],"genre_scores_gemma":[0.86867285,0.0006460401,0.1261109,0.000461267,0.00013577206,0.00031539827,0.00021240904,0.00018472133,0.003260581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973604,0.0014033407,0.000104514875,0.0004045018,0.0004271201,0.0003001734],"domain_scores_gemma":[0.9888837,0.008665145,0.0009491665,0.00072612416,0.00040327347,0.000372604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039298036,0.0014880027,0.0021778399,0.0006902632,0.00069682044,0.0017652081,0.002416021,0.0020058737,0.0024507758],"category_scores_gemma":[0.016473908,0.0009024656,0.000848662,0.0010517191,0.0021752135,0.0027602147,0.0023829637,0.0024426198,0.00064813474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028450333,0.0000716036,0.000775057,0.00009114405,0.000057184963,0.000056584857,0.000067647554,0.9456394,0.00070341857,0.03062453,0.00091603544,0.020712968],"study_design_scores_gemma":[0.000024924051,0.000041148385,0.00006367992,0.000014439911,0.000007660645,0.000012644839,0.0000054258016,0.97841716,0.00025963906,0.020900754,0.00024622184,0.0000063654506],"about_ca_topic_score_codex":0.0020108568,"about_ca_topic_score_gemma":0.0019627,"teacher_disagreement_score":0.0039298036,"about_ca_system_score_codex":0.0015593398,"about_ca_system_score_gemma":0.0016836022,"threshold_uncertainty_score":0.020783067},"labels":[],"label_agreement":null},{"id":"W2920229473","doi":"10.48550/arxiv.1903.01026","title":"Learning Modular Safe Policies in the Bandit Setting with Application to Adaptive Clinical Trials","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Robustness (evolution); Outlier; Computer science; Modular design; Mathematical optimization; Measure (data warehouse); Estimator; Flexibility (engineering); Suite; Artificial intelligence; Machine learning; Mathematics; Data mining; Statistics","score_opus":0.4112833942530587,"score_gpt":0.4118405645397245,"score_spread":0.0005571702866657979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920229473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026053848,0.0017976718,0.966226,0.0019945472,0.00007863305,0.00019219946,0.00013247978,0.00050349516,0.003021122],"genre_scores_gemma":[0.72076845,0.0017779919,0.27110788,0.0010028713,0.00026850143,0.0007788921,0.0002815919,0.00022508581,0.0037887671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98897564,0.008506846,0.0003522852,0.000858586,0.0008979516,0.00040868428],"domain_scores_gemma":[0.9326628,0.058356855,0.0037766264,0.0024160405,0.0017188081,0.0010689604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024138423,0.0019471315,0.0032231442,0.0014413162,0.0009103952,0.0029540872,0.0020627994,0.0033737016,0.003276464],"category_scores_gemma":[0.07702498,0.0009075531,0.0011239429,0.0016598594,0.0032666293,0.0029928316,0.0026596945,0.00498336,0.00073258084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042060425,0.00012232788,0.0013578831,0.00012722175,0.000101533864,0.000096284195,0.00011511945,0.8962257,0.0002547143,0.0663416,0.0013380855,0.033498924],"study_design_scores_gemma":[0.000085864034,0.000064963766,0.00016009556,0.000033183314,0.000016812604,0.000020205027,0.000012198265,0.9293809,0.00020742143,0.06945714,0.00054991624,0.000011252109],"about_ca_topic_score_codex":0.0028819977,"about_ca_topic_score_gemma":0.001837653,"teacher_disagreement_score":0.024138423,"about_ca_system_score_codex":0.002685665,"about_ca_system_score_gemma":0.0026845478,"threshold_uncertainty_score":0.12765771},"labels":[],"label_agreement":null},{"id":"W2922444559","doi":"10.24963/ijcai.2019/66","title":"Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descent","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Fictitious play; Convergence (economics); Nash equilibrium; Computer science; Counterfactual thinking; Benchmark (surveying); Mathematical optimization; Perfect information; Regret; Descent (aeronautics); Class (philosophy); Zero (linguistics); Imperfect; Mathematical economics; Mathematics; Economics; Artificial intelligence","score_opus":0.15620157088492598,"score_gpt":0.44148653121042214,"score_spread":0.28528496032549616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922444559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03652526,0.00016399774,0.9602805,0.00021535663,0.000019797388,0.000056181383,0.000038266437,0.00034069023,0.0023599127],"genre_scores_gemma":[0.8417458,0.00014557257,0.1552438,0.00017918834,0.00003285521,0.00019419128,0.00013325318,0.000115390765,0.0022099644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988029,0.0005927626,0.00004591774,0.00013982563,0.0002708226,0.00014771176],"domain_scores_gemma":[0.99581194,0.0031959193,0.00035200437,0.00026313248,0.00024413112,0.0001328564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002865974,0.0012575861,0.0015906404,0.000827227,0.000605612,0.0014423198,0.0014235338,0.0012710092,0.0017595039],"category_scores_gemma":[0.010681794,0.0007104154,0.0005600194,0.0006105402,0.0018326429,0.001946306,0.0017639785,0.001376842,0.0003656653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006745477,0.000031412757,0.0005070712,0.000024116232,0.000031522442,0.000029313072,0.000036615354,0.96985114,0.0002742485,0.018104753,0.00032625077,0.010716103],"study_design_scores_gemma":[0.000005406394,0.000010448074,0.000025256833,0.0000034049706,0.0000017671983,0.0000042034226,0.0000036521324,0.9923624,0.000107437554,0.00740216,0.00007229393,0.0000015423747],"about_ca_topic_score_codex":0.0041767983,"about_ca_topic_score_gemma":0.00422119,"teacher_disagreement_score":0.0041767983,"about_ca_system_score_codex":0.0016218278,"about_ca_system_score_gemma":0.001681871,"threshold_uncertainty_score":0.015156865},"labels":[],"label_agreement":null},{"id":"W2945633694","doi":"","title":"Fiduciary Bandits","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fiduciary; Ask price; Incentive; Action (physics); Computer science; Recommender system; Constraint (computer-aided design); Ex-ante; Face (sociological concept); Operations research; Mathematical economics; Economics; Microeconomics; Finance; Mathematics; Law; Machine learning; Political science","score_opus":0.3111492193743946,"score_gpt":0.31343074353404116,"score_spread":0.002281524159646553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945633694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053318284,0.0009466667,0.9246453,0.0020464645,0.00013362835,0.0001645112,0.0003408493,0.000623161,0.017781187],"genre_scores_gemma":[0.8314564,0.0008930144,0.15101346,0.0006548432,0.00023129137,0.0005118144,0.00035011058,0.00017388201,0.014715114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99543756,0.0022130844,0.0002484139,0.00092904636,0.0006562995,0.0005155534],"domain_scores_gemma":[0.9857364,0.0098423185,0.0012897595,0.0018300147,0.0008811271,0.0004203821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050863577,0.0015760221,0.0028757805,0.0009304198,0.0013389789,0.0033160914,0.002543907,0.00387751,0.004792544],"category_scores_gemma":[0.030179257,0.0008352686,0.0010614536,0.0012693784,0.003145577,0.0040457556,0.0024437949,0.0036447349,0.0016684931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046109306,0.00014564251,0.0016696102,0.0003078432,0.00015046603,0.00017345841,0.00028172645,0.4332982,0.0019362582,0.50264025,0.0075631626,0.051372323],"study_design_scores_gemma":[0.00006907506,0.000051724568,0.00021292978,0.000051819017,0.000023580611,0.00007368712,0.000032893913,0.77235615,0.0006088591,0.224636,0.0018582635,0.000024934798],"about_ca_topic_score_codex":0.0025891662,"about_ca_topic_score_gemma":0.0022524183,"teacher_disagreement_score":0.0050863577,"about_ca_system_score_codex":0.0022570041,"about_ca_system_score_gemma":0.0017973192,"threshold_uncertainty_score":0.026899576},"labels":[],"label_agreement":null},{"id":"W2948647439","doi":"10.48550/arxiv.1902.01239","title":"A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Sublinear function; Computer science; Minimax; Matching (statistics); Mathematical optimization; Collision; Algorithm; Mathematics; Machine learning; Discrete mathematics; Computer security; Statistics","score_opus":0.2895327430734515,"score_gpt":0.3426463910670395,"score_spread":0.053113647993587976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948647439","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013882185,0.00014532167,0.9790644,0.00063187245,0.00006754772,0.00019665301,0.00010311819,0.00062821957,0.005280749],"genre_scores_gemma":[0.34451497,0.0002070167,0.64479184,0.00057212746,0.00015439349,0.0009484506,0.0004694569,0.0002765459,0.008065202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788576,0.0007147366,0.00010345953,0.00052654627,0.0003697773,0.00039968485],"domain_scores_gemma":[0.9962303,0.0025090333,0.0003314518,0.00045806178,0.0002298875,0.00024122717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026916645,0.0016334085,0.0016558045,0.00063695683,0.0013128882,0.0022036205,0.0033117803,0.0029702869,0.008713189],"category_scores_gemma":[0.009900199,0.00074033625,0.00093475945,0.0012276102,0.0015619098,0.0030676487,0.0034446076,0.0031776284,0.0022196781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008726533,0.00040400616,0.0012328192,0.0002691269,0.000114799266,0.00016794624,0.0003913078,0.6587794,0.0035533563,0.14469829,0.01159989,0.17791644],"study_design_scores_gemma":[0.00012764092,0.00009822539,0.00008806959,0.000026314507,0.00001627839,0.000067912326,0.000045617577,0.932644,0.0007471824,0.06409199,0.0020329973,0.000013689215],"about_ca_topic_score_codex":0.002252352,"about_ca_topic_score_gemma":0.0026743019,"teacher_disagreement_score":0.008713189,"about_ca_system_score_codex":0.0019068924,"about_ca_system_score_gemma":0.003148446,"threshold_uncertainty_score":0.029148519},"labels":[],"label_agreement":null},{"id":"W2950236408","doi":"","title":"Prediction by Random-Walk Perturbation","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Random walk; Perturbation (astronomy); Order (exchange); Mathematics; Combinatorics; Time horizon; Computer science; Mathematical optimization; Discrete mathematics; Statistics; Physics; Economics","score_opus":0.2137636876773428,"score_gpt":0.27774421428219465,"score_spread":0.06398052660485185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950236408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04174255,0.00031252034,0.9537617,0.0007780348,0.00014467457,0.00008668318,0.00013788366,0.00046480785,0.002571183],"genre_scores_gemma":[0.90303946,0.00020474072,0.09186166,0.00041079705,0.00017049788,0.00013938823,0.0002458956,0.000095620206,0.0038319118],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981199,0.00077348994,0.00005595581,0.0004920947,0.00034508493,0.00021350519],"domain_scores_gemma":[0.9946122,0.0032908863,0.0006347618,0.0007275932,0.0004352153,0.00029930772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021925576,0.0011397402,0.0017282113,0.0004358528,0.0006571687,0.0011316135,0.0024911868,0.0017430866,0.0021580912],"category_scores_gemma":[0.011848391,0.0005658503,0.00062869024,0.00071678445,0.0014419182,0.0028367592,0.0015100893,0.0023656378,0.00071997405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003802292,0.000093089024,0.0007756391,0.000039019218,0.000053887714,0.00011470191,0.000054183354,0.9521719,0.0015362782,0.023564124,0.0027359382,0.018481018],"study_design_scores_gemma":[0.000014935845,0.000021695265,0.000038630984,0.0000020060086,0.0000035478581,0.000013814412,0.0000035442058,0.9892335,0.00035368992,0.010144966,0.00016478176,0.0000050038975],"about_ca_topic_score_codex":0.002316455,"about_ca_topic_score_gemma":0.0018873304,"teacher_disagreement_score":0.0024911868,"about_ca_system_score_codex":0.0012341846,"about_ca_system_score_gemma":0.0011458548,"threshold_uncertainty_score":0.011595488},"labels":[],"label_agreement":null},{"id":"W2951017703","doi":"","title":"On Local Regret","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Locality; Disjunct; Computer science; Generalization; Online learning; Artificial intelligence; Jump; Set (abstract data type); Machine learning; Statistical learning; Graph; Theoretical computer science; Mathematics; Psychology; Cognitive psychology; World Wide Web","score_opus":0.27637977516590406,"score_gpt":0.5120107174168465,"score_spread":0.2356309422509424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951017703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011937605,0.0023281053,0.96497023,0.0025888444,0.00024550245,0.00012824389,0.00033742574,0.00050369935,0.016960418],"genre_scores_gemma":[0.621968,0.004242755,0.3494575,0.004131825,0.0017570241,0.001193164,0.00089903234,0.001111902,0.0152388355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927141,0.0040337704,0.00021987196,0.0011012087,0.0012814633,0.00064954866],"domain_scores_gemma":[0.9705429,0.024246927,0.0009581892,0.00227212,0.0014533012,0.00052659336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009401655,0.002471479,0.0027967428,0.0013293175,0.0014483939,0.003147949,0.003044526,0.0028551477,0.0074075707],"category_scores_gemma":[0.0390615,0.00064738776,0.0014785926,0.0021729409,0.0037775699,0.005173483,0.003918384,0.0062941895,0.0015859567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045359813,0.00020021133,0.0018509389,0.00046244974,0.00020921703,0.00014222633,0.00016144905,0.45844048,0.0011240481,0.44822383,0.019783158,0.06894844],"study_design_scores_gemma":[0.00006295545,0.00012539602,0.00038036794,0.00008352642,0.00004486386,0.00008277373,0.000032990745,0.6949739,0.0006666326,0.30042788,0.0030963903,0.000022328551],"about_ca_topic_score_codex":0.0020957324,"about_ca_topic_score_gemma":0.0017593162,"teacher_disagreement_score":0.009401655,"about_ca_system_score_codex":0.0038850058,"about_ca_system_score_gemma":0.0023212172,"threshold_uncertainty_score":0.04972124},"labels":[],"label_agreement":null},{"id":"W2951277631","doi":"","title":"An Adaptive Algorithm for Finite Stochastic Partial Monitoring","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Logarithm; Minimax; Space (punctuation); Mathematical optimization; Computer science; Algorithm; Mathematics; Machine learning","score_opus":0.3480788863386984,"score_gpt":0.3467574326496035,"score_spread":0.0013214536890948647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951277631","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017142061,0.00011613918,0.97815245,0.000411513,0.00006263906,0.000090337555,0.00008621345,0.0008643264,0.0030743696],"genre_scores_gemma":[0.46692163,0.000120014345,0.5263615,0.00039180246,0.00010044189,0.0003464067,0.00030244372,0.0002140197,0.005241694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982994,0.00043971773,0.00009833226,0.0005422741,0.00039059133,0.00022975284],"domain_scores_gemma":[0.9972959,0.0013332291,0.00031331944,0.00063161727,0.00022194783,0.00020403316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016489468,0.0008368742,0.0011562251,0.00051872927,0.0006068526,0.0015608231,0.0031245616,0.0016688687,0.0041075354],"category_scores_gemma":[0.007855116,0.00036779427,0.0007997497,0.00078281556,0.0012037387,0.0029383851,0.0022497023,0.0022845708,0.0008941171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076415023,0.00037248083,0.0028268532,0.00022516542,0.00013792935,0.00019009488,0.0003391331,0.44742575,0.009705434,0.24366178,0.010157426,0.28419375],"study_design_scores_gemma":[0.00006761963,0.000050912273,0.00013134598,0.000010087635,0.000015538388,0.00006263039,0.0000131697625,0.9419195,0.0015213919,0.05480787,0.0013856142,0.00001424306],"about_ca_topic_score_codex":0.0014735339,"about_ca_topic_score_gemma":0.0021168212,"teacher_disagreement_score":0.0041075354,"about_ca_system_score_codex":0.0014826123,"about_ca_system_score_gemma":0.0018509463,"threshold_uncertainty_score":0.013741076},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.35771277002683183,"score_gpt":0.3531140666372869,"score_spread":0.004598703389544934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951455820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05917595,0.0013713985,0.9333305,0.0012662176,0.00009339803,0.00011892093,0.00049608876,0.0011345242,0.0030130958],"genre_scores_gemma":[0.8144631,0.0016580703,0.17051794,0.0007524757,0.0005484193,0.00041036395,0.0014801292,0.0003064914,0.0098630935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953739,0.0022757065,0.000215464,0.00084028125,0.0007459357,0.0005487474],"domain_scores_gemma":[0.97348344,0.021525491,0.0017967696,0.0015993285,0.0010237215,0.0005712477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008085603,0.0016910648,0.0035826953,0.0014550796,0.0010392002,0.002510096,0.0029554148,0.0026295797,0.0049087727],"category_scores_gemma":[0.030156594,0.0010085428,0.0012216589,0.002266727,0.0024425464,0.005657933,0.0019532728,0.0031288883,0.0015046994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053679367,0.00032557562,0.0028546103,0.00034506858,0.000095599906,0.00020379151,0.00012227484,0.78800964,0.0008856006,0.1310596,0.009214957,0.06634647],"study_design_scores_gemma":[0.000028620754,0.000048774255,0.0001809253,0.000009236844,0.000009653384,0.000037017347,0.000012588923,0.95718765,0.00024739135,0.04187647,0.00034967784,0.00001200444],"about_ca_topic_score_codex":0.0062516215,"about_ca_topic_score_gemma":0.0075044874,"teacher_disagreement_score":0.008085603,"about_ca_system_score_codex":0.0021063325,"about_ca_system_score_gemma":0.0020198154,"threshold_uncertainty_score":0.042761266},"labels":[],"label_agreement":null},{"id":"W2952123902","doi":"10.48550/arxiv.1801.01301","title":"Sequential Decision Making with Limited Observation Capability: Application to Wireless Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lagrangian relaxation; Interval (graph theory); Index (typography); Mathematical optimization; State (computer science); Computation; Computer science; State space; Relaxation (psychology); Markov decision process; Decision maker; Function (biology); Bellman equation; Mathematics; Space (punctuation); Operations research; Algorithm; Markov process; Statistics","score_opus":0.1943918856240933,"score_gpt":0.31734796998432135,"score_spread":0.12295608436022806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952123902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04589368,0.0009292671,0.9479917,0.0005686114,0.000071097566,0.000054141077,0.00008325087,0.00013844024,0.0042697047],"genre_scores_gemma":[0.9390818,0.0010804615,0.055891175,0.00011950639,0.0001347919,0.00012644957,0.00008380314,0.000038553506,0.0034435012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986386,0.0006786487,0.00005614572,0.0002288469,0.00023030218,0.00016738597],"domain_scores_gemma":[0.9910137,0.0074791536,0.000702221,0.00028428386,0.00030143792,0.0002191776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002914561,0.0011469699,0.0014020951,0.00051344186,0.0005595685,0.0013954798,0.0011802989,0.0011194998,0.002045576],"category_scores_gemma":[0.009299178,0.00048882625,0.0006566966,0.0011401067,0.0016401026,0.0018911003,0.001268025,0.002023006,0.00018114464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011465598,0.000050554467,0.0004805602,0.00007378198,0.00003775019,0.000091956004,0.00005868203,0.9392256,0.00057491584,0.047071848,0.00036877324,0.0118509205],"study_design_scores_gemma":[0.000008813869,0.000024660123,0.000056959638,0.0000048389743,0.0000048327574,0.000009253052,0.0000068888994,0.9814404,0.00011561237,0.01815956,0.00016437285,0.0000038629037],"about_ca_topic_score_codex":0.0045460123,"about_ca_topic_score_gemma":0.0024982924,"teacher_disagreement_score":0.0045460123,"about_ca_system_score_codex":0.0015949446,"about_ca_system_score_gemma":0.0012339666,"threshold_uncertainty_score":0.01541388},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.1870917374975287,"score_gpt":0.38669317927830393,"score_spread":0.19960144178077524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952908320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04335701,0.008060028,0.9288399,0.0034408642,0.0002705702,0.00011209909,0.00037279553,0.0006469121,0.014899739],"genre_scores_gemma":[0.8417225,0.007828468,0.13193007,0.002108127,0.0012402878,0.0008620789,0.00091113616,0.0007060308,0.012691248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99480444,0.0022544113,0.00017222641,0.0007359271,0.0012101873,0.0008228288],"domain_scores_gemma":[0.94002837,0.051097106,0.0028290383,0.002917286,0.0021680403,0.00096021465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01506853,0.0027222626,0.0029128361,0.002005511,0.0018222235,0.0037114804,0.0032343855,0.0027920618,0.0045696953],"category_scores_gemma":[0.07016343,0.0012767056,0.0016983448,0.0025605725,0.0049712826,0.007310618,0.0044951094,0.006228617,0.0009444454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006230156,0.00015793946,0.0020549875,0.00034675104,0.00019912329,0.00019490537,0.00020948976,0.6880626,0.0013038262,0.2795323,0.004852164,0.022462945],"study_design_scores_gemma":[0.00004140024,0.000054476444,0.00040018887,0.000080168786,0.000037658658,0.00005519008,0.000024676763,0.88383126,0.0004846019,0.11413522,0.0008333934,0.00002168786],"about_ca_topic_score_codex":0.0032242124,"about_ca_topic_score_gemma":0.002464138,"teacher_disagreement_score":0.01506853,"about_ca_system_score_codex":0.004814098,"about_ca_system_score_gemma":0.0023550796,"threshold_uncertainty_score":0.07969093},"labels":[],"label_agreement":null},{"id":"W2952938032","doi":"10.48550/arxiv.1110.6755","title":"PAC-Bayes-Bernstein Inequality for Martingales and its Application to\\n Multiarmed Bandits","year":2011,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bayes' theorem; Computer science; Inequality; Mathematical optimization; Interdependence; Artificial intelligence; Mathematics; Bayesian probability","score_opus":0.27802706403055605,"score_gpt":0.3265386299181593,"score_spread":0.04851156588760325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952938032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043994808,0.0010528939,0.98948133,0.0010904262,0.00008786673,0.000039063387,0.00013030172,0.000089954796,0.003628726],"genre_scores_gemma":[0.45324332,0.0062303944,0.51467204,0.0019989228,0.00096818147,0.00096789014,0.0007811063,0.0004164974,0.020721687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963922,0.0017979591,0.00014058565,0.0004985896,0.0008737877,0.00029685584],"domain_scores_gemma":[0.97090256,0.02432016,0.001146759,0.0011070081,0.0018102872,0.0007131477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011484657,0.0018257665,0.0021582546,0.0019752006,0.00086626736,0.0027682593,0.0030275355,0.0028280255,0.006348702],"category_scores_gemma":[0.04447289,0.001137157,0.0018288872,0.0016677864,0.0044077984,0.005789453,0.004293332,0.0070319534,0.0007928915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007723526,0.000044684828,0.00082797953,0.0002453654,0.00007580239,0.00012121056,0.00013160508,0.14531536,0.0012371356,0.82955927,0.0026733296,0.019691007],"study_design_scores_gemma":[0.00001593146,0.00003149079,0.0001769467,0.000053898268,0.000014216107,0.000040231458,0.000016264159,0.7159092,0.00044295102,0.28160554,0.0016718503,0.000021508487],"about_ca_topic_score_codex":0.003907948,"about_ca_topic_score_gemma":0.0033983819,"teacher_disagreement_score":0.011484657,"about_ca_system_score_codex":0.0032167854,"about_ca_system_score_gemma":0.0026033523,"threshold_uncertainty_score":0.06073737},"labels":[],"label_agreement":null},{"id":"W2954365962","doi":"10.48550/arxiv.1806.05819","title":"BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Learning to rank; Computer science; Ranking (information retrieval); Regret; Rank (graph theory); Online learning; Relevance (law); Quality (philosophy); Base (topology); Information retrieval; Machine learning; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.21393704804264105,"score_gpt":0.332489253193239,"score_spread":0.11855220515059797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954365962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0441747,0.0013835388,0.945343,0.0009343983,0.00018034864,0.00024514084,0.00035637897,0.0037968506,0.0035856506],"genre_scores_gemma":[0.6977338,0.0007442248,0.2876677,0.0009777972,0.0004448674,0.000558854,0.0012011053,0.00068002584,0.009991672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964837,0.0015800466,0.00016517084,0.000612984,0.000755342,0.00040279338],"domain_scores_gemma":[0.97847486,0.014623839,0.0014501452,0.0030062452,0.0016627106,0.0007821324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004831026,0.0023877532,0.00323998,0.001199822,0.0011166305,0.0019860296,0.0037844507,0.0028967576,0.005001928],"category_scores_gemma":[0.02553901,0.00090393156,0.0006702413,0.0017118296,0.0020938036,0.005418203,0.0021146315,0.0030534605,0.002901317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013274282,0.0008999298,0.0053584296,0.00055112713,0.0001888834,0.00022599581,0.00033908378,0.50711995,0.0038493904,0.03186651,0.021055322,0.42721787],"study_design_scores_gemma":[0.00009783847,0.00029296745,0.0002483529,0.00003138581,0.00002456116,0.00009410676,0.000034187415,0.9710924,0.0014520468,0.024916682,0.001691048,0.00002441201],"about_ca_topic_score_codex":0.0033341392,"about_ca_topic_score_gemma":0.0046998262,"teacher_disagreement_score":0.005001928,"about_ca_system_score_codex":0.0011027135,"about_ca_system_score_gemma":0.0025144205,"threshold_uncertainty_score":0.025549233},"labels":[],"label_agreement":null},{"id":"W2957302152","doi":"10.48550/arxiv.1907.05772","title":"Exploration by Optimisation in Partial Monitoring","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Observable; Bounded function; Minimax; Upper and lower bounds; Simple (philosophy); Matching (statistics); Action (physics); Degenerate energy levels; Mathematics; Outcome (game theory); Combinatorics; Mathematical optimization; Computer science; Discrete mathematics; Mathematical economics; Statistics; Physics; Mathematical analysis","score_opus":0.36010931496061505,"score_gpt":0.3313054139223404,"score_spread":0.028803901038274626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957302152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030240053,0.0002756215,0.9612475,0.0005682653,0.00002985443,0.000087224755,0.00014830881,0.0007659914,0.0066371877],"genre_scores_gemma":[0.77280414,0.00019926135,0.21960504,0.00026010102,0.00003857865,0.00033915674,0.00026262845,0.0002183136,0.006272842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984358,0.0006816162,0.000054677832,0.00035565178,0.00023837015,0.00023390549],"domain_scores_gemma":[0.99755704,0.0016459682,0.00020258914,0.00035425468,0.00008358788,0.00015643446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018318405,0.0011715312,0.001571906,0.000476547,0.00065001065,0.0013003642,0.0016810457,0.0013852128,0.0036250302],"category_scores_gemma":[0.007197698,0.0006077503,0.0010143995,0.00072562404,0.0020697264,0.002668596,0.004299229,0.0020335596,0.0007892453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006008727,0.0000845823,0.0010290967,0.00020765368,0.000084013285,0.00017712505,0.00027436257,0.741108,0.0031387666,0.17413397,0.0037991556,0.0753625],"study_design_scores_gemma":[0.00003816247,0.00004615704,0.00011305817,0.000016861026,0.000010034742,0.000029534733,0.000014025124,0.8829544,0.0007581451,0.11518872,0.0008204581,0.000010388678],"about_ca_topic_score_codex":0.0015000949,"about_ca_topic_score_gemma":0.0015112414,"teacher_disagreement_score":0.0036250302,"about_ca_system_score_codex":0.0013082606,"about_ca_system_score_gemma":0.0013501638,"threshold_uncertainty_score":0.012126923},"labels":[],"label_agreement":null},{"id":"W2962856402","doi":"10.1093/ej/uez043","title":"Learning While Experimenting","year":2019,"lang":"en","type":"article","venue":"The Economic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Pessimism; State (computer science); Computer science; Epistemology","score_opus":0.09921364006409483,"score_gpt":0.4137674019392119,"score_spread":0.3145537618751171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962856402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51843834,0.000435482,0.4250239,0.00483814,0.0001648854,0.00047079512,0.00034306943,0.00096585596,0.04931949],"genre_scores_gemma":[0.9548755,0.00014167011,0.039286923,0.00039435836,0.00004864888,0.00021738074,0.00016371465,0.00003793146,0.0048338654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980343,0.0009776907,0.00010043827,0.00043270303,0.00022804587,0.00022684356],"domain_scores_gemma":[0.9827137,0.012655706,0.0012104441,0.0018904094,0.00064127916,0.00088850013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036448906,0.0007461118,0.0008164825,0.00031219915,0.0005456172,0.0013976477,0.0010822372,0.0013646628,0.009324278],"category_scores_gemma":[0.02085857,0.00031843552,0.00045309152,0.0003227013,0.0018028067,0.0024565414,0.0012925122,0.0017844433,0.001261503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003013148,0.0018339069,0.026526889,0.00049035205,0.00028742666,0.00088374503,0.0011861892,0.47889903,0.019551743,0.22474943,0.0063039986,0.2362742],"study_design_scores_gemma":[0.00028365725,0.0011147007,0.0033533443,0.00009665444,0.00008945318,0.00017873572,0.0002560204,0.6985929,0.006943323,0.28215778,0.006865972,0.000067446985],"about_ca_topic_score_codex":0.0011541162,"about_ca_topic_score_gemma":0.0013412763,"teacher_disagreement_score":0.009324278,"about_ca_system_score_codex":0.0009426955,"about_ca_system_score_gemma":0.0009164381,"threshold_uncertainty_score":0.03119284},"labels":[],"label_agreement":null},{"id":"W2962980921","doi":"","title":"TopRank: A practical algorithm for online stochastic ranking","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Generality; Generalization; Learning to rank; Regret; Online algorithm; sort; Ranking (information retrieval); Rank (graph theory); Machine learning; Algorithm; Artificial intelligence; Sorting algorithm; Theoretical computer science; Sorting; Mathematics; Information retrieval","score_opus":0.18174090392477427,"score_gpt":0.48522840909620396,"score_spread":0.3034875051714297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962980921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023670637,0.00028839774,0.99250084,0.00036624772,0.00014640117,0.00017048798,0.00023500432,0.0017878187,0.002137786],"genre_scores_gemma":[0.13229401,0.00062312593,0.85704315,0.0004122419,0.0004094682,0.0007497541,0.0012283213,0.00047276547,0.0067671333],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966313,0.0012184754,0.00021494142,0.00044561987,0.0012020692,0.00028761188],"domain_scores_gemma":[0.9956579,0.002314966,0.0003029372,0.00072717166,0.0007873286,0.00020971804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041111084,0.001757566,0.0024380728,0.0019414814,0.0015484832,0.0026073174,0.0030565478,0.002342401,0.010855046],"category_scores_gemma":[0.013539281,0.0007464531,0.0009868866,0.0032353771,0.0014144267,0.0043006293,0.0025701015,0.0026418865,0.005262392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032794586,0.00026487472,0.0007899535,0.00034938366,0.000100710226,0.00010027513,0.000108377986,0.31090117,0.0012503124,0.13821697,0.046117026,0.50147307],"study_design_scores_gemma":[0.0001546486,0.00012220371,0.00010391254,0.000026691423,0.000015521915,0.00010511075,0.000028191202,0.8495667,0.00081354973,0.14098626,0.008050645,0.00002643602],"about_ca_topic_score_codex":0.0036597871,"about_ca_topic_score_gemma":0.0056576356,"teacher_disagreement_score":0.010855046,"about_ca_system_score_codex":0.0017003266,"about_ca_system_score_gemma":0.004515283,"threshold_uncertainty_score":0.036313772},"labels":[],"label_agreement":null},{"id":"W2963004721","doi":"10.1145/3178876.3186075","title":"Online Compact Convexified Factorization Machine","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Machine learning; Regret; Artificial intelligence; Online machine learning; Feature (linguistics); Online learning; Projection (relational algebra); Convex optimization; Algorithm; Active learning (machine learning); Regular polygon; Mathematics","score_opus":0.24648509767850507,"score_gpt":0.5073324829073448,"score_spread":0.2608473852288397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963004721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00791404,0.00035897325,0.9891699,0.00023714444,0.000053907566,0.000055092034,0.00011617602,0.0009762671,0.0011184603],"genre_scores_gemma":[0.4307177,0.000694038,0.56093085,0.0005241912,0.00024964623,0.0003670715,0.0014956305,0.00026416295,0.004756768],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861646,0.0004010948,0.00008659249,0.00039018533,0.00035277885,0.00015292189],"domain_scores_gemma":[0.9971409,0.0014844867,0.00027509313,0.00052966,0.00045549186,0.00011446708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017176707,0.001503331,0.0020564497,0.0005627281,0.00051548355,0.0013014581,0.0015078203,0.0016077728,0.0032671061],"category_scores_gemma":[0.008148156,0.0004333571,0.0006271916,0.00081736984,0.001269188,0.0024257125,0.0012866717,0.0022775268,0.0013006576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033008464,0.00014294717,0.00095559447,0.0002249132,0.000054054894,0.00017771579,0.00013227364,0.5400029,0.0045758495,0.037156045,0.0131618325,0.40308583],"study_design_scores_gemma":[0.000013019208,0.00002738421,0.000070956856,0.000009111724,0.0000035579808,0.00003235572,0.0000082455845,0.9892406,0.00082802254,0.008966461,0.0007943272,0.000006020712],"about_ca_topic_score_codex":0.0031159103,"about_ca_topic_score_gemma":0.002970229,"teacher_disagreement_score":0.0032671061,"about_ca_system_score_codex":0.00093281997,"about_ca_system_score_gemma":0.0015762316,"threshold_uncertainty_score":0.0109295845},"labels":[],"label_agreement":null},{"id":"W2963004847","doi":"","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Thompson sampling; Asymptotically optimal algorithm; Index (typography); Frequentist inference; Gaussian; Mathematical optimization; Computer science; Mathematics; Mathematical economics; Bayesian probability; Statistics; Artificial intelligence; Bayesian inference","score_opus":0.2738514103519363,"score_gpt":0.45927265146056295,"score_spread":0.18542124110862668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963004847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06562682,0.0009926417,0.917113,0.0015424774,0.00013263006,0.00010347392,0.00019169477,0.0006233411,0.013673976],"genre_scores_gemma":[0.8792983,0.0008725304,0.11132558,0.00052211067,0.00023066906,0.00025877552,0.00028752437,0.00029141232,0.0069130277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99727947,0.0012354463,0.000089704685,0.00039386062,0.0006071026,0.00039430294],"domain_scores_gemma":[0.9700551,0.024801282,0.0018698182,0.0015209519,0.0008404811,0.00091238745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062626577,0.0017529224,0.0019563492,0.0008353637,0.0009905315,0.0031389107,0.0028481255,0.0023320774,0.0050861477],"category_scores_gemma":[0.03448705,0.00082515454,0.0010661173,0.0011239417,0.002679692,0.0037051241,0.002134305,0.0045385305,0.0007702297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004428278,0.00016742606,0.0010543104,0.0001237854,0.0000848457,0.00010999133,0.00014230775,0.7868656,0.0015852165,0.18290652,0.0033569657,0.023160134],"study_design_scores_gemma":[0.00001909211,0.00003834487,0.00012730653,0.000014066445,0.0000095132145,0.000017773245,0.000012169107,0.95396864,0.00038400298,0.045145042,0.00025354387,0.000010536106],"about_ca_topic_score_codex":0.0031648476,"about_ca_topic_score_gemma":0.0029193067,"teacher_disagreement_score":0.0062626577,"about_ca_system_score_codex":0.0037158837,"about_ca_system_score_gemma":0.0027786053,"threshold_uncertainty_score":0.033120513},"labels":[],"label_agreement":null},{"id":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.24964690891773292,"score_gpt":0.44080407780224784,"score_spread":0.19115716888451492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963110737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018935022,0.0012475837,0.9908394,0.00045719088,0.000058284106,0.000051783863,0.000051297302,0.00011472427,0.0052861897],"genre_scores_gemma":[0.31357947,0.0060270033,0.6603411,0.0009683505,0.00066681835,0.0012535958,0.000542348,0.00036507315,0.016256211],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99624914,0.0024457686,0.00012870184,0.00038353348,0.0005851381,0.00020765433],"domain_scores_gemma":[0.9939229,0.0048208823,0.0003216933,0.0003221323,0.00046030237,0.00015204588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005782521,0.0022004019,0.0027528966,0.0012296905,0.00085758965,0.0027194526,0.0017909145,0.0030673149,0.009673085],"category_scores_gemma":[0.020352123,0.0010529301,0.0011790307,0.002028276,0.0019517962,0.0030163543,0.002933116,0.003536758,0.0019394166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009109772,0.00008062211,0.00050552806,0.00026359534,0.00012377315,0.00006471092,0.000070348826,0.5121517,0.0004354696,0.40873203,0.005631474,0.07184963],"study_design_scores_gemma":[0.000025903559,0.00002594126,0.000108528395,0.0000497193,0.00001620612,0.000026133626,0.000008403248,0.7755895,0.00018479057,0.22073448,0.0032169782,0.00001338575],"about_ca_topic_score_codex":0.0026650059,"about_ca_topic_score_gemma":0.0018513183,"teacher_disagreement_score":0.009673085,"about_ca_system_score_codex":0.0022898887,"about_ca_system_score_gemma":0.0020246222,"threshold_uncertainty_score":0.03235972},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5456077650671064,"score_gpt":0.5258773785639367,"score_spread":0.019730386503169717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963246254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017370163,0.0007398649,0.9752746,0.0018735433,0.000061182516,0.00017533038,0.00019392578,0.00022121519,0.0040902304],"genre_scores_gemma":[0.61429447,0.0009082834,0.3722328,0.00081437494,0.00021577059,0.0010194104,0.00045263075,0.00011018319,0.009952162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9844081,0.011172397,0.0005317514,0.0019034134,0.0015061914,0.00047817433],"domain_scores_gemma":[0.9574677,0.030707182,0.0045825653,0.004996953,0.0016400595,0.00060559646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01628684,0.0013061727,0.0023673286,0.0015446763,0.00078379986,0.0030677682,0.0023285444,0.0032780669,0.0068948474],"category_scores_gemma":[0.06377346,0.0016669417,0.0011409579,0.0025750813,0.0026369772,0.0056814393,0.0043834704,0.0030324792,0.0016598089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008974327,0.00022606814,0.002918294,0.00039887533,0.00024369427,0.00030607556,0.00030715243,0.25766295,0.0016888252,0.60294217,0.006935411,0.12547317],"study_design_scores_gemma":[0.00025773208,0.00017266966,0.0006760545,0.00013593292,0.00005735231,0.00012849242,0.000071306706,0.57532334,0.0011434563,0.41682643,0.005159469,0.000047705707],"about_ca_topic_score_codex":0.0010099083,"about_ca_topic_score_gemma":0.0009244609,"teacher_disagreement_score":0.01628684,"about_ca_system_score_codex":0.0020480335,"about_ca_system_score_gemma":0.0019845276,"threshold_uncertainty_score":0.08613402},"labels":[],"label_agreement":null},{"id":"W2963280733","doi":"","title":"DCM bandits: learning to rank with multiple clicks","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Logarithm; Online learning; Matching (statistics); Learning to rank; Rank (graph theory); Web page; Machine learning; Upper and lower bounds; Artificial intelligence; World Wide Web; Mathematics; Ranking (information retrieval); Statistics","score_opus":0.11166585086489081,"score_gpt":0.4292146443664688,"score_spread":0.31754879350157794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963280733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04360911,0.0009584599,0.9454795,0.0012123227,0.00015858204,0.00031844352,0.00049494614,0.0023354678,0.0054331943],"genre_scores_gemma":[0.71175075,0.00074932736,0.2720569,0.0010692434,0.00046362574,0.0007535446,0.0015014851,0.00042124026,0.0112339575],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669564,0.0014897778,0.0001456634,0.00054272683,0.0006736731,0.00045257527],"domain_scores_gemma":[0.9894637,0.007325516,0.00079535693,0.0011150818,0.00076102157,0.0005392809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00540759,0.0020339282,0.0033206001,0.00138909,0.0012252418,0.0021740422,0.0045918603,0.0032865487,0.006061103],"category_scores_gemma":[0.021227986,0.0010073598,0.0010643547,0.0024264904,0.0019646643,0.003877722,0.0026282906,0.0032807994,0.0024282834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011596337,0.0007020694,0.0039468138,0.00036081078,0.00013271312,0.00019871628,0.00017108244,0.69551134,0.0019029086,0.055653553,0.016578808,0.22368152],"study_design_scores_gemma":[0.00005960291,0.00007433565,0.00014145832,0.000013598381,0.000011742095,0.00004132784,0.000014126088,0.9783724,0.00044566908,0.020169348,0.00064625207,0.000010111454],"about_ca_topic_score_codex":0.0057882727,"about_ca_topic_score_gemma":0.006767552,"teacher_disagreement_score":0.006061103,"about_ca_system_score_codex":0.0020977296,"about_ca_system_score_gemma":0.0029488448,"threshold_uncertainty_score":0.028598368},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.13487576751992256,"score_gpt":0.4272213443219531,"score_spread":0.29234557680203055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963582321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007185695,0.0008937417,0.9867079,0.00044966434,0.00007076332,0.000046389792,0.00006451534,0.00022990153,0.0043514045],"genre_scores_gemma":[0.7538124,0.0016310895,0.23929429,0.0008435114,0.0005349756,0.0004809819,0.0002589545,0.00045682388,0.0026870302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904659,0.0037691267,0.00047119858,0.0016148298,0.0028111087,0.0008678396],"domain_scores_gemma":[0.9264156,0.059629846,0.0040785205,0.0058617266,0.0029143395,0.0010999815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012943925,0.0022995884,0.0024161004,0.001442923,0.0010116209,0.004188729,0.0032203314,0.002530761,0.0032649112],"category_scores_gemma":[0.08591015,0.00095165893,0.0012550241,0.0013880837,0.0054529095,0.010210061,0.0042473874,0.005985639,0.00046887525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021167354,0.000110922265,0.0013864464,0.00020552741,0.00011248771,0.00009542967,0.000139257,0.6219187,0.00096384593,0.3346011,0.0016082417,0.038646482],"study_design_scores_gemma":[0.0000139011945,0.00008531291,0.00030791873,0.000055901946,0.000019723506,0.000044769517,0.000017830771,0.82186776,0.0010889799,0.17574476,0.00073385984,0.000019297246],"about_ca_topic_score_codex":0.0020327673,"about_ca_topic_score_gemma":0.0013962428,"teacher_disagreement_score":0.012943925,"about_ca_system_score_codex":0.003091693,"about_ca_system_score_gemma":0.002774602,"threshold_uncertainty_score":0.0684548},"labels":[],"label_agreement":null},{"id":"W2963735997","doi":"10.1609/aaai.v33i01.33013943","title":"Meta-Descent for Online, Continual Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Range (aeronautics); Mathematical optimization; Hessian matrix; Artificial intelligence; Machine learning; Algorithm; Mathematics; Applied mathematics; Artificial neural network","score_opus":0.3855954766612691,"score_gpt":0.4881601340619269,"score_spread":0.10256465740065779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963735997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009653501,0.0008020802,0.98716486,0.00028995323,0.0000751044,0.000033131404,0.000046008096,0.0006412625,0.001294019],"genre_scores_gemma":[0.5027538,0.0007176624,0.49045646,0.00042397704,0.00019124325,0.00031389415,0.00033602284,0.00037052901,0.0044364324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99935955,0.000239636,0.000038891252,0.00012325526,0.00017548371,0.00006320228],"domain_scores_gemma":[0.9971699,0.0019484584,0.00022822242,0.00023822532,0.00031323536,0.00010196455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025709965,0.0012318809,0.0016544879,0.0008580172,0.0004504723,0.0012065667,0.0019469517,0.0016692232,0.0020100428],"category_scores_gemma":[0.006624053,0.0008137414,0.0008859412,0.00082035176,0.0010556963,0.001511484,0.001108679,0.0022569548,0.0006323237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000661617,0.000052090134,0.0005372718,0.00008412243,0.00007501623,0.000045613997,0.000033792414,0.94786745,0.00074806233,0.011073293,0.0014892349,0.037927918],"study_design_scores_gemma":[0.000004766679,0.000010253352,0.00003057083,0.000005334549,0.0000032249177,0.0000052139967,0.0000019361885,0.99714667,0.00015675322,0.0023613127,0.00027175524,0.000002190017],"about_ca_topic_score_codex":0.0040397192,"about_ca_topic_score_gemma":0.004872529,"teacher_disagreement_score":0.0040397192,"about_ca_system_score_codex":0.0010543002,"about_ca_system_score_gemma":0.0016266473,"threshold_uncertainty_score":0.013596892},"labels":[],"label_agreement":null},{"id":"W2963812988","doi":"10.1016/j.tcs.2013.09.024","title":"Adaptive and optimal online linear regression on <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.gif\" overflow=\"scroll\"><mml:msup><mml:mrow><mml:mi>ℓ</mml:mi></mml:mrow><mml:mrow><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>-balls","year":2013,"lang":"lv","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Agence Nationale de la Recherche; European Commission","keywords":"Regret; Ball (mathematics); Dimension (graph theory); Mathematics; Linear regression; Minimax; Algorithm; Discrete mathematics; Applied mathematics; Computer science; Combinatorics; Mathematical optimization; Statistics; Mathematical analysis","score_opus":0.030323114225871677,"score_gpt":0.2978322730377435,"score_spread":0.2675091588118718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963812988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012286816,0.0014850802,0.9597219,0.0033742746,0.00040530023,0.000106125495,0.0012124721,0.0020706537,0.01933735],"genre_scores_gemma":[0.41665262,0.0029641395,0.4654971,0.0017330076,0.0013867882,0.00081869133,0.0065190736,0.0018111275,0.1026174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99644476,0.0016532838,0.0001900465,0.00060982845,0.0007405353,0.00036154958],"domain_scores_gemma":[0.9817837,0.013550331,0.0006372107,0.0019764495,0.0015576847,0.00049475126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004282832,0.0019485108,0.0025585275,0.0011821064,0.00080375385,0.002557537,0.0021963636,0.001789942,0.023425082],"category_scores_gemma":[0.031166887,0.0009913287,0.0014327624,0.0019261616,0.001694988,0.0038256901,0.0033367025,0.0045854766,0.008130963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079971505,0.0003733263,0.0015057796,0.00052469503,0.00016213338,0.00026366385,0.00018426513,0.38168943,0.0017994515,0.32516798,0.08989715,0.19763239],"study_design_scores_gemma":[0.00006405408,0.000055957695,0.00049507973,0.000059901336,0.000025317155,0.000047375463,0.000027384764,0.8523829,0.0007496527,0.13956605,0.006506323,0.000019972606],"about_ca_topic_score_codex":0.00840398,"about_ca_topic_score_gemma":0.014024514,"teacher_disagreement_score":0.023425082,"about_ca_system_score_codex":0.0023127638,"about_ca_system_score_gemma":0.0033767747,"threshold_uncertainty_score":0.07836467},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.27494721211460194,"score_gpt":0.4837384434734039,"score_spread":0.20879123135880195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964007796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032362204,0.0045783394,0.9213657,0.0041126553,0.0003418189,0.00033738022,0.001369073,0.0014584336,0.034074374],"genre_scores_gemma":[0.7233104,0.005314615,0.24384233,0.0039142137,0.0011712493,0.0018979432,0.002675794,0.0017249193,0.01614844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99199027,0.0033488465,0.00032312464,0.0011844379,0.0019002032,0.0012531101],"domain_scores_gemma":[0.96540195,0.026521387,0.0018862025,0.003144485,0.0017775153,0.0012684745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009540077,0.0045673405,0.0041063437,0.002197482,0.0025367988,0.0063835764,0.0050432626,0.0039279805,0.012989031],"category_scores_gemma":[0.048323777,0.0017742444,0.0025758164,0.00367975,0.005823462,0.009620172,0.006080936,0.009687247,0.0033797768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012988675,0.00061035424,0.0020579107,0.00090116303,0.0002493796,0.00023491622,0.00029561608,0.6143597,0.002856811,0.30238137,0.019736517,0.055017427],"study_design_scores_gemma":[0.00005666449,0.00009401536,0.000304802,0.00013645603,0.000037408605,0.0000791679,0.00004632785,0.83452433,0.00082086865,0.16199312,0.0018839455,0.000022821498],"about_ca_topic_score_codex":0.0028420866,"about_ca_topic_score_gemma":0.0031939202,"teacher_disagreement_score":0.012989031,"about_ca_system_score_codex":0.0057089925,"about_ca_system_score_gemma":0.0035607019,"threshold_uncertainty_score":0.050453365},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.26156167212854786,"score_gpt":0.4801871304299516,"score_spread":0.21862545830140373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964072175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05209151,0.0015927182,0.9404638,0.0009728308,0.00015092308,0.000059488775,0.00014642788,0.00039152554,0.004130785],"genre_scores_gemma":[0.9507481,0.0009133728,0.04358191,0.00027715837,0.00018344051,0.00015081692,0.00009779445,0.0000655221,0.0039818594],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835014,0.0006396045,0.00007026507,0.00036672276,0.000313738,0.00025957584],"domain_scores_gemma":[0.98964953,0.008020634,0.00081928354,0.00059598405,0.00060435705,0.00031011974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028510725,0.0010953852,0.0014393348,0.00048043687,0.0004936462,0.0015490782,0.0013696189,0.0016665007,0.0019529047],"category_scores_gemma":[0.017280456,0.00044280483,0.0004736886,0.0006349812,0.0015507643,0.0024877363,0.0014386052,0.0020478433,0.00034383274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003484336,0.000079970836,0.0005944065,0.00022088367,0.000056943667,0.00009542183,0.000060395385,0.8727888,0.0013981668,0.09774462,0.0016914981,0.024920402],"study_design_scores_gemma":[0.000040518993,0.000066611705,0.00008984261,0.000018266739,0.000013951364,0.000023572931,0.0000073850556,0.9454207,0.00064666755,0.053184092,0.00048124383,0.0000070956526],"about_ca_topic_score_codex":0.0016352875,"about_ca_topic_score_gemma":0.0010494796,"teacher_disagreement_score":0.0028510725,"about_ca_system_score_codex":0.001904469,"about_ca_system_score_gemma":0.0013632702,"threshold_uncertainty_score":0.015078068},"labels":[],"label_agreement":null},{"id":"W2964096186","doi":"","title":"{Bayesian Multi-Scale Optimistic Optimization}","year":2014,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian optimization; Regret; Mathematical optimization; Computer science; Gaussian process; Global optimization; Optimization problem; Convergence (economics); Derivative-free optimization; Test functions for optimization; Continuous optimization; Random optimization; Bayesian probability; Function (biology); Gaussian; Multi-swarm optimization; Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.06710112123898992,"score_gpt":0.3386387153824301,"score_spread":0.2715375941434402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964096186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036977585,0.00057358743,0.97734296,0.0006989435,0.0000829797,0.000106513915,0.00026155697,0.0007727198,0.016462944],"genre_scores_gemma":[0.49066454,0.0016194684,0.47750938,0.0010140712,0.0003471101,0.00083195313,0.0009735037,0.0010230173,0.026016915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781513,0.000950036,0.000069385016,0.00034074162,0.0005976678,0.0002270608],"domain_scores_gemma":[0.9971058,0.001585597,0.00029729234,0.0005247559,0.0003303508,0.00015625218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029599129,0.002249041,0.0016870896,0.0008768273,0.0009807514,0.0021824692,0.002091574,0.0016322853,0.012781514],"category_scores_gemma":[0.0083864825,0.0008841273,0.0010206623,0.0016232337,0.001731955,0.0021759889,0.0038073112,0.0034247134,0.0030517683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024497442,0.00008073585,0.00043415945,0.00036763705,0.00009752591,0.0000942873,0.00007322222,0.6433112,0.0012468217,0.24210055,0.020145025,0.091803916],"study_design_scores_gemma":[0.000017170985,0.000025353507,0.000086857675,0.000029564719,0.000011327247,0.000026719841,0.000008699549,0.901414,0.00048603473,0.09481978,0.003061135,0.000013292063],"about_ca_topic_score_codex":0.0035542008,"about_ca_topic_score_gemma":0.0039987126,"teacher_disagreement_score":0.012781514,"about_ca_system_score_codex":0.0024317224,"about_ca_system_score_gemma":0.0028314914,"threshold_uncertainty_score":0.042758405},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.39633834779057253,"score_gpt":0.5102858031466518,"score_spread":0.11394745535607931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964240248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06520214,0.00066950993,0.92347246,0.0007867347,0.00009067739,0.00011597328,0.00029182888,0.0006360684,0.008734496],"genre_scores_gemma":[0.8777393,0.000444754,0.114959165,0.000396576,0.00008269094,0.00031962167,0.00036209886,0.00012365433,0.0055722278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998221,0.0007681129,0.00009726043,0.00037480093,0.00030927788,0.00022961585],"domain_scores_gemma":[0.9940645,0.0040121204,0.000578167,0.0006271662,0.00041458986,0.00030347175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024298087,0.0011951182,0.0019196676,0.00081297685,0.00074137485,0.0018382112,0.00198342,0.0016158936,0.004717187],"category_scores_gemma":[0.010426803,0.00057566253,0.00078495126,0.0013574725,0.0014638806,0.0021798157,0.0019694308,0.0019914792,0.0006855629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019309013,0.00009501815,0.0013308704,0.00013351488,0.000074995056,0.00012474447,0.0000674672,0.8562378,0.00092398474,0.10638484,0.0031983214,0.031235427],"study_design_scores_gemma":[0.000017930395,0.000029478275,0.00008052762,0.000010753646,0.000008055047,0.000026046235,0.000008550847,0.95815253,0.00018937975,0.04088238,0.0005882476,0.000006132674],"about_ca_topic_score_codex":0.002057913,"about_ca_topic_score_gemma":0.0021503137,"teacher_disagreement_score":0.004717187,"about_ca_system_score_codex":0.0011346915,"about_ca_system_score_gemma":0.000973145,"threshold_uncertainty_score":0.015780628},"labels":[],"label_agreement":null},{"id":"W2964278219","doi":"","title":"Thompson Sampling for Combinatorial Semi-Bandits.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Thompson sampling; Matroid; Oracle; Sampling (signal processing); Mathematics; Mathematical optimization; Independence (probability theory); Computer science; Combinatorics; Statistics","score_opus":0.27226303544098335,"score_gpt":0.5115727209194741,"score_spread":0.2393096854784908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964278219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017529627,0.0007974888,0.9756141,0.00046239258,0.00009966984,0.00013429117,0.00009075631,0.00030031885,0.004971364],"genre_scores_gemma":[0.6492397,0.0010864275,0.34009495,0.0006281554,0.0002901192,0.00072301,0.0004263252,0.00023836507,0.0072729527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732286,0.0017120402,0.00009048361,0.0003019925,0.00038605824,0.0001865938],"domain_scores_gemma":[0.9865588,0.01099243,0.00084072957,0.0008237517,0.0004154668,0.00036870418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049328287,0.0013291042,0.0017725419,0.0011300176,0.000840617,0.001929459,0.0019669293,0.0017753638,0.0050398614],"category_scores_gemma":[0.022167312,0.0007568907,0.0012627683,0.0016273034,0.0020332674,0.0025288633,0.0014698558,0.0024336062,0.0007680389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022772318,0.00011646096,0.0013905539,0.00019105527,0.00011196663,0.00012107576,0.00008628379,0.65855265,0.0008958898,0.30430326,0.0029692121,0.031033885],"study_design_scores_gemma":[0.000018995097,0.000028739403,0.00008692448,0.000014241344,0.000009335402,0.000019233437,0.000008611239,0.92704034,0.00019649036,0.07195295,0.00061860523,0.0000056715835],"about_ca_topic_score_codex":0.003290706,"about_ca_topic_score_gemma":0.0039938353,"teacher_disagreement_score":0.0050398614,"about_ca_system_score_codex":0.0021968496,"about_ca_system_score_gemma":0.0015044629,"threshold_uncertainty_score":0.026087642},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3686539785191696,"score_gpt":0.33170251449792354,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964315724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09339536,0.002078403,0.8740434,0.0029840125,0.0001519063,0.00022674567,0.00028634703,0.00028004107,0.026553858],"genre_scores_gemma":[0.89678156,0.0014928607,0.085504554,0.0008178829,0.00020029764,0.00052848354,0.00023141479,0.00019619288,0.01424662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692106,0.001784322,0.00011885993,0.00042986413,0.00036800327,0.0003779364],"domain_scores_gemma":[0.97768366,0.019072093,0.0013657511,0.00062122324,0.0006267966,0.00063043647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053063706,0.002034727,0.0022282454,0.0008652667,0.0007143329,0.002322169,0.0018751625,0.003043824,0.005952096],"category_scores_gemma":[0.030124376,0.00079132756,0.0008671416,0.0012294445,0.0026626722,0.0035971627,0.0020562343,0.0036646242,0.00095489406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047048985,0.00017942536,0.0015346128,0.00029126334,0.00014493635,0.00024053657,0.0003088309,0.6108882,0.0012532248,0.3562648,0.0028047557,0.025618989],"study_design_scores_gemma":[0.0000868604,0.00015362061,0.0002063315,0.000063266874,0.000023858562,0.000045211735,0.000042597432,0.8230346,0.00036934312,0.17490984,0.0010441002,0.000020292304],"about_ca_topic_score_codex":0.0024949685,"about_ca_topic_score_gemma":0.0016105842,"teacher_disagreement_score":0.005952096,"about_ca_system_score_codex":0.0019930871,"about_ca_system_score_gemma":0.0019676024,"threshold_uncertainty_score":0.028063118},"labels":[],"label_agreement":null},{"id":"W2965415665","doi":"10.24963/ijcai.2019/532","title":"Learning Multi-Objective Rewards and User Utility Function in Contextual Bandits for Personalized Ranking","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National University of Singapore","keywords":"Computer science; Ranking (information retrieval); Weighting; Context (archaeology); Function (biology); Machine learning; Artificial intelligence; Learning to rank","score_opus":0.11000894557218811,"score_gpt":0.4211775392848835,"score_spread":0.3111685937126954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965415665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08132121,0.0014940741,0.913052,0.0005710614,0.00004937731,0.000108843444,0.00013605288,0.0006536732,0.002613657],"genre_scores_gemma":[0.89552045,0.00045511592,0.10064086,0.00025124638,0.000074825664,0.00022920356,0.00020486467,0.00010778194,0.0025156755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812526,0.0010138118,0.0000826243,0.0003128136,0.00026095135,0.00020462138],"domain_scores_gemma":[0.9940977,0.004622275,0.0004694199,0.00026116354,0.0003255289,0.00022388365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033752841,0.0017735132,0.0024891212,0.00095957454,0.00061106536,0.0014145196,0.0014220265,0.0018100551,0.002571532],"category_scores_gemma":[0.013133268,0.0007167257,0.000621894,0.0010444825,0.0012302927,0.002691504,0.0012562482,0.0022201205,0.00056504004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024437474,0.00018621371,0.0014517852,0.0001119116,0.000068179295,0.000054875425,0.00008107217,0.93900555,0.0005315124,0.013649204,0.0008364955,0.043778777],"study_design_scores_gemma":[0.000014112331,0.00004747851,0.00011573617,0.000011259596,0.000009087021,0.000009030238,0.0000075480107,0.9924406,0.00017524807,0.007030125,0.000133819,0.000005871595],"about_ca_topic_score_codex":0.0050535616,"about_ca_topic_score_gemma":0.005707084,"teacher_disagreement_score":0.0050535616,"about_ca_system_score_codex":0.0015602123,"about_ca_system_score_gemma":0.0012827493,"threshold_uncertainty_score":0.017850399},"labels":[],"label_agreement":null},{"id":"W2966286942","doi":"","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring.","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Minimax; Mathematics; Bayesian probability; Mathematical economics; Degenerate energy levels; Mathematical optimization; Computer science; Discrete mathematics; Statistics","score_opus":0.09132089929786394,"score_gpt":0.4067404308935916,"score_spread":0.31541953159572766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966286942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061482014,0.0011966331,0.977047,0.0018334013,0.00015539335,0.00009107051,0.0002688926,0.0002015878,0.013057709],"genre_scores_gemma":[0.6866193,0.0036516008,0.2862615,0.002686225,0.0012229534,0.0009365972,0.0006300685,0.0005164686,0.017475316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926571,0.0033932729,0.00025970297,0.0011808779,0.001890404,0.00061863044],"domain_scores_gemma":[0.97078335,0.022286324,0.0021278015,0.0032261931,0.000984717,0.00059162895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010282083,0.0025227692,0.0022542903,0.0017882992,0.0013031301,0.004363826,0.004623093,0.0030706935,0.011006349],"category_scores_gemma":[0.049840085,0.0012968077,0.0026015579,0.0021615073,0.0055594807,0.010815438,0.0066371667,0.010038276,0.0016378094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014243246,0.00010554604,0.0006884271,0.00030752682,0.00015208487,0.00012750407,0.00021205988,0.13491836,0.001344937,0.83352506,0.0057087857,0.022767363],"study_design_scores_gemma":[0.000024279745,0.00008641195,0.0003347366,0.00010565768,0.000038029404,0.000119542725,0.000028426804,0.2918641,0.0008436472,0.70350456,0.0030173352,0.000033290573],"about_ca_topic_score_codex":0.0009086961,"about_ca_topic_score_gemma":0.00079041714,"teacher_disagreement_score":0.011006349,"about_ca_system_score_codex":0.003946359,"about_ca_system_score_gemma":0.0020017743,"threshold_uncertainty_score":0.054377496},"labels":[],"label_agreement":null},{"id":"W2966820259","doi":"","title":"Problem-dependent Regret Bounds for Online Learning with Feedback Graphs.","year":2019,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Computer science; Online learning; Theoretical computer science; Artificial intelligence; Machine learning; World Wide Web","score_opus":0.1217124348623598,"score_gpt":0.41820771941942625,"score_spread":0.2964952845570664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966820259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023734327,0.009264614,0.93889624,0.0037753796,0.0005817445,0.00026151078,0.0009438162,0.0007456971,0.021796653],"genre_scores_gemma":[0.7842795,0.00693384,0.189327,0.0023003917,0.0012896209,0.0009891106,0.0018066246,0.00071431213,0.01235958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9929463,0.0034972695,0.00021356177,0.00079154037,0.0016446566,0.00090671825],"domain_scores_gemma":[0.91800827,0.07217471,0.0022077668,0.00312473,0.0028920614,0.0015925524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011824571,0.0030511823,0.0027045761,0.001869493,0.0012191655,0.0035492342,0.0041408055,0.0032414324,0.007954157],"category_scores_gemma":[0.07505142,0.00094159535,0.0012273688,0.0024635496,0.0031215616,0.006683354,0.0038672634,0.00670093,0.0012520005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009193343,0.00044478642,0.0012091431,0.0007956593,0.00024093383,0.00011728019,0.00019786722,0.73027986,0.001045647,0.18889764,0.018141365,0.057710506],"study_design_scores_gemma":[0.000044868404,0.000084160994,0.00029710346,0.00012216285,0.00004916536,0.000044691944,0.00003055627,0.86798793,0.00042251483,0.12956707,0.0013321164,0.000017677785],"about_ca_topic_score_codex":0.0035901282,"about_ca_topic_score_gemma":0.0036210127,"teacher_disagreement_score":0.011824571,"about_ca_system_score_codex":0.0045612333,"about_ca_system_score_gemma":0.0032219558,"threshold_uncertainty_score":0.06253499},"labels":[],"label_agreement":null},{"id":"W2970168598","doi":"","title":"Surrogate Objectives for Batch Policy Optimization in One-step Decision Making","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical optimization; Entropy (arrow of time); Artificial intelligence; Multi-armed bandit; Constrained optimization problem; Action selection; Action (physics); Optimization problem; State (computer science); Surrogate model; Principle of maximum entropy; Machine learning; Mathematics; Algorithm; Regret; Psychology","score_opus":0.07992803755470389,"score_gpt":0.42332753069394063,"score_spread":0.34339949313923673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970168598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02374357,0.0008482864,0.97022295,0.0006846937,0.000072639166,0.000083805615,0.00011112144,0.00028061078,0.003952296],"genre_scores_gemma":[0.7832429,0.000720761,0.20977533,0.0005034396,0.00012284849,0.00047983046,0.0004079263,0.00020480852,0.004542138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998304,0.00097113685,0.00008014003,0.00023792218,0.00024763218,0.00015917243],"domain_scores_gemma":[0.98568,0.012166885,0.0007067147,0.00047989088,0.0006160293,0.0003505383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058346866,0.0017607615,0.0025430967,0.00079305127,0.0004968165,0.0018885165,0.0014743009,0.002600129,0.0032418037],"category_scores_gemma":[0.020962527,0.000791335,0.00083520444,0.00082832255,0.0022415973,0.002302784,0.0019184657,0.0031553872,0.0006452694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101030564,0.000050611507,0.00034474788,0.00007337433,0.000028898521,0.00003546344,0.000031938063,0.9669447,0.00029804272,0.02239065,0.00052624504,0.009174281],"study_design_scores_gemma":[0.00000471264,0.00001838946,0.000022942457,0.000009622619,0.0000022862396,0.0000038451017,0.0000026374173,0.99231684,0.00011878922,0.0074012307,0.000095935684,0.0000026365576],"about_ca_topic_score_codex":0.0019068089,"about_ca_topic_score_gemma":0.001472735,"teacher_disagreement_score":0.0058346866,"about_ca_system_score_codex":0.002006122,"about_ca_system_score_gemma":0.001634086,"threshold_uncertainty_score":0.030857146},"labels":[],"label_agreement":null},{"id":"W2970245835","doi":"","title":"Learning Reliable Policies in the Bandit Setting with Application to Adaptive Clinical Trials.","year":2019,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.44409328734001935,"score_gpt":0.5419922742734516,"score_spread":0.0978989869334323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970245835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041898333,0.0035200424,0.9474921,0.0030528896,0.0002636751,0.00045975923,0.00023319073,0.0007642297,0.002315717],"genre_scores_gemma":[0.79914975,0.0016777153,0.19299825,0.0010920106,0.00032456743,0.0012321676,0.00033961653,0.00013525378,0.0030507275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9800332,0.016865054,0.00068010064,0.001125501,0.00076314603,0.0005330385],"domain_scores_gemma":[0.78776026,0.19818518,0.005720254,0.0033761638,0.003242233,0.0017158178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046792407,0.001707726,0.0045065335,0.0016399513,0.0008381659,0.0032793076,0.0024407138,0.0038536184,0.0038522372],"category_scores_gemma":[0.17705362,0.0013506724,0.0010047547,0.0015511897,0.0027235472,0.0031270415,0.002462611,0.005553229,0.00075383973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002369605,0.00031979216,0.0046766335,0.00045010375,0.0004985978,0.0002856993,0.00030409283,0.8491476,0.00034492687,0.04633938,0.0034610424,0.091802455],"study_design_scores_gemma":[0.00025930462,0.00019973767,0.00045466263,0.0000738011,0.00007440128,0.000041701558,0.000037038317,0.95300484,0.00023930377,0.04500024,0.0005942747,0.000020639636],"about_ca_topic_score_codex":0.0049662776,"about_ca_topic_score_gemma":0.0032404726,"teacher_disagreement_score":0.046792407,"about_ca_system_score_codex":0.001817098,"about_ca_system_score_gemma":0.0036734566,"threshold_uncertainty_score":0.24746484},"labels":[],"label_agreement":null},{"id":"W2973807518","doi":"10.1109/access.2024.3510558","title":"Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Science and Engineering Research Board; Indian Institute of Technology Madras","keywords":"Mathematical optimization; Computer science; Set (abstract data type); Scheduling (production processes); Bellman equation; Observable; Class (philosophy); Mathematics; Artificial intelligence","score_opus":0.18320865466153252,"score_gpt":0.5301487381280565,"score_spread":0.346940083466524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973807518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011401355,0.00041815612,0.9850316,0.00023343335,0.00005310958,0.00004337361,0.000044693075,0.00015277401,0.0026215364],"genre_scores_gemma":[0.88246834,0.00074525713,0.11203047,0.00022202921,0.000099496,0.000256521,0.00012053125,0.000086911816,0.003970473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998667,0.0006998862,0.000059458725,0.00019602965,0.00020232388,0.00017547318],"domain_scores_gemma":[0.99746704,0.0019003431,0.00025743453,0.00013012248,0.00014761553,0.00009752391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021315962,0.0015494388,0.0014593877,0.00054727343,0.0006833536,0.0017337054,0.0010720755,0.0012711944,0.0032761747],"category_scores_gemma":[0.004243892,0.0005282993,0.0007861228,0.00072645326,0.0015692905,0.0014369888,0.0012248555,0.0022790344,0.00047228846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005991519,0.00002420894,0.00014989165,0.000051094994,0.000017212627,0.000043945183,0.00003493593,0.95953643,0.00046017632,0.032975554,0.00031545173,0.0063312217],"study_design_scores_gemma":[0.0000067346828,0.000016978447,0.000022255559,0.0000047976814,0.0000023914547,0.0000045549723,0.0000053085387,0.9893895,0.000102938204,0.010203228,0.00023836995,0.0000030172494],"about_ca_topic_score_codex":0.005269743,"about_ca_topic_score_gemma":0.0037658645,"teacher_disagreement_score":0.005269743,"about_ca_system_score_codex":0.0015341399,"about_ca_system_score_gemma":0.0014581562,"threshold_uncertainty_score":0.011273086},"labels":[],"label_agreement":null},{"id":"W2978459918","doi":"10.48550/arxiv.1910.01706","title":"Bounds for Approximate Regret-Matching Algorithms","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Computer science; Mathematical optimization; Generalization; Matching (statistics); Function (biology); Algorithm; Mathematics; Machine learning; Statistics","score_opus":0.28678316791238206,"score_gpt":0.33104138160431723,"score_spread":0.044258213691935167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978459918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0094758915,0.0034444006,0.95686024,0.0029051285,0.0003101137,0.00020301364,0.0004801285,0.0010570543,0.025264028],"genre_scores_gemma":[0.436631,0.005464058,0.52323717,0.004041578,0.0016304834,0.0019475139,0.0021795714,0.0023120686,0.022556586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9851716,0.0060137124,0.0006246614,0.002203857,0.004370813,0.0016153088],"domain_scores_gemma":[0.9518212,0.03755004,0.0015888591,0.0052366713,0.0026785124,0.001124747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014373889,0.0042712856,0.0040222146,0.002805594,0.0021337944,0.0058700917,0.0059086597,0.004551853,0.013396088],"category_scores_gemma":[0.092324786,0.0012307274,0.0033352473,0.0045782323,0.004116985,0.0121426275,0.007520387,0.011178822,0.0035986002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006273449,0.00034928237,0.0022153412,0.0007088442,0.0002997837,0.0001264658,0.00031879576,0.31301206,0.0018158894,0.55512327,0.01837019,0.10703275],"study_design_scores_gemma":[0.0000424061,0.00009471683,0.00031459192,0.00011900801,0.00006629051,0.000073431926,0.00004376841,0.6125448,0.0007870343,0.38120884,0.00468025,0.000024891751],"about_ca_topic_score_codex":0.0024795344,"about_ca_topic_score_gemma":0.002745711,"teacher_disagreement_score":0.014373889,"about_ca_system_score_codex":0.006478794,"about_ca_system_score_gemma":0.0037813885,"threshold_uncertainty_score":0.07601726},"labels":[],"label_agreement":null},{"id":"W2982146718","doi":"10.1287/ijoo.2019.0045","title":"An Ensemble Learning Framework for Model Fitting and Evaluation in Inverse Linear Optimization","year":2021,"lang":"en","type":"preprint","venue":"INFORMS Journal on Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Toronto","funders":"","keywords":"Metric (unit); Computer science; Mathematical optimization; Plan (archaeology); Inverse; Machine learning; Construct (python library); Optimization problem; Base (topology); Artificial intelligence; Mathematics; Algorithm; Engineering","score_opus":0.16963652680852584,"score_gpt":0.4728932681299927,"score_spread":0.30325674132146685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982146718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011885654,0.00010303381,0.998026,0.00010359118,0.000010914827,0.000017348248,0.000027307806,0.00013968808,0.00038345924],"genre_scores_gemma":[0.22600526,0.0004934363,0.76975244,0.0002744224,0.00016175535,0.0005719081,0.00046492537,0.0003916511,0.0018841206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99561596,0.0025597792,0.00018484017,0.00042777412,0.001022101,0.00018953672],"domain_scores_gemma":[0.9921721,0.00487204,0.000539319,0.0008781074,0.0013160178,0.0002223427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008274388,0.0017659713,0.00230926,0.001673373,0.00076433603,0.0021012772,0.0028061087,0.0022783123,0.0025056622],"category_scores_gemma":[0.01984061,0.00094721693,0.0016656964,0.0015432355,0.0013479751,0.0023716774,0.0031751734,0.0036681567,0.0006583661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000298494,0.00003139655,0.00029983852,0.000045330235,0.0000619553,0.000027093745,0.000039215534,0.9334717,0.00049661973,0.0326313,0.00092133315,0.031944297],"study_design_scores_gemma":[0.000002686907,0.000012357686,0.000024090137,0.0000062088766,0.0000045366623,0.0000049315877,0.0000022812683,0.9887636,0.00015518107,0.010770906,0.00024958036,0.0000037030266],"about_ca_topic_score_codex":0.0052550263,"about_ca_topic_score_gemma":0.0047571026,"teacher_disagreement_score":0.008274388,"about_ca_system_score_codex":0.001626979,"about_ca_system_score_gemma":0.001974164,"threshold_uncertainty_score":0.043759704},"labels":[],"label_agreement":null},{"id":"W2985478892","doi":"10.1016/j.tcs.2019.11.015","title":"A modular analysis of adaptive (non-)convex optimization: Optimism, composite objectives, variance reduction, and variational bounds","year":2019,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Engineering and Physical Sciences Research Council; Alberta Machine Intelligence Institute","keywords":"Mathematical proof; Mathematical optimization; Regret; Computer science; Generalization; Convex optimization; Modular design; Mathematics; Convex analysis; Regular polygon; Algorithm; Machine learning","score_opus":0.021383389473001273,"score_gpt":0.33536394111611845,"score_spread":0.31398055164311717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985478892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072171576,0.0003797577,0.9887876,0.00034703233,0.00003713594,0.000012326394,0.000022486267,0.000026013204,0.003170523],"genre_scores_gemma":[0.6341818,0.0018411007,0.3494898,0.00038283053,0.00069874345,0.0002142201,0.00013471619,0.00029500696,0.012761718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863404,0.00071074395,0.00004212888,0.00019975104,0.0003136525,0.00009961218],"domain_scores_gemma":[0.9971208,0.0017860092,0.0002745553,0.00031302942,0.0003608096,0.00014484987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040598945,0.0013318413,0.0010238517,0.0013027287,0.00040474068,0.0014401452,0.0016837472,0.0010087067,0.0032283864],"category_scores_gemma":[0.009301642,0.00069966953,0.0018654836,0.0009785425,0.0023990248,0.003227716,0.0032628465,0.0028518846,0.00037568618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003757511,0.000038082373,0.00038098812,0.00011795508,0.00009419565,0.000044742526,0.00009121366,0.15486372,0.0028669727,0.81744236,0.0013367113,0.022685567],"study_design_scores_gemma":[0.00000650022,0.000031216267,0.00025489263,0.000019527337,0.000022855977,0.000020761207,0.000011447541,0.6532216,0.00042518685,0.34517527,0.0007995201,0.000011139019],"about_ca_topic_score_codex":0.00085157854,"about_ca_topic_score_gemma":0.0008564428,"teacher_disagreement_score":0.0040598945,"about_ca_system_score_codex":0.0010226488,"about_ca_system_score_gemma":0.0008557983,"threshold_uncertainty_score":0.021471024},"labels":[],"label_agreement":null},{"id":"W2993775923","doi":"10.48550/arxiv.1912.02967","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Softmax function; Counterfactual thinking; Approximation error; Function approximation; Reinforcement learning; Perfect information; Function (biology); Mathematics; Mathematical optimization; Computer science; Applied mathematics; Mathematical economics; Artificial intelligence; Statistics; Artificial neural network","score_opus":0.24397190943936153,"score_gpt":0.33773912044899723,"score_spread":0.0937672110096357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993775923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019039059,0.0006363337,0.9724521,0.00095881947,0.000048489022,0.000119210825,0.000070168506,0.00033765627,0.006338266],"genre_scores_gemma":[0.64722914,0.0011506946,0.34304956,0.00113402,0.0001702662,0.00078403944,0.00028065458,0.00051038904,0.0056911907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922989,0.004468318,0.00025363558,0.00088067405,0.0014873476,0.0006111099],"domain_scores_gemma":[0.9751726,0.019371904,0.0015548348,0.0023336117,0.0010821256,0.00048486545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014076096,0.0024679666,0.002363786,0.001691043,0.0009493401,0.0029436091,0.0036508695,0.003118195,0.003956228],"category_scores_gemma":[0.06429777,0.0008354333,0.0019453631,0.0016511588,0.0036520548,0.006200381,0.0035071578,0.0060490384,0.0006695278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017500563,0.0001489428,0.0010419404,0.00015052827,0.00009999365,0.00007044213,0.00015619838,0.7037648,0.000803295,0.25700378,0.0021380605,0.034447066],"study_design_scores_gemma":[0.000018252114,0.000051794796,0.00010737414,0.000035895242,0.000016725233,0.000023902083,0.000018322782,0.9438749,0.00041381933,0.054831598,0.0005950335,0.000012371287],"about_ca_topic_score_codex":0.0032260965,"about_ca_topic_score_gemma":0.0023938322,"teacher_disagreement_score":0.014076096,"about_ca_system_score_codex":0.004286962,"about_ca_system_score_gemma":0.002425356,"threshold_uncertainty_score":0.07444239},"labels":[],"label_agreement":null},{"id":"W2993785662","doi":"10.48550/arxiv.1912.01718","title":"Risk-Averse Action Selection Using Extreme Value Theory Estimates of the CVaR","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"CVAR; Quantile; Estimator; Extreme value theory; Expected shortfall; Generalized Pareto distribution; Selection (genetic algorithm); Variance (accounting); Mathematical optimization; Extrapolation; Econometrics; Mathematics; Computer science; Statistics; Risk management; Economics; Artificial intelligence","score_opus":0.36099966413873114,"score_gpt":0.3320410035950809,"score_spread":0.02895866054365026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993785662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005833506,0.0002598169,0.9927725,0.00018520685,0.000019878067,0.00003957866,0.000028326082,0.00010972505,0.0007514636],"genre_scores_gemma":[0.58506763,0.001223516,0.40865096,0.0004569927,0.00023429231,0.0006832719,0.00037040334,0.00020942284,0.0031036097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614966,0.0020271132,0.00019241759,0.00055183977,0.0008329044,0.00024616404],"domain_scores_gemma":[0.96815854,0.027197015,0.001812594,0.0009774128,0.0014349654,0.00041952613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009263395,0.0017603859,0.0026957188,0.0021753905,0.0006572301,0.0024805593,0.002033907,0.0019483791,0.0035887056],"category_scores_gemma":[0.041841332,0.00096288655,0.0016136549,0.001422827,0.002478605,0.0030816859,0.0023665754,0.0041759037,0.00047183395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008541065,0.00011223078,0.0017199211,0.00016373004,0.00019868134,0.000094423645,0.00010067308,0.8884658,0.0007414617,0.07413748,0.0009880789,0.03319213],"study_design_scores_gemma":[0.000012019175,0.00003787186,0.00021128225,0.000039525476,0.000017584074,0.000021616554,0.000011760329,0.9479989,0.00029015786,0.05109212,0.00025310286,0.000014096065],"about_ca_topic_score_codex":0.0028816261,"about_ca_topic_score_gemma":0.0022050992,"teacher_disagreement_score":0.009263395,"about_ca_system_score_codex":0.0016918837,"about_ca_system_score_gemma":0.0021764785,"threshold_uncertainty_score":0.04899013},"labels":[],"label_agreement":null},{"id":"W2994873989","doi":"10.1109/cwit.2019.8929931","title":"Dynamic spectrum access under partial observations: A restless bandit approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Markov decision process; Markov process; Channel (broadcasting); Mathematical optimization; Scheduling (production processes); Partially observable Markov decision process; Resource allocation; Transmitter; Heuristic; Channel allocation schemes; Markov chain; Computer network; Wireless; Mathematics; Telecommunications","score_opus":0.26519510859321027,"score_gpt":0.4729444876965696,"score_spread":0.20774937910335933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994873989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060844306,0.00029027733,0.9349849,0.0006075892,0.000032761694,0.000081158854,0.0001592624,0.00020862916,0.0027910892],"genre_scores_gemma":[0.9370712,0.0003377716,0.058511283,0.00020946532,0.000089388916,0.00017526235,0.00018083802,0.000062917614,0.0033618426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978138,0.0009978793,0.00008824926,0.0003665083,0.00034897836,0.0003845401],"domain_scores_gemma":[0.9879773,0.009559288,0.001151853,0.00059402536,0.0004435589,0.0002739998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004222798,0.001402049,0.0022722569,0.0011849739,0.000867685,0.002442814,0.002312722,0.0016330073,0.0027539046],"category_scores_gemma":[0.015554648,0.0009853598,0.0009574477,0.0011935806,0.0033108313,0.0044214395,0.0024933645,0.002162401,0.00032183854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000217834,0.000055866873,0.000720091,0.000052802116,0.00005555998,0.00019592303,0.000097610166,0.9286782,0.00052397227,0.06209225,0.000272226,0.007037654],"study_design_scores_gemma":[0.000012137592,0.00001754194,0.000071216346,0.0000064147057,0.0000078158555,0.000011528744,0.00001143317,0.98023695,0.00015294086,0.019391239,0.00007290491,0.000007849162],"about_ca_topic_score_codex":0.006366342,"about_ca_topic_score_gemma":0.0048607863,"teacher_disagreement_score":0.006366342,"about_ca_system_score_codex":0.002270795,"about_ca_system_score_gemma":0.0015218259,"threshold_uncertainty_score":0.02233255},"labels":[],"label_agreement":null},{"id":"W2995725691","doi":"10.48550/arxiv.1912.09451","title":"An Iterative Riccati Algorithm for Online Linear Quadratic Control","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Sublinear function; Linear-quadratic regulator; Logarithm; Mathematics; Mathematical optimization; Hindsight bias; Controller (irrigation); Linear-quadratic-Gaussian control; Optimal control; Linear system; Riccati equation; Smoothing; Sequence (biology); Computer science; Discrete mathematics","score_opus":0.22565802047666222,"score_gpt":0.3500820730083962,"score_spread":0.124424052531734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995725691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028201726,0.00021350503,0.99298453,0.00015270367,0.00003705575,0.000052398707,0.000025951786,0.00037031795,0.003343383],"genre_scores_gemma":[0.5628035,0.0004808826,0.42573738,0.00034624836,0.00014609833,0.00049289386,0.00026342855,0.00025619156,0.009473287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988404,0.00037691774,0.00005069876,0.00027144354,0.00033282422,0.00012780125],"domain_scores_gemma":[0.9985948,0.00085275306,0.00013482488,0.00014436111,0.00022325273,0.00004993928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014908712,0.0011693693,0.001326086,0.00052614324,0.0004967883,0.0009851439,0.0016745977,0.0014424209,0.0039147343],"category_scores_gemma":[0.004061399,0.0005169484,0.0006613665,0.0009844853,0.0011784098,0.0011604748,0.0012662683,0.0024524727,0.0010704221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013127126,0.0001302435,0.000248772,0.00013091072,0.000053123025,0.00007388877,0.000099721445,0.83527416,0.0023428441,0.06440178,0.003917895,0.09319548],"study_design_scores_gemma":[0.0000117519185,0.000023632841,0.000025402333,0.0000038463686,0.0000027802441,0.000010245799,0.0000028520828,0.9917269,0.0003156086,0.0072826645,0.00058998464,0.000004295577],"about_ca_topic_score_codex":0.004541216,"about_ca_topic_score_gemma":0.0035753674,"teacher_disagreement_score":0.004541216,"about_ca_system_score_codex":0.001317855,"about_ca_system_score_gemma":0.0018187948,"threshold_uncertainty_score":0.013096094},"labels":[],"label_agreement":null},{"id":"W2997720193","doi":"10.1609/aaai.v34i04.6116","title":"Efficient Projection-Free Online Methods with Stochastic Recursive Gradient","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Regret; Logarithm; Projection (relational algebra); Mathematical optimization; Computer science; Estimator; Regular polygon; Convex optimization; Algorithm; Mathematics; Machine learning","score_opus":0.3080010328745577,"score_gpt":0.46401449363521663,"score_spread":0.15601346076065892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997720193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027584052,0.0001979727,0.9951154,0.00010982007,0.00003411398,0.000049660026,0.00002284898,0.00071562047,0.0009960543],"genre_scores_gemma":[0.2403924,0.00041551815,0.7509178,0.00036532275,0.00018162168,0.00053282094,0.0003441227,0.0005375238,0.006312888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987143,0.00045752883,0.00005216731,0.00019239633,0.00043499074,0.0001486297],"domain_scores_gemma":[0.99715555,0.0018050899,0.00020005082,0.000356664,0.00032866685,0.00015392457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016640171,0.001782725,0.0017349437,0.00060491747,0.0005708696,0.0011559784,0.0025379078,0.0018889155,0.0045466362],"category_scores_gemma":[0.0068154708,0.0009517451,0.0009327964,0.0007802099,0.0013351433,0.0021701388,0.0026145095,0.0031814277,0.0017853642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023956563,0.00020070956,0.00035845189,0.00020954954,0.00008158907,0.000098094264,0.000090592934,0.7544181,0.0036545165,0.032213774,0.005769426,0.20266567],"study_design_scores_gemma":[0.000015876236,0.000017841281,0.000021311613,0.000004653746,0.0000031944182,0.0000127586645,0.0000034434288,0.9949523,0.00040892945,0.004175416,0.0003795134,0.0000047168414],"about_ca_topic_score_codex":0.0041498365,"about_ca_topic_score_gemma":0.005409098,"teacher_disagreement_score":0.0045466362,"about_ca_system_score_codex":0.00073083444,"about_ca_system_score_gemma":0.0026412145,"threshold_uncertainty_score":0.015210032},"labels":[],"label_agreement":null},{"id":"W2997790181","doi":"10.1609/aaai.v34i04.5821","title":"Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"Division of Electrical, Communications and Cyber Systems; National Science Foundation","keywords":"Regret; Sublinear function; Probabilistic logic; Attack model; Computer science; Bounded function; Expected value; Algorithm; Adversary; Mathematical optimization; Mathematics; Discrete mathematics; Artificial intelligence; Machine learning; Computer security; Statistics","score_opus":0.4478936109603608,"score_gpt":0.4201507851199051,"score_spread":0.027742825840455676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997790181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03041013,0.0004159793,0.9647522,0.00040983193,0.000042906333,0.00006586545,0.00006219766,0.0005298544,0.0033110862],"genre_scores_gemma":[0.8655829,0.00039577088,0.13064879,0.00032379784,0.00008337233,0.00021665823,0.00012314865,0.00011198909,0.0025134753],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976162,0.0009844239,0.00010942007,0.00038791506,0.0004956981,0.00040640534],"domain_scores_gemma":[0.99154574,0.0057905964,0.0011776775,0.00077386596,0.00042717424,0.0002849363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037302228,0.0012205841,0.0019601814,0.0007269806,0.0008370581,0.0019440128,0.0020488182,0.0016820768,0.0013306633],"category_scores_gemma":[0.0123781925,0.00055010803,0.0007663362,0.0011075252,0.0018627004,0.0020034926,0.0021268195,0.0021485905,0.0004426282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013231309,0.00003223642,0.00026685063,0.000033328586,0.000031464002,0.00003129683,0.00003557252,0.96265906,0.0006637439,0.023501094,0.00053901813,0.012074045],"study_design_scores_gemma":[0.000011139499,0.000018294186,0.000033745535,0.000004585763,0.000003622085,0.000013075476,0.0000047008816,0.9881827,0.00022835558,0.011366744,0.0001291817,0.0000037669006],"about_ca_topic_score_codex":0.0027365047,"about_ca_topic_score_gemma":0.0016834507,"teacher_disagreement_score":0.0037302228,"about_ca_system_score_codex":0.0018543792,"about_ca_system_score_gemma":0.0018261558,"threshold_uncertainty_score":0.019727528},"labels":[],"label_agreement":null},{"id":"W2998546572","doi":"10.48550/arxiv.2009.09153","title":"Hidden Incentives for Auto-Induced Distributional Shift","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Incentive; Leverage (statistics); Computer science; Perception; Artificial intelligence; Machine learning; Paradigm shift; Economics; Microeconomics; Psychology","score_opus":0.3450151864016881,"score_gpt":0.33675152972918004,"score_spread":0.008263656672508057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998546572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42526075,0.0004423283,0.5481337,0.007834889,0.00018564724,0.00027139534,0.00045336402,0.0011345278,0.0162834],"genre_scores_gemma":[0.9841949,0.000057018482,0.013853074,0.00038183323,0.000052085077,0.000102141734,0.00005299028,0.00004239578,0.0012636051],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869718,0.007160264,0.0007562248,0.002031788,0.0021629177,0.0009171035],"domain_scores_gemma":[0.85687894,0.09568564,0.014478529,0.024606356,0.0052689523,0.0030815878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018434126,0.00078294874,0.001629367,0.0008103032,0.0011337758,0.0023197841,0.0019837127,0.003538774,0.0058847303],"category_scores_gemma":[0.10358583,0.00068328716,0.00095141865,0.0007272332,0.004581845,0.0045621577,0.0038426768,0.0049819243,0.00063714536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012448052,0.0008635606,0.037004378,0.00047585063,0.0004141861,0.0010479762,0.00095604593,0.17234676,0.013175428,0.6726592,0.0058890986,0.09392275],"study_design_scores_gemma":[0.00021054641,0.00049751543,0.006647985,0.00005616983,0.000058462996,0.00027418765,0.00029243153,0.4571055,0.0059511447,0.5262376,0.0025704752,0.000097975186],"about_ca_topic_score_codex":0.00085247366,"about_ca_topic_score_gemma":0.0008970013,"teacher_disagreement_score":0.018434126,"about_ca_system_score_codex":0.0018658397,"about_ca_system_score_gemma":0.0014478699,"threshold_uncertainty_score":0.09749013},"labels":[],"label_agreement":null},{"id":"W3000867405","doi":"10.1007/978-3-030-33950-0_19","title":"Policy Search on Aggregated State Space for Active Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"Springer proceedings in advanced robotics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Sampling (signal processing); Measure (data warehouse); Adaptive sampling; Computer science; Scalar (mathematics); Space (punctuation); Field (mathematics); State space; Mathematical optimization; Algorithm; Mathematics; Data mining; Statistics; Geometry; Computer vision; Pure mathematics","score_opus":0.15193684302990682,"score_gpt":0.42441289845431784,"score_spread":0.272476055424411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000867405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004077905,0.00042492402,0.99252194,0.0001549804,0.00007043196,0.000024177694,0.00004697345,0.00013472908,0.002544009],"genre_scores_gemma":[0.5590859,0.0015315504,0.4199421,0.00036950724,0.00050501915,0.0005436893,0.00062889507,0.00035518545,0.017038094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991013,0.0004385472,0.000049627863,0.00013264571,0.00019754715,0.00008024099],"domain_scores_gemma":[0.9965395,0.0028287796,0.00010638275,0.00019762438,0.0002350763,0.000092580434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023065722,0.0010421064,0.0021013392,0.00088825333,0.0005148351,0.0018758195,0.001678872,0.0013331496,0.004958308],"category_scores_gemma":[0.00746785,0.0008289132,0.0011227978,0.00146891,0.0012033111,0.002322422,0.0023846885,0.0027043908,0.0006462747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012294763,0.00006679251,0.00032449092,0.00016638431,0.00008296417,0.000042473683,0.00008087693,0.8021519,0.000725817,0.11213183,0.0030540498,0.08104945],"study_design_scores_gemma":[0.0000039308165,0.000008334263,0.0000239939,0.000007185447,0.0000034441648,0.00000429124,0.0000032382623,0.97696143,0.000073140596,0.022632256,0.00027661343,0.0000021434798],"about_ca_topic_score_codex":0.0036015797,"about_ca_topic_score_gemma":0.0032394396,"teacher_disagreement_score":0.004958308,"about_ca_system_score_codex":0.001368671,"about_ca_system_score_gemma":0.0011202076,"threshold_uncertainty_score":0.016587198},"labels":[],"label_agreement":null},{"id":"W3004262408","doi":"10.1109/lcsys.2020.2989110","title":"Dynamic and Distributed Online Convex Optimization for Demand Response of Commercial Buildings","year":2020,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency - Energy","keywords":"Regret; Demand response; Convex optimization; Upper and lower bounds; Time horizon; Regular polygon; Dual (grammatical number)","score_opus":0.05587819967213528,"score_gpt":0.3638840339324756,"score_spread":0.30800583426034034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004262408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028201617,0.00026354508,0.9670619,0.0003602009,0.000046224915,0.000028693355,0.00006527467,0.0001972785,0.0037753358],"genre_scores_gemma":[0.95379794,0.0001447858,0.04403347,0.00009461758,0.000041294894,0.00006155691,0.00007652368,0.00007147608,0.0016782926],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992648,0.00027946467,0.000021575233,0.00014393774,0.00016249965,0.00012777158],"domain_scores_gemma":[0.9982905,0.0011836936,0.00015330996,0.00012272225,0.00018122685,0.000068577145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011263598,0.0007631181,0.00084823306,0.0002175075,0.00032157355,0.00088548,0.000895826,0.0006587778,0.0021801693],"category_scores_gemma":[0.0041302927,0.00035025706,0.0004241756,0.0004943407,0.00063550245,0.0008621065,0.00083895726,0.0012311912,0.00023050143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041218158,0.000026931022,0.00015136389,0.000027781929,0.000009535768,0.000021823927,0.000012837165,0.98518246,0.00056391465,0.0051073264,0.00047594777,0.008378878],"study_design_scores_gemma":[0.0000021849123,0.000004775697,0.000024208366,6.130125e-7,8.2609665e-7,0.0000020949467,0.000002015938,0.99864644,0.00010379931,0.0011421879,0.000070023794,8.631228e-7],"about_ca_topic_score_codex":0.0048921956,"about_ca_topic_score_gemma":0.0036979178,"teacher_disagreement_score":0.0048921956,"about_ca_system_score_codex":0.001020494,"about_ca_system_score_gemma":0.0009440118,"threshold_uncertainty_score":0.009727478},"labels":[],"label_agreement":null},{"id":"W3005661940","doi":"10.1609/aaai.v35i8.16901","title":"Regret Bounds for Batched Bandits","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Office of Naval Research; Institut de Valorisation des Données; Canada First Research Excellence Fund; National Science Foundation","keywords":"Regret; Logarithm; Mathematical optimization; Simple (philosophy); Computer science; Multi-armed bandit; Mathematics; Algorithm; Machine learning","score_opus":0.349858033997507,"score_gpt":0.4633447509370407,"score_spread":0.11348671693953372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005661940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011941307,0.0021444762,0.97191554,0.0013733556,0.00031664508,0.0001893313,0.00047132943,0.0012662652,0.010381696],"genre_scores_gemma":[0.53100556,0.003835616,0.44121245,0.0018187301,0.0012238134,0.0012458748,0.0013695594,0.001442951,0.016845463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99263024,0.0022231126,0.0003914096,0.0014564407,0.0022172497,0.0010814888],"domain_scores_gemma":[0.9605368,0.028829664,0.0024857523,0.0046336316,0.0023702346,0.0011438818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010286466,0.004038423,0.003157027,0.0015978013,0.0017765539,0.005220371,0.0057680896,0.003409448,0.011019529],"category_scores_gemma":[0.04718895,0.0014272878,0.002570681,0.0024618637,0.0033665453,0.009119267,0.0045363596,0.008738587,0.0029683204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011207574,0.00042270892,0.0011110583,0.00049121026,0.00018663799,0.0001376857,0.00019447149,0.75021166,0.004707093,0.1664146,0.01086735,0.06413471],"study_design_scores_gemma":[0.00006229535,0.00008062064,0.00020132808,0.000055906785,0.000041470234,0.000043804972,0.000016595284,0.9140266,0.0013959979,0.082645684,0.0014070488,0.00002262277],"about_ca_topic_score_codex":0.0029563818,"about_ca_topic_score_gemma":0.0031129655,"teacher_disagreement_score":0.011019529,"about_ca_system_score_codex":0.0054177633,"about_ca_system_score_gemma":0.0035212997,"threshold_uncertainty_score":0.054400682},"labels":[],"label_agreement":null},{"id":"W3007722162","doi":"10.1109/tsp.2021.3089822","title":"Safe Linear Thompson Sampling With Side Information","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Signal Processing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Office of the President, University of California","keywords":"Frequentist inference; Regret; Thompson sampling; Set (abstract data type); Reliability (semiconductor); Linear programming; Mathematics; Computer science; Algorithm; Mathematical optimization; Sampling (signal processing); Combinatorics; Bayesian probability; Statistics; Bayesian inference","score_opus":0.14129229971825966,"score_gpt":0.41763110013686366,"score_spread":0.27633880041860404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007722162","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03118024,0.0003423942,0.96346384,0.00046164932,0.00004635534,0.00011093058,0.00011881087,0.00078735605,0.003488481],"genre_scores_gemma":[0.80132806,0.00030846207,0.18967007,0.00050341437,0.00012208891,0.00044688812,0.0004008734,0.00024245662,0.006977745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949602,0.0025513314,0.00016469484,0.0008035711,0.0009049245,0.00061510777],"domain_scores_gemma":[0.97923744,0.015492386,0.0014947079,0.00218096,0.0010091622,0.0005854019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054951813,0.001274923,0.0019483671,0.00077977503,0.0007835825,0.0018002087,0.0020526424,0.0016881501,0.0034792293],"category_scores_gemma":[0.022531291,0.0008049265,0.000996442,0.0009513298,0.0025146275,0.0024514124,0.0021138892,0.0025629764,0.0010210206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082176324,0.00011538041,0.001319591,0.00013593514,0.000085771164,0.00013253735,0.00012184044,0.854416,0.001878525,0.09458599,0.002514564,0.043872096],"study_design_scores_gemma":[0.000035165664,0.00005593088,0.00007109216,0.000009175418,0.000008657594,0.00001665553,0.000006821753,0.9660701,0.00071731344,0.032732017,0.00026967016,0.0000073513606],"about_ca_topic_score_codex":0.0031977757,"about_ca_topic_score_gemma":0.003209383,"teacher_disagreement_score":0.0054951813,"about_ca_system_score_codex":0.0022638352,"about_ca_system_score_gemma":0.0032025091,"threshold_uncertainty_score":0.029061615},"labels":[],"label_agreement":null},{"id":"W3008672633","doi":"10.4171/msl/38","title":"Optimal anytime regret with two experts","year":2023,"lang":"en","type":"article","venue":"Mathematical Statistics and Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Minimax; Time horizon; Constant (computer programming); Mathematical optimization; Computer science; Horizon; Mathematics; Machine learning","score_opus":0.09688300321347229,"score_gpt":0.43732907788875097,"score_spread":0.34044607467527865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008672633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075221196,0.0012329658,0.90816337,0.0029253673,0.00025422743,0.00010145844,0.00022533465,0.00038920972,0.011486895],"genre_scores_gemma":[0.8869003,0.00058081077,0.099682264,0.0006004538,0.00034349714,0.00016703254,0.0001957156,0.000085852094,0.011444048],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972156,0.0010847178,0.00008754189,0.0006957982,0.0004185042,0.000497837],"domain_scores_gemma":[0.9911924,0.006419622,0.00076907297,0.0006411142,0.00044917464,0.000528686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004373169,0.001579,0.0022267078,0.00046098477,0.0006960247,0.0015397524,0.0024166235,0.0029170243,0.0034693796],"category_scores_gemma":[0.018136935,0.00056407356,0.00095258106,0.0006163915,0.0018960562,0.0027920324,0.0018561073,0.0029542532,0.00059890136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072183326,0.00018336743,0.0008832463,0.00016497099,0.00010395831,0.00018817902,0.00015211207,0.8524062,0.0013567891,0.1153092,0.0035768456,0.024953302],"study_design_scores_gemma":[0.00006201493,0.00007803536,0.00017341605,0.000016963126,0.000016425849,0.000030352025,0.000015915575,0.93801814,0.0005461026,0.06047417,0.00055289123,0.000015548048],"about_ca_topic_score_codex":0.0027595283,"about_ca_topic_score_gemma":0.0015680208,"teacher_disagreement_score":0.004373169,"about_ca_system_score_codex":0.0017878168,"about_ca_system_score_gemma":0.0017446829,"threshold_uncertainty_score":0.023127794},"labels":[],"label_agreement":null},{"id":"W3009214291","doi":"10.48550/arxiv.2003.03456","title":"A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Maximization; Economics; Utility maximization; Microeconomics; Keynesian economics; Mathematical economics","score_opus":0.29663554765176436,"score_gpt":0.31414571951151904,"score_spread":0.017510171859754675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009214291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06936871,0.0010148233,0.92042905,0.0015081521,0.000088203815,0.0001597186,0.00016925871,0.0005006003,0.0067614964],"genre_scores_gemma":[0.7698567,0.0007079469,0.22002836,0.0005300973,0.00015547688,0.00044864952,0.00026343545,0.00023946348,0.007769883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997727,0.0010388944,0.00009207457,0.00043332746,0.00035287644,0.0003558385],"domain_scores_gemma":[0.9915412,0.00657236,0.0007071605,0.00034977548,0.00034084532,0.0004885984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048269103,0.0018021901,0.0027841297,0.00076708116,0.0007304048,0.0021037683,0.0021588986,0.0023676879,0.004635076],"category_scores_gemma":[0.014711151,0.0010108491,0.0009938376,0.0012519993,0.0020454885,0.002837814,0.002193286,0.0030061686,0.00067864795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045332013,0.00011805787,0.0006858554,0.00012784117,0.000070325485,0.00007643484,0.00009491926,0.9318934,0.00093246356,0.03924291,0.001546045,0.024758369],"study_design_scores_gemma":[0.000044828706,0.00006553109,0.00009684608,0.000019775855,0.000012916554,0.000016100686,0.000008452556,0.97565097,0.00033622878,0.023373375,0.0003662976,0.00000867159],"about_ca_topic_score_codex":0.004638384,"about_ca_topic_score_gemma":0.0029623501,"teacher_disagreement_score":0.0048269103,"about_ca_system_score_codex":0.002051794,"about_ca_system_score_gemma":0.0023621686,"threshold_uncertainty_score":0.025527418},"labels":[],"label_agreement":null},{"id":"W3012851896","doi":"","title":"Convergence of Gradient Methods on Bilinear Zero-Sum Games","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convergence (economics); Bilinear interpolation; Zero (linguistics); Applied mathematics; Adversarial system; Computer science; Mathematical optimization; Generative grammar; Zero-sum game; Mathematics; Algorithm; Artificial intelligence; Nash equilibrium","score_opus":0.35221709293036835,"score_gpt":0.5526990798639185,"score_spread":0.20048198693355018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012851896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018833358,0.00087351265,0.9678403,0.0008402973,0.00013399686,0.00013157015,0.00011527833,0.00019935943,0.011032324],"genre_scores_gemma":[0.6800381,0.0023286438,0.28658888,0.0011384785,0.00034461264,0.001033155,0.00043416943,0.0008622916,0.027231626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780446,0.0012365411,0.00009517493,0.0002929009,0.00033213387,0.0002387785],"domain_scores_gemma":[0.9873784,0.01031341,0.0004674549,0.00047804174,0.00087376474,0.0004889847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005609209,0.0022608968,0.001804334,0.0011938051,0.00074960035,0.0022923683,0.0020174426,0.001890107,0.0069489037],"category_scores_gemma":[0.029234182,0.00080793886,0.0011932509,0.0007412642,0.003203561,0.004297947,0.004583231,0.004341471,0.0011584129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021614064,0.00012729541,0.0007964975,0.0003436111,0.00008406398,0.00010797199,0.0002677524,0.3030055,0.001439838,0.65894675,0.0043822154,0.030282263],"study_design_scores_gemma":[0.000022652916,0.000041313968,0.00007145225,0.00004380131,0.0000097156835,0.000022536364,0.000032629036,0.76987576,0.00038903023,0.22859326,0.0008839746,0.000013945812],"about_ca_topic_score_codex":0.0021110715,"about_ca_topic_score_gemma":0.0019063097,"teacher_disagreement_score":0.0069489037,"about_ca_system_score_codex":0.0018985423,"about_ca_system_score_gemma":0.0018368862,"threshold_uncertainty_score":0.029664695},"labels":[],"label_agreement":null},{"id":"W3012922890","doi":"10.1007/s10614-021-10119-4","title":"Reinforcement Learning in Economics and Finance","year":2021,"lang":"en","type":"preprint","venue":"Computational Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; AXA Research Fund","keywords":"Reinforcement learning; Action (physics); Computer science; Set (abstract data type); Artificial intelligence; Time horizon; Q-learning; Behavioral economics; Order (exchange); Reinforcement; Process (computing); Term (time); Temporal difference learning; Economics; Microeconomics; Psychology; Finance; Social psychology","score_opus":0.08548769842633776,"score_gpt":0.3792800501201351,"score_spread":0.29379235169379736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012922890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037380695,0.04771404,0.83972377,0.03443277,0.0017003057,0.0000632796,0.0002719231,0.00033195483,0.03838134],"genre_scores_gemma":[0.78888077,0.027584262,0.140045,0.0017396561,0.0045929854,0.00025525945,0.00032964328,0.00020755338,0.036364786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989754,0.00067441404,0.00002974766,0.00009446757,0.0001746251,0.000051384694],"domain_scores_gemma":[0.9926292,0.006344863,0.00022924968,0.00022984295,0.00038402976,0.00018295673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022575015,0.00091465155,0.0014151138,0.0011086172,0.0005877785,0.0034017314,0.00093714363,0.0026495745,0.0064250943],"category_scores_gemma":[0.015012399,0.0005567176,0.00048388136,0.0020416754,0.0023318822,0.004218115,0.0012053847,0.00388472,0.0006554861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030079762,0.000050387815,0.00040419714,0.00016286559,0.00003879617,0.000026921058,0.000055645283,0.029257767,0.00015270885,0.9350365,0.0058559747,0.028928095],"study_design_scores_gemma":[0.000014493703,0.0000050021827,0.00015483765,0.00002445683,0.000005568632,0.000008293582,0.000014557495,0.10221118,0.000065516884,0.8942791,0.0032121113,0.000004923856],"about_ca_topic_score_codex":0.0042966288,"about_ca_topic_score_gemma":0.002037437,"teacher_disagreement_score":0.0064250943,"about_ca_system_score_codex":0.002353121,"about_ca_system_score_gemma":0.0014616186,"threshold_uncertainty_score":0.021494031},"labels":[],"label_agreement":null},{"id":"W3017369915","doi":"10.1287/moor.2019.1019","title":"Variance Regularization in Sequential Bayesian Optimization","year":2020,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regularization (linguistics); Mathematical optimization; Bayesian probability; A priori and a posteriori; Mathematics; Optimization problem; Computer science; Dynamic programming; Algorithm; Artificial intelligence","score_opus":0.29304720584955735,"score_gpt":0.49850097107321184,"score_spread":0.2054537652236545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017369915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044605955,0.0008772681,0.98427147,0.0013064159,0.000071817696,0.00003032435,0.0000768768,0.00015438034,0.008750939],"genre_scores_gemma":[0.54799354,0.003068508,0.42065424,0.0017273343,0.00062702567,0.00065381575,0.0005505936,0.0006536646,0.024071306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650013,0.0016643088,0.00011825088,0.0004837951,0.0009962743,0.00023727948],"domain_scores_gemma":[0.98848766,0.009253497,0.00065792195,0.00048752647,0.0008737509,0.00023968039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062415013,0.0014507911,0.0014524506,0.0011171183,0.00078682497,0.0023104257,0.001846852,0.0024074453,0.0041399226],"category_scores_gemma":[0.025657509,0.0009810774,0.0011593661,0.00115313,0.0032681713,0.0032421614,0.0027498219,0.0038687496,0.00068384607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038890936,0.00002370136,0.000540726,0.00014731484,0.00005167604,0.000073153635,0.00008820462,0.4815387,0.0005055535,0.49870092,0.0027442505,0.015546849],"study_design_scores_gemma":[0.000008193439,0.0000101234045,0.00010616165,0.000030415591,0.000005948071,0.000012900357,0.000009865592,0.76161176,0.00013907257,0.23675561,0.0012995835,0.000010465635],"about_ca_topic_score_codex":0.0077394997,"about_ca_topic_score_gemma":0.0066224,"teacher_disagreement_score":0.0077394997,"about_ca_system_score_codex":0.003348523,"about_ca_system_score_gemma":0.0028671012,"threshold_uncertainty_score":0.033008575},"labels":[],"label_agreement":null},{"id":"W3023384417","doi":"10.1109/isit45174.2021.9518176","title":"Regret Bounds for Safe Gaussian Process Bandit Optimization","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Mathematical optimization; Bayesian optimization; Computer science; Stochastic game; Gaussian process; Set (abstract data type); Constraint (computer-aided design); Function (biology); Bayesian probability; Gaussian; Mathematics; Artificial intelligence; Machine learning; Mathematical economics","score_opus":0.1769952684360234,"score_gpt":0.4986446823155516,"score_spread":0.32164941387952817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023384417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013071571,0.0020965694,0.9718916,0.0014923554,0.000097790864,0.00006611341,0.00015612159,0.0004893536,0.010638559],"genre_scores_gemma":[0.7280462,0.0034151613,0.25394794,0.0015483731,0.00044846538,0.00061414274,0.0007750442,0.0008727546,0.010332012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960521,0.0018702094,0.00012816518,0.0003904209,0.0010952064,0.0004639554],"domain_scores_gemma":[0.9655074,0.029513113,0.0013485206,0.0013215982,0.0016915203,0.0006179883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008742636,0.0021643497,0.0020764747,0.0011456655,0.0012332939,0.0032551312,0.0023370986,0.002499236,0.004917461],"category_scores_gemma":[0.04400567,0.0007757812,0.0011266845,0.0012651514,0.004184685,0.0032582066,0.0035360726,0.0055746627,0.0011692547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015588588,0.000053536274,0.0005751355,0.00012956526,0.00004568518,0.00005327226,0.00007851737,0.8787871,0.00039299813,0.1015497,0.0022166609,0.015961977],"study_design_scores_gemma":[0.00000907281,0.000017221619,0.000075289616,0.000027369206,0.0000070305155,0.000010297121,0.000010806686,0.9585309,0.00021897486,0.04073975,0.00034814948,0.0000050907834],"about_ca_topic_score_codex":0.005050872,"about_ca_topic_score_gemma":0.0034002492,"teacher_disagreement_score":0.008742636,"about_ca_system_score_codex":0.0035185302,"about_ca_system_score_gemma":0.0027018136,"threshold_uncertainty_score":0.04623598},"labels":[],"label_agreement":null},{"id":"W3028421523","doi":"10.1016/j.jeconom.2020.04.025","title":"The fast iterated bootstrap","year":2020,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Iterated function; Series (stratigraphy); Mathematics; Algorithm; Applied mathematics; Computer science","score_opus":0.602328803079659,"score_gpt":0.4419714958789592,"score_spread":0.1603573072006998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028421523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048927967,0.00082862854,0.9892511,0.00033943926,0.00021161213,0.000047034,0.000071007504,0.00046184825,0.0038965733],"genre_scores_gemma":[0.2246883,0.0013437921,0.7596486,0.000359029,0.0009545948,0.0004086271,0.00048872456,0.0008177141,0.011290574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99264175,0.0052206367,0.00022825955,0.000537786,0.0011361453,0.00023542084],"domain_scores_gemma":[0.97470677,0.015824897,0.0006963114,0.0059151202,0.0024886671,0.0003681968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010887955,0.0010901251,0.0020541374,0.0023903786,0.001267006,0.002854154,0.002234307,0.0021753316,0.0075741904],"category_scores_gemma":[0.053884715,0.0013225381,0.0019669002,0.0018282327,0.0022808567,0.0042034914,0.0030859003,0.0040410436,0.003411164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041278685,0.00013202158,0.0029717793,0.00029522993,0.00040826618,0.00038075063,0.00028610995,0.086502865,0.0033800278,0.5709129,0.011643266,0.322674],"study_design_scores_gemma":[0.000060702132,0.00007670841,0.0009505527,0.00007012372,0.00007738684,0.00026976282,0.000032101278,0.66981363,0.001563691,0.31596845,0.011064326,0.0000525504],"about_ca_topic_score_codex":0.0018839065,"about_ca_topic_score_gemma":0.0018846144,"teacher_disagreement_score":0.010887955,"about_ca_system_score_codex":0.00073584035,"about_ca_system_score_gemma":0.0016921945,"threshold_uncertainty_score":0.057581663},"labels":[],"label_agreement":null},{"id":"W3029510736","doi":"10.1016/j.artint.2020.103328","title":"On the equivalence of optimal recommendation sets and myopically optimal query sets","year":2020,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta; Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Computer science; Recommender system; Preference elicitation; Set (abstract data type); Preference; Equivalence (formal languages); Expected utility hypothesis; Information retrieval; Data mining; Machine learning; Mathematics","score_opus":0.33583112151467903,"score_gpt":0.46472001396090457,"score_spread":0.12888889244622553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029510736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15840447,0.0043874304,0.7574312,0.011361921,0.00040596392,0.00046002486,0.0015545085,0.0005032452,0.06549119],"genre_scores_gemma":[0.8941832,0.0029577815,0.089859635,0.0024564418,0.0011195061,0.0006455339,0.0010647461,0.0004369634,0.007276177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9752364,0.01378503,0.0012288835,0.002952364,0.00511448,0.0016829196],"domain_scores_gemma":[0.7726107,0.20109366,0.0059871776,0.012737734,0.0050667278,0.0025039208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024234038,0.001922211,0.0062020975,0.0031409287,0.0025037574,0.00836717,0.005756236,0.005016861,0.013469974],"category_scores_gemma":[0.15727177,0.002130711,0.0020180505,0.0042251446,0.009101003,0.019118724,0.009613823,0.0077326433,0.0008105507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084473204,0.00042292886,0.0013556329,0.00034976972,0.00017494366,0.000093644965,0.0005294146,0.10622909,0.0006434305,0.8473257,0.0054386146,0.03659214],"study_design_scores_gemma":[0.00011749924,0.00013016703,0.0005110846,0.000088545945,0.00003713239,0.00006257423,0.000090241396,0.19125725,0.0002803888,0.8065047,0.000888898,0.000031427324],"about_ca_topic_score_codex":0.0033889522,"about_ca_topic_score_gemma":0.002331646,"teacher_disagreement_score":0.024234038,"about_ca_system_score_codex":0.0052933567,"about_ca_system_score_gemma":0.0040033455,"threshold_uncertainty_score":0.1281634},"labels":[],"label_agreement":null},{"id":"W3033089188","doi":"10.48550/arxiv.2006.02585","title":"Online mirror descent and dual averaging: keeping pace in the dynamic case","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pace; Dual (grammatical number); Descent (aeronautics); Stochastic gradient descent; Computer science; Control theory (sociology); Artificial intelligence; Geodesy; Aerospace engineering; Engineering; Geography; Art","score_opus":0.31241003091884384,"score_gpt":0.3382989221110649,"score_spread":0.025888891192221042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033089188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027906936,0.0004283914,0.9647485,0.00082398386,0.000112353984,0.000046754354,0.000057945792,0.0003325526,0.0055425465],"genre_scores_gemma":[0.76384175,0.00044987194,0.22796683,0.0006146323,0.0002408448,0.00019606086,0.00014707587,0.00023841897,0.0063045286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984687,0.0006360555,0.000059074482,0.00035716587,0.00030468838,0.00017426841],"domain_scores_gemma":[0.99515814,0.0028108268,0.0004084461,0.0009936913,0.0003942959,0.00023454012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00336316,0.00080438284,0.0012234948,0.00047940618,0.00076588,0.0017065462,0.0016139861,0.0014470208,0.0023170344],"category_scores_gemma":[0.017158413,0.00055826176,0.00064630987,0.0006357072,0.0017872857,0.0030194204,0.0024909724,0.0024226764,0.0005357484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000671299,0.00026894838,0.0030384779,0.00021122444,0.00013219494,0.00023761924,0.00023776443,0.41934118,0.006849542,0.39598235,0.006215092,0.16681431],"study_design_scores_gemma":[0.000027701288,0.00005645945,0.0001598145,0.000012122427,0.000010276149,0.00004382297,0.000014983168,0.9198319,0.001445921,0.077349566,0.0010364897,0.000011001014],"about_ca_topic_score_codex":0.0014870146,"about_ca_topic_score_gemma":0.0014935248,"teacher_disagreement_score":0.00336316,"about_ca_system_score_codex":0.0009225062,"about_ca_system_score_gemma":0.0014914881,"threshold_uncertainty_score":0.017786324},"labels":[],"label_agreement":null},{"id":"W3035741541","doi":"","title":"Fiduciary Bandits","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fiduciary; Recommender system; Computer science; Incentive; Ask price; Constraint (computer-aided design); Action (physics); Face (sociological concept); Ex-ante; Operations research; Mathematical optimization; Risk analysis (engineering); Economics; Microeconomics; Business; Machine learning; Engineering; Mathematics; Finance; Law","score_opus":0.30271457978874516,"score_gpt":0.47533798022670787,"score_spread":0.1726234004379627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035741541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045438077,0.00076805265,0.93379176,0.0015651957,0.00012202655,0.00014461785,0.00022960812,0.0007040644,0.017236656],"genre_scores_gemma":[0.8279089,0.0007444768,0.15449029,0.0005883949,0.00019788975,0.00045441277,0.00026596134,0.0001940872,0.015155568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99577147,0.0019377447,0.0002262809,0.00086597766,0.00067990815,0.0005186481],"domain_scores_gemma":[0.9872111,0.008400509,0.0012100431,0.0018120145,0.0009335528,0.00043271776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047036577,0.0015250215,0.002799682,0.00088273035,0.0013284202,0.0031900227,0.002553753,0.0035830305,0.005087982],"category_scores_gemma":[0.027818516,0.0008528181,0.0010182924,0.0011150877,0.0031419843,0.0040536486,0.0025936142,0.0035533074,0.0017600474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045696163,0.00014454982,0.0014603512,0.0002857968,0.00012951974,0.00018625123,0.0002995722,0.45299953,0.0024265784,0.47863448,0.008096405,0.054879997],"study_design_scores_gemma":[0.00006687687,0.000055504668,0.00019308309,0.000046471916,0.000020305484,0.00008135722,0.000031740696,0.79898006,0.00066606747,0.19789074,0.001942627,0.000025184212],"about_ca_topic_score_codex":0.00240722,"about_ca_topic_score_gemma":0.0021928414,"teacher_disagreement_score":0.005087982,"about_ca_system_score_codex":0.0021110233,"about_ca_system_score_gemma":0.0018167754,"threshold_uncertainty_score":0.024875581},"labels":[],"label_agreement":null},{"id":"W3037507370","doi":"10.65109/hjfz7394","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of ƒ-Regression Counterfactual Regret Minimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Softmax function; Counterfactual thinking; Approximation error; Function approximation; Reinforcement learning; Perfect information; Approximation algorithm; Mathematical optimization; Computer science; Function (biology); Mathematics; Applied mathematics; Mathematical economics; Artificial intelligence; Artificial neural network; Machine learning","score_opus":0.19774246992382122,"score_gpt":0.44301282600521824,"score_spread":0.24527035608139702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037507370","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016372452,0.00051841466,0.976732,0.00072597835,0.000040355255,0.00010596824,0.000056450303,0.00024853865,0.0051998063],"genre_scores_gemma":[0.64591545,0.001103678,0.34439778,0.00091800315,0.00014969664,0.00075139833,0.00023210578,0.00042140664,0.006110574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99297595,0.0039121895,0.00023889066,0.00079448853,0.001457096,0.0006214544],"domain_scores_gemma":[0.97680354,0.01798653,0.0016095253,0.0020414859,0.001081347,0.00047764918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013678686,0.0022653101,0.0023338832,0.001527394,0.00088612904,0.0026829282,0.0035658488,0.0026125642,0.0037460274],"category_scores_gemma":[0.058848124,0.0008545614,0.0018719219,0.001529388,0.003462533,0.0058288425,0.003200648,0.0059361258,0.00059632736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014510217,0.0001228441,0.0008457542,0.00013073244,0.000089100446,0.00006338501,0.00015116108,0.718221,0.0007760544,0.25268507,0.0016438781,0.02512602],"study_design_scores_gemma":[0.000014864191,0.000044607867,0.000093239905,0.00003124567,0.000015063248,0.00002148067,0.000016759024,0.95197505,0.000344197,0.04692102,0.0005108246,0.000011697632],"about_ca_topic_score_codex":0.0032509349,"about_ca_topic_score_gemma":0.0024418542,"teacher_disagreement_score":0.013678686,"about_ca_system_score_codex":0.003966522,"about_ca_system_score_gemma":0.0023848792,"threshold_uncertainty_score":0.07234067},"labels":[],"label_agreement":null},{"id":"W3041060701","doi":"10.48550/arxiv.2007.05477","title":"Exponential Convergence of Gradient Methods in Concave Network Zero-sum Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zero-sum game; Zero (linguistics); Lipschitz continuity; Generalization; Convergence (economics); Mathematics; Nash equilibrium; Regular polygon; Fictitious play; Applied mathematics; Mathematical optimization; Mathematical economics; Pure mathematics; Mathematical analysis","score_opus":0.3396832296260758,"score_gpt":0.3713927499233881,"score_spread":0.03170952029731233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041060701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06556363,0.00030670498,0.9286494,0.00047107658,0.000037561527,0.00008863363,0.00004401891,0.00020363185,0.0046353308],"genre_scores_gemma":[0.8792665,0.00035545955,0.11547388,0.00019874699,0.000040120758,0.0002191446,0.000107121516,0.0001380602,0.0042009787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985625,0.0007949167,0.000044215616,0.00018890813,0.00024001097,0.00016957519],"domain_scores_gemma":[0.98716986,0.010935953,0.00055436837,0.00041963515,0.000552511,0.00036764616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041717654,0.0013873304,0.001234495,0.00076135056,0.0005940639,0.0014377485,0.0016610197,0.0011022295,0.0020003696],"category_scores_gemma":[0.020523656,0.00052371825,0.00060608465,0.0005106085,0.0023480789,0.0021046335,0.0023904014,0.0020645503,0.0003606643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001364177,0.000052950323,0.0010707092,0.00007117719,0.000038744307,0.0000626066,0.00014305071,0.89873,0.000973455,0.08624941,0.0006030803,0.011868485],"study_design_scores_gemma":[0.0000058625437,0.000011426381,0.00003584602,0.0000050952544,0.0000023101204,0.0000060830785,0.000008152419,0.98229593,0.00024461967,0.017289147,0.00009293796,0.0000026799962],"about_ca_topic_score_codex":0.0035101022,"about_ca_topic_score_gemma":0.0028042987,"teacher_disagreement_score":0.0041717654,"about_ca_system_score_codex":0.0017753061,"about_ca_system_score_gemma":0.0013235587,"threshold_uncertainty_score":0.02206266},"labels":[],"label_agreement":null},{"id":"W3043040027","doi":"10.48550/arxiv.2007.06699","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Sublinear function; Multi-armed bandit; Computer science; Nash equilibrium; Mathematical optimization; Mathematical economics; Social Welfare; Artificial intelligence; Algorithm; Mathematics; Machine learning; Law; Discrete mathematics; Political science","score_opus":0.5827502268841479,"score_gpt":0.3803343093108259,"score_spread":0.202415917573322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043040027","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009288022,0.00048008724,0.9865226,0.00036500202,0.00007804511,0.000064870714,0.000042379408,0.00017337338,0.0029856598],"genre_scores_gemma":[0.6820646,0.0007052302,0.3085826,0.000446791,0.00019007077,0.0005062163,0.00012852262,0.00012980629,0.007246164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974916,0.0011854013,0.00010931817,0.00041112106,0.00045727557,0.0003452797],"domain_scores_gemma":[0.9945156,0.003950906,0.00040408765,0.0005353445,0.0003418686,0.00025222346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004665422,0.0014280343,0.0017092093,0.00080766366,0.0011113648,0.0023351791,0.0024191444,0.0021878725,0.003334494],"category_scores_gemma":[0.011744435,0.0005405312,0.0008426885,0.0010231974,0.0022938324,0.0024123,0.0019216093,0.0022763493,0.00061615213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014358327,0.00009258531,0.00038998012,0.00008932666,0.000056296372,0.000047319798,0.0000935939,0.7917121,0.0006609121,0.17702712,0.0016941526,0.027992994],"study_design_scores_gemma":[0.000027700686,0.000021558322,0.00003694402,0.0000129911,0.0000073197284,0.000009884098,0.000009897662,0.9045684,0.00025753246,0.094359584,0.000681521,0.000006659396],"about_ca_topic_score_codex":0.002359461,"about_ca_topic_score_gemma":0.0022950745,"teacher_disagreement_score":0.004665422,"about_ca_system_score_codex":0.0023247756,"about_ca_system_score_gemma":0.0019438732,"threshold_uncertainty_score":0.024673402},"labels":[],"label_agreement":null},{"id":"W3043739328","doi":"10.65109/laqv4730","title":"The Effect of Strategic Noise in Linear Regression","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nash equilibrium; Computer science; Bounded function; Regularization (linguistics); Outcome (game theory); Focus (optics); Mathematical economics; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics","score_opus":0.21707434903919445,"score_gpt":0.49515051276018374,"score_spread":0.2780761637209893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043739328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06466813,0.0012097743,0.91093683,0.005863948,0.00017736183,0.00017205406,0.00015803965,0.00030141277,0.016512513],"genre_scores_gemma":[0.8715417,0.0013405868,0.116290696,0.002397152,0.00044036662,0.00043767746,0.00017635417,0.00024665182,0.007128724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9784259,0.013981653,0.00075265195,0.0026567862,0.0031055943,0.0010774129],"domain_scores_gemma":[0.8042353,0.1604516,0.013656131,0.014643836,0.0049951933,0.0020179162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021497853,0.0019526585,0.0023679277,0.0014784724,0.0021112142,0.005417226,0.0026459554,0.004384132,0.004796471],"category_scores_gemma":[0.14960368,0.0012242694,0.0013152437,0.0016628886,0.008001279,0.008032865,0.0056819483,0.006315849,0.0010005697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047156238,0.00019700792,0.0058841202,0.00033016887,0.00026015835,0.00029461703,0.0005952609,0.14526717,0.0037457463,0.80967104,0.0031747231,0.030108582],"study_design_scores_gemma":[0.000111763635,0.00022337673,0.0009899089,0.00010019116,0.000069997885,0.00012081511,0.00013079421,0.41596758,0.0024512904,0.5771218,0.0026513464,0.00006110823],"about_ca_topic_score_codex":0.0019536857,"about_ca_topic_score_gemma":0.0020683282,"teacher_disagreement_score":0.021497853,"about_ca_system_score_codex":0.002611727,"about_ca_system_score_gemma":0.0028094384,"threshold_uncertainty_score":0.11369294},"labels":[],"label_agreement":null},{"id":"W3043761458","doi":"","title":"Beyond Prioritized Replay: Sampling States in Model-Based RL via Simulated Priorities","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Sampling (signal processing); Key (lock); Benchmark (surveying); Equivalence (formal languages); Sample (material); Ideal (ethics); Mathematical optimization; Sampling bias; Sample size determination; Mathematics; Statistics; Telecommunications","score_opus":0.21948416268667387,"score_gpt":0.32630614007900377,"score_spread":0.1068219773923299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043761458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024427233,0.0003764829,0.97258794,0.0003945667,0.000046965382,0.00008430815,0.0000477515,0.00061461225,0.0014200149],"genre_scores_gemma":[0.8498125,0.0002862851,0.14656468,0.00044193995,0.00009164088,0.00024782453,0.00014174437,0.00017375033,0.002239598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815035,0.0010145947,0.000075613825,0.00031910356,0.00027784973,0.00016254908],"domain_scores_gemma":[0.9910114,0.006703315,0.0005154109,0.0007758166,0.00057381834,0.00042028876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004339144,0.001408397,0.0017221966,0.0007255864,0.00063292723,0.0016320951,0.0025657706,0.0016187562,0.0026919139],"category_scores_gemma":[0.021918088,0.0007289224,0.0006689079,0.00061406306,0.001423736,0.0033772674,0.002631898,0.0028561347,0.0004933242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005637576,0.00016040116,0.0015604022,0.00017857541,0.00010687527,0.00011141571,0.0003189588,0.9012084,0.0018680058,0.028916199,0.0016844705,0.06332258],"study_design_scores_gemma":[0.000034369197,0.000069586305,0.0000720758,0.000012329081,0.0000095184305,0.000017934279,0.000018085144,0.9860845,0.0004601388,0.012916263,0.00029726836,0.000007863755],"about_ca_topic_score_codex":0.0042478167,"about_ca_topic_score_gemma":0.0037596568,"teacher_disagreement_score":0.004339144,"about_ca_system_score_codex":0.0011318824,"about_ca_system_score_gemma":0.0018205323,"threshold_uncertainty_score":0.022947848},"labels":[],"label_agreement":null},{"id":"W3046075819","doi":"10.5539/ijsp.v9n5p40","title":"Estimating Smooth and Convex Functions","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Differentiable function; Estimator; Convex function; Regular polygon; Function (biology); Combinatorics; Applied mathematics; Convex combination; Convex optimization; Mathematical optimization; Mathematical analysis; Statistics","score_opus":0.11626796317296399,"score_gpt":0.42407798410454783,"score_spread":0.3078100209315838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046075819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068078055,0.00014721816,0.9923563,0.00013437017,0.000016018352,0.000022705844,0.00007627228,0.00024913473,0.00019024394],"genre_scores_gemma":[0.29210272,0.00076956704,0.700072,0.00043689233,0.00028984592,0.0003886568,0.0017491501,0.0003282598,0.0038628362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974039,0.0009526333,0.00012957449,0.00075319404,0.0005450859,0.00021562645],"domain_scores_gemma":[0.9907314,0.0058497256,0.00090060633,0.0011050773,0.0011868853,0.00022634612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053069694,0.0017071699,0.0025162618,0.0019228964,0.0006188505,0.002203543,0.0031418246,0.0027685869,0.001281516],"category_scores_gemma":[0.0193496,0.0014536994,0.0017964807,0.0016667441,0.0017076187,0.002819415,0.0022837669,0.0034669836,0.0007850732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014626067,0.000094008516,0.0030877972,0.0001439725,0.00015247741,0.00013612195,0.00008646985,0.8902586,0.0035290937,0.018275196,0.0025000405,0.08159003],"study_design_scores_gemma":[0.000005452687,0.000012500695,0.00022557491,0.0000051724655,0.0000057819248,0.0000142923445,0.000005083811,0.9952924,0.00038375173,0.0037308943,0.00031123788,0.000007835578],"about_ca_topic_score_codex":0.006386039,"about_ca_topic_score_gemma":0.004453645,"teacher_disagreement_score":0.006386039,"about_ca_system_score_codex":0.001459747,"about_ca_system_score_gemma":0.0020456647,"threshold_uncertainty_score":0.028066278},"labels":[],"label_agreement":null},{"id":"W3046729600","doi":"","title":"Finite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent","year":2020,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Regret; Gradient descent; Bounded function; Descent (aeronautics); Mathematical optimization; Computer science; Property (philosophy); Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis; Engineering; Machine learning","score_opus":0.12255929215823734,"score_gpt":0.37242527432546296,"score_spread":0.2498659821672256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046729600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033519953,0.00020441436,0.9610369,0.00033774629,0.000035663947,0.000053345935,0.000033398606,0.00049866794,0.004279772],"genre_scores_gemma":[0.8188206,0.00019976556,0.17499593,0.00027409205,0.000038284637,0.0003289862,0.00011501158,0.00027646025,0.004950889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822205,0.00085419865,0.00007044216,0.00029935822,0.0003656888,0.00018821156],"domain_scores_gemma":[0.99452764,0.0038670897,0.00043039882,0.00056799216,0.00031313347,0.00029376106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027960155,0.0013217574,0.0011284595,0.00060891197,0.00066045154,0.001109194,0.0019518993,0.0014218898,0.0021607873],"category_scores_gemma":[0.016206147,0.0006290858,0.00068416126,0.00049670093,0.0023301388,0.0017938508,0.0021249016,0.0023874114,0.0005145133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021828896,0.00011338277,0.0012097744,0.00007167867,0.00007129532,0.00017012865,0.0001489881,0.8189125,0.0020359755,0.14102805,0.0018684381,0.034151595],"study_design_scores_gemma":[0.000015125865,0.000032599568,0.00006509796,0.0000075396033,0.0000055723385,0.000015871512,0.000004127668,0.962427,0.000468382,0.036651596,0.00030105325,0.0000060890684],"about_ca_topic_score_codex":0.0032679073,"about_ca_topic_score_gemma":0.0030318825,"teacher_disagreement_score":0.0032679073,"about_ca_system_score_codex":0.0012348366,"about_ca_system_score_gemma":0.0016346049,"threshold_uncertainty_score":0.014786899},"labels":[],"label_agreement":null},{"id":"W3082716386","doi":"10.48550/arxiv.2008.13773","title":"Beyond variance reduction: Understanding the true impact of baselines on policy optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reduction (mathematics); Variance reduction; Variance (accounting); Econometrics; Economics; Computer science; Environmental science; Mathematics","score_opus":0.33460323019835514,"score_gpt":0.35245186452443816,"score_spread":0.017848634326083024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082716386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13955927,0.002738589,0.83482325,0.0059179366,0.00019132686,0.00013439283,0.00027109834,0.0008208053,0.01554333],"genre_scores_gemma":[0.9458205,0.0006817067,0.050481614,0.0006529715,0.00012353223,0.0001278141,0.00015725526,0.00023230583,0.0017222755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933408,0.0035490096,0.0002596252,0.0012928642,0.0010389218,0.0005187542],"domain_scores_gemma":[0.955556,0.034378994,0.0028530823,0.0047864146,0.001450331,0.00097512384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015585704,0.001204108,0.002504814,0.0012758486,0.00129881,0.0049917535,0.0017454362,0.0028405953,0.0029929471],"category_scores_gemma":[0.10386853,0.0008008158,0.0009432449,0.0010143515,0.0036708289,0.009314548,0.0035393306,0.0052375672,0.00054564606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004263203,0.00021059209,0.0055715875,0.00022942953,0.00019308823,0.00013134062,0.00031352884,0.5190145,0.0017489536,0.41151756,0.0027335158,0.057909604],"study_design_scores_gemma":[0.000027078135,0.0001398348,0.0010517217,0.000050456165,0.000022145448,0.000034635115,0.000046953686,0.7515382,0.0006915109,0.2455266,0.00084856607,0.000022284428],"about_ca_topic_score_codex":0.0028806427,"about_ca_topic_score_gemma":0.0020883686,"teacher_disagreement_score":0.015585704,"about_ca_system_score_codex":0.0027552105,"about_ca_system_score_gemma":0.0022842155,"threshold_uncertainty_score":0.08242607},"labels":[],"label_agreement":null},{"id":"W3084085014","doi":"","title":"Bandit Online Learning of Nash Equilibria in Monotone Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nash equilibrium; Monotonic function; Monotone polygon; Regular polygon; Mathematical optimization; Action (physics); Extension (predicate logic); Mathematical economics; Function (biology); Mathematics; Zero (linguistics); Best response; Computer science; Zero-sum game","score_opus":0.2829365411725819,"score_gpt":0.32831893201346246,"score_spread":0.04538239084088058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084085014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034103014,0.00019790886,0.96155703,0.00032739903,0.000034085515,0.000080971964,0.00003544644,0.00022431958,0.0034398704],"genre_scores_gemma":[0.8549549,0.000252901,0.14030533,0.00022737494,0.00006741586,0.00030204386,0.00009792369,0.00008318509,0.0037089703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982047,0.00089670636,0.00008250489,0.00031902906,0.00028427254,0.00021283355],"domain_scores_gemma":[0.9908065,0.0070626163,0.0007479809,0.0005413234,0.00060640374,0.00023512144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032787027,0.0012900218,0.0018050477,0.0006673151,0.00081716233,0.001832123,0.002401042,0.0017812812,0.0024780827],"category_scores_gemma":[0.016651401,0.00062145083,0.00063577754,0.0008119897,0.0020077378,0.0031860117,0.0021193216,0.0023837516,0.00059377635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031243978,0.00033346599,0.0013932507,0.00020800949,0.00011181959,0.000120186254,0.00019864141,0.81251407,0.0018533684,0.10537569,0.0013066697,0.07627244],"study_design_scores_gemma":[0.000015462598,0.000032187076,0.000044442993,0.000009770001,0.0000062415406,0.000011204311,0.0000097365355,0.9720195,0.00046349497,0.027185244,0.00019795919,0.000004873431],"about_ca_topic_score_codex":0.0027616853,"about_ca_topic_score_gemma":0.002525869,"teacher_disagreement_score":0.0032787027,"about_ca_system_score_codex":0.0013252445,"about_ca_system_score_gemma":0.0012900942,"threshold_uncertainty_score":0.017339647},"labels":[],"label_agreement":null},{"id":"W3085631657","doi":"10.1287/opre.2022.2380","title":"Learning Product Rankings Robust to Fake Users","year":2022,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Product (mathematics); Ranking (information retrieval); Analytics; Status quo; Data science; Learning to rank; Machine learning; Artificial intelligence; Mathematics; Economics","score_opus":0.36256294639491365,"score_gpt":0.5291875609008896,"score_spread":0.16662461450597593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085631657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1279592,0.00057843846,0.8674878,0.0011985295,0.00007373472,0.000105855564,0.00018301963,0.0010011357,0.0014122236],"genre_scores_gemma":[0.8640694,0.00027063847,0.13283399,0.00025133346,0.00016837403,0.0001192942,0.00052318384,0.000101490776,0.0016622207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636024,0.0015510737,0.00027515003,0.0007629485,0.0007469373,0.00030357068],"domain_scores_gemma":[0.9738962,0.016480358,0.0035690984,0.0029876898,0.0025133116,0.000553477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008534339,0.0012997722,0.0024354823,0.001787569,0.00074722397,0.0029759014,0.0018551968,0.002123634,0.0010774225],"category_scores_gemma":[0.04612711,0.00079576665,0.00065795146,0.0013094317,0.0022182802,0.003746716,0.0021041506,0.002674659,0.00079745153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005078291,0.00027599058,0.009083519,0.00015506477,0.00015016684,0.00017153713,0.00014805107,0.843614,0.0031383971,0.016550293,0.0028478187,0.12335733],"study_design_scores_gemma":[0.000008155116,0.000033040793,0.00027416152,0.0000047153108,0.0000050832027,0.00001635931,0.000010138236,0.9930326,0.00055791845,0.0059169857,0.00013421319,0.0000066109064],"about_ca_topic_score_codex":0.0019611286,"about_ca_topic_score_gemma":0.0012785711,"teacher_disagreement_score":0.008534339,"about_ca_system_score_codex":0.0010825295,"about_ca_system_score_gemma":0.0017202048,"threshold_uncertainty_score":0.045134425},"labels":[],"label_agreement":null},{"id":"W3085735333","doi":"10.48550/arxiv.2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Pessimism; Core (optical fiber); Computer science; Value (mathematics); Order (exchange); Mathematical optimization; Artificial intelligence; Econometrics; Economics; Machine learning; Mathematics","score_opus":0.2439048591061609,"score_gpt":0.3377463759698552,"score_spread":0.0938415168636943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085735333","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063558035,0.0020453983,0.92330384,0.0043678298,0.00020372211,0.000111889494,0.00019274469,0.00055290916,0.005663601],"genre_scores_gemma":[0.8746093,0.001240715,0.12020175,0.0012425054,0.00032984494,0.0002614721,0.00023234707,0.00033722643,0.0015448403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98192006,0.0102606565,0.0008279578,0.0026694073,0.002621215,0.0017007104],"domain_scores_gemma":[0.80958164,0.16279356,0.009587283,0.010684693,0.004388583,0.002964249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030154228,0.002144508,0.00304116,0.001581107,0.0018132671,0.006150447,0.0034382395,0.0034806,0.002662442],"category_scores_gemma":[0.1769186,0.0013981508,0.0015587505,0.0018368941,0.005512182,0.0099185435,0.004494096,0.0077322703,0.0005458486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074964133,0.00019098361,0.0035785616,0.00031015312,0.00019506976,0.00015589976,0.000266731,0.84272486,0.0010101857,0.12808228,0.002744354,0.019991238],"study_design_scores_gemma":[0.000056783043,0.00014270763,0.00029319627,0.00007293744,0.000024543917,0.00007347978,0.00005626893,0.86603475,0.0008589808,0.13185701,0.00050602376,0.000023348515],"about_ca_topic_score_codex":0.0021797689,"about_ca_topic_score_gemma":0.0014905476,"teacher_disagreement_score":0.030154228,"about_ca_system_score_codex":0.0040953583,"about_ca_system_score_gemma":0.004684683,"threshold_uncertainty_score":0.1594727},"labels":[],"label_agreement":null},{"id":"W3087995939","doi":"10.1109/access.2020.3026237","title":"Scalable Delay-Sensitive Polling of Sensors","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polling; Computer science; Scalability; Context (archaeology); Real-time computing; Wireless sensor network; Bandwidth (computing); Distributed computing; Computer network","score_opus":0.22623193526839752,"score_gpt":0.4665477995047696,"score_spread":0.24031586423637208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087995939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07154017,0.0006302623,0.92190844,0.00052178977,0.00014824874,0.00013702728,0.00008991114,0.00053139706,0.004492804],"genre_scores_gemma":[0.97454447,0.00015381747,0.023387317,0.000115931485,0.00003378651,0.000048328446,0.000034128254,0.000021062495,0.0016612138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987778,0.00036581076,0.0000644228,0.0002907353,0.00024017514,0.0002610684],"domain_scores_gemma":[0.99579805,0.002831133,0.00047170342,0.00041388115,0.00028151768,0.00020353292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002489255,0.0006377256,0.00087797677,0.00038032734,0.0006065964,0.0011754569,0.0016112899,0.00083808124,0.0015555323],"category_scores_gemma":[0.007239759,0.0004597698,0.00041630754,0.0006304227,0.00084090617,0.0014213828,0.0012693517,0.0010600544,0.00020276083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005620318,0.0001062969,0.0012543902,0.00012464054,0.000050350256,0.00021660962,0.00015651043,0.9128566,0.008402124,0.029788615,0.0017751311,0.04470664],"study_design_scores_gemma":[0.000014097841,0.000047222056,0.00013263673,0.0000052350842,0.000008649479,0.000029902252,0.000021778907,0.9901186,0.001191114,0.0079909945,0.00043422732,0.0000054827433],"about_ca_topic_score_codex":0.0021737546,"about_ca_topic_score_gemma":0.0017635277,"teacher_disagreement_score":0.002489255,"about_ca_system_score_codex":0.001158633,"about_ca_system_score_gemma":0.0010185912,"threshold_uncertainty_score":0.01316458},"labels":[],"label_agreement":null},{"id":"W3096455539","doi":"10.1111/poms.13296","title":"Optimal Bayesian Demand Learning over Short Horizons","year":2020,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Bayesian probability; Asymptotically optimal algorithm; Dynamic pricing; Revenue; Economics; Optimal stopping; Bayesian inference; Mathematical optimization; Computer science; Mathematical economics; Microeconomics; Mathematics; Finance; Artificial intelligence","score_opus":0.07210873665177904,"score_gpt":0.3837089765238756,"score_spread":0.31160023987209656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096455539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22045168,0.0006463169,0.76457745,0.0026100357,0.00006498178,0.00007380548,0.00034379918,0.00023803694,0.0109939445],"genre_scores_gemma":[0.9718792,0.00032111077,0.023777789,0.00013910136,0.000045161196,0.000054687956,0.00013022503,0.000042397958,0.0036103143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989986,0.00036491625,0.0000365867,0.0002014619,0.00016804526,0.00023042872],"domain_scores_gemma":[0.99322456,0.0054109683,0.0006289542,0.00018176401,0.00031303856,0.00024068385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024924208,0.0007132548,0.001429631,0.00051662576,0.00038888492,0.0015545764,0.0010515212,0.0016372169,0.0030432267],"category_scores_gemma":[0.01598734,0.00074522075,0.00046387664,0.00065106,0.0013395541,0.0030157277,0.00091147446,0.001934228,0.00029101747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102050115,0.00005844049,0.00044139396,0.000040344767,0.00001564473,0.000036229023,0.00003468721,0.9394676,0.00046683376,0.050689943,0.0006152957,0.008031608],"study_design_scores_gemma":[0.000011372565,0.000011575101,0.00011294242,0.0000045747483,0.000002677816,0.0000044484364,0.000008827953,0.97874874,0.00015049017,0.02081504,0.0001237385,0.0000055546893],"about_ca_topic_score_codex":0.0075370935,"about_ca_topic_score_gemma":0.00422433,"teacher_disagreement_score":0.0075370935,"about_ca_system_score_codex":0.0023600492,"about_ca_system_score_gemma":0.0020932308,"threshold_uncertainty_score":0.017123401},"labels":[],"label_agreement":null},{"id":"W3098528340","doi":"","title":"Differentiable Meta-Learning of Bandit Policies.","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differentiable function; Meta learning (computer science); Computer science; Artificial intelligence; Mathematics; Economics","score_opus":0.23017559285573402,"score_gpt":0.4086101303330043,"score_spread":0.17843453747727028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098528340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022199448,0.0027858687,0.96644896,0.0010049324,0.00016393005,0.000045693185,0.00011496186,0.00036710728,0.0068690223],"genre_scores_gemma":[0.885905,0.0015320317,0.1029654,0.00047083962,0.00018912031,0.00019978877,0.00025367408,0.00012910816,0.008355042],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989588,0.0005692044,0.000064850035,0.0001493919,0.00012989165,0.00012770943],"domain_scores_gemma":[0.9934993,0.0051758466,0.0004050232,0.00037106633,0.00038603824,0.00016263755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031013563,0.0009985984,0.0015708706,0.00066380104,0.00038796477,0.0019740907,0.0013544318,0.0019933945,0.003887188],"category_scores_gemma":[0.016878208,0.0006398204,0.00057924225,0.0010107461,0.0012044975,0.0020914646,0.0011036347,0.0025704415,0.00084796315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019163123,0.00009751564,0.0007189784,0.00015188105,0.00013053404,0.000049176688,0.000062650994,0.86855066,0.00048274646,0.07687354,0.0024438612,0.050246913],"study_design_scores_gemma":[0.000012239688,0.000019128087,0.000052904477,0.000021588401,0.000011699369,0.0000073578713,0.000004961644,0.9766604,0.00017466562,0.022694293,0.0003370906,0.0000038213802],"about_ca_topic_score_codex":0.003091142,"about_ca_topic_score_gemma":0.0032269324,"teacher_disagreement_score":0.003887188,"about_ca_system_score_codex":0.0013689524,"about_ca_system_score_gemma":0.0013475001,"threshold_uncertainty_score":0.016401768},"labels":[],"label_agreement":null},{"id":"W3101144313","doi":"","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Bounding overwatch; Inverse; Combinatorics; Adversarial system; Hessian matrix; Mathematics; Markov chain; Robustness (evolution); Computer science; Diagonal; Discrete mathematics; Markov process; Mathematical optimization; Artificial intelligence; Applied mathematics; Statistics","score_opus":0.05573393714338376,"score_gpt":0.3323731971055618,"score_spread":0.27663925996217803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101144313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061905824,0.0004263716,0.9325509,0.0012236511,0.00007273914,0.0000852957,0.00017796116,0.0005368414,0.0030203508],"genre_scores_gemma":[0.9127512,0.00024536776,0.08147031,0.0004289969,0.000120407545,0.00018228551,0.00029944282,0.00008227496,0.0044197426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988888,0.00037140423,0.000052780284,0.00034788664,0.0001542474,0.0001849321],"domain_scores_gemma":[0.99264115,0.005807964,0.00056813523,0.00047138392,0.00020970205,0.00030169173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025590383,0.001387584,0.0020934728,0.0004370077,0.0005515495,0.0016202636,0.0025019918,0.0027289977,0.0025538139],"category_scores_gemma":[0.0111631155,0.0007821785,0.00076504325,0.0005846416,0.001907771,0.003123708,0.0022538484,0.0032903387,0.0004990075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017248954,0.000054624627,0.00062976795,0.000055049117,0.000040684652,0.00006131962,0.0000424073,0.9617857,0.00026171978,0.025044803,0.00069103687,0.011160387],"study_design_scores_gemma":[0.000013990594,0.000017720346,0.00004030119,0.0000052127934,0.000005012655,0.000008412994,0.000004900162,0.9879084,0.00016421267,0.011700817,0.00012729505,0.000003736948],"about_ca_topic_score_codex":0.003822925,"about_ca_topic_score_gemma":0.0038586464,"teacher_disagreement_score":0.003822925,"about_ca_system_score_codex":0.0015379691,"about_ca_system_score_gemma":0.0016453415,"threshold_uncertainty_score":0.013533652},"labels":[],"label_agreement":null},{"id":"W3101613519","doi":"","title":"Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Estimator; Upper and lower bounds; Computer science; Adversarial system; Mathematical optimization; Simple (philosophy); Schedule; Mathematics; Markov process; Artificial intelligence; Machine learning; Statistics","score_opus":0.49969183307741133,"score_gpt":0.32662246015581875,"score_spread":0.17306937292159258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101613519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004024789,0.0010582883,0.988189,0.0010587316,0.00011238641,0.000073546835,0.00012101585,0.0003104027,0.0050519006],"genre_scores_gemma":[0.60411996,0.004422114,0.36895218,0.0032734463,0.0012302103,0.0014673898,0.0006382229,0.0012168268,0.014679686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916841,0.0035023033,0.00028555063,0.0012611033,0.002498962,0.0007680388],"domain_scores_gemma":[0.9359679,0.05181064,0.003054282,0.00504555,0.0027096597,0.0014119402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016469566,0.0045755254,0.0034680758,0.0030858286,0.001692841,0.0044109444,0.00573692,0.0038381056,0.0066868565],"category_scores_gemma":[0.075117745,0.0016027419,0.0028375213,0.0023583958,0.005818111,0.009301647,0.008610031,0.013307756,0.00173062],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032657865,0.00022570403,0.001546878,0.000491923,0.00020937552,0.00022854235,0.00025727856,0.46783733,0.0027258892,0.47983414,0.005646044,0.040670287],"study_design_scores_gemma":[0.000030770367,0.000065038446,0.00019281064,0.00010120052,0.000039886556,0.00006298484,0.0000181281,0.7768333,0.0014438537,0.21952364,0.0016590601,0.000029301764],"about_ca_topic_score_codex":0.0017378307,"about_ca_topic_score_gemma":0.0016074957,"teacher_disagreement_score":0.016469566,"about_ca_system_score_codex":0.0053254897,"about_ca_system_score_gemma":0.0035502193,"threshold_uncertainty_score":0.087100446},"labels":[],"label_agreement":null},{"id":"W3102232031","doi":"","title":"Adaptive Search Algorithms for Discrete Stochastic Optimization: A Smooth Best-Response Approach","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Army Research Office; Canada Research Chairs","keywords":"Convergence (economics); Mathematical optimization; Set (abstract data type); Local optimum; Computer science; Random search; Stochastic optimization; Sampling (signal processing); Algorithm; Finite set; Scheme (mathematics); Mathematics","score_opus":0.20159379791926774,"score_gpt":0.4412203572855472,"score_spread":0.23962655936627947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102232031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007692259,0.0002880813,0.9905158,0.00015397559,0.000021149033,0.00003301563,0.000007532467,0.00008099571,0.001207179],"genre_scores_gemma":[0.72644913,0.000825783,0.26772386,0.00022236482,0.000095017174,0.00052616437,0.0000745349,0.000121839716,0.003961372],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891055,0.0006706434,0.00003665217,0.00010540941,0.00020799988,0.00006865011],"domain_scores_gemma":[0.99633694,0.0030200416,0.0001873936,0.0001637189,0.00020155445,0.00009030343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026784344,0.001019362,0.0014395432,0.0009829515,0.00042594975,0.00096557464,0.0013104553,0.0014566678,0.001384192],"category_scores_gemma":[0.008536611,0.00064458617,0.00089523726,0.0008292648,0.0018667687,0.0011564927,0.0016320514,0.0016819478,0.00030481315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023635133,0.00001469051,0.00013646645,0.000025405108,0.000026549755,0.000017633858,0.000025552064,0.9671931,0.00034525996,0.026386928,0.000116476076,0.005688378],"study_design_scores_gemma":[0.00000599753,0.000010561781,0.00001197825,0.0000029603384,0.0000022496292,0.0000028988416,0.0000016600577,0.99468744,0.00005681026,0.0051092557,0.00010597007,0.0000022918869],"about_ca_topic_score_codex":0.0022878763,"about_ca_topic_score_gemma":0.0011341842,"teacher_disagreement_score":0.0026784344,"about_ca_system_score_codex":0.0009178328,"about_ca_system_score_gemma":0.0009889115,"threshold_uncertainty_score":0.014165103},"labels":[],"label_agreement":null},{"id":"W3102774599","doi":"","title":"Online algorithm for unsupervised sequential selection with contextual information","year":2020,"lang":"en","type":"article","venue":"OpenBU (Boston University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regret; Context (archaeology); Artificial intelligence; Selection (genetic algorithm); Unsupervised learning; Machine learning; Mathematical optimization; Algorithm; Mathematics","score_opus":0.11547673814735646,"score_gpt":0.3492813364494446,"score_spread":0.23380459830208813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102774599","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01781501,0.0005213282,0.97486013,0.00056561525,0.00009789928,0.00029776225,0.00023520162,0.0024893957,0.0031176438],"genre_scores_gemma":[0.40180758,0.00032749926,0.586277,0.00090340024,0.00032091167,0.0010102977,0.0015527008,0.0005944425,0.0072061284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982274,0.00066744024,0.00009828927,0.00041029116,0.00033219613,0.00026432323],"domain_scores_gemma":[0.9962463,0.0025576225,0.000257572,0.00041430365,0.00032913563,0.00019509438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026109011,0.0017994171,0.0022240377,0.0010834777,0.0008863385,0.0011132848,0.002651546,0.0017244049,0.0100200195],"category_scores_gemma":[0.0063514733,0.0008029894,0.0011742315,0.001403719,0.0012615925,0.002250414,0.0023139336,0.0023357626,0.0023995894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000961605,0.0004659762,0.003127044,0.0003749562,0.00021890973,0.00017247566,0.00024346779,0.46042636,0.0032748722,0.042005453,0.015350358,0.47337863],"study_design_scores_gemma":[0.00010528141,0.00008506319,0.0001719076,0.000016187378,0.000023017437,0.00004922568,0.000025886335,0.97466034,0.0007555546,0.022559255,0.0015380783,0.000010139883],"about_ca_topic_score_codex":0.0039730016,"about_ca_topic_score_gemma":0.007444196,"teacher_disagreement_score":0.0100200195,"about_ca_system_score_codex":0.0015982989,"about_ca_system_score_gemma":0.0034998462,"threshold_uncertainty_score":0.03352028},"labels":[],"label_agreement":null},{"id":"W3105983076","doi":"","title":"Comparator-adaptive Convex Bandits","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Comparator; Regret; Norm (philosophy); Mathematical optimization; Lipschitz continuity; Regular polygon; Convex optimization; Convex function; Estimator; Computer science; Oracle; Mathematics; Algorithm; Machine learning; Engineering; Statistics","score_opus":0.4560665325218811,"score_gpt":0.30483801282542755,"score_spread":0.15122851969645357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105983076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010757457,0.00038474333,0.9849754,0.00030734966,0.00005814325,0.000047979873,0.00007442482,0.00022928194,0.003165102],"genre_scores_gemma":[0.72436154,0.0006657451,0.2628635,0.00065895164,0.00019594256,0.0003886017,0.0003527131,0.00027557852,0.010237364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765515,0.0010861708,0.00012308895,0.00043639512,0.0004919137,0.0002072246],"domain_scores_gemma":[0.99130356,0.006008097,0.00082020997,0.0008030342,0.0008016715,0.00026341944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004765619,0.0011707938,0.0019963603,0.0007706684,0.00055760256,0.0022402606,0.0021725574,0.0019524067,0.0047560055],"category_scores_gemma":[0.025231153,0.00058660685,0.00070749235,0.0012800931,0.0018275785,0.003989852,0.0024991122,0.0030388867,0.0011063209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004102438,0.00014514664,0.0007918822,0.00020306993,0.00008645027,0.00009574523,0.00009097383,0.7254949,0.00224944,0.1922613,0.0030156262,0.07515525],"study_design_scores_gemma":[0.000020826259,0.000060005805,0.00007328509,0.000023888497,0.000009448619,0.000026952159,0.000007964787,0.9591966,0.0007753333,0.03915292,0.0006439596,0.0000088019515],"about_ca_topic_score_codex":0.0010053938,"about_ca_topic_score_gemma":0.0008458977,"teacher_disagreement_score":0.004765619,"about_ca_system_score_codex":0.001505431,"about_ca_system_score_gemma":0.0011380098,"threshold_uncertainty_score":0.025203288},"labels":[],"label_agreement":null},{"id":"W3106590465","doi":"10.1109/tcyb.2022.3164399","title":"Scalable Transfer Evolutionary Optimization: Coping With Big Task Instances","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Science and Engineering Research Council; Agency for Science, Technology and Research","keywords":"Scalability; Computer science; Task (project management); Artificial intelligence; Engineering","score_opus":0.06292899291217222,"score_gpt":0.32759518318869,"score_spread":0.26466619027651783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106590465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20633301,0.000939553,0.7842168,0.0012293123,0.00015103535,0.0001853857,0.0001912535,0.0013094245,0.0054441993],"genre_scores_gemma":[0.76860744,0.00027640653,0.22685295,0.0005356837,0.00009538499,0.00031587997,0.00048501117,0.00023903341,0.002592154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999305,0.00023864958,0.00003568834,0.00017547747,0.00015666388,0.000088521345],"domain_scores_gemma":[0.99744344,0.0017826105,0.00013887115,0.0002964238,0.00019409417,0.00014460685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017980712,0.0010084517,0.0011744743,0.00037576424,0.00055193785,0.00093869807,0.0020234114,0.0016774508,0.0018503908],"category_scores_gemma":[0.006920984,0.00038728022,0.0007667058,0.0005271492,0.0010353477,0.0018699601,0.0020426335,0.0023628306,0.00031549434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012263432,0.00017219265,0.0013557046,0.00010445426,0.000057609584,0.00015552898,0.00008638529,0.95039797,0.002098126,0.0063396906,0.001687909,0.037421722],"study_design_scores_gemma":[0.000012831801,0.00002295144,0.00011328393,0.0000029739763,0.0000040155937,0.000017187,0.000016553106,0.9959837,0.00032379365,0.0031745085,0.0003250938,0.0000030693402],"about_ca_topic_score_codex":0.0026341684,"about_ca_topic_score_gemma":0.0028209828,"teacher_disagreement_score":0.0026341684,"about_ca_system_score_codex":0.0005993962,"about_ca_system_score_gemma":0.00093695876,"threshold_uncertainty_score":0.009509265},"labels":[],"label_agreement":null},{"id":"W3106732744","doi":"10.1007/978-3-030-60382-3_5","title":"Learning-Based Reconfigurable Access Schemes for Virtualized M2M Networks","year":2020,"lang":"en","type":"book-chapter","venue":"Wireless networks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Regret; Thresholding; Scheme (mathematics); Thompson sampling; Estimator; Network packet; Sampling scheme; Sampling (signal processing); Throughput; Real-time computing; Computer network; Artificial intelligence; Machine learning; Telecommunications","score_opus":0.12933821713852361,"score_gpt":0.398868518956655,"score_spread":0.26953030181813137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106732744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033837315,0.0034053987,0.933175,0.00042232813,0.00037236756,0.0000483583,0.00008037361,0.0011479862,0.027510796],"genre_scores_gemma":[0.86239684,0.0019055551,0.11309568,0.00022419654,0.0002635365,0.000060254155,0.00009906029,0.0000969676,0.021857904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979824,0.00004734364,0.000008508118,0.000035846562,0.000065173415,0.00004494644],"domain_scores_gemma":[0.9997166,0.00012500543,0.000021725837,0.00007739249,0.000044484324,0.000014800129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024348346,0.00043000068,0.00038017653,0.00028556914,0.00030103882,0.0010085765,0.0010938351,0.0004701306,0.003632963],"category_scores_gemma":[0.00084849336,0.00014474515,0.0002054899,0.0005073006,0.00048455733,0.0011195377,0.000659367,0.0009281302,0.0006382041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003171037,0.00012251086,0.00026201658,0.00017814977,0.000048099406,0.00010946376,0.00009156128,0.24532054,0.032264862,0.2307184,0.01201603,0.4785513],"study_design_scores_gemma":[0.000012413304,0.00008994948,0.0001873105,0.00002474297,0.000011692902,0.00013672274,0.000025358157,0.9134961,0.007614724,0.0666195,0.01176445,0.000017113247],"about_ca_topic_score_codex":0.00049011374,"about_ca_topic_score_gemma":0.00078445254,"teacher_disagreement_score":0.003632963,"about_ca_system_score_codex":0.0006207633,"about_ca_system_score_gemma":0.0002421497,"threshold_uncertainty_score":0.012153447},"labels":[],"label_agreement":null},{"id":"W3110181803","doi":"10.1609/aaai.v35i8.16820","title":"Decentralized Multi-Agent Linear Bandits with Safety Constraints","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Regret; Computer science; Mathematical optimization; Network topology; Upper and lower bounds; Bipartite graph; Linear programming; Graph; Telecommunications network; Mathematics; Theoretical computer science; Computer network; Machine learning","score_opus":0.26689795052528154,"score_gpt":0.43374491983382724,"score_spread":0.1668469693085457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110181803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048802845,0.00022306108,0.94667536,0.00039435868,0.000049331044,0.000054967768,0.000059033082,0.00015647321,0.0035845523],"genre_scores_gemma":[0.9198722,0.00024280464,0.07560096,0.00014443188,0.000087174165,0.00014297277,0.000096991396,0.00005767875,0.003754807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989379,0.0004389432,0.000031648462,0.00021573988,0.00020509267,0.00017064053],"domain_scores_gemma":[0.9966627,0.0019692418,0.00056452333,0.00033087103,0.0002888703,0.00018382545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012896445,0.00080753135,0.001001897,0.00030692795,0.00062297756,0.0010918129,0.0012140648,0.0011009832,0.0019741491],"category_scores_gemma":[0.005873162,0.0003716897,0.00052507134,0.000507453,0.0010908492,0.0016075845,0.0014209247,0.0014759796,0.00032685432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009740643,0.000044167668,0.00039710698,0.00005743265,0.000025443012,0.00006151179,0.000040915394,0.95262444,0.0013208168,0.036590263,0.0004893997,0.008251049],"study_design_scores_gemma":[0.000012670062,0.0000283412,0.000055143257,0.0000032815142,0.0000035776902,0.00001079264,0.00000946443,0.9875501,0.00029792712,0.011656518,0.00036858727,0.0000037108898],"about_ca_topic_score_codex":0.0024437262,"about_ca_topic_score_gemma":0.0015869002,"teacher_disagreement_score":0.0024437262,"about_ca_system_score_codex":0.00095076486,"about_ca_system_score_gemma":0.0011810389,"threshold_uncertainty_score":0.0068983436},"labels":[],"label_agreement":null},{"id":"W3112678130","doi":"10.48550/arxiv.2012.03800","title":"Revenue Maximization and Learning in Products Ranking","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Revenue; Computer science; Product (mathematics); Regret; Ranking (information retrieval); Maximization; Purchasing; Mathematical optimization; Econometrics; Mathematics; Economics; Artificial intelligence; Machine learning; Marketing; Business","score_opus":0.2775072153582469,"score_gpt":0.29570446150170665,"score_spread":0.018197246143459744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112678130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16507193,0.0025378878,0.81854063,0.0020561363,0.00014442677,0.0001946977,0.00057447277,0.00096534967,0.009914543],"genre_scores_gemma":[0.8845882,0.0010061023,0.10696252,0.00036949586,0.000259647,0.00018057541,0.0007593756,0.00016084423,0.0057132444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980469,0.0008904524,0.00005723238,0.00040914837,0.00024109476,0.00035520009],"domain_scores_gemma":[0.9935582,0.0048814104,0.00048132075,0.00042803507,0.00032921755,0.00032170842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030046513,0.0016407344,0.0025140247,0.00087003614,0.00069580047,0.0016489155,0.0029016302,0.0018354143,0.004361517],"category_scores_gemma":[0.011743427,0.00081683614,0.001157074,0.0017492531,0.0016998168,0.0036061807,0.0014658364,0.00245216,0.00093935785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042303084,0.0003466392,0.0017199945,0.00019608383,0.000075468684,0.00015071119,0.000071002425,0.9027831,0.0008154626,0.036541153,0.0042371317,0.05264021],"study_design_scores_gemma":[0.00002734416,0.00004706156,0.00020371498,0.000005689116,0.000010193114,0.000022238215,0.000010097262,0.97732997,0.00025037807,0.021801984,0.00028458887,0.0000067925516],"about_ca_topic_score_codex":0.007347151,"about_ca_topic_score_gemma":0.005177455,"teacher_disagreement_score":0.007347151,"about_ca_system_score_codex":0.002886302,"about_ca_system_score_gemma":0.001790963,"threshold_uncertainty_score":0.020941615},"labels":[],"label_agreement":null},{"id":"W3114060070","doi":"","title":"Distributed Online Optimization over a Heterogeneous Network with Any-Batch Mirror Descent","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Distributed computing; Gradient descent; Artificial intelligence; Artificial neural network","score_opus":0.15685260508525875,"score_gpt":0.4146580197922753,"score_spread":0.25780541470701657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114060070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053258274,0.00024749237,0.9413869,0.0005680874,0.0001664386,0.000086106345,0.00009003925,0.0009989326,0.0031978192],"genre_scores_gemma":[0.8627351,0.00010148163,0.13114339,0.00017176819,0.00012323177,0.00015254244,0.0001806151,0.00011741511,0.0052744946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998995,0.00029603727,0.00005154443,0.00031739028,0.0001831198,0.00015685041],"domain_scores_gemma":[0.9980446,0.0009041306,0.00013094359,0.00046232183,0.0002944599,0.00016350695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017397859,0.00097034016,0.0019263048,0.00040476423,0.0011651492,0.0016977392,0.0028611857,0.0015895019,0.003465676],"category_scores_gemma":[0.0044817803,0.0006442432,0.00063951226,0.0007141686,0.0011248137,0.0023208319,0.0025338575,0.0016271693,0.00068046583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009778227,0.00023372484,0.0007591275,0.00007135932,0.000094864656,0.00019165015,0.00008053209,0.91729313,0.004540986,0.012071257,0.0037036298,0.059981976],"study_design_scores_gemma":[0.000017076918,0.000013759036,0.000026326872,6.3387125e-7,0.0000032115818,0.00000457195,0.0000040782566,0.9978543,0.0002363517,0.0017624093,0.000075619944,0.0000016765712],"about_ca_topic_score_codex":0.005899743,"about_ca_topic_score_gemma":0.008223783,"teacher_disagreement_score":0.005899743,"about_ca_system_score_codex":0.0011454074,"about_ca_system_score_gemma":0.0019844405,"threshold_uncertainty_score":0.01173085},"labels":[],"label_agreement":null},{"id":"W3114093453","doi":"10.1017/9781108571401.015","title":"The Exp3 Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Algorithm; Computer science; Content (measure theory); Information retrieval; Mathematics","score_opus":0.09992261373328512,"score_gpt":0.31480413668482143,"score_spread":0.2148815229515363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114093453","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041090054,0.0012494551,0.8880195,0.0010354385,0.00079570536,0.00038477083,0.0074878028,0.042863365,0.054054927],"genre_scores_gemma":[0.038963098,0.00073617784,0.8402495,0.001085795,0.0003414744,0.00065145997,0.022003366,0.013370954,0.08259817],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877375,0.00023130521,0.00008259618,0.0003532152,0.00040294242,0.00015612715],"domain_scores_gemma":[0.99861,0.00038961,0.00004033248,0.00053477817,0.00035465768,0.00007063653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013734153,0.0018180202,0.0011085576,0.0013584069,0.0010106219,0.0026839643,0.0027352402,0.0017149525,0.13169146],"category_scores_gemma":[0.0070218625,0.00064446026,0.001838233,0.0018496149,0.00060613203,0.0028732806,0.0023551178,0.0023345873,0.10425811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005051742,0.00012611036,0.00065142196,0.00037242178,0.00008583167,0.00010588309,0.00005505709,0.0140961455,0.0027200915,0.03259434,0.32141912,0.6272685],"study_design_scores_gemma":[0.0005003245,0.00017868027,0.0009226018,0.00021509385,0.00009364163,0.0008313563,0.0001411543,0.38467127,0.013772555,0.21865816,0.3799226,0.00009256092],"about_ca_topic_score_codex":0.0030945837,"about_ca_topic_score_gemma":0.004901178,"teacher_disagreement_score":0.13169146,"about_ca_system_score_codex":0.00078712765,"about_ca_system_score_gemma":0.002330497,"threshold_uncertainty_score":0.44055182},"labels":[],"label_agreement":null},{"id":"W3115085521","doi":"10.1017/9781108571401.005","title":"Stochastic Processes and Markov Chains","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov chain; Content (measure theory); Computer science; Markov process; Mathematics; Statistics; Machine learning","score_opus":0.08431149224347785,"score_gpt":0.3036433095587427,"score_spread":0.21933181731526485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115085521","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005764126,0.23324999,0.14999035,0.016229441,0.003914329,0.00007663708,0.0019246829,0.0007544315,0.58809596],"genre_scores_gemma":[0.1519484,0.19426988,0.029966485,0.003357678,0.004094687,0.00025852057,0.0022775764,0.00053328054,0.6132935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99974495,0.0000745412,0.000010376915,0.00004237519,0.00010768814,0.000020033029],"domain_scores_gemma":[0.99935216,0.00047277386,0.000028100569,0.000045906552,0.0000691891,0.00003186411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004905045,0.0007964757,0.00064350123,0.00075217243,0.00036368505,0.0015387293,0.00044190307,0.00084242923,0.032796092],"category_scores_gemma":[0.0020332285,0.0002814968,0.0004353242,0.0015745874,0.001188301,0.001627061,0.00055652234,0.001663967,0.009329966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012820019,0.00002364587,0.0002408282,0.00038144964,0.000021832513,0.000095667936,0.00016497634,0.006775522,0.0003171037,0.7455937,0.173286,0.07308653],"study_design_scores_gemma":[0.0000056779713,0.000015218823,0.00050338043,0.00019701582,0.000006575428,0.00010476331,0.00004705599,0.0055392506,0.00011545955,0.7180756,0.2753799,0.000010039382],"about_ca_topic_score_codex":0.0025473454,"about_ca_topic_score_gemma":0.002531382,"teacher_disagreement_score":0.032796092,"about_ca_system_score_codex":0.0013848178,"about_ca_system_score_gemma":0.0010403725,"threshold_uncertainty_score":0.10971385},"labels":[],"label_agreement":null},{"id":"W3116408070","doi":"10.1017/9781108571401.009","title":"The Explore-Then-Commit Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Commit; Computer science; Content (measure theory); Algorithm; Database; Mathematics","score_opus":0.1372628476713435,"score_gpt":0.3203234640648492,"score_spread":0.18306061639350568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116408070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009443081,0.0015479062,0.8811411,0.00234458,0.0011192156,0.0008992044,0.0046366244,0.033194195,0.06567414],"genre_scores_gemma":[0.0701196,0.0005580692,0.8512743,0.00076900894,0.00035954083,0.000903502,0.007475338,0.0074576535,0.061082914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755824,0.00051174674,0.00015349074,0.00059024297,0.0007507753,0.0004354508],"domain_scores_gemma":[0.994726,0.0019407787,0.00016451355,0.0020815053,0.00076405396,0.00032320348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023014368,0.0022191922,0.0017492899,0.0017611553,0.0018833615,0.0037979379,0.0042204466,0.0021323834,0.08302417],"category_scores_gemma":[0.013536001,0.00109912,0.0016974896,0.0029139302,0.0011377139,0.004324787,0.005139082,0.0037558225,0.03957043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000737466,0.00022978375,0.0008092983,0.0004883121,0.00010944453,0.00013896443,0.00018031505,0.025521172,0.002058228,0.06922315,0.2578606,0.6426433],"study_design_scores_gemma":[0.0007682098,0.00027642926,0.00061470474,0.00019404927,0.00015493695,0.0005964238,0.00033477554,0.42149246,0.0088523645,0.41431078,0.15229872,0.0001061007],"about_ca_topic_score_codex":0.0054010055,"about_ca_topic_score_gemma":0.012918745,"teacher_disagreement_score":0.08302417,"about_ca_system_score_codex":0.001303006,"about_ca_system_score_gemma":0.0062976973,"threshold_uncertainty_score":0.27774352},"labels":[],"label_agreement":null},{"id":"W3117242735","doi":"10.1017/9781108571401.023","title":"Contextual and Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Link (geometry); Information retrieval; Internet privacy; Computer network; Mathematics","score_opus":0.11857060093907623,"score_gpt":0.32116987956180976,"score_spread":0.20259927862273353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117242735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016938064,0.051205296,0.5163739,0.008803001,0.0014489306,0.000050960105,0.0013284899,0.00079786737,0.40305343],"genre_scores_gemma":[0.5431169,0.036663406,0.13443068,0.0031320872,0.0032048312,0.00023051325,0.0017634794,0.0008419233,0.2766161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929345,0.000313025,0.000027698923,0.00013039667,0.00015486569,0.00008045015],"domain_scores_gemma":[0.9987747,0.0008449009,0.0000613736,0.00016682308,0.000101165475,0.00005103319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011178065,0.0006575509,0.000728856,0.00061313517,0.0005532839,0.0026705933,0.0006292768,0.0010330529,0.025423821],"category_scores_gemma":[0.0054682475,0.0003065764,0.00040691256,0.0015944282,0.0015698337,0.002273571,0.0011449695,0.0020699983,0.0052127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004742093,0.000016648566,0.00020777601,0.00017762027,0.000024030864,0.000036861788,0.000069645976,0.016810128,0.00030308514,0.88436633,0.024557078,0.073383324],"study_design_scores_gemma":[0.000007256863,0.000015889902,0.00037337962,0.00010971751,0.000012456543,0.000043787903,0.000043369393,0.031304765,0.00022326472,0.9266533,0.041199327,0.000013495813],"about_ca_topic_score_codex":0.0031337242,"about_ca_topic_score_gemma":0.0041943495,"teacher_disagreement_score":0.025423821,"about_ca_system_score_codex":0.0014805193,"about_ca_system_score_gemma":0.0007115798,"threshold_uncertainty_score":0.08505118},"labels":[],"label_agreement":null},{"id":"W3117424601","doi":"10.1017/9781108571401.008","title":"Stochastic Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mathematical economics; Mathematics","score_opus":0.10339968304591471,"score_gpt":0.2996677950151826,"score_spread":0.19626811196926788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117424601","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011672798,0.009492109,0.7742123,0.004105877,0.00092674984,0.000051013012,0.0007951102,0.00090940227,0.19783467],"genre_scores_gemma":[0.4639844,0.017201057,0.1794112,0.0022633686,0.0024057042,0.0004847443,0.0019296523,0.000856688,0.33146316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992791,0.0003049991,0.000030377827,0.00012342224,0.00019092472,0.00007113648],"domain_scores_gemma":[0.9978219,0.0016612958,0.000087364686,0.00023686797,0.000115048526,0.00007759461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014339841,0.0010543464,0.0010731422,0.0005332987,0.0004925827,0.0024022954,0.0009866721,0.0013039036,0.021082126],"category_scores_gemma":[0.0053757518,0.00048057816,0.00075012055,0.0011303659,0.0012465257,0.0022265415,0.0011444151,0.0027623866,0.0074749403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000913444,0.000037315993,0.00023201591,0.00020470332,0.000053796663,0.000073495976,0.00005105353,0.07962112,0.00067596603,0.82263976,0.025180036,0.071139425],"study_design_scores_gemma":[0.000021570926,0.000028932667,0.0002069957,0.00011483026,0.0000176131,0.000057756857,0.000015385644,0.18964015,0.0004386707,0.7847454,0.024693571,0.00001920874],"about_ca_topic_score_codex":0.00091079826,"about_ca_topic_score_gemma":0.0011136688,"teacher_disagreement_score":0.021082126,"about_ca_system_score_codex":0.0010738642,"about_ca_system_score_gemma":0.0007760774,"threshold_uncertainty_score":0.07052678},"labels":[],"label_agreement":null},{"id":"W3118438270","doi":"10.1214/23-aos2315","title":"Relaxing the i.i.d. assumption: Adaptively minimax optimal regret via root-entropic regularization","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Regret; Minimax; Mathematics; Mathematical optimization; Regularization (linguistics); Entropy (arrow of time); Adversarial system; Computer science; Artificial intelligence; Statistics","score_opus":0.3214253860286645,"score_gpt":0.4722292110110216,"score_spread":0.15080382498235712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118438270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035763826,0.00029477116,0.959896,0.00090470916,0.0000391391,0.000043117197,0.00007518783,0.00017391167,0.0028093536],"genre_scores_gemma":[0.91266334,0.0003898609,0.08210339,0.00061398954,0.00014821814,0.00015911709,0.00012908055,0.00010888804,0.0036842483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976035,0.0011087081,0.0000786049,0.0005248206,0.00045083562,0.00023361981],"domain_scores_gemma":[0.98878855,0.008262492,0.0012099077,0.0009437317,0.00043648487,0.00035874298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050836992,0.0014562502,0.0017392169,0.0005850055,0.0006319035,0.0015370395,0.002191953,0.0018637646,0.0011756636],"category_scores_gemma":[0.020887185,0.00064016413,0.0008819616,0.00059806084,0.0031070197,0.0026435165,0.0028523363,0.004152127,0.00029230828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000123453,0.00007014453,0.0008283609,0.000065963846,0.00006315733,0.00015247481,0.00009024104,0.8866391,0.0018507175,0.099957466,0.001168433,0.008990466],"study_design_scores_gemma":[0.000008951442,0.000031582782,0.000101148595,0.000007731254,0.0000051987968,0.000017543147,0.0000072218704,0.9677125,0.0004052306,0.03154456,0.00015032727,0.000007945602],"about_ca_topic_score_codex":0.0017460721,"about_ca_topic_score_gemma":0.0013721223,"teacher_disagreement_score":0.0050836992,"about_ca_system_score_codex":0.0015292539,"about_ca_system_score_gemma":0.0013124751,"threshold_uncertainty_score":0.02688545},"labels":[],"label_agreement":null},{"id":"W3121333123","doi":"10.2139/ssrn.3685465","title":"Learning Product Rankings Robust to Fake Users","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Product (mathematics); Computer science; Business; Econometrics; Marketing; Economics; Mathematics","score_opus":0.08311210502914192,"score_gpt":0.37509100048157773,"score_spread":0.2919788954524358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121333123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4389484,0.0019461843,0.54536647,0.0033743037,0.00038653793,0.00020688781,0.00093105505,0.0030664487,0.0057737217],"genre_scores_gemma":[0.9658174,0.0002707095,0.028328141,0.0002516364,0.00032141784,0.00007848115,0.0009788482,0.0001586175,0.0037946883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926605,0.00331512,0.00035249916,0.0015069367,0.0016327625,0.0005320985],"domain_scores_gemma":[0.9154715,0.05954375,0.006954228,0.011336308,0.0053754873,0.001318776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011416892,0.0014855823,0.002611947,0.0027063438,0.0009587457,0.0038030108,0.0018284182,0.0030726444,0.0030106683],"category_scores_gemma":[0.08576286,0.0010606874,0.00090527657,0.0018522525,0.0023015256,0.0054151146,0.002630479,0.004100784,0.0021606344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004549177,0.0010380696,0.04755073,0.000859213,0.0009215022,0.00044519053,0.00039173145,0.34283397,0.008386549,0.047339078,0.025676873,0.52000797],"study_design_scores_gemma":[0.0000722426,0.0002486827,0.0025576018,0.00003024056,0.00006083651,0.000083855404,0.000052712618,0.9637407,0.002148344,0.030138647,0.00083902484,0.000027116022],"about_ca_topic_score_codex":0.001869907,"about_ca_topic_score_gemma":0.0017881042,"teacher_disagreement_score":0.011416892,"about_ca_system_score_codex":0.0013609566,"about_ca_system_score_gemma":0.0016521912,"threshold_uncertainty_score":0.06037903},"labels":[],"label_agreement":null},{"id":"W3127662496","doi":"10.1109/lcsys.2020.3043591","title":"On Data-Driven Multi-Product Pricing","year":2020,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Computer science; Boosting (machine learning); Mathematical optimization; Parametric statistics; Robust optimization; Task (project management); Product (mathematics); Machine learning; Artificial intelligence; Econometrics; Mathematics; Economics","score_opus":0.22847096646366055,"score_gpt":0.40817026663983635,"score_spread":0.1796993001761758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127662496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073135686,0.00057046546,0.98960996,0.0006914591,0.00009189223,0.00002709615,0.000064125736,0.00008414695,0.0015472699],"genre_scores_gemma":[0.75840855,0.0021283065,0.2313329,0.0008688746,0.00081017916,0.00026235412,0.000439182,0.00025251607,0.005497249],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647826,0.0018648726,0.00013537232,0.0005200762,0.0007257844,0.00027552422],"domain_scores_gemma":[0.9839526,0.012062946,0.0007791469,0.0013143208,0.0014926124,0.0003983062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008573407,0.0012653875,0.0022108036,0.0011507197,0.0005925148,0.0022728497,0.0025699,0.0021333892,0.0029008344],"category_scores_gemma":[0.031523805,0.0009832489,0.0011404124,0.0018600355,0.0021051022,0.004823094,0.0027280997,0.003574571,0.0004626688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006477622,0.00006294262,0.0006459123,0.000095108975,0.000048782247,0.00011134349,0.000046195662,0.8563488,0.00043523323,0.11826344,0.0014761657,0.022401342],"study_design_scores_gemma":[0.0000037985703,0.000008783675,0.00005603436,0.0000049949076,0.0000028376705,0.000009614888,0.0000022550644,0.9737607,0.00008209667,0.025783159,0.00028113482,0.000004584529],"about_ca_topic_score_codex":0.0035169323,"about_ca_topic_score_gemma":0.0018670495,"teacher_disagreement_score":0.008573407,"about_ca_system_score_codex":0.0017846444,"about_ca_system_score_gemma":0.0016883573,"threshold_uncertainty_score":0.045341074},"labels":[],"label_agreement":null},{"id":"W3128801098","doi":"10.1109/focs46700.2020.00132","title":"Optimal anytime regret for two experts","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Computer science; Human–computer interaction; Artificial intelligence; Machine learning","score_opus":0.301288413499801,"score_gpt":0.5098735360741435,"score_spread":0.20858512257434253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128801098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041282855,0.0004822001,0.9495627,0.0012905395,0.0001091673,0.00009122331,0.00012956276,0.00034765466,0.0067040194],"genre_scores_gemma":[0.7484336,0.00045804144,0.2344805,0.00066577655,0.0003158511,0.00041833654,0.00032817363,0.00019640278,0.0147034405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972916,0.0011005416,0.00009079065,0.0006329604,0.0004978838,0.0003861472],"domain_scores_gemma":[0.99277425,0.0052803354,0.00057255215,0.00065176614,0.0004123087,0.00030869467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046156603,0.0014094635,0.0017540274,0.00058139,0.00070845004,0.0015324055,0.0021969718,0.0024296402,0.0031804661],"category_scores_gemma":[0.018284524,0.00059080246,0.0009970455,0.0007272093,0.0015642212,0.0027651398,0.001966101,0.0030301388,0.00064780406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078992004,0.00026783446,0.0011712594,0.0002617942,0.00013995706,0.00012953505,0.00025965026,0.6911727,0.0032624123,0.20655206,0.007257491,0.08873535],"study_design_scores_gemma":[0.000060590715,0.00007736549,0.000198504,0.000021868562,0.000016693924,0.00003123277,0.000014652332,0.9203991,0.0009826109,0.07735852,0.0008249372,0.000013917364],"about_ca_topic_score_codex":0.0019190913,"about_ca_topic_score_gemma":0.0015995495,"teacher_disagreement_score":0.0046156603,"about_ca_system_score_codex":0.0018855857,"about_ca_system_score_gemma":0.0019176917,"threshold_uncertainty_score":0.024410248},"labels":[],"label_agreement":null},{"id":"W3133930710","doi":"10.1007/978-3-030-67661-2_2","title":"Exponential Convergence of Gradient Methods in Concave Network Zero-Sum Games","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zero-sum game; Zero (linguistics); Generalization; Lipschitz continuity; Convergence (economics); Nash equilibrium; Mathematics; Regular polygon; Computer science; Applied mathematics; Mathematical optimization; Mathematical analysis","score_opus":0.09317908722572378,"score_gpt":0.42548853662502933,"score_spread":0.33230944939930557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133930710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01674632,0.0017040404,0.9548767,0.0013632819,0.00023152451,0.000110341345,0.00008919904,0.00023518529,0.0246434],"genre_scores_gemma":[0.5843815,0.005869577,0.33565798,0.001161373,0.00071106665,0.0013312908,0.00042581907,0.0015043293,0.06895711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978581,0.001255792,0.000061493716,0.00019785928,0.00040658357,0.00022019605],"domain_scores_gemma":[0.98038906,0.016958335,0.00041620835,0.000500727,0.0012151987,0.00052046735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006209532,0.0026172989,0.0021816336,0.001862861,0.0009993684,0.003037721,0.003295984,0.002490598,0.0069724703],"category_scores_gemma":[0.033190932,0.0012155198,0.0014506074,0.0016629827,0.004581145,0.0050924397,0.0048829466,0.0058640987,0.0011975026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022696113,0.00014883153,0.0005377072,0.0004453014,0.000085182044,0.00008178934,0.00035721934,0.36484587,0.0015527931,0.58923477,0.0076653203,0.034818225],"study_design_scores_gemma":[0.000020607302,0.00002554907,0.00007720716,0.000046494137,0.0000113699325,0.000020963806,0.00003294385,0.8423066,0.00027894886,0.15617485,0.0009925672,0.0000118398975],"about_ca_topic_score_codex":0.004797605,"about_ca_topic_score_gemma":0.0030019202,"teacher_disagreement_score":0.0069724703,"about_ca_system_score_codex":0.0034588645,"about_ca_system_score_gemma":0.0024723916,"threshold_uncertainty_score":0.032839537},"labels":[],"label_agreement":null},{"id":"W3134845586","doi":"10.1017/apr.2021.61","title":"Conditions for indexability of restless bandits and an algorithm to compute Whittle index","year":2022,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Heuristic; Generalization; Mathematical optimization; Index (typography); Mathematics; Class (philosophy); Computation; Algorithm; Greedy algorithm; Computer science; Artificial intelligence","score_opus":0.08425595088796484,"score_gpt":0.4533254396725827,"score_spread":0.36906948878461787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134845586","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08336869,0.00008823172,0.9121736,0.00018999219,0.000026806165,0.00011679166,0.00006880811,0.00083418336,0.0031328301],"genre_scores_gemma":[0.6509435,0.000054177348,0.34707856,0.00010298443,0.000025578198,0.00015838628,0.00017243193,0.00013763909,0.0013267099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886584,0.00041768275,0.00008318119,0.00016927149,0.000244488,0.00021957562],"domain_scores_gemma":[0.992109,0.0052305944,0.0007038477,0.00090873137,0.0007239636,0.00032393626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025586064,0.0006207825,0.00080604287,0.0009329684,0.0006170924,0.0016002152,0.0013288213,0.0010623165,0.003752906],"category_scores_gemma":[0.01969911,0.0003304588,0.0005271364,0.00070675235,0.0015040961,0.0022639213,0.0016421833,0.0013128945,0.00049394247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068042235,0.00018475161,0.0038570485,0.000107996566,0.00005623113,0.00018340218,0.00022729128,0.7335119,0.006754692,0.1768829,0.0021322626,0.07542113],"study_design_scores_gemma":[0.000021809148,0.000024534322,0.00009297346,0.0000057578177,0.0000032531084,0.000013171459,0.000011717686,0.975715,0.0014457467,0.02249439,0.00016711601,0.0000046403056],"about_ca_topic_score_codex":0.002953639,"about_ca_topic_score_gemma":0.0027607752,"teacher_disagreement_score":0.003752906,"about_ca_system_score_codex":0.0012706006,"about_ca_system_score_gemma":0.0018713822,"threshold_uncertainty_score":0.013531327},"labels":[],"label_agreement":null},{"id":"W3136224158","doi":"10.1007/978-3-030-85172-9_9","title":"SEH: Size Estimate Hedging for Single-Server Queues","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Queue; Computer science; Scheduling (production processes); Heuristic; Simple (philosophy); Real-time computing; Distributed computing; Mathematical optimization; Computer network; Mathematics; Artificial intelligence","score_opus":0.12103199500715305,"score_gpt":0.4367620829872396,"score_spread":0.31573008798008656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136224158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046635367,0.00066287594,0.93818325,0.00083035894,0.00037007863,0.00020089802,0.0006661558,0.0094488375,0.00300221],"genre_scores_gemma":[0.7333971,0.0004923914,0.25181305,0.00035361858,0.0004904168,0.00020014987,0.0011547421,0.0009073279,0.011191173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823344,0.0005176838,0.00010655333,0.00021068224,0.0006586851,0.00027305319],"domain_scores_gemma":[0.9947542,0.0023511003,0.00024265917,0.0017610742,0.0005705937,0.0003203556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004030324,0.0011069361,0.0016822056,0.0011898322,0.00061999407,0.0023004704,0.0028388451,0.0011177607,0.010178245],"category_scores_gemma":[0.012774686,0.000739345,0.00080369785,0.0013194405,0.001042378,0.0031409378,0.0033274433,0.0025561776,0.0019398761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003962215,0.00050833094,0.002976151,0.00030397862,0.00021615319,0.00024168054,0.00022248311,0.40286148,0.012693719,0.080562994,0.039076302,0.45637456],"study_design_scores_gemma":[0.00015401459,0.00015895175,0.00034631448,0.000010886553,0.000023372537,0.000044787517,0.000022491839,0.95016235,0.004287837,0.0434297,0.0013375924,0.000021760745],"about_ca_topic_score_codex":0.00159057,"about_ca_topic_score_gemma":0.0014579,"teacher_disagreement_score":0.010178245,"about_ca_system_score_codex":0.0011567958,"about_ca_system_score_gemma":0.0018537623,"threshold_uncertainty_score":0.03404957},"labels":[],"label_agreement":null},{"id":"W3154042965","doi":"10.2139/ssrn.3803777","title":"Feature-Based Nonparametric Inventory Control with Censored Demand","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonparametric statistics; Feature (linguistics); Econometrics; Computer science; Control (management); Statistics; Inventory control; Artificial intelligence; Operations research; Mathematics","score_opus":0.026232811545800604,"score_gpt":0.34524579493030144,"score_spread":0.31901298338450085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154042965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044548992,0.00017982186,0.9540637,0.00015243303,0.000038643273,0.000031507432,0.00012311766,0.00025471457,0.00060698274],"genre_scores_gemma":[0.96054274,0.00013772606,0.037054084,0.00006311755,0.000077458426,0.00007713158,0.00022676912,0.000039005008,0.0017820918],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981974,0.0006850385,0.00009835935,0.00042478155,0.00034396496,0.00025041314],"domain_scores_gemma":[0.98835725,0.007976831,0.001378455,0.0010594947,0.0010141182,0.0002138778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004584212,0.0010254312,0.0026726692,0.0007081645,0.00045823993,0.0017730084,0.0024216613,0.0016902093,0.0017743771],"category_scores_gemma":[0.016811818,0.0007639323,0.0008538736,0.0013748799,0.0016496519,0.002654006,0.0014573685,0.0015766886,0.00028317244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072031334,0.00014689493,0.0013304484,0.00012261096,0.00007876679,0.00007348625,0.00005822923,0.93985075,0.0011167092,0.01810284,0.00061523856,0.037783768],"study_design_scores_gemma":[0.00001196622,0.00003077783,0.00021229069,0.000003187435,0.0000063010484,0.000006907457,0.0000023022803,0.9959189,0.00014941845,0.003602623,0.00004970453,0.000005553199],"about_ca_topic_score_codex":0.0042632115,"about_ca_topic_score_gemma":0.0028650763,"teacher_disagreement_score":0.004584212,"about_ca_system_score_codex":0.0010658015,"about_ca_system_score_gemma":0.001073894,"threshold_uncertainty_score":0.024243891},"labels":[],"label_agreement":null},{"id":"W3157613611","doi":"","title":"Online Sparse Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Reinforcement learning; Dimension (graph theory); Upper and lower bounds; Time horizon; Q-learning; Oracle; Mathematics; Lasso (programming language); Mathematical optimization; Computer science; Markov process; Combinatorics; Discrete mathematics; Artificial intelligence; Statistics","score_opus":0.40048191254290866,"score_gpt":0.49729921246262404,"score_spread":0.09681729991971538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157613611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062783174,0.0006849523,0.92910117,0.0014442083,0.00011723932,0.00009825698,0.0002402032,0.0005905677,0.0049401866],"genre_scores_gemma":[0.92852265,0.00027032022,0.06671134,0.0003585426,0.00014185875,0.00018031852,0.00029498985,0.00006624899,0.0034537392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985801,0.0005971172,0.0000527514,0.0003317843,0.00023597205,0.00020233098],"domain_scores_gemma":[0.9909383,0.0070606996,0.0006908505,0.0005719895,0.00035465945,0.00038350082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023309416,0.0010740514,0.0018827583,0.00036169728,0.00040825302,0.0010159086,0.001606502,0.0016028121,0.0031039696],"category_scores_gemma":[0.014279899,0.0005043797,0.00048786664,0.0004411484,0.001662245,0.0019727882,0.0016477478,0.002282195,0.00037519477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024007827,0.00014987522,0.0011901335,0.00012672367,0.000060671253,0.00010503748,0.000053142805,0.93955517,0.00054693094,0.035165407,0.0017266261,0.021080319],"study_design_scores_gemma":[0.000019147352,0.000025335223,0.00006955346,0.000005376287,0.0000034399573,0.0000075193498,0.0000032925757,0.9848232,0.00009993629,0.01478128,0.00015912931,0.0000027124752],"about_ca_topic_score_codex":0.0032746398,"about_ca_topic_score_gemma":0.0028343848,"teacher_disagreement_score":0.0032746398,"about_ca_system_score_codex":0.0012784037,"about_ca_system_score_gemma":0.0014094616,"threshold_uncertainty_score":0.012327373},"labels":[],"label_agreement":null},{"id":"W3158392704","doi":"","title":"On the Suboptimality of Negative Momentum for Minimax Optimization","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Momentum (technical analysis); Minimax; Convergence (economics); Mathematical optimization; Mathematics; Rate of convergence; Simple (philosophy); Applied mathematics; Computer science; Economics; Key (lock)","score_opus":0.47666892159196084,"score_gpt":0.4878975526146724,"score_spread":0.011228631022711544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158392704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028602833,0.0012538804,0.95280886,0.0018539266,0.00021336743,0.0000784881,0.000052662668,0.00022418793,0.014911772],"genre_scores_gemma":[0.8377011,0.0017852276,0.14910701,0.0011137999,0.0002325383,0.00037260776,0.00010560435,0.00043744166,0.00914468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777395,0.001160042,0.00007541524,0.0002920106,0.00041539807,0.00028326912],"domain_scores_gemma":[0.9821675,0.014770106,0.0007654498,0.0008063582,0.0009552345,0.0005352302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064441417,0.00169606,0.0015500647,0.0010887609,0.0012451397,0.0021852425,0.0013631313,0.0017651141,0.0034695116],"category_scores_gemma":[0.039996557,0.0007333848,0.0009708465,0.0006415041,0.005113989,0.0037840374,0.0030944438,0.004169783,0.0005661581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025429588,0.00008810157,0.0012054185,0.00026360256,0.00007224459,0.00026141625,0.00025246965,0.39059606,0.002904053,0.57955694,0.00410141,0.02044401],"study_design_scores_gemma":[0.000020013886,0.000056115507,0.00014944084,0.000059854854,0.000009370485,0.000043979457,0.0000262707,0.88522124,0.00056264986,0.112910636,0.00092471985,0.000015717322],"about_ca_topic_score_codex":0.0029579098,"about_ca_topic_score_gemma":0.0021194355,"teacher_disagreement_score":0.0064441417,"about_ca_system_score_codex":0.0017810074,"about_ca_system_score_gemma":0.0025630947,"threshold_uncertainty_score":0.034080267},"labels":[],"label_agreement":null},{"id":"W3162671465","doi":"10.1109/infocom42981.2021.9488698","title":"Delay-Tolerant Constrained OCO with Application to Network Resource Allocation","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); Ontario Tech University; University of Toronto","funders":"","keywords":"Regret; Computer science; Mathematical optimization; Benchmark (surveying); Sequence (biology); Constraint (computer-aided design); Convex function; Convex optimization; Resource allocation; Sublinear function; Term (time); Regular polygon; Mathematics","score_opus":0.04998465779926876,"score_gpt":0.3846377056724134,"score_spread":0.33465304787314465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162671465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027156968,0.0010240438,0.9647459,0.000768006,0.00017883952,0.00012372184,0.0001305769,0.0002817829,0.0055902894],"genre_scores_gemma":[0.8955005,0.00071482954,0.09921145,0.00039370294,0.00017462991,0.0001836694,0.00015210996,0.00012674354,0.0035423234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987998,0.00038511507,0.000046881418,0.00026088304,0.00027467107,0.00023264193],"domain_scores_gemma":[0.9965964,0.0022452346,0.00039545816,0.00025212913,0.0002847998,0.00022592733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018499311,0.0016863404,0.0014532912,0.00045233418,0.00051431253,0.0012804478,0.0016271523,0.0012846685,0.001923237],"category_scores_gemma":[0.0075152954,0.00043423046,0.00050226704,0.0012198439,0.0013134799,0.0014721868,0.0015495981,0.0019878622,0.00021432032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010171826,0.000046388894,0.00030455517,0.000067828594,0.000019782101,0.000077681005,0.00002696546,0.97507817,0.0005657202,0.011645797,0.0008862325,0.011179165],"study_design_scores_gemma":[0.000006116524,0.000017229178,0.00003164156,0.0000030325257,0.0000030760482,0.000011192074,0.000004550511,0.99596953,0.00016408313,0.0035318816,0.00025460098,0.0000030102672],"about_ca_topic_score_codex":0.0057475725,"about_ca_topic_score_gemma":0.0034158668,"teacher_disagreement_score":0.0057475725,"about_ca_system_score_codex":0.0014542795,"about_ca_system_score_gemma":0.0017044718,"threshold_uncertainty_score":0.011428237},"labels":[],"label_agreement":null},{"id":"W3167121994","doi":"10.1007/978-3-030-78270-2_49","title":"Multi-armed Bandit Algorithms for Adaptive Learning: A Survey","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Computer science; Adaptive learning; Artificial intelligence; Machine learning","score_opus":0.20252700003973068,"score_gpt":0.420883279384972,"score_spread":0.21835627934524132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167121994","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028167376,0.21343867,0.77175015,0.0010864028,0.00044536096,0.000063462874,0.000111247675,0.00044882356,0.009839155],"genre_scores_gemma":[0.120482884,0.3101536,0.5502674,0.0016840498,0.0038589702,0.0005092172,0.0006794489,0.00050390733,0.011860506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99786913,0.00078431156,0.00019910357,0.00045581016,0.0005693588,0.00012221948],"domain_scores_gemma":[0.995452,0.0034680457,0.00019917781,0.00037589498,0.00043267597,0.00007235383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033010715,0.0021710177,0.0035361452,0.0018179647,0.0006778683,0.0038725354,0.0029865594,0.0033989341,0.003963196],"category_scores_gemma":[0.00793594,0.001220683,0.0014555502,0.0066699674,0.0014948794,0.0038130467,0.0022044322,0.0036082289,0.0037359898],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001557906,0.00029424013,0.00079049193,0.0017696533,0.00019505927,0.000043581258,0.000095890515,0.1014349,0.00083059166,0.078635216,0.0092558395,0.8064988],"study_design_scores_gemma":[0.00008031932,0.00033835822,0.0008163065,0.0008051699,0.00014282283,0.00035920282,0.00009790407,0.75926477,0.001820026,0.18112813,0.05505806,0.000088905625],"about_ca_topic_score_codex":0.0015243632,"about_ca_topic_score_gemma":0.0012095268,"teacher_disagreement_score":0.003963196,"about_ca_system_score_codex":0.00087843026,"about_ca_system_score_gemma":0.0012254233,"threshold_uncertainty_score":0.017457902},"labels":[],"label_agreement":null},{"id":"W3170243566","doi":"10.48550/arxiv.2106.06885","title":"Online Learning with Optimism and Delay","year":2021,"lang":"en","type":"preprint","venue":"OpenBU (Boston University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Optimism; Computer science; Benchmarking; Online learning; Perspective (graphical); Robustness (evolution); Optimism bias; Machine learning; Artificial intelligence; Psychology; Multimedia; Marketing","score_opus":0.09327714844652883,"score_gpt":0.36399998972249875,"score_spread":0.2707228412759699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170243566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05612,0.0008659188,0.93788534,0.0012015434,0.00010245886,0.00004669422,0.00010281437,0.00077406387,0.0029011078],"genre_scores_gemma":[0.8950326,0.00037689856,0.10121053,0.00040690936,0.00012572076,0.00010180187,0.00014138361,0.00010058696,0.0025036715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985385,0.0006407448,0.00008103625,0.00028635692,0.0002519112,0.0002015236],"domain_scores_gemma":[0.9882145,0.008973687,0.00083017384,0.0010474273,0.00057025737,0.00036395254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035679177,0.001306926,0.0013316319,0.0004645335,0.00056004524,0.001850256,0.0021250045,0.0014719743,0.0021029448],"category_scores_gemma":[0.020553762,0.0006717456,0.00055328675,0.0006564404,0.001561901,0.0029942023,0.002057486,0.0031526468,0.00045134334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003764666,0.0000807375,0.0013663543,0.000118769174,0.00006937668,0.000060309434,0.00010302532,0.91645044,0.0009981652,0.039823964,0.0018369586,0.038715493],"study_design_scores_gemma":[0.000023751018,0.000035938498,0.00006823188,0.000011502253,0.000009882945,0.000014854194,0.000009724974,0.9730622,0.0005131061,0.025965791,0.00027867674,0.0000062694376],"about_ca_topic_score_codex":0.0020218752,"about_ca_topic_score_gemma":0.0019395836,"teacher_disagreement_score":0.0035679177,"about_ca_system_score_codex":0.0014451176,"about_ca_system_score_gemma":0.0017419553,"threshold_uncertainty_score":0.018869162},"labels":[],"label_agreement":null},{"id":"W3173847742","doi":"10.1017/9781108571401.019","title":"Foundations of Information Theory","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information theory; Internet privacy; World Wide Web; Information retrieval; Mathematics","score_opus":0.08999575418988723,"score_gpt":0.3177145385875525,"score_spread":0.22771878439766527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173847742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034466642,0.14332826,0.43424857,0.024796458,0.0020784943,0.00011227204,0.0019110326,0.00070490496,0.38937333],"genre_scores_gemma":[0.29384246,0.3015693,0.24392112,0.008961561,0.011298747,0.00089213107,0.0031756975,0.00061075436,0.13572828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973646,0.0010225173,0.00015041855,0.00032507544,0.00097462337,0.00016288058],"domain_scores_gemma":[0.9928174,0.005497419,0.00022588861,0.00084888056,0.00044754622,0.00016284584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027346693,0.0011164773,0.0012849498,0.0030625665,0.0011415858,0.007022245,0.0011670953,0.002256563,0.017235354],"category_scores_gemma":[0.007522241,0.0007004207,0.0009657816,0.0042421874,0.005018699,0.0065706614,0.0019338606,0.0042307237,0.007664855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005287005,0.00000845914,0.0000943342,0.00024149969,0.000023046729,0.000048157675,0.00008136786,0.0009572631,0.00011589226,0.9442369,0.022244452,0.031943407],"study_design_scores_gemma":[0.0000020328703,0.000004268585,0.00007215497,0.00010971712,0.00000486274,0.000056396213,0.000018506416,0.0010502667,0.000054583365,0.9626864,0.0359353,0.0000055295886],"about_ca_topic_score_codex":0.0012306613,"about_ca_topic_score_gemma":0.0008661556,"teacher_disagreement_score":0.017235354,"about_ca_system_score_codex":0.0032705425,"about_ca_system_score_gemma":0.0020315014,"threshold_uncertainty_score":0.057658076},"labels":[],"label_agreement":null},{"id":"W3174263485","doi":"","title":"Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Randomness; Intuition; Computer science; Mathematical economics; Mathematical optimization; Fictitious play; Mathematics; Game theory; Machine learning; Statistics","score_opus":0.1626154911242037,"score_gpt":0.42643700495823694,"score_spread":0.26382151383403324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174263485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13861638,0.0006513917,0.8448364,0.0018324716,0.00009896597,0.000105438376,0.0002043953,0.00025122645,0.013403447],"genre_scores_gemma":[0.9608389,0.00024079374,0.03472192,0.00037960976,0.00012563409,0.00017412352,0.0000836412,0.000048910282,0.0033863548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467635,0.00266699,0.00018000079,0.0007854932,0.0007421059,0.00094905106],"domain_scores_gemma":[0.98528093,0.01070429,0.0015952281,0.0010926473,0.0006343409,0.00069249055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060250578,0.0016394827,0.0023894133,0.00077482295,0.0010640783,0.0028748452,0.002633716,0.0030438558,0.0016764068],"category_scores_gemma":[0.020004814,0.0008338852,0.0013603248,0.001233412,0.0034255257,0.0030117389,0.0030846158,0.0027607896,0.00046539426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035807147,0.000121972706,0.0008491413,0.00010814575,0.00011119243,0.00026537577,0.00013233045,0.8836059,0.0014881981,0.1061936,0.0011636659,0.005602449],"study_design_scores_gemma":[0.000036648325,0.00007049189,0.00013371029,0.000013760775,0.000015920057,0.000056956436,0.000028253784,0.9452104,0.00035406885,0.053831577,0.00023492234,0.000013304397],"about_ca_topic_score_codex":0.0020276092,"about_ca_topic_score_gemma":0.0012407671,"teacher_disagreement_score":0.0060250578,"about_ca_system_score_codex":0.002116095,"about_ca_system_score_gemma":0.0016868623,"threshold_uncertainty_score":0.031863928},"labels":[],"label_agreement":null},{"id":"W3174325474","doi":"","title":"Asymptotically Optimal Information-Directed Sampling","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Asymptotically optimal algorithm; Frequentist inference; Regret; Thompson sampling; Mathematical optimization; Computer science; Simple (philosophy); Connection (principal bundle); Upper and lower bounds; Sampling (signal processing); Mathematics; Bayesian probability; Artificial intelligence; Bayesian inference; Machine learning","score_opus":0.1378188340422346,"score_gpt":0.4246927229571403,"score_spread":0.2868738889149057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174325474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010814827,0.0001999061,0.9849606,0.0003605152,0.00004652952,0.000079547564,0.000073843046,0.00045731434,0.0030068976],"genre_scores_gemma":[0.49505052,0.000335307,0.49849546,0.00052804244,0.00014818266,0.00045259946,0.00043527375,0.00023267105,0.004321934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974957,0.0012015849,0.000096964046,0.0003619257,0.00061319885,0.00023064514],"domain_scores_gemma":[0.9924948,0.0053817946,0.00038482167,0.0008692683,0.00053874584,0.00033047804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036710366,0.0009870294,0.0016387127,0.0009180969,0.00066885725,0.0017388593,0.0023374655,0.0016784926,0.00370083],"category_scores_gemma":[0.021473106,0.0006957942,0.0007564368,0.0010003529,0.0017789528,0.0021047136,0.0023588694,0.002659004,0.0010170378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004184564,0.00026293762,0.0014959854,0.00021053744,0.0000863471,0.00013270447,0.00017411738,0.5031307,0.0025361294,0.35481563,0.006423927,0.13031259],"study_design_scores_gemma":[0.000037061847,0.000032904034,0.00006656585,0.000016746635,0.000006940715,0.000028445831,0.000008898449,0.92540944,0.00060503185,0.07284599,0.000934264,0.0000077104605],"about_ca_topic_score_codex":0.0018097862,"about_ca_topic_score_gemma":0.0026285956,"teacher_disagreement_score":0.00370083,"about_ca_system_score_codex":0.002047173,"about_ca_system_score_gemma":0.002524137,"threshold_uncertainty_score":0.019414544},"labels":[],"label_agreement":null},{"id":"W3175059381","doi":"10.1017/9781108571401.028","title":"Stochastic Linear Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Mathematics; Mathematical optimization; Mathematical analysis","score_opus":0.10763108277616515,"score_gpt":0.3067051927718164,"score_spread":0.19907410999565125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175059381","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011607533,0.007436561,0.8095174,0.0043756035,0.00074854004,0.00005163035,0.00078761915,0.0009300738,0.16454498],"genre_scores_gemma":[0.4701847,0.014686756,0.17960279,0.0025401134,0.0022979912,0.0004999346,0.0018349912,0.0007608776,0.3275918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992285,0.00034136814,0.000030215848,0.00013742258,0.00018664838,0.000075853466],"domain_scores_gemma":[0.997335,0.0020746782,0.00011117398,0.00026370812,0.00012742124,0.00008797219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015783078,0.0010800682,0.0011177383,0.0004702523,0.00042328794,0.0024272858,0.0010997577,0.0014714684,0.022013336],"category_scores_gemma":[0.0058262674,0.0005043763,0.00075406895,0.0010792634,0.0013052393,0.0022652799,0.0011296329,0.0028581903,0.008054891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115153496,0.000048735816,0.00030231694,0.0002430784,0.00006451867,0.00009502072,0.000057961483,0.10221737,0.0009052964,0.7819905,0.02761516,0.086344935],"study_design_scores_gemma":[0.000026904638,0.00003995124,0.00023041824,0.00013084774,0.000021143407,0.00007366267,0.000018847744,0.27396336,0.00054582924,0.7016452,0.02327951,0.000024330879],"about_ca_topic_score_codex":0.00081192545,"about_ca_topic_score_gemma":0.001076992,"teacher_disagreement_score":0.022013336,"about_ca_system_score_codex":0.0010683022,"about_ca_system_score_gemma":0.00072330533,"threshold_uncertainty_score":0.073641956},"labels":[],"label_agreement":null},{"id":"W3175406278","doi":"10.1109/tai.2021.3074122","title":"Optimal Policy for Bernoulli Bandits: Computation and Algorithm Gauge","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Bernoulli's principle; Algorithm; Mathematical optimization; Computation; Variety (cybernetics); Approximate Bayesian computation; Time horizon; Thompson sampling; Bayesian probability; Artificial intelligence; Mathematics; Inference","score_opus":0.16748091965585976,"score_gpt":0.45981303194073087,"score_spread":0.2923321122848711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175406278","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031341102,0.00035835803,0.96078783,0.00044877964,0.000071426504,0.00010610636,0.00007046616,0.00094735634,0.0058685527],"genre_scores_gemma":[0.48941353,0.00038150095,0.506654,0.00029648744,0.00007218124,0.00032597434,0.00026305698,0.0003925274,0.0022006836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807954,0.00080619886,0.0001044212,0.00029883458,0.0004703081,0.00024059597],"domain_scores_gemma":[0.99107504,0.006815203,0.00045771975,0.0007097325,0.0006583996,0.00028391482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034073049,0.0009415882,0.0013252225,0.00087487523,0.0007460592,0.0021417742,0.0013074285,0.0015225484,0.004419297],"category_scores_gemma":[0.023098033,0.00048500183,0.00057607476,0.00097373716,0.0015863162,0.0022237264,0.0014524873,0.0021681325,0.00071259635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022322469,0.00011643446,0.0012745314,0.00009208212,0.000028400684,0.00004485106,0.000080866754,0.8605194,0.0011473557,0.06359945,0.0022708382,0.070602626],"study_design_scores_gemma":[0.000015759852,0.000017565715,0.000061269624,0.0000125312345,0.000003886993,0.000010392651,0.000009218609,0.98608404,0.0005238388,0.012922401,0.00033457775,0.000004491913],"about_ca_topic_score_codex":0.0073711546,"about_ca_topic_score_gemma":0.005767425,"teacher_disagreement_score":0.0073711546,"about_ca_system_score_codex":0.0025644714,"about_ca_system_score_gemma":0.0049948096,"threshold_uncertainty_score":0.018606663},"labels":[],"label_agreement":null},{"id":"W3175841314","doi":"","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture MDPs","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Mathematics; Minimax; Logarithm; Estimator; Bounded function; Combinatorics; Discrete mathematics; Regret; Mathematical optimization; Markov process; Computer science; Artificial intelligence; Statistics","score_opus":0.12812209112907322,"score_gpt":0.42388866202890896,"score_spread":0.2957665708998357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175841314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043236166,0.00092958193,0.9511062,0.0009550775,0.00006668054,0.000076234755,0.00009655034,0.00035758005,0.0031758354],"genre_scores_gemma":[0.8814241,0.0006222217,0.1108362,0.00050688157,0.00011624992,0.00027325237,0.0002337445,0.00019284667,0.0057944315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983766,0.000770126,0.00006622304,0.00035622626,0.00021294734,0.00021798749],"domain_scores_gemma":[0.98690784,0.010995051,0.0008075689,0.00043617058,0.00042486706,0.00042861424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042975447,0.001944089,0.0026607406,0.0006502641,0.0005695617,0.0016168846,0.0022107542,0.0022656021,0.0032344626],"category_scores_gemma":[0.019237835,0.0011873025,0.0009558189,0.00064574525,0.0026436145,0.002936811,0.0026870524,0.004106457,0.000481903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012876831,0.00006390307,0.0005349607,0.000078546815,0.00005560245,0.000057335466,0.000048943595,0.96002555,0.0003948712,0.030244514,0.0005600091,0.007806947],"study_design_scores_gemma":[0.000011828871,0.000016274147,0.000033297652,0.0000048409297,0.0000039308916,0.000003476604,0.0000028916822,0.9901966,0.000087082204,0.009557727,0.00007919826,0.0000028890609],"about_ca_topic_score_codex":0.0065328125,"about_ca_topic_score_gemma":0.003883637,"teacher_disagreement_score":0.0065328125,"about_ca_system_score_codex":0.002921406,"about_ca_system_score_gemma":0.002061725,"threshold_uncertainty_score":0.022727847},"labels":[],"label_agreement":null},{"id":"W3177486623","doi":"10.1017/9781108571401.033","title":"Foundations of Convex Analysis","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regular polygon; Content (measure theory); Mathematics; Geometry","score_opus":0.1365231072922998,"score_gpt":0.3444356365794961,"score_spread":0.2079125292871963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177486623","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026593502,0.09494886,0.41140577,0.009215174,0.00212283,0.00005170277,0.0018478791,0.0007877407,0.47696063],"genre_scores_gemma":[0.2030896,0.20538916,0.27531725,0.004490462,0.008792112,0.00053946424,0.0035598564,0.0016383148,0.29718384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905044,0.00025825488,0.00004359656,0.00015708215,0.0004220431,0.00006854392],"domain_scores_gemma":[0.99876,0.00072744524,0.00005775452,0.00020670818,0.00018309033,0.00006497071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013070606,0.001115596,0.00093651435,0.0016487333,0.00064593606,0.0028760482,0.00070716604,0.000904137,0.021475356],"category_scores_gemma":[0.0031884627,0.00054987316,0.0009539448,0.0024923044,0.0021940146,0.0020178305,0.001406917,0.0038954292,0.011535677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008184364,0.000010199359,0.0001290189,0.00024550917,0.000030346488,0.000043778324,0.00006636208,0.003620713,0.0003849655,0.8262677,0.09270866,0.07648451],"study_design_scores_gemma":[0.000003976447,0.000009345849,0.00034538683,0.00013090452,0.000009328717,0.0000863337,0.000022275863,0.004368533,0.00020937982,0.8310617,0.16374229,0.000010648934],"about_ca_topic_score_codex":0.0021414084,"about_ca_topic_score_gemma":0.0021065332,"teacher_disagreement_score":0.021475356,"about_ca_system_score_codex":0.0021149262,"about_ca_system_score_gemma":0.0012488782,"threshold_uncertainty_score":0.07184219},"labels":[],"label_agreement":null},{"id":"W3178495416","doi":"10.48550/arxiv.2107.06196","title":"No Regrets for Learning the Prior in Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Task (project management); Thompson sampling; Key (lock); Computer science; Bayesian probability; Bayes' theorem; Artificial intelligence; Sampling (signal processing); Prior probability; Machine learning; Mathematical optimization; Mathematics; Engineering; Computer vision","score_opus":0.25855875260942035,"score_gpt":0.3217372327608468,"score_spread":0.06317848015142646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178495416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03835438,0.0010246676,0.9504519,0.0016539057,0.00014961262,0.000110229936,0.00015708843,0.00079064467,0.007307559],"genre_scores_gemma":[0.7638656,0.0007674488,0.22297001,0.001161066,0.00034606742,0.00065997534,0.00049073854,0.0005809026,0.009158147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99437946,0.0033440192,0.00019463785,0.000816918,0.0008268034,0.00043815866],"domain_scores_gemma":[0.9761594,0.019311119,0.0010359542,0.001983759,0.00083923014,0.00067057053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007806905,0.0020399059,0.002623146,0.000767905,0.0016509482,0.0026602014,0.002867002,0.0032355895,0.0045493282],"category_scores_gemma":[0.042477466,0.0010603544,0.0011504457,0.0010289458,0.0032186694,0.00462378,0.0029158972,0.004758613,0.0011982505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006255785,0.00021595038,0.0016839242,0.00019849802,0.000112628775,0.000099983605,0.00020337704,0.76830053,0.001259538,0.15970649,0.006187513,0.061405957],"study_design_scores_gemma":[0.0000408066,0.000047055044,0.00013983014,0.000021648199,0.000012965707,0.000019788054,0.000013814117,0.9059085,0.00033979194,0.09283816,0.000605922,0.000011643208],"about_ca_topic_score_codex":0.003907772,"about_ca_topic_score_gemma":0.0040484504,"teacher_disagreement_score":0.007806905,"about_ca_system_score_codex":0.0026897897,"about_ca_system_score_gemma":0.0025915476,"threshold_uncertainty_score":0.041287363},"labels":[],"label_agreement":null},{"id":"W3182076562","doi":"10.1111/poms.13778","title":"Sublinear regret for learning POMDPs","year":2022,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Markov decision process; Reinforcement learning; Oracle; Computer science; Sublinear function; Partially observable Markov decision process; Mathematical optimization; Upper and lower bounds; Time horizon; Artificial intelligence; Markov chain; Machine learning; Markov process; Markov model; Mathematics; Statistics; Discrete mathematics","score_opus":0.12616657133808326,"score_gpt":0.43079632801594514,"score_spread":0.30462975667786185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182076562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023302265,0.0009669056,0.96565574,0.0015242564,0.00012707377,0.00007023625,0.00028689438,0.00070024544,0.007366427],"genre_scores_gemma":[0.8633843,0.00087730336,0.12419863,0.00060804246,0.00021140219,0.00043751323,0.00068634306,0.00032960132,0.009266939],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997026,0.0013230187,0.00011669949,0.0005154307,0.0006244422,0.0003944077],"domain_scores_gemma":[0.9812136,0.016153948,0.00095929165,0.0005090978,0.00061936607,0.0005446898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042320956,0.0018722134,0.0019484774,0.00080032187,0.0006866451,0.0021958319,0.0020976139,0.0020156845,0.004793979],"category_scores_gemma":[0.022835566,0.0010174152,0.0013530067,0.00076956867,0.002428145,0.003196631,0.0023299493,0.0039754766,0.0005536967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011024109,0.000056929053,0.00047447035,0.0001269333,0.000046257268,0.00006262823,0.0000574994,0.9126671,0.0002483826,0.07572598,0.0016984259,0.008725126],"study_design_scores_gemma":[0.000009198547,0.000011204869,0.000029457959,0.000006433261,0.000003115488,0.000003699289,0.000002809377,0.97449046,0.00007422409,0.025210707,0.00015577553,0.0000028341478],"about_ca_topic_score_codex":0.0070251347,"about_ca_topic_score_gemma":0.0051503037,"teacher_disagreement_score":0.0070251347,"about_ca_system_score_codex":0.0040895375,"about_ca_system_score_gemma":0.002676037,"threshold_uncertainty_score":0.029671788},"labels":[],"label_agreement":null},{"id":"W318353367","doi":"","title":"Using Adaptive Consultation of Experts to Improve Convergence Rates in Multiagent Learning (Short Paper)","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Regret; Computer science; Outcome (game theory); Advice (programming); Convergence (economics); Set (abstract data type); Nash equilibrium; Class (philosophy); Multi-agent system; Process (computing); Frame (networking); Order (exchange); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Mathematical economics","score_opus":0.28694779666301773,"score_gpt":0.48108388591712026,"score_spread":0.19413608925410253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W318353367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026927887,0.00050537626,0.9684588,0.0005361525,0.00008154508,0.00006805761,0.000013398489,0.0004101547,0.0029986545],"genre_scores_gemma":[0.7707876,0.0003356758,0.22355072,0.000476278,0.00020211788,0.00022694361,0.00004945253,0.0001680893,0.0042031147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971238,0.0017482208,0.00007922924,0.0003385306,0.0004494193,0.00026068377],"domain_scores_gemma":[0.98531336,0.0113791395,0.0007754657,0.00074870116,0.0012971333,0.0004862664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006111944,0.001213696,0.0014190199,0.0007724764,0.0007194929,0.0008314874,0.0019942191,0.0025371476,0.0025950354],"category_scores_gemma":[0.027019873,0.000484452,0.00060741504,0.0005650056,0.0014695514,0.0018187369,0.0018502366,0.0018277107,0.0006878049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000510787,0.00020298624,0.0013987897,0.000120232915,0.000091021626,0.00019049454,0.00025924013,0.8720554,0.0027885323,0.025985342,0.003943335,0.09245384],"study_design_scores_gemma":[0.000033955526,0.00006903956,0.00008190656,0.000008231371,0.000009153503,0.000019992973,0.000007701895,0.99364954,0.00065012695,0.0050484566,0.0004151357,0.0000066483685],"about_ca_topic_score_codex":0.0027775946,"about_ca_topic_score_gemma":0.0015676311,"teacher_disagreement_score":0.006111944,"about_ca_system_score_codex":0.001110422,"about_ca_system_score_gemma":0.0009974084,"threshold_uncertainty_score":0.03232348},"labels":[],"label_agreement":null},{"id":"W3184471030","doi":"","title":"Deep Reinforcement Learning for Optimal Stopping with Application in Financial Engineering","year":2021,"lang":"en","type":"article","venue":"Les Cahiers du GERAD","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Optimal stopping; Reinforcement learning; Computer science; Benchmark (surveying); Categorical variable; Stochastic control; Deep learning; Artificial intelligence; Mathematical optimization; Machine learning; Optimal control; Mathematics","score_opus":0.023690737743615155,"score_gpt":0.3158420411063364,"score_spread":0.29215130336272127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184471030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015881196,0.0049455552,0.97367847,0.001283521,0.00014529114,0.00003872781,0.00007593391,0.00040424464,0.0035471441],"genre_scores_gemma":[0.79115593,0.0042884285,0.19804637,0.0005097839,0.00026217237,0.0002497173,0.00025718048,0.00016046311,0.0050699543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992223,0.0003436784,0.000052995456,0.00014250378,0.0001697615,0.00006877101],"domain_scores_gemma":[0.9936326,0.005217037,0.00029718014,0.0001808272,0.0004924289,0.00017994126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027913023,0.0012185873,0.0016440151,0.00082612934,0.00042714213,0.0013264586,0.0011429971,0.0017020184,0.003221501],"category_scores_gemma":[0.014576906,0.0005364098,0.00064096844,0.001073084,0.001435846,0.0013438156,0.0013887865,0.0032963585,0.00042793338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006981685,0.00007966509,0.0013155878,0.00021914537,0.00006820371,0.000059328904,0.000065596185,0.886597,0.00062623876,0.05738948,0.0013541278,0.052155957],"study_design_scores_gemma":[0.000008325746,0.00001636262,0.000066695946,0.000015977133,0.000004672156,0.0000051785246,0.0000033329943,0.9806224,0.00014862638,0.018683622,0.00042048184,0.0000042201364],"about_ca_topic_score_codex":0.006102272,"about_ca_topic_score_gemma":0.004198622,"teacher_disagreement_score":0.006102272,"about_ca_system_score_codex":0.0016452122,"about_ca_system_score_gemma":0.0017008245,"threshold_uncertainty_score":0.014761984},"labels":[],"label_agreement":null},{"id":"W3186527071","doi":"10.23919/acc50511.2021.9482649","title":"On Data-driven Multi-Product Pricing","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Computer science; Boosting (machine learning); Mathematical optimization; Parametric statistics; Task (project management); Product (mathematics); Robust optimization; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.41519689702321394,"score_gpt":0.5222217993256624,"score_spread":0.10702490230244843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186527071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008659198,0.0006921662,0.9878248,0.00079168606,0.00008718868,0.000032736472,0.00007562842,0.00009952978,0.0017371012],"genre_scores_gemma":[0.7395601,0.0022904328,0.25010014,0.0009129121,0.0007767489,0.00031056657,0.00046830153,0.00024130501,0.0053395154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961383,0.0022391134,0.00013981052,0.00052722194,0.00067889364,0.00027675173],"domain_scores_gemma":[0.9805932,0.015239403,0.0009159193,0.001370344,0.0014627906,0.00041835342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009774202,0.0013494883,0.0024919193,0.0012454262,0.00067915197,0.00241457,0.0024976828,0.0021781994,0.0029406785],"category_scores_gemma":[0.036495175,0.0009912674,0.0011084973,0.001993795,0.0022797468,0.004932007,0.0028366675,0.0038459313,0.0005021105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007209564,0.0000749854,0.00070625136,0.00010065669,0.000056072415,0.00010053121,0.00004742689,0.8469212,0.00033388514,0.12739061,0.0015505112,0.022645868],"study_design_scores_gemma":[0.0000053188523,0.000009658092,0.00006434734,0.0000069239914,0.0000039025495,0.000009782606,0.0000026671157,0.9673235,0.00007880521,0.032196067,0.0002941577,0.00000494557],"about_ca_topic_score_codex":0.003925657,"about_ca_topic_score_gemma":0.002236498,"teacher_disagreement_score":0.009774202,"about_ca_system_score_codex":0.0019554072,"about_ca_system_score_gemma":0.0018579299,"threshold_uncertainty_score":0.05169159},"labels":[],"label_agreement":null},{"id":"W3186893068","doi":"10.2139/ssrn.3841273","title":"A General Framework for Resource Constrained Revenue Management with Demand Learning and Large Action Space","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Space (punctuation); Action (physics); Action learning; Revenue; Computer science; Business; Microeconomics; Economics; Mathematical economics; Mathematics; Mathematics education; Finance","score_opus":0.03539432286056208,"score_gpt":0.39525911774602984,"score_spread":0.35986479488546774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186893068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003753943,0.00033616592,0.9849694,0.001299233,0.00007695626,0.00006819534,0.00024590167,0.00013329886,0.009117011],"genre_scores_gemma":[0.6145823,0.0020941757,0.33585033,0.0013137177,0.00074106076,0.00090732006,0.0006467402,0.00029810768,0.043566197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982236,0.00067533285,0.00007291814,0.00037773396,0.0003301804,0.00032015643],"domain_scores_gemma":[0.99687225,0.0020531635,0.00021758638,0.00027702193,0.00034985557,0.00023018617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003375106,0.0015840975,0.0027218666,0.001009511,0.0010090681,0.0035721345,0.004410664,0.0033725407,0.016090421],"category_scores_gemma":[0.008264334,0.0010777545,0.0016806648,0.0021169954,0.0026887665,0.0050934856,0.0035355971,0.004065866,0.0016704879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003313003,0.00008085656,0.00018898617,0.00011389149,0.000038602608,0.00009594879,0.0000690256,0.38952285,0.0003964342,0.5944708,0.0041378806,0.010851643],"study_design_scores_gemma":[0.000021770098,0.0000205701,0.000057030775,0.000017136781,0.000011762883,0.000029132,0.000019038718,0.72944605,0.00007173484,0.2683862,0.001906051,0.00001344353],"about_ca_topic_score_codex":0.007959848,"about_ca_topic_score_gemma":0.007049062,"teacher_disagreement_score":0.016090421,"about_ca_system_score_codex":0.0028101986,"about_ca_system_score_gemma":0.003583696,"threshold_uncertainty_score":0.053827822},"labels":[],"label_agreement":null},{"id":"W3187572640","doi":"10.24963/ijcai.2021/481","title":"Toward Optimal Solution for the Context-Attentive Bandit Problem","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Thompson sampling; Regret; Computer science; Context (archaeology); Dialog box; Variety (cybernetics); Machine learning; Artificial intelligence; Recommender system; Baseline (sea); Sampling (signal processing); World Wide Web","score_opus":0.21702170598571818,"score_gpt":0.4445649393414074,"score_spread":0.2275432333556892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187572640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040287826,0.0018699405,0.9511175,0.0014042126,0.00012772126,0.00018698619,0.00020772885,0.00046735696,0.0043307417],"genre_scores_gemma":[0.5944111,0.0012158065,0.39658383,0.0012904521,0.00033543073,0.0006787952,0.00083090557,0.000255746,0.004397987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983675,0.0009830414,0.00006995097,0.0002971588,0.00014077516,0.00014154709],"domain_scores_gemma":[0.9886544,0.009971836,0.0004645151,0.00028359974,0.00039226707,0.00023349067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004463718,0.0019593877,0.002819533,0.0010433478,0.0008479301,0.0017293155,0.001971432,0.003246422,0.004244442],"category_scores_gemma":[0.015012866,0.0009011694,0.0009944371,0.0014046691,0.0016654426,0.002216644,0.0018315432,0.003412263,0.0010371682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005831044,0.00042777814,0.0030496155,0.00041992523,0.00018375082,0.00014881248,0.000303737,0.7955399,0.00097463524,0.059660576,0.009872368,0.12883583],"study_design_scores_gemma":[0.000042702624,0.000049365568,0.00015200663,0.00003353913,0.000015667121,0.000019448684,0.000033433233,0.97151864,0.0001542888,0.02740912,0.00056443905,0.000007377623],"about_ca_topic_score_codex":0.005839764,"about_ca_topic_score_gemma":0.0062831547,"teacher_disagreement_score":0.005839764,"about_ca_system_score_codex":0.0012561382,"about_ca_system_score_gemma":0.0023532934,"threshold_uncertainty_score":0.023606658},"labels":[],"label_agreement":null},{"id":"W3193611757","doi":"10.1109/twc.2022.3141094","title":"Unifying Futures and Spot Market: Overbooking-Enabled Resource Trading in Mobile Edge Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Futures contract; Negotiation; Dynamic pricing; Forward contract; Spot market; Profit (economics); Incentive; Operations research; Business; Microeconomics; Economics; Electricity","score_opus":0.06693934700005788,"score_gpt":0.3613072301788384,"score_spread":0.29436788317878054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193611757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16497925,0.0009116077,0.82818097,0.00033785164,0.00010795787,0.0001415001,0.00006717201,0.000338051,0.004935637],"genre_scores_gemma":[0.9653521,0.00017637202,0.033075463,0.0000696214,0.000034419765,0.000040559797,0.000027165766,0.000018989953,0.0012052414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987785,0.00041923884,0.000062692736,0.00023450852,0.00030062627,0.00020433727],"domain_scores_gemma":[0.9987644,0.0005702342,0.000183077,0.00017129432,0.00013674825,0.00017418525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019148918,0.0006930831,0.0010845538,0.00046822874,0.0007263331,0.0014306464,0.0017916817,0.0010503863,0.001851284],"category_scores_gemma":[0.0031086465,0.000294628,0.00046715813,0.0006882187,0.00097312225,0.0038749785,0.001744952,0.0010404409,0.00015447086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012379409,0.00048143166,0.0031386358,0.00022669007,0.00012587162,0.0013154318,0.00052182266,0.62157387,0.035701387,0.121897765,0.002807241,0.21097195],"study_design_scores_gemma":[0.000024212173,0.00013862288,0.00021714884,0.0000062964505,0.000012248772,0.0001742663,0.000045945184,0.9810703,0.0020796456,0.015238284,0.0009711385,0.000021896123],"about_ca_topic_score_codex":0.0013984079,"about_ca_topic_score_gemma":0.0010737957,"teacher_disagreement_score":0.0019148918,"about_ca_system_score_codex":0.0006194247,"about_ca_system_score_gemma":0.0009663427,"threshold_uncertainty_score":0.010127008},"labels":[],"label_agreement":null},{"id":"W3193685318","doi":"10.1017/9781108571401.047","title":"Markov Decision Processes","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Markov decision process; Markov chain; Markov process; Mathematics; Machine learning; Statistics","score_opus":0.09019827160613175,"score_gpt":0.318277106807889,"score_spread":0.22807883520175726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193685318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067252996,0.024521971,0.5152758,0.007998793,0.001379505,0.00016605898,0.0063436837,0.0010546502,0.43653426],"genre_scores_gemma":[0.27361238,0.044904877,0.10925295,0.0022818788,0.0017327645,0.000672351,0.009366866,0.00053481944,0.5576411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995616,0.00015429127,0.000020488778,0.000099090255,0.000120935176,0.000043604596],"domain_scores_gemma":[0.99875677,0.0009131573,0.00004930567,0.00010542223,0.00011481089,0.00006059336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074309536,0.0009066137,0.00080878695,0.00058702327,0.00040130978,0.0018949492,0.00079819694,0.0011889458,0.070203245],"category_scores_gemma":[0.0033292973,0.00030921237,0.0005178973,0.0011798115,0.00068261253,0.0015035443,0.00069933484,0.0017298961,0.018281933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041877927,0.000053569944,0.00053339906,0.0003181774,0.00004599825,0.00016127905,0.00009697932,0.024813665,0.00035093635,0.76048124,0.11382547,0.09927733],"study_design_scores_gemma":[0.000026533186,0.00003737243,0.00058827805,0.00017893007,0.000023658436,0.0001793124,0.000041536503,0.06495872,0.00024306426,0.7579146,0.17578274,0.000025149355],"about_ca_topic_score_codex":0.0018959335,"about_ca_topic_score_gemma":0.0024594748,"teacher_disagreement_score":0.070203245,"about_ca_system_score_codex":0.0010876537,"about_ca_system_score_gemma":0.00085647625,"threshold_uncertainty_score":0.23485327},"labels":[],"label_agreement":null},{"id":"W3193757218","doi":"10.1017/9781108571401.002","title":"Bandits, Probability and Concentration","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Mathematics","score_opus":0.11115866577009616,"score_gpt":0.3057460466407874,"score_spread":0.19458738087069127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193757218","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004636524,0.18904886,0.25054103,0.013382628,0.0033591108,0.000061305975,0.0010979068,0.0009652499,0.5369074],"genre_scores_gemma":[0.20719887,0.22624971,0.0793496,0.0051059597,0.0104356045,0.00035817357,0.0016661012,0.0011083892,0.4685276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99945694,0.00019172985,0.00002114816,0.000091986854,0.0001882637,0.000049873972],"domain_scores_gemma":[0.9987607,0.0009333838,0.000045778947,0.0001148556,0.00010689253,0.00003838092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092864624,0.0010541606,0.0011649112,0.0012463167,0.0006148762,0.003693376,0.00073549815,0.0016199913,0.02438972],"category_scores_gemma":[0.0045099338,0.00045261648,0.00046679712,0.003135681,0.0023555313,0.00326858,0.00091917085,0.0029059832,0.00945339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031792704,0.00002103591,0.00014380495,0.00036651033,0.000029531506,0.000042310363,0.00006622897,0.0101027815,0.00025494135,0.80001754,0.09387323,0.095050216],"study_design_scores_gemma":[0.000008469161,0.000016900107,0.0003326315,0.00017932165,0.000012383533,0.00008966189,0.000034856734,0.012558752,0.00024436004,0.8731127,0.11339344,0.000016638522],"about_ca_topic_score_codex":0.0037209345,"about_ca_topic_score_gemma":0.0028514522,"teacher_disagreement_score":0.02438972,"about_ca_system_score_codex":0.002034179,"about_ca_system_score_gemma":0.0010617438,"threshold_uncertainty_score":0.081591725},"labels":[],"label_agreement":null},{"id":"W3199199701","doi":"10.48550/arxiv.2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Term (time); Horizon; Computer science; Reinforcement; Recommender system; Artificial intelligence; Machine learning; Engineering; Mathematics","score_opus":0.3178481876547598,"score_gpt":0.33843505747722585,"score_spread":0.020586869822466047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199199701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055980716,0.0013111837,0.93963677,0.0005274869,0.000071569586,0.00008501612,0.000092779715,0.00096127694,0.0013331788],"genre_scores_gemma":[0.89684105,0.00043922666,0.09980778,0.00022198081,0.00008801556,0.00014134566,0.00021300366,0.00011532831,0.0021323587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806756,0.0007976855,0.0001104448,0.0005099557,0.0003270964,0.00018732296],"domain_scores_gemma":[0.9897885,0.007414469,0.00083734177,0.0007476478,0.00084571016,0.00036622604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048353104,0.001568474,0.0020444326,0.0006954127,0.00061560003,0.0014507109,0.0018270488,0.0018614243,0.0014739599],"category_scores_gemma":[0.01909666,0.0006886005,0.00047749325,0.00079918146,0.0013808913,0.0028507973,0.0012271408,0.0025148941,0.00054471375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002462733,0.00021659218,0.0023858338,0.00011216237,0.00009725877,0.000048444304,0.000076000055,0.9157991,0.0016895232,0.006879771,0.0012736642,0.07117534],"study_design_scores_gemma":[0.000012179859,0.00005993639,0.00015863407,0.0000066747252,0.0000071992395,0.0000075308426,0.0000048865522,0.99593085,0.00036054052,0.0033164385,0.00012882598,0.0000063342977],"about_ca_topic_score_codex":0.007833154,"about_ca_topic_score_gemma":0.006387927,"teacher_disagreement_score":0.007833154,"about_ca_system_score_codex":0.0016106203,"about_ca_system_score_gemma":0.0017859354,"threshold_uncertainty_score":0.025571883},"labels":[],"label_agreement":null},{"id":"W3202520435","doi":"10.1109/icdcs51616.2021.00126","title":"Poster: Multi-agent Combinatorial Bandits with Moving Arms","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Scheduling (production processes); Overhead (engineering); Wireless network; Crowdsourcing; Task (project management); Distributed computing; Wireless; Enhanced Data Rates for GSM Evolution; Job shop scheduling; Upper and lower bounds; Computer network; Mathematical optimization; Artificial intelligence; Routing (electronic design automation); Mathematics","score_opus":0.12498049373758835,"score_gpt":0.42311053471533827,"score_spread":0.2981300409777499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202520435","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024564747,0.00040663328,0.9630281,0.0007899799,0.00018502756,0.000082788436,0.00009178574,0.00029567574,0.0105552245],"genre_scores_gemma":[0.7622773,0.00038265364,0.22249326,0.00051277137,0.00020989259,0.00032210106,0.00023309892,0.00016056506,0.013408372],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986784,0.0006557194,0.000045104323,0.00025490663,0.00019575558,0.0001701004],"domain_scores_gemma":[0.99654275,0.0022504644,0.00036266918,0.00028522697,0.0002747399,0.0002840456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018088527,0.001334706,0.0012933015,0.00055772485,0.0009742986,0.0018458193,0.0015232002,0.0017694085,0.0062542027],"category_scores_gemma":[0.0064761573,0.00047916043,0.00086048903,0.00091005955,0.0013737123,0.0015288033,0.0019379826,0.0024149271,0.0009904045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020317866,0.00010897651,0.00048740796,0.00009406169,0.00006958638,0.000097283446,0.000057886427,0.8778542,0.0012048959,0.091934115,0.0046125916,0.023275804],"study_design_scores_gemma":[0.0000152026805,0.00003060886,0.00004334568,0.000006829362,0.0000065322342,0.000013871959,0.000007766777,0.98092043,0.0002509712,0.017872738,0.00082684914,0.0000048097236],"about_ca_topic_score_codex":0.0018331131,"about_ca_topic_score_gemma":0.0014393526,"teacher_disagreement_score":0.0062542027,"about_ca_system_score_codex":0.0012380665,"about_ca_system_score_gemma":0.000873562,"threshold_uncertainty_score":0.020922363},"labels":[],"label_agreement":null},{"id":"W3203261540","doi":"10.1287/moor.2023.1351","title":"Bilateral Trade: A Regret Minimization Perspective","year":2023,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca; Agence Nationale de la Recherche","keywords":"Regret; Hindsight bias; Bounded function; Mathematical economics; Mathematics; Benchmark (surveying); Perspective (graphical); Statistics; Psychology","score_opus":0.46240689411217983,"score_gpt":0.5846736458382126,"score_spread":0.12226675172603274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203261540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0138534,0.001568757,0.9611527,0.0030227366,0.00018085829,0.000099421755,0.00016568704,0.00014505621,0.019811345],"genre_scores_gemma":[0.7608784,0.0030938082,0.21019143,0.0013809948,0.0014269169,0.0006009048,0.00030402406,0.00038319523,0.021740353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99403954,0.0032271594,0.00015887793,0.00087040704,0.0011087265,0.00059535867],"domain_scores_gemma":[0.98777986,0.0092040505,0.0009738433,0.0009873093,0.00056020473,0.00049479736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00852093,0.0020629007,0.002046318,0.001080552,0.0012189269,0.003720282,0.0036351301,0.0034834957,0.009059997],"category_scores_gemma":[0.018195735,0.00083355594,0.0021411525,0.0011842382,0.0033727973,0.007594932,0.0029399698,0.0053167474,0.0008688619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021477419,0.00015413146,0.0004940068,0.0002735608,0.00012629139,0.00013540834,0.00015950286,0.29932392,0.0010373666,0.6735266,0.0030745307,0.02147988],"study_design_scores_gemma":[0.00004357165,0.000112068876,0.00021250836,0.00006384396,0.000045331377,0.0000828063,0.000042545755,0.46713787,0.0005001215,0.5284423,0.0032907727,0.00002614001],"about_ca_topic_score_codex":0.0013848811,"about_ca_topic_score_gemma":0.00083038164,"teacher_disagreement_score":0.009059997,"about_ca_system_score_codex":0.0033648738,"about_ca_system_score_gemma":0.0023291172,"threshold_uncertainty_score":0.045063555},"labels":[],"label_agreement":null},{"id":"W3204390043","doi":"10.2139/ssrn.3930622","title":"Dynamic Pricing with Fairness Constraints","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Dynamic pricing; Business; Economics; Microeconomics","score_opus":0.029526493173406148,"score_gpt":0.37649545766479586,"score_spread":0.3469689644913897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204390043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061167758,0.0006967493,0.8580068,0.0039226646,0.00059891003,0.00015488945,0.00026981143,0.0003478259,0.07483464],"genre_scores_gemma":[0.9240527,0.0003700109,0.044080045,0.00041644333,0.00043090768,0.00011925386,0.00011626359,0.00012164874,0.03029265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588567,0.0017780086,0.00011630495,0.0006080018,0.0008581709,0.0007537701],"domain_scores_gemma":[0.9922082,0.004817739,0.00041778656,0.0012196915,0.0007946355,0.0005420148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039667385,0.0010661026,0.001960913,0.00090669317,0.0014158033,0.0055784094,0.003150798,0.0028770987,0.016869713],"category_scores_gemma":[0.020748125,0.00094598444,0.0007657311,0.001947074,0.0019495478,0.006330055,0.0024225842,0.0038871677,0.0017803541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022819861,0.00021154553,0.000358128,0.000083901316,0.00004013225,0.00017480717,0.00007496983,0.1476086,0.00097036996,0.8140267,0.0067431196,0.029479614],"study_design_scores_gemma":[0.000055668846,0.000050112543,0.0001519476,0.00001632902,0.00002047468,0.00013958916,0.000030527524,0.5192601,0.00029530856,0.4771021,0.0028561875,0.000021637557],"about_ca_topic_score_codex":0.0015665569,"about_ca_topic_score_gemma":0.0009975248,"teacher_disagreement_score":0.016869713,"about_ca_system_score_codex":0.0022892677,"about_ca_system_score_gemma":0.0020400225,"threshold_uncertainty_score":0.05643487},"labels":[],"label_agreement":null},{"id":"W3204874277","doi":"10.48550/arxiv.2109.14733","title":"Batched Bandits with Crowd Externalities","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Externality; Computer science; Economics; Microeconomics","score_opus":0.28149544233302065,"score_gpt":0.2986513873188594,"score_spread":0.017155944985838723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204874277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05299791,0.0007674058,0.9388767,0.0010858655,0.00019758727,0.00016238615,0.0002722409,0.0012229941,0.004416945],"genre_scores_gemma":[0.85237765,0.000326479,0.13704221,0.0007926834,0.000214083,0.00042350293,0.0003513555,0.00015707493,0.008314916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974585,0.0010800968,0.00011611464,0.00061287486,0.00033665472,0.00039571684],"domain_scores_gemma":[0.99189985,0.0055805002,0.00073988055,0.0008249462,0.0005182503,0.0004366436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004534769,0.0017285896,0.002880937,0.0006707825,0.0010322782,0.0022552942,0.0024926672,0.0027706546,0.0038726712],"category_scores_gemma":[0.013712837,0.0010053809,0.0008095117,0.0010248638,0.0023100027,0.00313179,0.0021263075,0.003059467,0.0011544224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007943719,0.00016762516,0.000810592,0.00011712059,0.00008005827,0.00008378537,0.00008964579,0.91694367,0.0014303379,0.047264162,0.002746913,0.029471647],"study_design_scores_gemma":[0.000047720652,0.000048610695,0.000071439674,0.000015328525,0.000010691672,0.000011178903,0.000009011794,0.9815279,0.00050908094,0.01735313,0.00038592383,0.000009952455],"about_ca_topic_score_codex":0.005350605,"about_ca_topic_score_gemma":0.004705238,"teacher_disagreement_score":0.005350605,"about_ca_system_score_codex":0.0019376066,"about_ca_system_score_gemma":0.0018740258,"threshold_uncertainty_score":0.023982406},"labels":[],"label_agreement":null},{"id":"W3208296466","doi":"10.1609/aaai.v36i8.20891","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Convergence (economics); Gradient method; Computer science; Mathematical optimization; Applied mathematics; Work (physics); Rate of convergence; Mathematics; Economics; Physics; Telecommunications","score_opus":0.23281244621401168,"score_gpt":0.4911329585570102,"score_spread":0.2583205123429986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208296466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024333846,0.00069754344,0.96709543,0.00079798297,0.0000519944,0.000095849,0.000049879072,0.00019098862,0.0066864435],"genre_scores_gemma":[0.74499625,0.0016573153,0.24335086,0.00039185557,0.00015135536,0.0005825658,0.0001745735,0.00040702787,0.008288264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973193,0.0015876562,0.000104668565,0.00029440335,0.000482801,0.0002112402],"domain_scores_gemma":[0.9853217,0.011930564,0.0005757585,0.0005202619,0.0011777256,0.00047395058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007945873,0.0013141794,0.0013431452,0.0015333273,0.00080532127,0.0022870742,0.0011249,0.0018420113,0.0026661353],"category_scores_gemma":[0.04089117,0.00068418763,0.0010899184,0.0006457492,0.0038677647,0.002685139,0.003990862,0.0036292989,0.0006911429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017910125,0.00008575827,0.0013092085,0.00023819493,0.000054035765,0.00012371824,0.00034206643,0.47748497,0.0019947544,0.49006218,0.0016029832,0.026523076],"study_design_scores_gemma":[0.000018012503,0.000034773922,0.00013364243,0.000039520946,0.0000057221537,0.00001636267,0.00002437124,0.9075592,0.00045217722,0.09120892,0.00049818755,0.000009193886],"about_ca_topic_score_codex":0.0023595372,"about_ca_topic_score_gemma":0.001065901,"teacher_disagreement_score":0.007945873,"about_ca_system_score_codex":0.0016785525,"about_ca_system_score_gemma":0.0023186046,"threshold_uncertainty_score":0.042022347},"labels":[],"label_agreement":null},{"id":"W3210467483","doi":"10.48550/arxiv.2111.00870","title":"Statistical Consequences of Dueling Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Computer science; Thompson sampling; Operations research; Management science; Machine learning; Mathematics; Economics","score_opus":0.32076907952479783,"score_gpt":0.33607742809936747,"score_spread":0.015308348574569641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210467483","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084396504,0.001355258,0.90170604,0.0048218514,0.00028104038,0.00042148738,0.0005131982,0.00039361574,0.0061110016],"genre_scores_gemma":[0.8588668,0.00075774663,0.13244824,0.0020129285,0.0002710818,0.0011528094,0.0004356987,0.00019747349,0.00385714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9425356,0.044875577,0.002261163,0.0050838166,0.0041621923,0.0010816961],"domain_scores_gemma":[0.5952065,0.36030504,0.017643146,0.01900478,0.006557437,0.0012831055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09571703,0.0014530144,0.003406081,0.0015328878,0.0017829684,0.0041116453,0.0028271365,0.004078382,0.004739764],"category_scores_gemma":[0.34652513,0.0011642455,0.0015876377,0.0018677232,0.009445325,0.0062733586,0.0034016196,0.006596306,0.00059800583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006990305,0.00017652714,0.009797426,0.0003438425,0.0004388511,0.00038955623,0.00064837484,0.42828187,0.0007610755,0.5190964,0.0032381217,0.0361289],"study_design_scores_gemma":[0.00016753098,0.0001974775,0.0022709533,0.00012463579,0.00006694471,0.0000838732,0.00015354634,0.5367886,0.00065971917,0.45814425,0.001281703,0.000060785278],"about_ca_topic_score_codex":0.0037115915,"about_ca_topic_score_gemma":0.0020865013,"teacher_disagreement_score":0.09571703,"about_ca_system_score_codex":0.0026076261,"about_ca_system_score_gemma":0.0020350232,"threshold_uncertainty_score":0.50620604},"labels":[],"label_agreement":null},{"id":"W3211530479","doi":"","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multinomial logistic regression; Regret; Outcome (game theory); Computer science; Probabilistic logic; Logistic regression; Algorithm; Click-through rate; Revenue; Combinatorics; Mathematics; Artificial intelligence; Machine learning; Discrete mathematics; Mathematical economics; Information retrieval; Economics","score_opus":0.44194649559173543,"score_gpt":0.360482215254491,"score_spread":0.08146428033724445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211530479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067778714,0.00258433,0.97664577,0.0014523645,0.00021785103,0.00023321084,0.00040474389,0.0024839432,0.00919998],"genre_scores_gemma":[0.26282007,0.0025315543,0.7094682,0.0019355146,0.0005868096,0.001977493,0.002140319,0.0021785027,0.016361557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99512815,0.0022926654,0.00022938517,0.00072080817,0.00089489634,0.0007339633],"domain_scores_gemma":[0.98090094,0.014735896,0.0008595474,0.0015068066,0.0013436591,0.0006531307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005799683,0.0028779309,0.0045301216,0.0025896193,0.0017790418,0.0048580817,0.006932858,0.0047081443,0.019330654],"category_scores_gemma":[0.038772922,0.0016248247,0.001986075,0.003832866,0.0025698766,0.0065312344,0.0071185804,0.008118102,0.006701879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043834432,0.00046464414,0.0019058576,0.0005262364,0.00016915142,0.00019089099,0.00034159914,0.56822544,0.00097442453,0.20237261,0.025648491,0.19874239],"study_design_scores_gemma":[0.00004589421,0.000020381169,0.00006574957,0.00006538758,0.000011998897,0.00003104528,0.000024796607,0.9285389,0.00018413214,0.06896216,0.0020339706,0.000015502203],"about_ca_topic_score_codex":0.0108568175,"about_ca_topic_score_gemma":0.012435568,"teacher_disagreement_score":0.019330654,"about_ca_system_score_codex":0.0050166496,"about_ca_system_score_gemma":0.004390314,"threshold_uncertainty_score":0.06466746},"labels":[],"label_agreement":null},{"id":"W3211820441","doi":"","title":"Best-case lower bounds in online learning","year":2021,"lang":"en","type":"article","venue":"University of Twente Research Information","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Agencia Nacional de Investigación y Desarrollo; Natural Sciences and Engineering Research Council of Canada; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Sublinear function; Regret; Upper and lower bounds; Hindsight bias; Online learning; Computer science; Contrast (vision); Online algorithm; Mathematical optimization; Mathematics; Artificial intelligence; Algorithm; Machine learning; Discrete mathematics","score_opus":0.18059709452720507,"score_gpt":0.4517273856144851,"score_spread":0.27113029108728004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211820441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011738808,0.008473349,0.943248,0.0044290647,0.00056470785,0.00014964574,0.0005443256,0.00080513273,0.030047001],"genre_scores_gemma":[0.64912146,0.01022421,0.30723283,0.0052570254,0.0027564382,0.0017466915,0.001756199,0.0025364892,0.019368736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9760517,0.009962275,0.00094522705,0.0038466342,0.0062047355,0.002989389],"domain_scores_gemma":[0.85834205,0.11862292,0.004877357,0.0088615045,0.00683205,0.0024640807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024322229,0.0048349886,0.0044578924,0.0034654632,0.0029464106,0.008669374,0.0056844135,0.0047231503,0.011662862],"category_scores_gemma":[0.12867053,0.0017319584,0.0030380862,0.0041806553,0.006711622,0.016544694,0.0066284607,0.0147117665,0.0035935664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082115084,0.00052874687,0.002180925,0.0010755758,0.00028337634,0.0003168389,0.00056044717,0.39034215,0.002256236,0.5313067,0.015974853,0.054353103],"study_design_scores_gemma":[0.000035720834,0.00013084183,0.00033188393,0.00026008548,0.00006533602,0.00011867211,0.000078207864,0.5835109,0.001602163,0.4102697,0.0035493441,0.000047172867],"about_ca_topic_score_codex":0.0018253912,"about_ca_topic_score_gemma":0.0017022161,"teacher_disagreement_score":0.024322229,"about_ca_system_score_codex":0.005652222,"about_ca_system_score_gemma":0.0037349924,"threshold_uncertainty_score":0.12862974},"labels":[],"label_agreement":null},{"id":"W3212514152","doi":"","title":"Regime Switching Bandits","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Markov decision process; Upper and lower bounds; Stochastic matrix; Markov process; Observable; Computer science; State (computer science); Partially observable Markov decision process; Matrix (chemical analysis); Reinforcement learning; Probably approximately correct learning; Artificial intelligence; Mathematical optimization; Mathematics; Markov model; Algorithm; Machine learning; Unsupervised learning; Generalization error; Statistics","score_opus":0.1121872631780489,"score_gpt":0.4130105025504202,"score_spread":0.3008232393723713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212514152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09535291,0.00088279665,0.8884451,0.0011709419,0.000110220375,0.00010656327,0.00017132427,0.00038784332,0.01337227],"genre_scores_gemma":[0.955674,0.00039832486,0.037793234,0.00028060863,0.00008865019,0.00018497602,0.00009903848,0.00005611284,0.0054249805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998336,0.00077687064,0.00006727196,0.0002894025,0.00024196426,0.00028853415],"domain_scores_gemma":[0.98976713,0.008285281,0.0009191932,0.0004167901,0.00033938157,0.00027230728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034173313,0.00090643874,0.0018624982,0.000758905,0.00079130265,0.0020441387,0.0013857424,0.0020161862,0.005208036],"category_scores_gemma":[0.013532557,0.000527798,0.0007842952,0.00094174297,0.0019305798,0.0023888645,0.0017769758,0.0022483382,0.00059667876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024797276,0.00012517715,0.0012179009,0.000110298,0.000086464155,0.00017591382,0.000121192985,0.77546656,0.0012136595,0.19572268,0.0017603962,0.023751823],"study_design_scores_gemma":[0.00001510899,0.000020863175,0.000093990675,0.000010112122,0.0000065308254,0.000015597567,0.000009716213,0.95654565,0.00018924958,0.042800296,0.00028625858,0.0000066755565],"about_ca_topic_score_codex":0.0022931972,"about_ca_topic_score_gemma":0.0014388004,"teacher_disagreement_score":0.005208036,"about_ca_system_score_codex":0.0016063742,"about_ca_system_score_gemma":0.0007662778,"threshold_uncertainty_score":0.018072784},"labels":[],"label_agreement":null},{"id":"W3212608195","doi":"","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Sublinear function; Multi-armed bandit; Computer science; Nash equilibrium; Mathematical optimization; Social Welfare; Mathematical economics; Artificial intelligence; Algorithm; Mathematics; Machine learning; Discrete mathematics; Law","score_opus":0.3178937303358701,"score_gpt":0.4768734040535386,"score_spread":0.15897967371766852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212608195","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0090150405,0.00044864797,0.987248,0.0003162147,0.000069928814,0.0000588249,0.000032661148,0.00015500025,0.002655586],"genre_scores_gemma":[0.70851755,0.00067004934,0.2824379,0.00041065697,0.000171114,0.00046345175,0.000100291865,0.000116022384,0.0071129357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978783,0.0009710042,0.0000971907,0.00032924186,0.00041560258,0.00030864793],"domain_scores_gemma":[0.99509746,0.0035517123,0.00036049538,0.00042110423,0.00035365665,0.00021555807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045550824,0.0012913371,0.0016180382,0.0008184622,0.0010746701,0.0021829957,0.0021715611,0.0020923493,0.0032281377],"category_scores_gemma":[0.011684306,0.0005222796,0.0007367353,0.0009191822,0.0022026163,0.0023997847,0.0017841976,0.001963536,0.00056708703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013478944,0.00007709563,0.00034048324,0.00007513554,0.000048441576,0.00004400362,0.00008392109,0.82032764,0.0006286212,0.14844908,0.0013775349,0.028413292],"study_design_scores_gemma":[0.000023190525,0.000019319412,0.00003417614,0.000011456036,0.000006075077,0.000008823806,0.000008752533,0.9234735,0.000245024,0.07563268,0.0005308392,0.000006104551],"about_ca_topic_score_codex":0.00247952,"about_ca_topic_score_gemma":0.0024619328,"teacher_disagreement_score":0.0045550824,"about_ca_system_score_codex":0.0021503158,"about_ca_system_score_gemma":0.0018949232,"threshold_uncertainty_score":0.024089813},"labels":[],"label_agreement":null},{"id":"W3212900133","doi":"10.1109/tcns.2022.3153872","title":"Scalable Operator Allocation for Multirobot Assistance: A Restless Bandit Approach","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Scalability; Leverage (statistics); Robot; Computer science; Operator (biology); Mathematical optimization; Heuristic; Robot kinematics; Distributed computing; Artificial intelligence; Mobile robot; Mathematics","score_opus":0.08808758998774956,"score_gpt":0.3626182202265537,"score_spread":0.27453063023880414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212900133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029467573,0.00020625812,0.9655479,0.00023683856,0.00003425572,0.00007719042,0.000024920355,0.0002522552,0.00415265],"genre_scores_gemma":[0.9207298,0.00016732885,0.07554456,0.00015546897,0.000046929767,0.00014042288,0.00003676372,0.0000542707,0.0031244082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999387,0.00019945015,0.000021197278,0.000114680406,0.00014116669,0.00013639327],"domain_scores_gemma":[0.9989586,0.0005908349,0.00016883705,0.00009853175,0.00009384882,0.00008935036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012031054,0.00095190917,0.0010155124,0.00045108114,0.00051151164,0.00097432465,0.0011939325,0.00084577675,0.0033258402],"category_scores_gemma":[0.0025514537,0.00036091678,0.0004286281,0.0004658661,0.0012606286,0.0016458891,0.0013335306,0.0012900702,0.0003689009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013253356,0.000083911495,0.00024798955,0.000053684715,0.000020122076,0.000073374395,0.0000750819,0.9533827,0.0017717615,0.019193005,0.0006274333,0.024338385],"study_design_scores_gemma":[0.000009355672,0.000037749018,0.000041410774,0.000004364068,0.0000034240377,0.000009476729,0.000014138408,0.9930947,0.00031416546,0.0062805023,0.0001875456,0.0000031968914],"about_ca_topic_score_codex":0.0028251922,"about_ca_topic_score_gemma":0.0027009323,"teacher_disagreement_score":0.0033258402,"about_ca_system_score_codex":0.00095790887,"about_ca_system_score_gemma":0.001250256,"threshold_uncertainty_score":0.011126101},"labels":[],"label_agreement":null},{"id":"W3213203216","doi":"","title":"An Empirical Study of Neural Kernel Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Thompson sampling; Machine learning; Artificial intelligence; Gaussian process; Bayesian probability; Kernel (algebra); Artificial neural network; Deep neural networks; Process (computing); Gaussian; Mathematics","score_opus":0.3374988530824604,"score_gpt":0.3759152304890423,"score_spread":0.03841637740658188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213203216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5697341,0.013589013,0.38244846,0.007696079,0.00027942684,0.00019522631,0.0011084843,0.0009863315,0.023962941],"genre_scores_gemma":[0.97813034,0.0013407331,0.017018633,0.00028549394,0.00013060548,0.00011236102,0.000705047,0.0001332226,0.0021435644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99559695,0.0028346123,0.00020810858,0.0005510948,0.0005439285,0.00026538564],"domain_scores_gemma":[0.91057444,0.075365484,0.004089285,0.005905509,0.0030394578,0.0010257774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012859781,0.00093624846,0.0018992099,0.0014834125,0.0013932004,0.0028114268,0.0020681394,0.0020312557,0.0069362465],"category_scores_gemma":[0.11874888,0.0005161399,0.00077453506,0.0021045292,0.003639047,0.0061614364,0.0022697828,0.0046578064,0.0007321659],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082970026,0.00041676327,0.03829908,0.0005904123,0.0003087319,0.00040725106,0.00065612566,0.42479834,0.0009281132,0.43311098,0.015428488,0.08422584],"study_design_scores_gemma":[0.00007842545,0.00012741792,0.0053638094,0.00020634528,0.000043319942,0.00023119563,0.00029472227,0.78060734,0.0006179503,0.2081942,0.0041945744,0.00004067852],"about_ca_topic_score_codex":0.0039800447,"about_ca_topic_score_gemma":0.0031165767,"teacher_disagreement_score":0.012859781,"about_ca_system_score_codex":0.002324657,"about_ca_system_score_gemma":0.0011118583,"threshold_uncertainty_score":0.068009794},"labels":[],"label_agreement":null},{"id":"W3215887789","doi":"10.1109/tai.2021.3117743","title":"Delayed Reward Bernoulli Bandits: Optimal Policy and Predictive Meta-Algorithm PARDI","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bernoulli's principle; Computer science; Outcome (game theory); Reinforcement learning; Mathematical optimization; Index (typography); Algorithm; Range (aeronautics); Artificial intelligence; Mathematics; Mathematical economics; Engineering","score_opus":0.19533306039765136,"score_gpt":0.4366686007048083,"score_spread":0.24133554030715693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215887789","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040659983,0.0011767066,0.95148647,0.0005966365,0.00011683429,0.00011848284,0.00010157005,0.0009253374,0.0048180968],"genre_scores_gemma":[0.74748266,0.00042379886,0.24811344,0.0003889251,0.00008330234,0.0002854527,0.00022655932,0.00013519033,0.0028606902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988053,0.00048818666,0.00005472134,0.00022258455,0.0002648162,0.00016441087],"domain_scores_gemma":[0.99561274,0.003176387,0.00034372078,0.0002950482,0.00037413227,0.00019796815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029678238,0.0009722789,0.0016520622,0.00087640167,0.000477044,0.0015412229,0.0022648005,0.0017040896,0.0020643098],"category_scores_gemma":[0.010287621,0.0005288722,0.0005558888,0.00089742703,0.00093373185,0.0015530525,0.0011345828,0.002242036,0.00045657632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013834202,0.00006923902,0.00064138207,0.00004789095,0.00004404215,0.000023921768,0.000034229804,0.9525262,0.00039985907,0.009745201,0.00084796816,0.035481773],"study_design_scores_gemma":[0.000013456639,0.000024292669,0.000036827067,0.0000058787473,0.000006101474,0.000007579884,0.000003244247,0.9967616,0.00020344135,0.0027403636,0.00019412138,0.0000030800422],"about_ca_topic_score_codex":0.0042584147,"about_ca_topic_score_gemma":0.0035692877,"teacher_disagreement_score":0.0042584147,"about_ca_system_score_codex":0.0017858496,"about_ca_system_score_gemma":0.0029537797,"threshold_uncertainty_score":0.015695512},"labels":[],"label_agreement":null},{"id":"W4200629132","doi":"10.2139/ssrn.3978421","title":"Optimal No-Regret Learning in Strongly Monotone Games with Bandit Feedback","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Monotone polygon; Mathematical economics; Mathematical optimization; Computer science; Mathematics; Economics; Machine learning","score_opus":0.0280459300877103,"score_gpt":0.35069296440617387,"score_spread":0.3226470343184636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200629132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14352672,0.0012636054,0.8253711,0.0042785206,0.00023838299,0.0003150493,0.00042001705,0.0007856469,0.023800904],"genre_scores_gemma":[0.9402852,0.000671251,0.04703743,0.0006196862,0.00030880782,0.00041901186,0.00020968742,0.00015229238,0.010296595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950664,0.002859731,0.00018541717,0.0007128029,0.00047217592,0.0007034582],"domain_scores_gemma":[0.9519434,0.042323824,0.0019424169,0.0013981014,0.0011976348,0.0011945425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006768674,0.0028926176,0.00408061,0.0011394243,0.0010847367,0.0038923984,0.0035911275,0.0049770717,0.0047984608],"category_scores_gemma":[0.04865605,0.0016019638,0.0009127354,0.0010675148,0.0038045447,0.0062720627,0.0032696319,0.0044761715,0.00087346137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011551722,0.0004832621,0.0009592372,0.00040317877,0.00013523677,0.00010925884,0.00016365836,0.7970705,0.00087726046,0.1690134,0.00410974,0.025520083],"study_design_scores_gemma":[0.00010359494,0.00010292383,0.0001290261,0.000036310346,0.000019276413,0.000017464947,0.000021468244,0.891018,0.00027674204,0.10804939,0.00020892851,0.000016887523],"about_ca_topic_score_codex":0.003276483,"about_ca_topic_score_gemma":0.002824718,"teacher_disagreement_score":0.006768674,"about_ca_system_score_codex":0.0029236306,"about_ca_system_score_gemma":0.003600986,"threshold_uncertainty_score":0.035796583},"labels":[],"label_agreement":null},{"id":"W4205863870","doi":"10.1109/lra.2022.3140813","title":"Hybrid Hierarchical Learning for Adaptive Persuasion in Human-Robot Interaction","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Persuasion; Robot; Artificial intelligence; Human–computer interaction; Robustness (evolution); Benchmark (surveying); Architecture; Machine learning; Psychology","score_opus":0.09853142058525839,"score_gpt":0.4002143626322813,"score_spread":0.3016829420470229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205863870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050687887,0.0002520596,0.94378966,0.00020551698,0.000038977865,0.000106390544,0.00002761842,0.0018313468,0.0030606189],"genre_scores_gemma":[0.8252031,0.00012419796,0.17072712,0.00019727668,0.000031854237,0.00020284017,0.00006927989,0.000061558254,0.0033827529],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993162,0.00021497095,0.00003894316,0.00019397463,0.0001424631,0.00009340829],"domain_scores_gemma":[0.9990013,0.0004458443,0.000092192,0.00015372991,0.00022409846,0.000082800834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013251468,0.0007098706,0.000551065,0.0004835738,0.0006032814,0.00077915407,0.0014119927,0.0009986992,0.0023621977],"category_scores_gemma":[0.002970887,0.00033550232,0.00056243566,0.00029056642,0.0008506893,0.0012840292,0.0014723121,0.0011978215,0.00081692217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031059107,0.00054632005,0.0034323344,0.00016390336,0.00014970725,0.00013212801,0.00065504096,0.5055621,0.022408966,0.011254905,0.0020687243,0.4533152],"study_design_scores_gemma":[0.000014281201,0.00011645605,0.0004499507,0.00000654415,0.000015478403,0.000018286955,0.000026294168,0.9908036,0.0024149823,0.0054717963,0.00065042736,0.000011855532],"about_ca_topic_score_codex":0.0051968717,"about_ca_topic_score_gemma":0.006301485,"teacher_disagreement_score":0.0051968717,"about_ca_system_score_codex":0.0009043989,"about_ca_system_score_gemma":0.00079662027,"threshold_uncertainty_score":0.01033324},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11482899344122152,"score_gpt":0.33081690938041297,"score_spread":0.21598791593919145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206530644","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031893847,0.006442642,0.936176,0.0016133547,0.00058066536,0.0001671609,0.00048753904,0.0010357414,0.050307546],"genre_scores_gemma":[0.20235427,0.014421321,0.6748054,0.002450048,0.0012676591,0.0012534116,0.0021980852,0.0011344956,0.100115284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99784315,0.000880294,0.00013547878,0.00040092066,0.0005304456,0.00020968502],"domain_scores_gemma":[0.995665,0.0030204582,0.00023062946,0.00054346083,0.0004289734,0.00011147727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023740397,0.0020282732,0.0025446438,0.001326196,0.001219177,0.0045998353,0.0027348865,0.0028459285,0.02660274],"category_scores_gemma":[0.012509824,0.00077516417,0.0013162751,0.0027030704,0.0015276574,0.0031895284,0.0027033712,0.0034124204,0.011547004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016568707,0.00013058702,0.00066306855,0.0004299123,0.00018244117,0.00008686222,0.00012063939,0.2127413,0.0006515872,0.425747,0.04053511,0.31854585],"study_design_scores_gemma":[0.000056117005,0.000056676457,0.00017807382,0.00018829819,0.00004929845,0.000107868065,0.00004729583,0.5465144,0.0005025584,0.41874626,0.033522207,0.00003102887],"about_ca_topic_score_codex":0.0026836796,"about_ca_topic_score_gemma":0.0028095772,"teacher_disagreement_score":0.02660274,"about_ca_system_score_codex":0.0017660571,"about_ca_system_score_gemma":0.0018230086,"threshold_uncertainty_score":0.08899504},"labels":[],"label_agreement":null},{"id":"W4207076830","doi":"10.3982/ecta18324","title":"Dynamically Aggregating Diverse Information","year":2022,"lang":"en","type":"article","venue":"Econometrica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Computer science; Component (thermodynamics); Sample (material); Brownian motion; Gaussian; Point (geometry); Binary number; Mathematical optimization; Mathematics; Statistics","score_opus":0.10806584146520383,"score_gpt":0.3941978130461244,"score_spread":0.2861319715809206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207076830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51566726,0.0009797007,0.45620224,0.0026977123,0.00013514442,0.00017321926,0.00048371745,0.00046221438,0.023198823],"genre_scores_gemma":[0.97070146,0.00028541248,0.024579221,0.0001811787,0.000073633346,0.000064771884,0.00017873826,0.000031949272,0.0039036735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979792,0.0006572512,0.00012643966,0.00051391067,0.00039825996,0.00032487613],"domain_scores_gemma":[0.9861726,0.008895403,0.0016764883,0.0016657142,0.0010566246,0.00053314463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030483159,0.0007757461,0.0013514522,0.0011058379,0.0007021831,0.0032696023,0.0014853432,0.0016699274,0.004332839],"category_scores_gemma":[0.023351634,0.0008085696,0.00060979294,0.00143152,0.0009416447,0.005035129,0.0029067737,0.0014914712,0.0006803433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013701285,0.00064325123,0.01769837,0.00041319392,0.00042417977,0.001219479,0.0016714322,0.4317916,0.014331761,0.34971258,0.006107766,0.17461632],"study_design_scores_gemma":[0.00007723334,0.00013658723,0.0041429857,0.000045392786,0.00012501524,0.00016310599,0.00026837087,0.8504237,0.002467517,0.13927725,0.0028115185,0.00006136866],"about_ca_topic_score_codex":0.002782728,"about_ca_topic_score_gemma":0.002650226,"teacher_disagreement_score":0.004332839,"about_ca_system_score_codex":0.0014654937,"about_ca_system_score_gemma":0.00090484973,"threshold_uncertainty_score":0.016121209},"labels":[],"label_agreement":null},{"id":"W4210906234","doi":"10.1287/opre.2021.2240","title":"Dynamic Learning and Decision Making via Basis Weight Vectors","year":2022,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Continuation; Basis (linear algebra); Computer science; Mathematical optimization; Bellman equation; Process (computing); Set (abstract data type); Time horizon; Decision maker; Class (philosophy); Mathematics; Artificial intelligence; Algorithm; Operations research","score_opus":0.10884847178026896,"score_gpt":0.5124579529953524,"score_spread":0.4036094812150834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210906234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002434457,0.0001825667,0.9954733,0.00021853684,0.000044257173,0.00002739408,0.000019719084,0.00006721693,0.0015325175],"genre_scores_gemma":[0.28532907,0.0010317875,0.7019763,0.0003177976,0.00025654517,0.00055569265,0.00015394413,0.0001330022,0.010245927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836665,0.0008027446,0.00007369191,0.00021808033,0.0004051289,0.00013371918],"domain_scores_gemma":[0.9971433,0.0019075674,0.00018955432,0.00023960265,0.00040728797,0.000112592366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034113082,0.0013062299,0.0013681888,0.0011626014,0.00065662124,0.0017438551,0.0017122021,0.0016311582,0.00438986],"category_scores_gemma":[0.008998771,0.0006735611,0.0009747387,0.0015752211,0.0018877111,0.0031824308,0.0017576655,0.0035400838,0.0007330893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096777476,0.000092422364,0.0004126088,0.00009418916,0.00008264201,0.000041557712,0.00008368287,0.5438125,0.00092873554,0.34177762,0.0023553334,0.110221945],"study_design_scores_gemma":[0.000018062685,0.000018948911,0.00003861768,0.000013467041,0.000007502595,0.000009384043,0.0000051999746,0.92161053,0.00024434953,0.07702385,0.0010016315,0.000008368489],"about_ca_topic_score_codex":0.0039414437,"about_ca_topic_score_gemma":0.003369156,"teacher_disagreement_score":0.00438986,"about_ca_system_score_codex":0.0015846322,"about_ca_system_score_gemma":0.00204176,"threshold_uncertainty_score":0.018040955},"labels":[],"label_agreement":null},{"id":"W4210948966","doi":"10.1017/9781108571401.034","title":"Exp3 for Adversarial Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Content (measure theory); Computer science; Operations research; Information retrieval; Artificial intelligence; Mathematics","score_opus":0.1468442251773642,"score_gpt":0.33969331728319785,"score_spread":0.19284909210583365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210948966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023586967,0.0065992246,0.8685503,0.0031527139,0.0016400917,0.000094408795,0.0015412755,0.003364494,0.1126988],"genre_scores_gemma":[0.1893419,0.013079044,0.4565595,0.0061160396,0.0034917602,0.0011988843,0.0057466105,0.0052455487,0.3192207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999003,0.00031285107,0.000054826935,0.0001731951,0.00036124612,0.00009505444],"domain_scores_gemma":[0.9983656,0.0009967254,0.00006520216,0.00036138456,0.00015890514,0.000052186606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018421315,0.0014532731,0.00077965803,0.0007559439,0.0005576188,0.002025579,0.0015954677,0.0020126624,0.06329249],"category_scores_gemma":[0.007024257,0.00046815624,0.0010018077,0.001209286,0.0011729152,0.0029037667,0.0019232332,0.004330318,0.026932167],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017254439,0.000077424855,0.00029953266,0.000478834,0.00007509485,0.00014692543,0.00006836917,0.050153673,0.0017955052,0.5573599,0.16187868,0.22749352],"study_design_scores_gemma":[0.000035750196,0.000049493847,0.00024801123,0.00018828317,0.000020617157,0.00021551433,0.000018936767,0.21260273,0.0018935298,0.68702966,0.09766255,0.00003498338],"about_ca_topic_score_codex":0.0012633613,"about_ca_topic_score_gemma":0.002178078,"teacher_disagreement_score":0.06329249,"about_ca_system_score_codex":0.0010682335,"about_ca_system_score_gemma":0.00095772586,"threshold_uncertainty_score":0.21173447},"labels":[],"label_agreement":null},{"id":"W4210963705","doi":"10.1017/9781108571401.025","title":"Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematical optimization; Mathematics","score_opus":0.11979194893295043,"score_gpt":0.324009890147398,"score_spread":0.20421794121444758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210963705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059095845,0.029784193,0.58203685,0.0052981405,0.0023591549,0.000060426566,0.0022713568,0.0017002957,0.37057996],"genre_scores_gemma":[0.15780182,0.03700202,0.13147587,0.0023260042,0.00264332,0.00023908082,0.004105917,0.001275704,0.66313034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996692,0.000092393886,0.000013180394,0.000061347775,0.0001299928,0.000033880453],"domain_scores_gemma":[0.99936134,0.0003938023,0.000027139751,0.00008490515,0.000096765754,0.000036081423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007772945,0.00082768034,0.0008001198,0.0005660553,0.00031374593,0.0019290531,0.00067744276,0.00090279157,0.042196605],"category_scores_gemma":[0.0028605028,0.00030134866,0.00048075733,0.0013984911,0.00067683647,0.0014920045,0.0007772897,0.0017673555,0.023616705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009286111,0.00004960817,0.00027006952,0.00039683224,0.000057053476,0.00007088283,0.00005580257,0.047257043,0.0013715773,0.4896696,0.16281407,0.29789463],"study_design_scores_gemma":[0.000026003187,0.00006186536,0.00064169714,0.0003515615,0.00003234958,0.00018982086,0.000041065658,0.15564284,0.0016693877,0.524209,0.31709215,0.000042229403],"about_ca_topic_score_codex":0.0009898739,"about_ca_topic_score_gemma":0.0015066563,"teacher_disagreement_score":0.042196605,"about_ca_system_score_codex":0.0007996605,"about_ca_system_score_gemma":0.0006458527,"threshold_uncertainty_score":0.14116168},"labels":[],"label_agreement":null},{"id":"W4210974166","doi":"10.1017/9781108571401.032","title":"Adversarial Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence; Mathematics","score_opus":0.11693523532589903,"score_gpt":0.322636180878772,"score_spread":0.20570094555287297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210974166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005351228,0.013338547,0.7510555,0.0042756437,0.0017073305,0.00006481,0.0010239091,0.0016412515,0.22154173],"genre_scores_gemma":[0.2609302,0.022884749,0.20165259,0.0029375127,0.0029621883,0.00033914452,0.0032114,0.001491701,0.5035906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996265,0.000104701314,0.000014191811,0.00007579964,0.00013225946,0.00004652739],"domain_scores_gemma":[0.99906105,0.00062427134,0.000034233173,0.00013964638,0.00009918223,0.0000416216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008784985,0.0010764274,0.0008513327,0.00051531993,0.00036069372,0.0017165233,0.00087487604,0.0011921183,0.029228278],"category_scores_gemma":[0.0032528732,0.00033429833,0.0004047301,0.0009518679,0.00095614727,0.0018223989,0.0012446204,0.002721798,0.017296124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013976634,0.0000672177,0.00024101787,0.00034496028,0.000067882116,0.00008008582,0.000060404804,0.14632754,0.001966325,0.4068613,0.13957559,0.30426794],"study_design_scores_gemma":[0.000024135601,0.00007202612,0.0002923462,0.00025013828,0.00002692942,0.00013864994,0.000031329968,0.45189917,0.0019095155,0.4320952,0.113224335,0.000036222984],"about_ca_topic_score_codex":0.00092690927,"about_ca_topic_score_gemma":0.0013546216,"teacher_disagreement_score":0.029228278,"about_ca_system_score_codex":0.0007594469,"about_ca_system_score_gemma":0.0006104242,"threshold_uncertainty_score":0.09777832},"labels":[],"label_agreement":null},{"id":"W4211022090","doi":"10.1017/9781108571401.039","title":"Non-stationary Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematics","score_opus":0.09910510505895859,"score_gpt":0.31753404481789693,"score_spread":0.21842893975893835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211022090","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061905677,0.034867674,0.51504606,0.0037072331,0.003034844,0.00006835755,0.0016301554,0.0012558204,0.43419927],"genre_scores_gemma":[0.10237952,0.03681657,0.10999707,0.0012739028,0.002724327,0.00018423883,0.002719076,0.0011454612,0.74275994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99964297,0.00008213917,0.00001641291,0.00007135395,0.00015413895,0.000032963748],"domain_scores_gemma":[0.9991066,0.00054959056,0.00002982728,0.00013504687,0.00014610073,0.00003289526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007660902,0.0007911797,0.0008285397,0.00081772084,0.00042956643,0.002455351,0.00072672433,0.000947741,0.04166118],"category_scores_gemma":[0.00301014,0.00033922435,0.00041100977,0.0016146278,0.00072377105,0.0020671387,0.0007883316,0.0018291319,0.026763331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008652184,0.00004475648,0.00019331067,0.00042280837,0.000039665058,0.00007954371,0.00007002878,0.019847916,0.0020807835,0.48735014,0.14053108,0.3492535],"study_design_scores_gemma":[0.000023123905,0.00006414352,0.00065908127,0.00034515953,0.000034021916,0.0002653978,0.000050602423,0.10249766,0.0027415783,0.5145787,0.37870172,0.000038915772],"about_ca_topic_score_codex":0.0008160252,"about_ca_topic_score_gemma":0.0013979577,"teacher_disagreement_score":0.04166118,"about_ca_system_score_codex":0.00079455966,"about_ca_system_score_gemma":0.00060137117,"threshold_uncertainty_score":0.1393705},"labels":[],"label_agreement":null},{"id":"W4211042912","doi":"10.1017/9781108571401.037","title":"Other Topics","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Content (measure theory); World Wide Web; Data science; Mathematics","score_opus":0.13200117096951755,"score_gpt":0.3249582694357428,"score_spread":0.19295709846622525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211042912","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034302057,0.011634593,0.0013680005,0.004439118,0.007935644,0.00009474557,0.0024168578,0.0006461145,0.97112185],"genre_scores_gemma":[0.0008420133,0.004929291,0.0004655299,0.0010963136,0.0018859914,0.00003245744,0.0013686236,0.00030390834,0.9890758],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993247,0.000052685813,0.000026523338,0.000112208116,0.0003841346,0.00009963611],"domain_scores_gemma":[0.9988175,0.00016412712,0.00005073518,0.0001268835,0.00042313465,0.00041756695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006933011,0.0009231159,0.0008059181,0.0025680133,0.0013470055,0.0051876134,0.0011533963,0.0014675446,0.69076705],"category_scores_gemma":[0.0026006633,0.0002488901,0.0009026646,0.0034074313,0.00063010893,0.0037967977,0.0022599816,0.0018250515,0.5821104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018391589,0.000035002497,0.000080219,0.00026955377,0.0000027375424,0.00004171573,0.00008705788,0.000061441264,0.00038010604,0.010627414,0.87029517,0.11810123],"study_design_scores_gemma":[0.0000012612999,0.0000052306004,0.000087064516,0.00008846992,9.459817e-7,0.00003135025,0.00003065234,0.000011329701,0.000044708715,0.0012696593,0.9984274,0.0000018606224],"about_ca_topic_score_codex":0.0022595215,"about_ca_topic_score_gemma":0.004170991,"teacher_disagreement_score":0.69076705,"about_ca_system_score_codex":0.0016800689,"about_ca_system_score_gemma":0.0019480601,"threshold_uncertainty_score":0.44108325},"labels":[],"label_agreement":null},{"id":"W4211056168","doi":"10.1017/9781108571401.014","title":"Adversarial Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Adversarial system; Computer science; Content (measure theory); Computer security; Internet privacy; Political science; Business; Artificial intelligence; Mathematics","score_opus":0.10016456268885476,"score_gpt":0.29781126606216896,"score_spread":0.1976467033733142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211056168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010167371,0.0047934805,0.84484875,0.0034601185,0.00070539507,0.000066325316,0.00050515786,0.0009767417,0.13447666],"genre_scores_gemma":[0.5488686,0.0094932355,0.22151993,0.0027478468,0.0021595047,0.000590548,0.0016623364,0.0009942502,0.21196373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991148,0.00036278396,0.00003591503,0.00015755933,0.00022355354,0.00010529441],"domain_scores_gemma":[0.99662787,0.0026584456,0.000101078746,0.00040295537,0.000116043506,0.0000935713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016379458,0.0014526546,0.0011316491,0.0005669362,0.0005319681,0.0022041511,0.0011188164,0.0016793158,0.016185421],"category_scores_gemma":[0.0065193297,0.00049828243,0.000678548,0.0009019781,0.0018052231,0.002642418,0.0020091352,0.0041769845,0.0061132885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017055996,0.00006136476,0.00022729066,0.0002542405,0.00007117683,0.000086932996,0.00007237463,0.20163943,0.0013173581,0.66921365,0.030840779,0.096044876],"study_design_scores_gemma":[0.000024480789,0.000043363678,0.00011261851,0.0001065911,0.000015967142,0.000052914726,0.000015788253,0.3700574,0.0007047953,0.61535144,0.013495475,0.000019261333],"about_ca_topic_score_codex":0.00071715645,"about_ca_topic_score_gemma":0.00088010967,"teacher_disagreement_score":0.016185421,"about_ca_system_score_codex":0.0010745852,"about_ca_system_score_gemma":0.000788852,"threshold_uncertainty_score":0.054145694},"labels":[],"label_agreement":null},{"id":"W4211058984","doi":"10.1017/9781108571401.041","title":"Pure Exploration","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Information retrieval; Mathematics","score_opus":0.1638929471716128,"score_gpt":0.3254588598612687,"score_spread":0.16156591268965592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211058984","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016816021,0.007654617,0.11300499,0.0019890442,0.00095531956,0.000114032686,0.0016958299,0.0023819662,0.8705227],"genre_scores_gemma":[0.043437976,0.011884642,0.06865223,0.0013972496,0.0008149921,0.00027375566,0.0034054033,0.0027150293,0.86741865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993599,0.00010366249,0.000027181673,0.00015396015,0.00028015548,0.00007512268],"domain_scores_gemma":[0.999302,0.00022504007,0.000023722872,0.00023870509,0.0001481447,0.0000623441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006292231,0.0012104956,0.0008549816,0.0013438291,0.0009162626,0.0037864645,0.0014268768,0.0010172374,0.20501748],"category_scores_gemma":[0.0027837763,0.00043131766,0.0011189278,0.0017308869,0.0012922426,0.0052120453,0.0029061076,0.0016824061,0.11754686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071856615,0.000041103463,0.00018939319,0.0007126803,0.000030123287,0.00008648844,0.00014733845,0.0032049138,0.0017405348,0.43304628,0.21776168,0.34296766],"study_design_scores_gemma":[0.000011147051,0.000030268418,0.00018274607,0.00019766555,0.000014812154,0.00029364883,0.000053211512,0.0042752516,0.0015845881,0.28783423,0.7054984,0.000023989911],"about_ca_topic_score_codex":0.0007791448,"about_ca_topic_score_gemma":0.0015156398,"teacher_disagreement_score":0.20501748,"about_ca_system_score_codex":0.0010492677,"about_ca_system_score_gemma":0.0012056585,"threshold_uncertainty_score":0.6858518},"labels":[],"label_agreement":null},{"id":"W4211059639","doi":"10.1017/9781108571401.006","title":"Stochastic Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Economics","score_opus":0.11560849620300741,"score_gpt":0.3168541208218191,"score_spread":0.20124562461881168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211059639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060592587,0.017884176,0.6612195,0.0036703662,0.001808368,0.000068633686,0.0025016502,0.0016510994,0.30513698],"genre_scores_gemma":[0.21293446,0.03110871,0.19684306,0.002091124,0.0023697864,0.00033297835,0.0058792983,0.0017062502,0.54673433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995123,0.00014109649,0.000023674835,0.000091338065,0.00017692707,0.000054617274],"domain_scores_gemma":[0.9990872,0.0005395654,0.000042271662,0.00014169277,0.00013779421,0.000051498726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096240046,0.00091071747,0.0009637649,0.0007366805,0.00046919804,0.0023642967,0.0008229127,0.0010597052,0.04897824],"category_scores_gemma":[0.004018892,0.00033643216,0.00061359996,0.001636818,0.0007246393,0.0017059946,0.0009752004,0.0018266522,0.023629017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110038425,0.00005010701,0.00034322287,0.00036964339,0.000069376416,0.000065963555,0.000057101664,0.05610886,0.0012139562,0.5543359,0.12657395,0.260702],"study_design_scores_gemma":[0.0000302533,0.000054514243,0.0006501057,0.000291183,0.000039916613,0.00018259174,0.00003963179,0.18063313,0.001527109,0.5771228,0.23938696,0.000041855314],"about_ca_topic_score_codex":0.0013504159,"about_ca_topic_score_gemma":0.0018752248,"teacher_disagreement_score":0.04897824,"about_ca_system_score_codex":0.0008886441,"about_ca_system_score_gemma":0.00082687475,"threshold_uncertainty_score":0.16384852},"labels":[],"label_agreement":null},{"id":"W4211077145","doi":"10.1017/9781108571401.031","title":"Asymptotic Lower Bounds for Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Applied mathematics; Mathematical optimization; Computer science","score_opus":0.10754279321445281,"score_gpt":0.3270016872116386,"score_spread":0.21945889399718577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211077145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01549079,0.02408841,0.71941525,0.0072786417,0.0017013183,0.00013336955,0.0014286451,0.0015039984,0.2289596],"genre_scores_gemma":[0.5889253,0.036134996,0.2038854,0.005955406,0.0073642894,0.0018496801,0.0043933354,0.003087113,0.1484045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945205,0.0020290005,0.0001852573,0.0005933002,0.0018882059,0.0007837446],"domain_scores_gemma":[0.955225,0.036475655,0.0011526304,0.003068058,0.0031466403,0.0009320502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00810011,0.002833253,0.0028022365,0.0036431504,0.001674452,0.0071714106,0.003682312,0.0030212884,0.029138187],"category_scores_gemma":[0.057046756,0.0010679221,0.001816664,0.0048418078,0.0036152077,0.006306435,0.004369915,0.008794209,0.008162303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019343756,0.00011238654,0.00064346934,0.0005301961,0.000096590615,0.00008099739,0.00013436163,0.07327101,0.0010234438,0.82494813,0.032372132,0.06659379],"study_design_scores_gemma":[0.000025022564,0.0000509034,0.00044604184,0.00034449025,0.000050662504,0.00010849495,0.000056080855,0.23883067,0.0007976532,0.7464577,0.01279288,0.000039418726],"about_ca_topic_score_codex":0.0022132231,"about_ca_topic_score_gemma":0.0030172507,"teacher_disagreement_score":0.029138187,"about_ca_system_score_codex":0.005502199,"about_ca_system_score_gemma":0.0023920415,"threshold_uncertainty_score":0.0974769},"labels":[],"label_agreement":null},{"id":"W4211113691","doi":"10.1017/9781108571401.044","title":"Thompson Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Computer science; Computer vision","score_opus":0.20164323119999739,"score_gpt":0.3504672175813527,"score_spread":0.1488239863813553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211113691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005470177,0.0027441639,0.87882876,0.0012983662,0.0008083276,0.00036332497,0.002772278,0.0029713013,0.10474323],"genre_scores_gemma":[0.14244622,0.0032290893,0.6450421,0.0017367048,0.0010492771,0.0011276301,0.012048473,0.0041811,0.18913929],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976284,0.0011216624,0.00009337253,0.00044814456,0.00054826867,0.00016016724],"domain_scores_gemma":[0.99542445,0.0025845184,0.00011000818,0.0011793554,0.0004940033,0.00020770912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029430185,0.00091607316,0.0016134584,0.0013226974,0.000899461,0.0023024017,0.00200905,0.0011670253,0.07224432],"category_scores_gemma":[0.018184727,0.00045210787,0.0008470297,0.0025595082,0.0007400929,0.0017754313,0.0016987207,0.0015446123,0.028039847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027622603,0.00010674455,0.0015660467,0.00043859688,0.00016596931,0.00010948058,0.0001246103,0.038841937,0.0010205962,0.24245104,0.19223703,0.52266175],"study_design_scores_gemma":[0.00017266395,0.00013262514,0.0014306499,0.00029865172,0.00009331735,0.0003272277,0.000095997086,0.27051347,0.0020825115,0.51961136,0.20518096,0.000060618724],"about_ca_topic_score_codex":0.0033406198,"about_ca_topic_score_gemma":0.008742739,"teacher_disagreement_score":0.07224432,"about_ca_system_score_codex":0.0012121999,"about_ca_system_score_gemma":0.0020020402,"threshold_uncertainty_score":0.24168134},"labels":[],"label_agreement":null},{"id":"W4211119672","doi":"10.1017/9781108571401.017","title":"Lower Bounds for Bandits with Finitely Many Arms","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Combinatorics; Mathematics","score_opus":0.10913095436271733,"score_gpt":0.3121324960950227,"score_spread":0.20300154173230536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211119672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022680832,0.024303736,0.5382468,0.007921057,0.0014286716,0.00016891639,0.002349115,0.0013774391,0.40152344],"genre_scores_gemma":[0.5806379,0.03352021,0.19955908,0.00538352,0.0053158277,0.0022310421,0.004787789,0.0028894197,0.16567525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99601907,0.0013121733,0.00015808627,0.00058596476,0.0011899483,0.0007347605],"domain_scores_gemma":[0.95931005,0.034390647,0.0010368202,0.0028664842,0.0015253676,0.0008707515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054632477,0.0036926162,0.0028888627,0.0036931916,0.002370942,0.009623267,0.0040216376,0.0033981542,0.03677145],"category_scores_gemma":[0.034489177,0.001244717,0.0022808155,0.0053687575,0.0037263082,0.009907086,0.0040125907,0.011583324,0.010723659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020469794,0.00010248888,0.0004949865,0.00059528666,0.000094482304,0.000078818346,0.00015131816,0.03238906,0.00096475263,0.8875175,0.030681545,0.046725012],"study_design_scores_gemma":[0.000024642419,0.000041948035,0.0002705822,0.00026188765,0.000055439254,0.00009174727,0.0000449258,0.066165365,0.0006238249,0.92166746,0.010726145,0.000026032694],"about_ca_topic_score_codex":0.0016086256,"about_ca_topic_score_gemma":0.0023294296,"teacher_disagreement_score":0.03677145,"about_ca_system_score_codex":0.0054064845,"about_ca_system_score_gemma":0.002038721,"threshold_uncertainty_score":0.12301272},"labels":[],"label_agreement":null},{"id":"W4211129173","doi":"10.1017/9781108571401.003","title":"Introduction","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.09092964838076466,"score_gpt":0.3070685843658825,"score_spread":0.21613893598511785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211129173","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010287385,0.018461587,0.009823971,0.010052974,0.0140233105,0.00044986745,0.016796041,0.0028159088,0.9265476],"genre_scores_gemma":[0.0025314211,0.010615786,0.0035171688,0.0031884615,0.0023691945,0.00018077572,0.0102847675,0.0006652467,0.9666471],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992205,0.000060147326,0.000040720468,0.00018313424,0.00041623978,0.00007930752],"domain_scores_gemma":[0.9988102,0.00015957117,0.00005927242,0.00013650746,0.00059639366,0.00023807006],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008770679,0.0011032425,0.00062559254,0.0021638987,0.0009840103,0.0040014046,0.0017010123,0.0018407186,0.5640704],"category_scores_gemma":[0.002924185,0.00038754725,0.00069860945,0.0021515633,0.0005401274,0.0025590153,0.0018160034,0.0018574286,0.49342558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003003561,0.000032526543,0.00012209763,0.0004021814,0.0000036810632,0.000049997398,0.000065145934,0.00015420417,0.0004189352,0.01211117,0.8353888,0.15122132],"study_design_scores_gemma":[0.0000013841394,0.0000080644295,0.00010783761,0.00008493413,0.0000011310115,0.000036612513,0.0000146818875,0.000014660621,0.000061476254,0.0013571685,0.9983095,0.000002580124],"about_ca_topic_score_codex":0.002812181,"about_ca_topic_score_gemma":0.0032458447,"teacher_disagreement_score":0.4359296,"about_ca_system_score_codex":0.0015470779,"about_ca_system_score_gemma":0.0020041391,"threshold_uncertainty_score":0.62180066},"labels":[],"label_agreement":null},{"id":"W4211143440","doi":"10.1017/9781108571401.016","title":"The Exp3-IX Algorithm","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Algorithm; Computer science","score_opus":0.09735901328993013,"score_gpt":0.3147774227942208,"score_spread":0.21741840950429064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211143440","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060545634,0.0011904293,0.88700193,0.0012111834,0.000923347,0.00054958946,0.0048549604,0.029252738,0.06896117],"genre_scores_gemma":[0.0478411,0.0006247394,0.8452898,0.00086856494,0.0003981333,0.00071766245,0.013055478,0.0068713347,0.08433321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887186,0.00018850678,0.00007089494,0.00030941845,0.00039039532,0.00016891272],"domain_scores_gemma":[0.9988424,0.00028105325,0.00003503669,0.00047407913,0.00029105815,0.00007646026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012876758,0.0016298983,0.0011055272,0.0012744563,0.000994323,0.0026440874,0.0026159498,0.0016636107,0.1191219],"category_scores_gemma":[0.0059673847,0.0005293142,0.0014165065,0.0016303912,0.00065111025,0.0025355418,0.002696997,0.0024267328,0.07912679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005487788,0.00013955243,0.000578287,0.00029124526,0.000067048786,0.00008915628,0.000056169592,0.015298229,0.002741452,0.03627663,0.24640034,0.6975131],"study_design_scores_gemma":[0.0006387347,0.00025007446,0.0010266268,0.00022211202,0.00008296752,0.0007277115,0.00017886717,0.4652646,0.0136263305,0.24173735,0.27616495,0.00007968901],"about_ca_topic_score_codex":0.0025288274,"about_ca_topic_score_gemma":0.0039268667,"teacher_disagreement_score":0.1191219,"about_ca_system_score_codex":0.00089561526,"about_ca_system_score_gemma":0.0025547298,"threshold_uncertainty_score":0.39850247},"labels":[],"label_agreement":null},{"id":"W4211152972","doi":"10.1017/9781108571401.045","title":"Beyond Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.09638812491299197,"score_gpt":0.31239178348081303,"score_spread":0.21600365856782106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211152972","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003970681,0.0453624,0.44432646,0.008450356,0.003683576,0.00010610903,0.0011574586,0.0018646236,0.4910784],"genre_scores_gemma":[0.15292759,0.067181356,0.17227414,0.005656346,0.005966648,0.00041871952,0.0021515666,0.0032495942,0.590174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985947,0.00044912868,0.00006658623,0.00025423855,0.00048787065,0.00014750657],"domain_scores_gemma":[0.996888,0.0019127727,0.00010525428,0.00061639893,0.00037053748,0.00010702258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016150337,0.0012207319,0.001206242,0.0014947932,0.0011370557,0.0062519354,0.0012062989,0.0019497391,0.06484236],"category_scores_gemma":[0.009799517,0.0005537959,0.00076674233,0.0032377616,0.001966726,0.0072041275,0.0019424269,0.0041448423,0.0378556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076952405,0.000032257383,0.00012424884,0.0003124578,0.000026032723,0.000057250396,0.000092678136,0.007230655,0.00060736,0.6796923,0.0796995,0.23204823],"study_design_scores_gemma":[0.000011829052,0.000033113505,0.0001415437,0.00029778943,0.000015703457,0.0001502403,0.00004939859,0.016354643,0.00090854656,0.69811296,0.28390026,0.000023884522],"about_ca_topic_score_codex":0.0020089555,"about_ca_topic_score_gemma":0.0018910266,"teacher_disagreement_score":0.06484236,"about_ca_system_score_codex":0.0017250263,"about_ca_system_score_gemma":0.001242247,"threshold_uncertainty_score":0.2169193},"labels":[],"label_agreement":null},{"id":"W4211163949","doi":"10.1017/9781108571401.046","title":"Partial Monitoring","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Mathematics","score_opus":0.15381143126167723,"score_gpt":0.33711437854307724,"score_spread":0.1833029472814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211163949","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010443739,0.0074742846,0.26056904,0.005014589,0.0024917326,0.0008853479,0.023276495,0.03330366,0.65654117],"genre_scores_gemma":[0.1995733,0.0105584245,0.12834373,0.0029355835,0.0016534654,0.00085378875,0.04647147,0.008523069,0.60108715],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99779475,0.0002908971,0.00013382739,0.00043508806,0.0011283405,0.00021712059],"domain_scores_gemma":[0.9946654,0.0010254699,0.00024591896,0.0022360904,0.0015361025,0.00029102425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023415869,0.0012022675,0.0009807994,0.0019488343,0.0010083196,0.0039417767,0.001993329,0.001016107,0.14326045],"category_scores_gemma":[0.008224444,0.00040231855,0.0008471168,0.0023143431,0.0005786595,0.004828466,0.0021665525,0.0012499033,0.066850744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042720765,0.000073208794,0.001621148,0.00067261676,0.000039680588,0.00019562806,0.00017066742,0.004291115,0.0038747347,0.041019894,0.31345055,0.6341637],"study_design_scores_gemma":[0.000031527015,0.00012135758,0.0019399482,0.00036500604,0.00005818782,0.0004617758,0.00011303145,0.012184262,0.009004849,0.031069536,0.9445988,0.000051691855],"about_ca_topic_score_codex":0.0036617282,"about_ca_topic_score_gemma":0.0034945619,"teacher_disagreement_score":0.14326045,"about_ca_system_score_codex":0.0012376185,"about_ca_system_score_gemma":0.0021370375,"threshold_uncertainty_score":0.47925395},"labels":[],"label_agreement":null},{"id":"W4211171003","doi":"10.1017/9781108571401.001","title":"Preface","year":2020,"lang":"en","type":"other","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; World Wide Web; Mathematics","score_opus":0.22434086232381706,"score_gpt":0.49645233803165617,"score_spread":0.2721114757078391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211171003","genre_codex":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010430663,0.013684159,0.01313636,0.03261846,0.18583901,0.00092635985,0.04607877,0.003603826,0.70307004],"genre_scores_gemma":[0.003842112,0.009364059,0.0035517244,0.0058979136,0.029485332,0.00039730396,0.024649246,0.0017556968,0.92105675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990126,0.00010805835,0.00007691389,0.00016273232,0.00056537107,0.00007436259],"domain_scores_gemma":[0.99212986,0.0013272333,0.0003091266,0.0005709916,0.004686205,0.0009765102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016744001,0.0010456303,0.0007267614,0.0034075947,0.0015073143,0.003956585,0.0013263975,0.0011522471,0.5899243],"category_scores_gemma":[0.014883037,0.00035560894,0.00060960033,0.002553607,0.0005373737,0.0025161433,0.0014381032,0.0029765351,0.5039293],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012080068,0.000007694267,0.000039186554,0.00009168807,0.0000010464777,0.000013575071,0.00001595801,0.000062319195,0.00005701262,0.0020108905,0.9757829,0.021905696],"study_design_scores_gemma":[0.0000029128016,0.000008819779,0.0001647484,0.00013492603,0.0000012300923,0.000025444666,0.00001976612,0.000024766985,0.00004664017,0.0016305754,0.9979365,0.0000036410265],"about_ca_topic_score_codex":0.004062946,"about_ca_topic_score_gemma":0.004078018,"teacher_disagreement_score":0.5899243,"about_ca_system_score_codex":0.0019640576,"about_ca_system_score_gemma":0.002295213,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4211172573","doi":"10.1017/9781108571401.030","title":"Minimax Lower Bounds for Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Minimax; Mathematics; Mathematical optimization; Computer science; Applied mathematics","score_opus":0.12054412877025228,"score_gpt":0.3339099261002477,"score_spread":0.21336579732999544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211172573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01031923,0.027839204,0.71124816,0.007313864,0.0018236474,0.00009508332,0.0013998786,0.0010297262,0.23893127],"genre_scores_gemma":[0.45040232,0.045631185,0.23800923,0.0051914696,0.006273827,0.0015487606,0.0036620025,0.0031265544,0.24615471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973832,0.0009106391,0.00010304358,0.00034504404,0.0009583322,0.00029970167],"domain_scores_gemma":[0.985052,0.012223712,0.00041733272,0.0010357858,0.00096180144,0.00030939135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045718807,0.0023247956,0.0023061968,0.002094271,0.0010754664,0.006021472,0.0023543155,0.0025992154,0.029104678],"category_scores_gemma":[0.025854236,0.0008824752,0.0012806052,0.0030696632,0.0024252108,0.0049375826,0.0028325107,0.007749389,0.0081127435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012313573,0.00006586067,0.00026890752,0.00042723792,0.00007498034,0.00005278299,0.00008798939,0.07560831,0.00086841587,0.8060806,0.03704445,0.07929745],"study_design_scores_gemma":[0.000021910497,0.000047867285,0.0003037827,0.0002953244,0.000031265245,0.00007202979,0.000034574976,0.19427007,0.00082431926,0.78316873,0.020901203,0.000028831006],"about_ca_topic_score_codex":0.0012877107,"about_ca_topic_score_gemma":0.0017321224,"teacher_disagreement_score":0.029104678,"about_ca_system_score_codex":0.0034973929,"about_ca_system_score_gemma":0.0015654258,"threshold_uncertainty_score":0.09736484},"labels":[],"label_agreement":null},{"id":"W4211180791","doi":"10.1017/9781108571401.024","title":"Contextual Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Psychology; Artificial intelligence","score_opus":0.12866421338510198,"score_gpt":0.32146860365302693,"score_spread":0.19280439026792495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211180791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007693795,0.010442491,0.6064832,0.003211009,0.00133634,0.00013053804,0.0024087266,0.0017691063,0.3665248],"genre_scores_gemma":[0.34390524,0.018398212,0.32961398,0.0029528295,0.0025426727,0.0007074224,0.0057548643,0.0031901158,0.2929347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858487,0.0004631075,0.00007407346,0.00032682804,0.00038929525,0.00016196314],"domain_scores_gemma":[0.9972811,0.0014947056,0.00011388718,0.00063986355,0.00036157563,0.00010893734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016862432,0.001053212,0.0010740913,0.0012813946,0.0011559603,0.004480466,0.0012429245,0.0015679433,0.07219482],"category_scores_gemma":[0.0102341445,0.00046127202,0.00075595686,0.0025485028,0.0014970581,0.003910646,0.001959761,0.0027108595,0.0226158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012801414,0.00003839816,0.00031007783,0.00030211138,0.000038451297,0.000056551016,0.00011741022,0.0135442,0.00075704843,0.7529434,0.066589855,0.16517441],"study_design_scores_gemma":[0.000025746976,0.00004256411,0.00047380893,0.00034023417,0.00004043567,0.00016437046,0.00009324569,0.06551271,0.0013575547,0.7537611,0.17815322,0.000034962926],"about_ca_topic_score_codex":0.0021506513,"about_ca_topic_score_gemma":0.003309568,"teacher_disagreement_score":0.07219482,"about_ca_system_score_codex":0.0015279286,"about_ca_system_score_gemma":0.0010728049,"threshold_uncertainty_score":0.2415157},"labels":[],"label_agreement":null},{"id":"W4211193691","doi":"10.1017/9781108571401.029","title":"Stochastic Linear Bandits with Sparsity","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Mathematical optimization; Mathematics; Mathematical analysis","score_opus":0.10929667756822216,"score_gpt":0.30482737592319514,"score_spread":0.195530698354973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211193691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007030785,0.015041707,0.80239093,0.00563939,0.0012390872,0.00004605888,0.0014215109,0.0012748297,0.16591574],"genre_scores_gemma":[0.29682633,0.034092654,0.279649,0.003080111,0.0047856155,0.00042581232,0.0045679407,0.0016718395,0.37490064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99964154,0.00013567857,0.00001516108,0.000059464153,0.000118957854,0.000029293868],"domain_scores_gemma":[0.99880576,0.00087179994,0.000044646902,0.00013492048,0.00009961259,0.000043187712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000945401,0.0009075704,0.00078917155,0.00050903007,0.0002924811,0.0017351883,0.0005954025,0.00086017215,0.022471178],"category_scores_gemma":[0.00396723,0.0003843027,0.000435928,0.0012831605,0.00083332206,0.0017496928,0.0010388404,0.0021479812,0.011437679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010572984,0.000049930386,0.0003598589,0.00037481234,0.00006953162,0.00008655513,0.000072587616,0.075055085,0.0015439093,0.56411314,0.11690603,0.24126293],"study_design_scores_gemma":[0.000024465939,0.000047518417,0.00047071514,0.00022594378,0.000024861225,0.00012274199,0.000029214114,0.2882787,0.0011120929,0.62488014,0.08475253,0.00003108237],"about_ca_topic_score_codex":0.0010196078,"about_ca_topic_score_gemma":0.0016069884,"teacher_disagreement_score":0.022471178,"about_ca_system_score_codex":0.0006182321,"about_ca_system_score_gemma":0.0006308841,"threshold_uncertainty_score":0.07517362},"labels":[],"label_agreement":null},{"id":"W4211215680","doi":"10.1017/9781108571401.036","title":"The Relation between Adversarial and Stochastic Linear Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Relation (database); Adversarial system; Content (measure theory); Computer science; Mathematical optimization; Theoretical computer science; Artificial intelligence; Mathematics; Data mining","score_opus":0.09798280793259397,"score_gpt":0.3136995318673979,"score_spread":0.21571672393480396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211215680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018105226,0.013439421,0.76975733,0.005088937,0.0007592269,0.000033096203,0.0003775148,0.00043020703,0.19200905],"genre_scores_gemma":[0.69692355,0.016732983,0.11613725,0.0021076347,0.0021372237,0.00017943139,0.0006572962,0.00063845573,0.1644862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986626,0.0005495001,0.000051545907,0.00022604085,0.00038342967,0.00012688282],"domain_scores_gemma":[0.9915891,0.0071954154,0.00032029953,0.00048491854,0.00026137047,0.00014886279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001882125,0.00079365727,0.00080390007,0.0008346846,0.00060760847,0.003189598,0.0011987768,0.001559005,0.011489862],"category_scores_gemma":[0.012008701,0.0005232158,0.0005418737,0.0015568215,0.0030886978,0.003240177,0.0019262552,0.0039348933,0.0021486436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003568683,0.000010933732,0.00015351019,0.00007611382,0.000018461858,0.000038214333,0.000048725386,0.0500349,0.0002605709,0.9187256,0.0043529933,0.026244305],"study_design_scores_gemma":[0.0000046153655,0.000011805941,0.00015005034,0.000051101495,0.000007569858,0.000045250883,0.000013614691,0.13157786,0.00023952354,0.8616413,0.0062448727,0.000012332678],"about_ca_topic_score_codex":0.0019837937,"about_ca_topic_score_gemma":0.0013882588,"teacher_disagreement_score":0.011489862,"about_ca_system_score_codex":0.0019036832,"about_ca_system_score_gemma":0.00072750665,"threshold_uncertainty_score":0.038437426},"labels":[],"label_agreement":null},{"id":"W4211225820","doi":"10.1017/9781108571401.022","title":"High-Probability Lower Bounds","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Mathematics; Mathematical analysis","score_opus":0.10183471744309376,"score_gpt":0.3042910215945722,"score_spread":0.20245630415147847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211225820","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047844187,0.038439054,0.41778845,0.011391451,0.0035874022,0.00013345058,0.0033993747,0.0012905402,0.51918584],"genre_scores_gemma":[0.32254443,0.07597992,0.22600563,0.01326203,0.01902843,0.0018774606,0.009669572,0.005178272,0.32645425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944253,0.0015662037,0.0001874376,0.000832772,0.0021610095,0.0008273503],"domain_scores_gemma":[0.9671088,0.02481639,0.0006018651,0.0039381133,0.0026913632,0.0008434093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054866984,0.00360399,0.0033268346,0.004841626,0.002288365,0.0074313967,0.0045398152,0.003291396,0.06426891],"category_scores_gemma":[0.037102308,0.0010403111,0.0024682188,0.006757198,0.003684119,0.007886744,0.004830815,0.012729927,0.026760116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014487743,0.00009057452,0.0004994733,0.0009930035,0.000113665395,0.00016314519,0.00010615706,0.014195174,0.000697186,0.70237315,0.1846545,0.09596915],"study_design_scores_gemma":[0.000027332257,0.000036459118,0.00044127172,0.00032137512,0.00006735161,0.00025368467,0.000037542304,0.027120804,0.0006756275,0.9095527,0.061432183,0.00003369407],"about_ca_topic_score_codex":0.00214339,"about_ca_topic_score_gemma":0.002289822,"teacher_disagreement_score":0.06426891,"about_ca_system_score_codex":0.0051344014,"about_ca_system_score_gemma":0.0020752826,"threshold_uncertainty_score":0.21500093},"labels":[],"label_agreement":null},{"id":"W4211230244","doi":"10.1017/9781108571401.043","title":"Bayesian Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bayesian probability; Computer science; Content (measure theory); Artificial intelligence; Mathematics","score_opus":0.0991330921139965,"score_gpt":0.31334188231081306,"score_spread":0.21420879019681655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211230244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003070106,0.020567834,0.70244443,0.0033711526,0.0012225257,0.00007325039,0.0027635617,0.0017123887,0.2647748],"genre_scores_gemma":[0.14186502,0.03741654,0.33136922,0.0020293614,0.001981662,0.00036700213,0.0072065047,0.0021740613,0.47559062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992574,0.00025657576,0.000032426746,0.00012512665,0.00026506267,0.00006349376],"domain_scores_gemma":[0.9985183,0.0009666951,0.000061126666,0.00018718376,0.00020897856,0.00005764195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016312887,0.0010825988,0.0011611035,0.0010777315,0.0004983378,0.0027149352,0.0011808082,0.0015059054,0.058495615],"category_scores_gemma":[0.006698144,0.00047579332,0.00069394265,0.002265614,0.00077195495,0.0022035334,0.001041648,0.0020662043,0.031046297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001068577,0.000052423453,0.00040914136,0.00044103636,0.000096940035,0.000056301564,0.00007015783,0.048230294,0.00062244927,0.40016767,0.16280891,0.38693783],"study_design_scores_gemma":[0.00002896637,0.000041550895,0.00070172595,0.00039695756,0.00005157863,0.00016869763,0.000045407036,0.14929065,0.0010313937,0.5849271,0.26326516,0.000050825634],"about_ca_topic_score_codex":0.002364398,"about_ca_topic_score_gemma":0.0035426565,"teacher_disagreement_score":0.058495615,"about_ca_system_score_codex":0.0010775662,"about_ca_system_score_gemma":0.0009985717,"threshold_uncertainty_score":0.1956873},"labels":[],"label_agreement":null},{"id":"W4211235784","doi":"10.1017/9781108571401.007","title":"Concentration of Measure","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Measure (data warehouse); Content (measure theory); Computer science; Database; Mathematics","score_opus":0.1222825914765115,"score_gpt":0.3126055781601176,"score_spread":0.1903229866836061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211235784","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008457785,0.030959032,0.29071227,0.013234187,0.0013518227,0.000081590275,0.0012670305,0.0005523974,0.6533838],"genre_scores_gemma":[0.44107613,0.05116356,0.11308717,0.0076731998,0.008261399,0.00076187745,0.0022725912,0.0018503119,0.3738537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975442,0.00066127867,0.00009323323,0.00066190114,0.0008152109,0.00022418171],"domain_scores_gemma":[0.9924718,0.0045688585,0.0003498184,0.0010906548,0.0011703339,0.00034851406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025406834,0.0014085954,0.0017895262,0.00371772,0.0015753049,0.006249513,0.0016942113,0.0020685468,0.036717806],"category_scores_gemma":[0.015055251,0.0005530819,0.0013418295,0.0031473117,0.004549535,0.006662411,0.0031180484,0.0045761704,0.010479509],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005563975,0.0000038914286,0.00007110825,0.00008702832,0.000010035318,0.000018373687,0.00005936299,0.00047729854,0.00013911065,0.9778245,0.013435005,0.007868716],"study_design_scores_gemma":[0.0000042176453,0.000010582469,0.00020809859,0.00007498004,0.000009804505,0.000078893165,0.00002780722,0.0038483173,0.00027466606,0.9457256,0.049726836,0.00001016229],"about_ca_topic_score_codex":0.0020923624,"about_ca_topic_score_gemma":0.0011948853,"teacher_disagreement_score":0.036717806,"about_ca_system_score_codex":0.0047708233,"about_ca_system_score_gemma":0.001338627,"threshold_uncertainty_score":0.12283331},"labels":[],"label_agreement":null},{"id":"W4211236808","doi":"10.1017/9781108571401.004","title":"Foundations of Probability","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Action (physics); Computer science; Mathematics; Physics","score_opus":0.17185258790490945,"score_gpt":0.3399381421757821,"score_spread":0.16808555427087266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211236808","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00559665,0.07382454,0.30912676,0.02035604,0.0019716464,0.000038972517,0.0015674374,0.0006903124,0.58682775],"genre_scores_gemma":[0.5065495,0.12192174,0.112268426,0.005636413,0.010056297,0.00038142226,0.0018783932,0.0007029875,0.24060486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992055,0.00027592864,0.000032838427,0.00014246376,0.0002823288,0.0000609029],"domain_scores_gemma":[0.99765354,0.0016501708,0.00008664391,0.00028878768,0.00022997189,0.000090864756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012386356,0.00065783516,0.00072033814,0.0014955179,0.00088498025,0.0030296189,0.00065194984,0.0010673932,0.021583017],"category_scores_gemma":[0.0046424475,0.0003955386,0.00072455057,0.0015562122,0.0027844699,0.0032492324,0.0010927254,0.0026515787,0.0063749533],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003436314,0.0000033121296,0.000073173476,0.000064912114,0.0000071573118,0.000023164715,0.000044511406,0.0010340437,0.0000659683,0.9657353,0.018590037,0.0143549265],"study_design_scores_gemma":[0.0000020820887,0.0000035353942,0.00014374928,0.00004108126,0.0000030780284,0.000040245242,0.000012977052,0.0014108024,0.00004027381,0.95571667,0.04258162,0.000003911097],"about_ca_topic_score_codex":0.0017505635,"about_ca_topic_score_gemma":0.0012848581,"teacher_disagreement_score":0.021583017,"about_ca_system_score_codex":0.002262624,"about_ca_system_score_gemma":0.0012711907,"threshold_uncertainty_score":0.072202384},"labels":[],"label_agreement":null},{"id":"W4211243395","doi":"10.1017/9781108571401.040","title":"Ranking","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Ranking (information retrieval); Computer science; Artificial intelligence","score_opus":0.13068629293194783,"score_gpt":0.32197352614614366,"score_spread":0.19128723321419583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211243395","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003702761,0.003123497,0.057634316,0.0030738078,0.0024434552,0.0008430278,0.086127326,0.01701487,0.82603705],"genre_scores_gemma":[0.025235085,0.0046468587,0.03651048,0.0009990187,0.0007404575,0.00043612774,0.10524686,0.0058306875,0.8203544],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971354,0.00033418468,0.00012675139,0.0003987607,0.001692496,0.00031248428],"domain_scores_gemma":[0.9964227,0.0005786027,0.0001211827,0.0006538766,0.0018654767,0.00035812965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018631828,0.001791471,0.0012310985,0.0053819255,0.001290461,0.006347782,0.0019226886,0.00089516566,0.5119694],"category_scores_gemma":[0.00900462,0.00042937585,0.0010602075,0.0063699717,0.00040586447,0.004294492,0.0016340417,0.0014207223,0.47509006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006271864,0.00004155201,0.00046922578,0.0003007192,0.000016834272,0.000023839068,0.000030307237,0.0009850315,0.0005659384,0.014272011,0.76132846,0.2219034],"study_design_scores_gemma":[0.000019077544,0.000055540615,0.0014319032,0.00015717257,0.00001833856,0.0001136407,0.00012989144,0.0025383427,0.0012670604,0.015308678,0.97892326,0.000037119178],"about_ca_topic_score_codex":0.0053634667,"about_ca_topic_score_gemma":0.010096423,"teacher_disagreement_score":0.5119694,"about_ca_system_score_codex":0.0018947968,"about_ca_system_score_gemma":0.0023921144,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4211244366","doi":"10.1017/9781108571401.035","title":"Follow-the-regularised-Leader and Mirror Descent","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Descent (aeronautics); Mathematics; Computer science; Geology; Physics; Meteorology","score_opus":0.13432570621830284,"score_gpt":0.30901764966248446,"score_spread":0.17469194344418162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211244366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006632921,0.0034009994,0.8419366,0.0016950237,0.0013587555,0.0000850833,0.0004563574,0.0010163225,0.143418],"genre_scores_gemma":[0.28115508,0.005356695,0.33323935,0.0013015863,0.0010970535,0.00031856677,0.0014005874,0.0016830097,0.37444797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997242,0.00007595322,0.0000117585205,0.00006741312,0.00008175571,0.000038911607],"domain_scores_gemma":[0.9995198,0.0002433225,0.000025675956,0.00010916398,0.00006255645,0.000039535706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064474443,0.0007603264,0.0008517688,0.0003110645,0.00043564633,0.0011854668,0.0012138116,0.0010017448,0.024620563],"category_scores_gemma":[0.0031658781,0.0003107876,0.0006378268,0.00066455966,0.00071331323,0.0013642404,0.0009817648,0.0019557693,0.009708536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014433192,0.00008156738,0.00041670355,0.000325873,0.000066200446,0.00014859503,0.000101486,0.11606645,0.0014551376,0.5138674,0.11655579,0.25077042],"study_design_scores_gemma":[0.000050440143,0.00011442747,0.0003136648,0.00009545777,0.000025472513,0.00021515567,0.00003822342,0.39882022,0.0012519389,0.5321205,0.066921145,0.000033282064],"about_ca_topic_score_codex":0.0012818023,"about_ca_topic_score_gemma":0.0023981598,"teacher_disagreement_score":0.024620563,"about_ca_system_score_codex":0.00060040184,"about_ca_system_score_gemma":0.0009963367,"threshold_uncertainty_score":0.08236396},"labels":[],"label_agreement":null},{"id":"W4211244740","doi":"10.1017/9781108571401.021","title":"Instance-Dependent Lower Bounds","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Content (measure theory); Computer science; Theoretical computer science; Information retrieval; Computer network; Mathematics; Mathematical analysis","score_opus":0.0978907667440073,"score_gpt":0.31089200036536113,"score_spread":0.2130012336213538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211244740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005810065,0.018643327,0.5069573,0.009750343,0.0025202248,0.00024140454,0.005099286,0.0028714852,0.44810656],"genre_scores_gemma":[0.26487458,0.0340949,0.39008284,0.00838033,0.0075376807,0.0015259515,0.017375795,0.009148946,0.26697907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99351525,0.0016099903,0.00024834074,0.0011173857,0.0026504057,0.00085859024],"domain_scores_gemma":[0.97467333,0.01787424,0.00050130475,0.004673916,0.0015591304,0.00071796816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050422195,0.0033503454,0.002437325,0.0029353942,0.0013401507,0.008485038,0.0058497717,0.0026871087,0.078547314],"category_scores_gemma":[0.031953864,0.0013965121,0.0025237699,0.0051085525,0.0020566923,0.0108971605,0.00543425,0.014504042,0.028752277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021344602,0.00014808499,0.00036880837,0.0009019702,0.0001109137,0.000113153495,0.0000858647,0.027287204,0.0012511753,0.5918073,0.22435446,0.15335764],"study_design_scores_gemma":[0.00004017028,0.00006304857,0.00036074073,0.0003281748,0.00008993679,0.00029309336,0.0000444812,0.09802991,0.00183999,0.7855163,0.11335285,0.000041282383],"about_ca_topic_score_codex":0.0014458308,"about_ca_topic_score_gemma":0.0019015562,"teacher_disagreement_score":0.078547314,"about_ca_system_score_codex":0.005052138,"about_ca_system_score_gemma":0.0023706565,"threshold_uncertainty_score":0.26276696},"labels":[],"label_agreement":null},{"id":"W4211259986","doi":"10.1017/9781108571401.038","title":"Combinatorial Bandits","year":2020,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Content (measure theory); Computer network; Information retrieval; Mathematics","score_opus":0.10123300665543071,"score_gpt":0.31341962928951744,"score_spread":0.21218662263408672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211259986","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067484505,0.016591785,0.24225582,0.0027300227,0.0014810184,0.00008420786,0.0016245047,0.0008306647,0.7276535],"genre_scores_gemma":[0.2561343,0.033451594,0.13822623,0.002586161,0.0027925412,0.0005467676,0.004563635,0.0015106429,0.5601881],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994622,0.00013736877,0.000022798362,0.000102454615,0.0002042008,0.00007099714],"domain_scores_gemma":[0.9991641,0.0004560986,0.000032719465,0.00017227854,0.00011429902,0.00006037783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068620674,0.00091510307,0.0008989272,0.0012306132,0.00082109246,0.0034091868,0.00093095185,0.0011030713,0.047763795],"category_scores_gemma":[0.0029779363,0.00037207382,0.00057552266,0.002411574,0.0011976555,0.0023096544,0.0012205266,0.0025559403,0.017048353],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004887889,0.000033761014,0.00012862997,0.00023899275,0.000023375,0.000040264465,0.000044644083,0.012309195,0.0006639296,0.7724835,0.09801521,0.115969546],"study_design_scores_gemma":[0.000018354414,0.000029778974,0.00032358713,0.00019824145,0.000019200364,0.0001652868,0.000042789845,0.036205783,0.0008530416,0.75780636,0.20431492,0.00002263968],"about_ca_topic_score_codex":0.0010722067,"about_ca_topic_score_gemma":0.0015256868,"teacher_disagreement_score":0.047763795,"about_ca_system_score_codex":0.0014776138,"about_ca_system_score_gemma":0.0008256929,"threshold_uncertainty_score":0.1597858},"labels":[],"label_agreement":null},{"id":"W4214636767","doi":"10.1109/lcsys.2022.3155067","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","year":2022,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Convexity; Smoothness; Mathematical optimization; Lipschitz continuity; Convex optimization; Convex function; Regularization (linguistics); Upper and lower bounds; Mathematics; Function (biology); Bounded function; Computer science; Regular polygon; Artificial intelligence; Economics; Mathematical analysis","score_opus":0.09309093525136584,"score_gpt":0.3857145837651675,"score_spread":0.2926236485138016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214636767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10402443,0.00050822395,0.8891774,0.0007535544,0.000058430513,0.000078754805,0.00009123458,0.00036849483,0.004939454],"genre_scores_gemma":[0.9443352,0.00022045641,0.052361142,0.00017288151,0.00003782861,0.000087566565,0.000101975296,0.000094950585,0.0025880628],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99815243,0.0008234478,0.000061496656,0.00030302358,0.00039882248,0.00026068234],"domain_scores_gemma":[0.99395424,0.0043958127,0.00055318046,0.00046673696,0.00038137668,0.00024859837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047381767,0.0011679633,0.0013790487,0.00046398188,0.00067124394,0.0015699907,0.0014432576,0.0016117985,0.0017322461],"category_scores_gemma":[0.015966387,0.0005442151,0.00070658507,0.0004940105,0.0020436787,0.0019358229,0.0017760424,0.0021742997,0.00027907945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025161693,0.00005665537,0.0007208104,0.00004409645,0.000026736134,0.000109539025,0.000032177555,0.95826185,0.0014284035,0.028680686,0.0006644426,0.009723043],"study_design_scores_gemma":[0.000009794539,0.000036426474,0.00013458818,0.0000038420476,0.000003146416,0.000013859991,0.0000038811722,0.9936139,0.0003156108,0.005782227,0.00007839851,0.0000043528876],"about_ca_topic_score_codex":0.0041101263,"about_ca_topic_score_gemma":0.0030242486,"teacher_disagreement_score":0.0047381767,"about_ca_system_score_codex":0.0021474834,"about_ca_system_score_gemma":0.002149876,"threshold_uncertainty_score":0.02505821},"labels":[],"label_agreement":null},{"id":"W4214732409","doi":"10.1093/beheco/arac027","title":"On the strategic learning of signal associations","year":2022,"lang":"en","type":"article","venue":"Behavioral Ecology","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Softmax function; Stochastic game; Profitability index; Machine learning; Artificial intelligence; Prior probability; Bayesian probability; Mathematical economics; Mathematics; Deep learning","score_opus":0.3098390872045215,"score_gpt":0.48165174083419166,"score_spread":0.17181265362967013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214732409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74391586,0.00025568652,0.24776196,0.0014940829,0.00006754581,0.00010818285,0.000085670734,0.0002032615,0.0061077164],"genre_scores_gemma":[0.9890638,0.00006543417,0.009778633,0.00014444964,0.000017295491,0.00004149087,0.000037343445,0.000014785423,0.0008367762],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966397,0.0022467738,0.00010904091,0.00053779513,0.00025408587,0.00021251872],"domain_scores_gemma":[0.9660551,0.028387673,0.0024689399,0.0013728262,0.00097032305,0.00074504217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064821863,0.00077782874,0.00093497284,0.0007076747,0.00045280939,0.0016351218,0.0011120908,0.0014765946,0.002855293],"category_scores_gemma":[0.055176426,0.0005733381,0.00073422823,0.00041816258,0.0018342581,0.0020799006,0.0018446284,0.0018614163,0.00041564135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012570445,0.00058210216,0.04123836,0.00029804124,0.0003737455,0.00037587297,0.0011409202,0.74294126,0.008927932,0.067597136,0.0018300505,0.13343759],"study_design_scores_gemma":[0.000038902024,0.00021900941,0.003288655,0.00001911288,0.000024262703,0.000060251143,0.00006448814,0.9346078,0.00092959235,0.060435094,0.00028846972,0.000024305245],"about_ca_topic_score_codex":0.002113852,"about_ca_topic_score_gemma":0.0014934608,"teacher_disagreement_score":0.0064821863,"about_ca_system_score_codex":0.0010356589,"about_ca_system_score_gemma":0.00086824654,"threshold_uncertainty_score":0.034281492},"labels":[],"label_agreement":null},{"id":"W4220814865","doi":"10.1080/14697688.2022.2049356","title":"The reinforcement learning Kelly strategy","year":2022,"lang":"en","type":"article","venue":"Quantitative Finance","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Portfolio; Reinforcement; Computer science; Artificial intelligence; Face (sociological concept); Mathematical optimization; Operations research; Economics; Mathematics; Psychology; Sociology; Finance; Social psychology","score_opus":0.1802992795779892,"score_gpt":0.4634093563427167,"score_spread":0.2831100767647275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220814865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01765895,0.00038591796,0.966455,0.00063450326,0.0000868409,0.00009116067,0.00006518489,0.00039187286,0.014230556],"genre_scores_gemma":[0.8582797,0.000600048,0.12227346,0.0005244899,0.00011525042,0.00023216108,0.00007769558,0.00006752614,0.017829733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987471,0.0005877966,0.000057300073,0.00019151659,0.000292545,0.00012373734],"domain_scores_gemma":[0.9978034,0.0012355531,0.00025125616,0.00022872596,0.00035717987,0.00012387392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021649667,0.0008325272,0.0009389302,0.00045243767,0.00039620846,0.0013490726,0.0015643381,0.0012328135,0.005243911],"category_scores_gemma":[0.009184971,0.00026631076,0.00038574776,0.0003701381,0.0011540465,0.0015538498,0.0010959134,0.001111106,0.0010667137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027246453,0.00013368402,0.0013339277,0.00018037733,0.00011533376,0.00021558252,0.00014789938,0.49687296,0.0029406084,0.27000487,0.007182494,0.22059987],"study_design_scores_gemma":[0.000045856923,0.00011178384,0.00022929208,0.00003140599,0.000022331964,0.00009449264,0.00002149238,0.93039757,0.00094273116,0.06393496,0.004139716,0.000028347173],"about_ca_topic_score_codex":0.002996549,"about_ca_topic_score_gemma":0.001612642,"teacher_disagreement_score":0.005243911,"about_ca_system_score_codex":0.0009313258,"about_ca_system_score_gemma":0.0014784561,"threshold_uncertainty_score":0.0175426},"labels":[],"label_agreement":null},{"id":"W4224280172","doi":"10.3390/jrfm15040172","title":"Best-Arm Identification Using Extreme Value Theory Estimates of the CVaR","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CVAR; Estimator; Identification (biology); Expected shortfall; Extreme value theory; Selection (genetic algorithm); Value at risk; Econometrics; Computer science; Risk management; Sample (material); Value (mathematics); Mathematical optimization; Statistics; Mathematics; Economics; Finance; Artificial intelligence","score_opus":0.07843315199574445,"score_gpt":0.3692801890360355,"score_spread":0.290847037040291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224280172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009897371,0.0002868677,0.9880406,0.00026200982,0.0000236788,0.000043467415,0.00004515084,0.00020122548,0.001199561],"genre_scores_gemma":[0.6667424,0.0007749027,0.32774043,0.00037509066,0.0001750194,0.000455144,0.00035356003,0.00017866855,0.0032048726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956043,0.002927576,0.00017505286,0.00047050117,0.00057222566,0.0002504634],"domain_scores_gemma":[0.9736597,0.021952843,0.001822139,0.0010995588,0.001105877,0.00035977253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010621338,0.0017000976,0.003067694,0.0020754326,0.00072081876,0.0030811247,0.0021916972,0.002490483,0.003553117],"category_scores_gemma":[0.04362693,0.00079378963,0.0014400814,0.0016292748,0.0019454197,0.0031900513,0.0026105596,0.003049912,0.0007972434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014961227,0.00011144005,0.0021747262,0.00015181203,0.00020620164,0.00015460132,0.00007975715,0.87247616,0.0006715777,0.07825361,0.0012959599,0.04427443],"study_design_scores_gemma":[0.000015122697,0.000044028886,0.00019786083,0.000034448865,0.000016981125,0.000031179858,0.000012805307,0.94850975,0.00027876918,0.050574876,0.00026890857,0.000015147219],"about_ca_topic_score_codex":0.0011083394,"about_ca_topic_score_gemma":0.0009302013,"teacher_disagreement_score":0.010621338,"about_ca_system_score_codex":0.000812319,"about_ca_system_score_gemma":0.001767241,"threshold_uncertainty_score":0.056171656},"labels":[],"label_agreement":null},{"id":"W4225574046","doi":"10.1287/mnsc.2021.4194","title":"Analytical Solution to a Discrete-Time Model for Dynamic Learning and Decision Making","year":2022,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Partially observable Markov decision process; Discrete time and continuous time; Computer science; Mathematical optimization; Markov decision process; Dynamic decision-making; Set (abstract data type); Time horizon; Bellman equation; Constant (computer programming); Markov process; Process (computing); Markov chain; Mathematics; Markov model; Artificial intelligence; Machine learning","score_opus":0.06880974970414613,"score_gpt":0.4639385086242527,"score_spread":0.39512875892010657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225574046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091103185,0.0004708178,0.97773165,0.0015217981,0.000079574864,0.00004699222,0.00024945423,0.00008063151,0.01070874],"genre_scores_gemma":[0.77132463,0.0019587693,0.19760899,0.0003743457,0.00021343106,0.00068997155,0.00048080002,0.000072897834,0.027276177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990736,0.00036490744,0.000040304283,0.000183016,0.00019039949,0.00014776758],"domain_scores_gemma":[0.9973911,0.0018972144,0.00029613587,0.00007995687,0.0002167746,0.00011872923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021357962,0.0010776417,0.0014673811,0.0008014754,0.0006658254,0.002316823,0.0017043833,0.0029214465,0.007972224],"category_scores_gemma":[0.006709349,0.00081877457,0.0012334207,0.0013009309,0.0019001313,0.002072623,0.0012805174,0.0028673604,0.0007070596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023322376,0.000025131165,0.00023666584,0.000067882895,0.000023270875,0.000086940534,0.00006551398,0.7580675,0.00021111255,0.2359239,0.000980392,0.00428839],"study_design_scores_gemma":[0.000012435048,0.0000111631725,0.000059204474,0.000013754607,0.000006385321,0.000016272477,0.00001527534,0.924474,0.00005068796,0.07447466,0.0008587793,0.0000073769856],"about_ca_topic_score_codex":0.008952209,"about_ca_topic_score_gemma":0.0066599343,"teacher_disagreement_score":0.008952209,"about_ca_system_score_codex":0.0030057686,"about_ca_system_score_gemma":0.0031506708,"threshold_uncertainty_score":0.026669681},"labels":[],"label_agreement":null},{"id":"W4226099433","doi":"10.1007/s00498-022-00323-4","title":"Logarithmic regret in online linear quadratic control using Riccati updates","year":2022,"lang":"en","type":"article","venue":"Mathematics of Control Signals and Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Logarithm; Sublinear function; Linear-quadratic regulator; Mathematics; Controller (irrigation); Hindsight bias; Riccati equation; Linear-quadratic-Gaussian control; Mathematical optimization; Optimal control; Control (management); Computer science; Control theory (sociology); Discrete mathematics; Statistics; Artificial intelligence; Differential equation","score_opus":0.13527012559156412,"score_gpt":0.4094376742189131,"score_spread":0.27416754862734893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226099433","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047888275,0.001637342,0.93371236,0.0024810662,0.0002774162,0.00009525385,0.00023024046,0.00057752896,0.013100504],"genre_scores_gemma":[0.9441519,0.00070012704,0.042357165,0.00063146726,0.00028694273,0.00021526645,0.00023877277,0.00031338295,0.011104972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768615,0.0011075821,0.00008948079,0.00033188873,0.00053405715,0.000250957],"domain_scores_gemma":[0.9785831,0.018674655,0.0006275633,0.0008671885,0.0009180635,0.00032931438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048606936,0.0016784399,0.0023819562,0.0007285876,0.0007914486,0.0026961032,0.0024193379,0.0024684984,0.0057065785],"category_scores_gemma":[0.02507118,0.00090107747,0.0005719567,0.0011579869,0.002881466,0.004846511,0.002974324,0.003831535,0.00064716255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043848887,0.00018575821,0.0007364227,0.0002827026,0.000044903914,0.00011045345,0.0000871373,0.88040113,0.00089465815,0.08783826,0.0034710194,0.025509052],"study_design_scores_gemma":[0.000016169899,0.000025841005,0.00009616236,0.000008447665,0.0000048407614,0.000009882322,0.000006653033,0.97580075,0.00019406722,0.023713853,0.00011814948,0.000005051369],"about_ca_topic_score_codex":0.003959074,"about_ca_topic_score_gemma":0.0029500984,"teacher_disagreement_score":0.0057065785,"about_ca_system_score_codex":0.0025678815,"about_ca_system_score_gemma":0.0018692565,"threshold_uncertainty_score":0.025706112},"labels":[],"label_agreement":null},{"id":"W4226342350","doi":"10.1109/tvt.2022.3163078","title":"Optimal Channel Selection in Hybrid RF/VLC Networks: A Multi-Armed Bandit Approach","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Waterloo; Thunder Bay Regional Research Institute","funders":"","keywords":"Selection (genetic algorithm); Visible light communication; Computer science; Channel (broadcasting); Throughput; Wireless; Energy consumption; Radio frequency; Electronic engineering; Mathematical optimization; Convergence (economics); Multi-armed bandit; Engineering; Telecommunications; Mathematics; Machine learning; Electrical engineering","score_opus":0.054139025851553946,"score_gpt":0.34304758940708596,"score_spread":0.288908563555532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226342350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049956895,0.0006850563,0.9444564,0.00059352303,0.00003795109,0.00005959452,0.000044438766,0.00014914885,0.004016939],"genre_scores_gemma":[0.96054614,0.0003461547,0.036030147,0.00019919114,0.000059946615,0.00012248532,0.000039987557,0.00003872438,0.0026172262],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987167,0.00061294873,0.000034746165,0.00015880889,0.00020742018,0.00026939024],"domain_scores_gemma":[0.9967699,0.002315775,0.00044429518,0.00009390595,0.00026179588,0.00011439994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021584928,0.0009271729,0.0016445724,0.0007861853,0.00061086385,0.001637072,0.0012039526,0.0015596034,0.0014982404],"category_scores_gemma":[0.0049226927,0.00066030584,0.000594888,0.00080816133,0.0016914658,0.0012692973,0.001223626,0.0010412426,0.00018830503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036527745,0.000017113452,0.00023746684,0.000015833091,0.000019557448,0.000026782314,0.000017954131,0.9916214,0.00025810898,0.004477435,0.00014161467,0.0031302653],"study_design_scores_gemma":[0.00000321494,0.000008903984,0.000029905797,0.000001935669,0.0000034892219,0.0000035622438,0.0000044113913,0.9987909,0.00005485567,0.0010516666,0.000045196648,0.0000019464649],"about_ca_topic_score_codex":0.0066721323,"about_ca_topic_score_gemma":0.0037315786,"teacher_disagreement_score":0.0066721323,"about_ca_system_score_codex":0.0014147183,"about_ca_system_score_gemma":0.0011234195,"threshold_uncertainty_score":0.013266623},"labels":[],"label_agreement":null},{"id":"W4230736957","doi":"10.2139/ssrn.3249069","title":"Optimal Exploration","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computer science; Geology; Geography","score_opus":0.0941705604698524,"score_gpt":0.4321125470547117,"score_spread":0.3379419865848593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230736957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06957217,0.0020892152,0.7312232,0.0046917526,0.0006997688,0.00024126394,0.000676286,0.0007109438,0.1900955],"genre_scores_gemma":[0.78880906,0.0013629949,0.12173543,0.00089809706,0.00034897472,0.00047269982,0.0005451628,0.00034916983,0.085478425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995801,0.00013806402,0.000018607047,0.00010173506,0.000083650666,0.00007787959],"domain_scores_gemma":[0.99891424,0.0007049844,0.00006079371,0.00012816075,0.0000995143,0.00009223637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006461392,0.0008563354,0.0009881011,0.000940774,0.00065229315,0.0018809858,0.000741942,0.0018320349,0.02603629],"category_scores_gemma":[0.005801839,0.00042534535,0.00066661177,0.0008002811,0.001031056,0.0023780037,0.0023769373,0.0017365242,0.002029841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028669334,0.00015614995,0.0008344426,0.00032416286,0.00009595243,0.00012013104,0.0001265972,0.32765687,0.002340029,0.4941824,0.023691079,0.15018554],"study_design_scores_gemma":[0.000047512774,0.000090404654,0.0002872139,0.00008083297,0.000030537492,0.000104675986,0.00006367511,0.58777195,0.0008332678,0.40277395,0.007900277,0.000015816586],"about_ca_topic_score_codex":0.0006851739,"about_ca_topic_score_gemma":0.00072629855,"teacher_disagreement_score":0.02603629,"about_ca_system_score_codex":0.00070299965,"about_ca_system_score_gemma":0.0012970954,"threshold_uncertainty_score":0.08710009},"labels":[],"label_agreement":null},{"id":"W4237856594","doi":"10.2139/ssrn.3948140","title":"Network Revenue Management with Nonparametric Demand Learning: \\sqrt{T}-regret and Polynomial Dimension Dependency","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Nonparametric statistics; Dimension (graph theory); Dependency (UML); Polynomial; Revenue; Revenue management; Economics; Mathematical economics; Microeconomics; Econometrics; Mathematics; Computer science; Combinatorics; Artificial intelligence; Statistics; Finance","score_opus":0.02380355728856963,"score_gpt":0.32879120736682316,"score_spread":0.3049876500782535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237856594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04346871,0.0007464629,0.94653654,0.0028225458,0.00013431124,0.00012631241,0.00049492286,0.0005405887,0.005129697],"genre_scores_gemma":[0.84329665,0.0007559063,0.1447909,0.00071382977,0.0004919465,0.00028770973,0.0007568765,0.00039408304,0.008512043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771404,0.001209401,0.00006657702,0.0004089979,0.0002734131,0.00032748864],"domain_scores_gemma":[0.98074466,0.015373897,0.0009161621,0.0015171876,0.0008840845,0.00056405796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074734534,0.0015158895,0.0029930763,0.0007962089,0.0007854156,0.00266793,0.0036006987,0.003001806,0.0048655886],"category_scores_gemma":[0.029037511,0.0011401267,0.0010337442,0.0016953786,0.002665949,0.006048637,0.003522339,0.005198203,0.00075187936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029123217,0.00022558653,0.0010043826,0.00013090232,0.000047979054,0.000065858236,0.000044537188,0.9166283,0.000382912,0.049320575,0.0060445126,0.025813233],"study_design_scores_gemma":[0.0000130445715,0.000014052773,0.00005983497,0.000005528088,0.0000046203972,0.000008155894,0.000005759161,0.9819016,0.00009890817,0.017750831,0.00013412684,0.0000035925743],"about_ca_topic_score_codex":0.00678448,"about_ca_topic_score_gemma":0.0052456004,"teacher_disagreement_score":0.0074734534,"about_ca_system_score_codex":0.0028891414,"about_ca_system_score_gemma":0.0029356733,"threshold_uncertainty_score":0.0395239},"labels":[],"label_agreement":null},{"id":"W4242718810","doi":"10.1017/9781108571401.049","title":"Index","year":2020,"lang":"en","type":"paratext","venue":"Cambridge University Press eBooks","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Index (typography); Computer science; World Wide Web","score_opus":0.10867711622926478,"score_gpt":0.3512632323008547,"score_spread":0.24258611607158992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242718810","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006451129,0.0027909796,0.007846241,0.003922441,0.006680259,0.00075381174,0.18588118,0.00910564,0.7823743],"genre_scores_gemma":[0.0015791869,0.003332221,0.0028675972,0.0012109085,0.0018012666,0.00035231077,0.09628387,0.0031350702,0.8894376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856526,0.000115064206,0.00017583236,0.00020325278,0.000825256,0.00011535416],"domain_scores_gemma":[0.9917094,0.0012358929,0.00041529472,0.0009463755,0.0045591965,0.0011338606],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010653259,0.0013423753,0.0013657829,0.009280044,0.0013235492,0.00605145,0.0015134744,0.0011139893,0.85377634],"category_scores_gemma":[0.014597729,0.00049434166,0.00064169365,0.010968621,0.00047179798,0.004786537,0.0021289343,0.0014096167,0.84883296],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016793627,0.000015702093,0.0001041394,0.0002558873,0.000002093303,0.000014623489,0.000020009471,0.000075813325,0.00019413691,0.001709907,0.9468421,0.050748862],"study_design_scores_gemma":[0.0000035261457,0.000009554667,0.00022958816,0.00010443774,0.000002054873,0.000023816732,0.000018450186,0.00004347286,0.00009757626,0.0010442251,0.99841857,0.0000046566565],"about_ca_topic_score_codex":0.0038358434,"about_ca_topic_score_gemma":0.0036063143,"teacher_disagreement_score":0.14622366,"about_ca_system_score_codex":0.0020528974,"about_ca_system_score_gemma":0.002161469,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4281933381","doi":"10.3390/electronics11111782","title":"Cost-Aware Bandits for Efficient Channel Selection in Hybrid Band Networks","year":2022,"lang":"en","type":"article","venue":"Electronics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Thunder Bay Regional Research Institute","funders":"Japan Society for the Promotion of Science","keywords":"Throughput; Computer science; Heuristic; Energy consumption; Transmitter; Wireless; Channel (broadcasting); Selection (genetic algorithm); Efficient energy use; Convergence (economics); Multi-armed bandit; Energy (signal processing); Mathematical optimization; Computer network; Telecommunications; Computer engineering; Electronic engineering; Machine learning; Artificial intelligence; Engineering; Electrical engineering; Mathematics","score_opus":0.07562253431195153,"score_gpt":0.39552097523063184,"score_spread":0.3198984409186803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281933381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07143565,0.00049997616,0.9244072,0.00024130297,0.000040445055,0.00004877093,0.000029288845,0.00018365699,0.0031136496],"genre_scores_gemma":[0.94675785,0.00018897043,0.05158428,0.00010395957,0.00002717581,0.00008453852,0.00003706121,0.000031594856,0.0011846366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994305,0.0002525995,0.000019995947,0.00006868021,0.00012373159,0.000104373845],"domain_scores_gemma":[0.99805176,0.0013963488,0.00019247581,0.000110560664,0.00015643025,0.00009236244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012828349,0.00056730217,0.0008648913,0.0005228484,0.00049455586,0.00087617576,0.0008792861,0.0007401913,0.0018811863],"category_scores_gemma":[0.0043823863,0.0002563425,0.0002968348,0.0004919518,0.00096626906,0.0009695081,0.0008522828,0.00078088115,0.00020844658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016157166,0.00006350529,0.0008690631,0.000043652002,0.000023223878,0.00004525764,0.000055280274,0.9396035,0.0013171133,0.021199398,0.0007561148,0.03586229],"study_design_scores_gemma":[0.000008114746,0.0000217536,0.000067819514,0.000004806916,0.0000040425857,0.000009576885,0.000008188138,0.9955486,0.00027666046,0.0038589474,0.00018925026,0.0000021682736],"about_ca_topic_score_codex":0.002248184,"about_ca_topic_score_gemma":0.0023535765,"teacher_disagreement_score":0.002248184,"about_ca_system_score_codex":0.00081011787,"about_ca_system_score_gemma":0.0008480901,"threshold_uncertainty_score":0.0067843795},"labels":[],"label_agreement":null},{"id":"W4283217744","doi":"10.1109/infocom48880.2022.9796683","title":"Learning from Delayed Semi-Bandit Feedback under Strong Fairness Guarantees","year":2022,"lang":"en","type":"article","venue":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Computer science; Credibility; Online learning; Contrast (vision); Term (time); Mathematical optimization; State (computer science); Upper and lower bounds; Artificial intelligence; Mathematics; Algorithm; Machine learning","score_opus":0.21070162128076683,"score_gpt":0.40880948655989924,"score_spread":0.1981078652791324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283217744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04726369,0.0006133471,0.94715244,0.00071794237,0.000098780794,0.00011828107,0.00019254928,0.00043820858,0.0034048073],"genre_scores_gemma":[0.9115106,0.00044129096,0.083467,0.0004909463,0.00016551885,0.00028671132,0.00020889667,0.00012748,0.0033016528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969432,0.0012680482,0.00015264803,0.0005637831,0.00050699146,0.0005653342],"domain_scores_gemma":[0.97727543,0.018202033,0.0014817357,0.001115253,0.001142913,0.0007826627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068265116,0.0017881145,0.0027264238,0.0007137028,0.0010664653,0.0024408847,0.0022755696,0.0021655466,0.003046017],"category_scores_gemma":[0.024562197,0.00072023616,0.00089089875,0.0009900121,0.0021705911,0.002778802,0.00229433,0.003340982,0.0005876065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000307277,0.00011615611,0.0008643444,0.00011963456,0.000035860226,0.00007282783,0.00008706829,0.9431079,0.00084765395,0.034831487,0.0013897142,0.01822001],"study_design_scores_gemma":[0.00002546118,0.000034847006,0.0000638087,0.000010106551,0.0000058089922,0.000016532773,0.000011907791,0.98017234,0.00030520553,0.01914812,0.00020046777,0.000005412676],"about_ca_topic_score_codex":0.0029961758,"about_ca_topic_score_gemma":0.0025446657,"teacher_disagreement_score":0.0068265116,"about_ca_system_score_codex":0.0019246049,"about_ca_system_score_gemma":0.0028807565,"threshold_uncertainty_score":0.036102414},"labels":[],"label_agreement":null},{"id":"W4283778953","doi":"10.1111/poms.13786","title":"Bayesian dithering for learning: Asymptotically optimal policies in dynamic pricing","year":2022,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dither; Regret; Upper and lower bounds; Asymptotically optimal algorithm; Mathematical optimization; Computer science; Logarithm; Dynamic pricing; Parametric statistics; Bayesian probability; Order (exchange); Set (abstract data type); Mathematics; Economics; Artificial intelligence; Machine learning; Microeconomics; Statistics; Finance","score_opus":0.0443791077691186,"score_gpt":0.3906137799644066,"score_spread":0.34623467219528803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283778953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03579944,0.00063926907,0.95724326,0.001166648,0.000056258712,0.00008683606,0.00012241352,0.00052432163,0.0043614185],"genre_scores_gemma":[0.8271158,0.001117307,0.1635389,0.00087842566,0.00021728838,0.00035196941,0.00033748164,0.0002946345,0.0061481637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598974,0.0018663455,0.00015468703,0.00078406796,0.00072677265,0.00047836182],"domain_scores_gemma":[0.9710561,0.024199208,0.0014002989,0.0016428364,0.0009326641,0.0007688189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006762579,0.001674464,0.0032546518,0.0011514708,0.0011263711,0.0025417178,0.0031475183,0.0033587804,0.004057038],"category_scores_gemma":[0.04498291,0.0013863874,0.0010976311,0.0018807693,0.0034255565,0.007308664,0.0032388514,0.0051087295,0.0007052177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029693087,0.0001990426,0.0008882574,0.00012616132,0.00007412229,0.00009490879,0.00014035936,0.8414198,0.0007533325,0.1281234,0.0023332245,0.025550472],"study_design_scores_gemma":[0.000027095077,0.000039223967,0.00008524499,0.000010635345,0.000009221431,0.000015286294,0.000010271508,0.9404696,0.000272532,0.05871727,0.00033209965,0.000011528472],"about_ca_topic_score_codex":0.004276523,"about_ca_topic_score_gemma":0.0034520372,"teacher_disagreement_score":0.006762579,"about_ca_system_score_codex":0.003524872,"about_ca_system_score_gemma":0.0028116715,"threshold_uncertainty_score":0.035764337},"labels":[],"label_agreement":null},{"id":"W4283836917","doi":"10.1287/msom.2022.1128","title":"Online Personalized Assortment Optimization with High-Dimensional Customer Contextual Data","year":2022,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Regret; Scalability; Set (abstract data type); Relevance (law); Optimization problem; Curse of dimensionality; Benchmark (surveying); Mathematical optimization; Data mining; Machine learning; Algorithm; Database","score_opus":0.09720745596710767,"score_gpt":0.3677456167158194,"score_spread":0.27053816074871173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283836917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1046833,0.0008728655,0.88658804,0.001967926,0.00008999022,0.00030688097,0.0006630046,0.00051524636,0.0043127616],"genre_scores_gemma":[0.8588557,0.00066028925,0.13357458,0.0004461556,0.000147289,0.00042575772,0.00084096484,0.00010292005,0.004946251],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855226,0.0006040503,0.000060054048,0.0004062602,0.00018094052,0.00019642124],"domain_scores_gemma":[0.99551266,0.0033850248,0.00045170626,0.00022493133,0.00019381492,0.0002319351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023074425,0.001615792,0.0031285777,0.0006749514,0.00071354,0.0019503615,0.0021779984,0.0023962713,0.0044697546],"category_scores_gemma":[0.007355464,0.00090604246,0.0011583522,0.0016460858,0.0012991867,0.0028258467,0.0015837589,0.0025871191,0.0006088704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014427432,0.00012810883,0.0011799762,0.000080274636,0.000047553305,0.000101710255,0.000037545364,0.97451526,0.00024087024,0.00810913,0.0013428822,0.014072271],"study_design_scores_gemma":[0.000009185265,0.000020448115,0.00013198536,0.000004754739,0.000005921456,0.0000118917405,0.000014150089,0.9953759,0.0000890114,0.004181231,0.00015040694,0.000005055113],"about_ca_topic_score_codex":0.010519195,"about_ca_topic_score_gemma":0.00627156,"teacher_disagreement_score":0.010519195,"about_ca_system_score_codex":0.0019209408,"about_ca_system_score_gemma":0.0020711154,"threshold_uncertainty_score":0.020915985},"labels":[],"label_agreement":null},{"id":"W4285505943","doi":"10.1109/tnet.2022.3188285","title":"Delay-Tolerant OCO With Long-Term Constraints: Algorithm and Its Application to Network Resource Allocation","year":2022,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Networking","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada); University of Calgary; Ontario Tech University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centre of Innovation","keywords":"Regret; Computer science; Mathematical optimization; Convex function; Term (time); Convex optimization; Benchmark (surveying); Online algorithm; Algorithm; Regular polygon; Mathematics","score_opus":0.05761274990379705,"score_gpt":0.35392292111505874,"score_spread":0.2963101712112617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285505943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0137305595,0.00046890308,0.9814966,0.0005589996,0.00007657764,0.0001410005,0.000056585726,0.00032663703,0.0031441015],"genre_scores_gemma":[0.67164296,0.0006335032,0.32221538,0.0005629187,0.00014706141,0.00049550907,0.0002063877,0.00019448182,0.0039016851],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931,0.00017209053,0.000032671265,0.00016000206,0.00019304792,0.00013212142],"domain_scores_gemma":[0.99838567,0.0008679237,0.00020781724,0.0001431816,0.00023414148,0.00016134843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014518463,0.001424108,0.0013999515,0.0004681212,0.0005302815,0.0010623478,0.0016399357,0.0016251373,0.0019583139],"category_scores_gemma":[0.0047870846,0.0004507257,0.0004937483,0.0010301243,0.001096799,0.0011719866,0.0018216434,0.00201928,0.00028397646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099062825,0.00007023842,0.0005224776,0.00007921278,0.000021624839,0.00008805957,0.000047148427,0.9544131,0.0010557101,0.011539364,0.0017328304,0.03033115],"study_design_scores_gemma":[0.000008414687,0.000013941953,0.000026236796,0.0000035392998,0.000002341381,0.000013085492,0.000004613226,0.9975719,0.00018655977,0.0019158857,0.00025047208,0.000003023097],"about_ca_topic_score_codex":0.0062165447,"about_ca_topic_score_gemma":0.0046337564,"teacher_disagreement_score":0.0062165447,"about_ca_system_score_codex":0.0011823424,"about_ca_system_score_gemma":0.0023168856,"threshold_uncertainty_score":0.012360752},"labels":[],"label_agreement":null},{"id":"W4286375149","doi":"10.3982/ecta17664","title":"A Comment on “Using Randomization to Break the Curse of Dimensionality”","year":2022,"lang":"en","type":"article","venue":"Econometrica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Mathematics; Curse of dimensionality; Fraction (chemistry); Class (philosophy); Sample (material); Combinatorics; Statistics; Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.20650560890102532,"score_gpt":0.4499069444671524,"score_spread":0.24340133556612709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286375149","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003694321,0.0016598916,0.0029492863,0.9813384,0.009616702,0.000017246402,0.0002754862,0.00015616506,0.0036174082],"genre_scores_gemma":[0.007079053,0.00083860883,0.0023719412,0.96907604,0.017719226,0.000104616534,0.000048999733,0.00010429358,0.0026572272],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9743459,0.0086011095,0.0021929743,0.0048659504,0.008198204,0.0017959406],"domain_scores_gemma":[0.91569394,0.06374187,0.0043785097,0.0051652347,0.00960363,0.0014169038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027527291,0.0019756828,0.0025268977,0.00138259,0.0050379443,0.0056142146,0.009075899,0.040361736,0.014030119],"category_scores_gemma":[0.13130982,0.0013045396,0.0038313733,0.002274485,0.018947752,0.016322816,0.0051748725,0.05410413,0.010663507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077538374,0.000023899709,0.00032575877,0.00013668407,0.000048977698,0.00012741475,0.00035517025,0.00044062725,0.00020485822,0.108014025,0.8852316,0.0050134445],"study_design_scores_gemma":[0.000294004,0.00008748662,0.0015374204,0.0005642334,0.000071250084,0.00033987235,0.0003704399,0.002463965,0.001543752,0.25368845,0.73878545,0.00025373197],"about_ca_topic_score_codex":0.013689575,"about_ca_topic_score_gemma":0.010203134,"teacher_disagreement_score":0.040361736,"about_ca_system_score_codex":0.0047873114,"about_ca_system_score_gemma":0.0049164137,"threshold_uncertainty_score":0.14557993},"labels":[],"label_agreement":null},{"id":"W4286713636","doi":"10.48550/arxiv.2108.00892","title":"Indexability and Rollout Policy for Multi-State Partially Observable\\n Restless Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Observable; Monte Carlo method; State (computer science); Index (typography); Mathematical optimization; Computation; Computer science; Mathematical economics; Mathematics; Algorithm; Physics; Statistics","score_opus":0.49956896987802035,"score_gpt":0.37506037072957504,"score_spread":0.12450859914844531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286713636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26627174,0.00049048587,0.7229492,0.0010474676,0.00007396714,0.00020800698,0.00035425555,0.0007650424,0.007839822],"genre_scores_gemma":[0.97892773,0.00013072914,0.017681118,0.000102499085,0.00002420999,0.000094048315,0.00013955317,0.000052387968,0.0028477893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978447,0.0007373973,0.000135859,0.00043761774,0.00029983604,0.0005445472],"domain_scores_gemma":[0.98751324,0.008345574,0.0018778348,0.0009199711,0.00061818236,0.0007251421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038091252,0.0012552823,0.0017098848,0.0008013422,0.0010116121,0.0024492643,0.0017656116,0.0018853176,0.0037258766],"category_scores_gemma":[0.018574478,0.0006379839,0.0008804695,0.0006341276,0.002410418,0.0030775985,0.0016373354,0.0025941879,0.00042275002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005639898,0.00015569325,0.0020879917,0.000084522624,0.00005338406,0.00021911481,0.00020006896,0.90494853,0.002164583,0.073763594,0.0010277283,0.014730785],"study_design_scores_gemma":[0.00001838975,0.00004373561,0.00017394841,0.000007779718,0.000007949669,0.000012856113,0.000016149817,0.98806316,0.00046440112,0.011056567,0.0001261695,0.000008970401],"about_ca_topic_score_codex":0.0068101855,"about_ca_topic_score_gemma":0.0038950152,"teacher_disagreement_score":0.0068101855,"about_ca_system_score_codex":0.0025057408,"about_ca_system_score_gemma":0.0018044963,"threshold_uncertainty_score":0.02014482},"labels":[],"label_agreement":null},{"id":"W4289655140","doi":"10.1109/isit50566.2022.9834636","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Information Theory (ISIT)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Task (project management); Computer science; Artificial intelligence; Meta learning (computer science); Machine learning; Multi-task learning; Task analysis; Mathematical optimization; Mathematics; Engineering","score_opus":0.0688220592948622,"score_gpt":0.36678422878665645,"score_spread":0.29796216949179427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289655140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02498942,0.00084012205,0.97126454,0.000731147,0.000053384425,0.000052002113,0.00006580482,0.00024818478,0.0017554113],"genre_scores_gemma":[0.8671146,0.0005893109,0.12642556,0.00057146,0.00020954604,0.00038573443,0.00017621095,0.00015165379,0.00437603],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967464,0.0019038771,0.00012372712,0.00055043795,0.0003237636,0.00035175573],"domain_scores_gemma":[0.9880711,0.009467433,0.000951916,0.0006011109,0.00053182367,0.00037659777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00618944,0.0020074006,0.0035312339,0.00088577194,0.000911599,0.0026997225,0.0029262893,0.0036333017,0.0020421476],"category_scores_gemma":[0.01817562,0.0013248387,0.0012381166,0.001198428,0.0028849866,0.004279771,0.002876553,0.004069193,0.0005471887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010547898,0.00005628862,0.00052123074,0.0000613752,0.00007725668,0.000056685647,0.000056328037,0.95606023,0.00023602018,0.03303545,0.00046389428,0.009269807],"study_design_scores_gemma":[0.000011604836,0.000022897078,0.000037214642,0.000010721506,0.0000076052534,0.0000091462925,0.000007056742,0.97983325,0.00009918142,0.019832956,0.00012228084,0.0000061758496],"about_ca_topic_score_codex":0.0025069737,"about_ca_topic_score_gemma":0.0023031544,"teacher_disagreement_score":0.00618944,"about_ca_system_score_codex":0.002223955,"about_ca_system_score_gemma":0.0013742672,"threshold_uncertainty_score":0.03273326},"labels":[],"label_agreement":null},{"id":"W4292330968","doi":"10.48550/arxiv.2202.12843","title":"Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Smoothness; Convexity; Mathematical optimization; Lipschitz continuity; Convex optimization; Convex function; Regularization (linguistics); Upper and lower bounds; Computer science; Function (biology); Bounded function; Mathematics; Regular polygon; Economics; Artificial intelligence; Mathematical analysis","score_opus":0.3304196183855856,"score_gpt":0.35242914424509725,"score_spread":0.02200952585951166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292330968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13219981,0.0005722723,0.8595321,0.0009872192,0.00006145822,0.00008682384,0.00011007177,0.00041962916,0.006030616],"genre_scores_gemma":[0.93359864,0.00024926677,0.06273534,0.00018134301,0.000041299423,0.00009203286,0.00012531911,0.0001023954,0.0028743558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811447,0.00090181694,0.000060388767,0.00030623405,0.00038166184,0.00023531428],"domain_scores_gemma":[0.99334574,0.0049320566,0.00057227997,0.00051333377,0.0003795371,0.00025699506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00501918,0.001068063,0.0013487526,0.0004970751,0.0007128807,0.0016741762,0.001436668,0.0016240838,0.0016953658],"category_scores_gemma":[0.01815397,0.00052107277,0.00068060233,0.0005654214,0.0019901,0.0020931698,0.0017983263,0.002265667,0.0002936742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030626162,0.000075976735,0.0010065292,0.000052805066,0.000032857937,0.0001115551,0.000042187563,0.93985426,0.0013727356,0.042744655,0.0009064886,0.013493793],"study_design_scores_gemma":[0.000011936477,0.000034003046,0.00014781962,0.000004408148,0.0000037796842,0.000012297131,0.000004276062,0.99046165,0.00032598485,0.008894346,0.00009533935,0.0000041237004],"about_ca_topic_score_codex":0.004305537,"about_ca_topic_score_gemma":0.0033393262,"teacher_disagreement_score":0.00501918,"about_ca_system_score_codex":0.0022841892,"about_ca_system_score_gemma":0.00217745,"threshold_uncertainty_score":0.026544213},"labels":[],"label_agreement":null},{"id":"W4294691466","doi":"10.23919/acc53348.2022.9867309","title":"Dynamic Regret Bounds without Lipschitz Continuity: Online Convex Optimization with Multiple Mirror Descent Steps","year":2022,"lang":"en","type":"article","venue":"2022 American Control Conference (ACC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Lipschitz continuity; Path (computing); Mathematical optimization; Convex optimization; Upper and lower bounds; Gradient descent; Mathematics; Path length; Sequence (biology); Regular polygon; Computer science; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.0478450906761866,"score_gpt":0.3652658143209036,"score_spread":0.317420723644717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294691466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034544177,0.0018031399,0.9553159,0.0012237584,0.00012810777,0.00010753366,0.00016954147,0.000444674,0.0062631452],"genre_scores_gemma":[0.84901255,0.0013970236,0.14169972,0.0007805467,0.00026309895,0.0003090007,0.00031347814,0.00033954473,0.005885089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99700767,0.001101477,0.00011880588,0.00056359835,0.0007901286,0.00041827964],"domain_scores_gemma":[0.9815677,0.013409056,0.0014837809,0.0019341153,0.0010199248,0.00058542663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052555623,0.0022441137,0.0021577082,0.00069048814,0.00089190615,0.002186632,0.0027860063,0.0018509993,0.0033306743],"category_scores_gemma":[0.029484503,0.0009287113,0.0012097245,0.000969309,0.0023770707,0.0045676464,0.003005063,0.0039787614,0.0005402613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034372168,0.00018141564,0.0017389075,0.00016744478,0.00009575737,0.00020101805,0.00008585379,0.90785605,0.0022458402,0.051236637,0.0029436604,0.03290371],"study_design_scores_gemma":[0.000011231634,0.000046052373,0.00014659092,0.000011659742,0.000008160379,0.000025370158,0.000006621667,0.989037,0.00045671186,0.009977641,0.00026582615,0.0000071518743],"about_ca_topic_score_codex":0.0035668588,"about_ca_topic_score_gemma":0.0028350304,"teacher_disagreement_score":0.0052555623,"about_ca_system_score_codex":0.0024211418,"about_ca_system_score_gemma":0.0024746268,"threshold_uncertainty_score":0.02779442},"labels":[],"label_agreement":null},{"id":"W4298085585","doi":"10.48550/arxiv.1001.4475","title":"X-Armed Bandits","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Alberta Innovates; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Computer science","score_opus":0.2954986038164982,"score_gpt":0.318239257490027,"score_spread":0.022740653673528843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298085585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0640901,0.00097572623,0.91720825,0.0008246564,0.00011809249,0.000100955454,0.00026512367,0.00032370863,0.016093358],"genre_scores_gemma":[0.8557586,0.0008101853,0.123683184,0.0005495865,0.00022832851,0.00029452727,0.00031864736,0.0000971121,0.01825981],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881005,0.00051481323,0.00005092429,0.0002835798,0.00015714833,0.00018341513],"domain_scores_gemma":[0.9983278,0.0009504271,0.00026174638,0.00025479626,0.00008102069,0.00012425963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014348398,0.0011277599,0.0014832881,0.00042934227,0.0007828828,0.0017149829,0.0015415208,0.0017808651,0.005567541],"category_scores_gemma":[0.004003629,0.0004412008,0.0008722441,0.00084919104,0.0014052425,0.0021873345,0.0021531782,0.0021200941,0.0010327185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003558513,0.0001502562,0.0009612796,0.00013019546,0.00010706259,0.00018499407,0.000088021516,0.74690866,0.0017955977,0.2166363,0.0028658798,0.029815886],"study_design_scores_gemma":[0.000033786215,0.00007631156,0.00011591478,0.00001282851,0.0000133574,0.000035197805,0.000012431814,0.93660617,0.000401244,0.061041936,0.0016423438,0.000008487581],"about_ca_topic_score_codex":0.0018240181,"about_ca_topic_score_gemma":0.0016534682,"teacher_disagreement_score":0.005567541,"about_ca_system_score_codex":0.0010818832,"about_ca_system_score_gemma":0.0007476381,"threshold_uncertainty_score":0.018625319},"labels":[],"label_agreement":null},{"id":"W4300920027","doi":"10.1609/aaai.v29i1.9445","title":"Solving Games with Functional Regret Estimation","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures; Office of Naval Research; Multidisciplinary University Research Initiative; Compute Canada","keywords":"Regret; Generalization; Abstraction; Computer science; Corollary; Function (biology); Nash equilibrium; Mathematical optimization; Sequence (biology); Quality (philosophy); Artificial intelligence; Mathematical economics; Machine learning; Mathematics; Discrete mathematics","score_opus":0.28698360957141944,"score_gpt":0.4462518374060486,"score_spread":0.15926822783462918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300920027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067878296,0.0000905463,0.9915031,0.00020119404,0.000015723052,0.000037564503,0.000014307648,0.00018333923,0.0011663979],"genre_scores_gemma":[0.6018902,0.00031280235,0.39178842,0.00033732416,0.00012379214,0.00043424993,0.00015259793,0.00020704213,0.0047536297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799407,0.0010633253,0.00007753639,0.0002843101,0.00040317234,0.0001775269],"domain_scores_gemma":[0.9958526,0.002892484,0.00034896433,0.00044646332,0.00026577016,0.00019370939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00378629,0.0017471603,0.0015749398,0.0006959785,0.00055468234,0.0015970574,0.002154733,0.0018603986,0.0024821174],"category_scores_gemma":[0.012284148,0.0008107631,0.0011909548,0.0005110019,0.0017113962,0.00321982,0.0029736143,0.0030009372,0.00046466262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011030025,0.00010645709,0.0005669198,0.00010780724,0.00005900598,0.000052004954,0.00012260195,0.89165837,0.0009526553,0.07031531,0.001116746,0.03483182],"study_design_scores_gemma":[0.000012152452,0.000024396599,0.00004363481,0.0000078834,0.000004526797,0.000008764944,0.000004922952,0.97705895,0.0002410284,0.022338178,0.00025136094,0.00000416227],"about_ca_topic_score_codex":0.0025353548,"about_ca_topic_score_gemma":0.002330383,"teacher_disagreement_score":0.00378629,"about_ca_system_score_codex":0.0015843998,"about_ca_system_score_gemma":0.0018578786,"threshold_uncertainty_score":0.020024061},"labels":[],"label_agreement":null},{"id":"W4306317496","doi":"10.1145/3511808.3557436","title":"Risk-Aware Bid Optimization for Online Display Advertisement","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information &amp; Knowledge Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Mitacs","keywords":"Bidding; Real-time bidding; Profit (economics); Budget constraint; Display advertising; Computer science; Common value auction; Lagrangian relaxation; Online advertising; Operations research; Mathematical optimization; Microeconomics; The Internet; Economics; Engineering; Mathematics","score_opus":0.1311048228999324,"score_gpt":0.41385315945114975,"score_spread":0.28274833655121734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306317496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036670856,0.0008914362,0.95688665,0.00061776495,0.00007237472,0.00013112984,0.00022881557,0.0003496502,0.004151324],"genre_scores_gemma":[0.8163956,0.00059902895,0.17571668,0.00029651186,0.00010396981,0.00023057387,0.00045577047,0.00021630687,0.00598557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842656,0.0008083248,0.000060035265,0.00025939647,0.00027447054,0.00017125501],"domain_scores_gemma":[0.9966445,0.0024144764,0.00026467053,0.00021443445,0.0002608464,0.00020100384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038766004,0.0010985228,0.0019599502,0.00060385437,0.00046282832,0.0020638215,0.0018470206,0.0013812424,0.0034432528],"category_scores_gemma":[0.007387777,0.0009765956,0.0010429805,0.00090095005,0.00094479055,0.0026702236,0.0010980049,0.0022652089,0.00059134496],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018007493,0.00016976077,0.00085537013,0.000105944724,0.00005681812,0.000082071296,0.000107541906,0.9408894,0.0009948841,0.024837494,0.0030137212,0.028706895],"study_design_scores_gemma":[0.000010958707,0.000020373176,0.00010355741,0.0000044105063,0.0000054841557,0.000012204121,0.0000108760505,0.99097264,0.000118339034,0.008386879,0.0003489504,0.000005436431],"about_ca_topic_score_codex":0.00440542,"about_ca_topic_score_gemma":0.004041007,"teacher_disagreement_score":0.00440542,"about_ca_system_score_codex":0.0017643899,"about_ca_system_score_gemma":0.0019684387,"threshold_uncertainty_score":0.020501673},"labels":[],"label_agreement":null},{"id":"W4313350174","doi":"10.1016/j.orl.2022.12.006","title":"Gradient boosting for convex cone predict and optimize problems","year":2022,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Toronto","funders":"","keywords":"Regret; Gradient boosting; Convex optimization; Mathematical optimization; Boosting (machine learning); Regular polygon; Computer science; Quadratic programming; Quadratic equation; Artificial intelligence; Mathematics; Machine learning; Random forest","score_opus":0.26017722015919637,"score_gpt":0.4724558772527916,"score_spread":0.21227865709359522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313350174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005843328,0.0011335855,0.98999715,0.00057887245,0.00011279476,0.000053543103,0.00005856047,0.00024938677,0.0019728984],"genre_scores_gemma":[0.3821076,0.0026787664,0.59603304,0.0009567398,0.00083989685,0.00054766616,0.0008591215,0.0006354229,0.015341722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817824,0.0008673876,0.00007182534,0.00017974814,0.00050959707,0.00019307551],"domain_scores_gemma":[0.99451435,0.003608443,0.00027184834,0.00041520962,0.00089730974,0.0002927936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057403506,0.0017020312,0.0034662276,0.0012924697,0.00087189936,0.0021316034,0.0024067631,0.0024167716,0.0034578785],"category_scores_gemma":[0.0145587595,0.001445254,0.0011824341,0.0016050341,0.0017685025,0.0022900573,0.002299222,0.004170518,0.0011349892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026459325,0.00028557668,0.0010191167,0.00037753183,0.00013317318,0.00010061012,0.00007322412,0.71963334,0.0016674317,0.12439247,0.01455434,0.13749869],"study_design_scores_gemma":[0.000008966909,0.000014512609,0.000052979824,0.000011683863,0.000005936971,0.000008657548,0.0000029905023,0.97903216,0.00014704133,0.020239463,0.00047197982,0.0000036543422],"about_ca_topic_score_codex":0.004416898,"about_ca_topic_score_gemma":0.0040708045,"teacher_disagreement_score":0.0057403506,"about_ca_system_score_codex":0.0014190868,"about_ca_system_score_gemma":0.0021202818,"threshold_uncertainty_score":0.030358195},"labels":[],"label_agreement":null},{"id":"W4314946896","doi":"10.1109/cdc51059.2022.9992683","title":"A modified Thompson sampling-based learning algorithm for unknown linear systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Upper and lower bounds; Norm (philosophy); Algorithm; Thompson sampling; Combinatorics; Quadratic equation; Sampling (signal processing); Discrete mathematics; Mathematics; Computer science; Statistics; Mathematical analysis; Philosophy","score_opus":0.1707192101122855,"score_gpt":0.4198898418535795,"score_spread":0.24917063174129403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314946896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047630654,0.00015413291,0.9931253,0.00015262935,0.00004750112,0.0000661988,0.000036357524,0.00038752926,0.0012672403],"genre_scores_gemma":[0.36053544,0.00025239697,0.6312827,0.00053436926,0.00021593888,0.0005156254,0.00040351003,0.00031109792,0.0059489645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887496,0.00035919235,0.000056032542,0.00024729344,0.00035095098,0.00011152726],"domain_scores_gemma":[0.99801624,0.0011906317,0.00014073073,0.00017985905,0.00036747204,0.00010499523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015801919,0.0011247966,0.0018279133,0.00056421047,0.0005442304,0.0010807532,0.0025723334,0.0019843369,0.0043471637],"category_scores_gemma":[0.006030429,0.00059391384,0.00071445754,0.00084019575,0.00093432807,0.0014921295,0.0013977056,0.0020825812,0.0009436007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001650563,0.00008818825,0.00051921554,0.00008466419,0.00006115208,0.0000636228,0.00006723997,0.84928,0.0015826023,0.0144047905,0.0027383994,0.130945],"study_design_scores_gemma":[0.000017608689,0.000023371324,0.000034205106,0.0000026443493,0.0000027075616,0.000007863228,0.0000014689008,0.99713624,0.00018808969,0.0022565413,0.00032563639,0.0000036738686],"about_ca_topic_score_codex":0.00896596,"about_ca_topic_score_gemma":0.008163284,"teacher_disagreement_score":0.00896596,"about_ca_system_score_codex":0.0012009152,"about_ca_system_score_gemma":0.0017207037,"threshold_uncertainty_score":0.01782757},"labels":[],"label_agreement":null},{"id":"W4314947473","doi":"10.1109/cdc51059.2022.9992636","title":"Achieving Logarithmic Regret via Hints in Online Learning of Noisy LQR Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Logarithm; Sublinear function; Matrix (chemical analysis); Computer science; Mathematical optimization; Limit (mathematics); Square root; Mathematics; Algorithm; Discrete mathematics; Machine learning","score_opus":0.08411755925804429,"score_gpt":0.38517055816339696,"score_spread":0.30105299890535264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314947473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053283658,0.0006793823,0.94128495,0.00093285006,0.00005204801,0.00005406246,0.000094920666,0.0010559241,0.0025622644],"genre_scores_gemma":[0.946075,0.00029928706,0.051190015,0.00034891666,0.00008210443,0.00011807498,0.00012499567,0.00013038474,0.0016313008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973023,0.0013879505,0.000119243785,0.0003852031,0.00049913774,0.00030621988],"domain_scores_gemma":[0.97531056,0.021148471,0.0013337132,0.0009616072,0.0008435438,0.0004021784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005638317,0.0019174652,0.0020971468,0.0006346627,0.0005726634,0.0018228577,0.0016971907,0.002185258,0.001566847],"category_scores_gemma":[0.033117503,0.00092165713,0.00058108335,0.0006285165,0.0029128003,0.0032338414,0.0022487435,0.0031107808,0.00046313964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002994059,0.000053397343,0.0004931063,0.000091927184,0.000025637288,0.00007199267,0.000060366136,0.97893333,0.0004982033,0.011027665,0.0004122003,0.0080327885],"study_design_scores_gemma":[0.000018913483,0.000041438532,0.00006750506,0.0000076086517,0.0000041336048,0.000009226447,0.0000054494526,0.9893283,0.00032205015,0.010121966,0.00006719739,0.000006139455],"about_ca_topic_score_codex":0.003167576,"about_ca_topic_score_gemma":0.0021462515,"teacher_disagreement_score":0.005638317,"about_ca_system_score_codex":0.0016050319,"about_ca_system_score_gemma":0.0013065838,"threshold_uncertainty_score":0.029818594},"labels":[],"label_agreement":null},{"id":"W4315489038","doi":"10.1109/cdc51059.2022.9992898","title":"Partially observable restless bandits with restarts: indexability and computation of Whittle index","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reset (finance); Observable; Computation; Computer science; Index (typography); State (computer science); Markov process; Mathematical optimization; Markov decision process; Mathematics; Algorithm; Statistics; Economics","score_opus":0.11834800633433555,"score_gpt":0.386241167763421,"score_spread":0.2678931614290854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070126474,0.000255524,0.9255811,0.0002733103,0.000031397383,0.00007472166,0.0001266046,0.00052983034,0.0030011467],"genre_scores_gemma":[0.9424193,0.00012919407,0.05487017,0.00009191879,0.000024763542,0.00013086988,0.00014829414,0.00010002403,0.0020855719],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985863,0.0005041899,0.00008691966,0.00027485183,0.00025766095,0.00029017325],"domain_scores_gemma":[0.9889531,0.008016699,0.0012449715,0.0009269666,0.00048593714,0.0003723385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034008843,0.0011910876,0.0017775606,0.0008051586,0.00058767066,0.0023403305,0.0018820489,0.0015205693,0.004040103],"category_scores_gemma":[0.020241627,0.00058982713,0.0006904036,0.00075679296,0.0026399135,0.0037883713,0.0018705924,0.0021641406,0.00035383573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023306557,0.000042284646,0.0006442547,0.000050809565,0.000025720685,0.00008970392,0.00006189432,0.91701514,0.0008090437,0.071622185,0.0003238089,0.009082081],"study_design_scores_gemma":[0.000008021342,0.000016335207,0.000051668994,0.0000065778145,0.0000031963161,0.000007539868,0.0000057021057,0.976775,0.00028106695,0.022781575,0.000058606627,0.0000046989303],"about_ca_topic_score_codex":0.0037572444,"about_ca_topic_score_gemma":0.0023891167,"teacher_disagreement_score":0.004040103,"about_ca_system_score_codex":0.0021140007,"about_ca_system_score_gemma":0.0017082285,"threshold_uncertainty_score":0.017985761},"labels":[],"label_agreement":null},{"id":"W4315489128","doi":"10.1109/cdc51059.2022.9992906","title":"Bandit learning with regularized second-order mirror descent","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Huawei Technologies","keywords":"Descent (aeronautics); Computer science; Order (exchange); Gradient descent; Artificial intelligence; Mathematical optimization; Applied mathematics; Mathematics; Physics; Artificial neural network","score_opus":0.07159991721118657,"score_gpt":0.3584330874760927,"score_spread":0.2868331702649061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011932194,0.00018242185,0.9849636,0.00022840188,0.000037997193,0.000052931875,0.000024801077,0.00018280846,0.0023947933],"genre_scores_gemma":[0.70562696,0.00035280266,0.28359464,0.00046486862,0.00010569535,0.00040948152,0.00016435834,0.00014926186,0.009131878],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892265,0.00049618725,0.000051982996,0.00016073884,0.00024036395,0.00012801489],"domain_scores_gemma":[0.99740356,0.0016213945,0.0002679108,0.0002791786,0.00030622087,0.00012174981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021963886,0.0011131798,0.0016908507,0.0005849386,0.0006484969,0.0016790343,0.0015746398,0.0020709755,0.0022642035],"category_scores_gemma":[0.0077539743,0.0006349812,0.0006551198,0.0006573282,0.0016774797,0.0017591604,0.0015390364,0.0019034521,0.0007084976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014717573,0.00012569736,0.0007434773,0.000106644395,0.000077616605,0.0001019334,0.000108293745,0.83926946,0.0015577838,0.113629125,0.0017601338,0.04237275],"study_design_scores_gemma":[0.000006815481,0.000017461463,0.000026484518,0.0000044239096,0.000002122016,0.0000082772085,0.00000322303,0.9895633,0.00019220299,0.009995864,0.00017656808,0.0000032763778],"about_ca_topic_score_codex":0.0039164303,"about_ca_topic_score_gemma":0.004225448,"teacher_disagreement_score":0.0039164303,"about_ca_system_score_codex":0.0012041086,"about_ca_system_score_gemma":0.0018719576,"threshold_uncertainty_score":0.011615753},"labels":[],"label_agreement":null},{"id":"W4317036118","doi":"10.1145/3580491","title":"SEH: Size Estimate Hedging Scheduling of Queues","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scheduling (production processes); Computer science; Queue; Variance (accounting); Mathematical optimization; Mathematics; Computer network; Accounting; Economics","score_opus":0.16515148452082612,"score_gpt":0.44962101077759437,"score_spread":0.28446952625676825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317036118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098209746,0.0004689533,0.8967165,0.00036178666,0.00016067467,0.00014795213,0.00012730961,0.0015387868,0.0022682846],"genre_scores_gemma":[0.8925477,0.000117492906,0.105446294,0.00016430416,0.00007646948,0.00006090954,0.00010669648,0.00007558154,0.0014044972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982521,0.00064232067,0.000116690106,0.00027460686,0.0004563749,0.00025780327],"domain_scores_gemma":[0.9943561,0.0029942119,0.00065271463,0.0009903362,0.0006940714,0.00031258242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00355805,0.0006579687,0.0009922076,0.00065959484,0.0005103134,0.0009481464,0.0018197214,0.0006618696,0.0018594151],"category_scores_gemma":[0.011570009,0.00045551278,0.00041261065,0.000623648,0.0008921276,0.0017399697,0.0013106957,0.0012605848,0.00031915976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075553707,0.0001753007,0.003108561,0.0000908394,0.000074128795,0.00010486366,0.00016726032,0.8343306,0.0076705967,0.024034768,0.002913901,0.12657367],"study_design_scores_gemma":[0.000031648968,0.00013892491,0.00033909717,0.000005371401,0.0000090242565,0.000023809922,0.000015140168,0.9882824,0.0023436227,0.008349828,0.00044748426,0.000013731693],"about_ca_topic_score_codex":0.002368507,"about_ca_topic_score_gemma":0.0019397229,"teacher_disagreement_score":0.00355805,"about_ca_system_score_codex":0.0010681556,"about_ca_system_score_gemma":0.0016166999,"threshold_uncertainty_score":0.018817008},"labels":[],"label_agreement":null},{"id":"W4318350404","doi":"10.48550/arxiv.2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind","keywords":"Laplacian matrix; Computer science; Reinforcement learning; Eigenfunction; Scalability; Variety (cybernetics); Laplace operator; Artificial intelligence; Graph; Machine learning; Mathematical optimization; Theoretical computer science; Eigenvalues and eigenvectors; Mathematics","score_opus":0.459823302277091,"score_gpt":0.35417161248423545,"score_spread":0.10565168979285555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318350404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038166117,0.00039973704,0.9577094,0.00047703704,0.0000321047,0.0000520905,0.00015239847,0.00071781006,0.0022933937],"genre_scores_gemma":[0.8032027,0.00030657696,0.19112982,0.00027902398,0.000049747996,0.00020755392,0.0003584289,0.00018569721,0.0042804815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995448,0.00014623745,0.000025625519,0.00010836934,0.00010518152,0.00006972704],"domain_scores_gemma":[0.99773824,0.0015412626,0.00018016805,0.00019897721,0.0001735578,0.00016784093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011290299,0.00079758145,0.0010275387,0.0008943046,0.00049646356,0.001201227,0.0017794719,0.001475955,0.0037714073],"category_scores_gemma":[0.006457096,0.00061728124,0.0008178054,0.0006690297,0.0012917282,0.002759935,0.0023626024,0.0020744326,0.00055668206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022905454,0.000113552764,0.0020693867,0.000112026224,0.000058951642,0.00014079003,0.00018983783,0.83338696,0.0030366797,0.05105341,0.0030054732,0.10660396],"study_design_scores_gemma":[0.000008771837,0.000015627813,0.00007151453,0.000008586183,0.0000032326525,0.000014510917,0.000009256022,0.9751081,0.0003063239,0.024179399,0.00026913706,0.0000055076443],"about_ca_topic_score_codex":0.002469601,"about_ca_topic_score_gemma":0.003904391,"teacher_disagreement_score":0.0037714073,"about_ca_system_score_codex":0.0010101637,"about_ca_system_score_gemma":0.0010358149,"threshold_uncertainty_score":0.012616575},"labels":[],"label_agreement":null},{"id":"W4318903797","doi":"10.48550/arxiv.2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Education, India; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Mathematical economics; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.30295243332312344,"score_gpt":0.3149585968044796,"score_spread":0.012006163481356136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318903797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04613724,0.00049180794,0.94468665,0.001342562,0.00008939473,0.0002004503,0.0005080549,0.0005623781,0.005981374],"genre_scores_gemma":[0.83459866,0.00056927727,0.15569909,0.0006639759,0.00017042541,0.00055507984,0.0007790576,0.00020552798,0.006758988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973888,0.0012432392,0.0001344308,0.00046730752,0.0003890977,0.00037701873],"domain_scores_gemma":[0.9906205,0.006790203,0.00081753236,0.0008950486,0.00047269676,0.00040400293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004064399,0.0016627382,0.0030241797,0.0006004737,0.0009277238,0.0023508642,0.00265629,0.0022625227,0.0047993492],"category_scores_gemma":[0.011692139,0.00090665603,0.0010734065,0.0012138347,0.002077394,0.0033144099,0.0018021102,0.003009253,0.0010025745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005627327,0.00015081144,0.0009656843,0.00019822599,0.0000881908,0.00013409366,0.00009470664,0.891064,0.0012719075,0.0749337,0.0035552657,0.026980763],"study_design_scores_gemma":[0.000046491885,0.000055233177,0.00011200383,0.000016213888,0.000012215272,0.000034506767,0.000018055862,0.9551124,0.00038147983,0.04369471,0.0005068083,0.000009883318],"about_ca_topic_score_codex":0.0031676874,"about_ca_topic_score_gemma":0.0034089894,"teacher_disagreement_score":0.0047993492,"about_ca_system_score_codex":0.001705293,"about_ca_system_score_gemma":0.0022651097,"threshold_uncertainty_score":0.021494865},"labels":[],"label_agreement":null},{"id":"W4321484040","doi":"10.1109/lcsys.2023.3247359","title":"An Online Newton’s Method for Time-Varying Linear Equality Constraints","year":2023,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Science and Engineering Research Council; Institut de Valorisation des Données","keywords":"Sublinear function; Regret; Hessian matrix; Convexity; Mathematical optimization; Smoothness; Constraint (computer-aided design); Function (biology); Online algorithm; Computer science; Mathematics; Applied mathematics; Discrete mathematics","score_opus":0.1808500052879728,"score_gpt":0.46985864577287056,"score_spread":0.28900864048489777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321484040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025393623,0.00016183709,0.9949656,0.00017244746,0.00004459302,0.000037061363,0.000026890504,0.00015002469,0.001902083],"genre_scores_gemma":[0.24467783,0.00041256784,0.7456489,0.00034843475,0.00015540358,0.00034702304,0.00016393991,0.0002682704,0.007977634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99959284,0.00016526296,0.000012207891,0.00006507836,0.00012137756,0.000043200645],"domain_scores_gemma":[0.9987571,0.0008474679,0.00011595245,0.00007640855,0.00013061737,0.00007241062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009315317,0.0010780893,0.0011239771,0.00038838177,0.00045577684,0.00078078476,0.0012166783,0.0014621539,0.004702227],"category_scores_gemma":[0.0034219318,0.0005950839,0.00056671846,0.00053503417,0.0010021772,0.001322574,0.0013045426,0.0022568817,0.0005746506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000797847,0.000048729198,0.0002442157,0.00009048486,0.000028714196,0.0000906468,0.000056175933,0.92123574,0.0014250391,0.029535092,0.002431378,0.044734057],"study_design_scores_gemma":[0.0000059858976,0.000008544502,0.000015595213,0.0000035524101,0.0000012541334,0.0000069306107,0.000001798642,0.9967398,0.00014031517,0.0025968794,0.00047701012,0.000002283403],"about_ca_topic_score_codex":0.006820375,"about_ca_topic_score_gemma":0.0064560594,"teacher_disagreement_score":0.006820375,"about_ca_system_score_codex":0.00080747897,"about_ca_system_score_gemma":0.002018254,"threshold_uncertainty_score":0.01573056},"labels":[],"label_agreement":null},{"id":"W4365800375","doi":"10.1109/icc56513.2022.10093670","title":"Restless Bandits for Sensor Scheduling in Energy Constrained Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Polytechnique Montréal","funders":"","keywords":"Markov decision process; Computer science; Scheduling (production processes); Partially observable Markov decision process; Mathematical optimization; Wireless sensor network; Channel (broadcasting); Observable; Job shop scheduling; Dynamic programming; Markov process; Energy consumption; Markov chain; Real-time computing; Markov model; Computer network; Algorithm; Mathematics; Engineering","score_opus":0.13562584791877827,"score_gpt":0.42956079650066964,"score_spread":0.2939349485818914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365800375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066654555,0.0011282115,0.9263284,0.00059548207,0.00010109254,0.00007633034,0.000120976016,0.0002781497,0.004716706],"genre_scores_gemma":[0.9510588,0.00069371593,0.04442084,0.00015130654,0.00006246064,0.00012012663,0.00008636625,0.00005073459,0.0033556502],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895275,0.0005262516,0.000048641716,0.00014703172,0.00014699709,0.00017846149],"domain_scores_gemma":[0.99709857,0.0020944374,0.00036719348,0.00012993667,0.0001790696,0.0001308413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017571051,0.0010054393,0.0011138439,0.00048638703,0.00066540035,0.001309287,0.0008179429,0.0009251843,0.0024806631],"category_scores_gemma":[0.005318886,0.000329752,0.0004898506,0.00085377437,0.0011326629,0.0015870951,0.00083157694,0.0013768733,0.00027053308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019819524,0.000050536528,0.0003768675,0.00006367711,0.000022031189,0.00006845565,0.000053335487,0.9599987,0.00078280765,0.028893355,0.00062397297,0.008868089],"study_design_scores_gemma":[0.000011591887,0.000034063465,0.000052661162,0.0000057806496,0.0000055346936,0.000009761245,0.000009805049,0.9883862,0.0002135871,0.011051362,0.00021570285,0.0000039302513],"about_ca_topic_score_codex":0.0046483716,"about_ca_topic_score_gemma":0.0030471163,"teacher_disagreement_score":0.0046483716,"about_ca_system_score_codex":0.0013860739,"about_ca_system_score_gemma":0.0010530655,"threshold_uncertainty_score":0.010056734},"labels":[],"label_agreement":null},{"id":"W4377078544","doi":"10.2139/ssrn.4448249","title":"Adaptive Neyman Allocation","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Computer science; Mathematics; Econometrics; Statistics","score_opus":0.09883633605555571,"score_gpt":0.4255126959982633,"score_spread":0.3266763599427076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377078544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00810071,0.00033088692,0.96563506,0.00027443157,0.00022695745,0.000054532517,0.000036736084,0.0003012274,0.025039488],"genre_scores_gemma":[0.5436231,0.0006587569,0.3914046,0.0007313817,0.00048844714,0.00022072444,0.00015892302,0.00018214066,0.062531956],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902666,0.00036711863,0.000037993916,0.00018677839,0.0002666256,0.000114860755],"domain_scores_gemma":[0.9990339,0.00036221425,0.000068509195,0.00026472073,0.00020700459,0.00006374807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010940982,0.00058290473,0.0007052758,0.0005547825,0.0006731905,0.0015410035,0.00082207256,0.0010337107,0.013188609],"category_scores_gemma":[0.0038379177,0.000266312,0.00035920853,0.0009941283,0.00076670473,0.0011320797,0.0014771431,0.00090610626,0.0039208154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007649986,0.00022575886,0.0008578071,0.0001517843,0.000103437545,0.00016460796,0.00010624271,0.14022124,0.026385708,0.2920535,0.011495254,0.5274697],"study_design_scores_gemma":[0.00008539966,0.00017328275,0.0007627794,0.00003475432,0.000058612157,0.00049366883,0.00004750397,0.8324259,0.0122146765,0.13435584,0.019296156,0.000051407904],"about_ca_topic_score_codex":0.00034114523,"about_ca_topic_score_gemma":0.0005854177,"teacher_disagreement_score":0.013188609,"about_ca_system_score_codex":0.00055317837,"about_ca_system_score_gemma":0.00093118293,"threshold_uncertainty_score":0.044120252},"labels":[],"label_agreement":null},{"id":"W4378498571","doi":"10.48550/arxiv.2305.15383","title":"On the Minimax Regret for Online Learning with Feedback Graphs","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Combinatorics; Upper and lower bounds; Omega; Mathematics; Logarithm; Regret; Minimax; Independence number; Discrete mathematics; Graph; Statistics; Mathematical economics; Physics; Mathematical analysis","score_opus":0.3688545516703471,"score_gpt":0.32528310905810887,"score_spread":0.04357144261223822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378498571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028379714,0.0044133468,0.944498,0.0031742444,0.00044463473,0.00020074387,0.0006052919,0.0016074978,0.016676426],"genre_scores_gemma":[0.75785565,0.004568791,0.209815,0.0035181146,0.0015588658,0.0008846095,0.0013694849,0.0014740357,0.018955544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99472505,0.0021696133,0.00016107205,0.0009771229,0.001282012,0.0006852463],"domain_scores_gemma":[0.96333605,0.03144484,0.0011393226,0.0021492408,0.0012040901,0.0007265132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007904378,0.0038122677,0.003527531,0.0017624603,0.0014260848,0.002478651,0.003379656,0.0028793444,0.008814124],"category_scores_gemma":[0.038194526,0.0009789715,0.0017790351,0.0019094198,0.004181948,0.009354436,0.0042031617,0.007437364,0.002001901],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066725834,0.00027304378,0.0010321471,0.00060206273,0.0001351376,0.00015923267,0.00018593653,0.767674,0.001822736,0.16400222,0.010830863,0.05261539],"study_design_scores_gemma":[0.000033799828,0.0000916981,0.00024322073,0.00005948659,0.00002117652,0.00003818829,0.000016964286,0.88705814,0.00061717036,0.110729344,0.0010711764,0.00001972559],"about_ca_topic_score_codex":0.002984554,"about_ca_topic_score_gemma":0.0030840044,"teacher_disagreement_score":0.008814124,"about_ca_system_score_codex":0.004358006,"about_ca_system_score_gemma":0.0029596288,"threshold_uncertainty_score":0.041802883},"labels":[],"label_agreement":null},{"id":"W4378499052","doi":"10.48550/arxiv.2305.15653","title":"Alternating Subgradient Methods for Convex-Concave Saddle-Point Problems","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subgradient method; Mathematics; Iterated function; Sequence (biology); Saddle point; Convex function; Mathematical optimization; Regular polygon; Convex optimization; Saddle; Bounded function; Linear matrix inequality; Rate of convergence; Applied mathematics; Mathematical analysis; Computer science; Geometry","score_opus":0.5393300625195931,"score_gpt":0.4107714676144865,"score_spread":0.12855859490510663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378499052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019736383,0.00013049974,0.99690276,0.000100471756,0.000021873244,0.000027349772,0.000010328111,0.00006042565,0.00077263993],"genre_scores_gemma":[0.1976319,0.00059020706,0.7963068,0.00025040237,0.000112067224,0.0004063928,0.00012747366,0.00021820542,0.0043565067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989203,0.00063279754,0.0000514511,0.000095567746,0.0002294535,0.00007047557],"domain_scores_gemma":[0.9983339,0.001018942,0.00014966282,0.00013425172,0.00027171525,0.00009158289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003097508,0.001626179,0.001487353,0.0007535054,0.00044904975,0.0010731678,0.0018035673,0.0015145852,0.0020130388],"category_scores_gemma":[0.0056443727,0.00080048316,0.0012157978,0.00072060764,0.0012302593,0.0014057799,0.0016332516,0.0027217309,0.0007922556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103371785,0.00007847067,0.00046782903,0.00021431614,0.000095548945,0.00011000764,0.00013559396,0.85905915,0.003614013,0.08528491,0.0023738118,0.048462972],"study_design_scores_gemma":[0.000009397344,0.000021538528,0.00002014883,0.0000074216914,0.0000039515367,0.000009633792,0.0000037356992,0.9921482,0.00036656603,0.0068272953,0.00057828805,0.0000038431467],"about_ca_topic_score_codex":0.001994423,"about_ca_topic_score_gemma":0.0017535,"teacher_disagreement_score":0.003097508,"about_ca_system_score_codex":0.0009245071,"about_ca_system_score_gemma":0.0014460394,"threshold_uncertainty_score":0.016381383},"labels":[],"label_agreement":null},{"id":"W4380088575","doi":"10.1017/apr.2022.77","title":"Conditions for indexability of restless bandits and an algorithm to compute whittle index – CORRIGENDUM","year":2023,"lang":"en","type":"erratum","venue":"Advances in Applied Probability","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Index (typography); Minor (academic); Applied mathematics; Algorithm; Computer science; Humanities","score_opus":0.12686806210954524,"score_gpt":0.4554397477832125,"score_spread":0.32857168567366724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380088575","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02153799,0.00048760293,0.9539472,0.0014373749,0.0010821202,0.0001488017,0.00060589507,0.0012496808,0.019503396],"genre_scores_gemma":[0.43962872,0.00065922836,0.52531046,0.0014420813,0.0011960422,0.0006271927,0.0016217798,0.0020142966,0.027500242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976025,0.00083241385,0.00021009796,0.0005186887,0.00060343667,0.00023285575],"domain_scores_gemma":[0.9783347,0.015369134,0.00068996043,0.002508934,0.002555231,0.000541932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00427416,0.000983054,0.0012887549,0.0014629086,0.00082489505,0.0032745586,0.0019159911,0.00157391,0.024695266],"category_scores_gemma":[0.064165674,0.000493946,0.00088893366,0.0013748687,0.0025719625,0.004480353,0.0021611503,0.0034332713,0.005893502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004015044,0.000097229684,0.0018509809,0.00028078668,0.00005704109,0.00042869913,0.0002897501,0.061763037,0.0038976849,0.7832919,0.032314286,0.11532716],"study_design_scores_gemma":[0.000045806817,0.000054640575,0.0006006888,0.0000881641,0.000018520215,0.00011586633,0.000055870023,0.47732508,0.0032950917,0.5122377,0.0061069815,0.00005548527],"about_ca_topic_score_codex":0.0018217379,"about_ca_topic_score_gemma":0.002221953,"teacher_disagreement_score":0.024695266,"about_ca_system_score_codex":0.0014092367,"about_ca_system_score_gemma":0.0013183847,"threshold_uncertainty_score":0.082613945},"labels":[],"label_agreement":null},{"id":"W4380136285","doi":"10.48550/arxiv.2306.04923","title":"Unconstrained Online Learning with Unbounded Losses","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regret; Lipschitz continuity; Bounded function; Saddle point; Mathematics; Leverage (statistics); Domain (mathematical analysis); Combinatorics; Upper and lower bounds; Matching (statistics); Saddle; Mathematical optimization; Discrete mathematics; Computer science; Pure mathematics; Mathematical analysis","score_opus":0.35451916831325986,"score_gpt":0.32717478354327845,"score_spread":0.02734438476998141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380136285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010167428,0.00036072626,0.9829016,0.00071863196,0.00006350356,0.000051418265,0.00009605373,0.00045420777,0.005186449],"genre_scores_gemma":[0.5602412,0.00071982195,0.42283627,0.0007719138,0.00026204326,0.00046765164,0.00068956823,0.00041065877,0.013600838],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980604,0.0008516723,0.00008522292,0.000451528,0.00038278554,0.0001683858],"domain_scores_gemma":[0.99334913,0.00504791,0.0003154181,0.0007721925,0.00030536053,0.00020986363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030400802,0.0012835652,0.0014200399,0.00057079754,0.00070085906,0.0017975364,0.002125848,0.001818877,0.004245212],"category_scores_gemma":[0.014618919,0.0006723349,0.0007804961,0.0009936923,0.0017750232,0.00367479,0.00277582,0.0038394458,0.0013507073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022776374,0.00016821429,0.0005614988,0.00018991825,0.000050957722,0.0001283906,0.000078898745,0.7340587,0.0011926115,0.18939209,0.0071936166,0.0667574],"study_design_scores_gemma":[0.000016053675,0.00001790022,0.00005286597,0.000012182237,0.000003358198,0.000017059803,0.0000051558736,0.93703395,0.00041988533,0.061493278,0.0009237755,0.0000046167784],"about_ca_topic_score_codex":0.0013852793,"about_ca_topic_score_gemma":0.0012782753,"teacher_disagreement_score":0.004245212,"about_ca_system_score_codex":0.0014323156,"about_ca_system_score_gemma":0.0014851713,"threshold_uncertainty_score":0.016077638},"labels":[],"label_agreement":null},{"id":"W4380788747","doi":"10.2196/39754","title":"Using Bandit Algorithms to Maximize SARS-CoV-2 Case-Finding: Evaluation and Feasibility Study","year":2023,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Drug Abuse; Ohio Department of Health; Ohio State University; National Center for Advancing Translational Sciences; Yale University","keywords":"Computer science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus disease 2019 (COVID-19); Algorithm; 2019-20 coronavirus outbreak; Medicine; Virology; Infectious disease (medical specialty)","score_opus":0.5841122104648553,"score_gpt":0.5754093158131417,"score_spread":0.008702894651713589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380788747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81488943,0.0010905042,0.17499216,0.00091367296,0.00006081572,0.0022572577,0.000316079,0.0004185442,0.005061575],"genre_scores_gemma":[0.90226066,0.00034061476,0.09504489,0.00013555028,0.000035675104,0.0011423444,0.0003104897,0.00004029567,0.00068945694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98671097,0.0106386915,0.00051279296,0.00072082225,0.0009516528,0.00046502383],"domain_scores_gemma":[0.84520084,0.14159253,0.0038668513,0.0027652485,0.0055793542,0.0009952503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025003646,0.0018870169,0.0015480776,0.0016748953,0.0006840931,0.0013707522,0.00231806,0.0021123549,0.0021858113],"category_scores_gemma":[0.085097484,0.0007367051,0.0011326586,0.001348422,0.0011924749,0.0020617004,0.0016275079,0.00153359,0.00039618448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050737215,0.0042011575,0.031926043,0.00051260897,0.00036766042,0.00021076329,0.00030044996,0.8555511,0.00092848105,0.005123444,0.0010996772,0.0947049],"study_design_scores_gemma":[0.00033106498,0.001427114,0.0020198165,0.00002469708,0.000057372177,0.000062335675,0.00006285125,0.99421483,0.00045062893,0.0011714454,0.00016238476,0.00001542897],"about_ca_topic_score_codex":0.009905393,"about_ca_topic_score_gemma":0.0037282687,"teacher_disagreement_score":0.025003646,"about_ca_system_score_codex":0.0026006685,"about_ca_system_score_gemma":0.0028493092,"threshold_uncertainty_score":0.1322335},"labels":[],"label_agreement":null},{"id":"W4381568467","doi":"10.48550/arxiv.2306.10835","title":"Online Dynamic Submodular Optimization","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Submodular set function; Regret; Mathematical optimization; Online algorithm; Computer science; Gradient descent; Function (biology); Optimization problem; Time horizon; Upper and lower bounds; Approximation algorithm; Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.30933241769867287,"score_gpt":0.33002842229157897,"score_spread":0.020696004592906103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381568467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00788277,0.00031558375,0.9855855,0.0004877177,0.00006656356,0.000091194,0.00013456652,0.0007437485,0.004692385],"genre_scores_gemma":[0.44701627,0.00051833974,0.5433095,0.0007397274,0.00016904835,0.0005350185,0.0006926554,0.00037515242,0.0066442876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987478,0.0004525838,0.000040504037,0.0002930467,0.0002714598,0.00019459911],"domain_scores_gemma":[0.9979387,0.0012224043,0.0002146648,0.0003408391,0.00016116565,0.00012223802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014630996,0.0015462112,0.0016519623,0.00059177296,0.0005548915,0.0014731769,0.0020997708,0.0015703584,0.00418964],"category_scores_gemma":[0.0047828313,0.00062480813,0.0007592295,0.0012630804,0.0010993504,0.0020243302,0.0020272387,0.0025416284,0.0010395393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017825159,0.0002680881,0.0005412898,0.00017076237,0.0000595661,0.000087499066,0.00006337611,0.7969048,0.0016196733,0.07010331,0.011928864,0.11807451],"study_design_scores_gemma":[0.000021008496,0.000024701587,0.000040854167,0.0000065066138,0.0000034529155,0.000016207701,0.0000064661585,0.9782171,0.00028445522,0.020365415,0.0010099361,0.0000039447677],"about_ca_topic_score_codex":0.0020074407,"about_ca_topic_score_gemma":0.0029753735,"teacher_disagreement_score":0.00418964,"about_ca_system_score_codex":0.0013559607,"about_ca_system_score_gemma":0.001853264,"threshold_uncertainty_score":0.014015734},"labels":[],"label_agreement":null},{"id":"W4381664137","doi":"10.1098/rsos.230157","title":"Signal detection models as contextual bandits","year":2023,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Computer science; Discriminative model; Exploit; Decision rule; Softmax function; Decision theory; Satisficing; Heuristic; Detection theory; Function (biology); Expected utility hypothesis; SIGNAL (programming language); Parametric statistics; Artificial intelligence; Machine learning; Mathematics; Mathematical economics; Statistics","score_opus":0.15742306652613147,"score_gpt":0.4586805725953694,"score_spread":0.3012575060692379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381664137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028906489,0.0007274481,0.96363044,0.0010175441,0.00008313225,0.00009293578,0.00022153341,0.00043823477,0.004882414],"genre_scores_gemma":[0.859471,0.0009921656,0.1281361,0.0005540917,0.00023269383,0.00046530133,0.00030907316,0.00017500427,0.009664659],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960573,0.002269132,0.00016936394,0.0007316619,0.00042663404,0.00034600592],"domain_scores_gemma":[0.987242,0.009901138,0.0012671824,0.00070315285,0.00064434577,0.00024227629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062920395,0.0015883491,0.0019269713,0.0013467246,0.00063634646,0.0030950266,0.002595817,0.0027869868,0.005829442],"category_scores_gemma":[0.026393022,0.0010579086,0.001337238,0.0012397239,0.0030603628,0.0037305523,0.002066176,0.003328446,0.0012468006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015361902,0.0000478552,0.0010138006,0.00012339634,0.000085241656,0.000109230044,0.00017702431,0.6812405,0.00093799236,0.2985435,0.0010355781,0.016532226],"study_design_scores_gemma":[0.000017717555,0.000024256527,0.0001437332,0.000022901755,0.000014985844,0.000015571268,0.0000155357,0.89886534,0.00016363908,0.10016804,0.0005318636,0.000016376733],"about_ca_topic_score_codex":0.0047224932,"about_ca_topic_score_gemma":0.0033606598,"teacher_disagreement_score":0.0062920395,"about_ca_system_score_codex":0.0021319045,"about_ca_system_score_gemma":0.0010001684,"threshold_uncertainty_score":0.033275902},"labels":[],"label_agreement":null},{"id":"W4382239476","doi":"10.1609/aaai.v37i6.25886","title":"Opposite Online Learning via Sequentially Integrated Stochastic Gradient Descent Estimators","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China; Jinan Science and Technology Bureau","keywords":"Stochastic gradient descent; Estimator; Statistic; Computer science; Test statistic; Inference; Statistical hypothesis testing; Gradient descent; Construct (python library); Constant (computer programming); Artificial intelligence; Statistical inference; Machine learning; Mathematical optimization; Mathematics; Statistics; Artificial neural network","score_opus":0.241087663382757,"score_gpt":0.4270665249868488,"score_spread":0.18597886160409177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009351777,0.00009891339,0.98949265,0.00012543357,0.0000298235,0.000045700614,0.000020656342,0.00025766005,0.0005773291],"genre_scores_gemma":[0.49381995,0.00022535284,0.50160223,0.0004005214,0.00017284944,0.00036797687,0.00029341225,0.00016953194,0.002948252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99589694,0.0019420859,0.00022080842,0.00076766027,0.0009076551,0.00026495947],"domain_scores_gemma":[0.99043864,0.0065336376,0.00078701996,0.000824872,0.0010892315,0.00032661582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056413896,0.0011079632,0.002119473,0.0009315206,0.0005369943,0.0014234979,0.0022867043,0.0014790229,0.0015201654],"category_scores_gemma":[0.022315381,0.00077842345,0.0008086821,0.0008772229,0.0020751583,0.0020846268,0.002051909,0.0021312758,0.00049109466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005660324,0.0003286145,0.0064324415,0.00025707492,0.00021504084,0.00023428412,0.00019338471,0.58660513,0.0051587485,0.09241804,0.0029515966,0.30463952],"study_design_scores_gemma":[0.000028953418,0.00005341671,0.00017493397,0.0000058592323,0.000010160814,0.000028222656,0.0000049050823,0.98976094,0.00080559,0.008811607,0.0003064994,0.000008851009],"about_ca_topic_score_codex":0.0024549214,"about_ca_topic_score_gemma":0.0021263508,"teacher_disagreement_score":0.0056413896,"about_ca_system_score_codex":0.0009935338,"about_ca_system_score_gemma":0.0024236597,"threshold_uncertainty_score":0.029834867},"labels":[],"label_agreement":null},{"id":"W4384157874","doi":"10.1109/netsoft57336.2023.10175461","title":"A Bandit Approach to Online Pricing for Heterogeneous Edge Resource Allocation","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Cloud computing; Enhanced Data Rates for GSM Evolution; Profit (economics); Resource allocation; Mathematical optimization; Greedy algorithm; Resource (disambiguation); Online algorithm; Thompson sampling; Edge computing; Algorithm; Artificial intelligence; Computer network; Mathematics","score_opus":0.2267947498082454,"score_gpt":0.45815091056837876,"score_spread":0.23135616076013335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384157874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011918885,0.00034908016,0.9840619,0.00036593093,0.00007185467,0.000071029186,0.00004067392,0.00021679368,0.0029037728],"genre_scores_gemma":[0.82384855,0.0006806843,0.16879787,0.00042531372,0.0001831036,0.0002626813,0.00012370378,0.00010846151,0.0055696387],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746287,0.0012451774,0.000104657076,0.00031026942,0.00055604085,0.00032101633],"domain_scores_gemma":[0.9937987,0.0044470984,0.00055439095,0.00035024734,0.0006459192,0.00020358522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004717601,0.0012007224,0.0021037974,0.0011182842,0.0011088327,0.0031253952,0.002622828,0.0022491247,0.0045724185],"category_scores_gemma":[0.015685838,0.0007248358,0.0008410865,0.0019308204,0.0018451096,0.003374633,0.0015834927,0.002533841,0.0007488196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016823437,0.000111724425,0.0006825596,0.00007589668,0.000043498174,0.00009508144,0.0000734792,0.8934377,0.0005793869,0.062413495,0.0021394703,0.040179413],"study_design_scores_gemma":[0.000006045718,0.000014332154,0.00003468896,0.0000044918406,0.000004208437,0.000011392065,0.000005507104,0.99170685,0.000102496815,0.007903747,0.00020181252,0.000004532345],"about_ca_topic_score_codex":0.0050730673,"about_ca_topic_score_gemma":0.004274286,"teacher_disagreement_score":0.0050730673,"about_ca_system_score_codex":0.0021390843,"about_ca_system_score_gemma":0.0018089234,"threshold_uncertainty_score":0.024949372},"labels":[],"label_agreement":null},{"id":"W4384916830","doi":"10.1109/lsp.2023.3296913","title":"Effective Online Portfolio Selection for the Long-Short Market Using Mirror Gradient Descent","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Regret; Portfolio; Mathematical optimization; Computer science; Stochastic gradient descent; Gradient descent; Online algorithm; Selection (genetic algorithm); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.14173142515177545,"score_gpt":0.43425186841988433,"score_spread":0.2925204432681089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384916830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016721116,0.0003895241,0.9804677,0.00030156373,0.000036752244,0.00006403827,0.00003598802,0.00036343661,0.001619837],"genre_scores_gemma":[0.62068635,0.00064042036,0.36861908,0.00043133702,0.00019492808,0.00033669666,0.0003447821,0.00021584744,0.008530526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988325,0.00049290515,0.000054674994,0.0001902236,0.0002943839,0.00013538335],"domain_scores_gemma":[0.99781185,0.0014112564,0.00020373166,0.00017058935,0.00025098835,0.00015158992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029337911,0.0012180755,0.0022211096,0.00073272997,0.0006327861,0.0013682618,0.0015470402,0.0014944737,0.0034730316],"category_scores_gemma":[0.0054234182,0.0006057887,0.00063636433,0.0010961588,0.0009147575,0.0022593762,0.0013054475,0.001601315,0.00079748157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034184862,0.0002693846,0.0013178791,0.00012789441,0.00011302412,0.00021326219,0.00006948806,0.73320013,0.0027331945,0.03881072,0.006276795,0.21652637],"study_design_scores_gemma":[0.000019048077,0.000036415917,0.00008475979,0.000003992397,0.0000052708333,0.000023977786,0.0000038363833,0.9914038,0.0004047128,0.0076326244,0.00037687243,0.0000046834143],"about_ca_topic_score_codex":0.002154651,"about_ca_topic_score_gemma":0.0023183313,"teacher_disagreement_score":0.0034730316,"about_ca_system_score_codex":0.0010865823,"about_ca_system_score_gemma":0.0019311659,"threshold_uncertainty_score":0.015515506},"labels":[],"label_agreement":null},{"id":"W4385804701","doi":"10.1109/iccci59363.2023.10210156","title":"Multi-Armed Bandit-Aided Near-Optimal Over-The-Air Updates in Multi-Band V2X Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Japan Society for the Promotion of Science London","keywords":"Payload (computing); Computer science; Dissemination; Computer network; Heuristic; Cache; Base station; Real-time computing; Telecommunications; Network packet","score_opus":0.1863415444020136,"score_gpt":0.4592689362975821,"score_spread":0.27292739189556847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385804701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20155828,0.0024352663,0.7826197,0.0007430537,0.00022200299,0.00014319886,0.00013271254,0.000586316,0.011559476],"genre_scores_gemma":[0.97598433,0.00022836267,0.020761136,0.00013743278,0.000047989688,0.00007789391,0.000066912355,0.00003361992,0.002662369],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944466,0.00019919896,0.00002416304,0.00009012358,0.00008447575,0.00015737361],"domain_scores_gemma":[0.9979837,0.0014449,0.00023072406,0.0000472296,0.00018910263,0.000104339306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010753522,0.0012314949,0.0017637074,0.00047470332,0.0006804788,0.0013073095,0.0009850289,0.0011515351,0.0024017182],"category_scores_gemma":[0.0030747293,0.00063944154,0.0004468948,0.0005189033,0.0009764973,0.0009686042,0.0012770079,0.0011184621,0.00024694332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079724196,0.00001827914,0.00032055643,0.000026895616,0.000014748126,0.000054555192,0.00003150134,0.9905822,0.00035080838,0.0016972951,0.00037473018,0.006448777],"study_design_scores_gemma":[0.000007927539,0.000020953476,0.000042893203,0.0000023698008,0.0000031997545,0.000006145213,0.000009789139,0.99924576,0.00008507859,0.00049379165,0.000079869686,0.0000022850652],"about_ca_topic_score_codex":0.010321405,"about_ca_topic_score_gemma":0.007875689,"teacher_disagreement_score":0.010321405,"about_ca_system_score_codex":0.0008093424,"about_ca_system_score_gemma":0.0013120333,"threshold_uncertainty_score":0.020522654},"labels":[],"label_agreement":null},{"id":"W4386245216","doi":"10.1109/infocom53939.2023.10228986","title":"Constrained Bandit Learning with Switching Costs for Wireless Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Regret; Wireless network; Block (permutation group theory); Wireless; Constraint (computer-aided design); Selection (genetic algorithm); Mathematical optimization; Computer network; Sublinear function; Distributed computing; Artificial intelligence; Machine learning; Mathematics; Telecommunications","score_opus":0.09346752566879607,"score_gpt":0.4246086438738163,"score_spread":0.33114111820502024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386245216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020291125,0.00083700015,0.9742793,0.00068262283,0.00007332241,0.00007605211,0.00008790511,0.0003049273,0.0033677844],"genre_scores_gemma":[0.87850094,0.0011657112,0.113382064,0.000577021,0.00018602365,0.00035476347,0.00022334358,0.0001362386,0.005474038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852043,0.00070042175,0.00006609093,0.0001989933,0.00028364765,0.00023047464],"domain_scores_gemma":[0.99220467,0.0062013376,0.0006092678,0.00037782488,0.00036929085,0.00023769446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031610094,0.0012294739,0.0015530422,0.0006630534,0.0006483316,0.0017213736,0.0015801288,0.0014795504,0.0035296986],"category_scores_gemma":[0.012842983,0.0006427336,0.0005456341,0.0011679434,0.0015302583,0.0022528684,0.0015454678,0.0026949905,0.0005271218],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014088476,0.000057171328,0.00047819188,0.00007248884,0.000031449978,0.000038163904,0.00003566945,0.94041955,0.00040750267,0.03814291,0.0012982163,0.018877843],"study_design_scores_gemma":[0.0000116756955,0.000018673123,0.000050838415,0.000009202824,0.0000050247872,0.00000814401,0.000005921911,0.98515075,0.00015521373,0.014306979,0.0002732667,0.0000042881516],"about_ca_topic_score_codex":0.004466836,"about_ca_topic_score_gemma":0.0037769454,"teacher_disagreement_score":0.004466836,"about_ca_system_score_codex":0.0019063652,"about_ca_system_score_gemma":0.0018972849,"threshold_uncertainty_score":0.016717255},"labels":[],"label_agreement":null},{"id":"W4387164682","doi":"10.1109/tsc.2023.3320674","title":"Offloading Dependent Tasks in Edge Computing With Unknown System-Side Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Leverage (statistics); Dependency (UML); Task (project management); Artificial intelligence; Theoretical computer science; Machine learning; Algorithm","score_opus":0.04869230615834702,"score_gpt":0.3553354334982302,"score_spread":0.3066431273398832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387164682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13156022,0.0004940108,0.8603375,0.0008395613,0.0001007769,0.00013236847,0.00014719121,0.0002721267,0.0061161984],"genre_scores_gemma":[0.93718314,0.00025033668,0.05655172,0.0001726392,0.00008255654,0.000121445526,0.0001166423,0.00008815403,0.005433445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888223,0.00029834194,0.000051651736,0.00029716434,0.00017811311,0.0002924398],"domain_scores_gemma":[0.99683493,0.0020101916,0.00033823328,0.00028029562,0.00028963116,0.00024678605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015629817,0.0014855433,0.0016951254,0.0005113961,0.0009853683,0.0012796323,0.0018683306,0.0019415941,0.0034940785],"category_scores_gemma":[0.005757107,0.0007005275,0.0006191611,0.0008768644,0.0011841728,0.00235313,0.0017651477,0.001683078,0.00046616237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033688755,0.00012582674,0.0007724902,0.000097246855,0.00003305296,0.00030940346,0.00010249935,0.96186817,0.003194441,0.008296115,0.0010319519,0.023832023],"study_design_scores_gemma":[0.000011470782,0.000039364633,0.00024370565,0.0000047751937,0.000008905435,0.00002869423,0.000027256996,0.9927255,0.0007730239,0.00588264,0.00024742592,0.0000071632417],"about_ca_topic_score_codex":0.004502847,"about_ca_topic_score_gemma":0.004305833,"teacher_disagreement_score":0.004502847,"about_ca_system_score_codex":0.0009896891,"about_ca_system_score_gemma":0.00118318,"threshold_uncertainty_score":0.011688888},"labels":[],"label_agreement":null},{"id":"W4387341621","doi":"10.1287/opre.2023.0017","title":"Learning and Optimization with Seasonal Patterns","year":2023,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Computer science; Exploit; Mathematical optimization; Horizon; Time horizon; Upper and lower bounds; Operations research; Artificial intelligence; Machine learning; Mathematics","score_opus":0.21259826416806105,"score_gpt":0.5232147028851709,"score_spread":0.31061643871710987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387341621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09547903,0.0012380374,0.8960846,0.0016791397,0.00011755287,0.00003942811,0.00012342354,0.00017919287,0.0050596725],"genre_scores_gemma":[0.9383769,0.0005904706,0.056123763,0.00030902517,0.0001129442,0.00008114827,0.00013810277,0.000051244624,0.004216299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991768,0.00037042273,0.000036965273,0.00018559824,0.00011121349,0.000118949734],"domain_scores_gemma":[0.99622726,0.0028506774,0.00035445447,0.0002063146,0.00023558721,0.00012562015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021553002,0.0005922763,0.0009802254,0.0003086501,0.00034457416,0.0010174051,0.000670786,0.001034017,0.0020053869],"category_scores_gemma":[0.008713786,0.00048153655,0.0005818398,0.0004521611,0.0009536303,0.001085085,0.00078613026,0.0014558717,0.00021171207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007819688,0.000036071193,0.0012133461,0.000048079128,0.000058085,0.000046820838,0.000042333406,0.94509304,0.00042668686,0.035893075,0.0010064162,0.016057923],"study_design_scores_gemma":[0.000005749483,0.000009696846,0.00014061594,0.0000037269588,0.000003601268,0.000004169245,0.0000045240117,0.98784083,0.000068282825,0.011736549,0.00018025146,0.0000020737518],"about_ca_topic_score_codex":0.0042346707,"about_ca_topic_score_gemma":0.0026622089,"teacher_disagreement_score":0.0042346707,"about_ca_system_score_codex":0.000866097,"about_ca_system_score_gemma":0.00084697275,"threshold_uncertainty_score":0.011398494},"labels":[],"label_agreement":null},{"id":"W4387869921","doi":"10.1109/icc45041.2023.10279145","title":"Reservation of Virtualized Resources with Optimistic Online Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"National Natural Science Foundation of China; Science Foundation Ireland; European Commission; Santa Fe Institute","keywords":"Reservation; Computer science; Regret; Service (business); Lease; Key (lock); Network virtualization; Virtualization; Computer network; Operations research; Machine learning; Computer security; Mathematics","score_opus":0.20999103032942962,"score_gpt":0.4727449675016023,"score_spread":0.26275393717217266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387869921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08777603,0.00043188006,0.9033304,0.0010746404,0.00009111395,0.00008500395,0.000089080226,0.0008628964,0.0062589254],"genre_scores_gemma":[0.9655898,0.00007756193,0.03223586,0.00016377978,0.000032068896,0.000046812445,0.000052636962,0.000031438103,0.0017700426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878067,0.00044979277,0.00005418067,0.00022838255,0.00022857168,0.000258342],"domain_scores_gemma":[0.99655116,0.0021624912,0.0004114089,0.00033404623,0.00030745234,0.00023339364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002000737,0.000831848,0.0012679392,0.00033724928,0.00061076257,0.0015392276,0.0018796803,0.0011119907,0.0023205911],"category_scores_gemma":[0.005417768,0.0005988009,0.00042616157,0.00038443698,0.0012777932,0.0016382352,0.0015531182,0.00161683,0.00042604783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020212447,0.000061396546,0.000500386,0.000029890996,0.000019183528,0.000062287785,0.000054681528,0.9747499,0.0004503375,0.008371115,0.0007675714,0.0147311315],"study_design_scores_gemma":[0.000007667098,0.000009254047,0.00001658467,0.0000016311262,0.000001757263,0.000004198844,0.000004855875,0.9973864,0.00012682138,0.002366173,0.00007259018,0.0000020295224],"about_ca_topic_score_codex":0.0044001043,"about_ca_topic_score_gemma":0.0040267347,"teacher_disagreement_score":0.0044001043,"about_ca_system_score_codex":0.0012971646,"about_ca_system_score_gemma":0.0022627488,"threshold_uncertainty_score":0.010581017},"labels":[],"label_agreement":null},{"id":"W4387914395","doi":"10.1109/codit58514.2023.10284153","title":"On Parameter Selection for First-Order Methods: A Matrix Analysis Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convexity; Rate of convergence; Convergence (economics); Mathematical optimization; Computer science; Stability (learning theory); Applied mathematics; Selection (genetic algorithm); Range (aeronautics); Matrix (chemical analysis); Mathematics; Artificial intelligence; Machine learning","score_opus":0.23487230915963445,"score_gpt":0.5631011984125778,"score_spread":0.32822888925294336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387914395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081970566,0.0007171497,0.9955148,0.00032660257,0.00006376448,0.000034912206,0.000013220959,0.00006270243,0.0024471846],"genre_scores_gemma":[0.19383165,0.006130761,0.77843565,0.00086700864,0.0008430314,0.0009011479,0.0001642538,0.0008056638,0.01802078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982665,0.00090909743,0.000069456066,0.00017814274,0.0004768457,0.00009998059],"domain_scores_gemma":[0.9917108,0.0064650634,0.00040732924,0.00039322072,0.000864078,0.00015951598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049580582,0.0021031997,0.0012549709,0.0016294833,0.0010379095,0.0024401683,0.001453525,0.0020653384,0.006475121],"category_scores_gemma":[0.016484959,0.0007588349,0.0015925863,0.0012687009,0.002591259,0.0024092498,0.0027127734,0.004485522,0.0018211189],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006403871,0.00009415684,0.0006670391,0.000573569,0.0001048936,0.00016985125,0.000311904,0.37008032,0.004152587,0.55370605,0.004254928,0.065820746],"study_design_scores_gemma":[0.0000074923482,0.000026328838,0.00006098336,0.0000574418,0.00000954428,0.000039237337,0.000017984183,0.9182871,0.0005825231,0.077529326,0.0033663732,0.000015711475],"about_ca_topic_score_codex":0.0036513382,"about_ca_topic_score_gemma":0.0035701545,"teacher_disagreement_score":0.006475121,"about_ca_system_score_codex":0.0016705204,"about_ca_system_score_gemma":0.0022204935,"threshold_uncertainty_score":0.026221037},"labels":[],"label_agreement":null},{"id":"W4388082363","doi":"10.1109/africon55910.2023.10293356","title":"Bandit Algorithms Applied in Online Advertisement to Evaluate Click-Through Rates","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; John Abbott College","funders":"","keywords":"Click-through rate; Computer science; Algorithm; Advertising; World Wide Web; Business","score_opus":0.24434533584965396,"score_gpt":0.524817116986591,"score_spread":0.280471781136937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388082363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06109357,0.0013256251,0.9315014,0.00037787302,0.00009769229,0.00020413687,0.00013418913,0.0012145481,0.004051023],"genre_scores_gemma":[0.8461249,0.00056062423,0.14945468,0.00024485204,0.00007411813,0.00032342362,0.00023605155,0.00010947244,0.002871939],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978471,0.0010070854,0.00016925453,0.00036337075,0.0003980732,0.00021520877],"domain_scores_gemma":[0.9906324,0.0068710702,0.0008861874,0.00036633265,0.0010395909,0.00020448654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048126816,0.0013957084,0.002073707,0.0017231216,0.0006618021,0.0022896228,0.0015395302,0.00179258,0.0024878096],"category_scores_gemma":[0.01773119,0.0005091662,0.0005191141,0.0015721539,0.0008747777,0.0015205445,0.0007949421,0.0017639499,0.0007964719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041372373,0.00018765859,0.0031330558,0.00012231832,0.00010429276,0.00006160795,0.000100819256,0.85606325,0.0012865872,0.010055266,0.0013918199,0.12707964],"study_design_scores_gemma":[0.00000854426,0.000031822223,0.00023557925,0.000009197757,0.000008180623,0.0000127544845,0.0000073822857,0.99684554,0.00044937918,0.002210781,0.0001746784,0.000006172644],"about_ca_topic_score_codex":0.0065642125,"about_ca_topic_score_gemma":0.004062238,"teacher_disagreement_score":0.0065642125,"about_ca_system_score_codex":0.0015358712,"about_ca_system_score_gemma":0.0013153163,"threshold_uncertainty_score":0.025452256},"labels":[],"label_agreement":null},{"id":"W4388685754","doi":"10.48550/arxiv.2311.07565","title":"Exploration via linearly perturbed loss minimisation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Minimisation (clinical trials); Perturbation (astronomy); Mathematics; Mathematical optimization; Applied mathematics; Computer science; Linear programming; Simple (philosophy); Algorithm; Statistics; Physics","score_opus":0.47377980120383045,"score_gpt":0.33473689470705636,"score_spread":0.1390429064967741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388685754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011427311,0.00033457784,0.98389786,0.00044651452,0.000049375532,0.00006167876,0.00009673329,0.0007201065,0.0029657534],"genre_scores_gemma":[0.60331416,0.00039258023,0.38504592,0.00080178556,0.0001493584,0.00056567224,0.0004595555,0.0005852539,0.0086856885],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983082,0.0009440291,0.00006238024,0.00024385379,0.00030153999,0.00014002518],"domain_scores_gemma":[0.9961241,0.0027815374,0.00028341662,0.00041977677,0.00022555015,0.00016562473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021482348,0.0011903765,0.0011538271,0.0005458741,0.00040424787,0.0013052325,0.0015998808,0.0016835677,0.004398778],"category_scores_gemma":[0.013049703,0.0005602596,0.00071334856,0.0005455961,0.0016518703,0.0018819475,0.0031591663,0.0023985787,0.0013692825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025218868,0.00005735284,0.0007259173,0.00012871795,0.00006950345,0.00011388691,0.00010802915,0.88806796,0.0022925695,0.05855302,0.0029563438,0.04667449],"study_design_scores_gemma":[0.000021573464,0.000037103982,0.0000464531,0.000017544357,0.000005600357,0.000022199347,0.000007860349,0.96767586,0.0006647754,0.030692123,0.00080052094,0.000008253428],"about_ca_topic_score_codex":0.0011644268,"about_ca_topic_score_gemma":0.0013134355,"teacher_disagreement_score":0.004398778,"about_ca_system_score_codex":0.0008314228,"about_ca_system_score_gemma":0.0010834355,"threshold_uncertainty_score":0.014715433},"labels":[],"label_agreement":null},{"id":"W4388740203","doi":"10.1109/tcns.2023.3333402","title":"On Learning Whittle Index Policy for Restless Bandits With Scalable Regret","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Scalability; Notation; Discrete mathematics; Mathematics; Computer science; Artificial intelligence; Machine learning; Arithmetic","score_opus":0.0682088884693561,"score_gpt":0.3776760523188988,"score_spread":0.30946716384954265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388740203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029734693,0.0005305832,0.9645248,0.0007081341,0.000059956124,0.00009558128,0.00009694149,0.00090288126,0.0033464436],"genre_scores_gemma":[0.8234594,0.0005546176,0.1685115,0.0009036909,0.00021774568,0.00045546767,0.00036774887,0.00035857622,0.0051711784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979024,0.0010248293,0.000089347195,0.00033073584,0.0003597798,0.00029297773],"domain_scores_gemma":[0.9876573,0.009832646,0.00085942383,0.0007579002,0.00046054623,0.00043218894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005123185,0.0021001138,0.00315106,0.0008522592,0.0008028923,0.001972438,0.0024267281,0.00251119,0.003894216],"category_scores_gemma":[0.02138646,0.000893716,0.0011144993,0.001037391,0.002915973,0.003551753,0.0024207572,0.003845217,0.00092297746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018495516,0.0000828497,0.00054237637,0.000059067544,0.000036706944,0.00005376797,0.000044302626,0.9579166,0.00045268342,0.02518004,0.0011643653,0.014282384],"study_design_scores_gemma":[0.00001186291,0.000020778698,0.000027763317,0.000005109444,0.000002807399,0.000005143618,0.000002335324,0.9924448,0.000097245844,0.0073175523,0.00006121462,0.0000034077352],"about_ca_topic_score_codex":0.0059878067,"about_ca_topic_score_gemma":0.0048697093,"teacher_disagreement_score":0.0059878067,"about_ca_system_score_codex":0.0026105177,"about_ca_system_score_gemma":0.0027859905,"threshold_uncertainty_score":0.027094305},"labels":[],"label_agreement":null},{"id":"W4389262778","doi":"10.1016/j.peva.2023.102394","title":"Two families of indexable partially observable restless bandits and Whittle index computation","year":2023,"lang":"en","type":"article","venue":"Performance Evaluation","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Observability; Observable; Computation; State space; State (computer science); Mathematical optimization; Index (typography); Computer science; Mathematics; Space (punctuation); Applied mathematics; Algorithm; Statistics","score_opus":0.26607368673150594,"score_gpt":0.48535070565636956,"score_spread":0.21927701892486362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389262778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09859396,0.0013295094,0.88643104,0.00097195315,0.00015791944,0.0001764291,0.00031318006,0.0007633066,0.011262619],"genre_scores_gemma":[0.83497435,0.0008789554,0.15468821,0.0002880267,0.00021816621,0.000314697,0.00040647024,0.00021212394,0.008018937],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950923,0.002223494,0.00021059652,0.0005958914,0.001172045,0.0007057797],"domain_scores_gemma":[0.9839833,0.009797498,0.0011947297,0.0030304175,0.0011882137,0.0008058222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006765437,0.0016618789,0.0027195197,0.0018007023,0.001266839,0.004151039,0.003380506,0.002664347,0.0045543495],"category_scores_gemma":[0.030047957,0.00071019237,0.0013504068,0.002596386,0.0036937988,0.0055545927,0.0035324388,0.0029389479,0.0006839944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009664993,0.00019364619,0.0010984748,0.00018209392,0.00010434281,0.0001295549,0.00021347652,0.27439845,0.0018675228,0.6729046,0.003515904,0.044425394],"study_design_scores_gemma":[0.000073396,0.0001188568,0.00019166432,0.000035769808,0.000029720119,0.000045712684,0.000031513504,0.804405,0.0010346868,0.1930083,0.0010036213,0.00002179565],"about_ca_topic_score_codex":0.0019697954,"about_ca_topic_score_gemma":0.0015336681,"teacher_disagreement_score":0.006765437,"about_ca_system_score_codex":0.0025583033,"about_ca_system_score_gemma":0.0028237633,"threshold_uncertainty_score":0.035779476},"labels":[],"label_agreement":null},{"id":"W4389891511","doi":"10.32920/24625161.v1","title":"Financial Bandits - Development of Thompson Sampling for Financial Data","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Class (philosophy); Artificial intelligence; Focus (optics); Bayesian probability; Thompson sampling; Machine learning; Financial market; Parametric statistics; Bayesian inference; Sampling (signal processing); Finance; Economics; Mathematics","score_opus":0.7430885098891811,"score_gpt":0.5754503766900538,"score_spread":0.16763813319912724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389891511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034348979,0.00070317957,0.9928403,0.0004272138,0.000096600095,0.00004899387,0.0000962044,0.00018461954,0.0021679117],"genre_scores_gemma":[0.32537362,0.0031957936,0.66032547,0.0006380226,0.00070695806,0.0005962374,0.0007380627,0.00038831076,0.008037596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633384,0.0023183872,0.00017794764,0.0003741266,0.0006583935,0.0001373618],"domain_scores_gemma":[0.98789155,0.009154739,0.00076865585,0.0009327883,0.0009242229,0.0003280837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074825427,0.0011158235,0.001512203,0.0016860259,0.0006962018,0.0029677209,0.0021343974,0.0018925132,0.0034819166],"category_scores_gemma":[0.03793207,0.00090035016,0.0010716342,0.002182867,0.002053817,0.0029071234,0.0023318822,0.003767278,0.0010589809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007877787,0.000051478764,0.0022218053,0.00011906078,0.000111828056,0.00017613235,0.00014451821,0.33082753,0.00064760534,0.5756076,0.003880844,0.086132854],"study_design_scores_gemma":[0.000012575135,0.000014560795,0.00017597161,0.0000347056,0.000008200858,0.000027586957,0.000009054732,0.83656746,0.0002513001,0.15991159,0.002974507,0.000012539375],"about_ca_topic_score_codex":0.0058246576,"about_ca_topic_score_gemma":0.004605581,"teacher_disagreement_score":0.0074825427,"about_ca_system_score_codex":0.0016495821,"about_ca_system_score_gemma":0.0018063644,"threshold_uncertainty_score":0.03957194},"labels":[],"label_agreement":null},{"id":"W4389891535","doi":"10.32920/24625161","title":"Financial Bandits - Development of Thompson Sampling for Financial Data","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Class (philosophy); Artificial intelligence; Focus (optics); Bayesian probability; Machine learning; Parametric statistics; Financial market; Bayesian inference; Mathematical finance; Finance; Economics; Mathematics","score_opus":0.7430885098891811,"score_gpt":0.5754503766900538,"score_spread":0.16763813319912724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389891535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034348979,0.00070317957,0.9928403,0.0004272138,0.000096600095,0.00004899387,0.0000962044,0.00018461954,0.0021679117],"genre_scores_gemma":[0.32537362,0.0031957936,0.66032547,0.0006380226,0.00070695806,0.0005962374,0.0007380627,0.00038831076,0.008037596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99633384,0.0023183872,0.00017794764,0.0003741266,0.0006583935,0.0001373618],"domain_scores_gemma":[0.98789155,0.009154739,0.00076865585,0.0009327883,0.0009242229,0.0003280837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074825427,0.0011158235,0.001512203,0.0016860259,0.0006962018,0.0029677209,0.0021343974,0.0018925132,0.0034819166],"category_scores_gemma":[0.03793207,0.00090035016,0.0010716342,0.002182867,0.002053817,0.0029071234,0.0023318822,0.003767278,0.0010589809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007877787,0.000051478764,0.0022218053,0.00011906078,0.000111828056,0.00017613235,0.00014451821,0.33082753,0.00064760534,0.5756076,0.003880844,0.086132854],"study_design_scores_gemma":[0.000012575135,0.000014560795,0.00017597161,0.0000347056,0.000008200858,0.000027586957,0.000009054732,0.83656746,0.0002513001,0.15991159,0.002974507,0.000012539375],"about_ca_topic_score_codex":0.0058246576,"about_ca_topic_score_gemma":0.004605581,"teacher_disagreement_score":0.0074825427,"about_ca_system_score_codex":0.0016495821,"about_ca_system_score_gemma":0.0018063644,"threshold_uncertainty_score":0.03957194},"labels":[],"label_agreement":null},{"id":"W4389974594","doi":"10.48550/arxiv.2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Monte Carlo tree search; Computer science; Regret; Context (archaeology); Monte Carlo method; Tree (set theory); Suite; Algorithm; Mathematical optimization; Machine learning; Mathematics; Statistics","score_opus":0.35889327179290864,"score_gpt":0.33277038649446816,"score_spread":0.02612288529844048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389974594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10446758,0.00074784615,0.8895258,0.0007685358,0.000056179204,0.00009466675,0.00021130673,0.00072765135,0.0034003854],"genre_scores_gemma":[0.8290779,0.00023168145,0.16839747,0.00024130588,0.00005281334,0.00014449378,0.0003486735,0.00012980904,0.0013759099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978192,0.0011482236,0.00010858309,0.0003177377,0.00038311825,0.0002231172],"domain_scores_gemma":[0.9865789,0.011247952,0.0006051053,0.0007311448,0.00055337796,0.00028359875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038385778,0.0007756552,0.001675285,0.0007957182,0.0005816028,0.0012545986,0.0013655396,0.0013831035,0.0013659768],"category_scores_gemma":[0.01819799,0.0005745416,0.0007501174,0.0011640049,0.0013694873,0.0016798307,0.0015124133,0.0017300558,0.0002177019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009931347,0.000023874472,0.0007440232,0.0000305181,0.000025678775,0.000042875967,0.000026387395,0.97684574,0.000248356,0.011615705,0.0004768437,0.009820728],"study_design_scores_gemma":[0.000007732481,0.000008282515,0.000052817984,0.000003404971,0.000003116955,0.0000068000545,0.0000023299208,0.99373007,0.000107511776,0.0059752185,0.00010097177,0.0000017580842],"about_ca_topic_score_codex":0.008985886,"about_ca_topic_score_gemma":0.007177344,"teacher_disagreement_score":0.008985886,"about_ca_system_score_codex":0.0015569377,"about_ca_system_score_gemma":0.002236434,"threshold_uncertainty_score":0.020300627},"labels":[],"label_agreement":null},{"id":"W4391539883","doi":"10.1177/10591478241231858","title":"A Nonparametric Learning Algorithm for a Stochastic Multi-echelon Inventory Problem","year":2024,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Nonparametric statistics; Computer science; Decision maker; Time horizon; Mathematical optimization; Sequence (biology); Product (mathematics); Matching (statistics); A priori and a posteriori; Inventory control; Mathematical economics; Mathematics; Operations research; Econometrics; Statistics","score_opus":0.10217860712911685,"score_gpt":0.41911980975443025,"score_spread":0.3169412026253134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391539883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011663322,0.00020134651,0.9862309,0.000303042,0.00002677867,0.000045709236,0.0000399836,0.00016972904,0.0013191123],"genre_scores_gemma":[0.50139666,0.00037820445,0.49269608,0.0003393957,0.0001486099,0.00044793633,0.00033971923,0.00012443685,0.0041289567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990477,0.0004267363,0.000042937038,0.00018192246,0.00019667132,0.000103962004],"domain_scores_gemma":[0.99567693,0.0031956644,0.00033556024,0.00018997397,0.00045489796,0.00014689096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028427178,0.0007687755,0.0017749893,0.00066799024,0.00061299873,0.0011448577,0.0019980643,0.0020848736,0.0024411993],"category_scores_gemma":[0.009121848,0.0006151722,0.00061982183,0.0010415224,0.0012369414,0.0017802132,0.0015523251,0.0020494694,0.00044294327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007436729,0.00006325275,0.00046920514,0.000050189643,0.000024067342,0.00003001354,0.000030884225,0.9487119,0.00029227615,0.0119908275,0.0008641641,0.037398804],"study_design_scores_gemma":[0.0000077252735,0.000011315236,0.000030814517,0.000003325696,0.0000016104915,0.0000053654794,0.0000022784961,0.9967609,0.00004743329,0.0029971458,0.00012992091,0.0000021832443],"about_ca_topic_score_codex":0.0046277144,"about_ca_topic_score_gemma":0.0037265401,"teacher_disagreement_score":0.0046277144,"about_ca_system_score_codex":0.0015247733,"about_ca_system_score_gemma":0.0023641763,"threshold_uncertainty_score":0.01503396},"labels":[],"label_agreement":null},{"id":"W4392044436","doi":"10.1287/msom.2021.0135","title":"Feature-Based Inventory Control with Censored Demand","year":2024,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inventory control; Feature (linguistics); Computer science; Regret; Mathematical optimization; Inventory theory; Operations research; Mathematics; Machine learning","score_opus":0.035355270218556556,"score_gpt":0.34184070000304223,"score_spread":0.3064854297844857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392044436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07199038,0.001002483,0.9190511,0.0012778403,0.00014778208,0.00027929846,0.0005057942,0.0003777946,0.0053674453],"genre_scores_gemma":[0.9649727,0.000474085,0.030604782,0.00014438905,0.00012529985,0.00023559081,0.00024450794,0.000038902766,0.0031597726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810636,0.0006800527,0.00008886302,0.00051873963,0.00035467022,0.00025131422],"domain_scores_gemma":[0.99456006,0.0032570285,0.0010481065,0.0003171962,0.00055283285,0.0002648103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026955097,0.0016866832,0.0028061755,0.0007376419,0.0004858495,0.0018782566,0.0030153894,0.0021720186,0.0028644633],"category_scores_gemma":[0.00860533,0.0007732946,0.00099692,0.0012676072,0.0016558219,0.0023122644,0.0013634325,0.001923374,0.00034198308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020400657,0.00007565425,0.0008013094,0.00017904071,0.000060558497,0.0001891202,0.000053352753,0.9665951,0.00067150034,0.019173067,0.0010428161,0.010954402],"study_design_scores_gemma":[0.000023331564,0.000041670708,0.000202229,0.000010361408,0.000011825135,0.000025665187,0.000007191375,0.9928109,0.00016078251,0.0064962255,0.00019789963,0.000011908928],"about_ca_topic_score_codex":0.00661231,"about_ca_topic_score_gemma":0.0029207643,"teacher_disagreement_score":0.00661231,"about_ca_system_score_codex":0.0019155664,"about_ca_system_score_gemma":0.0016344603,"threshold_uncertainty_score":0.0142554045},"labels":[],"label_agreement":null},{"id":"W4392270931","doi":"10.48550/arxiv.2402.17235","title":"Stochastic Gradient Succeeds for Bandits","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Mathematical economics; Computer science; Economics; Econometrics; Mathematics","score_opus":0.29064790336143387,"score_gpt":0.3273040213724201,"score_spread":0.03665611801098623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392270931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03033372,0.000489118,0.9580398,0.000859183,0.00010087966,0.00007122052,0.000055446762,0.0004852014,0.009565424],"genre_scores_gemma":[0.781611,0.00081287965,0.2044927,0.00069676974,0.0002103283,0.0003415939,0.0001579563,0.00037279289,0.01130405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837,0.0006370917,0.00008133884,0.0002767012,0.00041463386,0.00022026699],"domain_scores_gemma":[0.9928871,0.005245721,0.00056698604,0.0005984021,0.00048385037,0.00021793292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027699026,0.0012462912,0.0013718989,0.00077950646,0.0008810641,0.0016988865,0.00094494136,0.0014277236,0.0039115003],"category_scores_gemma":[0.019923225,0.0004674334,0.00068290695,0.00074213435,0.0021641736,0.0021582248,0.0018374851,0.0024640558,0.0011262386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002958668,0.00011246658,0.0010592276,0.00018787014,0.000072128685,0.00013262536,0.0001542942,0.5915805,0.0032222185,0.33382517,0.003512797,0.06584489],"study_design_scores_gemma":[0.000016728447,0.000039052356,0.000086498854,0.000020465846,0.000009034274,0.000024746158,0.000009116112,0.92596596,0.00083905313,0.07203738,0.00094420003,0.000007722281],"about_ca_topic_score_codex":0.002785512,"about_ca_topic_score_gemma":0.0024711618,"teacher_disagreement_score":0.0039115003,"about_ca_system_score_codex":0.0012942768,"about_ca_system_score_gemma":0.0017227797,"threshold_uncertainty_score":0.014648795},"labels":[],"label_agreement":null},{"id":"W4392487808","doi":"10.48550/arxiv.2403.01315","title":"Near-optimal Per-Action Regret Bounds for Sleeping Bandits","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Action (physics); Mathematical economics; Economics; Computer science; Mathematics; Econometrics; Statistics; Physics","score_opus":0.35036165592399393,"score_gpt":0.35515225202680634,"score_spread":0.0047905961028124056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392487808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02526744,0.0021818995,0.95464796,0.0011464418,0.00019578706,0.00014090654,0.0003655465,0.0012207552,0.014833272],"genre_scores_gemma":[0.6576823,0.0026860547,0.32242063,0.0017142706,0.0006133237,0.0007364406,0.0009494792,0.0012830046,0.011914521],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956493,0.0012930331,0.0002107387,0.00090787513,0.0011898422,0.0007492049],"domain_scores_gemma":[0.97761106,0.015303123,0.0014648222,0.00349346,0.0012782061,0.0008493562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068824575,0.0033241685,0.0027340073,0.0011531931,0.0011913939,0.0030438427,0.0047073066,0.002344487,0.008786416],"category_scores_gemma":[0.034405787,0.0011502873,0.0027089538,0.0017000887,0.0030861015,0.0061879125,0.0038483685,0.008328317,0.0021900972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079142227,0.00036164874,0.0019020882,0.00054656254,0.00018931906,0.00016683975,0.00030597893,0.7701762,0.0055319383,0.13947274,0.008605613,0.07194965],"study_design_scores_gemma":[0.00004510587,0.0001188947,0.00041225838,0.00007574717,0.00005058719,0.00007386164,0.000032137366,0.916202,0.0020659827,0.079475045,0.0014221288,0.000026224574],"about_ca_topic_score_codex":0.0021398948,"about_ca_topic_score_gemma":0.0028504692,"teacher_disagreement_score":0.008786416,"about_ca_system_score_codex":0.0034464248,"about_ca_system_score_gemma":0.0031667994,"threshold_uncertainty_score":0.03639835},"labels":[],"label_agreement":null},{"id":"W4392847906","doi":"10.2196/52688","title":"New Approach to Equitable Intervention Planning to Improve Engagement and Outcomes in a Digital Health Program: Simulation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Diabetes","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Verily Life Sciences","keywords":"Psychological intervention; Dropout (neural networks); Intervention (counseling); Digital health; Outcome (game theory); Resource allocation; Computer science; Resource (disambiguation); Process management; Medicine; Business; Health care; Nursing; Machine learning; Economics; Microeconomics","score_opus":0.15457686544406057,"score_gpt":0.516135049651501,"score_spread":0.36155818420744046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392847906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73428005,0.0006461765,0.23693117,0.0038396635,0.00016969281,0.00086378295,0.0012187642,0.0002367323,0.021813825],"genre_scores_gemma":[0.96586096,0.00020283894,0.030387092,0.00025767906,0.000024864969,0.00058283925,0.00024011666,0.000018999963,0.0024244832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985455,0.00094648404,0.000045566045,0.00016398326,0.00007743022,0.00022104061],"domain_scores_gemma":[0.98693687,0.010816698,0.0007274054,0.00035044493,0.0005060931,0.00066238124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038725128,0.0009758036,0.0010691779,0.0008519941,0.00058142404,0.001406586,0.0014894606,0.0022367928,0.006957906],"category_scores_gemma":[0.013075017,0.0004947739,0.0011851409,0.00078394136,0.0011806649,0.0014761686,0.0019451772,0.0023264196,0.00022140816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011468656,0.00022111347,0.0024305198,0.000043299122,0.00003989385,0.000049782782,0.00006995902,0.9891242,0.00007327281,0.005379085,0.000256466,0.0021976863],"study_design_scores_gemma":[0.000091311864,0.00010690772,0.000332977,0.000014481819,0.000020603356,0.0000069507787,0.00006458878,0.9964479,0.00007398067,0.002478685,0.00035483742,0.0000067271603],"about_ca_topic_score_codex":0.023082957,"about_ca_topic_score_gemma":0.014636376,"teacher_disagreement_score":0.023082957,"about_ca_system_score_codex":0.0022455628,"about_ca_system_score_gemma":0.0031309251,"threshold_uncertainty_score":0.045897245},"labels":[],"label_agreement":null},{"id":"W4393146897","doi":"10.1609/aaai.v38i19.30182","title":"Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Volatility (finance); Computer science; Internet privacy; Computer security; Artificial intelligence; Business; Econometrics; Economics","score_opus":0.23644016349401392,"score_gpt":0.4303859763608097,"score_spread":0.1939458128667958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393146897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022455929,0.00024599495,0.97471637,0.00044697057,0.000031498133,0.0000842421,0.000036701986,0.00025548,0.0017267399],"genre_scores_gemma":[0.9118868,0.00037333067,0.084217906,0.0003698985,0.00007593811,0.0002697315,0.00008604225,0.00009755054,0.002622762],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947154,0.0028370384,0.00022417365,0.0008037911,0.0008309053,0.0005887443],"domain_scores_gemma":[0.9770313,0.017461995,0.0016394579,0.0019301551,0.0013287464,0.0006083798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076377015,0.0015517671,0.002690093,0.001109194,0.0011108826,0.0028488175,0.0024110498,0.0021911801,0.002350788],"category_scores_gemma":[0.03690648,0.0006379535,0.0009377014,0.0013086986,0.003738516,0.004615293,0.0035933722,0.0035116053,0.0006248998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057717756,0.00025067927,0.002049187,0.00016813139,0.00011683233,0.00021044885,0.00028647366,0.7455083,0.0019249521,0.17386074,0.001750287,0.0732967],"study_design_scores_gemma":[0.000028615876,0.00006438934,0.00010143506,0.000017989483,0.0000132138575,0.000048320042,0.000020339083,0.939706,0.000800891,0.058922112,0.00026241541,0.000014230147],"about_ca_topic_score_codex":0.0014308528,"about_ca_topic_score_gemma":0.0009905621,"teacher_disagreement_score":0.0076377015,"about_ca_system_score_codex":0.0016788393,"about_ca_system_score_gemma":0.002568635,"threshold_uncertainty_score":0.04039246},"labels":[],"label_agreement":null},{"id":"W4393157138","doi":"10.1609/aaai.v38i14.29443","title":"Learning Not to Regret","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Grantová Agentura České Republiky","keywords":"Regret; Psychology; Computer science; Machine learning","score_opus":0.2905248091849463,"score_gpt":0.4733330005536306,"score_spread":0.18280819136868431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393157138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03828497,0.0009887287,0.9468472,0.0021047667,0.00022805014,0.00012236621,0.00017085574,0.001334416,0.009918585],"genre_scores_gemma":[0.76673853,0.0005219293,0.22361228,0.0015644872,0.00031082652,0.00030102933,0.0003771957,0.00041299543,0.0061606723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973213,0.0011418798,0.000111049536,0.00071476237,0.00043203283,0.0002789246],"domain_scores_gemma":[0.99273515,0.0048117796,0.0005202018,0.0011720363,0.0005244528,0.0002362917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003685625,0.0016685582,0.0016870246,0.0005818631,0.0006821787,0.0018582836,0.0021822504,0.0023157145,0.0041053724],"category_scores_gemma":[0.021423167,0.0006444035,0.0009601077,0.0006079009,0.0020708593,0.0029349867,0.0018172235,0.0039932625,0.0009938007],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026832632,0.00020389141,0.002176178,0.00022644745,0.00017822624,0.00007955953,0.000119704615,0.8121713,0.0014259045,0.06805477,0.0074906345,0.107605],"study_design_scores_gemma":[0.0000319489,0.000068768844,0.00015274023,0.000025955998,0.000021374168,0.00003657434,0.000013553881,0.9539856,0.0007070367,0.043808803,0.0011390531,0.00000865703],"about_ca_topic_score_codex":0.0017811449,"about_ca_topic_score_gemma":0.0021659455,"teacher_disagreement_score":0.0041053724,"about_ca_system_score_codex":0.0017705972,"about_ca_system_score_gemma":0.0023250985,"threshold_uncertainty_score":0.019491673},"labels":[],"label_agreement":null},{"id":"W4393160289","doi":"10.1609/aaai.v38i15.29558","title":"Multiobjective Lipschitz Bandits under Lexicographic Ordering","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Lexicographical order; Lipschitz continuity; Mathematics; Mathematical economics; Mathematical optimization; Applied mathematics; Combinatorics; Pure mathematics","score_opus":0.2554005872919155,"score_gpt":0.44457654767578736,"score_spread":0.18917596038387186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393160289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03527399,0.0004060966,0.9582959,0.00038789163,0.0000348704,0.00012210914,0.00008454511,0.00035450436,0.0050401087],"genre_scores_gemma":[0.5850222,0.00049620523,0.40531284,0.0003797777,0.00008871586,0.0003832275,0.0002912655,0.00013655798,0.007889116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854565,0.0007530681,0.00006714871,0.00017762808,0.00024615935,0.00021043624],"domain_scores_gemma":[0.99737996,0.0018698473,0.0002682721,0.00014985328,0.00018367167,0.00014838313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025754988,0.001217474,0.0018350002,0.0006891717,0.0006549359,0.0014484291,0.0012145633,0.0014376417,0.0032589685],"category_scores_gemma":[0.0057470305,0.000569746,0.00070782244,0.00097110687,0.0010993509,0.002048656,0.0013425837,0.0020302015,0.0007439357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025551248,0.00013038967,0.00080128724,0.00011625634,0.000045381767,0.00009238116,0.00009153942,0.90423024,0.0010923243,0.042196345,0.0016249566,0.049323346],"study_design_scores_gemma":[0.00002972817,0.00004910208,0.000070131326,0.0000123549125,0.000005984271,0.000014904049,0.000013870524,0.98363566,0.00047927297,0.015388387,0.00029496444,0.0000055754435],"about_ca_topic_score_codex":0.003266673,"about_ca_topic_score_gemma":0.0031596692,"teacher_disagreement_score":0.003266673,"about_ca_system_score_codex":0.0014027728,"about_ca_system_score_gemma":0.0016213276,"threshold_uncertainty_score":0.013620734},"labels":[],"label_agreement":null},{"id":"W4393277074","doi":"10.54254/2755-2721/54/20241586","title":"Assessing the robustness of Multi-Armed Bandit algorithms against biased initialization","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Initialization; Robustness (evolution); Adaptability; Computer science; Recommender system; Thompson sampling; Greedy algorithm; Upper and lower bounds; Commit; Machine learning; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.101806615478968,"score_gpt":0.405559755997657,"score_spread":0.30375314051868896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393277074","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7543615,0.0018231223,0.23378399,0.0015483061,0.00018115043,0.0002831206,0.00031724985,0.00039584443,0.0073056556],"genre_scores_gemma":[0.97434676,0.00031037309,0.024343919,0.00015875575,0.00003616298,0.00011295516,0.00015994535,0.000037187998,0.0004939403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926341,0.0045844615,0.0004125736,0.0008705436,0.001018929,0.00047928985],"domain_scores_gemma":[0.90339756,0.07846125,0.00665335,0.0071818805,0.0032799053,0.0010261539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018616948,0.0009819345,0.0011951437,0.0011803978,0.0010822843,0.002688934,0.0014740911,0.0019589635,0.0009896467],"category_scores_gemma":[0.11542984,0.00043941152,0.00065009895,0.0011099956,0.0016269494,0.0024152582,0.0017387393,0.0020747979,0.0003376411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005553152,0.00015791006,0.01691798,0.0001544315,0.00032503728,0.00009126173,0.00022561188,0.9425053,0.0012803671,0.012450789,0.0007491506,0.024586927],"study_design_scores_gemma":[0.000050379043,0.00044487213,0.0034699703,0.00006782164,0.000062931365,0.00007214634,0.0001875103,0.9828471,0.0016615139,0.010536523,0.00056478626,0.000034482026],"about_ca_topic_score_codex":0.0071801515,"about_ca_topic_score_gemma":0.0043815253,"teacher_disagreement_score":0.018616948,"about_ca_system_score_codex":0.0014979737,"about_ca_system_score_gemma":0.0021007713,"threshold_uncertainty_score":0.09845698},"labels":[],"label_agreement":null},{"id":"W4393335276","doi":"10.1287/mnsc.2022.00893","title":"On Statistical Discrimination as a Failure of Social Learning: A Multiarmed Bandit Approach","year":2024,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Social learning; Statistical learning; Machine learning; Knowledge management","score_opus":0.06935144906801434,"score_gpt":0.4468491803035057,"score_spread":0.37749773123549135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393335276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13985051,0.0017218908,0.8407635,0.006679736,0.00023411067,0.00014539312,0.0003098404,0.0002968483,0.009998151],"genre_scores_gemma":[0.9536403,0.001379543,0.032300666,0.0009354381,0.0004529743,0.00026697206,0.000167538,0.00012016962,0.010736363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99489635,0.0029901685,0.00018114198,0.00074445095,0.00046319704,0.0007246329],"domain_scores_gemma":[0.93600285,0.052460823,0.0065481854,0.0019658753,0.001715097,0.001307192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01699047,0.0015074844,0.0029244742,0.0022562377,0.0013166305,0.0034377477,0.0027348709,0.0039259773,0.0066634407],"category_scores_gemma":[0.05607495,0.0008565742,0.0017267549,0.0014828044,0.0051946263,0.0042580795,0.0033346796,0.004310806,0.00068679726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001884943,0.0001779528,0.009560583,0.00019512833,0.00024119586,0.0004901654,0.0004311087,0.5715205,0.00071320275,0.39310962,0.0034474423,0.019924585],"study_design_scores_gemma":[0.000023575236,0.00004118713,0.0007841609,0.000038463077,0.00003320275,0.00003637321,0.00005394326,0.8898204,0.00010410456,0.10861086,0.00042639414,0.000027427126],"about_ca_topic_score_codex":0.008211491,"about_ca_topic_score_gemma":0.004232739,"teacher_disagreement_score":0.01699047,"about_ca_system_score_codex":0.0028522778,"about_ca_system_score_gemma":0.0017925466,"threshold_uncertainty_score":0.08985525},"labels":[],"label_agreement":null},{"id":"W4394775968","doi":"10.48550/arxiv.2404.06516","title":"Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Regret; Nash equilibrium; Mathematical optimization; Best response; Correlated equilibrium; Computer science; Sublinear function; Epsilon-equilibrium; Convergence (economics); Markov chain; Stackelberg competition; Markov decision process; Flexibility (engineering); Mathematical economics; Mathematics; Markov process; Game theory; Equilibrium selection; Repeated game; Economics; Statistics; Discrete mathematics","score_opus":0.12614915939140928,"score_gpt":0.29944468377243866,"score_spread":0.17329552438102938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394775968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054989994,0.00048053282,0.9366806,0.00080176955,0.000051334173,0.00010470483,0.00012236356,0.0003461709,0.006422521],"genre_scores_gemma":[0.8627475,0.0005056373,0.13142787,0.00035187587,0.00006527232,0.00031581588,0.00017274499,0.00018910185,0.0042242003],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968401,0.0016940017,0.00010848452,0.00045781946,0.00043321608,0.00046629517],"domain_scores_gemma":[0.9843785,0.0130722225,0.0007348145,0.0006459665,0.00064799667,0.00052052015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004091364,0.0015481116,0.0019868503,0.00075151905,0.0010145878,0.0018857484,0.0018545099,0.0017836161,0.0030945044],"category_scores_gemma":[0.02618642,0.00069078367,0.000915043,0.0008254758,0.0020851078,0.0034590585,0.00223915,0.0026058473,0.00065752363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028618195,0.00012214592,0.00093393837,0.00017496878,0.000065760636,0.00011472414,0.00012889253,0.8252498,0.0011545649,0.14736569,0.0018516183,0.022551723],"study_design_scores_gemma":[0.00002222234,0.000029744808,0.00006541277,0.0000115291505,0.000005555209,0.000021945962,0.000015121752,0.9370852,0.00031650488,0.06220012,0.0002197171,0.0000068862487],"about_ca_topic_score_codex":0.0034893402,"about_ca_topic_score_gemma":0.0036713977,"teacher_disagreement_score":0.004091364,"about_ca_system_score_codex":0.0019084185,"about_ca_system_score_gemma":0.002537167,"threshold_uncertainty_score":0.0216375},"labels":[],"label_agreement":null},{"id":"W4394780679","doi":"10.48550/arxiv.2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Prior probability; Machine learning; Reinforcement learning; Artificial intelligence; Regret; Bayesian probability; Principle of maximum entropy; Posterior probability; Task (project management); Entropy (arrow of time); Engineering","score_opus":0.35285953384187685,"score_gpt":0.360209135595926,"score_spread":0.00734960175404914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394780679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20406574,0.00059973315,0.78706646,0.0021600095,0.00008380043,0.00018353724,0.00027603304,0.00042954928,0.0051351446],"genre_scores_gemma":[0.9364232,0.0002356474,0.05922543,0.00025592337,0.00007259631,0.00023456018,0.00020310821,0.00005288207,0.0032966288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971294,0.0015533966,0.00009429948,0.00064944517,0.00026726915,0.00030634287],"domain_scores_gemma":[0.96597934,0.029480895,0.0017634823,0.0011354142,0.00060184347,0.0010390569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005476256,0.0013087471,0.0021630824,0.0004357107,0.00060843624,0.0014500066,0.0019855732,0.0023839048,0.004664248],"category_scores_gemma":[0.024682336,0.0008380369,0.00091918005,0.00058589946,0.002092659,0.002823418,0.0019738993,0.0035879656,0.00050333125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005335179,0.00021599965,0.0014445513,0.0001385613,0.00009396553,0.00018621614,0.00022448697,0.93546206,0.00068530475,0.040092047,0.00078757823,0.020135649],"study_design_scores_gemma":[0.00006411971,0.0000543555,0.00016885159,0.00001197285,0.000009799756,0.000012740816,0.00001761974,0.9705418,0.00026654804,0.028608726,0.0002331599,0.000010197932],"about_ca_topic_score_codex":0.005226127,"about_ca_topic_score_gemma":0.0035054968,"teacher_disagreement_score":0.005476256,"about_ca_system_score_codex":0.0016618654,"about_ca_system_score_gemma":0.0018025477,"threshold_uncertainty_score":0.02896154},"labels":[],"label_agreement":null},{"id":"W4396780329","doi":"10.1016/j.jfranklin.2024.106884","title":"Online composite optimization with time-varying regularizers","year":2024,"lang":"en","type":"article","venue":"Journal of the Franklin Institute","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Regret; Metric (unit); Path (computing); Convex optimization; Upper and lower bounds; Function (biology); Regular polygon; Variation (astronomy); Convex function; Mathematical optimization; Mathematics; Computer science; Optimization problem; Online algorithm; Combinatorics; Statistics; Mathematical analysis; Physics; Engineering","score_opus":0.0543017719601523,"score_gpt":0.3727089263373512,"score_spread":0.3184071543771989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396780329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016098894,0.00046400487,0.97894627,0.00045650714,0.00021081527,0.00003530129,0.00008092886,0.00024518682,0.0034621859],"genre_scores_gemma":[0.7113846,0.0008106426,0.26951647,0.000396293,0.0008119251,0.00022252114,0.00033511303,0.0002757895,0.016246641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794704,0.00084761035,0.000107210784,0.00046244884,0.00041015205,0.00022557256],"domain_scores_gemma":[0.98824024,0.009355126,0.0005426573,0.0008252154,0.0007303526,0.0003064043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039452664,0.0017892256,0.0022502441,0.000809236,0.0005908298,0.0025097309,0.0017000693,0.0021714082,0.004470748],"category_scores_gemma":[0.015686162,0.0009431105,0.0008514719,0.0014080469,0.0018565526,0.003560563,0.0025892747,0.0032684759,0.0009788483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001045106,0.00029748157,0.0005557354,0.0002522318,0.00012252487,0.00013216853,0.000060952145,0.8345932,0.0025628991,0.084802285,0.0044085826,0.07116677],"study_design_scores_gemma":[0.000020585192,0.000047714348,0.000048272137,0.000006437549,0.000009074798,0.000012262475,0.000004897933,0.98618686,0.00049205427,0.012909168,0.00025598088,0.000006709113],"about_ca_topic_score_codex":0.0015754896,"about_ca_topic_score_gemma":0.0022005024,"teacher_disagreement_score":0.004470748,"about_ca_system_score_codex":0.0010110274,"about_ca_system_score_gemma":0.0018172209,"threshold_uncertainty_score":0.020864785},"labels":[],"label_agreement":null},{"id":"W4396982365","doi":"10.1109/tdsc.2024.3401836","title":"A Differentially Private Approach for Budgeted Combinatorial Multi-Armed Bandits","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Mathematical economics; Operations research; Economics; Mathematics","score_opus":0.08362743912680343,"score_gpt":0.38310144994046785,"score_spread":0.2994740108136644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396982365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009901292,0.00046689724,0.984624,0.00088093977,0.00007927504,0.00012258961,0.00019890346,0.00026620767,0.003459872],"genre_scores_gemma":[0.789478,0.0012697475,0.19952027,0.0010481963,0.00031543055,0.0007416165,0.0003615053,0.0002470312,0.0070181764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99276614,0.004127656,0.0002960524,0.00096024125,0.0012197014,0.00063012546],"domain_scores_gemma":[0.98082596,0.014077424,0.0016619932,0.002132429,0.0007273376,0.00057493505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008604017,0.0020653985,0.0026257157,0.0010396393,0.0009766718,0.0035271975,0.003538508,0.0029221796,0.00503012],"category_scores_gemma":[0.030869713,0.0010424793,0.0014324446,0.001934621,0.0031191423,0.0047225296,0.0033626857,0.005270358,0.0009804855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054655405,0.00018871675,0.0007970909,0.0002403996,0.000120804514,0.00023682983,0.00020966018,0.69422907,0.0024519812,0.26280382,0.003242824,0.03493227],"study_design_scores_gemma":[0.000060622922,0.00007217835,0.0000986117,0.00004546322,0.000022957982,0.0000647917,0.000021401886,0.8534988,0.0007902019,0.1440376,0.0012616551,0.000025675456],"about_ca_topic_score_codex":0.0013229684,"about_ca_topic_score_gemma":0.0010888485,"teacher_disagreement_score":0.008604017,"about_ca_system_score_codex":0.0030416066,"about_ca_system_score_gemma":0.0026909886,"threshold_uncertainty_score":0.04550296},"labels":[],"label_agreement":null},{"id":"W4399452441","doi":"10.2139/ssrn.4851778","title":"LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Content (measure theory); Online learning; Algorithm; Artificial intelligence; Multimedia; Mathematics","score_opus":0.18847935546344036,"score_gpt":0.4652270319985441,"score_spread":0.27674767653510374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399452441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004328441,0.00014386736,0.9730945,0.00028414762,0.00012001131,0.00018617946,0.0004491324,0.019572714,0.0018209545],"genre_scores_gemma":[0.10501335,0.00006671371,0.8845704,0.0004608705,0.0001351965,0.0010102278,0.0014452474,0.0012730713,0.006024892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971521,0.0014009337,0.00015377805,0.0004918284,0.000593783,0.0002075854],"domain_scores_gemma":[0.9932191,0.0035951016,0.00032932337,0.0015486926,0.0009455996,0.00036235317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040569785,0.0013608703,0.0015176458,0.002079665,0.0010624161,0.0019243273,0.0043657133,0.0038120558,0.026304428],"category_scores_gemma":[0.020031316,0.0006386236,0.0008778751,0.0016637889,0.0010149054,0.0033532174,0.0038630995,0.003032351,0.013473408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001486186,0.00067181024,0.0012585124,0.0003123929,0.00012310737,0.00011507635,0.000090212896,0.07223385,0.00924267,0.019009773,0.03665599,0.85880053],"study_design_scores_gemma":[0.0001901719,0.00014097578,0.00019518641,0.000018472982,0.000018238132,0.000042479813,0.000020264679,0.97069204,0.0052100644,0.01905388,0.004398053,0.000020131096],"about_ca_topic_score_codex":0.0022089886,"about_ca_topic_score_gemma":0.0038096302,"teacher_disagreement_score":0.026304428,"about_ca_system_score_codex":0.001353615,"about_ca_system_score_gemma":0.0027360376,"threshold_uncertainty_score":0.08799708},"labels":[],"label_agreement":null},{"id":"W4399486984","doi":"10.1109/tnnls.2024.3373749","title":"Off-Policy Prediction Learning: An Empirical Study of Online Algorithms","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"DeepMind; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Machine learning; Artificial intelligence; Empirical research; Algorithm; Mathematics; Statistics","score_opus":0.09340242677426551,"score_gpt":0.42801860975608086,"score_spread":0.33461618298181534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399486984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44329408,0.009360685,0.5355562,0.0023792211,0.00023083514,0.00043211188,0.00047391857,0.0008528509,0.0074200854],"genre_scores_gemma":[0.9186867,0.0014854022,0.0772456,0.00029783387,0.00011592791,0.0003653124,0.00055327325,0.0001798893,0.0010700976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991546,0.0049008457,0.0005692848,0.0013777171,0.0012521524,0.0003540687],"domain_scores_gemma":[0.806066,0.17601442,0.0047706678,0.007866136,0.0044757654,0.00080691645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019755377,0.0014421241,0.0013164725,0.0015749526,0.0007861583,0.0016203538,0.0021713637,0.0020865987,0.0016218735],"category_scores_gemma":[0.12070854,0.0005990166,0.0010276684,0.0012204894,0.0026819764,0.0053118626,0.0014331419,0.003946389,0.00024745197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000841257,0.0010331866,0.032443047,0.00079387584,0.00034710128,0.00014484064,0.00038175352,0.75557196,0.0011393795,0.037771493,0.003551195,0.165981],"study_design_scores_gemma":[0.000042716758,0.00029854153,0.0025619145,0.00009574348,0.000027504968,0.00009435255,0.00008163182,0.98203456,0.0008557993,0.013123607,0.00076304795,0.000020572019],"about_ca_topic_score_codex":0.0035428049,"about_ca_topic_score_gemma":0.0016767867,"teacher_disagreement_score":0.019755377,"about_ca_system_score_codex":0.001968049,"about_ca_system_score_gemma":0.0012997048,"threshold_uncertainty_score":0.1044777},"labels":[],"label_agreement":null},{"id":"W4399688013","doi":"10.1145/3673660.3655074","title":"Online Conversion with Switching Costs: Robust and Learning-Augmented Algorithms","year":2024,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universitas Brawijaya","keywords":"Computer science; Online algorithm; Purchasing; Maximization; Competitive analysis; Function (biology); Minification; Time horizon; Intersection (aeronautics); Baseline (sea); Benchmark (surveying); Mathematical optimization; Algorithm; Mathematics; Economics","score_opus":0.19324229646391108,"score_gpt":0.45433722490865697,"score_spread":0.2610949284447459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399688013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022443987,0.0008456466,0.96802956,0.0008770703,0.00012867624,0.00014290866,0.00012436952,0.0011840377,0.0062237624],"genre_scores_gemma":[0.66777295,0.00071010226,0.3244257,0.00062804064,0.00026874672,0.00031917932,0.00038041928,0.0003392864,0.0051555545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724495,0.0010105866,0.00016016432,0.00059597404,0.0005594892,0.00042890207],"domain_scores_gemma":[0.9890469,0.007925375,0.00091779267,0.001108336,0.0006866248,0.00031492626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041515944,0.001930078,0.0024575244,0.0010478282,0.0007940393,0.0034262664,0.0036873608,0.0028654784,0.004615378],"category_scores_gemma":[0.017054427,0.0008557658,0.0010865207,0.0019323125,0.0019575153,0.004915238,0.0022019784,0.004127383,0.0009416644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022567734,0.00027857837,0.0006933587,0.00010904075,0.000049773742,0.000043139964,0.000051956493,0.892914,0.00050423446,0.027718624,0.0027361126,0.074675545],"study_design_scores_gemma":[0.000017146825,0.00002727465,0.00004404977,0.0000062985564,0.000005550426,0.000012275699,0.000007083103,0.9882301,0.00020979188,0.011172053,0.00026377087,0.0000045354254],"about_ca_topic_score_codex":0.0043774648,"about_ca_topic_score_gemma":0.003024339,"teacher_disagreement_score":0.004615378,"about_ca_system_score_codex":0.0020703007,"about_ca_system_score_gemma":0.0030706208,"threshold_uncertainty_score":0.021956027},"labels":[],"label_agreement":null},{"id":"W4401813859","doi":"10.1007/s10107-024-02130-y","title":"Machine learning augmented branch and bound for mixed integer linear programming","year":2024,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Government of Canada; Polytechnique Montréal","keywords":"Integer programming; Mathematics; Branch and bound; Branch and cut; Branch and price; Linear programming; Integer (computer science); Mathematical optimization; Numerical analysis; Computer science; Mathematical analysis","score_opus":0.09935322029303427,"score_gpt":0.4338918460942113,"score_spread":0.334538625801177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401813859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039624567,0.0009511942,0.9878983,0.00051925937,0.00012361935,0.000054650853,0.00007269494,0.00054596626,0.0058718827],"genre_scores_gemma":[0.34213498,0.0015905092,0.6474007,0.0006242528,0.00045804016,0.00062219275,0.0005471859,0.00041348685,0.006208766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976676,0.0011930709,0.000094524024,0.00024459793,0.0005976256,0.0002024679],"domain_scores_gemma":[0.991663,0.006512837,0.0005458965,0.00037021592,0.00075697893,0.00015110253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045882524,0.0017634546,0.002242981,0.0012650422,0.0006747115,0.0029481244,0.0016407665,0.0015049415,0.0067432714],"category_scores_gemma":[0.012800988,0.0007227475,0.00091570977,0.0019302407,0.0014831185,0.0018875307,0.0019677202,0.003954258,0.0017372626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008518792,0.00007659952,0.0003540028,0.00016401136,0.00004355033,0.000036463603,0.000030817704,0.8793586,0.00029034485,0.054174103,0.0034246582,0.061961677],"study_design_scores_gemma":[0.000005138494,0.000010843504,0.000017087312,0.000016220629,0.0000026106738,0.0000041209532,0.000002055279,0.9841769,0.00009805117,0.01502062,0.00064427743,0.0000021872072],"about_ca_topic_score_codex":0.0028897102,"about_ca_topic_score_gemma":0.0025483866,"teacher_disagreement_score":0.0067432714,"about_ca_system_score_codex":0.0015397691,"about_ca_system_score_gemma":0.0021860267,"threshold_uncertainty_score":0.02426523},"labels":[],"label_agreement":null},{"id":"W4401879294","doi":"10.1109/tnet.2024.3444593","title":"Game-Theoretic Bandits for Network Optimization With High-Probability Swap-Regret Upper Bounds","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Networking","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"British Columbia Knowledge Development Fund; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Regret; Swap (finance); Computer science; Mathematical optimization; Mathematical economics; Upper and lower bounds; Mathematics; Economics; Machine learning","score_opus":0.0798903136994101,"score_gpt":0.37092698617727515,"score_spread":0.291036672477865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401879294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01673554,0.002142286,0.96917033,0.001007102,0.00016938207,0.000089332,0.00013912993,0.00035615952,0.010190837],"genre_scores_gemma":[0.840534,0.0032176904,0.14050056,0.000931666,0.00049707975,0.0006105777,0.00035760264,0.0003369714,0.013013775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99717295,0.0014673434,0.00010245906,0.00035499776,0.0004923221,0.00040989625],"domain_scores_gemma":[0.9877907,0.009800115,0.0008442584,0.00050717936,0.00065570977,0.00040201488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053720814,0.0030081775,0.00318886,0.0011259592,0.0011882631,0.002939799,0.0024157406,0.002635127,0.004967927],"category_scores_gemma":[0.017983826,0.0009964363,0.0012295195,0.0015186043,0.0028296947,0.004316083,0.002641085,0.0047941953,0.00093586056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014017176,0.00010232334,0.0004712358,0.00017115993,0.00007003073,0.00008311644,0.000075306525,0.86635405,0.0004665815,0.11847174,0.0024657717,0.011128481],"study_design_scores_gemma":[0.000014402621,0.000029943387,0.00005663532,0.000018007087,0.000012529239,0.000010984745,0.000011160806,0.95692104,0.00012471355,0.0422826,0.0005109295,0.0000069356806],"about_ca_topic_score_codex":0.0039285123,"about_ca_topic_score_gemma":0.0031751266,"teacher_disagreement_score":0.0053720814,"about_ca_system_score_codex":0.0028233859,"about_ca_system_score_gemma":0.0019807382,"threshold_uncertainty_score":0.028410614},"labels":[],"label_agreement":null},{"id":"W4402027991","doi":"10.2139/ssrn.4939739","title":"Efficient Task Scheduling in Cloud Computing Using a Cnn-Enhanced Sine Cosine Harris Hawk Optimization Algorithm","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Cloud computing; Computer science; Trigonometric functions; Sine; Algorithm; Scheduling (production processes); Discrete cosine transform; Mathematical optimization; Artificial intelligence; Mathematics; Operating system; Geometry","score_opus":0.04720138436569951,"score_gpt":0.39270563365660033,"score_spread":0.34550424929090084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402027991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09530578,0.0005929821,0.89301133,0.00046903294,0.0002727649,0.00010421139,0.00014050055,0.0010718919,0.0090315],"genre_scores_gemma":[0.78898406,0.00013348284,0.20581986,0.00017487771,0.00007844897,0.000088842455,0.00016607424,0.00015533977,0.0043989643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979,0.000029522234,0.000009879379,0.000053741765,0.000049739992,0.00006717427],"domain_scores_gemma":[0.9996846,0.0001072108,0.00003120774,0.000040435567,0.00008683926,0.00004970592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041930503,0.00043287672,0.0007759953,0.00026594562,0.000495293,0.0007061017,0.0010387033,0.0005549288,0.0035435439],"category_scores_gemma":[0.0012358292,0.00024405916,0.0003484099,0.0006303408,0.00030254043,0.00061213615,0.00063751015,0.00060140557,0.00039923345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024978595,0.0000765495,0.0007475167,0.000055839264,0.000027609958,0.000058464604,0.000032228403,0.8845398,0.0049516736,0.0059471983,0.0041936487,0.09911978],"study_design_scores_gemma":[0.0000058435576,0.000008389922,0.00004267936,8.601035e-7,0.0000017519658,0.0000036396107,0.000003308475,0.9987631,0.00025944953,0.0007631102,0.00014684632,0.00000108858],"about_ca_topic_score_codex":0.01587657,"about_ca_topic_score_gemma":0.019268475,"teacher_disagreement_score":0.01587657,"about_ca_system_score_codex":0.00093659776,"about_ca_system_score_gemma":0.0023252734,"threshold_uncertainty_score":0.03156829},"labels":[],"label_agreement":null},{"id":"W4402158975","doi":"10.1109/icc51166.2024.10623091","title":"Online Optimization for Network Resource Allocation and Comparison with Reinforcement Learning Techniques","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Resource allocation; Resource management (computing); Resource (disambiguation); Artificial intelligence; Distributed computing; Computer network","score_opus":0.08962090951805965,"score_gpt":0.4361140075983547,"score_spread":0.34649309808029505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402158975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06138748,0.0051950226,0.9223147,0.0011708833,0.00025641674,0.00015535415,0.0000633289,0.0007665063,0.008690403],"genre_scores_gemma":[0.86955243,0.0014152323,0.1257525,0.00030847685,0.00018708229,0.00018600882,0.00009563607,0.00012858064,0.0023739636],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979976,0.0010648656,0.00007933588,0.0002322158,0.00043720336,0.00018879009],"domain_scores_gemma":[0.9895132,0.008767803,0.00044302302,0.0004351566,0.0006387719,0.0002019862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004521507,0.0011838581,0.0019751377,0.0010395587,0.0004909746,0.0010724278,0.0016190251,0.0016736622,0.002398897],"category_scores_gemma":[0.013061684,0.00038941094,0.00054959813,0.0009600121,0.0012618239,0.0020176317,0.0012027966,0.0021617457,0.0002658787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116067444,0.0001320432,0.00031688146,0.00006411871,0.000035020745,0.000016459806,0.000014367867,0.9652569,0.0001670791,0.0055513117,0.00047229117,0.027857523],"study_design_scores_gemma":[0.000008045871,0.0000179173,0.000033100416,0.0000035746266,0.0000030056854,0.000003082623,0.0000022592237,0.99841344,0.000058981936,0.0013703716,0.0000847373,0.0000015003902],"about_ca_topic_score_codex":0.006302405,"about_ca_topic_score_gemma":0.0028718547,"teacher_disagreement_score":0.006302405,"about_ca_system_score_codex":0.001772266,"about_ca_system_score_gemma":0.0017949211,"threshold_uncertainty_score":0.02391231},"labels":[],"label_agreement":null},{"id":"W4402177679","doi":"10.1007/978-3-031-71033-9_23","title":"Matroid Bayesian Online Selection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Matroid; Selection (genetic algorithm); Bayesian probability; Artificial intelligence; Machine learning; Mathematics; Discrete mathematics","score_opus":0.055674133154967324,"score_gpt":0.3871011574410021,"score_spread":0.33142702428603477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402177679","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009849796,0.002367652,0.8768477,0.0017758085,0.0004985297,0.000091236776,0.0006073146,0.0009922808,0.106969796],"genre_scores_gemma":[0.39311758,0.0036680219,0.35318953,0.0015624879,0.0019889271,0.00039058793,0.0020969266,0.0009938084,0.24299209],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898785,0.00035764682,0.000031715335,0.00016608521,0.00037504593,0.00008167282],"domain_scores_gemma":[0.99822754,0.0009934626,0.000078899444,0.00037226526,0.00022127388,0.000106691696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012663713,0.0006947651,0.0010833787,0.0006589649,0.000452916,0.0015177968,0.0013664607,0.0009841907,0.02407725],"category_scores_gemma":[0.004937526,0.00041943812,0.00043086358,0.0015509578,0.00061998965,0.0017323912,0.0012447372,0.0019040385,0.00662781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033708758,0.00015928753,0.0003880711,0.00021815815,0.000055725508,0.00010936286,0.00005666479,0.060214795,0.0029146124,0.33738667,0.10198703,0.49617264],"study_design_scores_gemma":[0.00006472185,0.00012708157,0.0004612294,0.000062165935,0.000030097308,0.0003343983,0.00002609598,0.50020623,0.0023004229,0.44977298,0.046586618,0.000027938597],"about_ca_topic_score_codex":0.00054061133,"about_ca_topic_score_gemma":0.0009531157,"teacher_disagreement_score":0.02407725,"about_ca_system_score_codex":0.000812887,"about_ca_system_score_gemma":0.000749199,"threshold_uncertainty_score":0.08054638},"labels":[],"label_agreement":null},{"id":"W4403321765","doi":"10.1007/s11432-023-4086-5","title":"Improved dynamic regret of distributed online multiple Frank-Wolfe convex optimization","year":2024,"lang":"en","type":"article","venue":"Science China Information Sciences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Computer science; Regular polygon; Mathematical optimization; Mathematics; Machine learning; Geometry","score_opus":0.04907183590157569,"score_gpt":0.41944849127908757,"score_spread":0.37037665537751185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403321765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026506519,0.0008091262,0.96307635,0.0010468519,0.00030625035,0.000068072026,0.00019183055,0.00040836635,0.0075865565],"genre_scores_gemma":[0.853579,0.0005442429,0.1310237,0.00056983106,0.0004259782,0.00022515372,0.00035835296,0.00028410245,0.012989693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966432,0.0011556657,0.00012879107,0.00061743526,0.0008567606,0.000598249],"domain_scores_gemma":[0.9940084,0.0037587858,0.0003572597,0.0006118749,0.000928459,0.0003352819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049231527,0.002170931,0.0031115543,0.0007875853,0.0009908708,0.0026032089,0.0031316173,0.0025563051,0.0052549513],"category_scores_gemma":[0.013827924,0.0010732291,0.0008819969,0.0014518151,0.0018498369,0.00340656,0.0031640215,0.003576596,0.0008779212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003751989,0.0001348933,0.00036973952,0.00013241524,0.000051090807,0.00013153347,0.000054387176,0.9432433,0.0011020207,0.02718829,0.004080914,0.023136199],"study_design_scores_gemma":[0.000015486394,0.000024314679,0.000053083128,0.0000050611593,0.000005794856,0.000017917855,0.0000050301414,0.99508494,0.00018411527,0.004442729,0.00015638974,0.0000050988992],"about_ca_topic_score_codex":0.0045975107,"about_ca_topic_score_gemma":0.004232518,"teacher_disagreement_score":0.0052549513,"about_ca_system_score_codex":0.0024248587,"about_ca_system_score_gemma":0.0034717594,"threshold_uncertainty_score":0.026036441},"labels":[],"label_agreement":null},{"id":"W4403712928","doi":"10.2139/ssrn.4997308","title":"Diversified Learning: Bayesian Control with Multiple Biased Information Sources","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian probability; Control (management); Computer science; Bayesian inference; Econometrics; Artificial intelligence; Machine learning; Economics","score_opus":0.029570063751934193,"score_gpt":0.33137014164052725,"score_spread":0.30180007788859303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403712928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014758185,0.00063690206,0.98096484,0.001002783,0.00007294403,0.000065474705,0.00008191671,0.000121494035,0.0022954983],"genre_scores_gemma":[0.71854544,0.0017533102,0.26751518,0.0008776192,0.0007495973,0.0005730341,0.0003362178,0.00021374058,0.009435876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867553,0.00786364,0.00055988826,0.0022380764,0.0017498544,0.00083319144],"domain_scores_gemma":[0.9089008,0.07808211,0.004480717,0.004667941,0.0028285508,0.001039893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02178302,0.002242643,0.0044959565,0.0026441186,0.0012978888,0.0061446554,0.0049256366,0.0055113644,0.0045655156],"category_scores_gemma":[0.10430357,0.002668898,0.0013531329,0.0035648034,0.005976734,0.0109686935,0.0068701194,0.0060142074,0.0006594544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007405147,0.00018939242,0.0011629685,0.00029516974,0.00038052618,0.00017129738,0.00023991475,0.47666663,0.00061629055,0.45223606,0.0021207232,0.06518055],"study_design_scores_gemma":[0.000087258806,0.00003496307,0.00013532808,0.000042826458,0.000044455664,0.000028220255,0.000013031196,0.7037603,0.00028152822,0.2951287,0.00041097385,0.00003234422],"about_ca_topic_score_codex":0.0035394246,"about_ca_topic_score_gemma":0.002357862,"teacher_disagreement_score":0.02178302,"about_ca_system_score_codex":0.0028678745,"about_ca_system_score_gemma":0.002772368,"threshold_uncertainty_score":0.115201},"labels":[],"label_agreement":null},{"id":"W4403918350","doi":"10.1109/sm63044.2024.10733530","title":"A Contextual Multi-armed Bandit Approach to Personalized Trip Itinerary Planning","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Motors (Canada); University of Toronto","funders":"","keywords":"Computer science; Operations research; Artificial intelligence; Engineering","score_opus":0.31925255590611645,"score_gpt":0.49861399214305346,"score_spread":0.179361436236937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403918350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027320152,0.0010110403,0.96725065,0.00047334612,0.000084759915,0.00011386718,0.00018712535,0.0003225629,0.0032363692],"genre_scores_gemma":[0.7485423,0.0008003127,0.24678132,0.00030406992,0.00016837718,0.0003828227,0.00039852693,0.00008890794,0.0025332952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982318,0.0010707211,0.00006853297,0.00028675538,0.00015257212,0.00018967965],"domain_scores_gemma":[0.99770004,0.0016046719,0.00020977814,0.00011565797,0.00025921638,0.00011065575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019378444,0.0012500642,0.0015884232,0.0009340891,0.0006936127,0.0017457545,0.0017127775,0.0016989236,0.0034399752],"category_scores_gemma":[0.005181873,0.00070302916,0.00091011723,0.0015083997,0.00077605597,0.0011666056,0.0013458104,0.0016185028,0.00047157946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007391573,0.000044426928,0.0005192041,0.00005409266,0.000048689828,0.00003917344,0.00004403695,0.97579217,0.00025466434,0.0075628418,0.00047283722,0.015094075],"study_design_scores_gemma":[0.0000051642032,0.000023028455,0.00007684956,0.0000061903393,0.000009703948,0.0000062817576,0.000011057902,0.9970611,0.000064038126,0.002464002,0.00026860402,0.0000040155423],"about_ca_topic_score_codex":0.01653237,"about_ca_topic_score_gemma":0.01581983,"teacher_disagreement_score":0.01653237,"about_ca_system_score_codex":0.0012808163,"about_ca_system_score_gemma":0.0014381285,"threshold_uncertainty_score":0.03287226},"labels":[],"label_agreement":null},{"id":"W4404342998","doi":"10.48550/arxiv.2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données","keywords":"Computer science; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.1995701599587951,"score_gpt":0.36146541367314483,"score_spread":0.16189525371434973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404342998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010653088,0.00084421877,0.9852483,0.0005505118,0.000059964404,0.000064909116,0.000070626906,0.00018379073,0.0023245495],"genre_scores_gemma":[0.7462745,0.0021079497,0.24331176,0.00065722235,0.00031541332,0.00062559015,0.00034585423,0.00022421253,0.0061374204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765426,0.0013366565,0.000111666646,0.0003759094,0.0002860545,0.00023553193],"domain_scores_gemma":[0.98499054,0.012837505,0.00085859396,0.00047011254,0.00051304733,0.00033019626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00524169,0.0020192896,0.0028131665,0.001060366,0.0008101514,0.0025239019,0.0019842044,0.0023773469,0.00362671],"category_scores_gemma":[0.017468335,0.0010356031,0.0012269474,0.001546762,0.0027848803,0.0031454319,0.0020698642,0.0041445093,0.0005896973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012965447,0.000071930925,0.0005457355,0.000121646444,0.000057769794,0.000051121493,0.00007349331,0.9137378,0.00027091618,0.06394978,0.0011430912,0.01984715],"study_design_scores_gemma":[0.0000140648735,0.000026430178,0.000052948322,0.00001980811,0.000008874751,0.000009442214,0.00000961525,0.96186596,0.00012691399,0.037577495,0.00028154493,0.0000069121907],"about_ca_topic_score_codex":0.005373106,"about_ca_topic_score_gemma":0.0035151478,"teacher_disagreement_score":0.005373106,"about_ca_system_score_codex":0.0025031345,"about_ca_system_score_gemma":0.0022737212,"threshold_uncertainty_score":0.027721047},"labels":[],"label_agreement":null},{"id":"W4405974431","doi":"10.1109/pimrc59610.2024.10817426","title":"Edge Selection Non-Cooperative Game in IoT Edge Computing","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Edge computing; Selection (genetic algorithm); Internet of Things; Human–computer interaction; Artificial intelligence; Computer security","score_opus":0.10095882738346541,"score_gpt":0.46636873714286897,"score_spread":0.3654099097594036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405974431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15304163,0.00043106903,0.81949955,0.0016284486,0.00017526574,0.0002829676,0.000226931,0.00015750625,0.02455655],"genre_scores_gemma":[0.97427714,0.0001919813,0.019333228,0.00021552826,0.000038382495,0.00018845702,0.000052374868,0.00001601289,0.005686898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882835,0.0005380923,0.00003763351,0.0002009435,0.00014603273,0.00024902012],"domain_scores_gemma":[0.9982003,0.0011722859,0.00014261065,0.00008097736,0.00013126024,0.00027261165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010751263,0.0009180785,0.0011904308,0.0003250724,0.0008942462,0.0014275407,0.0016977685,0.0016092331,0.003101523],"category_scores_gemma":[0.0030617686,0.00029281172,0.0005158148,0.000448971,0.0014727259,0.0016189773,0.0018930446,0.0013418889,0.00032998563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007298869,0.00028627602,0.001841973,0.00018607615,0.000101037,0.0010465547,0.00042715043,0.76176035,0.0058985767,0.19644725,0.006167834,0.025107015],"study_design_scores_gemma":[0.000033120417,0.00007224498,0.00019737339,0.000010693406,0.000011620252,0.00007127676,0.00008445078,0.96184057,0.00033742609,0.036520258,0.00080695166,0.000013939609],"about_ca_topic_score_codex":0.0018769886,"about_ca_topic_score_gemma":0.0017609862,"teacher_disagreement_score":0.003101523,"about_ca_system_score_codex":0.0009814084,"about_ca_system_score_gemma":0.00087490893,"threshold_uncertainty_score":0.010375619},"labels":[],"label_agreement":null},{"id":"W4406033644","doi":"10.1287/opre.2021.0445","title":"Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback","year":2025,"lang":"en","type":"article","venue":"Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Monotone polygon; Computer science; Mathematical optimization; Online learning; Mathematical economics; Operations research; Mathematics; Multimedia; Machine learning","score_opus":0.13094003215085015,"score_gpt":0.4967886970957619,"score_spread":0.36584866494491175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406033644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053512458,0.0005748554,0.93956405,0.0008383371,0.000086688524,0.00011870089,0.00006948454,0.00033060947,0.0049048224],"genre_scores_gemma":[0.9262775,0.0003335255,0.06901416,0.00040158333,0.00008652087,0.00026940648,0.00011222791,0.00009001621,0.0034150828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974148,0.0013189595,0.00012328013,0.00040201715,0.00036336403,0.0003774621],"domain_scores_gemma":[0.9848999,0.012211841,0.00092129846,0.00062476133,0.00081758894,0.0005245902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004613654,0.002018967,0.002519536,0.00067944324,0.00083763327,0.0018178619,0.0021030207,0.0021203917,0.001951915],"category_scores_gemma":[0.022417178,0.00089300657,0.0007585363,0.0005797692,0.0024613172,0.0028252418,0.0022289387,0.0028406708,0.0003863854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002587279,0.00016613884,0.0008531098,0.00011633743,0.00007123667,0.00008970367,0.00008987767,0.9365904,0.0005468879,0.043875933,0.0009715773,0.016370112],"study_design_scores_gemma":[0.000013540649,0.000028538227,0.00004839188,0.0000072546613,0.0000049704786,0.000007422247,0.000006374155,0.98789716,0.00015459742,0.011739009,0.000087490436,0.000005192352],"about_ca_topic_score_codex":0.004260211,"about_ca_topic_score_gemma":0.0032371047,"teacher_disagreement_score":0.004613654,"about_ca_system_score_codex":0.0018408666,"about_ca_system_score_gemma":0.0022836416,"threshold_uncertainty_score":0.024399638},"labels":[],"label_agreement":null},{"id":"W4406610289","doi":"10.1109/tac.2025.3532181","title":"Model Approximation in MDPs With Unbounded Per-Step Cost","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Innovation for Defence Excellence and Security","keywords":"Computer science; Mathematical optimization; Mathematics; Applied mathematics","score_opus":0.05376352359343873,"score_gpt":0.3732842671564823,"score_spread":0.31952074356304355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406610289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034217943,0.001210187,0.95629245,0.0014506932,0.000112464695,0.00012947668,0.00038272818,0.0005368282,0.0056672115],"genre_scores_gemma":[0.8468094,0.0010225243,0.14404199,0.00036960785,0.00011142111,0.00042698573,0.00063811766,0.00014034183,0.006439525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998307,0.0007085661,0.00008629431,0.00035813256,0.00029204323,0.00024800305],"domain_scores_gemma":[0.99328655,0.0055109765,0.00043625504,0.00023523523,0.00031589944,0.00021506753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024835558,0.0017479414,0.0024380751,0.0007149367,0.00075517956,0.0020929808,0.0017417478,0.0023457555,0.0036661376],"category_scores_gemma":[0.010044675,0.0011390782,0.0012736,0.00092048163,0.0012296225,0.002128815,0.002021803,0.0029899208,0.00048561365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034194523,0.0000146793745,0.00016105257,0.000046463407,0.000018020553,0.0000295021,0.000016648479,0.989426,0.00004757578,0.007052742,0.00023899927,0.002913999],"study_design_scores_gemma":[0.00000916943,0.000008838605,0.00002328942,0.0000069691846,0.000004985808,0.0000043685513,0.00000640478,0.99296737,0.000058849706,0.0067099603,0.00019717118,0.000002750047],"about_ca_topic_score_codex":0.020845007,"about_ca_topic_score_gemma":0.012098966,"teacher_disagreement_score":0.020845007,"about_ca_system_score_codex":0.0027669617,"about_ca_system_score_gemma":0.0032429334,"threshold_uncertainty_score":0.04144734},"labels":[],"label_agreement":null},{"id":"W4407666409","doi":"10.1051/itmconf/20257301011","title":"Application of Multi-Armed Bandit Algorithm in Quantitative Finance","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.1175976055207516,"score_gpt":0.4653464346115648,"score_spread":0.34774882909081317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407666409","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01725001,0.0015109577,0.97581714,0.00045424735,0.000076987766,0.00006850843,0.00004627324,0.0005628043,0.0042130053],"genre_scores_gemma":[0.6814962,0.0012914363,0.31213918,0.00032373407,0.00013657994,0.00032443134,0.00019618787,0.00011255307,0.0039796303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986841,0.0006068458,0.000090389614,0.00021927246,0.00028691755,0.00011246295],"domain_scores_gemma":[0.99768126,0.0016725655,0.00017614795,0.000080998965,0.00033622194,0.000052741725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028912593,0.0010481152,0.001690994,0.0016772618,0.00088860636,0.001949908,0.0011334987,0.0018066604,0.0020785944],"category_scores_gemma":[0.0060289516,0.0006118547,0.0009950077,0.0016408345,0.0008513932,0.0010644002,0.001001898,0.0015036875,0.00037486656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052516956,0.00004887469,0.0013261125,0.00007622991,0.00010455067,0.000051208608,0.000049932565,0.92245954,0.00047161253,0.008564471,0.0006879732,0.06610702],"study_design_scores_gemma":[0.000003125437,0.000008217092,0.00008398845,0.0000047487633,0.000004442718,0.0000042631177,0.0000029906919,0.99801767,0.00008263935,0.0016087613,0.0001760419,0.0000030657923],"about_ca_topic_score_codex":0.018826827,"about_ca_topic_score_gemma":0.008185711,"teacher_disagreement_score":0.018826827,"about_ca_system_score_codex":0.0012726501,"about_ca_system_score_gemma":0.0018348256,"threshold_uncertainty_score":0.03743452},"labels":[],"label_agreement":null},{"id":"W4407727497","doi":"10.2139/ssrn.5123355","title":"Online Learning for Dynamic Service Mode Control","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Service (business); Mode (computer interface); Control (management); Process management; Business; Artificial intelligence; Human–computer interaction; Marketing","score_opus":0.044638952952109144,"score_gpt":0.4428699914955502,"score_spread":0.39823103854344105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407727497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03754723,0.00046955034,0.95144695,0.00074325653,0.0001685159,0.0000394965,0.00006118824,0.00028923896,0.009234654],"genre_scores_gemma":[0.9743266,0.00025303068,0.016300574,0.00016019102,0.00012302882,0.000059995375,0.000048198308,0.000053832922,0.008674529],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952483,0.00014276612,0.000019913468,0.000104752275,0.00010712601,0.00010067877],"domain_scores_gemma":[0.99597114,0.00321671,0.00019734768,0.0002034208,0.00030514225,0.00010618883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012710964,0.0006948678,0.0010080991,0.0004191565,0.00048724786,0.0011940935,0.00094860414,0.0011668352,0.007454089],"category_scores_gemma":[0.008073882,0.00028716328,0.00038216368,0.0005266477,0.0012027669,0.0015778315,0.0011731382,0.0019742486,0.00050545705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003111334,0.00024533187,0.00056160445,0.0001718958,0.00003944963,0.00006980032,0.00009961468,0.7696849,0.0017424462,0.12293817,0.0033341448,0.10080144],"study_design_scores_gemma":[0.000009155786,0.000022995133,0.000068171066,0.000005903116,0.0000037841708,0.000007170303,0.000004348482,0.96838355,0.00017250808,0.031074787,0.00024416257,0.0000034518548],"about_ca_topic_score_codex":0.003944425,"about_ca_topic_score_gemma":0.0028014837,"teacher_disagreement_score":0.007454089,"about_ca_system_score_codex":0.0010362432,"about_ca_system_score_gemma":0.0011133878,"threshold_uncertainty_score":0.024936438},"labels":[],"label_agreement":null},{"id":"W4408818067","doi":"10.1016/j.ejor.2025.03.011","title":"The multi-armed bandit problem under the mean-variance setting","year":2025,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Computer science; Mathematical optimization; Mathematics; Statistics; Econometrics; Economics","score_opus":0.23597087264581235,"score_gpt":0.5101706528117763,"score_spread":0.27419978016596397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408818067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021045087,0.0014936104,0.9700294,0.0016939703,0.00010668663,0.00018856353,0.00024561887,0.00024598997,0.00495109],"genre_scores_gemma":[0.7504591,0.0025026908,0.22862884,0.0011208331,0.00050927844,0.0012630224,0.0006701128,0.00022624624,0.014619841],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948619,0.002994131,0.00023369186,0.00086755556,0.0005582066,0.0004844857],"domain_scores_gemma":[0.9753871,0.020719215,0.0018121911,0.00065142976,0.0009729356,0.00045708273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010142263,0.0023408048,0.0047292174,0.001303307,0.0012194343,0.0039041669,0.0034970867,0.0057765124,0.0051148743],"category_scores_gemma":[0.029797085,0.0013727668,0.0014506709,0.002138016,0.0032180652,0.0044431207,0.0026544265,0.004905538,0.0012666851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023796181,0.00008320075,0.00085634354,0.00018240606,0.000091671696,0.000115762705,0.00008136694,0.90230423,0.00021875999,0.07896176,0.0019362974,0.014930161],"study_design_scores_gemma":[0.0000455011,0.000042163745,0.0001577987,0.000034885972,0.000015462776,0.000031040985,0.000016384769,0.947501,0.0001300568,0.051594328,0.00041529778,0.000016112343],"about_ca_topic_score_codex":0.0050224513,"about_ca_topic_score_gemma":0.0028466133,"teacher_disagreement_score":0.010142263,"about_ca_system_score_codex":0.0024790284,"about_ca_system_score_gemma":0.0024071753,"threshold_uncertainty_score":0.0536381},"labels":[],"label_agreement":null},{"id":"W4409365726","doi":"10.1609/aaai.v39i13.33507","title":"Every Bit Helps: Achieving the Optimal Distortion with a Few Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bit (key); Distortion (music); Computer science; Arithmetic; Algorithm; Theoretical computer science; Mathematics; Computer security; Telecommunications","score_opus":0.15755457449808338,"score_gpt":0.41326942252001436,"score_spread":0.255714848021931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409365726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14884691,0.007489408,0.76922095,0.015167679,0.0006121897,0.0006108577,0.0015604481,0.003092333,0.053399246],"genre_scores_gemma":[0.6941957,0.001562878,0.28953168,0.0020744249,0.0003231052,0.0004019855,0.00086860097,0.00068672624,0.010354923],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9890674,0.0053051612,0.00053053384,0.0014335947,0.002548908,0.0011144108],"domain_scores_gemma":[0.9623988,0.023752224,0.0015086741,0.009051255,0.0020338064,0.0012552218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007285973,0.002390324,0.0037682857,0.0012937523,0.0026620938,0.0048210365,0.0047870255,0.003442649,0.01155754],"category_scores_gemma":[0.05179727,0.0010407374,0.0015022442,0.0027807665,0.00334855,0.013546524,0.005623896,0.004949115,0.0038979982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062618577,0.0013365974,0.007002068,0.00091793376,0.000342205,0.00077651726,0.0017522391,0.18091227,0.019599155,0.28923193,0.047582526,0.4442847],"study_design_scores_gemma":[0.00043270076,0.0005930344,0.0017499273,0.0001517714,0.00016826566,0.0012447106,0.0010276686,0.5528362,0.010567792,0.4165839,0.014521779,0.00012225848],"about_ca_topic_score_codex":0.0050248224,"about_ca_topic_score_gemma":0.00492402,"teacher_disagreement_score":0.01155754,"about_ca_system_score_codex":0.0035858117,"about_ca_system_score_gemma":0.004248408,"threshold_uncertainty_score":0.038663864},"labels":[],"label_agreement":null},{"id":"W4410602017","doi":"10.6000/1929-6029.2025.14.28","title":"Response Adaptive Randomization Using Biomarkers with Exponentially Decreasing Probability Sequence","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequence (biology); Randomization; Exponential growth; Statistics; Mathematics; Computer science; Econometrics; Applied mathematics; Biology; Bioinformatics; Mathematical analysis; Clinical trial; Genetics","score_opus":0.2564553604632724,"score_gpt":0.5629981862205483,"score_spread":0.3065428257572759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410602017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014465331,0.00052855135,0.9828188,0.00050027255,0.00017410038,0.0005865665,0.00006955549,0.00018639826,0.0006703484],"genre_scores_gemma":[0.5171647,0.0009722644,0.47284874,0.0011249633,0.00033391884,0.0041190316,0.00020923285,0.000085562206,0.0031415746],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9552725,0.03833979,0.0008560401,0.0029833647,0.0018876342,0.00066067284],"domain_scores_gemma":[0.946608,0.044285107,0.0033932403,0.0028231088,0.0021375278,0.00075306953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0327724,0.0015862234,0.0027423801,0.0013708782,0.0004917029,0.0013232972,0.0021557165,0.0022212542,0.0045505464],"category_scores_gemma":[0.06204612,0.0006454788,0.0013963624,0.0011150541,0.002114527,0.0025388133,0.0014071527,0.002331189,0.000741455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0080526015,0.0013351202,0.007893186,0.0018084231,0.0009967526,0.000531217,0.0006091386,0.30630934,0.00905471,0.4189053,0.0029915632,0.24151255],"study_design_scores_gemma":[0.0022744788,0.0058739185,0.0016426151,0.00020362208,0.0003842708,0.00041995256,0.000079387486,0.8319469,0.004299211,0.14684114,0.005892186,0.0001422846],"about_ca_topic_score_codex":0.00033359445,"about_ca_topic_score_gemma":0.00018808467,"teacher_disagreement_score":0.0327724,"about_ca_system_score_codex":0.00097506604,"about_ca_system_score_gemma":0.0021081546,"threshold_uncertainty_score":0.1733191},"labels":[],"label_agreement":null},{"id":"W4410845474","doi":"10.1017/9780511820809.007","title":"Toppling conjectures","year":2015,"lang":"en","type":"other","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Geology; Geography","score_opus":0.29098476486513714,"score_gpt":0.5337833791020361,"score_spread":0.24279861423689897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410845474","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34036666,0.0019480437,0.16128033,0.0056851404,0.00065566803,0.0001679084,0.0012296695,0.00086562295,0.487801],"genre_scores_gemma":[0.9530278,0.00065034424,0.014433143,0.0011079902,0.00045122195,0.00014165782,0.0009366336,0.00014142996,0.029109642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980136,0.00040630755,0.000090102054,0.0005267426,0.00051260425,0.00045065983],"domain_scores_gemma":[0.99469936,0.0032610341,0.00043275495,0.0007107883,0.00037937783,0.00051664456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010896142,0.0007811167,0.00087400706,0.0009882282,0.0025508846,0.004204341,0.0016821584,0.0022087798,0.031940524],"category_scores_gemma":[0.010016747,0.0004937657,0.0009715021,0.0013422167,0.004287526,0.005637726,0.0024931568,0.0034809755,0.0028645683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008742225,0.000052089723,0.00088185974,0.00008467059,0.000015691265,0.00015049404,0.00031894067,0.0048162234,0.0006010747,0.9772909,0.005232999,0.01046762],"study_design_scores_gemma":[0.000030830422,0.000028483393,0.00038111088,0.00002639358,0.000008312857,0.00012310925,0.00013872042,0.012093224,0.00040411533,0.98019,0.006559749,0.000015785672],"about_ca_topic_score_codex":0.0013157763,"about_ca_topic_score_gemma":0.0010300943,"teacher_disagreement_score":0.031940524,"about_ca_system_score_codex":0.0015605177,"about_ca_system_score_gemma":0.00072326435,"threshold_uncertainty_score":0.1068517},"labels":[],"label_agreement":null},{"id":"W4411921768","doi":"10.1137/23m1592559","title":"Unsynchronized Decentralized Q-Learning: Two Timescale Analysis by Persistence","year":2025,"lang":"en","type":"article","venue":"SIAM Journal on Control and Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Persistence (discontinuity); Mathematics; Q-learning; Artificial intelligence; Computer science; Engineering; Geotechnical engineering","score_opus":0.023443965379088803,"score_gpt":0.36435067225376544,"score_spread":0.3409067068746766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411921768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15432438,0.0008511849,0.82395303,0.0030630545,0.00018757363,0.00007870961,0.00018026106,0.00040992518,0.016951973],"genre_scores_gemma":[0.9832675,0.0002661484,0.010686996,0.00020917697,0.000112893526,0.00006095239,0.000037736707,0.00009407238,0.005264477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921477,0.0002347571,0.00003385963,0.00017152494,0.00016874979,0.00017634705],"domain_scores_gemma":[0.99087185,0.0059455135,0.0009763039,0.0010253175,0.0007185309,0.00046249156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024609845,0.000510626,0.0011267698,0.0006028391,0.0006900145,0.0019389597,0.0017115396,0.0015638503,0.00693202],"category_scores_gemma":[0.018888041,0.0004889878,0.000669937,0.0006001413,0.002186446,0.0036551235,0.0027694693,0.002044449,0.00040516438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025353947,0.00012428679,0.0018434451,0.00018594792,0.00008346481,0.00019482011,0.0003041618,0.30003172,0.0035494661,0.6614775,0.0037770106,0.028174656],"study_design_scores_gemma":[0.000027128315,0.00003662866,0.0005247972,0.000011647866,0.000014480278,0.000033275865,0.000040990086,0.8680086,0.00026158895,0.13054058,0.00048413346,0.000016054],"about_ca_topic_score_codex":0.0017302535,"about_ca_topic_score_gemma":0.00083143386,"teacher_disagreement_score":0.00693202,"about_ca_system_score_codex":0.0012072864,"about_ca_system_score_gemma":0.001488595,"threshold_uncertainty_score":0.023189902},"labels":[],"label_agreement":null},{"id":"W4411946019","doi":"10.1145/3736252.3742659","title":"No-Regret Incentive-Compatible Online Learning under Exact Truthfulness with Non-Myopic Experts","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Leonard N. Stern School of Business, New York University","keywords":"Regret; Incentive; Computer science; Incentive compatibility; Machine learning; Microeconomics; Economics","score_opus":0.06397387203485884,"score_gpt":0.4264049429812383,"score_spread":0.3624310709463795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411946019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13935758,0.00069679494,0.84691334,0.0026056962,0.00013445306,0.00031925458,0.0005137442,0.00084071804,0.0086184405],"genre_scores_gemma":[0.92814976,0.00033132482,0.06528888,0.00049611216,0.00015013233,0.00030916583,0.00020085787,0.00009855041,0.0049752626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99439114,0.0028477474,0.00024541005,0.00096480787,0.00075617933,0.00079475937],"domain_scores_gemma":[0.9521791,0.0370593,0.0045172777,0.0036055294,0.0011115179,0.0015273194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009749956,0.002063524,0.0030288815,0.0006487908,0.0007489942,0.0022013383,0.0038900694,0.0033324617,0.004655837],"category_scores_gemma":[0.041483734,0.0011020084,0.0012478759,0.0008858179,0.0025798709,0.005398926,0.0022813582,0.0039512576,0.0006878112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013953627,0.00051862386,0.0017423563,0.0003766669,0.00016027957,0.00035684323,0.00031062044,0.7753277,0.0025963385,0.1832388,0.002902093,0.031074386],"study_design_scores_gemma":[0.00014877054,0.0001559273,0.00019829709,0.000021976306,0.000020809606,0.00006254475,0.00002230557,0.8736143,0.0006002118,0.12474256,0.00038665946,0.000025586443],"about_ca_topic_score_codex":0.0015529956,"about_ca_topic_score_gemma":0.0009907745,"teacher_disagreement_score":0.009749956,"about_ca_system_score_codex":0.0022129673,"about_ca_system_score_gemma":0.002669821,"threshold_uncertainty_score":0.051563382},"labels":[],"label_agreement":null},{"id":"W4411950882","doi":"10.1109/infocom55648.2025.11044606","title":"Faster Convergence for Unknown-Game Bandits","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Convergence (economics); Computer science; Mathematical optimization; Artificial intelligence; Mathematics; Economics","score_opus":0.15792765889689803,"score_gpt":0.519286465163955,"score_spread":0.361358806267057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411950882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061011106,0.0015286844,0.91412175,0.0011915494,0.00040740124,0.00014746218,0.00013573094,0.0006915188,0.020764776],"genre_scores_gemma":[0.74470913,0.0011636694,0.23001386,0.00087634136,0.0003236161,0.0004754291,0.00031120938,0.000822023,0.02130471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960174,0.0019796875,0.00014303718,0.00046101422,0.0007724803,0.0006263679],"domain_scores_gemma":[0.9577766,0.03585635,0.0009866874,0.0027463743,0.0018604991,0.000773497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008535767,0.0020166375,0.002814281,0.0017322643,0.0014625354,0.0037049374,0.0022345027,0.0028763248,0.013380079],"category_scores_gemma":[0.05584209,0.0009803623,0.0014978703,0.0013517278,0.0032654249,0.0059198425,0.0039183954,0.005165035,0.0021297033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077609025,0.00021859474,0.0012696981,0.0005041892,0.00015101113,0.00014600478,0.00043964287,0.44217765,0.0035683932,0.489108,0.006958059,0.05468277],"study_design_scores_gemma":[0.00005832742,0.000052983985,0.00017613372,0.00006652877,0.000019834366,0.000044041033,0.000052576022,0.8403036,0.00069320906,0.15744756,0.0010680367,0.000017105158],"about_ca_topic_score_codex":0.00350368,"about_ca_topic_score_gemma":0.003643739,"teacher_disagreement_score":0.013380079,"about_ca_system_score_codex":0.0022830823,"about_ca_system_score_gemma":0.0021143367,"threshold_uncertainty_score":0.045141995},"labels":[],"label_agreement":null},{"id":"W4413143600","doi":"10.1016/j.automatica.2025.112499","title":"Distributed mirror descent for online bandit saddle point problem","year":2025,"lang":"en","type":"article","venue":"Automatica","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Saddle point; Descent (aeronautics); Saddle; Computer science; Mathematical optimization; Point (geometry); Mathematics; Control theory (sociology); Distributed computing; Artificial intelligence; Engineering; Geometry; Control (management); Aerospace engineering","score_opus":0.10802154007385688,"score_gpt":0.46627725848189344,"score_spread":0.35825571840803655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413143600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020124698,0.00029746373,0.9755225,0.000605398,0.00008450239,0.00004913137,0.00006608814,0.00019560833,0.0030546945],"genre_scores_gemma":[0.77908397,0.00062772987,0.20128727,0.00049306906,0.00024813836,0.0005286313,0.0003733514,0.00039311452,0.016964702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913496,0.0003961242,0.00003761255,0.00015418336,0.00016969714,0.00010739708],"domain_scores_gemma":[0.99392915,0.0046410025,0.00034712907,0.00035362213,0.00048503143,0.00024397603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026748537,0.0014459381,0.002394651,0.00075473427,0.0008784839,0.002097572,0.0019315354,0.0028053108,0.0052812537],"category_scores_gemma":[0.013795721,0.0010043781,0.00083036156,0.0007512745,0.0018174846,0.0023507334,0.0026173561,0.0027297358,0.0008583046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037207638,0.00022866717,0.0008959839,0.00030708264,0.000120276054,0.00019783665,0.00014197713,0.7976206,0.0025831312,0.14240694,0.0064246138,0.048700772],"study_design_scores_gemma":[0.000015221026,0.000018401817,0.00003828785,0.0000061025917,0.0000048272987,0.000008773195,0.000005923838,0.97781914,0.00013323344,0.021811694,0.00013445652,0.000003893401],"about_ca_topic_score_codex":0.0037673032,"about_ca_topic_score_gemma":0.0035138654,"teacher_disagreement_score":0.0052812537,"about_ca_system_score_codex":0.0011966588,"about_ca_system_score_gemma":0.0021730205,"threshold_uncertainty_score":0.017667532},"labels":[],"label_agreement":null},{"id":"W4414165913","doi":"10.1109/tcns.2025.3608004","title":"One-Point Sampling for Distributed Bandit Convex Optimization With Time-Varying Constraints","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Regret; Sublinear function; Upper and lower bounds; Convex function; Constraint (computer-aided design); Convex optimization; Benchmark (surveying); Projection (relational algebra)","score_opus":0.05865261333941649,"score_gpt":0.3494235832352155,"score_spread":0.290770969895799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414165913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011608431,0.00033902636,0.9858942,0.0002746564,0.00004085737,0.00006434366,0.000045349887,0.00022559891,0.0015075089],"genre_scores_gemma":[0.7335366,0.00068169093,0.25846198,0.00045187454,0.0001593619,0.0005533492,0.00038625914,0.00024758343,0.0055213077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798954,0.0010247821,0.000068017835,0.00036592872,0.000356661,0.00019499399],"domain_scores_gemma":[0.9934278,0.0049857046,0.0004597152,0.00043091376,0.0004582165,0.00023762054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003699805,0.00159951,0.0020637587,0.0004371156,0.0006860397,0.001402302,0.0018767515,0.0015625256,0.0028851551],"category_scores_gemma":[0.012241955,0.00084097113,0.0008958093,0.0008217569,0.001728495,0.002187904,0.0018562027,0.0029827696,0.000575732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019966521,0.00008166938,0.0004886956,0.00008259859,0.000045575398,0.000085565276,0.000046238176,0.95231485,0.0005176391,0.027697306,0.0011213345,0.017318958],"study_design_scores_gemma":[0.000010034665,0.000016521864,0.000028140768,0.0000035042915,0.0000029236678,0.0000062721533,0.000004031534,0.9937913,0.00013707386,0.0058759735,0.00012191868,0.000002321248],"about_ca_topic_score_codex":0.0048565236,"about_ca_topic_score_gemma":0.00405167,"teacher_disagreement_score":0.0048565236,"about_ca_system_score_codex":0.0017107544,"about_ca_system_score_gemma":0.0015091046,"threshold_uncertainty_score":0.019566715},"labels":[],"label_agreement":null},{"id":"W4414213966","doi":"10.1007/s10479-025-06821-3","title":"On the sensitivity of restless bandits solutions to uncertainty in the models of the arms","year":2025,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Heuristic; Theory of computation; Equivalence (formal languages); Sensitivity (control systems); Scheduling (production processes); Markov process; Job shop scheduling; Dynamic programming","score_opus":0.601241179788179,"score_gpt":0.5791320940734874,"score_spread":0.022109085714691612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414213966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30226892,0.007744518,0.637014,0.015140302,0.00045482692,0.00026308178,0.0012556773,0.00069238094,0.03516624],"genre_scores_gemma":[0.97015196,0.0036665506,0.01611291,0.0010584407,0.00041796663,0.00022543586,0.00045697085,0.0002052648,0.0077044447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99317944,0.0045702304,0.00022725754,0.0006907061,0.00053968845,0.000792759],"domain_scores_gemma":[0.7570537,0.22492358,0.00944693,0.0033278111,0.0031799017,0.0020681077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02055503,0.0029389076,0.0052864314,0.0030940864,0.0015165269,0.006136149,0.0032822248,0.0053770803,0.0063832863],"category_scores_gemma":[0.14462347,0.0024667683,0.002429023,0.002147035,0.00815363,0.007319483,0.0057995045,0.008173896,0.00044809724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003488671,0.00008405768,0.0013000529,0.0002457321,0.00018324394,0.000115675815,0.00017949878,0.8357634,0.0006382681,0.15327816,0.0023688958,0.0054942286],"study_design_scores_gemma":[0.000045268673,0.000069017726,0.00054057117,0.00009109263,0.000060697035,0.000041869953,0.00009208118,0.83728546,0.00023013809,0.16114783,0.00033485008,0.00006115571],"about_ca_topic_score_codex":0.008136946,"about_ca_topic_score_gemma":0.0027622683,"teacher_disagreement_score":0.02055503,"about_ca_system_score_codex":0.004130454,"about_ca_system_score_gemma":0.0024094514,"threshold_uncertainty_score":0.10870671},"labels":[],"label_agreement":null},{"id":"W4416250108","doi":"10.1002/sta4.70119","title":"Matrix Freedman Inequality for Sub‐Weibull Martingales","year":2025,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hermitian matrix; Upper and lower bounds; Eigenvalues and eigenvectors; Covariance matrix; Freedman; Matrix (chemical analysis); Range (aeronautics); Inequality","score_opus":0.1491050896707326,"score_gpt":0.5308173076417018,"score_spread":0.38171221797096916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416250108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033487972,0.0005683003,0.951181,0.0010857859,0.00010808295,0.000036003246,0.00020863657,0.0001442922,0.013179831],"genre_scores_gemma":[0.8863076,0.00097249413,0.09995747,0.0008242607,0.00027108594,0.00024458618,0.0002065092,0.00014474787,0.011071123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984515,0.00049422303,0.000079038175,0.00026059189,0.00048231674,0.00023239672],"domain_scores_gemma":[0.9860475,0.009765104,0.0011456433,0.00082143623,0.0016368523,0.0005835547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044800616,0.00079283706,0.00079838827,0.0015206495,0.00058340025,0.0018693525,0.0015751123,0.0010129319,0.007512885],"category_scores_gemma":[0.020593796,0.0004176216,0.00073922134,0.0007390798,0.0031425476,0.0041418714,0.0022181873,0.0027775867,0.0009531266],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003749516,0.00001775814,0.00054521096,0.000063557796,0.000022919108,0.00008004348,0.000105985986,0.037702274,0.0024622171,0.95137435,0.0012530618,0.0063351346],"study_design_scores_gemma":[0.000010928295,0.000031104984,0.00053596805,0.00004947814,0.000009994682,0.00007727687,0.00004752942,0.52474487,0.0019620822,0.47071454,0.0017817126,0.00003453531],"about_ca_topic_score_codex":0.0013355546,"about_ca_topic_score_gemma":0.00093776296,"teacher_disagreement_score":0.007512885,"about_ca_system_score_codex":0.0016985453,"about_ca_system_score_gemma":0.0013785207,"threshold_uncertainty_score":0.025133133},"labels":[],"label_agreement":null},{"id":"W4416251985","doi":"10.1109/ijcnn64981.2025.11227713","title":"Upper confidence bound multi-armed bandits for partially observed Hawkes processes","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Point process; Regret; Event (particle physics); Process (computing); Set (abstract data type); Point (geometry); Upper and lower bounds; Ranking (information retrieval)","score_opus":0.2590586033651935,"score_gpt":0.47764199471521024,"score_spread":0.21858339135001675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416251985","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05807578,0.0025910414,0.9328663,0.0016946957,0.00015355767,0.00017768466,0.00041841264,0.0007722069,0.0032503854],"genre_scores_gemma":[0.8839585,0.0014650284,0.10354891,0.0010928547,0.00040595033,0.0005966767,0.0011555104,0.00030983388,0.007466854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99605584,0.0018813452,0.00023821233,0.000759363,0.00060139253,0.00046387088],"domain_scores_gemma":[0.9394446,0.052530784,0.002931601,0.0018809113,0.0021392894,0.0010729001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012268074,0.0030456102,0.005045323,0.0016362376,0.0012314873,0.0033997644,0.0037350282,0.0036642705,0.004435087],"category_scores_gemma":[0.054753784,0.0013856487,0.0014114489,0.0014160223,0.0035037082,0.004473856,0.003462293,0.005736191,0.0011170508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022406655,0.00007082355,0.0016685111,0.00013004425,0.0000857323,0.00008843763,0.000071442155,0.9617098,0.00035956057,0.022551842,0.0010609642,0.011978753],"study_design_scores_gemma":[0.000016005835,0.000026916494,0.00013572742,0.000023934135,0.00001145524,0.000011831072,0.000008326691,0.9878037,0.0001328567,0.011673953,0.00014590383,0.000009420766],"about_ca_topic_score_codex":0.0054855924,"about_ca_topic_score_gemma":0.0043259384,"teacher_disagreement_score":0.012268074,"about_ca_system_score_codex":0.002415929,"about_ca_system_score_gemma":0.002293001,"threshold_uncertainty_score":0.06488061},"labels":[],"label_agreement":null},{"id":"W4416566621","doi":"10.1017/eec.2025.10027","title":"Strategies in the multi-armed bandit","year":2025,"lang":"en","type":"article","venue":"Experimental Economics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Baylor University; University of Toronto; Purdue University","keywords":"Reinforcement learning; Probabilistic logic; Selection (genetic algorithm); Multi-armed bandit; Set (abstract data type)","score_opus":0.13607813791203105,"score_gpt":0.48556625018957017,"score_spread":0.3494881122775391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416566621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79089195,0.00036230392,0.20265429,0.00070614275,0.000053628344,0.0004525261,0.00014767816,0.00014698588,0.004584576],"genre_scores_gemma":[0.9650648,0.00010407615,0.0330587,0.00020093333,0.000022231588,0.00050822727,0.000051513223,0.00001668334,0.0009728652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9848964,0.012282367,0.00045314798,0.0009918067,0.0009008267,0.00047531593],"domain_scores_gemma":[0.955213,0.03497129,0.0053590406,0.0029769351,0.00092135486,0.00055836997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018668987,0.0010768484,0.001771532,0.00068440643,0.0005728806,0.0019900836,0.0012848318,0.0017599503,0.0025163684],"category_scores_gemma":[0.045173947,0.0005203387,0.00071036635,0.0006375609,0.001835176,0.0016982438,0.0010485147,0.0016280822,0.00046429533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045415084,0.002156954,0.018765386,0.0004117734,0.00085785595,0.00015334271,0.0008266514,0.7818079,0.0089075435,0.11595719,0.0014802299,0.064133674],"study_design_scores_gemma":[0.00037099776,0.0009779612,0.0041809157,0.000050279617,0.000066195455,0.000031372314,0.00011055468,0.9446051,0.0017888488,0.047122393,0.0006531077,0.00004231756],"about_ca_topic_score_codex":0.0013415567,"about_ca_topic_score_gemma":0.0007926475,"teacher_disagreement_score":0.018668987,"about_ca_system_score_codex":0.0014501011,"about_ca_system_score_gemma":0.00070613064,"threshold_uncertainty_score":0.09873223},"labels":[],"label_agreement":null},{"id":"W4417297121","doi":"10.48550/arxiv.2512.10906","title":"Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Cornell Atkinson Center for Sustainability, Cornell University; David R. Atkinson Center for a Sustainable Future , Cornell University","keywords":"Subgradient method; Semidefinite programming; Convex optimization; Optimal control; Regret; Minimax; Convexity; Probability distribution; Ambiguity; Stochastic control","score_opus":0.1950033316790077,"score_gpt":0.29831358147250475,"score_spread":0.10331024979349704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417297121","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023366662,0.00018439254,0.9739898,0.00027952562,0.000033862314,0.00003483199,0.000060671173,0.00016496715,0.0018852394],"genre_scores_gemma":[0.95226306,0.00017326184,0.045971137,0.000103821716,0.00005300161,0.00008801517,0.00008725065,0.000058713387,0.0012017966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988551,0.00040878128,0.00004592627,0.00024084447,0.00030402362,0.00014536358],"domain_scores_gemma":[0.9966281,0.0021930446,0.00057349843,0.00018349611,0.00029386676,0.00012802352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025717486,0.0011833125,0.0015807773,0.0004170495,0.0004006206,0.0015446924,0.0011090043,0.001107213,0.0011211935],"category_scores_gemma":[0.009033353,0.0005090708,0.0006234635,0.00049968174,0.0015744314,0.0013814522,0.0015974416,0.001943063,0.00017130852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038703605,0.000014197935,0.00010339454,0.000026051963,0.000009618758,0.00002565741,0.000014175071,0.98641425,0.0004304465,0.009027108,0.00016823338,0.0037281183],"study_design_scores_gemma":[0.000005009201,0.000014592691,0.000034765373,0.0000027996678,0.0000016946254,0.0000037323864,0.0000024677522,0.9955515,0.0002076867,0.0041135503,0.00005927284,0.000002778209],"about_ca_topic_score_codex":0.0031144281,"about_ca_topic_score_gemma":0.001466744,"teacher_disagreement_score":0.0031144281,"about_ca_system_score_codex":0.0012916587,"about_ca_system_score_gemma":0.0015970537,"threshold_uncertainty_score":0.013600886},"labels":[],"label_agreement":null},{"id":"W44932258","doi":"","title":"Online Queries for Collaborative Filtering","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Precomputation; Collaborative filtering; Computer science; Recommender system; Information retrieval; Computation; Theoretical computer science; Algorithm","score_opus":0.1817496231968929,"score_gpt":0.5025650383189986,"score_spread":0.32081541512210565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44932258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028453167,0.0010166587,0.9890646,0.0011315885,0.000103326965,0.00010387729,0.00016616809,0.0003562077,0.005212326],"genre_scores_gemma":[0.47443664,0.002517072,0.5037355,0.0012562007,0.0013596519,0.0011087016,0.0013938118,0.00050352386,0.0136888735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98784536,0.005009403,0.00075529155,0.0019807029,0.0036575522,0.00075171806],"domain_scores_gemma":[0.95818895,0.030627513,0.0014878052,0.005765921,0.0033156148,0.00061425136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01037027,0.0018574133,0.0033537068,0.0018230625,0.002138077,0.0067970683,0.0052344105,0.0043866285,0.013637169],"category_scores_gemma":[0.06883924,0.0011453748,0.0012755546,0.0035188694,0.0032130461,0.016253091,0.005186258,0.005756588,0.003154459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033403456,0.00021388958,0.0006547231,0.0003760909,0.00006143393,0.00012261975,0.00036695352,0.13851535,0.00096802495,0.73225623,0.0150689,0.11106172],"study_design_scores_gemma":[0.00004377517,0.000048369144,0.00011095792,0.000044267952,0.000017115912,0.00007183486,0.00005838524,0.54688615,0.00043945122,0.44682947,0.005431878,0.00001834622],"about_ca_topic_score_codex":0.004130432,"about_ca_topic_score_gemma":0.0024804203,"teacher_disagreement_score":0.013637169,"about_ca_system_score_codex":0.0037486334,"about_ca_system_score_gemma":0.0022302044,"threshold_uncertainty_score":0.054843903},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.37014291537915395,"score_gpt":0.4472209630766811,"score_spread":0.07707804769752713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W53582479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009631106,0.0019481935,0.98097044,0.00081535085,0.0001093863,0.00004141013,0.0000673018,0.00021329417,0.0062034745],"genre_scores_gemma":[0.8464805,0.0031992008,0.14087269,0.00082353054,0.0007091725,0.0004690141,0.0003971138,0.00038028133,0.0066685434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970715,0.0012403653,0.00009718142,0.00037543857,0.0008737957,0.00034166648],"domain_scores_gemma":[0.9752907,0.020912586,0.0011521959,0.0007967445,0.0014490677,0.00039866546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062239994,0.0023963535,0.0015132157,0.00093299954,0.0008851725,0.0021201426,0.0016255574,0.001692309,0.0035326534],"category_scores_gemma":[0.032787833,0.0004974154,0.00097143906,0.0010526507,0.0028361536,0.0027804119,0.002674602,0.003946481,0.00060417474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022475261,0.00006016467,0.0006526296,0.0002587005,0.00007278224,0.0000741876,0.000104096995,0.8723424,0.0012290371,0.099865615,0.0023358783,0.022779794],"study_design_scores_gemma":[0.0000116340725,0.00004231839,0.00013235191,0.00002728203,0.00001092349,0.000015250232,0.000008515063,0.96325827,0.00032045034,0.035753857,0.00041185977,0.0000072202615],"about_ca_topic_score_codex":0.0022489093,"about_ca_topic_score_gemma":0.0011135478,"teacher_disagreement_score":0.0062239994,"about_ca_system_score_codex":0.0021774513,"about_ca_system_score_gemma":0.0013360375,"threshold_uncertainty_score":0.03291607},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07402534430139121,"score_gpt":0.39450746002030646,"score_spread":0.3204821157189153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W659523800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47954115,0.00477376,0.49271142,0.0018881694,0.0003042861,0.00048325126,0.0011497007,0.0017757276,0.01737246],"genre_scores_gemma":[0.8696679,0.00062381657,0.12619495,0.00026993811,0.00007436733,0.00016889701,0.0010689691,0.00021971612,0.0017115384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947895,0.0025947287,0.00026302476,0.0005125222,0.0014136373,0.00042656285],"domain_scores_gemma":[0.96421593,0.028278276,0.0016081823,0.0027367321,0.00240576,0.0007551306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010269091,0.0015517103,0.0012447964,0.00088267494,0.00068005384,0.0013738,0.0018895477,0.0022220681,0.0027578375],"category_scores_gemma":[0.032981932,0.0003439085,0.0006252611,0.0013153715,0.0017259999,0.002098849,0.0019077974,0.002156527,0.0005766826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011160339,0.00030043718,0.0028895093,0.00020611817,0.00007697667,0.00008083899,0.000044077107,0.9534169,0.0015809614,0.00909309,0.0023178414,0.028877188],"study_design_scores_gemma":[0.000060359915,0.0002365098,0.00058901624,0.000015152102,0.000009098317,0.000058709462,0.000017155342,0.99408084,0.0010745464,0.003541507,0.00030583856,0.000011294674],"about_ca_topic_score_codex":0.0034320885,"about_ca_topic_score_gemma":0.0027399592,"teacher_disagreement_score":0.010269091,"about_ca_system_score_codex":0.001847797,"about_ca_system_score_gemma":0.0022380266,"threshold_uncertainty_score":0.054308772},"labels":[],"label_agreement":null},{"id":"W6892570696","doi":"10.5281/zenodo.11867602","title":"Iso 3103 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardization; Order (exchange); Brewing; International standardization; Sensory analysis","score_opus":0.09434761987973811,"score_gpt":0.3624524832899565,"score_spread":0.2681048634102184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892570696","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027048175,0.0008822367,0.00497929,0.0006438806,0.002264487,0.00035032711,0.008709232,0.0059277867,0.97597224],"genre_scores_gemma":[0.0016690334,0.001283187,0.002645063,0.0005990292,0.0004560104,0.00016574471,0.00950474,0.003163725,0.9805135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99700445,0.00014894303,0.00016606861,0.00023410896,0.002246138,0.00020028831],"domain_scores_gemma":[0.9938366,0.00034471403,0.00016935481,0.00057962973,0.0046525677,0.00041715134],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021258884,0.002256448,0.0013546847,0.0057941703,0.0017821285,0.009014089,0.004345711,0.0031817046,0.7894591],"category_scores_gemma":[0.0075118532,0.00123122,0.0013718049,0.004655735,0.0010523179,0.006736941,0.0030652683,0.0026318517,0.7949007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007489463,0.000055516855,0.00006053265,0.00045421405,0.000004827375,0.00007384553,0.000045222907,0.00018860029,0.0014423919,0.0046906318,0.8802959,0.112613395],"study_design_scores_gemma":[0.000008118323,0.000018214181,0.0001268962,0.00008022529,0.0000030679794,0.000058245536,0.000026258554,0.00005337072,0.00058409304,0.00075068045,0.9982821,0.000008852366],"about_ca_topic_score_codex":0.0062257512,"about_ca_topic_score_gemma":0.0065429932,"teacher_disagreement_score":0.21054089,"about_ca_system_score_codex":0.0022619877,"about_ca_system_score_gemma":0.0035255216,"threshold_uncertainty_score":0.30031097},"labels":[],"label_agreement":null},{"id":"W6968595109","doi":"10.5281/zenodo.3554750","title":"Statistical Consequences of using Multi-armed Bandits to Conduct Adaptive Educational Experiments","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Key (lock); Statistical power; Randomized experiment; Design of experiments; Statistical hypothesis testing; Statistical analysis","score_opus":0.31909689091757365,"score_gpt":0.45198857970293516,"score_spread":0.1328916887853615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968595109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26561832,0.0006542433,0.7225544,0.0030513154,0.00027041044,0.0024664125,0.00028811654,0.00061658694,0.004480171],"genre_scores_gemma":[0.8078262,0.00016026181,0.18568921,0.001196469,0.000065322114,0.0041143885,0.0001401014,0.000055910492,0.00075207243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.85146934,0.1269524,0.004491127,0.008041765,0.007386815,0.0016585697],"domain_scores_gemma":[0.39892775,0.53377306,0.02748873,0.03197604,0.0063456907,0.0014887926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16040713,0.0014429071,0.0018041974,0.0007121202,0.0013182523,0.0027966232,0.0024203162,0.0028215633,0.002270271],"category_scores_gemma":[0.3724174,0.0012089004,0.0014772164,0.000888871,0.005513244,0.003944513,0.0023607507,0.005180381,0.00047031845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009555975,0.0024460137,0.06958719,0.0011522387,0.0029111453,0.00043460616,0.0016847148,0.61373234,0.010985865,0.114340134,0.002605954,0.1705639],"study_design_scores_gemma":[0.0019716108,0.005497477,0.02033691,0.0003037213,0.0005138212,0.000118900796,0.0004098232,0.7876242,0.010069033,0.16934758,0.0036305708,0.00017626528],"about_ca_topic_score_codex":0.0019760572,"about_ca_topic_score_gemma":0.001930032,"teacher_disagreement_score":0.16040713,"about_ca_system_score_codex":0.0027337836,"about_ca_system_score_gemma":0.0029850234,"threshold_uncertainty_score":0.8483241},"labels":[],"label_agreement":null},{"id":"W6977790614","doi":"10.6084/m9.figshare.7145417.v1","title":"Additional file 2: of Global, regional, and national prevalence of hepatitis B infection in the general and key populations living with HIV: a systematic review and meta-analysis protocol","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Protocol (science); Key (lock); Hepatitis B; Hepatitis B virus; Population; Quality (philosophy)","score_opus":0.23891528062892448,"score_gpt":0.45106282257667835,"score_spread":0.21214754194775387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977790614","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009041322,0.00063967495,0.0014846869,0.00047044142,0.00011517234,0.009012359,0.98598146,0.00033368616,0.0010582746],"genre_scores_gemma":[0.044076916,0.0029969225,0.041074574,0.0034760535,0.00040268354,0.48788983,0.39774683,0.001108373,0.021227757],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99504423,0.0015857577,0.0016894974,0.00075277203,0.0006176911,0.000310082],"domain_scores_gemma":[0.90654665,0.078254804,0.006599098,0.0030281525,0.004826714,0.0007446104],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014993422,0.0020723655,0.0045143845,0.006106188,0.001167217,0.0026178306,0.002480124,0.0016726594,0.7120228],"category_scores_gemma":[0.119247116,0.001771425,0.007970093,0.007795596,0.0008046412,0.004202617,0.0017524934,0.001818298,0.021057675],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053145164,0.00020705059,0.004010999,0.5715156,0.0072018085,0.00016529845,0.00040836385,0.002301417,0.00038613903,0.004711996,0.38274702,0.021029824],"study_design_scores_gemma":[0.15896183,0.0029501026,0.062513284,0.23392485,0.04779564,0.0011138148,0.0012828942,0.010228481,0.0029001816,0.0378439,0.43936998,0.001114981],"about_ca_topic_score_codex":0.0072143967,"about_ca_topic_score_gemma":0.015455714,"teacher_disagreement_score":0.7120228,"about_ca_system_score_codex":0.0030620277,"about_ca_system_score_gemma":0.007206212,"threshold_uncertainty_score":0.41076452},"labels":[],"label_agreement":null},{"id":"W6979268663","doi":"","title":"Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Minimax; Regret; Estimator; Lasso (programming language); Logarithm; Upper and lower bounds; Thresholding; Dimension (graph theory); Least-squares function approximation","score_opus":0.1399943811085759,"score_gpt":0.4363972147109591,"score_spread":0.2964028336023832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979268663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009811535,0.0010436339,0.9843885,0.0008572986,0.00007491174,0.00008752191,0.00013085101,0.0003910691,0.0032147274],"genre_scores_gemma":[0.5399346,0.0020880888,0.44374523,0.0010487036,0.00046142167,0.0010920855,0.0008540222,0.0005530283,0.010222796],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996872,0.0017597527,0.00017650632,0.00044459038,0.00041722582,0.000329973],"domain_scores_gemma":[0.9844087,0.013032846,0.0008550483,0.00083298597,0.0005820895,0.0002883905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069886893,0.0021096868,0.0033937113,0.0010512022,0.0009848244,0.002758012,0.0029443468,0.0028995713,0.0049052266],"category_scores_gemma":[0.023969224,0.0011370368,0.0013574531,0.001838528,0.002465213,0.0033476318,0.0030702879,0.0045684488,0.001558352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000298415,0.00015467856,0.0008399012,0.00025268563,0.00012010887,0.00009275153,0.00013071683,0.81368697,0.0008123838,0.1339083,0.0034508156,0.04625234],"study_design_scores_gemma":[0.00003470581,0.000034634228,0.000077302444,0.000031768515,0.000012248905,0.00001717867,0.000014623909,0.9422339,0.00030785918,0.056707606,0.00051843864,0.000009672362],"about_ca_topic_score_codex":0.0029050675,"about_ca_topic_score_gemma":0.002700611,"teacher_disagreement_score":0.0069886893,"about_ca_system_score_codex":0.002337074,"about_ca_system_score_gemma":0.0024975722,"threshold_uncertainty_score":0.036960185},"labels":[],"label_agreement":null},{"id":"W7024151739","doi":"","title":"Putting Trials on Trial: Sexual Assault and the Failure of the Legal Profession","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Distrust; Sexual assault; Commit; Economic Justice; Criminal justice; Sexual violence; Criminal trial; Suicide prevention","score_opus":0.22828142911056837,"score_gpt":0.5148975797955458,"score_spread":0.2866161506849775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024151739","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5007833,0.029634442,0.0024883468,0.30248427,0.0017680073,0.00005919279,0.000066578395,0.00006475624,0.16265115],"genre_scores_gemma":[0.9670274,0.008526782,0.00024904913,0.016002996,0.00037673,0.000016985125,0.000019901607,0.00003666692,0.007743496],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888022,0.005787497,0.0003230059,0.00047371464,0.0021383977,0.0024752808],"domain_scores_gemma":[0.98045564,0.010528277,0.0023823797,0.0007671622,0.0018048295,0.0040617497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007818903,0.00024600336,0.0004769046,0.0015777542,0.025595818,0.013029145,0.0018711613,0.0057856585,0.005822369],"category_scores_gemma":[0.031255078,0.00039607534,0.0003395317,0.0017722787,0.061070923,0.008135125,0.007869388,0.011695858,0.00057772215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009126941,0.00014961681,0.029014891,0.0002444493,0.000030089135,0.0041752663,0.6766197,0.00016484318,0.00048266278,0.17372648,0.037520107,0.077780575],"study_design_scores_gemma":[0.000023862794,0.00011226076,0.019290179,0.0012395415,0.000023717274,0.0030241846,0.8175679,0.0001643693,0.0004075983,0.034978986,0.123085596,0.00008190552],"about_ca_topic_score_codex":0.1509542,"about_ca_topic_score_gemma":0.24104336,"teacher_disagreement_score":0.1509542,"about_ca_system_score_codex":0.012567356,"about_ca_system_score_gemma":0.020376338,"threshold_uncertainty_score":0.30015105},"labels":[],"label_agreement":null},{"id":"W7024172320","doi":"","title":"Recherche-action-formation sur l'efficacité du changement assisté dans la réalite de la pratique","year":2007,"lang":"fr","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Fusible alloy; Hyporeflexia; Dysgeusia","score_opus":0.0843459556938104,"score_gpt":0.36524212314077903,"score_spread":0.28089616744696866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024172320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1198785,0.0020535812,0.7950945,0.004196115,0.00044269176,0.02052201,0.00067802053,0.00093798456,0.056196596],"genre_scores_gemma":[0.27297565,0.0012236985,0.6942272,0.0007962989,0.00004207942,0.016497767,0.00033134222,0.00011245401,0.013793444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94411105,0.044566695,0.0020521528,0.0049538002,0.0036804972,0.00063571875],"domain_scores_gemma":[0.90405715,0.07919085,0.0036291126,0.0059051206,0.00613501,0.001082685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053626522,0.0017962346,0.0018489582,0.0027238852,0.00270844,0.005010548,0.003317562,0.0017636745,0.02486438],"category_scores_gemma":[0.08528683,0.0012334378,0.00364708,0.0019958634,0.0041880645,0.0054001473,0.0054576853,0.003193934,0.0026305893],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011621008,0.0035941938,0.018053135,0.0069524664,0.0006390403,0.00019657235,0.05455811,0.011856067,0.0051145824,0.16136917,0.0048539345,0.73165065],"study_design_scores_gemma":[0.0043001203,0.010975082,0.07708211,0.010980547,0.0037109994,0.0007263785,0.09314307,0.18149109,0.03768067,0.3830065,0.19610289,0.00080057926],"about_ca_topic_score_codex":0.008968113,"about_ca_topic_score_gemma":0.013902209,"teacher_disagreement_score":0.053626522,"about_ca_system_score_codex":0.0070811645,"about_ca_system_score_gemma":0.014534459,"threshold_uncertainty_score":0.28360754},"labels":[],"label_agreement":null},{"id":"W7025114976","doi":"","title":"Transform Fresno: 2024 Progress Report on Implementation of the Transformative Climate Communities Program Grant","year":2024,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformative learning; Legislature; Transformational leadership; Disadvantaged; State (computer science); Globe; Climate change; Conference of the parties; Program evaluation","score_opus":0.058399282912740214,"score_gpt":0.3845701843569714,"score_spread":0.32617090144423116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025114976","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025406906,0.0073984265,0.010147736,0.121752344,0.011357206,0.008334974,0.1373066,0.0055773896,0.6727184],"genre_scores_gemma":[0.100562654,0.008833425,0.042704232,0.03789666,0.0012753529,0.014377438,0.18119061,0.0021972004,0.6109625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98661554,0.0020083552,0.00042057646,0.00052589504,0.0076574483,0.0027720786],"domain_scores_gemma":[0.9843114,0.0013291168,0.0005451704,0.0004314319,0.008333911,0.0050490303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019027669,0.001280601,0.0005672757,0.0022725773,0.0026980322,0.0059238737,0.003437689,0.0038732728,0.06592891],"category_scores_gemma":[0.02019113,0.00059999886,0.0008385062,0.0015192637,0.0008861261,0.0029261992,0.005797201,0.0035316262,0.020088734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014982042,0.00020608463,0.0024304518,0.0002898578,0.000022979342,0.00013838836,0.00021481956,0.0003338087,0.00032923438,0.0073246416,0.9413296,0.04723031],"study_design_scores_gemma":[0.00012247251,0.00019488821,0.007424502,0.00026374258,0.000022446786,0.000056634737,0.00044662462,0.0003534052,0.00042781772,0.00083345064,0.98982567,0.000028363194],"about_ca_topic_score_codex":0.22417934,"about_ca_topic_score_gemma":0.22761874,"teacher_disagreement_score":0.22417934,"about_ca_system_score_codex":0.0088080615,"about_ca_system_score_gemma":0.086578846,"threshold_uncertainty_score":0.44574893},"labels":[],"label_agreement":null},{"id":"W7043060603","doi":"","title":"Regret Analysis of Bilateral Trade with a Smoothed Adversary","year":2024,"lang":"en","type":"article","venue":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Regret; Order (exchange); Adversary; Bilateral trade; Minimax","score_opus":0.0785588179925852,"score_gpt":0.3637387840940678,"score_spread":0.2851799661014826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043060603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20406152,0.00079513504,0.7774418,0.001906195,0.00010272903,0.00014648648,0.00020665274,0.00044434884,0.014895048],"genre_scores_gemma":[0.969864,0.00029275313,0.024548551,0.00018871053,0.00008485692,0.00009339444,0.00007395044,0.0000623876,0.004791436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968991,0.0014424489,0.00009564517,0.0004876883,0.00050041516,0.00057465635],"domain_scores_gemma":[0.98168325,0.013917168,0.0015820462,0.0014080862,0.0006171563,0.00079223927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062424364,0.0012202716,0.0014417808,0.0005915414,0.0007915443,0.002012109,0.0022102199,0.0020089888,0.0043233414],"category_scores_gemma":[0.022490382,0.0005280562,0.0010663839,0.0006999896,0.002858265,0.0037079044,0.0023638378,0.002943143,0.00047433403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042916826,0.00012202237,0.0011632994,0.00009183234,0.000077760626,0.00013518191,0.00011725636,0.90101355,0.0017053935,0.0851089,0.001120182,0.008915534],"study_design_scores_gemma":[0.000027312524,0.00006564581,0.00014894246,0.000007211325,0.0000119909,0.00003490764,0.000019976897,0.9641308,0.0003373871,0.034990095,0.00021652986,0.000009271418],"about_ca_topic_score_codex":0.0021473977,"about_ca_topic_score_gemma":0.0010533455,"teacher_disagreement_score":0.0062424364,"about_ca_system_score_codex":0.0025411472,"about_ca_system_score_gemma":0.0015762503,"threshold_uncertainty_score":0.033013582},"labels":[],"label_agreement":null},{"id":"W7096516363","doi":"","title":"University of Alberta MULTI-ARMED BANDIT PROBLEMS UNDER DELAYED FEEDBACK","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Adversarial system; Upper and lower bounds; Term (time); Key (lock); Online learning; Style (visual arts)","score_opus":0.12231490048786577,"score_gpt":0.372325968829354,"score_spread":0.25001106834148823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096516363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11416001,0.010718103,0.73275304,0.014808347,0.0016360799,0.0005228772,0.0020723017,0.0011934664,0.122135796],"genre_scores_gemma":[0.74987346,0.004810507,0.17197078,0.00076692464,0.00055642665,0.00042008658,0.0012367802,0.00016730827,0.070197694],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922025,0.00025310073,0.00003140727,0.00016920708,0.00016157898,0.00016451243],"domain_scores_gemma":[0.99673283,0.0024990628,0.00017126018,0.00013001877,0.00026506203,0.00020184385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015262563,0.0019149592,0.0017893661,0.0006210506,0.0009492321,0.0029629949,0.0013278802,0.0022910228,0.006466629],"category_scores_gemma":[0.005169732,0.00051173253,0.00071165035,0.0014713128,0.0014379334,0.0012132649,0.0013169572,0.0031997962,0.0009671246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031019605,0.00015567477,0.0006576887,0.00020190935,0.00006271548,0.00019358154,0.000054601973,0.894383,0.0005147196,0.05718117,0.014084815,0.032199964],"study_design_scores_gemma":[0.00005680936,0.00003691431,0.0001608177,0.00002844492,0.00001365651,0.000016626465,0.000017614117,0.96502733,0.0003119284,0.031672247,0.0026458646,0.000011689904],"about_ca_topic_score_codex":0.05840643,"about_ca_topic_score_gemma":0.047732215,"teacher_disagreement_score":0.05840643,"about_ca_system_score_codex":0.0045858356,"about_ca_system_score_gemma":0.004606952,"threshold_uncertainty_score":0.116132975},"labels":[],"label_agreement":null},{"id":"W7097340650","doi":"","title":"Multi-armed bandits, Gittins index, and its calculation. http://www.ece.mcgill.ca/ amahaj1/projects/bandits/book/2013-bandit -computations.pdf [7","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Lemma (botany); Key (lock); Counterfactual thinking","score_opus":0.10099396275231036,"score_gpt":0.3823988705056625,"score_spread":0.28140490775335214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097340650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00392903,0.014351934,0.8753798,0.006269088,0.0013899729,0.0001710432,0.0034168034,0.0053642862,0.08972791],"genre_scores_gemma":[0.14890511,0.009233476,0.73950285,0.0019265986,0.0016739058,0.0009027293,0.0057131425,0.0027645982,0.08937762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984825,0.00061229646,0.00010216889,0.00020519673,0.00048408005,0.00011383371],"domain_scores_gemma":[0.9959825,0.0023608503,0.00026372197,0.00064842234,0.00062858604,0.000115950344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026297022,0.0019106569,0.0013060296,0.0021063725,0.0010708934,0.0033999684,0.0023902946,0.0026389796,0.038113225],"category_scores_gemma":[0.021397322,0.0014178521,0.00077771646,0.0039241076,0.0011605778,0.0058771423,0.0018673055,0.003580381,0.018797226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018096306,0.00018682779,0.0014784213,0.00040718674,0.00014623138,0.00014212492,0.00013000198,0.09227874,0.00051837123,0.37180668,0.2897223,0.24300216],"study_design_scores_gemma":[0.000052376276,0.000048790454,0.001130322,0.0002558037,0.00004947276,0.0001846036,0.000061068735,0.38391167,0.0011404977,0.53825134,0.07483921,0.000074942385],"about_ca_topic_score_codex":0.008988422,"about_ca_topic_score_gemma":0.017500618,"teacher_disagreement_score":0.038113225,"about_ca_system_score_codex":0.0020069631,"about_ca_system_score_gemma":0.0021142222,"threshold_uncertainty_score":0.12750149},"labels":[],"label_agreement":null},{"id":"W7100077618","doi":"","title":"Author manuscript, published in &amp;quot;Advances in Neural Information Processing Systems, Canada (2008)&amp;quot; Algorithms for Infinitely Many-Armed Bandits","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Logarithm; Artificial neural network; Information processing; Imprecise probability; Probability distribution","score_opus":0.12492032992043503,"score_gpt":0.3955459154269162,"score_spread":0.2706255855064812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100077618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010773226,0.018518947,0.55112255,0.03717628,0.049728762,0.00092148676,0.011662552,0.006075448,0.3140208],"genre_scores_gemma":[0.09274764,0.008313026,0.25481915,0.0039351666,0.00409601,0.0004970351,0.006806209,0.0034116851,0.625374],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989525,0.00019668296,0.00007532876,0.00034410667,0.00029506074,0.00013619165],"domain_scores_gemma":[0.9966085,0.0011709863,0.0001656293,0.0007411478,0.0010610784,0.00025272966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001993163,0.0012175118,0.0019372727,0.0011298901,0.0014185525,0.00609115,0.0022009318,0.0025876914,0.22056255],"category_scores_gemma":[0.011777132,0.0008218638,0.00076767383,0.0024769797,0.0013886986,0.003443138,0.001935589,0.0021838571,0.05905141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037164747,0.00012437631,0.0011418142,0.0006605888,0.00020753677,0.00032389682,0.0001399847,0.024648257,0.0017618876,0.07375501,0.48223296,0.41463205],"study_design_scores_gemma":[0.00023412151,0.00009737306,0.0011747275,0.00050869,0.000101234764,0.0004711665,0.0001536165,0.18904828,0.004440429,0.1359939,0.6676754,0.00010105747],"about_ca_topic_score_codex":0.0075333808,"about_ca_topic_score_gemma":0.019383999,"teacher_disagreement_score":0.22056255,"about_ca_system_score_codex":0.0026834246,"about_ca_system_score_gemma":0.0033721384,"threshold_uncertainty_score":0.7378552},"labels":[],"label_agreement":null},{"id":"W7105903772","doi":"10.23952/jano.7.2025.3.04","title":"Robust contextual bandit method for optimal loan offering","year":2025,"lang":"","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Loan; Context (archaeology); Term (time); Production (economics); Robustness (evolution)","score_opus":0.058461756882175794,"score_gpt":0.38796934007498757,"score_spread":0.32950758319281176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105903772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010718433,0.00044034907,0.9852889,0.00042055626,0.00004751413,0.00007114306,0.00014861519,0.00041430135,0.0024501546],"genre_scores_gemma":[0.72067463,0.0007142162,0.27062333,0.00050829607,0.00019450866,0.00044682005,0.00066769955,0.00019900281,0.005971532],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983537,0.0008630769,0.0000706843,0.00027407412,0.00024279143,0.00019565741],"domain_scores_gemma":[0.9957054,0.0032754652,0.0003317739,0.0002545507,0.0003171139,0.000115658026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037970322,0.0011453802,0.002207102,0.00092121767,0.0005883757,0.0017061504,0.0016207951,0.0019696634,0.006970569],"category_scores_gemma":[0.012110143,0.0006637087,0.00089049956,0.0010602499,0.0012671914,0.0016491895,0.0015490856,0.0023443096,0.001514105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020745263,0.00006380226,0.0010440524,0.000100257574,0.000075756085,0.00006622375,0.00007671086,0.9052199,0.0006225541,0.04575256,0.0016149287,0.045155697],"study_design_scores_gemma":[0.000009464608,0.0000142286835,0.00007724004,0.000009656169,0.000008135087,0.0000049519945,0.0000069125726,0.9877891,0.00014119605,0.011605701,0.00032824746,0.0000051273264],"about_ca_topic_score_codex":0.0061198333,"about_ca_topic_score_gemma":0.0047210436,"teacher_disagreement_score":0.006970569,"about_ca_system_score_codex":0.0011405222,"about_ca_system_score_gemma":0.0018171524,"threshold_uncertainty_score":0.023318827},"labels":[],"label_agreement":null},{"id":"W7108210594","doi":"10.1109/tac.2025.3639124","title":"Online Best-Response Algorithm in Open Noncooperative Games","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Regret; Interval (graph theory); Stability (learning theory); Upper and lower bounds; Trajectory; Nash equilibrium; Online algorithm; Online learning; Cournot competition","score_opus":0.04965455923632081,"score_gpt":0.42018282951190844,"score_spread":0.37052827027558766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7108210594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029458992,0.00019038556,0.9670778,0.00034391735,0.00004942487,0.00009523286,0.000040462506,0.00033100494,0.002412719],"genre_scores_gemma":[0.8900752,0.00019257459,0.10302095,0.000300427,0.000084435036,0.00034710133,0.00012463918,0.00011231126,0.0057423464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99532974,0.00204983,0.00018947464,0.0010710643,0.00068508246,0.00067475205],"domain_scores_gemma":[0.9825081,0.013779175,0.0012794385,0.00076921115,0.00092897913,0.0007350091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00481175,0.0013307711,0.0023796503,0.0005850786,0.0009377407,0.0019862745,0.0029544227,0.0025174303,0.002551081],"category_scores_gemma":[0.017314514,0.00060271565,0.00073055766,0.00065378816,0.002699317,0.0027888133,0.0026885122,0.0029945069,0.00077487796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004690739,0.00036231344,0.0009035029,0.0001675214,0.00009559028,0.0003163777,0.00034332304,0.87506866,0.0021559822,0.08269969,0.0018016079,0.035616346],"study_design_scores_gemma":[0.0000347066,0.00005953132,0.00004621877,0.000005753014,0.0000060501534,0.000031779,0.000022903245,0.96625763,0.0003784288,0.032893077,0.00025518457,0.000008793365],"about_ca_topic_score_codex":0.0016161558,"about_ca_topic_score_gemma":0.00094275567,"teacher_disagreement_score":0.00481175,"about_ca_system_score_codex":0.0012195267,"about_ca_system_score_gemma":0.0015507302,"threshold_uncertainty_score":0.02544725},"labels":[],"label_agreement":null},{"id":"W7112773223","doi":"","title":"A Parametric Contextual Online Learning Theory of Brokerage","year":2024,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche; University of Ottawa","keywords":"Regret; Asset (computer security); Parametric statistics; Context (archaeology); Online learning","score_opus":0.25388020423483015,"score_gpt":0.4610343178363569,"score_spread":0.20715411360152675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7112773223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029116018,0.0010597049,0.96121025,0.0017978699,0.00009979973,0.000090651,0.0001830181,0.00024065467,0.0062019774],"genre_scores_gemma":[0.8719036,0.0015801048,0.1155947,0.00056824484,0.00050784374,0.00028762923,0.00033911987,0.00012619645,0.009092607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961079,0.0017824295,0.0001424536,0.0009620214,0.000534263,0.00047090033],"domain_scores_gemma":[0.978505,0.016629878,0.0017929883,0.0014887007,0.0007510335,0.0008323607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055221296,0.0013649344,0.002640584,0.0010185597,0.0010339604,0.0033228686,0.0040326444,0.0033219384,0.0077680233],"category_scores_gemma":[0.033103142,0.0009980501,0.0012282629,0.0015692979,0.003487202,0.009176132,0.003963601,0.004723477,0.00082354544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027691954,0.00023538865,0.0017851114,0.00023344929,0.000104843406,0.00021675881,0.00029619096,0.5789507,0.00068211684,0.38535354,0.0036952477,0.028169705],"study_design_scores_gemma":[0.000026119655,0.000052170184,0.00017515058,0.000016150923,0.000018212595,0.000031665004,0.000025528761,0.8463206,0.00015558365,0.15232164,0.0008426605,0.000014485492],"about_ca_topic_score_codex":0.0033111619,"about_ca_topic_score_gemma":0.0021319017,"teacher_disagreement_score":0.0077680233,"about_ca_system_score_codex":0.002374555,"about_ca_system_score_gemma":0.0016498403,"threshold_uncertainty_score":0.02920419},"labels":[],"label_agreement":null},{"id":"W7117323897","doi":"10.1007/s10994-025-06943-6","title":"Extended UCB Policies for Multi-armed Bandit Problems","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Regret; Process (computing); Markov decision process; Simplicity; Order (exchange); Reinforcement learning; Extension (predicate logic)","score_opus":0.15270853510586288,"score_gpt":0.48696366916655853,"score_spread":0.3342551340606956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117323897","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018022189,0.0019670578,0.969257,0.0010963611,0.00022861769,0.00011618842,0.00019313788,0.0004153303,0.008704057],"genre_scores_gemma":[0.6957247,0.0035886972,0.27374986,0.0009805163,0.0005851321,0.0011047948,0.0007270842,0.00052546733,0.023013832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99609417,0.002332142,0.00018084004,0.00035201685,0.0005921317,0.00044869093],"domain_scores_gemma":[0.9830089,0.0126418155,0.0009575584,0.0012408815,0.0014323243,0.0007184897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007665602,0.0017153616,0.0033120434,0.00148158,0.001006124,0.003590556,0.002785838,0.0031732302,0.009099055],"category_scores_gemma":[0.028091291,0.0011078966,0.00088275643,0.0021254597,0.0020538052,0.0036780792,0.0029515042,0.004284423,0.00223261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034176814,0.00017852047,0.00053059123,0.00027363648,0.00008131799,0.00008138409,0.00014559942,0.78422636,0.00065066956,0.15481259,0.006997162,0.051680434],"study_design_scores_gemma":[0.000037151094,0.00003881512,0.00006825851,0.00005388462,0.000010311489,0.0000170678,0.000014652116,0.9495411,0.00015794268,0.048982147,0.0010663475,0.000012198016],"about_ca_topic_score_codex":0.0035900443,"about_ca_topic_score_gemma":0.002302555,"teacher_disagreement_score":0.009099055,"about_ca_system_score_codex":0.0018440448,"about_ca_system_score_gemma":0.0025857538,"threshold_uncertainty_score":0.0405401},"labels":[],"label_agreement":null},{"id":"W7117744886","doi":"10.3390/s26010226","title":"Comparative Evaluation of Bandit-Style Heuristic Policies for Moving Target Detection in a Linear Grid Environment","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Defense Acquisition Program Administration","keywords":"Heuristics; Grid; Heuristic; Greedy algorithm; Monte Carlo method; Posterior probability; Probability distribution; Sampling (signal processing); Bayesian probability","score_opus":0.139089121442262,"score_gpt":0.4653359788925978,"score_spread":0.3262468574503358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117744886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84763044,0.00352864,0.13341494,0.001015976,0.00018997346,0.00020744724,0.00026738457,0.000996492,0.012748743],"genre_scores_gemma":[0.98305917,0.0003147562,0.015868878,0.000089901034,0.000012596817,0.000050519153,0.000113747374,0.00003882432,0.0004517597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788314,0.0010639223,0.0001192716,0.0002497996,0.00035754582,0.0003262093],"domain_scores_gemma":[0.9817122,0.015030489,0.0008294057,0.0009091565,0.00093811646,0.0005806124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041936347,0.00081730605,0.0010822378,0.00084589404,0.00050379446,0.001087301,0.0012212105,0.0012124216,0.001062318],"category_scores_gemma":[0.020123549,0.00028067327,0.00031441456,0.00082286296,0.0009204873,0.0013135443,0.0009790331,0.00088385906,0.00022455827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080698763,0.0002445761,0.0019462141,0.00012566954,0.000060541508,0.000034050507,0.00005556814,0.9677183,0.00039935947,0.0035579607,0.0007354576,0.024315238],"study_design_scores_gemma":[0.00006566554,0.00027313302,0.00039294147,0.000014193357,0.000014293535,0.00001531929,0.000046057972,0.99657404,0.00048702757,0.001933754,0.00017575656,0.000007895884],"about_ca_topic_score_codex":0.008892919,"about_ca_topic_score_gemma":0.006558863,"teacher_disagreement_score":0.008892919,"about_ca_system_score_codex":0.0018743122,"about_ca_system_score_gemma":0.0019517574,"threshold_uncertainty_score":0.022178292},"labels":[],"label_agreement":null},{"id":"W7123346749","doi":"10.1109/cdc57313.2025.11312073","title":"Online bandit non-cooperative games with arbitrary delays","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Regret; Online learning; Order (exchange); Upper and lower bounds; Multi-armed bandit; Online algorithm","score_opus":0.043627701022410335,"score_gpt":0.4100376357551577,"score_spread":0.3664099347327474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123346749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085223176,0.0004444578,0.90745395,0.00037454165,0.000091838614,0.00008835968,0.00010960732,0.00020306944,0.006011005],"genre_scores_gemma":[0.9760561,0.00022882661,0.020041084,0.00010527494,0.000035011868,0.000098264136,0.000048138798,0.000020250103,0.0033669642],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988067,0.0003841072,0.00004917974,0.00025186405,0.00019966616,0.0003084105],"domain_scores_gemma":[0.9959061,0.00288278,0.0005347863,0.00023238243,0.00023847246,0.00020532962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016307142,0.001460653,0.0012979252,0.0003449048,0.00061302795,0.0015400758,0.0017870255,0.001327701,0.0017688518],"category_scores_gemma":[0.0067754067,0.00038700268,0.0005333585,0.00067707524,0.0013618908,0.001954636,0.0012944741,0.0016382312,0.00025185634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019512993,0.00007062947,0.0004623778,0.000053099026,0.00002301025,0.00015871698,0.000047495818,0.9516244,0.0009840054,0.036666136,0.00043911772,0.00927594],"study_design_scores_gemma":[0.000012763403,0.00002756167,0.000048913593,0.0000037244963,0.0000060904636,0.000016880951,0.000013255712,0.9900373,0.00032582716,0.009271589,0.00023090685,0.000005138614],"about_ca_topic_score_codex":0.005113817,"about_ca_topic_score_gemma":0.0035562078,"teacher_disagreement_score":0.005113817,"about_ca_system_score_codex":0.0016480373,"about_ca_system_score_gemma":0.0011466203,"threshold_uncertainty_score":0.011957407},"labels":[],"label_agreement":null},{"id":"W7124160515","doi":"10.65109/bvlt2388","title":"Using adaptive consultation of experts to improve convergence rates in multiagent learning","year":2008,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convergence (economics); Set (abstract data type); Multi-agent system; Advice (programming); Process (computing); Class (philosophy); Order (exchange)","score_opus":0.28631231996863216,"score_gpt":0.4785216023773186,"score_spread":0.19220928240868645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124160515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033047266,0.0004270299,0.9623274,0.00049457623,0.00004958968,0.00008869653,0.000016046451,0.000516652,0.0030328007],"genre_scores_gemma":[0.8369791,0.00023688826,0.15910913,0.00038128145,0.00011234216,0.00024178218,0.000051732248,0.000119818986,0.0027678963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954555,0.0027339254,0.00014557877,0.00051835016,0.0007352698,0.00041136338],"domain_scores_gemma":[0.9768727,0.017895348,0.001484049,0.0011601067,0.0018972807,0.00069054257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0083099175,0.0016291761,0.0017125648,0.0010569768,0.00088265474,0.0010335274,0.0026357572,0.0030550167,0.0021758606],"category_scores_gemma":[0.037121784,0.00060842437,0.00063473376,0.00064804463,0.0016778159,0.00231761,0.0023559334,0.0021512932,0.0006825569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047595205,0.00019955878,0.0015056055,0.00011221157,0.00008478167,0.00019079969,0.00029785087,0.9169919,0.0021975103,0.021567978,0.0019015057,0.054474328],"study_design_scores_gemma":[0.000039162624,0.00007351835,0.0000831445,0.000009815571,0.000008883982,0.000023809895,0.000011476134,0.9927209,0.0005536468,0.0061973464,0.00027052793,0.000007719834],"about_ca_topic_score_codex":0.0031211877,"about_ca_topic_score_gemma":0.002016691,"teacher_disagreement_score":0.0083099175,"about_ca_system_score_codex":0.0013448905,"about_ca_system_score_gemma":0.0013578869,"threshold_uncertainty_score":0.043947577},"labels":[],"label_agreement":null},{"id":"W7124305818","doi":"10.65109/hhyv8660","title":"An Online Learning Theory of Brokerage","year":2024,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Regret; Bounded function; Constant (computer programming); Focus (optics); Online learning; Online algorithm","score_opus":0.1508691918332686,"score_gpt":0.47760096021013443,"score_spread":0.3267317683768658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124305818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026502524,0.0016995746,0.94726086,0.003994713,0.00023795832,0.00012434335,0.00020324635,0.00024439505,0.019732406],"genre_scores_gemma":[0.84461457,0.003012002,0.12263794,0.0010431749,0.001012432,0.0004267684,0.00029083877,0.00013659096,0.026825653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99656206,0.0015718504,0.0001398828,0.0007383823,0.00051992154,0.0004680666],"domain_scores_gemma":[0.9867464,0.009797931,0.0012375863,0.0010144882,0.0006538294,0.00054991315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043806145,0.0014311927,0.002213418,0.0010383589,0.0013192709,0.0036033872,0.0033642917,0.0036993271,0.010102201],"category_scores_gemma":[0.024095621,0.0006992302,0.0012983789,0.0017993785,0.0033592673,0.009228739,0.003036442,0.0044404045,0.0014328156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000163759,0.00020098433,0.0012031273,0.00021077847,0.000085392356,0.00018989964,0.00021911976,0.27386126,0.0005860871,0.68574405,0.0047616293,0.032773864],"study_design_scores_gemma":[0.00003806846,0.000045493383,0.00014313291,0.000018706143,0.000013642497,0.00004141698,0.00002715099,0.582958,0.00014840227,0.41468686,0.0018656423,0.000013560557],"about_ca_topic_score_codex":0.0027279397,"about_ca_topic_score_gemma":0.0014116814,"teacher_disagreement_score":0.010102201,"about_ca_system_score_codex":0.002746739,"about_ca_system_score_gemma":0.0016878751,"threshold_uncertainty_score":0.033795238},"labels":[],"label_agreement":null},{"id":"W7124307892","doi":"10.65109/apzr4957","title":"Learning in Games with Progressive Hiding","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Counterfactual thinking; Imperfect; Regret; Perfect information; Information hiding; Recall; Complete information","score_opus":0.045895036896597706,"score_gpt":0.44139978224570314,"score_spread":0.39550474534910546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124307892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11060217,0.0002487444,0.8820048,0.00072355726,0.000033400775,0.00020140421,0.00012194144,0.00035523978,0.0057087606],"genre_scores_gemma":[0.89918727,0.00034772855,0.094774105,0.00021727927,0.000053560503,0.00028554996,0.00013809149,0.000067013105,0.0049293665],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974564,0.0012236139,0.00012589226,0.00041101477,0.0004116801,0.00037140626],"domain_scores_gemma":[0.9878368,0.009396322,0.0009543632,0.0011105528,0.00028136847,0.0004207109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041599716,0.0015425774,0.0015529423,0.00054768886,0.00071689376,0.0016785885,0.0018000621,0.0015297811,0.0030536982],"category_scores_gemma":[0.017364286,0.0008633083,0.0010211758,0.0006439651,0.0027789883,0.004528159,0.0029111456,0.0031870597,0.00045849947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050067727,0.00023040953,0.0013633365,0.00016413491,0.00010412881,0.0001775348,0.00033245183,0.71879154,0.00181484,0.23279585,0.0012913598,0.04243368],"study_design_scores_gemma":[0.00007669073,0.000098691155,0.00016144256,0.000017306726,0.000017226223,0.00003008693,0.00002775473,0.8074536,0.0007740797,0.19077823,0.00054997124,0.000014891385],"about_ca_topic_score_codex":0.0024922262,"about_ca_topic_score_gemma":0.002503374,"teacher_disagreement_score":0.0041599716,"about_ca_system_score_codex":0.0015736867,"about_ca_system_score_gemma":0.0017068798,"threshold_uncertainty_score":0.022000313},"labels":[],"label_agreement":null},{"id":"W7125929930","doi":"10.1145/3768292.3793394","title":"10.1145/3768292.3793394","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Portfolio; Process (computing); Component (thermodynamics)","score_opus":0.05551599963377606,"score_gpt":0.3566894785234227,"score_spread":0.30117347888964663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125929930","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034543981,0.009034932,0.017498631,0.0027702444,0.0028125627,0.0005777494,0.035048407,0.023175973,0.9056271],"genre_scores_gemma":[0.0067218305,0.0037039698,0.0038920743,0.0011438166,0.00024057443,0.00028400202,0.016825134,0.003160674,0.964028],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992112,0.00005971571,0.000062470135,0.0002315703,0.00027219325,0.00016292199],"domain_scores_gemma":[0.9981591,0.00043711343,0.00010912937,0.00067123264,0.00035438006,0.00026913048],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020601666,0.003898404,0.0028224022,0.0031084395,0.002281432,0.0049353335,0.0029741104,0.005581484,0.9300392],"category_scores_gemma":[0.003524425,0.00199644,0.0015165393,0.011003561,0.00164766,0.009993246,0.0057621445,0.0033755472,0.95062214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032545772,0.00022287585,0.00061657716,0.0006310742,0.00006114141,0.0002153931,0.000075953954,0.0013280264,0.0012738631,0.0074596195,0.6812302,0.30655986],"study_design_scores_gemma":[0.000066059685,0.00004166833,0.0009398291,0.00028891518,0.000060701455,0.0001761736,0.00006707509,0.001743323,0.00075643964,0.0031956048,0.9926301,0.00003414431],"about_ca_topic_score_codex":0.020298934,"about_ca_topic_score_gemma":0.013697265,"teacher_disagreement_score":0.06996077,"about_ca_system_score_codex":0.0027314278,"about_ca_system_score_gemma":0.0013212048,"threshold_uncertainty_score":0.09979057},"labels":[],"label_agreement":null},{"id":"W7132960036","doi":"","title":"Online Learning and Optimization in Communication Networks","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Exploit; Online algorithm; Wireless network; Resource allocation; Optimization problem; Convex optimization; Stochastic gradient descent; Asynchrony (computer programming); Key (lock); Gradient descent","score_opus":0.0873601606606339,"score_gpt":0.4951564731886173,"score_spread":0.4077963125279834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132960036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008486025,0.0018827724,0.985033,0.00086839224,0.00012502755,0.000043613087,0.000050295104,0.000118612945,0.003392243],"genre_scores_gemma":[0.71212244,0.005632057,0.2693409,0.0005442779,0.0006787906,0.000528945,0.00022794108,0.00016905332,0.010755613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980471,0.00093360204,0.00008084003,0.00039455813,0.0003527262,0.00019116238],"domain_scores_gemma":[0.9939183,0.0047593075,0.00040519712,0.0003726363,0.0004423512,0.000102239836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028820867,0.0016903164,0.00160052,0.0007714182,0.0006331432,0.0025374044,0.0016177839,0.0019333527,0.0025172757],"category_scores_gemma":[0.009790359,0.0006827007,0.0008075702,0.0012683535,0.0023562405,0.0032887347,0.0018428138,0.0026918845,0.0003427122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026179143,0.000031940894,0.00032360715,0.00009635312,0.000037416085,0.00003190366,0.000040367562,0.9036049,0.00022256706,0.07778982,0.00088139507,0.01691356],"study_design_scores_gemma":[0.0000036816814,0.000011114483,0.00004229017,0.000008294456,0.000003100952,0.000004990349,0.0000058892497,0.9731635,0.00009118183,0.026218278,0.00044419282,0.0000033934323],"about_ca_topic_score_codex":0.0036425726,"about_ca_topic_score_gemma":0.0023122455,"teacher_disagreement_score":0.0036425726,"about_ca_system_score_codex":0.002549565,"about_ca_system_score_gemma":0.0014643784,"threshold_uncertainty_score":0.01849842},"labels":[],"label_agreement":null},{"id":"W7133405170","doi":"","title":"Lexicographic Lipschitz Bandits:New Algorithms and a Lower Bound","year":2025,"lang":"en","type":"article","venue":"CityU Scholars","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; City University of Hong Kong","keywords":"Lexicographical order; Regret; Upper and lower bounds; Lipschitz continuity; Dimension (graph theory); Matching (statistics)","score_opus":0.07882936778791948,"score_gpt":0.4231396116865803,"score_spread":0.34431024389866083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133405170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0136117255,0.0020533765,0.96600705,0.0019663447,0.00019240053,0.00014920058,0.00018526126,0.0008254523,0.015009176],"genre_scores_gemma":[0.25726724,0.002122777,0.71840405,0.0013757425,0.000563055,0.0006796398,0.00055923295,0.00068368297,0.018344624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978696,0.00091772864,0.000092033646,0.00031675407,0.00052923337,0.00027458623],"domain_scores_gemma":[0.9907575,0.0074986047,0.00042495085,0.0006523247,0.00040007336,0.00026659732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036634037,0.0017475204,0.0022398706,0.0012103313,0.0011372388,0.0033047616,0.002625341,0.003622513,0.0074627935],"category_scores_gemma":[0.017863557,0.0010036086,0.0012395239,0.0020494976,0.0025712312,0.005499525,0.0030416008,0.0061221747,0.0017690194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005604285,0.00031168514,0.0013276512,0.00044139315,0.00009913192,0.00018919216,0.00024929,0.5829117,0.002053131,0.26095638,0.013932536,0.13696748],"study_design_scores_gemma":[0.000053277043,0.000054219356,0.000079139994,0.000058038328,0.000017672774,0.00005298812,0.000027309785,0.9230223,0.0006936686,0.07365016,0.0022787591,0.000012633896],"about_ca_topic_score_codex":0.0026788116,"about_ca_topic_score_gemma":0.0039505316,"teacher_disagreement_score":0.0074627935,"about_ca_system_score_codex":0.0025721914,"about_ca_system_score_gemma":0.0025450045,"threshold_uncertainty_score":0.024965525},"labels":[],"label_agreement":null},{"id":"W7135006558","doi":"","title":"An Online Learning Theory of Trading-Volume Maximization","year":2025,"lang":"en","type":"article","venue":"Bristol Research (University of Bristol)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Regret; Earnings; Complement (music); Asset (computer security); Profit (economics); Private information retrieval; Maximization; Logarithm; Function (biology)","score_opus":0.1984716496858113,"score_gpt":0.43981916459205045,"score_spread":0.24134751490623915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135006558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01456358,0.0011512614,0.974944,0.0015046656,0.0001344363,0.000081456805,0.00017696836,0.00021021185,0.0072334167],"genre_scores_gemma":[0.7943026,0.0025069378,0.18670236,0.00086068566,0.00076619955,0.00054208067,0.00040185798,0.00020627702,0.013710914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997497,0.0012167653,0.00010073049,0.0005107468,0.0003732163,0.00030145617],"domain_scores_gemma":[0.9890581,0.008907236,0.0006823666,0.0005213751,0.0004865041,0.00034451525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041122995,0.0018030403,0.002623313,0.0009584256,0.00083006127,0.0029562227,0.003041643,0.0024024027,0.0057722447],"category_scores_gemma":[0.016470553,0.00072464236,0.0013809373,0.0016788378,0.0026121656,0.0053893323,0.0021955434,0.0038300776,0.00082793203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015412003,0.00013783961,0.00089738995,0.00023347833,0.00008864983,0.00012301918,0.00014346742,0.668098,0.0005998791,0.29584134,0.0031545318,0.030528437],"study_design_scores_gemma":[0.000020461239,0.000028275852,0.000079754216,0.000011755057,0.00000893547,0.00001578088,0.000008009863,0.85897386,0.00010482005,0.14012435,0.0006149666,0.00000899683],"about_ca_topic_score_codex":0.0026004813,"about_ca_topic_score_gemma":0.0018861936,"teacher_disagreement_score":0.0057722447,"about_ca_system_score_codex":0.0026835955,"about_ca_system_score_gemma":0.0017858794,"threshold_uncertainty_score":0.021748185},"labels":[],"label_agreement":null},{"id":"W7139010223","doi":"10.1109/globecom59602.2025.11432650","title":"Kelly Bets and Single-Letter Codes: Optimal Information Processing in Natural Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Upper and lower bounds; Information processing; Population; Simple (philosophy); Point (geometry); Code (set theory); Investment (military); Complete information","score_opus":0.039392630988728174,"score_gpt":0.3778315229514149,"score_spread":0.3384388919626867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139010223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34903258,0.0011099181,0.6244496,0.0018313613,0.00008868338,0.00009802715,0.00018856363,0.00020641637,0.022994878],"genre_scores_gemma":[0.9657738,0.00032833326,0.031188939,0.00016446077,0.00003854735,0.0000741533,0.00003800427,0.000031999658,0.0023617698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978066,0.0009299084,0.000087592605,0.00028303673,0.00049921253,0.00039372809],"domain_scores_gemma":[0.9863723,0.010531958,0.0011226104,0.000783572,0.0007112493,0.00047835207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002695038,0.0006737364,0.0009078299,0.00086723117,0.0008054782,0.003013064,0.0009805653,0.0016233092,0.0021280858],"category_scores_gemma":[0.025121685,0.00043321153,0.00035152823,0.00092321535,0.0032817926,0.0040724697,0.0016381479,0.0014956674,0.0003702782],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031420263,0.00007989763,0.0011485828,0.00012441812,0.000037772512,0.00016471786,0.00027230466,0.31094015,0.005568265,0.6534665,0.0014576197,0.026425544],"study_design_scores_gemma":[0.000031334963,0.000067579094,0.0003300697,0.00002993167,0.000008533585,0.00009499645,0.00005767236,0.5664109,0.0020443555,0.43022949,0.0006571809,0.000037899365],"about_ca_topic_score_codex":0.002099755,"about_ca_topic_score_gemma":0.0014136637,"teacher_disagreement_score":0.003013064,"about_ca_system_score_codex":0.002191345,"about_ca_system_score_gemma":0.0013759847,"threshold_uncertainty_score":0.01589942},"labels":[],"label_agreement":null},{"id":"W852997015","doi":"10.1007/978-3-319-18356-5_7","title":"Budget-Driven Big Data Classification","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Class (philosophy); Big data; Process (computing); Machine learning; Artificial intelligence; Set (abstract data type); Data set; Training set; Support vector machine; Data mining; Scale (ratio); Programming language","score_opus":0.37212191456823307,"score_gpt":0.4431382603684922,"score_spread":0.07101634580025912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W852997015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009921189,0.0017850103,0.97671854,0.0028486827,0.00044445173,0.00019322432,0.00093917723,0.00155625,0.00559351],"genre_scores_gemma":[0.4540505,0.0023103252,0.5043833,0.0020871393,0.0019396031,0.0009378276,0.005254318,0.0012061639,0.027830843],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752694,0.001096094,0.00011647486,0.0004194229,0.000565982,0.00027507526],"domain_scores_gemma":[0.9874292,0.008667936,0.00044655058,0.0017727533,0.0011831933,0.00050030183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006857839,0.0013525455,0.0028767434,0.0012157509,0.0007058453,0.002423135,0.004060371,0.0020523611,0.010843235],"category_scores_gemma":[0.023243073,0.0012307772,0.0011392409,0.0023599875,0.0011883633,0.005015355,0.0034581758,0.0037857345,0.0028576017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081212644,0.0002926114,0.0028274695,0.000492219,0.00021570937,0.00011084378,0.00011660727,0.4140805,0.001669181,0.08635533,0.07493841,0.41808903],"study_design_scores_gemma":[0.000024360092,0.000024320747,0.00017300906,0.000026307105,0.000013706316,0.000025574798,0.000014668147,0.9186262,0.00038454466,0.07840863,0.0022699954,0.000008623798],"about_ca_topic_score_codex":0.002243075,"about_ca_topic_score_gemma":0.004007462,"teacher_disagreement_score":0.010843235,"about_ca_system_score_codex":0.0016503078,"about_ca_system_score_gemma":0.00239351,"threshold_uncertainty_score":0.036274254},"labels":[],"label_agreement":null},{"id":"W9422450","doi":"","title":"Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Hindsight bias; Minimax; Outcome (game theory); Action (physics); Logarithm; Computer science; Mathematical optimization; Mathematics; Mathematical economics; Statistics; Psychology","score_opus":0.24345939677892353,"score_gpt":0.40468048743075924,"score_spread":0.1612210906518357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9422450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22299281,0.002170077,0.74773234,0.0045518293,0.0002496656,0.00029090157,0.0015312773,0.0006289764,0.019852092],"genre_scores_gemma":[0.9594843,0.00085395883,0.027963558,0.0004897846,0.00019467436,0.00043010854,0.00072404556,0.00014003801,0.009719467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963741,0.0020420474,0.00015829652,0.00046242785,0.00032285837,0.00064023153],"domain_scores_gemma":[0.9651681,0.030696437,0.0015925486,0.0006301739,0.0007188516,0.0011938476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074625113,0.0022608386,0.0037615683,0.0012243242,0.00092135114,0.0027745995,0.0023369472,0.0024845235,0.005473551],"category_scores_gemma":[0.01802961,0.000959537,0.0011476158,0.0010683932,0.0027096006,0.0029022787,0.002874147,0.0030958473,0.0004939888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038293758,0.00008164937,0.001218957,0.00016608441,0.00010998677,0.00013189718,0.000074139396,0.95024556,0.00020418175,0.039415926,0.0018462132,0.006122521],"study_design_scores_gemma":[0.000044652195,0.000057362064,0.00017657255,0.000016692436,0.00001015418,0.000019378178,0.000015862517,0.96901727,0.00006308209,0.030408666,0.00015878175,0.000011483676],"about_ca_topic_score_codex":0.0063538547,"about_ca_topic_score_gemma":0.0046984414,"teacher_disagreement_score":0.0074625113,"about_ca_system_score_codex":0.0036434932,"about_ca_system_score_gemma":0.0026741263,"threshold_uncertainty_score":0.039466023},"labels":[],"label_agreement":null}]}