{"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,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Computer science; Machine learning; Psychology; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009982992,0.0002203729,0.0003636404,0.000599192,0.0001381957,0.0003150574,0.0005735887,0.0001488177,0.02625784],"category_scores_gemma":[0.009154683,0.000179973,0.00003804838,0.0005809106,0.00004877152,0.0006573871,0.00115098,0.0004908728,0.000924679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003080244,"about_ca_system_score_gemma":0.0001105889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005052623,"about_ca_topic_score_gemma":0.001628581,"domain_scores_codex":[0.9960949,0.0002193049,0.0007776039,0.0006973312,0.001664196,0.0005466695],"domain_scores_gemma":[0.9977521,0.0008093429,0.000248229,0.0003639141,0.0005929331,0.0002334366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001832766,0.001161113,0.3250928,0.0002791162,0.00004928613,0.002507789,0.02174427,0.09383928,0.003390062,0.0000195053,0.2811516,0.2689324],"study_design_scores_gemma":[0.0251599,0.002223017,0.5670281,0.008593146,0.00001755997,0.0001509611,0.0066596,0.3005489,0.001263988,0.001634004,0.08460059,0.002120259],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9664217,0.002221035,0.003081694,0.0003689367,0.0003872718,0.008601933,0.01557092,0.0002672367,0.00307934],"genre_scores_gemma":[0.9944631,0.000002581151,0.0003256736,0.00002444333,0.00002872598,0.0003679875,0.002235472,0.00002213969,0.002529911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2668121,"threshold_uncertainty_score":0.9998532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.33005442763166,"score_gpt":0.4855699151820237,"score_spread":0.1555154875503637,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}