{"id":"W4403935894","doi":"10.1145/3652620.3676878","title":"Towards Model Repair by Human Opinion--Guided Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Human–computer interaction; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511533,0.0002373517,0.0001843864,0.0001666462,0.0002720765,0.0005615367,0.000853961,0.00009055214,0.0001614399],"category_scores_gemma":[0.00005221436,0.0002139387,0.0001764658,0.0003958645,0.00004170812,0.0007560849,0.0005856923,0.000398566,0.0003306922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001616087,"about_ca_system_score_gemma":0.0001384027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005950277,"about_ca_topic_score_gemma":3.871925e-7,"domain_scores_codex":[0.9977947,0.00004924033,0.0004882609,0.0005756591,0.0006315907,0.0004605095],"domain_scores_gemma":[0.9990118,0.00004670663,0.00006910231,0.0006586007,0.00007389968,0.0001399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.577667e-7,0.000004780109,0.00001754555,0.0000390346,0.00002987815,0.000003798047,0.0003319,0.742165,0.0004358016,0.1798165,0.07633061,0.0008247086],"study_design_scores_gemma":[0.0001278768,0.0001244781,0.000006778143,0.00006097215,0.000005334046,0.000006666581,0.00001752708,0.925166,0.0006729221,0.0006596722,0.0728878,0.0002639395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000130058,0.0001554381,0.8770303,0.0006579119,0.0005061734,0.0001661066,2.366766e-7,0.002596868,0.1187569],"genre_scores_gemma":[0.7558439,0.0001093456,0.09273491,0.0008414891,0.0001681791,0.00004294001,0.00005022106,0.00005540121,0.1501536],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7842954,"threshold_uncertainty_score":0.8724168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03763230770512827,"score_gpt":0.3118472252698286,"score_spread":0.2742149175647003,"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."}}