{"id":"W4401006785","doi":"10.2139/ssrn.4905086","title":"Modeling Behavioral Deviations in Adls Using Inverse Reinforcement Learning and Higher-Order Markov Chains","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Markov chain; Reinforcement learning; Reinforcement; Inverse; Order (exchange); Computer science; Artificial intelligence; Mathematics; Machine learning; Psychology; Social psychology; Economics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001940355,0.0003549852,0.0003442433,0.0007060205,0.0002114689,0.0005873155,0.0009042925,0.0002550781,0.000008148614],"category_scores_gemma":[0.00004080297,0.000371277,0.0001011554,0.0004094254,0.00003843537,0.0003897002,0.002681777,0.006568086,0.000004542323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002376725,"about_ca_system_score_gemma":0.003331759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007303352,"about_ca_topic_score_gemma":0.001012974,"domain_scores_codex":[0.9964922,0.0001512984,0.0006061351,0.0006266419,0.0004081227,0.001715574],"domain_scores_gemma":[0.9990867,0.00002512466,0.000242045,0.0004226708,0.0001176465,0.0001058341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004245661,0.0002133445,0.002364176,0.0002414935,0.0004694502,0.0002116081,0.003461233,0.4206007,0.0006042962,0.4191271,0.0001857534,0.1524783],"study_design_scores_gemma":[0.0002035333,0.0001332744,0.00001384894,0.0004535489,0.0000590586,0.0001937825,0.0002329759,0.8806259,0.00001783309,0.1175658,0.0001280927,0.0003723794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1726618,0.002100021,0.8233262,0.0005421499,0.0004674395,0.0002855108,0.000003626708,0.0002849852,0.0003282685],"genre_scores_gemma":[0.9393805,0.00295267,0.0567954,0.00004813414,0.000165429,0.00002552479,0.00002386959,0.00004663867,0.0005618252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7667187,"threshold_uncertainty_score":0.9998739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03202399944545242,"score_gpt":0.3151733611271011,"score_spread":0.2831493616816487,"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."}}