{"id":"W1529722424","doi":"10.1007/11944836_23","title":"Testing Probabilistic Equivalence Through Reinforcement Learning","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Equivalence (formal languages); Markov decision process; Probabilistic logic; Computer science; Reinforcement learning; Bisimulation; TRACE (psycholinguistics); Markov process; Witness; Theoretical computer science; Algorithm; Artificial intelligence; Discrete mathematics; Mathematics; Programming language; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.001848056,0.0006046484,0.0005121117,0.0004777491,0.0004781108,0.0006329402,0.003880819,0.0003117744,0.00001396642],"category_scores_gemma":[0.001029672,0.0005824938,0.0001078059,0.001063942,0.000864517,0.001284649,0.001781704,0.00123939,0.00006506101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006712433,"about_ca_system_score_gemma":0.000581486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006424536,"about_ca_topic_score_gemma":0.000007591183,"domain_scores_codex":[0.9949788,0.00008126615,0.0008589076,0.001778739,0.0014062,0.0008960564],"domain_scores_gemma":[0.9963633,0.0008079269,0.00063818,0.001624665,0.0004507999,0.0001150684],"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":[0.000002234238,0.00001251005,0.00004352254,0.0000794377,0.000003506501,0.00002622502,0.0003437227,0.652309,0.000187604,0.06937807,0.00001089257,0.2776033],"study_design_scores_gemma":[0.0001291867,0.0002404091,0.000130126,0.0005427476,0.000006911005,0.00005985661,9.755498e-8,0.8413638,0.000976085,0.1546771,0.001246929,0.0006267423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003308744,0.0002102789,0.966844,0.0001258849,0.001367911,0.000568516,7.57482e-7,0.0003789804,0.03047055],"genre_scores_gemma":[0.05177527,0.00001113034,0.9466326,0.0003811095,0.0003707898,0.00002272011,0.000004976609,0.00003723176,0.0007641473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2769766,"threshold_uncertainty_score":0.9996626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05150164505242391,"score_gpt":0.2925115154425397,"score_spread":0.2410098703901158,"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."}}