{"id":"W2003520601","doi":"10.1016/j.ic.2013.02.002","title":"Testing probabilistic equivalence through Reinforcement Learning","year":2013,"lang":"en","type":"article","venue":"Information and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Equivalence (formal languages); Mathematics; Bisimulation; Decidability; Probabilistic logic; Discrete mathematics; Theoretical computer science; Computer science","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":[0.000289984,0.00008694761,0.00007171251,0.00007083244,0.0001946994,0.0004078285,0.0001711219,0.00003597503,0.000009065259],"category_scores_gemma":[0.0003470536,0.00008306104,0.00001320184,0.0003140397,0.00003151677,0.00604104,0.0001027177,0.00009939989,0.0001970987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004192251,"about_ca_system_score_gemma":0.00003000768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005265085,"about_ca_topic_score_gemma":1.19208e-7,"domain_scores_codex":[0.9991226,0.00005344514,0.0003538124,0.0001084083,0.0002171047,0.0001446094],"domain_scores_gemma":[0.9992436,0.00009602614,0.000223737,0.0001205406,0.0002747681,0.00004138157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001802003,0.000007725363,0.0002952813,0.00008253375,0.00000391904,1.122493e-7,0.003594846,0.1644006,0.0001456888,0.1501859,0.0001236776,0.6811579],"study_design_scores_gemma":[0.0001456241,0.00008212324,0.008694226,0.00002368125,0.000001625358,0.00001074286,0.0001314554,0.9771416,0.0001389592,0.01275548,0.0007687983,0.0001056511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0206564,0.00001102497,0.9692508,0.0001576817,0.0001310915,0.0003184893,8.772699e-8,0.0002364725,0.009237969],"genre_scores_gemma":[0.5941372,0.000003249634,0.405541,0.0002412871,0.00001080566,0.00003916864,0.00000721517,0.000001765212,0.00001829439],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.812741,"threshold_uncertainty_score":0.4379608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05048742108083468,"score_gpt":0.2990773554567007,"score_spread":0.248589934375866,"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."}}