{"id":"W4416677530","doi":"10.1109/models67397.2025.00025","title":"Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance","year":2025,"lang":"","type":"article","venue":"","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; State space; Certainty; Space (punctuation); Complex system; Key (lock)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001692717,0.001273943,0.0006082,0.0004146522,0.0004371344,0.0008352117,0.001349111,0.0009452074,0.002368295],"category_scores_gemma":[0.007104903,0.0005571287,0.0008109427,0.0002573841,0.001565266,0.00112448,0.001619466,0.001756361,0.0003726993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009312402,"about_ca_system_score_gemma":0.001821418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004721312,"about_ca_topic_score_gemma":0.007199337,"domain_scores_codex":[0.9988202,0.0004606818,0.00005424186,0.0002137875,0.0003560625,0.00009490401],"domain_scores_gemma":[0.996669,0.002236536,0.0003615482,0.0003707593,0.0002454997,0.0001166784],"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":[0.00007053627,0.00008114757,0.0007705561,0.00007963064,0.0000236102,0.0001017356,0.0002044633,0.93704,0.003691868,0.008838901,0.0006107098,0.04848683],"study_design_scores_gemma":[0.00001591803,0.00003513429,0.00004461471,0.00000942233,0.000006667798,0.00001572637,0.0000151185,0.992458,0.001374094,0.005267427,0.0007528909,0.000005062927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01862168,0.00005995522,0.9783172,0.0001289215,0.00001281691,0.00008253873,0.00002452007,0.001126317,0.001626114],"genre_scores_gemma":[0.5583978,0.0001030958,0.4387456,0.0001337182,0.00001749412,0.0002467984,0.0001296621,0.0002706222,0.00195513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004721312,"threshold_uncertainty_score":0.009387672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02346897398349878,"score_gpt":0.2765449182279479,"score_spread":0.2530759442444491,"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."}}