{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004485698,0.0004893881,0.000433423,0.0003008804,0.0007422667,0.0003747038,0.001404528,0.0001540176,0.00009147193],"category_scores_gemma":[0.000004707287,0.0004715408,0.0001148532,0.0009255012,0.0001453434,0.0009247237,0.0002728551,0.0005594526,0.00001220519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003410013,"about_ca_system_score_gemma":0.0002569925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001758778,"about_ca_topic_score_gemma":0.00002279569,"domain_scores_codex":[0.997161,0.00007587707,0.0008271954,0.0006802129,0.0005689035,0.0006867527],"domain_scores_gemma":[0.9983971,0.00004372427,0.0001570273,0.000965849,0.0002807026,0.0001556285],"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":[0.000005275154,0.0000378357,0.00003296679,0.00009103488,0.00004178957,0.000001190711,0.0007326395,0.6332392,0.0007219366,0.3436092,0.01208639,0.009400576],"study_design_scores_gemma":[0.0004987682,0.0002386831,0.00002413071,0.0003574799,0.00002825465,0.000002784707,0.00001063028,0.9282307,0.001995524,0.00101258,0.06710656,0.0004939063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002028594,0.000138899,0.973844,0.001330271,0.00005641159,0.0007344951,0.000006375488,0.001527722,0.02215899],"genre_scores_gemma":[0.5105935,0.00004998534,0.4732502,0.0004191565,0.000008500157,0.0001216345,0.00003198457,0.00002067573,0.01550431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5103907,"threshold_uncertainty_score":0.9997736,"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."}}