{"id":"W4409589849","doi":"10.1007/978-3-031-85870-3_7","title":"Towards Topologically Diverse Probabilistic Planning Benchmarks: Synthetic Domain Generation for Markov Decision Processes","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Probabilistic logic; Markov chain; Computer science; Domain (mathematical analysis); Markov decision process; Artificial intelligence; Markov model; Markov process; Machine learning; Mathematics; 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":[0.001216455,0.000388337,0.0006629812,0.0007479044,0.0006650866,0.0002420954,0.001006437,0.0003047128,0.00002928992],"category_scores_gemma":[0.003524355,0.0003497122,0.00005279195,0.001432517,0.0002028947,0.0004121254,0.0008540456,0.0001981757,0.000004045745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002145083,"about_ca_system_score_gemma":0.0005669066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001135311,"about_ca_topic_score_gemma":0.0005920621,"domain_scores_codex":[0.9972109,0.00009896674,0.0007846392,0.001405348,0.0002581533,0.0002419518],"domain_scores_gemma":[0.9957902,0.0009783756,0.0004602801,0.001197277,0.001511013,0.00006282372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000807936,0.0003599185,0.0182315,0.004416768,0.003990427,0.000018688,0.01273841,0.001129085,0.00007273601,0.7323567,0.0848663,0.1417387],"study_design_scores_gemma":[0.002483176,0.0004955226,0.009719544,0.006520378,0.009417342,0.00002156524,0.002400194,0.5272398,0.0000899841,0.2825201,0.1547046,0.004387852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009849003,0.01017014,0.9794088,0.0004410132,0.000450534,0.0006767258,0.0003037936,0.0001106145,0.008339868],"genre_scores_gemma":[0.2402401,0.04217691,0.5938804,0.0004343771,0.001974361,0.0004506473,0.06874014,0.0002047976,0.05189832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5261107,"threshold_uncertainty_score":0.9998955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1106022081699415,"score_gpt":0.3539953488020479,"score_spread":0.2433931406321064,"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."}}