{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002969167,0.0009435571,0.0008192093,0.001060348,0.0007308895,0.001289213,0.001958881,0.001625567,0.003890278],"category_scores_gemma":[0.01375578,0.00053533,0.0008478073,0.001525635,0.001216582,0.001374577,0.001676481,0.00172713,0.000426347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718173,"about_ca_system_score_gemma":0.001621356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009136073,"about_ca_topic_score_gemma":0.01352733,"domain_scores_codex":[0.9986411,0.0007220373,0.00006842872,0.0001996559,0.0002774169,0.00009141907],"domain_scores_gemma":[0.9882393,0.009987588,0.000263095,0.0006559244,0.0006377969,0.0002163508],"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":[0.0001200918,0.0001143606,0.0006155837,0.0001199264,0.00002837251,0.00004927307,0.00007772551,0.9516903,0.0004508296,0.01825478,0.003621155,0.02485759],"study_design_scores_gemma":[0.00001491142,0.00001336379,0.00004100992,0.000005736215,0.000002862428,0.000006045041,0.00001348474,0.9909729,0.0003292571,0.008249573,0.0003486488,0.000002295196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.271405,0.001179238,0.6951542,0.001643963,0.0002263831,0.0003789586,0.003601164,0.003754015,0.02265701],"genre_scores_gemma":[0.6660373,0.0002721463,0.3271017,0.0002249552,0.00003965164,0.0003237628,0.003704433,0.0004446323,0.001851492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009136073,"threshold_uncertainty_score":0.01816583,"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."}}