{"id":"W4405632789","doi":"10.1016/j.datak.2024.102393","title":"Coupling MDL and Markov chain Monte Carlo to sample diverse pattern sets","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Markov chain Monte Carlo; Coupling (piping); Statistical physics; Monte Carlo method; Markov chain; Computer science; Sample (material); Algorithm; Physics; Mathematics; Statistics; Machine learning; Materials science; Thermodynamics","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":[0.0002996945,0.0001396191,0.0001184291,0.0001511167,0.00005715525,0.0003117087,0.0008259375,0.00004115988,0.000007261991],"category_scores_gemma":[0.0001003194,0.0001366184,0.00002071955,0.0003856129,0.00001049813,0.0005510327,0.001113318,0.0001380924,0.00005630737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004524998,"about_ca_system_score_gemma":0.00002645848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004620138,"about_ca_topic_score_gemma":0.00001103717,"domain_scores_codex":[0.9990394,0.000007275317,0.0001471374,0.000472539,0.0001145362,0.0002191691],"domain_scores_gemma":[0.9990206,0.0001369879,0.00001276208,0.0006760097,0.00003650857,0.0001171691],"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":[0.000002071565,0.00002277595,0.0001647052,0.0002885788,0.00003379129,0.00003629267,0.001278664,0.00005153507,0.00268205,0.001518667,0.00481343,0.9891074],"study_design_scores_gemma":[0.00003995921,0.00001687893,0.000325104,0.0001134268,0.000005885486,0.000006599069,0.0000177233,0.9463562,0.0009792682,0.00001116962,0.05196174,0.0001660621],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002985674,0.001849534,0.9933626,0.0002243813,0.0004567144,0.0001345665,0.0001974862,0.0007376787,0.00005137383],"genre_scores_gemma":[0.8849618,0.0002530274,0.1139348,0.00006855298,0.0003021772,0.00004293563,0.0001124468,0.00004949839,0.0002746831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9889414,"threshold_uncertainty_score":0.5571135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03342681986294629,"score_gpt":0.2847333065404637,"score_spread":0.2513064866775174,"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."}}