{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005190631,0.0006738356,0.002102611,0.001881586,0.0007958274,0.002080668,0.002669292,0.002238531,0.003844512],"category_scores_gemma":[0.02601424,0.001409038,0.001153947,0.0017835,0.001667201,0.002593642,0.002157411,0.00262989,0.0007915583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00223071,"about_ca_system_score_gemma":0.002546731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01303328,"about_ca_topic_score_gemma":0.01462481,"domain_scores_codex":[0.9983468,0.0007497497,0.0001002002,0.0002410619,0.0004242868,0.0001379089],"domain_scores_gemma":[0.973656,0.02214199,0.0008402708,0.00158553,0.001298806,0.0004774425],"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":[0.00005097779,0.00006587956,0.0007122814,0.0000428097,0.00004493487,0.00002534475,0.00002618874,0.9707906,0.000236037,0.01250247,0.0003541667,0.01514836],"study_design_scores_gemma":[0.000003826982,0.000002857818,0.0000192402,0.000001820209,0.000001817094,0.000002580197,0.000001258577,0.995326,0.00005357381,0.004530204,0.00005477308,0.000002142298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01360406,0.0001471116,0.9843806,0.000203855,0.00003896388,0.00007034868,0.00007065717,0.0006515755,0.0008327788],"genre_scores_gemma":[0.5735095,0.0002114177,0.4219998,0.0004172922,0.0001284925,0.0005161089,0.0005823686,0.000397968,0.002237194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01303328,"threshold_uncertainty_score":0.02745098,"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."}}