{"id":"W2127163205","doi":"10.1145/1102351.1102412","title":"PAC-Bayes risk bounds for sample-compressed Gibbs classifiers","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bayes' theorem; Gibbs sampling; Computer science; Naive Bayes classifier; Sample (material); Artificial intelligence; Pattern recognition (psychology); Machine learning; Bayesian probability; Support vector machine; Physics","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":[0.01293769,0.002172709,0.003046972,0.002338678,0.00154437,0.004198614,0.003787411,0.003431171,0.006576824],"category_scores_gemma":[0.08043876,0.001257302,0.001754918,0.002255919,0.00465977,0.0100389,0.004590363,0.008017263,0.001680938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005689386,"about_ca_system_score_gemma":0.002633612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002703912,"about_ca_topic_score_gemma":0.00223687,"domain_scores_codex":[0.9895654,0.003499318,0.0004284282,0.001300392,0.004611919,0.0005944484],"domain_scores_gemma":[0.9516186,0.03920404,0.001610316,0.003180435,0.00370108,0.0006856627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003396209,0.00009763387,0.001334011,0.0002855625,0.0001383608,0.0001971356,0.0002658103,0.276809,0.001161946,0.627534,0.007695977,0.08414093],"study_design_scores_gemma":[0.00002528413,0.00003730877,0.0002473129,0.00006313716,0.0000298766,0.0001246444,0.00001743498,0.6199185,0.0008562056,0.3762612,0.002391062,0.00002800896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006103491,0.002219569,0.9829746,0.001465499,0.0001529549,0.0000756914,0.0001670946,0.0002874715,0.006553672],"genre_scores_gemma":[0.3947695,0.005733889,0.5745527,0.002396531,0.002267621,0.001490695,0.001685709,0.001085965,0.01601744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01293769,"threshold_uncertainty_score":0.0684219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0106195081588074,"score_gpt":0.2574498896767193,"score_spread":0.2468303815179119,"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."}}