{"id":"W2136945987","doi":"","title":"Risk Bounds for Randomized Sample Compressed Classifiers","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"occam; Computer science; Classifier (UML); Compressed sensing; Compression (physics); Data compression; Sample (material); Artificial intelligence; Upper and lower bounds; Algorithm; Pattern recognition (psychology); Mathematics","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":[0.0005427471,0.0001111814,0.0003046167,0.00005994732,0.0003980762,0.00008617334,0.0004876528,0.00004125457,0.00004557598],"category_scores_gemma":[0.0004915583,0.00008172821,0.0001845422,0.0001403165,0.0001043461,0.0001450091,0.00007560157,0.0001308655,0.00002307057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001094214,"about_ca_system_score_gemma":0.00004453393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004512347,"about_ca_topic_score_gemma":0.00000531264,"domain_scores_codex":[0.998953,0.0001620142,0.0001998361,0.0002791957,0.0001652783,0.0002406798],"domain_scores_gemma":[0.9978852,0.001529926,0.00009409233,0.0003466223,0.00005760334,0.0000865111],"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":[0.01109753,0.0005843065,0.007925165,0.0000794773,0.0006030384,0.00003465444,0.007255774,0.01005072,0.0002767982,0.6125361,0.1446947,0.2048617],"study_design_scores_gemma":[0.04855142,0.00004077951,0.0002640715,0.000002443659,0.000008202119,0.000008282681,0.000008002207,0.9089512,0.0001304728,0.008605238,0.03328497,0.0001449795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003006224,0.00004875676,0.9897741,0.0007346205,0.0003665315,0.0003059036,0.000005093249,0.0003292432,0.005429504],"genre_scores_gemma":[0.3228718,0.00004709135,0.6716362,0.0005259727,0.0001558066,0.00008950839,0.000009331682,0.00001177329,0.004652591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8989004,"threshold_uncertainty_score":0.333278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0170943287020262,"score_gpt":0.254127227780124,"score_spread":0.2370328990780978,"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."}}