{"id":"W4391012831","doi":"10.48550/arxiv.2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Estimator; Estimation; Bayes' theorem; Shot (pellet); Computer science; Conditional probability; Image (mathematics); Process (computing); Conditional probability distribution; Set (abstract data type); Artificial intelligence; Statistics; Machine learning; Pattern recognition (psychology); Mathematics; Bayesian probability; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002980085,0.001154089,0.001663506,0.00149495,0.0008078341,0.001782924,0.002582992,0.001384536,0.004719637],"category_scores_gemma":[0.01386689,0.000688176,0.000923423,0.001136604,0.001597762,0.00372582,0.002626219,0.003049051,0.001410128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001592188,"about_ca_system_score_gemma":0.002659898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007924547,"about_ca_topic_score_gemma":0.007553444,"domain_scores_codex":[0.9976005,0.0006842242,0.0001156729,0.0006778763,0.0007178395,0.0002038795],"domain_scores_gemma":[0.9955838,0.002757516,0.0003611035,0.0004632727,0.0006824771,0.0001518339],"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":[0.000411554,0.000175586,0.002607202,0.0004988969,0.0001764131,0.0001443995,0.0004066086,0.3768677,0.006271537,0.07995699,0.009292277,0.5231909],"study_design_scores_gemma":[0.00001237984,0.00002963916,0.0004314959,0.00003771142,0.00001489116,0.00005048652,0.00002349158,0.9626793,0.003238691,0.03173077,0.001724658,0.0000266062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007944388,0.0005424902,0.9877364,0.0003069323,0.00003998994,0.00005232741,0.0002093971,0.001070429,0.00209779],"genre_scores_gemma":[0.50152,0.0009012378,0.4876742,0.0005674952,0.0001859174,0.0003513634,0.001743036,0.0004811775,0.006575624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007924547,"threshold_uncertainty_score":0.01578879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0538596064554008,"score_gpt":0.2118131156306399,"score_spread":0.1579535091752391,"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."}}