{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003308969,0.000276251,0.000202607,0.0003640721,0.000307207,0.0003563451,0.0004366945,0.000255174,0.00005719145],"category_scores_gemma":[0.0002202061,0.0003262055,0.0002113182,0.0004348648,0.00009055236,0.0007903447,0.0002873043,0.0004173295,0.0004686867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000511637,"about_ca_system_score_gemma":0.0004153027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005560483,"about_ca_topic_score_gemma":0.000003976202,"domain_scores_codex":[0.9985736,0.0001064433,0.000308364,0.0005968726,0.0001805005,0.000234189],"domain_scores_gemma":[0.9983621,0.000474231,0.0003007051,0.0003652748,0.0003768116,0.000120911],"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":[0.00003336859,0.00003496194,0.00002251241,0.00009419751,0.00001948869,0.000004050579,0.00009451413,0.509559,0.000001699198,0.4869672,0.001636598,0.001532387],"study_design_scores_gemma":[0.0005712836,0.00007281682,0.001753161,0.0001015932,0.00004136347,0.000001564763,0.00003307336,0.8218718,0.00002220168,0.1697381,0.00551305,0.0002800187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005350898,0.00001210941,0.9891797,0.0003205316,0.0007542729,0.0005336604,0.001084389,0.0003810155,0.00238339],"genre_scores_gemma":[0.9803228,0.000003604868,0.003676093,0.000121553,0.0001101697,0.00001470754,0.01536891,0.00001225817,0.0003698517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9855036,"threshold_uncertainty_score":0.999919,"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."}}