{"id":"W4404672160","doi":"10.1007/978-3-031-73024-5_10","title":"Markov Knowledge Distillation: Make Nasty Teachers Trained by Self-undermining Knowledge Distillation Fully Distillable","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Distillation; Computer science; Markov chain; Markov process; Artificial intelligence; Machine learning; Chromatography; Chemistry; Mathematics; Statistics","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":[0.001066018,0.0007084068,0.0006007451,0.0003287563,0.0005728512,0.001077874,0.001788008,0.001300331,0.01118915],"category_scores_gemma":[0.004853563,0.0005063933,0.0005622791,0.000367564,0.001342731,0.004128642,0.003844813,0.003399915,0.003806322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006604283,"about_ca_system_score_gemma":0.00210312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002573628,"about_ca_topic_score_gemma":0.00678945,"domain_scores_codex":[0.9993006,0.0001707989,0.00002979287,0.0002286508,0.0001841525,0.00008602325],"domain_scores_gemma":[0.9983352,0.000697265,0.00008058106,0.0005145508,0.0002535544,0.000118885],"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":[0.0006747669,0.0002296207,0.001346796,0.0002573854,0.00007622729,0.0001082252,0.0005025523,0.1005172,0.01724619,0.1775756,0.03605099,0.6654145],"study_design_scores_gemma":[0.00007338514,0.0001218843,0.0003192655,0.00007050787,0.00004039955,0.00006963316,0.0001008756,0.7296533,0.01861057,0.2292258,0.02167656,0.00003778703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02786698,0.0005048056,0.941713,0.002047077,0.0004154322,0.00007760345,0.00064489,0.007602195,0.01912792],"genre_scores_gemma":[0.5046471,0.0003919469,0.4480588,0.0009877263,0.0001935238,0.0001757443,0.001471452,0.0009684344,0.04310526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01118915,"threshold_uncertainty_score":0.03743136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01415122816492169,"score_gpt":0.2643206319185038,"score_spread":0.2501694037535821,"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."}}