{"id":"W4399511705","doi":"10.48550/arxiv.2406.04512","title":"To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Robustness (evolution); Distillation; Computer science; Biochemical engineering; Process engineering; Engineering; Chromatography; Chemistry","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":[0.006615957,0.003032137,0.001641229,0.00154735,0.001289119,0.003218683,0.003286452,0.002707406,0.005287901],"category_scores_gemma":[0.03064805,0.0008310676,0.001563912,0.001279735,0.002151019,0.008170827,0.005807331,0.005986632,0.003839294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00116952,"about_ca_system_score_gemma":0.002123376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01578973,"about_ca_topic_score_gemma":0.01666602,"domain_scores_codex":[0.9950821,0.002223564,0.0002505592,0.001513227,0.0005798272,0.000350681],"domain_scores_gemma":[0.9877551,0.007963732,0.0003090055,0.002816353,0.0008634512,0.00029237],"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":[0.001599482,0.000358061,0.005399429,0.0006111657,0.000652866,0.000370254,0.0006038513,0.4799592,0.009675338,0.02114326,0.02806121,0.4515659],"study_design_scores_gemma":[0.00006829682,0.0001503338,0.0006067746,0.0001081539,0.00007892931,0.0001183795,0.0001630927,0.9564605,0.009278819,0.02777675,0.005124589,0.00006543995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2678349,0.01106484,0.6463215,0.009209255,0.001357549,0.000285732,0.005604942,0.03435216,0.02396903],"genre_scores_gemma":[0.815489,0.001166689,0.1603762,0.00230695,0.0002629818,0.0002063851,0.00829758,0.002693384,0.009200781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01578973,"threshold_uncertainty_score":0.03498894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1658194347244474,"score_gpt":0.2395218233615591,"score_spread":0.07370238863711168,"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."}}