{"id":"W7077871132","doi":"10.48448/z1ge-nn81","title":"uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Distillation; Process (computing); Filter (signal processing); Limiting; Scaling; Ground truth; Data modeling","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":[0.003480355,0.002625498,0.001496932,0.002081352,0.001222704,0.002861545,0.004708346,0.00270755,0.01177507],"category_scores_gemma":[0.01360944,0.001292506,0.002101749,0.001712247,0.001405589,0.006610437,0.005025621,0.005446185,0.008339473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001956177,"about_ca_system_score_gemma":0.002642911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009922748,"about_ca_topic_score_gemma":0.02201785,"domain_scores_codex":[0.9981114,0.0006500327,0.0000942647,0.0006377143,0.0003596848,0.0001470025],"domain_scores_gemma":[0.9951692,0.002385285,0.0001625313,0.001682718,0.0004547609,0.0001455058],"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":[0.0009288031,0.0006057888,0.003588757,0.001284923,0.0004011098,0.0003934682,0.000506903,0.1581556,0.0101889,0.03535602,0.115042,0.6735477],"study_design_scores_gemma":[0.00008959317,0.00008498884,0.0003666576,0.00009433487,0.00003593948,0.0001011474,0.00007660913,0.9102786,0.01058487,0.05300606,0.02522913,0.00005204477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01691321,0.001567315,0.8842561,0.001318768,0.0003932771,0.0002612327,0.00860591,0.0805046,0.006179628],"genre_scores_gemma":[0.2199701,0.0008879562,0.7187033,0.001240708,0.0001992445,0.0007396661,0.03873747,0.005928626,0.01359282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01177507,"threshold_uncertainty_score":0.03939158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07164414791243726,"score_gpt":0.3280595007821475,"score_spread":0.2564153528697103,"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."}}