{"id":"W4404554853","doi":"10.32388/cyzn0g","title":"Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning","year":2024,"lang":"en","type":"preprint","venue":"Qeios","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Generalization; Sample (material); Set (abstract data type); Computer science; Compression (physics); Data compression; Artificial intelligence; Machine learning; Theoretical computer science; Mathematics","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":[0.005677093,0.001692218,0.001254173,0.001291012,0.0005416537,0.002087907,0.002398191,0.002432524,0.003211945],"category_scores_gemma":[0.02474657,0.0007911156,0.000876263,0.001310278,0.002598031,0.006979955,0.003880985,0.005326005,0.0006894319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001698337,"about_ca_system_score_gemma":0.0009474953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009409793,"about_ca_topic_score_gemma":0.001279426,"domain_scores_codex":[0.9978956,0.0009772361,0.0001015059,0.0003885154,0.0005012087,0.0001360046],"domain_scores_gemma":[0.9863446,0.01013716,0.0008401431,0.001671245,0.0007275862,0.0002793508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002809327,0.0001001293,0.001501271,0.0002780962,0.0001636406,0.000136612,0.0002929331,0.5963264,0.004022717,0.2277703,0.003039255,0.1660878],"study_design_scores_gemma":[0.00001143819,0.00005608236,0.0001412628,0.00003827064,0.00001628525,0.00003635087,0.00001463513,0.8834556,0.00159695,0.1137639,0.0008572291,0.00001201158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01409564,0.0007159482,0.9822735,0.0006139595,0.0000314178,0.00004149698,0.00009456742,0.000324215,0.001809151],"genre_scores_gemma":[0.6385358,0.002235995,0.3490844,0.0009462598,0.0004380269,0.0006736962,0.0006718058,0.0005295078,0.006884538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005677093,"threshold_uncertainty_score":0.03002369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04949213236746966,"score_gpt":0.3020212841254092,"score_spread":0.2525291517579396,"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."}}