{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004178296,0.0003175355,0.0004169873,0.0001938091,0.0001833314,0.001108428,0.001231065,0.0002506357,0.0001581814],"category_scores_gemma":[0.000235199,0.0002730975,0.0001882143,0.0003403815,0.00001584154,0.0001306811,0.003205798,0.001044447,0.0004677035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008175794,"about_ca_system_score_gemma":0.00009487355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00147731,"about_ca_topic_score_gemma":0.00004386453,"domain_scores_codex":[0.9974754,0.0003428446,0.0003736965,0.001105251,0.0004387154,0.0002640506],"domain_scores_gemma":[0.9981161,0.0002360498,0.0001961274,0.001210827,0.00008915724,0.0001517681],"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":[0.00001611209,0.000124647,0.002796161,0.0002687204,0.001297598,0.00001881353,0.004324479,0.6508856,0.001523561,0.07465532,0.08043706,0.183652],"study_design_scores_gemma":[0.00006109261,0.00002357371,0.001204242,0.0001128886,0.0002351971,0.00000114094,0.000008790685,0.7801943,0.000100746,0.01724739,0.2004881,0.0003225528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005310302,0.002082135,0.9853815,0.003145917,0.001744891,0.0002841153,0.00008289069,0.0008816876,0.001086578],"genre_scores_gemma":[0.7392074,0.0001705921,0.2518105,0.001019566,0.001362389,0.0002610151,0.003664464,0.0000795446,0.002424509],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7338971,"threshold_uncertainty_score":0.9999721,"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."}}