{"id":"W2996151541","doi":"","title":"A Constructive Prediction of the Generalization Error Across Scales","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Generalization; Dependency (UML); Computer science; Constructive; Construct (python library); Artificial neural network; Artificial intelligence; Functional dependency; Scale (ratio); Range (aeronautics); Scaling; Generalization error; Machine learning; Algorithm; Theoretical computer science; Data mining; Mathematics; Process (computing)","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":[],"consensus_categories":[],"category_scores_codex":[0.00005856957,0.00007597957,0.00007585913,0.00002576771,0.0002160051,0.0001095843,0.0006320665,0.00003172658,0.00004657247],"category_scores_gemma":[0.0001505673,0.00006117869,0.00006398433,0.0003329173,0.000109382,0.0002545883,0.0001759678,0.0001816687,0.00001717803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001880343,"about_ca_system_score_gemma":0.00003956012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002162365,"about_ca_topic_score_gemma":0.000006683121,"domain_scores_codex":[0.9990271,0.00008179976,0.0002186049,0.0002659916,0.0003090278,0.00009743637],"domain_scores_gemma":[0.9991907,0.00007468516,0.000194843,0.0001988265,0.0002930487,0.00004782609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000164056,0.00006469475,0.04170839,0.000006075878,0.00005635463,0.000001152044,0.004535801,0.06824885,0.0160945,0.8574606,0.001478123,0.01032907],"study_design_scores_gemma":[0.0003158169,0.00006036213,0.0675515,0.00003204477,0.000005859275,0.000007128822,0.0005851603,0.9197649,0.003611052,0.005408243,0.002560414,0.00009747663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3798777,0.00001386111,0.5453901,0.0569152,0.001084085,0.0005162417,0.0001160345,0.0002690737,0.01581773],"genre_scores_gemma":[0.9977198,0.00001207351,0.001465088,0.0003372869,0.0001257587,0.00003415426,0.00002394485,0.000004912448,0.0002769517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8520523,"threshold_uncertainty_score":0.2494794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0703062179486579,"score_gpt":0.3414039447837197,"score_spread":0.2710977268350617,"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."}}