{"id":"W3040388267","doi":"10.1145/3377930.3390210","title":"Advanced statistical analysis of empirical performance scaling","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scaling; Computer science; Heuristic; Range (aeronautics); Polynomial; Time complexity; Algorithm; Solver; Degree (music); Bounded function; Theoretical computer science; Artificial intelligence; 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":[0.01844367,0.0016386,0.001930964,0.004637028,0.001191837,0.002794617,0.002379178,0.001718811,0.006114734],"category_scores_gemma":[0.1871535,0.0008317588,0.001533496,0.004754485,0.003803354,0.006858699,0.003052115,0.006261515,0.001345174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002144824,"about_ca_system_score_gemma":0.002331554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002090856,"about_ca_topic_score_gemma":0.001125231,"domain_scores_codex":[0.9849107,0.005619247,0.0007627209,0.003466516,0.004238953,0.001001927],"domain_scores_gemma":[0.8182037,0.1239185,0.01143877,0.03559805,0.009243889,0.001597056],"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":[0.0004496866,0.0006125888,0.03742109,0.0008028262,0.0005295314,0.0005296197,0.000897183,0.3831182,0.004445792,0.4231154,0.02275648,0.1253216],"study_design_scores_gemma":[0.00003966668,0.0001285615,0.005900006,0.00007462895,0.0000458393,0.0002023864,0.0001449301,0.8387288,0.001882325,0.1482468,0.004550696,0.0000553915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09591594,0.002173975,0.881422,0.002505518,0.0003916838,0.0003430245,0.001732172,0.003506074,0.01200964],"genre_scores_gemma":[0.8727232,0.001405716,0.1149486,0.001043107,0.0008511652,0.001625795,0.002997772,0.001344448,0.003060258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01844367,"threshold_uncertainty_score":0.09754062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03903037565258369,"score_gpt":0.3306267773805176,"score_spread":0.2915964017279339,"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."}}