{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001119558,0.00004763927,0.0001367187,0.00006717147,0.0000322997,0.00002471432,0.0003155728,0.00001785465,0.00007197403],"category_scores_gemma":[0.0001430548,0.00003893034,0.00003291153,0.0009531888,0.0000200123,0.0001664645,0.00008521941,0.00007343631,0.00002899807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005468001,"about_ca_system_score_gemma":0.00001929146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005764491,"about_ca_topic_score_gemma":9.742932e-7,"domain_scores_codex":[0.999316,0.00003792971,0.0001731608,0.000216049,0.0001685549,0.00008824697],"domain_scores_gemma":[0.9994979,0.0001039051,0.00005284911,0.000230977,0.00003590126,0.0000785055],"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":[0.00003360748,0.00008539119,0.2941954,0.00005610982,0.0002141716,0.00000285651,0.001463628,0.02807541,0.001820084,0.09638049,0.001268266,0.5764046],"study_design_scores_gemma":[0.00005654749,0.00003506798,0.2028797,0.000001051296,0.00002735709,1.490765e-7,0.00001257478,0.795212,0.0002301042,0.00001556824,0.001488687,0.00004110769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09407853,0.000008136489,0.9013042,0.002520739,0.00001510947,0.00002127431,0.000004093258,0.00007682079,0.00197108],"genre_scores_gemma":[0.8641996,0.000004704939,0.1352679,0.0004713947,0.000008272156,0.000001126826,0.0000232018,0.000001534475,0.00002228888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.770121,"threshold_uncertainty_score":0.1587533,"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."}}