{"id":"W3148086288","doi":"10.48550/arxiv.2104.03446","title":"Functional L-Optimality Subsampling for Massive Data","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science","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"],"consensus_categories":[],"category_scores_codex":[0.0005915292,0.0002596104,0.0004437356,0.00006757817,0.0001453279,0.00008658917,0.0007658746,0.0002794909,0.0005540668],"category_scores_gemma":[0.002659477,0.0002906949,0.0001626517,0.0001613074,0.000112598,0.0001215141,0.001818355,0.0004710779,0.00001138847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165296,"about_ca_system_score_gemma":0.0002833353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005290925,"about_ca_topic_score_gemma":0.00003452436,"domain_scores_codex":[0.9980859,0.0001650142,0.0002569505,0.001113742,0.000088909,0.0002894473],"domain_scores_gemma":[0.9951898,0.002534581,0.0002518742,0.001511718,0.0003769394,0.0001351069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000098623,0.0001550538,0.0006881521,0.0005458033,0.0002413353,0.00007564886,0.00004983444,0.006466656,0.00004008712,0.988598,0.002286152,0.0007546405],"study_design_scores_gemma":[0.0003885304,0.00002524735,0.001112649,0.000135028,0.0003394087,0.000001813067,0.0002379771,0.2308228,0.00006035082,0.7662134,0.0002926524,0.0003701586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05549732,0.00002695087,0.9413492,0.00006096551,0.0005759635,0.0003338545,0.00100246,0.0000813864,0.00107191],"genre_scores_gemma":[0.5960049,0.00004107111,0.4022575,0.00005144144,0.0001900662,0.000002839181,0.0006171783,0.00003016843,0.0008048367],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5405076,"threshold_uncertainty_score":0.9999545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5717554437975846,"score_gpt":0.3239819711541475,"score_spread":0.2477734726434371,"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."}}