{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01484786,0.001175317,0.00175974,0.001770173,0.0009022037,0.001287476,0.002118427,0.001338157,0.002329045],"category_scores_gemma":[0.04294639,0.0007884259,0.001888408,0.001406337,0.002423419,0.002026467,0.002766087,0.002553127,0.0005406582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001411778,"about_ca_system_score_gemma":0.002278171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00574763,"about_ca_topic_score_gemma":0.00565978,"domain_scores_codex":[0.9918459,0.005756225,0.0003482307,0.0008088113,0.00102841,0.0002124494],"domain_scores_gemma":[0.9717622,0.02202523,0.001113842,0.003362002,0.001362434,0.0003742832],"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":[0.000500668,0.0002175592,0.01101234,0.001090951,0.0006108187,0.0007968982,0.0005609773,0.4326414,0.00688726,0.3357572,0.007783327,0.2021406],"study_design_scores_gemma":[0.00003386243,0.00008783106,0.001187157,0.0000399147,0.00002934045,0.0001033821,0.0000593689,0.8723712,0.001449705,0.1219727,0.002639684,0.00002593477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00342181,0.0001983469,0.995517,0.0002218543,0.00003542232,0.00004686854,0.00007740112,0.0001665175,0.0003148266],"genre_scores_gemma":[0.1904136,0.0006658594,0.8044167,0.000622811,0.0002893212,0.0006804973,0.0009401179,0.000296746,0.001674352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01484786,"threshold_uncertainty_score":0.07852393,"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."}}