{"id":"W4402469547","doi":"10.1080/10618600.2024.2402279","title":"Optimal Subsampling for Functional Quasi-Mode Regression with Big Data","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Control Systems and Identification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Regression analysis; Regression; Statistics; Big data; Mathematics; Econometrics; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002057822,0.0000793213,0.0001361953,0.000114977,0.00006382403,0.0001219436,0.00006751453,0.00003361519,0.000003662377],"category_scores_gemma":[0.00003537238,0.00005519073,0.00002711371,0.0001071597,0.00003103562,0.0001386403,0.00001125366,0.0001258897,4.081147e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000138041,"about_ca_system_score_gemma":0.00004353096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002883987,"about_ca_topic_score_gemma":0.000007506675,"domain_scores_codex":[0.9992633,0.00001148572,0.0003044939,0.00009988083,0.0002406342,0.00008018208],"domain_scores_gemma":[0.9991801,0.0004538239,0.00005778387,0.00005610268,0.0001857713,0.00006635805],"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":[0.0003528969,0.00009275076,0.0006615671,0.00071127,0.0005292132,0.00004460873,0.0001626283,0.7402517,0.0004463565,0.07431027,0.03998697,0.1424498],"study_design_scores_gemma":[0.0003763092,0.0001183302,0.005800591,0.0001445477,0.00006075001,0.0001258316,0.00001559654,0.9652809,0.00000291526,0.01986936,0.008123424,0.00008142169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02689811,0.0008824141,0.9708031,0.0002077011,0.0006134851,0.00006406379,0.0005049029,0.00002040493,0.000005788744],"genre_scores_gemma":[0.9486006,0.00005522519,0.05048671,0.00001094539,0.0005543581,0.000002623173,0.0002558285,0.00001385142,0.00001983203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9217025,"threshold_uncertainty_score":0.2250613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03885070936412945,"score_gpt":0.2764204649498461,"score_spread":0.2375697555857166,"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."}}