{"id":"W7136098884","doi":"","title":"Optimal subsampling for high-dimensional partially linear models via machine learning methods","year":2025,"lang":"en","type":"article","venue":"CityU Scholars","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Endogeneity; Estimator; Instrumental variable; Linear model; Leverage (statistics); Martingale (probability theory); Parametric statistics; Asymptotic distribution; Consistency (knowledge bases); Additive model","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":[0.00263608,0.0002106224,0.0004163022,0.0001112225,0.000330622,0.0001005666,0.0002336734,0.0001558489,0.0001247103],"category_scores_gemma":[0.007760611,0.0001934251,0.0001178719,0.0002281003,0.00006619311,0.0001763282,0.0001540296,0.0006117771,0.000007730097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004545786,"about_ca_system_score_gemma":0.00008521311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002710597,"about_ca_topic_score_gemma":0.000003673932,"domain_scores_codex":[0.9981288,0.0004128703,0.0004752433,0.000400389,0.0002076357,0.0003750289],"domain_scores_gemma":[0.9952099,0.003990518,0.000121072,0.0002781461,0.0002808025,0.0001195901],"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":[0.0001716977,0.0001406176,0.0002883859,0.0001775186,0.0001287882,0.000004488782,0.00009204112,0.01762413,0.01150885,0.8893101,0.0002278748,0.0803255],"study_design_scores_gemma":[0.0004215603,0.00006355188,0.0001100038,0.00005994094,0.00007068864,0.000001770816,0.000005870021,0.4772706,0.005926798,0.5151116,0.0008044452,0.000153093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05917054,0.0001206227,0.9392892,0.0002032972,0.0002933437,0.0003093796,0.00003450529,0.0001256004,0.0004535852],"genre_scores_gemma":[0.0679881,0.000004424884,0.9309921,0.0002564964,0.00007092581,0.00005901952,0.00001737999,0.00003020789,0.0005814005],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4596465,"threshold_uncertainty_score":0.9290737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1317479525967904,"score_gpt":0.4403878970745448,"score_spread":0.3086399444777544,"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."}}