{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01742828,0.001533412,0.002763455,0.001690782,0.0009854824,0.001513184,0.002617752,0.001493519,0.001590837],"category_scores_gemma":[0.05256772,0.001224397,0.001881877,0.001322562,0.002474785,0.002064677,0.002246958,0.002142929,0.0003453223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001421133,"about_ca_system_score_gemma":0.002430052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005969631,"about_ca_topic_score_gemma":0.005077194,"domain_scores_codex":[0.9896319,0.007921256,0.0003385914,0.0009313293,0.0009137574,0.0002631656],"domain_scores_gemma":[0.9665493,0.02822324,0.001527186,0.002112512,0.001275933,0.0003117721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003397787,0.0002266493,0.006262795,0.0004964824,0.0005645198,0.0003211389,0.000402794,0.6575722,0.002277281,0.1894134,0.002109122,0.1400139],"study_design_scores_gemma":[0.00002342479,0.00003801685,0.0002795569,0.00001754621,0.00002501249,0.00002129368,0.00001778593,0.9648257,0.000494392,0.03371111,0.0005326939,0.00001350886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003158598,0.0001613451,0.9963132,0.00007975772,0.00001443055,0.0000398742,0.00002086313,0.000100387,0.0001115323],"genre_scores_gemma":[0.2531459,0.000722421,0.7428813,0.0003377679,0.0001913457,0.0007778837,0.0005783239,0.0001803549,0.001184806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01742828,"threshold_uncertainty_score":0.09217066,"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."}}