{"id":"W4407384740","doi":"10.48550/arxiv.2502.05353","title":"Point-Identifying Semiparametric Sample Selection Models with No Excluded Variable","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Semiparametric regression; Sample (material); Selection (genetic algorithm); Variable (mathematics); Semiparametric model; Econometrics; Computer science; Feature selection; Statistics; Artificial intelligence; Mathematics; Nonparametric statistics; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01936862,0.001030318,0.002583182,0.001423911,0.0008465246,0.002028283,0.003449736,0.001830844,0.006319333],"category_scores_gemma":[0.07844264,0.000948319,0.002022287,0.001724293,0.002803865,0.003435577,0.004311115,0.003342596,0.001404213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009146585,"about_ca_system_score_gemma":0.001392726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001600207,"about_ca_topic_score_gemma":0.001542848,"domain_scores_codex":[0.983442,0.01277769,0.0004656866,0.001431003,0.001465073,0.0004185904],"domain_scores_gemma":[0.9250014,0.0593222,0.005632729,0.007220521,0.002352937,0.0004703028],"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":[0.0003012894,0.0002800279,0.02124559,0.000474424,0.0005418182,0.000591787,0.001198627,0.169619,0.001181706,0.6418526,0.004282329,0.1584308],"study_design_scores_gemma":[0.0001042954,0.000229349,0.002991806,0.00008733112,0.0001029664,0.0001662159,0.0001796936,0.527455,0.001022221,0.463374,0.004230686,0.00005644423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009999636,0.00009403982,0.9883047,0.0002511254,0.00001984762,0.0001075461,0.0001118634,0.0001768899,0.0009343637],"genre_scores_gemma":[0.6624169,0.0005422772,0.3259821,0.0005466252,0.0002084181,0.001552306,0.0009522637,0.0001905161,0.007608547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01936862,"threshold_uncertainty_score":0.1024323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2084485786293317,"score_gpt":0.3848030266356639,"score_spread":0.1763544480063322,"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."}}