{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008862531,0.0004272079,0.0007428338,0.0003337705,0.000178388,0.000145995,0.0004191938,0.0004026783,0.0005612943],"category_scores_gemma":[0.006264923,0.0003731263,0.000108454,0.0008847529,0.00006212004,0.0001369448,0.0005416723,0.001054883,0.00005988604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002092585,"about_ca_system_score_gemma":0.0003485045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009765691,"about_ca_topic_score_gemma":0.00002744539,"domain_scores_codex":[0.9974309,0.0002655769,0.0006213987,0.0008080589,0.0003869097,0.0004872148],"domain_scores_gemma":[0.9943631,0.003861318,0.0003548938,0.0007280021,0.0005601235,0.000132587],"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":[0.0003516197,0.0009840913,0.07754306,0.008129185,0.001270134,0.0000248004,0.0009209603,0.006410903,0.001038915,0.884192,0.01007179,0.009062549],"study_design_scores_gemma":[0.0003894932,0.0001000357,0.001871281,0.0009855418,0.0003084463,0.00000592615,0.00003850479,0.06308867,0.0008881316,0.9313551,0.0004149364,0.0005539528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05582996,0.00006502651,0.9299279,0.00003781949,0.0006061115,0.0005857162,0.0001487949,0.0002492279,0.01254948],"genre_scores_gemma":[0.06634185,0.00006672322,0.9296639,0.0001448025,0.0001753732,0.0001843569,0.00004471596,0.00005110071,0.003327171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07567178,"threshold_uncertainty_score":0.9998721,"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."}}