{"id":"W4405031622","doi":"10.48550/arxiv.2411.19908","title":"Another look at statistical inference with machine learning-imputed data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Connaught Fund; University of Toronto","keywords":"Inference; Computer science; Artificial intelligence","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001529042,0.0002776723,0.0002630179,0.0001681393,0.0004557566,0.0001830826,0.001116817,0.000099383,0.003149298],"category_scores_gemma":[0.00002455842,0.000250688,0.00004882784,0.00007519103,0.001171348,0.0002202324,0.002565434,0.0008203267,0.0008250585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001653246,"about_ca_system_score_gemma":0.0001919667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007347699,"about_ca_topic_score_gemma":0.003689151,"domain_scores_codex":[0.9983734,0.00006943991,0.0001336253,0.001042231,0.000121118,0.0002601763],"domain_scores_gemma":[0.9987466,0.0001022582,0.0001214301,0.0008353367,0.00008210012,0.0001123273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001352588,0.00008476978,0.000505181,0.0001988933,0.0001317965,0.0006791137,0.003026217,0.006335759,0.000006472852,0.9838183,0.004868951,0.000209266],"study_design_scores_gemma":[0.0006483294,0.0004086155,0.0001697699,0.0004131003,0.000506602,0.0000102522,0.0004081796,0.2715048,0.000006328713,0.191611,0.5330403,0.001272677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2328228,0.001368462,0.02702738,0.001112465,0.003247957,0.001032288,0.006512779,0.001591971,0.7252839],"genre_scores_gemma":[0.9508793,0.00006125859,0.00009597569,0.0001202976,0.0002142712,4.548996e-7,0.0003356331,0.00002660088,0.04826621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7922073,"threshold_uncertainty_score":0.9999945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1796749919673583,"score_gpt":0.2007751662993064,"score_spread":0.02110017433194808,"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."}}