{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03446443,0.001273601,0.001870282,0.002805275,0.001617809,0.005109801,0.004736236,0.003586076,0.007109588],"category_scores_gemma":[0.1715501,0.001093457,0.002496116,0.00390494,0.01036484,0.01204412,0.005078059,0.01337302,0.001248372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002274272,"about_ca_system_score_gemma":0.0029498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004183348,"about_ca_topic_score_gemma":0.003102273,"domain_scores_codex":[0.9814379,0.01386442,0.0004434506,0.001828769,0.002131977,0.000293459],"domain_scores_gemma":[0.8380128,0.142831,0.003574402,0.01170877,0.003141386,0.0007317551],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005805485,0.00005783122,0.002398777,0.0002631085,0.0001813546,0.000113469,0.0003545056,0.02017005,0.0002656958,0.9236692,0.005119096,0.04734889],"study_design_scores_gemma":[0.00002100584,0.00003856387,0.0004343409,0.0001323052,0.00002043304,0.00006168821,0.00006115068,0.05427819,0.0002665308,0.9368149,0.007843617,0.00002742357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002397318,0.002198202,0.9813948,0.01094146,0.000342818,0.00003478183,0.0001878397,0.0001820303,0.002320837],"genre_scores_gemma":[0.2243819,0.007060384,0.7417844,0.01366035,0.003299149,0.0004707634,0.0007933756,0.0005962647,0.007953491],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9655356,"threshold_uncertainty_score":0.1822675,"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."}}