{"id":"W4407590575","doi":"10.48550/arxiv.2502.09618","title":"Pitfalls of Evidence-Based AI Policy","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Real world evidence; Economics; Political science; Computer science; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.3102045,0.001887031,0.003738364,0.01040342,0.008351237,0.02382734,0.01011369,0.03186681,0.003858108],"category_scores_gemma":[0.3984274,0.002083597,0.003539157,0.005648565,0.06600273,0.03623627,0.01417438,0.05861003,0.001977442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01927649,"about_ca_system_score_gemma":0.03289539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009489047,"about_ca_topic_score_gemma":0.005065986,"domain_scores_codex":[0.7026501,0.1734075,0.02060074,0.01959939,0.07891564,0.004826513],"domain_scores_gemma":[0.3679433,0.5591698,0.01118798,0.01632277,0.03996225,0.005413847],"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":[0.00004650959,0.00004460732,0.0002484879,0.0005249158,0.00006648913,0.00009589091,0.0007904809,0.0009806469,0.00008131299,0.9611965,0.01742297,0.01850118],"study_design_scores_gemma":[0.00007687838,0.00002826453,0.0002055582,0.001723192,0.00003746399,0.0001077313,0.0005095686,0.00133462,0.0001865244,0.9471611,0.04858186,0.00004732448],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.00139492,0.02018506,0.02107375,0.933273,0.00226915,0.00008627593,0.00009463637,0.00006267765,0.02156063],"genre_scores_gemma":[0.2528757,0.03105042,0.07904425,0.6191506,0.01228555,0.001165726,0.0001809123,0.0002066289,0.004040178],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9916488,"threshold_uncertainty_score":0.8506407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5813366753732095,"score_gpt":0.5334698738213864,"score_spread":0.0478668015518231,"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."}}