{"id":"W4410907699","doi":"10.70777/si.v2i2.14611","title":"Pitfalls of Evidence-Based AI Policy","year":2025,"lang":"en","type":"article","venue":"SuperIntelligence - Robotics - Safety & Alignment","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000685824,0.0003036887,0.0005516469,0.0004509739,0.0001737948,0.00003012771,0.0003239842,0.000209132,0.0004227723],"category_scores_gemma":[0.0008677357,0.0002575249,0.0002592903,0.001062489,0.0003126368,0.0001709242,0.00008980784,0.000311153,0.0001487973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007354729,"about_ca_system_score_gemma":0.002306099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886081,"about_ca_topic_score_gemma":0.00005701034,"domain_scores_codex":[0.9969037,0.0001147517,0.001281415,0.0005217356,0.0005948393,0.0005835788],"domain_scores_gemma":[0.997588,0.0005362899,0.0001465629,0.0008845735,0.0005705809,0.0002739426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002769728,0.003071001,0.142987,0.003551389,0.000541561,0.00005484384,0.005191305,0.1881517,0.02723128,0.1914473,0.003367465,0.4316354],"study_design_scores_gemma":[0.0002299781,0.001687343,0.01039031,0.005697353,0.0004034737,0.00002429928,0.004393253,0.01909823,0.9196876,0.01598909,0.02163412,0.0007649619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0740966,0.004155743,0.7119298,0.1970636,0.00330363,0.00346655,0.00003918934,0.0002758487,0.005669023],"genre_scores_gemma":[0.9847952,0.002359651,0.005429039,0.005394419,0.0002679825,0.00004926765,0.00002550332,0.00002786224,0.001651044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9106987,"threshold_uncertainty_score":0.9999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2312626749960818,"score_gpt":0.4610154853350626,"score_spread":0.2297528103389808,"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."}}