{"id":"W4411542027","doi":"10.1145/3715275.3732211","title":"Trustworthy ML Regulation as a Principal-Agent Problem","year":2025,"lang":"en","type":"article","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Trustworthiness; Computer science; Principal (computer security); Computer security; Principal component analysis; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02239996,0.001094296,0.002602425,0.0009664213,0.001679879,0.007716354,0.003419446,0.005157996,0.004896348],"category_scores_gemma":[0.05341951,0.001166209,0.001337214,0.001145744,0.007244027,0.006892082,0.004751128,0.007644601,0.0008214051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00304589,"about_ca_system_score_gemma":0.005000166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002305869,"about_ca_topic_score_gemma":0.001772519,"domain_scores_codex":[0.9768906,0.01333051,0.001047137,0.00420419,0.003040872,0.001486686],"domain_scores_gemma":[0.9254167,0.05742071,0.006300158,0.005396422,0.0036469,0.001819138],"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":[0.0002947601,0.0001873635,0.002372908,0.0004498884,0.0001993012,0.0005064951,0.0007569246,0.27901,0.001351004,0.6666582,0.005931512,0.04228167],"study_design_scores_gemma":[0.000129903,0.00007512766,0.00040757,0.00007257822,0.0000415968,0.0001346273,0.0001583648,0.3828239,0.0007734906,0.6098356,0.005504229,0.00004311882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02474624,0.0005991491,0.9551327,0.006861308,0.0001450241,0.0002329295,0.0001701782,0.0002359703,0.0118764],"genre_scores_gemma":[0.8205846,0.0007079741,0.1675321,0.001271039,0.0004669226,0.0004747179,0.0001980809,0.0001490961,0.008615642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02239996,"threshold_uncertainty_score":0.1184638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0590448122556027,"score_gpt":0.4013054912616431,"score_spread":0.3422606790060403,"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."}}