{"id":"W4409348492","doi":"10.1609/aaai.v39i27.35108","title":"Certified Trustworthiness in the Era of Large Language Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Access Control and Trust","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Trustworthiness; Certification; Computer science; Linguistics; Political science; Computer security; Philosophy; Law","routes":{"ca_aff":true,"ca_fund":false,"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":[0.03545273,0.0009318877,0.001523772,0.001506406,0.00255647,0.009507867,0.003367739,0.003531041,0.004038457],"category_scores_gemma":[0.1851844,0.001460341,0.001786454,0.001306983,0.009548331,0.01931285,0.01109185,0.009928705,0.001674174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007877019,"about_ca_system_score_gemma":0.007315815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004476962,"about_ca_topic_score_gemma":0.0044751,"domain_scores_codex":[0.9566506,0.02274925,0.002588542,0.004487182,0.01203995,0.001484515],"domain_scores_gemma":[0.8080554,0.116018,0.006301615,0.05536311,0.01183691,0.002424961],"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":[0.0004799865,0.0001317551,0.003210258,0.0005899109,0.0001757269,0.0003315525,0.001712282,0.09546564,0.005318056,0.724745,0.01429056,0.1535493],"study_design_scores_gemma":[0.00005532253,0.00007018894,0.0002887791,0.000147358,0.00004355238,0.0001407047,0.0001572622,0.2835406,0.005564841,0.6950751,0.01485763,0.00005869484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01832154,0.001390425,0.9590274,0.01006459,0.0002922081,0.0001700138,0.0001697275,0.004143454,0.006420513],"genre_scores_gemma":[0.6149691,0.001796432,0.3706012,0.003434725,0.0005907233,0.0004940667,0.0006105875,0.001906294,0.00559694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03545273,"threshold_uncertainty_score":0.1874942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0646789908497029,"score_gpt":0.3533518392017687,"score_spread":0.2886728483520657,"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."}}