{"id":"W4404953002","doi":"10.1109/issre62328.2024.00035","title":"AI-Supported Eliminative Argumentation: Practical Experience Generating Defeaters to Increase Confidence in Assurance Cases","year":2024,"lang":"en","type":"article","venue":"","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Critical Systems Labs; University of Toronto","funders":"","keywords":"Argumentation theory; Computer science; Artificial intelligence; Psychology; Epistemology; Philosophy","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":[0.02427997,0.001449645,0.0006301521,0.001570201,0.001457087,0.003843392,0.004352326,0.002878135,0.005951165],"category_scores_gemma":[0.1151023,0.0006547368,0.0007585612,0.0009526868,0.003276563,0.004412168,0.004820071,0.002776454,0.001619677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332774,"about_ca_system_score_gemma":0.001469359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008830972,"about_ca_topic_score_gemma":0.001724527,"domain_scores_codex":[0.9763041,0.01758724,0.001034035,0.001202218,0.003369318,0.0005029928],"domain_scores_gemma":[0.7949193,0.1834017,0.002679411,0.01017642,0.006732265,0.002090902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00187707,0.005761349,0.02146452,0.004179117,0.0002928428,0.004761073,0.1164091,0.06287941,0.04367055,0.04051474,0.02297367,0.6752165],"study_design_scores_gemma":[0.002128639,0.00794955,0.01467757,0.00220852,0.0004375041,0.006285745,0.04300173,0.4353092,0.09596355,0.08795144,0.3033818,0.0007048239],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6584563,0.00102761,0.2946719,0.002796107,0.0001785805,0.001369473,0.0003983987,0.002866633,0.03823499],"genre_scores_gemma":[0.6780569,0.0004359056,0.3152251,0.0005244478,0.00004393661,0.0003636394,0.000554643,0.0004329107,0.004362441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02427997,"threshold_uncertainty_score":0.1284063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02100938820562495,"score_gpt":0.3085016468004227,"score_spread":0.2874922585947978,"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."}}