{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001952922,0.000194163,0.0001767873,0.0001862593,0.00002793384,0.0001347602,0.00009977542,0.00005603407,0.0001684595],"category_scores_gemma":[0.000258033,0.0002011652,0.00003176201,0.0004706983,0.00002411677,0.000502768,0.00002724919,0.0001814063,0.0001489524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002586712,"about_ca_system_score_gemma":0.00006691846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002078538,"about_ca_topic_score_gemma":0.00007675399,"domain_scores_codex":[0.998816,0.00003516567,0.0003656456,0.000299428,0.0001918378,0.0002919354],"domain_scores_gemma":[0.9991968,0.0004403255,0.00001332445,0.0001843759,0.00003886599,0.0001262629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003214382,0.0000497439,0.002694505,0.0008052803,0.0001409071,0.003863246,0.02069271,0.8357279,0.1105874,0.01190343,0.009005556,0.004497152],"study_design_scores_gemma":[0.0002368017,0.0000566222,0.003027238,0.0005332641,0.00001458395,0.0005240102,0.002448467,0.9324707,0.05229171,0.00002353977,0.007779343,0.0005937095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6377348,0.000324244,0.3542379,0.0008198164,0.001222816,0.0006189482,0.00001378575,0.001291458,0.003736264],"genre_scores_gemma":[0.9843876,0.00000847864,0.014738,0.0002109432,0.00008270743,0.0002878092,0.000006525375,0.00003835851,0.0002395946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3466528,"threshold_uncertainty_score":0.8203279,"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."}}