{"id":"W4409435353","doi":"10.1017/dsj.2025.7","title":"AI-driven FMEA: integration of large language models for faster and more accurate risk analysis","year":2025,"lang":"en","type":"article","venue":"Design Science","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"Lunds Universitet","keywords":"Computer science; Risk analysis (engineering); Linguistics; Business; 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":[0.001312855,0.00007890743,0.0001435993,0.0006387664,0.0001264038,0.0001677838,0.0008286226,0.00002958847,0.000001229314],"category_scores_gemma":[0.0007966743,0.00006567258,0.00004476621,0.002943126,0.0001308764,0.0008030257,0.0002211666,0.00008562569,8.559208e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003767397,"about_ca_system_score_gemma":0.0001380898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003041901,"about_ca_topic_score_gemma":0.000007357288,"domain_scores_codex":[0.9988669,0.0000412627,0.0001475905,0.0003707728,0.0003201619,0.0002532703],"domain_scores_gemma":[0.9986308,0.0005784621,0.00005127478,0.0004379616,0.0002455809,0.00005587816],"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":[0.00006209419,0.0001908323,0.02302021,0.0001488297,0.0003239729,0.00001190797,0.02579341,0.6237123,0.1427821,0.09564012,0.001090681,0.08722355],"study_design_scores_gemma":[0.0001336387,0.00002799314,0.009393704,0.00001366999,0.00002199032,3.36481e-7,0.00007808053,0.9720933,0.01704314,0.001124938,0.000007472705,0.00006169028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05910537,0.00007839876,0.9402972,0.000172603,0.0000526351,0.0002111495,0.00001002602,0.00005317955,0.00001942033],"genre_scores_gemma":[0.8617303,0.000006243847,0.1380805,0.00007014962,0.000004455982,0.00002400859,8.715484e-7,0.000002304008,0.00008122138],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8026249,"threshold_uncertainty_score":0.267805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03117296970543392,"score_gpt":0.3418963231019013,"score_spread":0.3107233533964674,"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."}}