{"id":"W4396955972","doi":"10.1017/pds.2024.204","title":"Integrating large language models for improved failure mode and effects analysis (FMEA): a framework and case study","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Design Society","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Failure mode and effects analysis; Computer science; Reliability engineering; Natural language processing; Engineering","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":[0.001093223,0.0001505379,0.000230632,0.00007579075,0.0001676236,0.0003862986,0.0003987237,0.00008992689,2.053984e-7],"category_scores_gemma":[0.000535092,0.0001043344,0.0001700508,0.001009987,0.00003918463,0.0003967807,0.0003972434,0.0002976847,7.30057e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003917135,"about_ca_system_score_gemma":0.00002809623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005091457,"about_ca_topic_score_gemma":0.000003634742,"domain_scores_codex":[0.9989725,0.00001383191,0.0001497433,0.0004112744,0.0001905593,0.0002621199],"domain_scores_gemma":[0.9982249,0.00137116,0.00004599997,0.0001612472,0.0001327815,0.00006395814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004751019,0.0005381246,0.01323488,0.005597662,0.007091317,0.0001119248,0.8288107,0.002616008,0.07156669,0.04342724,0.004704274,0.02225366],"study_design_scores_gemma":[0.0002028732,0.0001117574,0.00007864463,0.000091355,0.0001939792,0.000049636,0.006389426,0.9867889,0.002365274,0.003605234,0.00000300236,0.0001199093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3769459,0.000429315,0.6217436,0.0001306832,0.00002740259,0.0005960569,0.000004262012,0.0001215556,0.000001262601],"genre_scores_gemma":[0.7522269,0.000005702218,0.2475768,0.00002739074,0.00002440338,0.0001067815,1.479994e-7,0.00001353986,0.00001831756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9841729,"threshold_uncertainty_score":0.4254634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01332308256745129,"score_gpt":0.290211175171413,"score_spread":0.2768880926039617,"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."}}