{"id":"W4414015740","doi":"10.11159/cist25.131","title":"A Case Study on Fault Type Classification and Action Prediction Using Unstructured Text Data from Automotive Parts Manufacturers","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of SMEs and Startups","keywords":"Automotive industry; Unstructured data; Computer science; Fault (geology); Type (biology); Action (physics); Data mining; Artificial intelligence; Natural language processing; Big data; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001971706,0.0008213401,0.0004991759,0.001829958,0.0009788302,0.0008350533,0.001159617,0.002093799,0.001210775],"category_scores_gemma":[0.007393846,0.0001902324,0.0006366218,0.002300113,0.000657377,0.001146823,0.0006270282,0.0009508038,0.0006773249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105074,"about_ca_system_score_gemma":0.0009936587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01663455,"about_ca_topic_score_gemma":0.02074826,"domain_scores_codex":[0.9983057,0.000500665,0.0001961042,0.0003590359,0.0004706386,0.0001677661],"domain_scores_gemma":[0.9913993,0.006397329,0.000404582,0.0005316886,0.001049566,0.0002175593],"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":[0.002066972,0.003018597,0.2850479,0.001976875,0.00034114,0.04270596,0.007698994,0.2464205,0.02418778,0.004310638,0.0397739,0.3424508],"study_design_scores_gemma":[0.0002190177,0.001258639,0.1313759,0.0002971556,0.0002795069,0.005971079,0.008964054,0.7622524,0.04347599,0.007976323,0.03772942,0.0002005297],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9560698,0.0008508549,0.02889944,0.002413374,0.0001683293,0.0003354324,0.007278161,0.0008463609,0.003138277],"genre_scores_gemma":[0.9571022,0.0003729969,0.03025946,0.0003393027,0.00007477221,0.0001795381,0.008406609,0.00006277284,0.003202294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01663455,"threshold_uncertainty_score":0.03307545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03235488762567704,"score_gpt":0.2731600207545474,"score_spread":0.2408051331288704,"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."}}