{"id":"W4315486958","doi":"10.1007/s00170-022-10649-7","title":"Online prediction of automotive tempered glass quality using machine learning","year":2023,"lang":"en","type":"article","venue":"The International Journal of Advanced Manufacturing Technology","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Machine learning; Quality assurance; Automotive industry; Artificial intelligence; Quality (philosophy); Support vector machine; Mean squared error; Regression; Computer science; Regression analysis; Field (mathematics); Process (computing); Industrial engineering; Engineering; Mathematics; Statistics","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":[0.0004647553,0.0001087435,0.0002335205,0.0005989913,0.00005873981,0.00001346076,0.0003535519,0.0001268081,0.00001429247],"category_scores_gemma":[0.0002821805,0.0000818143,0.00009590291,0.0002344899,0.0000486823,0.000145676,0.00008243703,0.0005329038,0.000003400288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001709584,"about_ca_system_score_gemma":0.00001693897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002818361,"about_ca_topic_score_gemma":0.000009891824,"domain_scores_codex":[0.9987888,0.00004366769,0.000604327,0.00008482196,0.000344701,0.0001336285],"domain_scores_gemma":[0.9990826,0.0001201494,0.0003971128,0.0001229309,0.0002554202,0.00002184885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001131815,0.00002592396,0.0005249133,0.00001893098,0.0002423217,0.00002048318,0.0001425253,0.6309032,0.3480697,0.00008600138,0.00004622158,0.0198066],"study_design_scores_gemma":[0.000987694,0.000162582,0.004017414,0.0001725019,0.00002173679,0.0002333723,0.0008485504,0.02727313,0.9617882,0.001309794,0.003086191,0.00009885922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937004,0.00009214442,0.003625353,0.0002641032,0.00187597,0.00008029743,0.00003320699,0.0002834051,0.00004515798],"genre_scores_gemma":[0.9988316,0.0001336504,0.0007287571,0.000006613639,0.0002269709,0.000001512208,0.000006156772,0.00001889205,0.00004579002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6137185,"threshold_uncertainty_score":0.333629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03302414998139032,"score_gpt":0.2966282283219305,"score_spread":0.2636040783405402,"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."}}