{"id":"W4412530917","doi":"10.1007/978-3-031-86893-1_33","title":"Comparison of Deep Learning Architectures in Ultrasonic Quality Control for Resistance Spot Welding Using Semantic Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in production engineering","topic":"Advanced Welding Techniques Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Spot welding; Segmentation; Artificial intelligence; Welding; Computer science; Quality (philosophy); Ultrasonic sensor; Computer vision; Materials science; Acoustics; Composite material; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004607681,0.0004421278,0.0009075447,0.000964489,0.0000481298,0.00001856725,0.0001592856,0.0003406992,0.00000841156],"category_scores_gemma":[0.000943229,0.0005368561,0.0001744384,0.0003012053,0.00002920418,0.00007154055,0.00002017258,0.0009803212,1.96595e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006153787,"about_ca_system_score_gemma":0.00001781982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001560892,"about_ca_topic_score_gemma":0.0002862138,"domain_scores_codex":[0.9979792,0.00002988931,0.0009375342,0.0004990215,0.0002205811,0.0003337782],"domain_scores_gemma":[0.9987953,0.0005095822,0.0002623882,0.0003232475,0.00008103305,0.00002843923],"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":[0.00003930556,0.000008061049,0.0004700301,0.001629149,0.00009603694,0.0000010808,0.0002520103,0.9554616,0.03308785,0.0003818897,0.000001359305,0.008571645],"study_design_scores_gemma":[0.0004604465,0.00002719788,0.0001376179,0.002259851,0.0001699079,0.000003149979,0.00001270891,0.8690065,0.122726,0.004185764,0.0003243257,0.0006864835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00648565,0.003036435,0.9886624,0.00003276071,0.0004350561,0.0007677552,0.000009708731,0.0003610126,0.0002092544],"genre_scores_gemma":[0.9179345,0.0001053139,0.08139557,0.000004206683,0.0001573399,0.00005282613,0.00003472582,0.0001042351,0.0002112412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9114489,"threshold_uncertainty_score":0.9997083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524402365401063,"score_gpt":0.2964221870662584,"score_spread":0.2811781634122478,"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."}}