{"id":"W4413925757","doi":"10.1109/lsens.2025.3605519","title":"PixTransNet: A Sensor-Aware CNN–Transformer Model for Magnetic Flux Leakage Defect Segmentation","year":2025,"lang":"en","type":"article","venue":"IEEE Sensors Letters","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Magnetic flux leakage; Transformer; Leakage (economics); Segmentation; Materials science; Computer science; Artificial intelligence; Electrical engineering; Engineering; Economics; Electromagnetic coil; Voltage","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":[0.0001350496,0.0003330954,0.0002682393,0.0002675056,0.0001036929,0.00004844647,0.0001730582,0.0001252804,0.00001689902],"category_scores_gemma":[0.00001796358,0.0003754056,0.000202423,0.0002600024,0.0000793293,0.0001519411,0.00000489739,0.0002313543,0.00001713118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001921119,"about_ca_system_score_gemma":0.00002027368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001348285,"about_ca_topic_score_gemma":0.00001142286,"domain_scores_codex":[0.9986548,0.00003650644,0.0003228202,0.0003480054,0.0001667575,0.0004710562],"domain_scores_gemma":[0.9993827,0.0001739707,0.00003050179,0.0002964873,0.00005341574,0.00006287088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002723476,0.00001208423,0.0002069197,0.000341985,0.00006966483,0.000007899318,0.0003954463,0.05734945,0.9331585,0.0002105856,0.00719225,0.001027969],"study_design_scores_gemma":[0.00187436,0.0001338483,0.0006782814,0.0003003516,0.0003240033,0.00002725331,0.000115282,0.506533,0.4779538,0.01060741,0.0002916463,0.001160741],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4980893,0.00003478715,0.4982392,0.0004200948,0.0002438458,0.0006885557,0.00005578928,0.0009594247,0.001269045],"genre_scores_gemma":[0.7734423,0.00001280116,0.2250301,0.0008771159,0.00006660957,0.0001754137,0.00003644736,0.0001063845,0.0002527676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4552047,"threshold_uncertainty_score":0.9998698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270373990154964,"score_gpt":0.2429443275127217,"score_spread":0.230240587611172,"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."}}