{"id":"W4406603979","doi":"10.48550/arxiv.2501.09994","title":"Multi-Modal Attention Networks for Enhanced Segmentation and Depth Estimation of Subsurface Defects in Pulse Thermography","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thermography; Modal; Pulse (music); Segmentation; Estimation; Materials science; Acoustics; Geology; Computer science; Optics; Artificial intelligence; Telecommunications; Engineering; Physics; Composite material; Infrared","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004660173,0.0008562979,0.0005063767,0.0006734369,0.0002047611,0.0004356305,0.000982343,0.0008179948,0.001005078],"category_scores_gemma":[0.001148945,0.0002720239,0.0006085119,0.0004600894,0.0003556908,0.0008410224,0.0008882022,0.0008690369,0.0002699683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007159792,"about_ca_system_score_gemma":0.0005269417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00903113,"about_ca_topic_score_gemma":0.00920546,"domain_scores_codex":[0.9998214,0.0000297609,0.00000716457,0.00006549838,0.00003902889,0.00003727549],"domain_scores_gemma":[0.9996958,0.000130437,0.00003574529,0.00003506324,0.0000842837,0.00001874625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004289682,0.0002137785,0.002976883,0.0001306666,0.000120534,0.0002143143,0.0001462591,0.4446037,0.05222284,0.002345515,0.003937712,0.4926589],"study_design_scores_gemma":[0.000003159515,0.00003079547,0.0005594449,0.000004959379,0.00001549386,0.00002283025,0.000009662283,0.9918118,0.006329876,0.0008989038,0.0003088216,0.000004332431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2416572,0.001742381,0.7483923,0.0005089702,0.0001151689,0.00007297211,0.0004937036,0.00373601,0.003281235],"genre_scores_gemma":[0.9204634,0.0003805228,0.07457659,0.0002238017,0.00005422975,0.00005403646,0.0007935627,0.00008972579,0.003364159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00903113,"threshold_uncertainty_score":0.01795709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01769583732358788,"score_gpt":0.2651030758361521,"score_spread":0.2474072385125642,"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."}}