{"id":"W4401831819","doi":"10.21203/rs.3.rs-4725549/v1","title":"HyDD: Hybrid Defect Detection Framework for Inspection using X-ray CT Data","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Nondestructive testing; Automated X-ray inspection; Process (computing); Reliability engineering; Aerospace; Visual inspection; Segmentation; Artificial intelligence; Automotive industry; Image processing; Real-time computing; Engineering; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006182436,0.001324123,0.001239099,0.001672696,0.0002944028,0.001437431,0.002123455,0.001404641,0.005040218],"category_scores_gemma":[0.001243213,0.0007724057,0.001548549,0.0007335043,0.0004588494,0.000995247,0.001840792,0.001076139,0.002002101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003989036,"about_ca_system_score_gemma":0.0006989151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003397021,"about_ca_topic_score_gemma":0.005397927,"domain_scores_codex":[0.9996437,0.00004253406,0.0000161154,0.00009813609,0.0001580386,0.00004147837],"domain_scores_gemma":[0.9996791,0.00007566401,0.00002732011,0.00009416682,0.00009574173,0.00002808873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005898457,0.0002827278,0.003840861,0.0007283636,0.00042786,0.0004812771,0.0001361599,0.2318369,0.0825837,0.01069398,0.02465381,0.6437446],"study_design_scores_gemma":[0.00001934353,0.00004903433,0.0007025974,0.00001813402,0.00003034497,0.0002236313,0.00001773035,0.9720991,0.01625432,0.005166995,0.005391313,0.00002740718],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002513282,0.0001123626,0.9895141,0.00003418563,0.00001897218,0.00003186722,0.0004883949,0.007078161,0.000208625],"genre_scores_gemma":[0.1082356,0.0002986498,0.8834399,0.0001137521,0.00004961653,0.0001570408,0.003015077,0.001277858,0.003412544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005040218,"threshold_uncertainty_score":0.01686126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1244306795288708,"score_gpt":0.430418836402564,"score_spread":0.3059881568736931,"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."}}