{"id":"W4318715726","doi":"10.2139/ssrn.4329704","title":"Automatic Detection of Surface Defects Based on Deep Random Chains","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Fuse (electrical); Variety (cybernetics); Generalization; Sample (material); Pattern recognition (psychology); Machine learning; Pixel; Scale (ratio); Focus (optics); Data mining; Mathematics; Engineering; Cartography","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":[0.001841817,0.0001523917,0.0002519826,0.0003024182,0.0001344831,0.00002860509,0.00009571109,0.0001405249,0.00001725566],"category_scores_gemma":[0.0001035775,0.0001355688,0.0001718796,0.000668672,0.00001154491,0.0000790421,0.000006252484,0.0009842223,0.00009097172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005635609,"about_ca_system_score_gemma":0.0002022009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002130114,"about_ca_topic_score_gemma":0.0001515117,"domain_scores_codex":[0.9980605,0.000119392,0.0003546874,0.0001146209,0.000316034,0.001034817],"domain_scores_gemma":[0.9994776,0.0001526859,0.0001050095,0.0001523661,0.00005203489,0.00006028726],"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":[0.0002458506,0.00003937499,0.0002082217,0.00009779201,0.0001998901,0.000009007733,0.0001696925,0.7952893,0.0810419,0.0008029707,0.00009108977,0.1218049],"study_design_scores_gemma":[0.002975728,0.0006314639,0.0003982316,0.00009218564,0.00003444926,0.00007949714,0.0003673267,0.9662406,0.02712423,0.001610891,0.0002418281,0.0002035545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.930081,0.0002402331,0.06769957,0.00001523402,0.0009513332,0.0002034468,0.00000128449,0.00037937,0.0004285926],"genre_scores_gemma":[0.9994492,0.0001621202,0.00001002077,0.00000640418,0.0002117737,0.000006052561,0.000001584682,0.00003997375,0.0001128941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1709513,"threshold_uncertainty_score":0.5528336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008137303335409216,"score_gpt":0.2144588776607417,"score_spread":0.2063215743253325,"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."}}