{"id":"W2775775898","doi":"10.1109/smc.2017.8122572","title":"Seam tracking in automated welding","year":2017,"lang":"en","type":"article","venue":"","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Welding; Tracking (education); Computer vision; Computer science; Noise (video); Enhanced Data Rates for GSM Evolution; Key (lock); Artificial intelligence; Image processing; Edge detection; Robot welding; Ground truth; Image (mathematics); Engineering; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005242647,0.0002538191,0.0004080439,0.0006796473,0.0003239225,0.0005258931,0.0007265741,0.000825486,0.0009320545],"category_scores_gemma":[0.001398839,0.0003535636,0.0002689576,0.0008499504,0.000442369,0.0006676294,0.0004810184,0.0003414618,0.0003934231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003967204,"about_ca_system_score_gemma":0.0004250547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003484047,"about_ca_topic_score_gemma":0.001811636,"domain_scores_codex":[0.9995479,0.00009071844,0.00001502557,0.0001182121,0.000195337,0.00003288557],"domain_scores_gemma":[0.9995926,0.0001788593,0.00007492644,0.0000643063,0.00007667928,0.00001272593],"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":[0.0002014454,0.00006380556,0.001342735,0.000184627,0.00003907038,0.0001568542,0.0002441096,0.3502863,0.08905996,0.01482151,0.001299507,0.5423],"study_design_scores_gemma":[0.0000114537,0.0001010595,0.001684692,0.00001728315,0.000009622492,0.0001343932,0.00003269734,0.9683054,0.01929732,0.006528875,0.003852938,0.00002420872],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03338652,0.0007681489,0.9631472,0.00004807528,0.00003800834,0.00001755484,0.00002248464,0.0007365268,0.001835523],"genre_scores_gemma":[0.6127513,0.0008657695,0.381473,0.0000568637,0.00005396737,0.00003466825,0.00007768746,0.000116137,0.004570576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003484047,"threshold_uncertainty_score":0.00692755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02046059606457457,"score_gpt":0.2946066535791635,"score_spread":0.274146057514589,"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."}}