{"id":"W3044219677","doi":"10.1016/j.addma.2020.101468","title":"Adaptive vision-based detection of laser-material interaction for directed energy deposition","year":2020,"lang":"en","type":"article","venue":"Additive manufacturing","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thresholding; Keyhole; Materials science; Artificial intelligence; Energy (signal processing); Energy minimization; Feature (linguistics); Feature extraction; Laser; Pattern recognition (psychology); Computer vision; Computer science; Data acquisition; Minification; Image (mathematics); Optics; Mathematics","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":[0.0002476523,0.0003970882,0.0003798365,0.0008191965,0.0001950875,0.0006165848,0.0007588399,0.0006831087,0.00150769],"category_scores_gemma":[0.0006582487,0.0002894555,0.0003059895,0.0005171608,0.0002872777,0.0005238948,0.000659323,0.0005186823,0.0005593568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005052537,"about_ca_system_score_gemma":0.0005559561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00104718,"about_ca_topic_score_gemma":0.002335471,"domain_scores_codex":[0.9997467,0.0000296432,0.000006783082,0.0000563509,0.0001275638,0.00003293816],"domain_scores_gemma":[0.9997246,0.00009698499,0.00003801197,0.00002587972,0.0000923068,0.00002215967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003203311,0.0001991828,0.001327803,0.0001388432,0.00004417945,0.00006169137,0.00006149043,0.01112124,0.7662592,0.001452819,0.001525788,0.2174874],"study_design_scores_gemma":[0.00002901394,0.0001770481,0.006236967,0.00002346499,0.00003558274,0.000254011,0.00003302744,0.6872728,0.3018524,0.001364799,0.002676467,0.00004433639],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1796669,0.00114366,0.8118588,0.0002497759,0.000145327,0.00008722266,0.0001498912,0.001679234,0.005019164],"genre_scores_gemma":[0.7896633,0.0004602304,0.2058293,0.0001886956,0.00004479413,0.00007084315,0.0001920427,0.0001092984,0.003441443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00150769,"threshold_uncertainty_score":0.005043745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101917158664762,"score_gpt":0.2167081523917036,"score_spread":0.2065164365252274,"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."}}