{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002068418,0.0001256298,0.0001412787,0.00006043207,0.00005398652,0.00002022777,0.00005567676,0.0000710216,0.00004784821],"category_scores_gemma":[0.00001985491,0.0001223886,0.00006808351,0.00004996907,0.00001664328,0.0001192142,0.00001579525,0.00006495131,0.000001256725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005174094,"about_ca_system_score_gemma":0.000004316546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008841624,"about_ca_topic_score_gemma":0.00003878032,"domain_scores_codex":[0.9994668,0.0000198717,0.0001641897,0.0001447272,0.00008006077,0.0001243579],"domain_scores_gemma":[0.9996784,0.0001211357,0.00005878558,0.00005882273,0.00003773007,0.00004515203],"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":[0.001080894,0.0000596656,0.000003467065,0.0003315033,0.0001777364,0.00001046387,0.0001874914,0.1835768,0.6564046,0.00002415961,0.002154468,0.1559888],"study_design_scores_gemma":[0.0001989024,0.0002516492,0.0001538605,0.0000805079,0.00001945978,8.505975e-7,0.00002770849,0.05208429,0.9457582,0.00007431466,0.001226078,0.0001241514],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5123824,0.00001951476,0.4851948,0.0000451556,0.0003750317,0.0002462777,0.0003417016,0.0009789281,0.0004161041],"genre_scores_gemma":[0.9979434,0.00001408208,0.001576515,0.00003134574,0.0002132358,0.00006771818,0.0001222525,0.00002900055,0.000002433744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.485561,"threshold_uncertainty_score":0.4990862,"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."}}