{"id":"W4328102250","doi":"10.2351/7.0000769","title":"Quality classification model with machine learning for porosity prediction in laser welding aluminum alloys","year":2023,"lang":"en","type":"article","venue":"Journal of Laser Applications","topic":"Welding Techniques and Residual Stresses","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Université du Québec à Rimouski","funders":"","keywords":"Porosity; Welding; Materials science; Process (computing); Quality (philosophy); Laser beam welding; Machine learning; Computer science; Artificial intelligence; Algorithm; Process engineering; Mechanical engineering; Metallurgy; Composite material; Engineering","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":[0.0004531213,0.00009021354,0.000150107,0.0001666839,0.00009516052,0.00002645201,0.0001215576,0.00007222428,0.000004926483],"category_scores_gemma":[0.00002526776,0.00007642249,0.00005264823,0.0003308317,0.00001775203,0.0001467859,0.00001377011,0.0002421636,0.000003102087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008149244,"about_ca_system_score_gemma":0.00002325529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001235204,"about_ca_topic_score_gemma":0.00005781086,"domain_scores_codex":[0.9992216,0.00001931163,0.0003622466,0.0001001806,0.0001554422,0.0001412288],"domain_scores_gemma":[0.9994953,0.00009543559,0.0001375893,0.0001183743,0.00009942405,0.00005386953],"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":[0.00002828864,0.00004329423,0.01147528,0.00006569287,0.00002478681,7.324353e-7,0.00009036296,0.9788998,0.005050569,0.0001570095,0.003147652,0.001016544],"study_design_scores_gemma":[0.001103139,0.0001505124,0.06636526,0.0001464467,0.00006721827,0.00002002509,0.0002807689,0.8705417,0.03651307,0.003533515,0.02097203,0.0003063173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5185792,0.00006112035,0.4792256,0.0006463138,0.00005258754,0.0004546638,0.00004892328,0.0003597262,0.0005718359],"genre_scores_gemma":[0.991043,0.0002007912,0.00819336,0.00001136754,0.0001158545,0.0001533517,0.00004977528,0.00002447514,0.0002079912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4724638,"threshold_uncertainty_score":0.3116419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0370863501755366,"score_gpt":0.2915651854060541,"score_spread":0.2544788352305176,"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."}}