{"id":"W4391053171","doi":"10.1007/s10845-023-02296-w","title":"Automated porosity segmentation in laser powder bed fusion part using computed tomography: a validity study","year":2024,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; National Research Council Canada; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Repeatability; Reproducibility; Segmentation; Artificial intelligence; Reliability (semiconductor); Porosity; Convolutional neural network; Materials science; Computer science; Process (computing); Computer vision; Pattern recognition (psychology); Mathematics; Statistics; Composite material","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":[0.0005463292,0.0002598094,0.0003599631,0.0005306901,0.00006830924,0.000224235,0.0001645688,0.00007699281,0.0002316433],"category_scores_gemma":[0.00001500565,0.000220694,0.0001273157,0.0001931467,0.00001882885,0.0004155687,0.0000570854,0.0003268872,0.00001151146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002106693,"about_ca_system_score_gemma":0.00002798464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003890687,"about_ca_topic_score_gemma":0.00002323949,"domain_scores_codex":[0.9983708,0.0000979714,0.0007525501,0.0001879767,0.0003249563,0.0002657811],"domain_scores_gemma":[0.9994895,0.0001088044,0.0001371099,0.0001134709,0.00006179341,0.00008925509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000326547,0.0008686784,0.008251717,0.002333757,0.001001148,0.002014983,0.007236813,0.8613992,0.09327202,0.00000714265,0.001873435,0.02141453],"study_design_scores_gemma":[0.0002892943,0.0001414969,0.01121245,0.0005963029,0.0000749616,0.00007876985,0.0004783584,0.01607174,0.9701975,0.0001141555,0.0004820045,0.0002629847],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930413,0.0003405666,0.00404288,0.00001405733,0.001911298,0.0002546198,0.00001427272,0.0003423219,0.00003868782],"genre_scores_gemma":[0.9988245,0.0001099342,0.0006988454,0.00001527137,0.0002892309,0.000003368804,0.000009750097,0.00004118817,0.000007847036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8769255,"threshold_uncertainty_score":0.8999639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03545795196432908,"score_gpt":0.2810314367351691,"score_spread":0.24557348477084,"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."}}