{"id":"W4394787069","doi":"10.1016/j.eswa.2024.123974","title":"Accelerated semantic segmentation of additively manufactured metal matrix composites: Generating datasets, evaluating convolutional and transformer models, and developing the MicroSegQ+ Tool","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Additive Manufacturing and 3D Printing Technologies","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; National Research Council Canada","funders":"National Research Council Canada","keywords":"Computer science; Segmentation; Modular design; Exploit; Transformer; Process (computing); Data mining; Artificial intelligence; Machine learning; Pattern recognition (psychology)","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":[0.0001942858,0.000170799,0.0001703312,0.00008136558,0.0002513416,0.0001335498,0.00009966691,0.00005819903,0.000004800688],"category_scores_gemma":[0.000005998077,0.0001197655,0.00001823555,0.0001393598,0.0001070528,0.0001907516,0.00002732163,0.0001303199,0.000002222623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005135558,"about_ca_system_score_gemma":0.00003254652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005096484,"about_ca_topic_score_gemma":0.000005048324,"domain_scores_codex":[0.9991363,0.00003160795,0.0002809523,0.0002377527,0.0001439447,0.0001693996],"domain_scores_gemma":[0.9995603,0.0001725392,0.00004992451,0.0001490029,0.00004481074,0.00002343042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004236606,0.00005079267,0.0001226143,0.003095998,0.001633954,0.000007204555,0.008394443,0.1577215,0.7129204,0.03521242,0.003932096,0.07686616],"study_design_scores_gemma":[0.0003511888,0.00003797118,0.0004543439,0.000474156,0.00008966688,0.0001119209,0.002235953,0.8062342,0.1846969,0.0002615637,0.004663478,0.0003886307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182633,0.007732139,0.7717635,0.0001561517,0.00005299582,0.0009804675,0.000562405,0.0004436165,0.00004535581],"genre_scores_gemma":[0.9708047,0.0002554,0.02761942,0.000013436,0.00004945456,0.0007197223,0.0004939078,0.00002635168,0.0000176261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7525414,"threshold_uncertainty_score":0.4883894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0351437185471675,"score_gpt":0.2931258139229141,"score_spread":0.2579820953757466,"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."}}