{"id":"W4380519919","doi":"10.2139/ssrn.4477075","title":"Optical Tomography and Machine Learning for In-Situ Defects Detection in Laser Powder Bed Fusion: A Self-Organizing Map and U-Net Based Approach","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Net (polyhedron); In situ; Fusion; Artificial intelligence; Self-organizing map; Laser; Computer science; Computer vision; Materials science; Optics; Geography; Physics; Artificial neural network; Mathematics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010548,0.0003093292,0.0003733052,0.0004497783,0.0001151634,0.0001553347,0.000104051,0.0002600087,0.000004158958],"category_scores_gemma":[0.00005845561,0.0003024077,0.0000646492,0.0001512665,0.00002217498,0.000083111,0.0001132908,0.0023856,0.000001027619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002847534,"about_ca_system_score_gemma":0.0001680217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002916456,"about_ca_topic_score_gemma":0.001132449,"domain_scores_codex":[0.9980621,0.000074955,0.0003103708,0.0003428032,0.0001332792,0.001076512],"domain_scores_gemma":[0.9995902,0.0001353055,0.00008527867,0.0000842494,0.00003321473,0.00007170947],"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":[0.003196037,0.001061748,0.05839867,0.03566309,0.003673058,0.0003198207,0.007916501,0.5803987,0.1724462,0.003254605,0.0001136017,0.1335579],"study_design_scores_gemma":[0.01959902,0.002843017,0.06965996,0.003675614,0.001055068,0.001472463,0.004149265,0.2146824,0.4565671,0.2169698,0.002455727,0.006870552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672393,0.002985891,0.0288553,0.00005339875,0.0002512357,0.0003655151,0.000007595718,0.0001963609,0.00004541343],"genre_scores_gemma":[0.9964842,0.002250591,0.0008411184,0.00001078077,0.0002050846,0.00005705846,0.00004416962,0.00009116919,0.00001588426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3657163,"threshold_uncertainty_score":0.9999428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009272784009345053,"score_gpt":0.20147536242074,"score_spread":0.192202578411395,"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."}}