{"id":"W4415097358","doi":"10.1080/17452759.2025.2569543","title":"Pioneering ML-driven framework for in-situ vertical surface roughness prediction in LPBF","year":2025,"lang":"en","type":"article","venue":"Virtual and Physical Prototyping","topic":"Surface Roughness and Optical Measurements","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Surface roughness; Photodiode; Surface finish; Boosting (machine learning); Laser; Laser scanning; Process (computing)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009494644,0.001109062,0.0009307399,0.0005395699,0.0002468499,0.0008712527,0.001379062,0.001148522,0.001308101],"category_scores_gemma":[0.001962292,0.0005374267,0.001081217,0.0004484584,0.0004915529,0.0005827328,0.0007245672,0.001499816,0.0005963984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006411218,"about_ca_system_score_gemma":0.001016155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009707706,"about_ca_topic_score_gemma":0.008660931,"domain_scores_codex":[0.9996127,0.00008032189,0.00001934086,0.0001215039,0.0001192624,0.00004687248],"domain_scores_gemma":[0.9993827,0.0003251535,0.00006241118,0.00004094993,0.0001631516,0.00002558711],"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":[0.00008372405,0.00005414805,0.0009497086,0.00008977159,0.00007254825,0.00005405729,0.00003805118,0.9206803,0.009820513,0.002630986,0.0007669002,0.06475931],"study_design_scores_gemma":[0.000001765709,0.000008557273,0.00006620678,0.000001666986,0.000002976626,0.000003689377,0.000001184878,0.9986771,0.0006081035,0.0004668799,0.0001595177,0.000002276261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00874697,0.0002694855,0.9890833,0.00007402297,0.00002054774,0.00002320881,0.00009014246,0.001280921,0.0004113142],"genre_scores_gemma":[0.65671,0.0004869577,0.3377056,0.0002185456,0.0001144656,0.0003800787,0.00087042,0.0003612594,0.003152674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009707706,"threshold_uncertainty_score":0.01930243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01690046623650988,"score_gpt":0.2597101770952248,"score_spread":0.2428097108587149,"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."}}