{"id":"W4410458444","doi":"10.1016/j.aime.2025.100163","title":"Towards generalizable machine learning prediction of downskin surface roughness in laser powder bed fusion","year":2025,"lang":"en","type":"article","venue":"Advances in Industrial and Manufacturing Engineering","topic":"Additive Manufacturing Materials and Processes","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Fusion; Surface roughness; Surface finish; Materials science; Artificial intelligence; Laser; Surface (topology); Computer science; Machine learning; Composite material; Computer vision; Mechanical engineering; Optics; Engineering; Mathematics; Physics; Geometry; Philosophy","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":[0.002288583,0.0007067632,0.0006433401,0.0006950257,0.0002935558,0.001180159,0.0007337808,0.0009992217,0.0005858913],"category_scores_gemma":[0.005018111,0.0003154089,0.0009579787,0.0004852141,0.0005818618,0.0009772344,0.000591626,0.001472267,0.0003663422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006946033,"about_ca_system_score_gemma":0.000604182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005749208,"about_ca_topic_score_gemma":0.005875067,"domain_scores_codex":[0.9995363,0.0001144723,0.00002813766,0.0001548138,0.0001245822,0.00004166893],"domain_scores_gemma":[0.9985052,0.0008001112,0.0001222654,0.0002477095,0.0002983887,0.00002627409],"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":[0.0002253103,0.0001334049,0.0195549,0.0001578674,0.00009115122,0.0001044744,0.0001723966,0.9011284,0.01976328,0.001928828,0.001332657,0.05540731],"study_design_scores_gemma":[0.000004172939,0.00002976789,0.002659048,0.000008009632,0.000005930072,0.00001428934,0.00002689933,0.9920303,0.003839026,0.001096426,0.0002761064,0.00001003687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7073746,0.0006146336,0.2866541,0.0005430111,0.00005977369,0.0001115387,0.0008656913,0.001847491,0.001929102],"genre_scores_gemma":[0.9604831,0.0001735426,0.0373691,0.00008496101,0.00001631449,0.0000721742,0.0009802687,0.0001182792,0.0007023021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005749208,"threshold_uncertainty_score":0.01210332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009763204051348841,"score_gpt":0.2108993350614801,"score_spread":0.2011361310101313,"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."}}