{"id":"W4400673654","doi":"10.2139/ssrn.4896959","title":"Increasing 3d Printing Accuracy Through Convolutional Neural Network-Based Compensation for Geometric Deviations","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Convolutional neural network; Compensation (psychology); Computer science; 3D printing; Artificial intelligence; Artificial neural network; Computer vision; Pattern recognition (psychology); Engineering; Psychology; Mechanical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005008189,0.000934199,0.0004566573,0.0005927447,0.0002336,0.000829166,0.0008508057,0.0008175993,0.002612313],"category_scores_gemma":[0.001877394,0.0003978953,0.0004360429,0.0006165756,0.0003430424,0.0009423372,0.0009485377,0.0007478245,0.000824563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007497086,"about_ca_system_score_gemma":0.0006867334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003293978,"about_ca_topic_score_gemma":0.00582545,"domain_scores_codex":[0.9993743,0.00003974955,0.0000355553,0.0001488404,0.0003373245,0.00006437527],"domain_scores_gemma":[0.9992199,0.0001771076,0.0001191559,0.0002314381,0.0002275759,0.00002476169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004216776,0.000106536,0.002292417,0.0001637134,0.00006953439,0.0001544421,0.00007853,0.3470193,0.2620003,0.003324206,0.002460994,0.3819084],"study_design_scores_gemma":[0.000007516902,0.00005220079,0.001205144,0.00001114097,0.000020565,0.00008712606,0.000005893161,0.9064242,0.08997072,0.000685362,0.001511478,0.00001867061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1484208,0.000849737,0.8370588,0.0002773588,0.000252034,0.00003389013,0.000198156,0.003782132,0.009127056],"genre_scores_gemma":[0.8623836,0.0003072143,0.132897,0.00009899568,0.00003652724,0.00001704851,0.0001974795,0.0002075038,0.00385458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003293978,"threshold_uncertainty_score":0.008739114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0165712502170276,"score_gpt":0.2525149851173836,"score_spread":0.235943734900356,"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."}}