{"id":"W4402513561","doi":"10.21203/rs.3.rs-4908235/v1","title":"An Edge-Based Neural Network Architecture for Instance Segmentation in Machining Feature Recognition","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial neural network; Feature (linguistics); Segmentation; Architecture; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Computer science; Pattern recognition (psychology); Machining; Engineering; Geography; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007403244,0.0002660638,0.0002356079,0.0004898541,0.0001239903,0.0003449444,0.0002411588,0.0003834945,0.00002695296],"category_scores_gemma":[0.00005593295,0.0002696275,0.00008436414,0.0004001868,0.00002710273,0.00008834521,0.0001064368,0.002176855,0.000006265857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766011,"about_ca_system_score_gemma":0.0001037255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003021586,"about_ca_topic_score_gemma":0.0003285502,"domain_scores_codex":[0.9981524,0.0001546149,0.0002391709,0.0005077265,0.0004065585,0.0005394784],"domain_scores_gemma":[0.9992486,0.0001629102,0.00003742231,0.000299739,0.0001531865,0.00009818237],"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":[0.00007727064,0.00001666551,0.0001357841,0.005374054,0.0000135353,0.000008323029,0.0004384461,0.8928071,0.00004905988,0.0000159334,0.0007641049,0.1002998],"study_design_scores_gemma":[0.0003829913,0.0001018933,0.0009021791,0.002125914,0.00001274285,9.987134e-7,0.00008683808,0.9843356,0.001148226,0.01000054,0.000576495,0.0003255699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6642007,0.01152857,0.3039739,0.001836379,0.003585984,0.009064876,0.001308298,0.002266348,0.002235001],"genre_scores_gemma":[0.9737789,0.000148336,0.02076063,0.0000340945,0.0008070542,0.001088713,0.003200173,0.0001309631,0.00005114472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3095782,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03921207708387871,"score_gpt":0.3404191703341432,"score_spread":0.3012070932502645,"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."}}