{"id":"W4387738484","doi":"10.2139/ssrn.4605931","title":"Application of Self-Supervised Contrastive Learning for Mixed-Type Wafer Map Defect Recognition and Classification","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Wafer; Computer science; Pattern recognition (psychology); Natural language processing; Machine learning; Materials science; Nanotechnology","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":[],"consensus_categories":[],"category_scores_codex":[0.001893424,0.000233415,0.0003739871,0.0002684991,0.0001420882,0.00006244585,0.0001009005,0.0004717284,0.000002297177],"category_scores_gemma":[0.0001555866,0.0002373209,0.0001730499,0.0002013661,0.00001605562,0.00008992664,0.00003168503,0.002161959,0.00002991197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007224118,"about_ca_system_score_gemma":0.0004163301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005481694,"about_ca_topic_score_gemma":0.0001013997,"domain_scores_codex":[0.9981135,0.0001309102,0.0005457138,0.0002797954,0.0001972043,0.0007328355],"domain_scores_gemma":[0.9988751,0.0001775975,0.0003201724,0.0001391567,0.000431365,0.00005664868],"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":[0.001119516,0.0001418283,0.002563615,0.002366378,0.004076542,0.000001770247,0.001482368,0.04891716,0.06299832,0.00430015,0.0009100637,0.8711223],"study_design_scores_gemma":[0.005571192,0.002184825,0.004908224,0.001040119,0.001408263,0.0002185717,0.004868794,0.8037998,0.006114298,0.1626832,0.005515519,0.00168721],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.453976,0.001908535,0.5402885,0.00004811712,0.001866296,0.001374643,0.00002791838,0.0004295485,0.00008049173],"genre_scores_gemma":[0.9965006,0.00218372,0.0002131679,0.000001993894,0.0006347885,0.0001341585,0.0001656728,0.0000788516,0.0000870325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8694351,"threshold_uncertainty_score":0.9677665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03414157279409939,"score_gpt":0.2531726965841994,"score_spread":0.2190311237901,"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."}}