{"id":"W4382317845","doi":"10.1609/aaai.v37i13.26869","title":"High-Throughput, High-Performance Deep Learning-Driven Light Guide Plate Surface Visual Quality Inspection Tailored for Real-World Manufacturing Environments","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Workflow; Visual inspection; Throughput; Deep learning; Artificial intelligence; Computer science; Quality (philosophy); Consistency (knowledge bases); Computer vision; Database","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":[0.0003643128,0.00104171,0.0004656852,0.0004207914,0.0002004749,0.0006206195,0.001903634,0.000642819,0.002399065],"category_scores_gemma":[0.0009203421,0.0003988749,0.0004710051,0.0002585915,0.0004058857,0.0008702368,0.001206756,0.001234741,0.0009028801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000960383,"about_ca_system_score_gemma":0.001372578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005261828,"about_ca_topic_score_gemma":0.009710751,"domain_scores_codex":[0.9996905,0.00002146897,0.000009360163,0.00008008291,0.0001448889,0.00005364932],"domain_scores_gemma":[0.9996953,0.00006254178,0.00003323486,0.00004697808,0.0001189013,0.00004305141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004644729,0.0004058188,0.005517201,0.0004640193,0.0001326899,0.000522471,0.0001812165,0.5135124,0.1484696,0.004319348,0.01527213,0.3107385],"study_design_scores_gemma":[0.00001368366,0.00006036591,0.0004593507,0.000006240107,0.000007073827,0.00003239319,0.000009712719,0.9790286,0.01847895,0.0007957676,0.001097284,0.00001056354],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07923582,0.0003207051,0.8949891,0.0003062133,0.00009236825,0.0002377015,0.0006112503,0.01933346,0.004873413],"genre_scores_gemma":[0.6321315,0.0002077525,0.3576385,0.0004108239,0.00002287209,0.0002297855,0.002084687,0.0005582841,0.00671573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005261828,"threshold_uncertainty_score":0.0104624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05683405684072034,"score_gpt":0.3015492252839531,"score_spread":0.2447151684432327,"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."}}