{"id":"W3081106937","doi":"10.1117/12.2570605","title":"Evaluation of deep learning-generated lens design starting points","year":2020,"lang":"en","type":"article","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Lens (geology); Computer science; Deep learning; Artificial neural network; Artificial intelligence; Quality (philosophy); Field (mathematics); Through-the-lens metering; Machine learning; Computer engineering; Engineering; Mathematics","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":[0.001202353,0.00006914835,0.0001156763,0.00003948426,0.00003462996,0.00001446639,0.00002937773,0.00007025585,0.0003283923],"category_scores_gemma":[0.0003738307,0.00006401227,0.00003158413,0.0002239326,0.000004077772,0.00008458584,0.000006554491,0.000107547,0.0000662023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004036805,"about_ca_system_score_gemma":0.00001532868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456113,"about_ca_topic_score_gemma":0.000002850838,"domain_scores_codex":[0.9990175,0.0002157877,0.0002407404,0.00008969566,0.0003397064,0.00009654996],"domain_scores_gemma":[0.9996153,0.00003629518,0.00004297617,0.00005359837,0.0002147051,0.00003717517],"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":[0.00001088847,0.000002890831,0.00006934971,0.00001131795,0.00002836451,3.196778e-7,0.0003670078,0.8481311,0.1131048,0.00001237916,0.0004533615,0.03780818],"study_design_scores_gemma":[0.0003479967,0.00008357804,0.00005936097,0.000006485818,0.00002429052,4.023305e-7,0.0001376132,0.8142458,0.184715,0.00001593175,0.0003021688,0.00006141371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6198601,0.0001436854,0.3713269,0.00005103202,0.0003251208,0.000374786,7.130985e-7,0.0004151303,0.007502549],"genre_scores_gemma":[0.9992434,0.000002517737,0.0005733639,0.00002129974,0.0001222298,0.000006831471,0.000001923081,0.00001513302,0.00001334495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3793832,"threshold_uncertainty_score":0.3595666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.114692739909731,"score_gpt":0.2687121336657022,"score_spread":0.1540193937559712,"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."}}