{"id":"W3012176411","doi":"10.1038/s41524-020-00380-w","title":"Quantifying defects in thin films using machine vision","year":2020,"lang":"en","type":"preprint","venue":"npj Computational Materials","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia","funders":"Natural Resources Canada; Canada Research Chairs; Canada First Research Excellence Fund; University of British Columbia; Western Canada Research Grid; Compute Canada","keywords":"Convolutional neural network; Computer science; Thin film; Personalization; Software; Artificial intelligence; Image processing; Sensitivity (control systems); Machine vision; Materials science; Computer vision; Image (mathematics); Nanotechnology; Electronic engineering; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005279763,0.0003551022,0.0006410499,0.0003040903,0.00007449309,0.0002970007,0.0001681716,0.0004610905,0.0002020781],"category_scores_gemma":[0.00007616232,0.0003718158,0.0001081503,0.0002108974,0.00001506193,0.0001175899,0.0001772594,0.0004436492,0.0001013571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001729245,"about_ca_system_score_gemma":0.00007375381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003708724,"about_ca_topic_score_gemma":0.00001712148,"domain_scores_codex":[0.9978921,0.0002081619,0.0008431472,0.0004221117,0.0003906598,0.000243818],"domain_scores_gemma":[0.9993383,0.000134226,0.0001936539,0.0001848228,0.00007147523,0.00007753942],"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":[0.00004099333,0.00001251307,0.0001127827,0.0004586982,0.00002930798,0.00002000098,0.0001462738,0.8578905,0.1407201,0.0001657689,0.00022328,0.0001796806],"study_design_scores_gemma":[0.0009416509,0.00006294986,0.00322374,0.001298714,0.00003522026,0.00003186416,0.00003689462,0.9435159,0.04513315,0.004660227,0.0003282152,0.0007314672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9677131,0.0002742775,0.02474465,0.00002833477,0.005783939,0.0006308772,0.0002252535,0.0003933035,0.000206248],"genre_scores_gemma":[0.9933429,0.000008564324,0.005716037,0.00003498956,0.0005182868,0.00002812769,0.0002685392,0.0000786146,0.000003908066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09558699,"threshold_uncertainty_score":0.9998734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.077918200655731,"score_gpt":0.3148924281072619,"score_spread":0.2369742274515309,"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."}}