{"id":"W4224937141","doi":"10.1109/crv55824.2022.00036","title":"CellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection","year":2022,"lang":"en","type":"article","venue":"","topic":"Photovoltaic System Optimization Techniques","field":"Energy","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Photovoltaic system; Computer science; Benchmark (surveying); Artificial intelligence; Electroluminescence; Solar cell; Electricity; Process (computing); Computer hardware; Embedded system; Electrical engineering; Engineering; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008427147,0.000361104,0.0004054559,0.0002874883,0.001043483,0.0001043988,0.0003255928,0.0001342807,0.001752692],"category_scores_gemma":[0.00004487568,0.0003878495,0.0004439955,0.0009453265,0.00007628493,0.0001343747,0.00007304063,0.0002442886,0.00003616986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005565341,"about_ca_system_score_gemma":0.0001743172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004229736,"about_ca_topic_score_gemma":0.001438597,"domain_scores_codex":[0.997155,0.0004527269,0.0005919067,0.0006787492,0.0004780375,0.0006435858],"domain_scores_gemma":[0.9985767,0.0002537647,0.0003479031,0.0005176514,0.0001953733,0.0001086286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007996557,0.0004103121,0.004049556,0.0001166494,0.00008918718,0.000008792105,0.00009091644,0.1131668,0.8167638,0.002208806,0.06201184,0.0002837221],"study_design_scores_gemma":[0.003664114,0.001497656,0.0001350546,0.00002252955,0.0001574344,0.00003190981,0.0001582618,0.3742971,0.5594668,0.001172254,0.05850595,0.0008908467],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0749511,0.0005684972,0.8973607,0.000115709,0.0009896756,0.004668303,0.00008866169,0.004568711,0.01668862],"genre_scores_gemma":[0.9766555,0.000008872864,0.01433238,0.0007727209,0.0001752755,0.00303139,0.0005772916,0.0001340382,0.004312559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9017044,"threshold_uncertainty_score":0.9998574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009904834609224212,"score_gpt":0.2194529744794917,"score_spread":0.2095481398702675,"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."}}