{"id":"W4387653858","doi":"10.1002/aaai.12129","title":"SolderNet: Towards trustworthy visual inspection of solder joints in electronics manufacturing using explainable artificial intelligence","year":2023,"lang":"en","type":"article","venue":"AI Magazine","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"","keywords":"Soldering; Printed circuit board; Electronics; Visual inspection; Joint (building); Transparency (behavior); Automated optical inspection; Manufacturing engineering; Engineering; Computer science; Trustworthiness; Engineering drawing; Artificial intelligence; Electrical engineering; Computer security; Architectural engineering; Materials science","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":[0.0004255633,0.000171928,0.0002760849,0.0004862659,0.0000659007,0.00003754963,0.00007401834,0.0001689773,0.00005988915],"category_scores_gemma":[0.00003263895,0.000183325,0.00007440741,0.0007419474,0.00002040358,0.0002212658,0.00003727362,0.0003091741,0.0001200196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002128902,"about_ca_system_score_gemma":0.00004007264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001508326,"about_ca_topic_score_gemma":0.0001791259,"domain_scores_codex":[0.9986193,0.00003817465,0.0005195115,0.0002119895,0.0002045071,0.0004065475],"domain_scores_gemma":[0.9996656,0.00002642207,0.00006682699,0.0001507593,0.00004378604,0.00004665329],"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":[0.0001428861,0.0000928425,0.0003677645,0.000332223,0.0000753651,0.00005238815,0.0009313894,0.5727071,0.1382092,0.0004772483,0.0008288892,0.2857827],"study_design_scores_gemma":[0.0002250907,0.0001826286,0.001767614,0.0001367016,0.00001348393,0.0000198642,0.0002805349,0.5740605,0.4204115,0.001013208,0.00160678,0.0002820737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770194,0.00009070901,0.02062078,0.00002097802,0.000933015,0.0002525751,0.000002794997,0.0004103595,0.0006494142],"genre_scores_gemma":[0.9994658,0.00004486065,0.00005394857,0.000009542078,0.000272627,0.00001346062,0.000007333995,0.00004178815,0.00009065759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2855006,"threshold_uncertainty_score":0.7475778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03762574234437778,"score_gpt":0.2885290436264102,"score_spread":0.2509033012820324,"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."}}