{"id":"W4393950777","doi":"10.3390/electronics13071368","title":"Robustness Assessment of AI-Based 2D Object Detection Systems: A Method and Lessons Learned from Two Industrial Cases","year":2024,"lang":"en","type":"article","venue":"Electronics","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thornhill Medical (Canada)","funders":"Agencia Estatal de Investigación; Association Nationale de la Recherche et de la Technologie; European Commission","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Machine learning; Systems engineering; Engineering; Chemistry","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":[0.0007252609,0.0002120444,0.0003718287,0.0002452318,0.00008636077,0.0001699999,0.00006864221,0.0002852965,0.0000165282],"category_scores_gemma":[0.00006708362,0.0002017607,0.00009979936,0.0004827169,0.00001665075,0.0001348343,0.00001624431,0.0007464387,0.000001744415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003741875,"about_ca_system_score_gemma":0.0002776477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005420113,"about_ca_topic_score_gemma":0.0002634568,"domain_scores_codex":[0.9984803,0.0002476266,0.0003998383,0.0003102838,0.0002624232,0.0002995803],"domain_scores_gemma":[0.9991406,0.0004583621,0.0000608979,0.000215943,0.00005888206,0.0000653767],"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":[0.00005895854,0.00001473258,0.00004904726,0.0001507286,0.000208944,0.00002311741,0.00005117945,0.7551438,0.0491911,0.0004815658,0.0001666535,0.1944602],"study_design_scores_gemma":[0.0009012168,0.0002841913,0.0000184229,0.0002283952,0.0001199127,0.00004140584,0.00007550736,0.9252509,0.06075915,0.00006492282,0.01203086,0.0002250575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3257653,0.007870175,0.6630817,0.0000614721,0.002143553,0.0004095957,0.00005815985,0.0004549377,0.0001550715],"genre_scores_gemma":[0.9987885,0.0001144584,0.0003294873,0.000004368116,0.0006095855,0.00004914463,0.00001560724,0.00005213489,0.00003670395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6730232,"threshold_uncertainty_score":0.8227562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06235466887569336,"score_gpt":0.3441968338894969,"score_spread":0.2818421650138035,"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."}}