{"id":"W4414348545","doi":"10.1109/tse.2025.3611329","title":"DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks for Image Analysis","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland; General Motors Corporation","keywords":"Artificial neural network; Image (mathematics); Pattern recognition (psychology); Test (biology); Image processing; Differential (mechanical device)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003613571,0.001763237,0.0009682697,0.001836576,0.0003821569,0.0008481131,0.003907755,0.001786971,0.008573485],"category_scores_gemma":[0.01525741,0.00082631,0.00135269,0.0006572013,0.001112938,0.001775204,0.002294365,0.002424213,0.001292933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133844,"about_ca_system_score_gemma":0.00150714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002521813,"about_ca_topic_score_gemma":0.003835669,"domain_scores_codex":[0.9975379,0.001110231,0.0001626549,0.0004268259,0.0005748305,0.0001876021],"domain_scores_gemma":[0.9913775,0.006303549,0.0003022208,0.0008992187,0.0009500196,0.0001675193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001409083,0.0003582975,0.005195445,0.0005262049,0.0003868807,0.000658726,0.0001663268,0.3658089,0.02125873,0.02653794,0.01989697,0.5577965],"study_design_scores_gemma":[0.00007483416,0.0001046204,0.0002137623,0.00001716954,0.00001972997,0.00008021622,0.00001078269,0.9780399,0.008401519,0.01200685,0.001018875,0.00001174276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01203455,0.0001375545,0.9746915,0.0001331554,0.00005866791,0.0001159949,0.0003699989,0.01163716,0.0008215903],"genre_scores_gemma":[0.2945056,0.00008210327,0.6975482,0.0004416816,0.00008348875,0.0005985071,0.002103722,0.002349055,0.002287712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008573485,"threshold_uncertainty_score":0.0286811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01220046323444045,"score_gpt":0.2224542094514625,"score_spread":0.210253746217022,"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."}}