{"id":"W4401879061","doi":"10.1109/compsac61105.2024.00148","title":"Enhancing Valid Test Input Generation with Distribution Awareness for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial neural network; Test (biology); Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004808445,0.0014021,0.000907018,0.001582026,0.0003719726,0.001075134,0.002077358,0.001032971,0.001592899],"category_scores_gemma":[0.02910781,0.0005973165,0.000735854,0.0007337124,0.001162517,0.00217469,0.001826406,0.001753222,0.0003975595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00147616,"about_ca_system_score_gemma":0.002562641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002728633,"about_ca_topic_score_gemma":0.003594745,"domain_scores_codex":[0.995281,0.001926881,0.0003398247,0.0007158269,0.001339773,0.0003966227],"domain_scores_gemma":[0.9777349,0.01410377,0.002416207,0.002670636,0.002600261,0.0004742639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005903197,0.0005029205,0.01790658,0.0002004162,0.0001096588,0.0003483534,0.0002463678,0.4993661,0.02353581,0.006472382,0.00290737,0.4478137],"study_design_scores_gemma":[0.0000257391,0.00008233911,0.0006776422,0.00001299979,0.00001777362,0.00008458009,0.00001771661,0.9845939,0.01062423,0.003457029,0.0003945216,0.00001149132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08869325,0.0002497498,0.9025745,0.0003075306,0.00003438086,0.0001729831,0.0001091596,0.00672942,0.001128936],"genre_scores_gemma":[0.8200421,0.00007509843,0.1781262,0.0002246057,0.00002766748,0.0001814799,0.0002930922,0.0003542052,0.0006754702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004808445,"threshold_uncertainty_score":0.02542979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01841692417481953,"score_gpt":0.2711883901525361,"score_spread":0.2527714659777165,"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."}}