{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001096038,0.00008259441,0.00006256909,0.00002949423,0.0002084943,0.0003139978,0.0001669409,0.00004394073,0.000005042968],"category_scores_gemma":[0.000008004151,0.00006402768,0.0000367326,0.0003564749,0.00001399838,0.000255073,0.00003937402,0.00006022075,0.000003480618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004457862,"about_ca_system_score_gemma":0.00002477456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001496105,"about_ca_topic_score_gemma":0.00004589324,"domain_scores_codex":[0.9993609,0.000008706863,0.000131117,0.0002823606,0.00007630902,0.0001405752],"domain_scores_gemma":[0.9995775,0.00007489048,0.00002599223,0.0002076238,0.00007620497,0.00003781748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008139609,0.0001121377,0.0007083353,0.00008997924,0.0000366919,0.000008235565,0.0001849856,0.03695397,0.02336138,0.5034416,0.005731804,0.4293627],"study_design_scores_gemma":[0.00003875194,0.00009477659,0.00007346121,0.00000683532,0.000005882957,0.00002001613,0.000003665062,0.9549458,0.04210521,0.0005269627,0.002081627,0.00009702408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002683674,0.0000589933,0.9954568,0.00054855,0.0001359923,0.0002653513,0.000005091495,0.0007440444,0.0001014592],"genre_scores_gemma":[0.9585164,0.000005460168,0.04058938,0.0001028652,0.0002305046,0.0002856449,0.00006254445,0.000007746743,0.0001994107],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558328,"threshold_uncertainty_score":0.3027888,"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."}}