{"id":"W4379540121","doi":"10.48550/arxiv.2306.02879","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"JST-Mirai Program; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research; City University of Hong Kong","keywords":"Robustness (evolution); Computer science; Generalization; Artificial neural network; Neuron; Measure (data warehouse); Deep neural networks; Artificial intelligence; Biological neuron model; Distribution (mathematics); Machine learning; Data mining; Mathematics; Neuroscience; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003663884,0.000207285,0.0002173256,0.0002026984,0.0002107571,0.00009788279,0.0005170621,0.0002927516,0.00000243109],"category_scores_gemma":[0.0002384505,0.0002684261,0.00007751892,0.0005301088,0.00005676431,0.0005831628,0.001235765,0.000579035,0.000006528083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002251163,"about_ca_system_score_gemma":0.00007617415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001957533,"about_ca_topic_score_gemma":0.000033954,"domain_scores_codex":[0.9984446,0.000264109,0.0002075173,0.0007729938,0.0001250569,0.0001857282],"domain_scores_gemma":[0.9986302,0.0001383082,0.0004695828,0.0005370796,0.0001693297,0.00005550369],"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":[0.00002342965,0.00001459704,0.001484982,0.00009917207,0.00002786878,0.0000185748,0.0003934609,0.9570112,0.0009653996,0.03776344,0.000026265,0.002171649],"study_design_scores_gemma":[0.0002643147,0.0000375555,0.006812602,0.00009549034,0.00003561017,9.916896e-7,0.00001648751,0.9410121,0.0009864274,0.05042631,0.00008138522,0.0002307276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2331254,0.000004916082,0.7652919,0.00007583091,0.0009835738,0.0001679702,0.000005559055,0.0002811267,0.00006375861],"genre_scores_gemma":[0.9984658,0.0001082937,0.0009960434,0.0000210535,0.00009570953,7.385864e-7,0.00008318508,0.0000195475,0.000209628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7653404,"threshold_uncertainty_score":0.9999768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07808514671438535,"score_gpt":0.2156635214529107,"score_spread":0.1375783747385253,"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."}}