{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00732248,0.001488583,0.001590177,0.001883632,0.0006768694,0.001539258,0.002490988,0.001979321,0.0009171741],"category_scores_gemma":[0.03739677,0.0005782009,0.001020202,0.0008661255,0.002799783,0.003319906,0.00461544,0.003216604,0.000318615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001206749,"about_ca_system_score_gemma":0.000958606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002724777,"about_ca_topic_score_gemma":0.002829602,"domain_scores_codex":[0.9968457,0.001290371,0.0002164532,0.000667701,0.0007150662,0.0002648002],"domain_scores_gemma":[0.9782565,0.01421129,0.002047492,0.00352588,0.001280976,0.0006779528],"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":[0.0006178704,0.000199333,0.04584303,0.0001901403,0.0003725906,0.0005171557,0.0005497948,0.7323576,0.00970161,0.01528001,0.003918545,0.1904523],"study_design_scores_gemma":[0.000009729575,0.00006736187,0.002025693,0.00002549456,0.00001945059,0.0000885694,0.00003575894,0.9815997,0.002912201,0.01287343,0.0003271764,0.00001545516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2899249,0.00125641,0.7015936,0.001641397,0.0001028869,0.0001066998,0.0003621515,0.002032157,0.00297981],"genre_scores_gemma":[0.9680517,0.0001996848,0.02994277,0.0003667883,0.00008002272,0.0000599443,0.0004421958,0.0001921887,0.0006646976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00732248,"threshold_uncertainty_score":0.03872544,"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."}}