{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W2GNOZ33E3FJF55AJY4UYFG35V","short_pith_number":"pith:W2GNOZ33","schema_version":"1.0","canonical_sha256":"b68cd7677b26ca92f7a04e394c14dbed5234e1ff31bcc65ff65c2fafce4dedff","source":{"kind":"arxiv","id":"2207.10290","version":1},"attestation_state":"computed","paper":{"title":"AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhai Nie, Furao Shen, Jian Zhao, Xiaoliang Liu","submitted_at":"2022-07-21T04:02:24Z","abstract_excerpt":"Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalizatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.10290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T04:02:24Z","cross_cats_sorted":[],"title_canon_sha256":"126e3547eaf7cb5d9fa1066aeae42ff52bfc824e6bcb1e5da654209c743d74f8","abstract_canon_sha256":"fca8f8d136856689f1a4225ff41c702670c877bf0e8348aa1d03d22fc40f7b77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:23.505423Z","signature_b64":"4Xv5JyPttFOmAwIsXVIlSktjLIXdsmQ+QjmPxPHvdGUvnikTywoYEev+0OT0oQFkv07fklYAdWuO4iNH9p8WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b68cd7677b26ca92f7a04e394c14dbed5234e1ff31bcc65ff65c2fafce4dedff","last_reissued_at":"2026-07-05T04:42:23.505042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:23.505042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhai Nie, Furao Shen, Jian Zhao, Xiaoliang Liu","submitted_at":"2022-07-21T04:02:24Z","abstract_excerpt":"Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10290","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.10290/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.10290","created_at":"2026-07-05T04:42:23.505097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10290v1","created_at":"2026-07-05T04:42:23.505097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10290","created_at":"2026-07-05T04:42:23.505097+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2GNOZ33E3FJ","created_at":"2026-07-05T04:42:23.505097+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2GNOZ33E3FJF55A","created_at":"2026-07-05T04:42:23.505097+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2GNOZ33","created_at":"2026-07-05T04:42:23.505097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V","json":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V.json","graph_json":"https://pith.science/api/pith-number/W2GNOZ33E3FJF55AJY4UYFG35V/graph.json","events_json":"https://pith.science/api/pith-number/W2GNOZ33E3FJF55AJY4UYFG35V/events.json","paper":"https://pith.science/paper/W2GNOZ33"},"agent_actions":{"view_html":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V","download_json":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V.json","view_paper":"https://pith.science/paper/W2GNOZ33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10290&json=true","fetch_graph":"https://pith.science/api/pith-number/W2GNOZ33E3FJF55AJY4UYFG35V/graph.json","fetch_events":"https://pith.science/api/pith-number/W2GNOZ33E3FJF55AJY4UYFG35V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V/action/storage_attestation","attest_author":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V/action/author_attestation","sign_citation":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V/action/citation_signature","submit_replication":"https://pith.science/pith/W2GNOZ33E3FJF55AJY4UYFG35V/action/replication_record"}},"created_at":"2026-07-05T04:42:23.505097+00:00","updated_at":"2026-07-05T04:42:23.505097+00:00"}