{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V5IRFBGIETQELMEOISPJNSTHYF","short_pith_number":"pith:V5IRFBGI","schema_version":"1.0","canonical_sha256":"af511284c824e045b08e449e96ca67c172780b87d1f7dcea50179840a635e640","source":{"kind":"arxiv","id":"2406.05372","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiancong Xiao, Qi Long, Ruoyu Sun, Weijie J. Su","submitted_at":"2024-06-08T06:45:19Z","abstract_excerpt":"Training Deep Neural Networks (DNNs) with adversarial examples often results in poor generalization to test-time adversarial data. This paper investigates this issue, known as adversarially robust generalization, through the lens of Rademacher complexity. Building upon the studies by Khim and Loh (2018); Yin et al. (2019), numerous works have been dedicated to this problem, yet achieving a satisfactory bound remains an elusive goal. Existing works on DNNs either apply to a surrogate loss instead of the robust loss or yield bounds that are notably looser compared to their standard counterparts."},"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":"2406.05372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-08T06:45:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc31d9a29f06e92943942231dcc7055e1763e6c97c8b36f8090bdcb73e210154","abstract_canon_sha256":"5d787d6ed607fa3fef29602e35f3d8179d1d074702772031fe457196b5eeb822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:04.629633Z","signature_b64":"ioT90Mek2kkMRfVGL2iUfnTtHlFs/nZ2YNjfRelLQzfORfvcI9aBRLulq7NfoxxKb/ibWfXGPklVpkI5xQI3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af511284c824e045b08e449e96ca67c172780b87d1f7dcea50179840a635e640","last_reissued_at":"2026-07-05T08:29:04.629157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:04.629157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiancong Xiao, Qi Long, Ruoyu Sun, Weijie J. Su","submitted_at":"2024-06-08T06:45:19Z","abstract_excerpt":"Training Deep Neural Networks (DNNs) with adversarial examples often results in poor generalization to test-time adversarial data. This paper investigates this issue, known as adversarially robust generalization, through the lens of Rademacher complexity. Building upon the studies by Khim and Loh (2018); Yin et al. (2019), numerous works have been dedicated to this problem, yet achieving a satisfactory bound remains an elusive goal. Existing works on DNNs either apply to a surrogate loss instead of the robust loss or yield bounds that are notably looser compared to their standard counterparts."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05372","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/2406.05372/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":"2406.05372","created_at":"2026-07-05T08:29:04.629218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05372v1","created_at":"2026-07-05T08:29:04.629218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05372","created_at":"2026-07-05T08:29:04.629218+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5IRFBGIETQE","created_at":"2026-07-05T08:29:04.629218+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5IRFBGIETQELMEO","created_at":"2026-07-05T08:29:04.629218+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5IRFBGI","created_at":"2026-07-05T08:29:04.629218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12449","citing_title":"Adversarially robust generalization theory via Jacobian regularization for deep neural networks","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF","json":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF.json","graph_json":"https://pith.science/api/pith-number/V5IRFBGIETQELMEOISPJNSTHYF/graph.json","events_json":"https://pith.science/api/pith-number/V5IRFBGIETQELMEOISPJNSTHYF/events.json","paper":"https://pith.science/paper/V5IRFBGI"},"agent_actions":{"view_html":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF","download_json":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF.json","view_paper":"https://pith.science/paper/V5IRFBGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05372&json=true","fetch_graph":"https://pith.science/api/pith-number/V5IRFBGIETQELMEOISPJNSTHYF/graph.json","fetch_events":"https://pith.science/api/pith-number/V5IRFBGIETQELMEOISPJNSTHYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF/action/storage_attestation","attest_author":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF/action/author_attestation","sign_citation":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF/action/citation_signature","submit_replication":"https://pith.science/pith/V5IRFBGIETQELMEOISPJNSTHYF/action/replication_record"}},"created_at":"2026-07-05T08:29:04.629218+00:00","updated_at":"2026-07-05T08:29:04.629218+00:00"}