{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YWMFFGCWQJ2SJVVAQILCOZZFEJ","short_pith_number":"pith:YWMFFGCW","schema_version":"1.0","canonical_sha256":"c598529856827524d6a08216276725225c0ce9a571d1efb412ddc139ba0ceda1","source":{"kind":"arxiv","id":"2401.04727","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Adversarial Training at Scale","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Hongru Zhu, Xianhang Li, Zeyu Wang","submitted_at":"2024-01-09T18:58:40Z","abstract_excerpt":"The machine learning community has witnessed a drastic change in the training pipeline, pivoted by those ''foundation models'' with unprecedented scales. However, the field of adversarial training is lagging behind, predominantly centered around small model sizes like ResNet-50, and tiny and low-resolution datasets like CIFAR-10. To bridge this transformation gap, this paper provides a modern re-examination with adversarial training, investigating its potential benefits when applied at scale. Additionally, we introduce an efficient and effective training strategy to enable adversarial training"},"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":"2401.04727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T18:58:40Z","cross_cats_sorted":[],"title_canon_sha256":"cd9550329e02f8a055d46fa13cffef9d3f3a8a8f0a9a0340dd135763dbc9a5d2","abstract_canon_sha256":"398ecb19404dc9820a03b81fd2ff88cf74eed5498782e20fc293e1c183deb000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:21.822327Z","signature_b64":"SRGrOlo3VAy8yUkShz0eXr58ikEhvoCMmpkrK7ffzpeSQo+gMjhaxwaPIict9y6/VcOz53k1+de9IvRYNFr8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c598529856827524d6a08216276725225c0ce9a571d1efb412ddc139ba0ceda1","last_reissued_at":"2026-07-05T08:10:21.821848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:21.821848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Adversarial Training at Scale","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Hongru Zhu, Xianhang Li, Zeyu Wang","submitted_at":"2024-01-09T18:58:40Z","abstract_excerpt":"The machine learning community has witnessed a drastic change in the training pipeline, pivoted by those ''foundation models'' with unprecedented scales. However, the field of adversarial training is lagging behind, predominantly centered around small model sizes like ResNet-50, and tiny and low-resolution datasets like CIFAR-10. To bridge this transformation gap, this paper provides a modern re-examination with adversarial training, investigating its potential benefits when applied at scale. Additionally, we introduce an efficient and effective training strategy to enable adversarial training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04727","kind":"arxiv","version":2},"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/2401.04727/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":"2401.04727","created_at":"2026-07-05T08:10:21.821914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04727v2","created_at":"2026-07-05T08:10:21.821914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04727","created_at":"2026-07-05T08:10:21.821914+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWMFFGCWQJ2S","created_at":"2026-07-05T08:10:21.821914+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWMFFGCWQJ2SJVVA","created_at":"2026-07-05T08:10:21.821914+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWMFFGCW","created_at":"2026-07-05T08:10:21.821914+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/YWMFFGCWQJ2SJVVAQILCOZZFEJ","json":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ.json","graph_json":"https://pith.science/api/pith-number/YWMFFGCWQJ2SJVVAQILCOZZFEJ/graph.json","events_json":"https://pith.science/api/pith-number/YWMFFGCWQJ2SJVVAQILCOZZFEJ/events.json","paper":"https://pith.science/paper/YWMFFGCW"},"agent_actions":{"view_html":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ","download_json":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ.json","view_paper":"https://pith.science/paper/YWMFFGCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04727&json=true","fetch_graph":"https://pith.science/api/pith-number/YWMFFGCWQJ2SJVVAQILCOZZFEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YWMFFGCWQJ2SJVVAQILCOZZFEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ/action/storage_attestation","attest_author":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ/action/author_attestation","sign_citation":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ/action/citation_signature","submit_replication":"https://pith.science/pith/YWMFFGCWQJ2SJVVAQILCOZZFEJ/action/replication_record"}},"created_at":"2026-07-05T08:10:21.821914+00:00","updated_at":"2026-07-05T08:10:21.821914+00:00"}