{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IT6J2SOUUVTRMXIES4TSR377ZK","short_pith_number":"pith:IT6J2SOU","schema_version":"1.0","canonical_sha256":"44fc9d49d4a567165d04972728efffca96978050c5c139373ebb9eb82237e2e3","source":{"kind":"arxiv","id":"2202.01832","version":2},"attestation_state":"computed","paper":{"title":"Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Li, Danny Son, Evelyn Ma, Jacky Yibo Zhang, Oluwasanmi Koyejo, Xiaojun Xu","submitted_at":"2022-02-03T20:26:27Z","abstract_excerpt":"Machine learning (ML) robustness and domain generalization are fundamentally correlated: they essentially concern data distribution shifts under adversarial and natural settings, respectively. On one hand, recent studies show that more robust (adversarially trained) models are more generalizable. On the other hand, there is a lack of theoretical understanding of their fundamental connections. In this paper, we explore the relationship between regularization and domain transferability considering different factors such as norm regularization and data augmentations (DA). We propose a general the"},"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":"2202.01832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-03T20:26:27Z","cross_cats_sorted":[],"title_canon_sha256":"419893c461c7f15a5187db1fed9b2b638ce904266a4aa683ed1fafa969a8f7f7","abstract_canon_sha256":"a224cd816d829472e90f5cd121811290d9cb5351b0c7bdacee25f019d3af840f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:28.009645Z","signature_b64":"zwX64EF0W5x+gA3i6VRIPLGRPZASJ2s1FtEo28syKLGorELOPb3saoFdL+W8VZOT6cA79H2JJ7+YlANAPQCKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44fc9d49d4a567165d04972728efffca96978050c5c139373ebb9eb82237e2e3","last_reissued_at":"2026-07-05T04:34:28.009217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:28.009217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Li, Danny Son, Evelyn Ma, Jacky Yibo Zhang, Oluwasanmi Koyejo, Xiaojun Xu","submitted_at":"2022-02-03T20:26:27Z","abstract_excerpt":"Machine learning (ML) robustness and domain generalization are fundamentally correlated: they essentially concern data distribution shifts under adversarial and natural settings, respectively. On one hand, recent studies show that more robust (adversarially trained) models are more generalizable. On the other hand, there is a lack of theoretical understanding of their fundamental connections. In this paper, we explore the relationship between regularization and domain transferability considering different factors such as norm regularization and data augmentations (DA). We propose a general the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01832","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/2202.01832/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":"2202.01832","created_at":"2026-07-05T04:34:28.009282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01832v2","created_at":"2026-07-05T04:34:28.009282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01832","created_at":"2026-07-05T04:34:28.009282+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT6J2SOUUVTR","created_at":"2026-07-05T04:34:28.009282+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT6J2SOUUVTRMXIE","created_at":"2026-07-05T04:34:28.009282+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT6J2SOU","created_at":"2026-07-05T04:34:28.009282+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/IT6J2SOUUVTRMXIES4TSR377ZK","json":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK.json","graph_json":"https://pith.science/api/pith-number/IT6J2SOUUVTRMXIES4TSR377ZK/graph.json","events_json":"https://pith.science/api/pith-number/IT6J2SOUUVTRMXIES4TSR377ZK/events.json","paper":"https://pith.science/paper/IT6J2SOU"},"agent_actions":{"view_html":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK","download_json":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK.json","view_paper":"https://pith.science/paper/IT6J2SOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01832&json=true","fetch_graph":"https://pith.science/api/pith-number/IT6J2SOUUVTRMXIES4TSR377ZK/graph.json","fetch_events":"https://pith.science/api/pith-number/IT6J2SOUUVTRMXIES4TSR377ZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK/action/storage_attestation","attest_author":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK/action/author_attestation","sign_citation":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK/action/citation_signature","submit_replication":"https://pith.science/pith/IT6J2SOUUVTRMXIES4TSR377ZK/action/replication_record"}},"created_at":"2026-07-05T04:34:28.009282+00:00","updated_at":"2026-07-05T04:34:28.009282+00:00"}