{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:352Y2OCVXB5A2UXTVI42MJ72QY","short_pith_number":"pith:352Y2OCV","schema_version":"1.0","canonical_sha256":"df758d3855b87a0d52f3aa39a627fa862d7cb9d140f768a37d30210823c2c5ea","source":{"kind":"arxiv","id":"2305.00374","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Feng Liu, Jingfeng Zhang, Masashi Sugiyama, Mohan Kankanhalli, Xilie Xu","submitted_at":"2023-04-30T03:12:21Z","abstract_excerpt":"Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring costly annotations. To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation. However, it is unclear how the style-independence property benefits ACL-learned robust represent"},"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":"2305.00374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-30T03:12:21Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6d639f73ec6d86fe6815ea0c998e2886899192c5c50fb76ed4dfbfbf6dfc04c9","abstract_canon_sha256":"aa15da215324eea4e3fa79ada2358c8e7f02c299a1476650c1ec29d02e21b9cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:58.505393Z","signature_b64":"HioRazmp6Dj3d66RFe3XVPLG8uk9RDBQqMEuzv/ietGUNY97If/4DDJWNiA5C091MoNbiJljOY0yqphEioKJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df758d3855b87a0d52f3aa39a627fa862d7cb9d140f768a37d30210823c2c5ea","last_reissued_at":"2026-07-05T07:03:58.504859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:58.504859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Feng Liu, Jingfeng Zhang, Masashi Sugiyama, Mohan Kankanhalli, Xilie Xu","submitted_at":"2023-04-30T03:12:21Z","abstract_excerpt":"Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring costly annotations. To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation. However, it is unclear how the style-independence property benefits ACL-learned robust represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00374","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/2305.00374/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":"2305.00374","created_at":"2026-07-05T07:03:58.504923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00374v2","created_at":"2026-07-05T07:03:58.504923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00374","created_at":"2026-07-05T07:03:58.504923+00:00"},{"alias_kind":"pith_short_12","alias_value":"352Y2OCVXB5A","created_at":"2026-07-05T07:03:58.504923+00:00"},{"alias_kind":"pith_short_16","alias_value":"352Y2OCVXB5A2UXT","created_at":"2026-07-05T07:03:58.504923+00:00"},{"alias_kind":"pith_short_8","alias_value":"352Y2OCV","created_at":"2026-07-05T07:03:58.504923+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/352Y2OCVXB5A2UXTVI42MJ72QY","json":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY.json","graph_json":"https://pith.science/api/pith-number/352Y2OCVXB5A2UXTVI42MJ72QY/graph.json","events_json":"https://pith.science/api/pith-number/352Y2OCVXB5A2UXTVI42MJ72QY/events.json","paper":"https://pith.science/paper/352Y2OCV"},"agent_actions":{"view_html":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY","download_json":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY.json","view_paper":"https://pith.science/paper/352Y2OCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00374&json=true","fetch_graph":"https://pith.science/api/pith-number/352Y2OCVXB5A2UXTVI42MJ72QY/graph.json","fetch_events":"https://pith.science/api/pith-number/352Y2OCVXB5A2UXTVI42MJ72QY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY/action/storage_attestation","attest_author":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY/action/author_attestation","sign_citation":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY/action/citation_signature","submit_replication":"https://pith.science/pith/352Y2OCVXB5A2UXTVI42MJ72QY/action/replication_record"}},"created_at":"2026-07-05T07:03:58.504923+00:00","updated_at":"2026-07-05T07:03:58.504923+00:00"}