{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6QHSBACXTWB55VBZRTGHEL4AVS","short_pith_number":"pith:6QHSBACX","schema_version":"1.0","canonical_sha256":"f40f2080579d83ded4398ccc722f80acafb0e8b24dee9580350442ad82114bf7","source":{"kind":"arxiv","id":"2505.12681","version":1},"attestation_state":"computed","paper":{"title":"On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alan Mitkiy, Hana Satou","submitted_at":"2025-05-19T03:56:51Z","abstract_excerpt":"Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model vulnerabilities, recent studies suggest that they can also serve as constructive tools for data augmentation. In this work, we systematically investigate the role of adversarial data augmentation (ADA) in enhancing both robustness and adaptivity in transfer learning settings. We analyze how adversarial examples, when used strategically during training, improve dom"},"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":"2505.12681","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T03:56:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9388b1991c01274ea4efdd2891f4211783a40c3ab65b545c67c943341feb5f97","abstract_canon_sha256":"e0fd85365339dba025a2b06bbf8d8fa0d795aca2bc549bc1165d8a54be92f46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:08.096515Z","signature_b64":"mBg4alY82THrGgSc9gGzDNn+knXCXvQFGC2gaFV2bffz5a5WHpgK+8PjIXUh6AwPl7ewyj7tWyjWCgU/wYKECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f40f2080579d83ded4398ccc722f80acafb0e8b24dee9580350442ad82114bf7","last_reissued_at":"2026-07-05T11:05:08.095986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:08.095986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alan Mitkiy, Hana Satou","submitted_at":"2025-05-19T03:56:51Z","abstract_excerpt":"Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model vulnerabilities, recent studies suggest that they can also serve as constructive tools for data augmentation. In this work, we systematically investigate the role of adversarial data augmentation (ADA) in enhancing both robustness and adaptivity in transfer learning settings. We analyze how adversarial examples, when used strategically during training, improve dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12681","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/2505.12681/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":"2505.12681","created_at":"2026-07-05T11:05:08.096043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12681v1","created_at":"2026-07-05T11:05:08.096043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12681","created_at":"2026-07-05T11:05:08.096043+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QHSBACXTWB5","created_at":"2026-07-05T11:05:08.096043+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QHSBACXTWB55VBZ","created_at":"2026-07-05T11:05:08.096043+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QHSBACX","created_at":"2026-07-05T11:05:08.096043+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/6QHSBACXTWB55VBZRTGHEL4AVS","json":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS.json","graph_json":"https://pith.science/api/pith-number/6QHSBACXTWB55VBZRTGHEL4AVS/graph.json","events_json":"https://pith.science/api/pith-number/6QHSBACXTWB55VBZRTGHEL4AVS/events.json","paper":"https://pith.science/paper/6QHSBACX"},"agent_actions":{"view_html":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS","download_json":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS.json","view_paper":"https://pith.science/paper/6QHSBACX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12681&json=true","fetch_graph":"https://pith.science/api/pith-number/6QHSBACXTWB55VBZRTGHEL4AVS/graph.json","fetch_events":"https://pith.science/api/pith-number/6QHSBACXTWB55VBZRTGHEL4AVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS/action/storage_attestation","attest_author":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS/action/author_attestation","sign_citation":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS/action/citation_signature","submit_replication":"https://pith.science/pith/6QHSBACXTWB55VBZRTGHEL4AVS/action/replication_record"}},"created_at":"2026-07-05T11:05:08.096043+00:00","updated_at":"2026-07-05T11:05:08.096043+00:00"}