{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MA3FBSD75HCVWMYAW2M5NEB66X","short_pith_number":"pith:MA3FBSD7","schema_version":"1.0","canonical_sha256":"603650c87fe9c55b3300b699d6903ef5f276e1848a6b784fccf4ab6f05c62850","source":{"kind":"arxiv","id":"2403.10834","version":1},"attestation_state":"computed","paper":{"title":"SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jonghyun Lee, Juhyeon Shin, Sungroh Yoon, Uiwon Hwang","submitted_at":"2024-03-16T07:05:47Z","abstract_excerpt":"In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)$^2$), a novel approa"},"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":"2403.10834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T07:05:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c48590822f3105a175072033b2faa7f52a7a073ed9bbcb5a49fbf9f93801a687","abstract_canon_sha256":"97f6ccaf3ec8737104df940862fd32dc529f27c53176350e66629a8864cd5b97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:07.759745Z","signature_b64":"4Hcy4Jfq6d7GrOd9dsqJv6+jvAEZqm3kGj+kKktugo2XVAnetQ2/9nNnUwHClPNmQl5W6cQS19R/oI320mHCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"603650c87fe9c55b3300b699d6903ef5f276e1848a6b784fccf4ab6f05c62850","last_reissued_at":"2026-07-05T07:57:07.759349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:07.759349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jonghyun Lee, Juhyeon Shin, Sungroh Yoon, Uiwon Hwang","submitted_at":"2024-03-16T07:05:47Z","abstract_excerpt":"In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)$^2$), a novel approa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10834","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/2403.10834/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":"2403.10834","created_at":"2026-07-05T07:57:07.759407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10834v1","created_at":"2026-07-05T07:57:07.759407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10834","created_at":"2026-07-05T07:57:07.759407+00:00"},{"alias_kind":"pith_short_12","alias_value":"MA3FBSD75HCV","created_at":"2026-07-05T07:57:07.759407+00:00"},{"alias_kind":"pith_short_16","alias_value":"MA3FBSD75HCVWMYA","created_at":"2026-07-05T07:57:07.759407+00:00"},{"alias_kind":"pith_short_8","alias_value":"MA3FBSD7","created_at":"2026-07-05T07:57:07.759407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00808","citing_title":"Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15775","citing_title":"Continual Learning of Domain-Invariant Representations","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X","json":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X.json","graph_json":"https://pith.science/api/pith-number/MA3FBSD75HCVWMYAW2M5NEB66X/graph.json","events_json":"https://pith.science/api/pith-number/MA3FBSD75HCVWMYAW2M5NEB66X/events.json","paper":"https://pith.science/paper/MA3FBSD7"},"agent_actions":{"view_html":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X","download_json":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X.json","view_paper":"https://pith.science/paper/MA3FBSD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10834&json=true","fetch_graph":"https://pith.science/api/pith-number/MA3FBSD75HCVWMYAW2M5NEB66X/graph.json","fetch_events":"https://pith.science/api/pith-number/MA3FBSD75HCVWMYAW2M5NEB66X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X/action/storage_attestation","attest_author":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X/action/author_attestation","sign_citation":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X/action/citation_signature","submit_replication":"https://pith.science/pith/MA3FBSD75HCVWMYAW2M5NEB66X/action/replication_record"}},"created_at":"2026-07-05T07:57:07.759407+00:00","updated_at":"2026-07-05T07:57:07.759407+00:00"}