{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5D6265UOPK6AJFO3RB5V2TIQX","short_pith_number":"pith:F5D6265U","schema_version":"1.0","canonical_sha256":"2f47ed7bb473d5e024aedc43daea6885d4d732283d39b3908fd30515871ac9b3","source":{"kind":"arxiv","id":"2410.15811","version":2},"attestation_state":"computed","paper":{"title":"Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jindong Li, Qi Wang, Shengsheng Wang, Yongguang Li, Yueqi Cao","submitted_at":"2024-10-21T09:25:49Z","abstract_excerpt":"Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model's performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns. However, most existing SF-UDA approaches assume the availability of abundant source domain samples, which is often impractical due to the high cost of data annotation. To address the dual challenges of limited source data and privacy concerns, we introduce a data-efficient, CLIP-powered dual-branch network (CDBN). This architecture consists of a cross-domain featu"},"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":"2410.15811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T09:25:49Z","cross_cats_sorted":[],"title_canon_sha256":"537d0ba8a0bdf7fe1058532c0ee2926aa9ec9688952c84765be9fc94d5fec4d3","abstract_canon_sha256":"a71abaabd052b6a7af8c095f9445ca9a639ed73285cc22deef1c1100d5507e0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:31.601644Z","signature_b64":"KoXOP/JJTB2MG+Ckq0vc29qBXq5kHlxZdRnh4uO/rqZUBmCLl8UM6pbpyOrAn5W9DZvOTpEnky9fQ5rOIb3vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f47ed7bb473d5e024aedc43daea6885d4d732283d39b3908fd30515871ac9b3","last_reissued_at":"2026-07-05T09:26:31.601123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:31.601123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jindong Li, Qi Wang, Shengsheng Wang, Yongguang Li, Yueqi Cao","submitted_at":"2024-10-21T09:25:49Z","abstract_excerpt":"Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model's performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns. However, most existing SF-UDA approaches assume the availability of abundant source domain samples, which is often impractical due to the high cost of data annotation. To address the dual challenges of limited source data and privacy concerns, we introduce a data-efficient, CLIP-powered dual-branch network (CDBN). This architecture consists of a cross-domain featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15811","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/2410.15811/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":"2410.15811","created_at":"2026-07-05T09:26:31.601185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15811v2","created_at":"2026-07-05T09:26:31.601185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15811","created_at":"2026-07-05T09:26:31.601185+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5D6265UOPK6","created_at":"2026-07-05T09:26:31.601185+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5D6265UOPK6AJFO","created_at":"2026-07-05T09:26:31.601185+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5D6265U","created_at":"2026-07-05T09:26:31.601185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05547","citing_title":"Adapting Vision-Language Models Without Labels: A Comprehensive Survey","ref_index":120,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX","json":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX.json","graph_json":"https://pith.science/api/pith-number/F5D6265UOPK6AJFO3RB5V2TIQX/graph.json","events_json":"https://pith.science/api/pith-number/F5D6265UOPK6AJFO3RB5V2TIQX/events.json","paper":"https://pith.science/paper/F5D6265U"},"agent_actions":{"view_html":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX","download_json":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX.json","view_paper":"https://pith.science/paper/F5D6265U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15811&json=true","fetch_graph":"https://pith.science/api/pith-number/F5D6265UOPK6AJFO3RB5V2TIQX/graph.json","fetch_events":"https://pith.science/api/pith-number/F5D6265UOPK6AJFO3RB5V2TIQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX/action/storage_attestation","attest_author":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX/action/author_attestation","sign_citation":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX/action/citation_signature","submit_replication":"https://pith.science/pith/F5D6265UOPK6AJFO3RB5V2TIQX/action/replication_record"}},"created_at":"2026-07-05T09:26:31.601185+00:00","updated_at":"2026-07-05T09:26:31.601185+00:00"}