{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ZXMV73X5TOM5BYMVFJHAKEP7Z","short_pith_number":"pith:3ZXMV73X","schema_version":"1.0","canonical_sha256":"de6ecaff77ecdcce870ca95270288ffe52011cebf02361dc0f21a3d74ad4810a","source":{"kind":"arxiv","id":"2308.10450","version":2},"attestation_state":"computed","paper":{"title":"COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Ling Shao, Tao Zhou, Xinghong Liu, Yi Zhou","submitted_at":"2023-08-21T03:50:19Z","abstract_excerpt":"Universal domain adaptation (UniDA) aims to address domain and category shifts across data sources. Recently, due to more stringent data restrictions, researchers have introduced source-free UniDA (SF-UniDA). SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain. However, existing SF-UniDA methods still require an extensive quantity of labeled source samples to train a source model, resulting in significant labeling costs. To tackle this issue, we present a novel plug-and-play classifier-oriented calibration (COCA) method. COCA,"},"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":"2308.10450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T03:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"e1c3e84a3d4ff42a1062d3a0486fc52fb25890b5c779a2f4d3cbe49a86eebf8a","abstract_canon_sha256":"834ac6493d4f98b19a19c53ae9098de8b6ff7fd10fbfa28e3fbc0e3a7203bc9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:32.407079Z","signature_b64":"ntxL4aE/anKTlVFWlmzWat+sUt/PKdQYpFBXlCStK3m535D0AHLW3a+urVIIF/syr11RD2q7zCYFfsJyw7XzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6ecaff77ecdcce870ca95270288ffe52011cebf02361dc0f21a3d74ad4810a","last_reissued_at":"2026-07-05T07:54:32.406609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:32.406609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Ling Shao, Tao Zhou, Xinghong Liu, Yi Zhou","submitted_at":"2023-08-21T03:50:19Z","abstract_excerpt":"Universal domain adaptation (UniDA) aims to address domain and category shifts across data sources. Recently, due to more stringent data restrictions, researchers have introduced source-free UniDA (SF-UniDA). SF-UniDA methods eliminate the need for direct access to source samples when performing adaptation to the target domain. However, existing SF-UniDA methods still require an extensive quantity of labeled source samples to train a source model, resulting in significant labeling costs. To tackle this issue, we present a novel plug-and-play classifier-oriented calibration (COCA) method. COCA,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10450","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/2308.10450/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":"2308.10450","created_at":"2026-07-05T07:54:32.406666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10450v2","created_at":"2026-07-05T07:54:32.406666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10450","created_at":"2026-07-05T07:54:32.406666+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZXMV73X5TOM","created_at":"2026-07-05T07:54:32.406666+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZXMV73X5TOM5BYM","created_at":"2026-07-05T07:54:32.406666+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZXMV73X","created_at":"2026-07-05T07:54:32.406666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03521","citing_title":"Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z","json":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z.json","graph_json":"https://pith.science/api/pith-number/3ZXMV73X5TOM5BYMVFJHAKEP7Z/graph.json","events_json":"https://pith.science/api/pith-number/3ZXMV73X5TOM5BYMVFJHAKEP7Z/events.json","paper":"https://pith.science/paper/3ZXMV73X"},"agent_actions":{"view_html":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z","download_json":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z.json","view_paper":"https://pith.science/paper/3ZXMV73X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10450&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZXMV73X5TOM5BYMVFJHAKEP7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZXMV73X5TOM5BYMVFJHAKEP7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z/action/storage_attestation","attest_author":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z/action/author_attestation","sign_citation":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z/action/citation_signature","submit_replication":"https://pith.science/pith/3ZXMV73X5TOM5BYMVFJHAKEP7Z/action/replication_record"}},"created_at":"2026-07-05T07:54:32.406666+00:00","updated_at":"2026-07-05T07:54:32.406666+00:00"}