{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LS6674HPGDZ3GENBZ5PK6NLVR2","short_pith_number":"pith:LS6674HP","schema_version":"1.0","canonical_sha256":"5cbdeff0ef30f3b311a1cf5eaf35758e914373cc650869dc95e4a8a145f1440f","source":{"kind":"arxiv","id":"2101.02839","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Domain Adaptation of Black-Box Source Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haojian Zhang, Kui Jia, Lei Zhang, Yabin Zhang","submitted_at":"2021-01-08T04:00:49Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain. In the traditional UDA setting, labeled source data are assumed to be available for adaptation. Due to increasing concerns for data privacy, source-free UDA is highly appreciated as a new UDA setting, where only a trained source model is assumed to be available, while labeled source data remain private. However, trained source models may also be unavailable in practice since source models may have commercial values and exposing source models br"},"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":"2101.02839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-08T04:00:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b4b4a6ae013d8b1036bcdb9182688089de89ef96775df358a3a29feacadb49b9","abstract_canon_sha256":"95f0d174bb86e3579b2f5ac86368eb4b55b6705fa20b023bf8bf51ffc8281912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:54.435606Z","signature_b64":"NITIZJ9gRiFLfCKNwgY12Ig+4PWtHlXycctpgMYNLxB+PYlZQTftQzemt0Bt/OUqoJp1bPu0U4VUkissgyzUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbdeff0ef30f3b311a1cf5eaf35758e914373cc650869dc95e4a8a145f1440f","last_reissued_at":"2026-07-05T02:26:54.435149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:54.435149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Domain Adaptation of Black-Box Source Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haojian Zhang, Kui Jia, Lei Zhang, Yabin Zhang","submitted_at":"2021-01-08T04:00:49Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain. In the traditional UDA setting, labeled source data are assumed to be available for adaptation. Due to increasing concerns for data privacy, source-free UDA is highly appreciated as a new UDA setting, where only a trained source model is assumed to be available, while labeled source data remain private. However, trained source models may also be unavailable in practice since source models may have commercial values and exposing source models br"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02839","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/2101.02839/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":"2101.02839","created_at":"2026-07-05T02:26:54.435205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02839v2","created_at":"2026-07-05T02:26:54.435205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02839","created_at":"2026-07-05T02:26:54.435205+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS6674HPGDZ3","created_at":"2026-07-05T02:26:54.435205+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS6674HPGDZ3GENB","created_at":"2026-07-05T02:26:54.435205+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS6674HP","created_at":"2026-07-05T02:26:54.435205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00509","citing_title":"Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2","json":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2.json","graph_json":"https://pith.science/api/pith-number/LS6674HPGDZ3GENBZ5PK6NLVR2/graph.json","events_json":"https://pith.science/api/pith-number/LS6674HPGDZ3GENBZ5PK6NLVR2/events.json","paper":"https://pith.science/paper/LS6674HP"},"agent_actions":{"view_html":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2","download_json":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2.json","view_paper":"https://pith.science/paper/LS6674HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02839&json=true","fetch_graph":"https://pith.science/api/pith-number/LS6674HPGDZ3GENBZ5PK6NLVR2/graph.json","fetch_events":"https://pith.science/api/pith-number/LS6674HPGDZ3GENBZ5PK6NLVR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2/action/storage_attestation","attest_author":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2/action/author_attestation","sign_citation":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2/action/citation_signature","submit_replication":"https://pith.science/pith/LS6674HPGDZ3GENBZ5PK6NLVR2/action/replication_record"}},"created_at":"2026-07-05T02:26:54.435205+00:00","updated_at":"2026-07-05T02:26:54.435205+00:00"}