{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YRUTRIOQ2L43DWJEODLURQ45MP","short_pith_number":"pith:YRUTRIOQ","schema_version":"1.0","canonical_sha256":"c46938a1d0d2f9b1d92470d748c39d63e91c40d09e96a6858a2b583e5391261e","source":{"kind":"arxiv","id":"2104.01539","version":3},"attestation_state":"computed","paper":{"title":"DINE: Domain Adaptation from Single and Multiple Black-box Predictors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Hu, Jian Liang, Jiashi Feng, Ran He","submitted_at":"2021-04-04T05:29:05Z","abstract_excerpt":"To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw"},"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":"2104.01539","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-04T05:29:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"742cbbb199bf9e190a4e36be486b71493f031236b275f400122a65e8da618065","abstract_canon_sha256":"e2d8fbbafbe7ede703af2998ff2eec881fa2b743d832ce4667958f4aa0b68bff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:22.083393Z","signature_b64":"EAjRC1PW35Bc4VzrFkh8plv+8QpX/gci8Bdu3ZebEhizr10CBFTm344DftbZmFzGW2j0DRbLF/NQ1wUMj/zeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c46938a1d0d2f9b1d92470d748c39d63e91c40d09e96a6858a2b583e5391261e","last_reissued_at":"2026-07-05T04:10:22.082960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:22.082960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DINE: Domain Adaptation from Single and Multiple Black-box Predictors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dapeng Hu, Jian Liang, Jiashi Feng, Ran He","submitted_at":"2021-04-04T05:29:05Z","abstract_excerpt":"To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01539","kind":"arxiv","version":3},"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/2104.01539/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":"2104.01539","created_at":"2026-07-05T04:10:22.083019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01539v3","created_at":"2026-07-05T04:10:22.083019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01539","created_at":"2026-07-05T04:10:22.083019+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRUTRIOQ2L43","created_at":"2026-07-05T04:10:22.083019+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRUTRIOQ2L43DWJE","created_at":"2026-07-05T04:10:22.083019+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRUTRIOQ","created_at":"2026-07-05T04:10:22.083019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14301","citing_title":"What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP","json":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP.json","graph_json":"https://pith.science/api/pith-number/YRUTRIOQ2L43DWJEODLURQ45MP/graph.json","events_json":"https://pith.science/api/pith-number/YRUTRIOQ2L43DWJEODLURQ45MP/events.json","paper":"https://pith.science/paper/YRUTRIOQ"},"agent_actions":{"view_html":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP","download_json":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP.json","view_paper":"https://pith.science/paper/YRUTRIOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01539&json=true","fetch_graph":"https://pith.science/api/pith-number/YRUTRIOQ2L43DWJEODLURQ45MP/graph.json","fetch_events":"https://pith.science/api/pith-number/YRUTRIOQ2L43DWJEODLURQ45MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP/action/storage_attestation","attest_author":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP/action/author_attestation","sign_citation":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP/action/citation_signature","submit_replication":"https://pith.science/pith/YRUTRIOQ2L43DWJEODLURQ45MP/action/replication_record"}},"created_at":"2026-07-05T04:10:22.083019+00:00","updated_at":"2026-07-05T04:10:22.083019+00:00"}