{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CGEXDJZDDWM4YWRAGSDJQIRJKI","short_pith_number":"pith:CGEXDJZD","schema_version":"1.0","canonical_sha256":"118971a7231d99cc5a2034869822295231b532d93220407fb8528364b91741fe","source":{"kind":"arxiv","id":"2106.11344","version":1},"attestation_state":"computed","paper":{"title":"f-Domain-Adversarial Learning: Theory and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler","submitted_at":"2021-06-21T18:21:09Z","abstract_excerpt":"Unsupervised domain adaptation is used in many machine learning applications where, during training, a model has access to unlabeled data in the target domain, and a related labeled dataset. In this paper, we introduce a novel and general domain-adversarial framework. Specifically, we derive a novel generalization bound for domain adaptation that exploits a new measure of discrepancy between distributions based on a variational characterization of f-divergences. It recovers the theoretical results from Ben-David et al. (2010a) as a special case and supports divergences used in practice. Based "},"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":"2106.11344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T18:21:09Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"49111abe576cf17d0c8f59e4d52e79e74cb5103e0a44e1626fdc750dfa320207","abstract_canon_sha256":"f7e9d3d3a5a7cb3eea679288845f824a7029a7fee198629ed789e7acbefa360d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:59.830002Z","signature_b64":"N8t3uHO30UFcw7VED43ZS+7Oz1YppWaL3uDDP4ULcURPWhFsx/83JuXT1AZ/EXwGShgYjnN1GFAtPCiq0bkgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"118971a7231d99cc5a2034869822295231b532d93220407fb8528364b91741fe","last_reissued_at":"2026-07-05T02:50:59.829502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:59.829502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"f-Domain-Adversarial Learning: Theory and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler","submitted_at":"2021-06-21T18:21:09Z","abstract_excerpt":"Unsupervised domain adaptation is used in many machine learning applications where, during training, a model has access to unlabeled data in the target domain, and a related labeled dataset. In this paper, we introduce a novel and general domain-adversarial framework. Specifically, we derive a novel generalization bound for domain adaptation that exploits a new measure of discrepancy between distributions based on a variational characterization of f-divergences. It recovers the theoretical results from Ben-David et al. (2010a) as a special case and supports divergences used in practice. Based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11344","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/2106.11344/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":"2106.11344","created_at":"2026-07-05T02:50:59.829562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11344v1","created_at":"2026-07-05T02:50:59.829562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11344","created_at":"2026-07-05T02:50:59.829562+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGEXDJZDDWM4","created_at":"2026-07-05T02:50:59.829562+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGEXDJZDDWM4YWRA","created_at":"2026-07-05T02:50:59.829562+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGEXDJZD","created_at":"2026-07-05T02:50:59.829562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21205","citing_title":"Learning from Limited and Imperfect Data","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI","json":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI.json","graph_json":"https://pith.science/api/pith-number/CGEXDJZDDWM4YWRAGSDJQIRJKI/graph.json","events_json":"https://pith.science/api/pith-number/CGEXDJZDDWM4YWRAGSDJQIRJKI/events.json","paper":"https://pith.science/paper/CGEXDJZD"},"agent_actions":{"view_html":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI","download_json":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI.json","view_paper":"https://pith.science/paper/CGEXDJZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11344&json=true","fetch_graph":"https://pith.science/api/pith-number/CGEXDJZDDWM4YWRAGSDJQIRJKI/graph.json","fetch_events":"https://pith.science/api/pith-number/CGEXDJZDDWM4YWRAGSDJQIRJKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI/action/storage_attestation","attest_author":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI/action/author_attestation","sign_citation":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI/action/citation_signature","submit_replication":"https://pith.science/pith/CGEXDJZDDWM4YWRAGSDJQIRJKI/action/replication_record"}},"created_at":"2026-07-05T02:50:59.829562+00:00","updated_at":"2026-07-05T02:50:59.829562+00:00"}