{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VWWBD5PBS6HNEXODXS5CNZHSFW","short_pith_number":"pith:VWWBD5PB","schema_version":"1.0","canonical_sha256":"adac11f5e1978ed25dc3bcba26e4f22d9b08ea485d5809df30b6ed793bdcf889","source":{"kind":"arxiv","id":"2310.17594","version":2},"attestation_state":"computed","paper":{"title":"SPA: A Graph Spectral Alignment Perspective for Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Huang, Gang Chen, Haobo Wang, Junbo Zhao, Lei Feng, Ying Jin, Zhiqing Xiao","submitted_at":"2023-10-26T17:13:48Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment m"},"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":"2310.17594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T17:13:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ceb20c421e56af7643770054fcfb045938cca7b97d0f753fea3ab23b8448e2c","abstract_canon_sha256":"ad88ff0bd1cb18360e2e607abf38b6af2c7a5dd2780fd0fc272ce08f9f1f2457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:50.109185Z","signature_b64":"DdVVnZZUT/vi+gZ1mW4r6Nu8gdWNMD9NJzWENs7Uh0TS+2aP283hXLUZUaM2HXwnjAsqb8TRfevSvJLeMq56Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adac11f5e1978ed25dc3bcba26e4f22d9b08ea485d5809df30b6ed793bdcf889","last_reissued_at":"2026-07-05T07:05:50.108710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:50.108710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPA: A Graph Spectral Alignment Perspective for Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Huang, Gang Chen, Haobo Wang, Junbo Zhao, Lei Feng, Ying Jin, Zhiqing Xiao","submitted_at":"2023-10-26T17:13:48Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17594","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/2310.17594/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":"2310.17594","created_at":"2026-07-05T07:05:50.108768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17594v2","created_at":"2026-07-05T07:05:50.108768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17594","created_at":"2026-07-05T07:05:50.108768+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWWBD5PBS6HN","created_at":"2026-07-05T07:05:50.108768+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWWBD5PBS6HNEXOD","created_at":"2026-07-05T07:05:50.108768+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWWBD5PB","created_at":"2026-07-05T07:05:50.108768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW","json":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW.json","graph_json":"https://pith.science/api/pith-number/VWWBD5PBS6HNEXODXS5CNZHSFW/graph.json","events_json":"https://pith.science/api/pith-number/VWWBD5PBS6HNEXODXS5CNZHSFW/events.json","paper":"https://pith.science/paper/VWWBD5PB"},"agent_actions":{"view_html":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW","download_json":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW.json","view_paper":"https://pith.science/paper/VWWBD5PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17594&json=true","fetch_graph":"https://pith.science/api/pith-number/VWWBD5PBS6HNEXODXS5CNZHSFW/graph.json","fetch_events":"https://pith.science/api/pith-number/VWWBD5PBS6HNEXODXS5CNZHSFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW/action/storage_attestation","attest_author":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW/action/author_attestation","sign_citation":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW/action/citation_signature","submit_replication":"https://pith.science/pith/VWWBD5PBS6HNEXODXS5CNZHSFW/action/replication_record"}},"created_at":"2026-07-05T07:05:50.108768+00:00","updated_at":"2026-07-05T07:05:50.108768+00:00"}