{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QZ2BWOP7LEYCFESFY26YDRGYY4","short_pith_number":"pith:QZ2BWOP7","schema_version":"1.0","canonical_sha256":"86741b39ff5930229245c6bd81c4d8c721430a24300d76f38badc7d53ed5da7c","source":{"kind":"arxiv","id":"2408.12185","version":1},"attestation_state":"computed","paper":{"title":"Rank and Align: Towards Effective Source-free Graph Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Jingyang Yuan, Junyu Luo, Langechuan Liu, Ming Zhang, Wei Ju, Xiao Luo, Yifan Wang, Zhiping Xiao","submitted_at":"2024-08-22T08:00:50Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inhar"},"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":"2408.12185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T08:00:50Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"4f7de7cdb4f28fe288494493341773a0a7d4371b81790613a1bd3a9ab905f2af","abstract_canon_sha256":"ed6c32d871f1eaa182f091dc89fd08d5ed673288db6e772034b0bf28fee7230a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:05.438699Z","signature_b64":"twUDF0kdwpm/jifv623F4lq+1NH7IGGIA0HUxZeVxD92dOS+upbWQ1eR0uKBq2H/ly8pxFH9bgIV7TTEnjMJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86741b39ff5930229245c6bd81c4d8c721430a24300d76f38badc7d53ed5da7c","last_reissued_at":"2026-07-05T08:58:05.438261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:05.438261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rank and Align: Towards Effective Source-free Graph Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Jingyang Yuan, Junyu Luo, Langechuan Liu, Ming Zhang, Wei Ju, Xiao Luo, Yifan Wang, Zhiping Xiao","submitted_at":"2024-08-22T08:00:50Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inhar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12185","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/2408.12185/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":"2408.12185","created_at":"2026-07-05T08:58:05.438326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12185v1","created_at":"2026-07-05T08:58:05.438326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12185","created_at":"2026-07-05T08:58:05.438326+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZ2BWOP7LEYC","created_at":"2026-07-05T08:58:05.438326+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZ2BWOP7LEYCFESF","created_at":"2026-07-05T08:58:05.438326+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZ2BWOP7","created_at":"2026-07-05T08:58:05.438326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00808","citing_title":"Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4","json":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4.json","graph_json":"https://pith.science/api/pith-number/QZ2BWOP7LEYCFESFY26YDRGYY4/graph.json","events_json":"https://pith.science/api/pith-number/QZ2BWOP7LEYCFESFY26YDRGYY4/events.json","paper":"https://pith.science/paper/QZ2BWOP7"},"agent_actions":{"view_html":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4","download_json":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4.json","view_paper":"https://pith.science/paper/QZ2BWOP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12185&json=true","fetch_graph":"https://pith.science/api/pith-number/QZ2BWOP7LEYCFESFY26YDRGYY4/graph.json","fetch_events":"https://pith.science/api/pith-number/QZ2BWOP7LEYCFESFY26YDRGYY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4/action/storage_attestation","attest_author":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4/action/author_attestation","sign_citation":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4/action/citation_signature","submit_replication":"https://pith.science/pith/QZ2BWOP7LEYCFESFY26YDRGYY4/action/replication_record"}},"created_at":"2026-07-05T08:58:05.438326+00:00","updated_at":"2026-07-05T08:58:05.438326+00:00"}