{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WQ5W7LNS3RXCLZZZH6ZX2GLYQS","short_pith_number":"pith:WQ5W7LNS","schema_version":"1.0","canonical_sha256":"b43b6fadb2dc6e25e7393fb37d197884907d94c065fe67f06a08daf4b70c637c","source":{"kind":"arxiv","id":"2505.13989","version":2},"attestation_state":"computed","paper":{"title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guang Zeng, Guoren Wang, Qi Zhang, Rong-Hua Li, Xunkai Li, Yanzhe Wen, Zhu Lei","submitted_at":"2025-05-20T06:37:18Z","abstract_excerpt":"Recently, large language models (LLMs) have significantly advanced text-attributed graph (TAG) learning. However, existing methods inadequately handle data uncertainty in open-world scenarios, especially concerning limited labeling and unknown-class nodes. Prior solutions typically rely on isolated semantic or structural approaches for unknown-class rejection, lacking effective annotation pipelines. To address these limitations, we propose Open-world Graph Assistant (OGA), an LLM-based framework that combines adaptive label traceability, which integrates semantics and topology for unknown-clas"},"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":"2505.13989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T06:37:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40f3e9eb4e17a61b33d63ddc6360268c6c36de000aa92e175a02359ff9c04444","abstract_canon_sha256":"faf7be89d28fe9d10988d37c828aaddf2fae36abedc796b23e687140f94539ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:33.163676Z","signature_b64":"CgngWvqlxfoUq1EiZi+isg7gHz4zSQfl68tOlftub8Gg0+mmlTLw+hdIiUKZvOCpoWWARw1tkxHkxiu3rf0tDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43b6fadb2dc6e25e7393fb37d197884907d94c065fe67f06a08daf4b70c637c","last_reissued_at":"2026-07-05T11:06:33.163285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:33.163285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guang Zeng, Guoren Wang, Qi Zhang, Rong-Hua Li, Xunkai Li, Yanzhe Wen, Zhu Lei","submitted_at":"2025-05-20T06:37:18Z","abstract_excerpt":"Recently, large language models (LLMs) have significantly advanced text-attributed graph (TAG) learning. However, existing methods inadequately handle data uncertainty in open-world scenarios, especially concerning limited labeling and unknown-class nodes. Prior solutions typically rely on isolated semantic or structural approaches for unknown-class rejection, lacking effective annotation pipelines. To address these limitations, we propose Open-world Graph Assistant (OGA), an LLM-based framework that combines adaptive label traceability, which integrates semantics and topology for unknown-clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13989","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/2505.13989/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":"2505.13989","created_at":"2026-07-05T11:06:33.163346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13989v2","created_at":"2026-07-05T11:06:33.163346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13989","created_at":"2026-07-05T11:06:33.163346+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ5W7LNS3RXC","created_at":"2026-07-05T11:06:33.163346+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ5W7LNS3RXCLZZZ","created_at":"2026-07-05T11:06:33.163346+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ5W7LNS","created_at":"2026-07-05T11:06:33.163346+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/WQ5W7LNS3RXCLZZZH6ZX2GLYQS","json":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS.json","graph_json":"https://pith.science/api/pith-number/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/graph.json","events_json":"https://pith.science/api/pith-number/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/events.json","paper":"https://pith.science/paper/WQ5W7LNS"},"agent_actions":{"view_html":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS","download_json":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS.json","view_paper":"https://pith.science/paper/WQ5W7LNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13989&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/action/storage_attestation","attest_author":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/action/author_attestation","sign_citation":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/action/citation_signature","submit_replication":"https://pith.science/pith/WQ5W7LNS3RXCLZZZH6ZX2GLYQS/action/replication_record"}},"created_at":"2026-07-05T11:06:33.163346+00:00","updated_at":"2026-07-05T11:06:33.163346+00:00"}