{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7JXJ6QRSYFGIZD425QVHBUECKO","short_pith_number":"pith:7JXJ6QRS","schema_version":"1.0","canonical_sha256":"fa6e9f4232c14c8c8f9aec2a70d082538b17f1de355de2898017daa45c41110d","source":{"kind":"arxiv","id":"2503.22097","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Graph Out-of-Distribution Detection with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Mengyuan Li, Ryan A. Rossi, Yue Zhao, Yushun Dong, Zhengtao Yao, Ziyi Wang","submitted_at":"2025-03-28T02:37:18Z","abstract_excerpt":"Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled nodes in text-attributed graphs (TAGs) is challenging and costly due to their complex textual and structural characteristics. Large language models (LLMs), known for their powerful zero-shot capabilities in textual tasks, show promise but struggle to naturally capture the critical structural information inherent to TAGs, limiting their direct effectiveness.\n  To"},"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":"2503.22097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T02:37:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0126e0de1c003239eb036d8d9c3849328161951adfd5515c74a2c90c87e9cd12","abstract_canon_sha256":"317b471e359adbd9fa86c85b3b807038d48aea365488b7fb4270aabf10510335"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:03.090553Z","signature_b64":"KpEW4ro6hSad7Xabu1Tf4qrfMKeXK/6HAQC97OCv5Tvj02hHrEqjYq4gk3+o1YCPzfTbbYxJQtgZEiR4URYFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa6e9f4232c14c8c8f9aec2a70d082538b17f1de355de2898017daa45c41110d","last_reissued_at":"2026-07-05T10:41:03.090092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:03.090092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Graph Out-of-Distribution Detection with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Mengyuan Li, Ryan A. Rossi, Yue Zhao, Yushun Dong, Zhengtao Yao, Ziyi Wang","submitted_at":"2025-03-28T02:37:18Z","abstract_excerpt":"Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled nodes in text-attributed graphs (TAGs) is challenging and costly due to their complex textual and structural characteristics. Large language models (LLMs), known for their powerful zero-shot capabilities in textual tasks, show promise but struggle to naturally capture the critical structural information inherent to TAGs, limiting their direct effectiveness.\n  To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22097","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/2503.22097/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":"2503.22097","created_at":"2026-07-05T10:41:03.090150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22097v1","created_at":"2026-07-05T10:41:03.090150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22097","created_at":"2026-07-05T10:41:03.090150+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JXJ6QRSYFGI","created_at":"2026-07-05T10:41:03.090150+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JXJ6QRSYFGIZD42","created_at":"2026-07-05T10:41:03.090150+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JXJ6QRS","created_at":"2026-07-05T10:41:03.090150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.21186","citing_title":"GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO","json":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO.json","graph_json":"https://pith.science/api/pith-number/7JXJ6QRSYFGIZD425QVHBUECKO/graph.json","events_json":"https://pith.science/api/pith-number/7JXJ6QRSYFGIZD425QVHBUECKO/events.json","paper":"https://pith.science/paper/7JXJ6QRS"},"agent_actions":{"view_html":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO","download_json":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO.json","view_paper":"https://pith.science/paper/7JXJ6QRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22097&json=true","fetch_graph":"https://pith.science/api/pith-number/7JXJ6QRSYFGIZD425QVHBUECKO/graph.json","fetch_events":"https://pith.science/api/pith-number/7JXJ6QRSYFGIZD425QVHBUECKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO/action/storage_attestation","attest_author":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO/action/author_attestation","sign_citation":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO/action/citation_signature","submit_replication":"https://pith.science/pith/7JXJ6QRSYFGIZD425QVHBUECKO/action/replication_record"}},"created_at":"2026-07-05T10:41:03.090150+00:00","updated_at":"2026-07-05T10:41:03.090150+00:00"}