{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZR7XNSWB4GDTMHXPZPUZ5P2JET","short_pith_number":"pith:ZR7XNSWB","schema_version":"1.0","canonical_sha256":"cc7f76cac1e187361eefcbe99ebf4924c6e73b02605f286e58960aca2d8170cd","source":{"kind":"arxiv","id":"2504.21186","version":2},"attestation_state":"computed","paper":{"title":"GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Langzhou He, Mengyuan Li, Philip S. Yu, Xuzhi Zhang, Yue Zhao, Yushun Dong, Zhengtao Yao, Ziyi Wang","submitted_at":"2025-04-29T21:42:54Z","abstract_excerpt":"Out-of-distribution (OOD) detection is critical for ensuring the safety and reliability of machine learning systems, particularly in dynamic and open-world environments. In the vision and text domains, zero-shot OOD detection - which requires no training on in-distribution (ID) data - has advanced significantly through the use of large-scale pretrained models, such as vision-language models (VLMs) and large language models (LLMs). However, zero-shot OOD detection in graph-structured data remains largely unexplored, primarily due to the challenges posed by complex relational structures and the "},"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":"2504.21186","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T21:42:54Z","cross_cats_sorted":[],"title_canon_sha256":"9776611aba06d1e415982b956746ada8c29c450ec802394a2830a327005db7bc","abstract_canon_sha256":"f5f073907ec77db3c31f961589e10691062b9559f2f52ca229256b38324c1033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:21.972431Z","signature_b64":"RyzHHVv+iVP9jV4d2HJvbZyPaHIYVsGluI3cDYq9o8Zdev+sZAg4VRQ5BTGr6sYwhKebfRtahjF2w5eLIm1pCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc7f76cac1e187361eefcbe99ebf4924c6e73b02605f286e58960aca2d8170cd","last_reissued_at":"2026-07-05T11:04:21.971896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:21.971896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Langzhou He, Mengyuan Li, Philip S. Yu, Xuzhi Zhang, Yue Zhao, Yushun Dong, Zhengtao Yao, Ziyi Wang","submitted_at":"2025-04-29T21:42:54Z","abstract_excerpt":"Out-of-distribution (OOD) detection is critical for ensuring the safety and reliability of machine learning systems, particularly in dynamic and open-world environments. In the vision and text domains, zero-shot OOD detection - which requires no training on in-distribution (ID) data - has advanced significantly through the use of large-scale pretrained models, such as vision-language models (VLMs) and large language models (LLMs). However, zero-shot OOD detection in graph-structured data remains largely unexplored, primarily due to the challenges posed by complex relational structures and the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21186","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/2504.21186/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":"2504.21186","created_at":"2026-07-05T11:04:21.971954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21186v2","created_at":"2026-07-05T11:04:21.971954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21186","created_at":"2026-07-05T11:04:21.971954+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR7XNSWB4GDT","created_at":"2026-07-05T11:04:21.971954+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR7XNSWB4GDTMHXP","created_at":"2026-07-05T11:04:21.971954+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR7XNSWB","created_at":"2026-07-05T11:04:21.971954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32016","citing_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET","json":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET.json","graph_json":"https://pith.science/api/pith-number/ZR7XNSWB4GDTMHXPZPUZ5P2JET/graph.json","events_json":"https://pith.science/api/pith-number/ZR7XNSWB4GDTMHXPZPUZ5P2JET/events.json","paper":"https://pith.science/paper/ZR7XNSWB"},"agent_actions":{"view_html":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET","download_json":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET.json","view_paper":"https://pith.science/paper/ZR7XNSWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21186&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR7XNSWB4GDTMHXPZPUZ5P2JET/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR7XNSWB4GDTMHXPZPUZ5P2JET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET/action/storage_attestation","attest_author":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET/action/author_attestation","sign_citation":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET/action/citation_signature","submit_replication":"https://pith.science/pith/ZR7XNSWB4GDTMHXPZPUZ5P2JET/action/replication_record"}},"created_at":"2026-07-05T11:04:21.971954+00:00","updated_at":"2026-07-05T11:04:21.971954+00:00"}