{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DZR7273FYNTDEXEQRVQKHQEJE2","short_pith_number":"pith:DZR7273F","schema_version":"1.0","canonical_sha256":"1e63fd7f65c366325c908d60a3c08926b09ddbe54ae69b89fca5dc4951fe7c07","source":{"kind":"arxiv","id":"2410.12126","version":2},"attestation_state":"computed","paper":{"title":"What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.AI","authors_text":"Dongqi Fu, Hanghang Tong, Jingrui He, Liri Fang, Vetle I. Torvik, Zihao Li","submitted_at":"2024-10-16T00:01:31Z","abstract_excerpt":"Graphs, as a relational data structure, have been widely used for various application scenarios, like molecule design and recommender systems. Recently, large language models (LLMs) are reorganizing in the AI community for their expected reasoning and inference abilities. Making LLMs understand graph-based relational data has great potential, including but not limited to (1) distillate external knowledge base for eliminating hallucination and breaking the context window limit for LLMs' inference during the retrieval augmentation generation process; (2) taking graph data as the input and direct"},"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":"2410.12126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-16T00:01:31Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"e912b6bc50841d203e4f9b30ed33074a4f361ca9272c6f68fdc7c349d78a43d3","abstract_canon_sha256":"6b30a897ad0c9070db7fd11d907b9b293ca8cb7b3af78f845bae2e1d6565b394"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:46.295980Z","signature_b64":"k8J0Cdn4pwEOtwaNgJLEf7W8WlfTDXH8hSz4rVkkC7YdeRRYOo/mYU4F5NHWFvcYViRN7JRmWBpAZROMBISeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e63fd7f65c366325c908d60a3c08926b09ddbe54ae69b89fca5dc4951fe7c07","last_reissued_at":"2026-07-05T10:15:46.295461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:46.295461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.AI","authors_text":"Dongqi Fu, Hanghang Tong, Jingrui He, Liri Fang, Vetle I. Torvik, Zihao Li","submitted_at":"2024-10-16T00:01:31Z","abstract_excerpt":"Graphs, as a relational data structure, have been widely used for various application scenarios, like molecule design and recommender systems. Recently, large language models (LLMs) are reorganizing in the AI community for their expected reasoning and inference abilities. Making LLMs understand graph-based relational data has great potential, including but not limited to (1) distillate external knowledge base for eliminating hallucination and breaking the context window limit for LLMs' inference during the retrieval augmentation generation process; (2) taking graph data as the input and direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12126","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/2410.12126/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":"2410.12126","created_at":"2026-07-05T10:15:46.295515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12126v2","created_at":"2026-07-05T10:15:46.295515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12126","created_at":"2026-07-05T10:15:46.295515+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZR7273FYNTD","created_at":"2026-07-05T10:15:46.295515+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZR7273FYNTDEXEQ","created_at":"2026-07-05T10:15:46.295515+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZR7273F","created_at":"2026-07-05T10:15:46.295515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00620","citing_title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2","json":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2.json","graph_json":"https://pith.science/api/pith-number/DZR7273FYNTDEXEQRVQKHQEJE2/graph.json","events_json":"https://pith.science/api/pith-number/DZR7273FYNTDEXEQRVQKHQEJE2/events.json","paper":"https://pith.science/paper/DZR7273F"},"agent_actions":{"view_html":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2","download_json":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2.json","view_paper":"https://pith.science/paper/DZR7273F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12126&json=true","fetch_graph":"https://pith.science/api/pith-number/DZR7273FYNTDEXEQRVQKHQEJE2/graph.json","fetch_events":"https://pith.science/api/pith-number/DZR7273FYNTDEXEQRVQKHQEJE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2/action/storage_attestation","attest_author":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2/action/author_attestation","sign_citation":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2/action/citation_signature","submit_replication":"https://pith.science/pith/DZR7273FYNTDEXEQRVQKHQEJE2/action/replication_record"}},"created_at":"2026-07-05T10:15:46.295515+00:00","updated_at":"2026-07-05T10:15:46.295515+00:00"}