{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AAHF2WBKSBTSJGKKY3MXRP5DQB","short_pith_number":"pith:AAHF2WBK","schema_version":"1.0","canonical_sha256":"000e5d582a906724994ac6d978bfa3805100001112b19b342f30f0566e777e3f","source":{"kind":"arxiv","id":"2410.22372","version":1},"attestation_state":"computed","paper":{"title":"A Hierarchical Language Model For Interpretable Graph Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sambhav Khurana, Shuiwang Ji, Shurui Gui, Xiner Li","submitted_at":"2024-10-29T00:28:02Z","abstract_excerpt":"Large language models (LLMs) are being increasingly explored for graph tasks. Despite their remarkable success in text-based tasks, LLMs' capabilities in understanding explicit graph structures remain limited, particularly with large graphs. In this work, we introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure, effectively enhancing graph structure understanding abilities. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, a"},"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":"2410.22372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T00:28:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"484a9efacabfe7584642de78e57644fc5d0f86e75cad7613591ffa47081af606","abstract_canon_sha256":"88a6747d88e54304784d7344f59cbcfbe8a1f85ac4ed41cc45c117507c5a2b19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:15.653081Z","signature_b64":"JFTIds3snwF8RbXNuda+BgUJZMdOm6l+3TA+iTnt7DlzLTaK4ZArduzAVE/reJU970g6yShWfzajxMCtfzlqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000e5d582a906724994ac6d978bfa3805100001112b19b342f30f0566e777e3f","last_reissued_at":"2026-07-05T09:28:15.652630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:15.652630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchical Language Model For Interpretable Graph Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sambhav Khurana, Shuiwang Ji, Shurui Gui, Xiner Li","submitted_at":"2024-10-29T00:28:02Z","abstract_excerpt":"Large language models (LLMs) are being increasingly explored for graph tasks. Despite their remarkable success in text-based tasks, LLMs' capabilities in understanding explicit graph structures remain limited, particularly with large graphs. In this work, we introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure, effectively enhancing graph structure understanding abilities. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22372","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/2410.22372/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":"2410.22372","created_at":"2026-07-05T09:28:15.652688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22372v1","created_at":"2026-07-05T09:28:15.652688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22372","created_at":"2026-07-05T09:28:15.652688+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAHF2WBKSBTS","created_at":"2026-07-05T09:28:15.652688+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAHF2WBKSBTSJGKK","created_at":"2026-07-05T09:28:15.652688+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAHF2WBK","created_at":"2026-07-05T09:28:15.652688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06865","citing_title":"Are Large Language Models Suitable for Graph Computation? Progress and Prospects","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03606","citing_title":"Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB","json":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB.json","graph_json":"https://pith.science/api/pith-number/AAHF2WBKSBTSJGKKY3MXRP5DQB/graph.json","events_json":"https://pith.science/api/pith-number/AAHF2WBKSBTSJGKKY3MXRP5DQB/events.json","paper":"https://pith.science/paper/AAHF2WBK"},"agent_actions":{"view_html":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB","download_json":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB.json","view_paper":"https://pith.science/paper/AAHF2WBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22372&json=true","fetch_graph":"https://pith.science/api/pith-number/AAHF2WBKSBTSJGKKY3MXRP5DQB/graph.json","fetch_events":"https://pith.science/api/pith-number/AAHF2WBKSBTSJGKKY3MXRP5DQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB/action/storage_attestation","attest_author":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB/action/author_attestation","sign_citation":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB/action/citation_signature","submit_replication":"https://pith.science/pith/AAHF2WBKSBTSJGKKY3MXRP5DQB/action/replication_record"}},"created_at":"2026-07-05T09:28:15.652688+00:00","updated_at":"2026-07-05T09:28:15.652688+00:00"}