{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:74YBKF4SVYKZIMWHOPMNEAVWD4","short_pith_number":"pith:74YBKF4S","schema_version":"1.0","canonical_sha256":"ff30151792ae159432c773d8d202b61f3935553ac588b9006bb27a382c611940","source":{"kind":"arxiv","id":"2511.07457","version":2},"attestation_state":"computed","paper":{"title":"GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Donghong Cai, Jiarui Feng, Muhan Zhang, Yixin Chen","submitted_at":"2025-11-06T21:56:58Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, effectively adapting LLMs to structural data, such as knowledge graphs or web graphs, remains a fundamental challenge. Some approaches adopt complex strategies to convert graphs into text sequences, resulting in significant token overhead and rendering them impractical for large-scale graphs. Others introduce additional modules to encode graphs into fixed-size token representations for LLMs. However, these methods typically require large-sca"},"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":"2511.07457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-11-06T21:56:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87d5e81ff7b2f7c145ae6337716d71132e9d4753997a7596b4ce027fb566faae","abstract_canon_sha256":"6861f52fc35b8033af46099f8bbef2cd43a2b5d779e92675f250cc6490890674"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:40.765246Z","signature_b64":"c+Ozcz3rO+VPdowbqQ6rDPdWfACY+hS2CGD9ZGhWioIkX6rhpsXM1NjHFAKzFt7UABIJqgcvzXq0ewjPnETLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff30151792ae159432c773d8d202b61f3935553ac588b9006bb27a382c611940","last_reissued_at":"2026-07-21T01:21:40.764250Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:40.764250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Donghong Cai, Jiarui Feng, Muhan Zhang, Yixin Chen","submitted_at":"2025-11-06T21:56:58Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, effectively adapting LLMs to structural data, such as knowledge graphs or web graphs, remains a fundamental challenge. Some approaches adopt complex strategies to convert graphs into text sequences, resulting in significant token overhead and rendering them impractical for large-scale graphs. Others introduce additional modules to encode graphs into fixed-size token representations for LLMs. However, these methods typically require large-sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07457","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/2511.07457/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":"2511.07457","created_at":"2026-07-21T01:21:40.764727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07457v2","created_at":"2026-07-21T01:21:40.764727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07457","created_at":"2026-07-21T01:21:40.764727+00:00"},{"alias_kind":"pith_short_12","alias_value":"74YBKF4SVYKZ","created_at":"2026-07-21T01:21:40.764727+00:00"},{"alias_kind":"pith_short_16","alias_value":"74YBKF4SVYKZIMWH","created_at":"2026-07-21T01:21:40.764727+00:00"},{"alias_kind":"pith_short_8","alias_value":"74YBKF4S","created_at":"2026-07-21T01:21:40.764727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.02938","citing_title":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4","json":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4.json","graph_json":"https://pith.science/api/pith-number/74YBKF4SVYKZIMWHOPMNEAVWD4/graph.json","events_json":"https://pith.science/api/pith-number/74YBKF4SVYKZIMWHOPMNEAVWD4/events.json","paper":"https://pith.science/paper/74YBKF4S"},"agent_actions":{"view_html":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4","download_json":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4.json","view_paper":"https://pith.science/paper/74YBKF4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07457&json=true","fetch_graph":"https://pith.science/api/pith-number/74YBKF4SVYKZIMWHOPMNEAVWD4/graph.json","fetch_events":"https://pith.science/api/pith-number/74YBKF4SVYKZIMWHOPMNEAVWD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4/action/storage_attestation","attest_author":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4/action/author_attestation","sign_citation":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4/action/citation_signature","submit_replication":"https://pith.science/pith/74YBKF4SVYKZIMWHOPMNEAVWD4/action/replication_record"}},"created_at":"2026-07-21T01:21:40.764727+00:00","updated_at":"2026-07-21T01:21:40.764727+00:00"}