{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DYTYONCTTZTSLUOOENVUTYD4X2","short_pith_number":"pith:DYTYONCT","schema_version":"1.0","canonical_sha256":"1e278734539e6725d1ce236b49e07cbeb6b7e70927d7390326863aae8ae9e6ac","source":{"kind":"arxiv","id":"2508.14427","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junliang Du, Mengjie Wang, Wuyang Zhang, Xiandong Meng, Yexin Tian","submitted_at":"2025-08-20T04:52:12Z","abstract_excerpt":"This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm framework based on knowledge graph injection. The method builds on pretrained language models and introduces structured graph information for auxiliary learning. A graph neural network is used to encode entities and their relations, constructing a graph-based semantic representation. A fusion mechanism is then designed to jointly model the knowledge graph embeddi"},"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":"2508.14427","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T04:52:12Z","cross_cats_sorted":[],"title_canon_sha256":"0419fd23e87fd6085b3b6221e2ae9a534429f323a5e79c2d4372ecfe1fc04551","abstract_canon_sha256":"072355a7597e619be115a462f218306645f6a611feb8cf4075d910557f989541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:31.670567Z","signature_b64":"Z581+PFTNx0IcTM16WrdGswj1qalsbt1z0dhjJDsCx2TdS68yU122zYgazbV8iJDMM1achBuOlc5EimquqnGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e278734539e6725d1ce236b49e07cbeb6b7e70927d7390326863aae8ae9e6ac","last_reissued_at":"2026-07-05T11:56:31.670103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:31.670103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junliang Du, Mengjie Wang, Wuyang Zhang, Xiandong Meng, Yexin Tian","submitted_at":"2025-08-20T04:52:12Z","abstract_excerpt":"This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm framework based on knowledge graph injection. The method builds on pretrained language models and introduces structured graph information for auxiliary learning. A graph neural network is used to encode entities and their relations, constructing a graph-based semantic representation. A fusion mechanism is then designed to jointly model the knowledge graph embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14427","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/2508.14427/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":"2508.14427","created_at":"2026-07-05T11:56:31.670159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14427v1","created_at":"2026-07-05T11:56:31.670159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14427","created_at":"2026-07-05T11:56:31.670159+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYTYONCTTZTS","created_at":"2026-07-05T11:56:31.670159+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYTYONCTTZTSLUOO","created_at":"2026-07-05T11:56:31.670159+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYTYONCT","created_at":"2026-07-05T11:56:31.670159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04973","citing_title":"Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2","json":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2.json","graph_json":"https://pith.science/api/pith-number/DYTYONCTTZTSLUOOENVUTYD4X2/graph.json","events_json":"https://pith.science/api/pith-number/DYTYONCTTZTSLUOOENVUTYD4X2/events.json","paper":"https://pith.science/paper/DYTYONCT"},"agent_actions":{"view_html":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2","download_json":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2.json","view_paper":"https://pith.science/paper/DYTYONCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14427&json=true","fetch_graph":"https://pith.science/api/pith-number/DYTYONCTTZTSLUOOENVUTYD4X2/graph.json","fetch_events":"https://pith.science/api/pith-number/DYTYONCTTZTSLUOOENVUTYD4X2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2/action/storage_attestation","attest_author":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2/action/author_attestation","sign_citation":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2/action/citation_signature","submit_replication":"https://pith.science/pith/DYTYONCTTZTSLUOOENVUTYD4X2/action/replication_record"}},"created_at":"2026-07-05T11:56:31.670159+00:00","updated_at":"2026-07-05T11:56:31.670159+00:00"}