{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U6DWQ76JELR6I4PY7KQMAPURRN","short_pith_number":"pith:U6DWQ76J","schema_version":"1.0","canonical_sha256":"a787687fc922e3e471f8faa0c03e918b55610d2fea5e69001653bf3bf8c971cf","source":{"kind":"arxiv","id":"2410.18415","version":1},"attestation_state":"computed","paper":{"title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu","submitted_at":"2024-10-24T04:01:40Z","abstract_excerpt":"Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs' step-wise reasoning capabilities and KGs' structural nature. In this paper, we present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. We first define a concept, well-formed chain, which consists of a sequence of interrela"},"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":"2410.18415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T04:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"e61e336677cd30b834278270cf0eb719cf54fd9d4ee4411e29568bf906234c11","abstract_canon_sha256":"1a41088a6d2ece775d17205fdf8049b0c71f70d3ff4e90f071e44c0acca28819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:07.980906Z","signature_b64":"91BFhbJegeVEdJaEjB7SqdDruMeTCzezL8+aE21hGl2ibnKOFJC0/RD598twkeNHkpPo39Zo8B0yWW0NXKhACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a787687fc922e3e471f8faa0c03e918b55610d2fea5e69001653bf3bf8c971cf","last_reissued_at":"2026-07-05T09:25:07.980408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:07.980408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Helen Meng, Hongyin Luo, James Glass, Kun Li, Tianhua Zhang, Xixin Wu","submitted_at":"2024-10-24T04:01:40Z","abstract_excerpt":"Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs' step-wise reasoning capabilities and KGs' structural nature. In this paper, we present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. We first define a concept, well-formed chain, which consists of a sequence of interrela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18415","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/2410.18415/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":"2410.18415","created_at":"2026-07-05T09:25:07.980470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18415v1","created_at":"2026-07-05T09:25:07.980470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18415","created_at":"2026-07-05T09:25:07.980470+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6DWQ76JELR6","created_at":"2026-07-05T09:25:07.980470+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6DWQ76JELR6I4PY","created_at":"2026-07-05T09:25:07.980470+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6DWQ76J","created_at":"2026-07-05T09:25:07.980470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17086","citing_title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN","json":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN.json","graph_json":"https://pith.science/api/pith-number/U6DWQ76JELR6I4PY7KQMAPURRN/graph.json","events_json":"https://pith.science/api/pith-number/U6DWQ76JELR6I4PY7KQMAPURRN/events.json","paper":"https://pith.science/paper/U6DWQ76J"},"agent_actions":{"view_html":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN","download_json":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN.json","view_paper":"https://pith.science/paper/U6DWQ76J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18415&json=true","fetch_graph":"https://pith.science/api/pith-number/U6DWQ76JELR6I4PY7KQMAPURRN/graph.json","fetch_events":"https://pith.science/api/pith-number/U6DWQ76JELR6I4PY7KQMAPURRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN/action/storage_attestation","attest_author":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN/action/author_attestation","sign_citation":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN/action/citation_signature","submit_replication":"https://pith.science/pith/U6DWQ76JELR6I4PY7KQMAPURRN/action/replication_record"}},"created_at":"2026-07-05T09:25:07.980470+00:00","updated_at":"2026-07-05T09:25:07.980470+00:00"}