{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6FE7OF32VDWXLXFUD52BQVOM4O","short_pith_number":"pith:6FE7OF32","schema_version":"1.0","canonical_sha256":"f149f7177aa8ed75dcb41f741855cce3bf2220c1a24708058c982d56f5c3f345","source":{"kind":"arxiv","id":"2308.13259","version":2},"attestation_state":"computed","paper":{"title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuantao Yin, Feiyu Duan, Keheng Wang, Peiguang Li, Sirui Wang, Wenge Rong, Yunsen Xian, Zhang Xiong","submitted_at":"2023-08-25T09:23:55Z","abstract_excerpt":"Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come with incorrect or unfaithful intermediate reasoning steps, especially in the context of answering knowledge-intensive tasks such as KBQA. To alleviate this issue, we propose a framework called Knowledge-Driven Chain-of-Thought (KD-CoT) to verify and modify reasoning traces in CoT via interaction with external knowledge, and thus overcome the hallucinations an"},"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":"2308.13259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T09:23:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba0d0a7cc3aa0fb73ff53299a54aa89a2180e51ab7086ec9023177961df06a32","abstract_canon_sha256":"7a20662b9344289ad698a020ca9cbc725da869e762793ddfa622725f81bb382c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:33.202021Z","signature_b64":"cFDku7KYKiqc2mDF2kr3FElvqu18Ih/+TBCPJTpUM0xb3Sb7lbJWviwqoOKW5KjJWJ0e/RwE9/qZVqgd6lZrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f149f7177aa8ed75dcb41f741855cce3bf2220c1a24708058c982d56f5c3f345","last_reissued_at":"2026-07-05T07:06:33.201541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:33.201541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuantao Yin, Feiyu Duan, Keheng Wang, Peiguang Li, Sirui Wang, Wenge Rong, Yunsen Xian, Zhang Xiong","submitted_at":"2023-08-25T09:23:55Z","abstract_excerpt":"Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come with incorrect or unfaithful intermediate reasoning steps, especially in the context of answering knowledge-intensive tasks such as KBQA. To alleviate this issue, we propose a framework called Knowledge-Driven Chain-of-Thought (KD-CoT) to verify and modify reasoning traces in CoT via interaction with external knowledge, and thus overcome the hallucinations an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13259","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/2308.13259/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":"2308.13259","created_at":"2026-07-05T07:06:33.201598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13259v2","created_at":"2026-07-05T07:06:33.201598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13259","created_at":"2026-07-05T07:06:33.201598+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FE7OF32VDWX","created_at":"2026-07-05T07:06:33.201598+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FE7OF32VDWXLXFU","created_at":"2026-07-05T07:06:33.201598+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FE7OF32","created_at":"2026-07-05T07:06:33.201598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25486","citing_title":"RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17086","citing_title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O","json":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O.json","graph_json":"https://pith.science/api/pith-number/6FE7OF32VDWXLXFUD52BQVOM4O/graph.json","events_json":"https://pith.science/api/pith-number/6FE7OF32VDWXLXFUD52BQVOM4O/events.json","paper":"https://pith.science/paper/6FE7OF32"},"agent_actions":{"view_html":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O","download_json":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O.json","view_paper":"https://pith.science/paper/6FE7OF32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13259&json=true","fetch_graph":"https://pith.science/api/pith-number/6FE7OF32VDWXLXFUD52BQVOM4O/graph.json","fetch_events":"https://pith.science/api/pith-number/6FE7OF32VDWXLXFUD52BQVOM4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O/action/storage_attestation","attest_author":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O/action/author_attestation","sign_citation":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O/action/citation_signature","submit_replication":"https://pith.science/pith/6FE7OF32VDWXLXFUD52BQVOM4O/action/replication_record"}},"created_at":"2026-07-05T07:06:33.201598+00:00","updated_at":"2026-07-05T07:06:33.201598+00:00"}