{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GT35AHSUMRQTJ7P4D5K4GPN75Y","short_pith_number":"pith:GT35AHSU","schema_version":"1.0","canonical_sha256":"34f7d01e54646134fdfc1f55c33dbfee1d7d52c4f01c4d085e11e3cacfe1a929","source":{"kind":"arxiv","id":"2405.18357","version":2},"attestation_state":"computed","paper":{"title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Fei, Jundong Xu, Liangming Pan, Mong-Li Lee, Qian Liu, Wynne Hsu","submitted_at":"2024-05-28T16:55:33Z","abstract_excerpt":"While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought, namely SymbCoT, a fully LLM-based framework that integrates symbolic expressions and logic rules with CoT prompting. Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and "},"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":"2405.18357","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T16:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"e147c82ffd57d868059278f476e835a349f4daf72d698cf6b733caf9560845ec","abstract_canon_sha256":"03fe32a0d737ae5046b77e0e5ccd1c099ef607ef54add49aa7260ed61de9a4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:12.719508Z","signature_b64":"TNyb/jC8R8f7r8KmHpsNNSvb4uC1R7l/ChkByvNYxmSzqkdSNYeGqRseVIXkoz+X1Vd4uoHc1El5PBhTv4DJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f7d01e54646134fdfc1f55c33dbfee1d7d52c4f01c4d085e11e3cacfe1a929","last_reissued_at":"2026-07-05T08:30:12.718934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:12.718934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Fei, Jundong Xu, Liangming Pan, Mong-Li Lee, Qian Liu, Wynne Hsu","submitted_at":"2024-05-28T16:55:33Z","abstract_excerpt":"While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought, namely SymbCoT, a fully LLM-based framework that integrates symbolic expressions and logic rules with CoT prompting. Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18357","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/2405.18357/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":"2405.18357","created_at":"2026-07-05T08:30:12.718993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18357v2","created_at":"2026-07-05T08:30:12.718993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18357","created_at":"2026-07-05T08:30:12.718993+00:00"},{"alias_kind":"pith_short_12","alias_value":"GT35AHSUMRQT","created_at":"2026-07-05T08:30:12.718993+00:00"},{"alias_kind":"pith_short_16","alias_value":"GT35AHSUMRQTJ7P4","created_at":"2026-07-05T08:30:12.718993+00:00"},{"alias_kind":"pith_short_8","alias_value":"GT35AHSU","created_at":"2026-07-05T08:30:12.718993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20254","citing_title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24765","citing_title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14053","citing_title":"Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24341","citing_title":"GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y","json":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y.json","graph_json":"https://pith.science/api/pith-number/GT35AHSUMRQTJ7P4D5K4GPN75Y/graph.json","events_json":"https://pith.science/api/pith-number/GT35AHSUMRQTJ7P4D5K4GPN75Y/events.json","paper":"https://pith.science/paper/GT35AHSU"},"agent_actions":{"view_html":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y","download_json":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y.json","view_paper":"https://pith.science/paper/GT35AHSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18357&json=true","fetch_graph":"https://pith.science/api/pith-number/GT35AHSUMRQTJ7P4D5K4GPN75Y/graph.json","fetch_events":"https://pith.science/api/pith-number/GT35AHSUMRQTJ7P4D5K4GPN75Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y/action/storage_attestation","attest_author":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y/action/author_attestation","sign_citation":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y/action/citation_signature","submit_replication":"https://pith.science/pith/GT35AHSUMRQTJ7P4D5K4GPN75Y/action/replication_record"}},"created_at":"2026-07-05T08:30:12.718993+00:00","updated_at":"2026-07-05T08:30:12.718993+00:00"}