{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HSBUTI6YDJNM7KOFSNGF2URGV7","short_pith_number":"pith:HSBUTI6Y","schema_version":"1.0","canonical_sha256":"3c8349a3d81a5acfa9c5934c5d5226afe3c85959a6141b5c2e9b697a1b685cca","source":{"kind":"arxiv","id":"2309.11054","version":2},"attestation_state":"computed","paper":{"title":"Design of Chain-of-Thought in Math Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.CL","authors_text":"Hang Li, Trung Quoc Luong, Xiaoran Jin, Xinbo Zhang, Zhanming Jie","submitted_at":"2023-09-20T04:17:28Z","abstract_excerpt":"Chain-of-Thought (CoT) plays a crucial role in reasoning for math problem solving. We conduct a comprehensive examination of methods for designing CoT, comparing conventional natural language CoT with various program CoTs, including the self-describing program, the comment-describing program, and the non-describing program. Furthermore, we investigate the impact of programming language on program CoTs, comparing Python and Wolfram Language. Through extensive experiments on GSM8K, MATHQA, and SVAMP, we find that program CoTs often have superior effectiveness in math problem solving. Notably, th"},"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":"2309.11054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-20T04:17:28Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PL"],"title_canon_sha256":"e1004bdcedf0b37a2a63365a99926436eda1b06cc9150d2cc3a529936182348e","abstract_canon_sha256":"866f5d9e4692270e377d2ff28c149a91ab2862d6391355f35b15bc04f0baf288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:59.323579Z","signature_b64":"gvt4I0rsyzwx1dKZbP/7F/Nes7X3ufRt8S2pEzjTFEC2DYwFlbKuzwLGWg0fPIMsNYc+dRbOyiDm8FPEelWnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c8349a3d81a5acfa9c5934c5d5226afe3c85959a6141b5c2e9b697a1b685cca","last_reissued_at":"2026-07-05T06:55:59.323125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:59.323125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design of Chain-of-Thought in Math Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PL"],"primary_cat":"cs.CL","authors_text":"Hang Li, Trung Quoc Luong, Xiaoran Jin, Xinbo Zhang, Zhanming Jie","submitted_at":"2023-09-20T04:17:28Z","abstract_excerpt":"Chain-of-Thought (CoT) plays a crucial role in reasoning for math problem solving. We conduct a comprehensive examination of methods for designing CoT, comparing conventional natural language CoT with various program CoTs, including the self-describing program, the comment-describing program, and the non-describing program. Furthermore, we investigate the impact of programming language on program CoTs, comparing Python and Wolfram Language. Through extensive experiments on GSM8K, MATHQA, and SVAMP, we find that program CoTs often have superior effectiveness in math problem solving. Notably, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11054","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/2309.11054/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":"2309.11054","created_at":"2026-07-05T06:55:59.323185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11054v2","created_at":"2026-07-05T06:55:59.323185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11054","created_at":"2026-07-05T06:55:59.323185+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSBUTI6YDJNM","created_at":"2026-07-05T06:55:59.323185+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSBUTI6YDJNM7KOF","created_at":"2026-07-05T06:55:59.323185+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSBUTI6Y","created_at":"2026-07-05T06:55:59.323185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20995","citing_title":"KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7","json":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7.json","graph_json":"https://pith.science/api/pith-number/HSBUTI6YDJNM7KOFSNGF2URGV7/graph.json","events_json":"https://pith.science/api/pith-number/HSBUTI6YDJNM7KOFSNGF2URGV7/events.json","paper":"https://pith.science/paper/HSBUTI6Y"},"agent_actions":{"view_html":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7","download_json":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7.json","view_paper":"https://pith.science/paper/HSBUTI6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11054&json=true","fetch_graph":"https://pith.science/api/pith-number/HSBUTI6YDJNM7KOFSNGF2URGV7/graph.json","fetch_events":"https://pith.science/api/pith-number/HSBUTI6YDJNM7KOFSNGF2URGV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7/action/storage_attestation","attest_author":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7/action/author_attestation","sign_citation":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7/action/citation_signature","submit_replication":"https://pith.science/pith/HSBUTI6YDJNM7KOFSNGF2URGV7/action/replication_record"}},"created_at":"2026-07-05T06:55:59.323185+00:00","updated_at":"2026-07-05T06:55:59.323185+00:00"}