{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FQMCDKHNVWX7RW6KQIJFTMP55X","short_pith_number":"pith:FQMCDKHN","canonical_record":{"source":{"id":"2305.04091","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"f56516d1ca947cb363110d8bea974c14791c50e9325777e0a715a28c362e970d","abstract_canon_sha256":"f065ef4bf5e68e80903b1ad1da282d69025925c2b3235bae6ac3930ef1d10a4a"},"schema_version":"1.0"},"canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","source":{"kind":"arxiv","id":"2305.04091","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04091","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04091v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04091","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"FQMCDKHNVWX7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FQMCDKHNVWX7RW6K","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FQMCDKHN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FQMCDKHNVWX7RW6KQIJFTMP55X","target":"record","payload":{"canonical_record":{"source":{"id":"2305.04091","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"f56516d1ca947cb363110d8bea974c14791c50e9325777e0a715a28c362e970d","abstract_canon_sha256":"f065ef4bf5e68e80903b1ad1da282d69025925c2b3235bae6ac3930ef1d10a4a"},"schema_version":"1.0"},"canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.467490Z","signature_b64":"0Ezq/Y76dBJPKZ1ZKEfnTACgSNgCoOTBXGKfTiQ7e7KGWekfMamw2n4DHaTTRmrmXZK4uFqalj7dAGYFUCX7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","last_reissued_at":"2026-05-17T23:38:48.467034Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.467034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.04091","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EutzuzfyuUKbnFI8W6WecNY3aqbpwgoddVGb9gO5ltUM0WlTPBeDGhYmlWxeRZGTLFFNn2pfuWcwNFUa45DVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:32.463791Z"},"content_sha256":"8d82de18bfe0b95ef71d3098f6ccce4f8b0f2d7e3731fbc7ed19965dfa2e3d21","schema_version":"1.0","event_id":"sha256:8d82de18bfe0b95ef71d3098f6ccce4f8b0f2d7e3731fbc7ed19965dfa2e3d21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FQMCDKHNVWX7RW6KQIJFTMP55X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ee-Peng Lim, Lei Wang, Roy Ka-Wei Lee, Wanyu Xu, Yihuai Lan, Yunshi Lan, Zhiqiang Hu","submitted_at":"2023-05-06T16:34:37Z","abstract_excerpt":"Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zero-shot-CoT concatenates the target problem statement with \"Let's think step by step\" as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation erro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8a80f66e3f1f9c1d7f1e6df22f2072c7b98d11e28e71f28b4759a3313000f6ff"},"source":{"id":"2305.04091","kind":"arxiv","version":3},"verdict":{"id":"6b747126-1475-4eac-bbaa-f08dac9ff3c0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:40:06.485739Z","strongest_claim":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem.","one_line_summary":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors.","pith_extraction_headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning."},"references":{"count":25,"sample":[{"doi":"","year":2016,"title":"On the advance of making language models better reasoners.arXiv preprint arXiv:2206.02336, 2","work_id":"43823128-e3c9-4d2e-8e37-8e23c025e9d0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","work_id":"7226ffd7-2787-4b30-823a-785e230e85d1","ref_index":2,"cited_arxiv_id":"2304.11477","is_internal_anchor":true},{"doi":"","year":2080,"title":"Measuring and Narrowing the Compositionality Gap in Language Models","work_id":"79aa4add-ff4a-4871-9c74-6f473b0579c1","ref_index":3,"cited_arxiv_id":"2210.03350","is_internal_anchor":true},{"doi":"","year":2023,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","ref_index":4,"cited_arxiv_id":"2201.08239","is_internal_anchor":true},{"doi":"","year":null,"title":"Convert A cents to dollars","work_id":"20a509f4-362a-4a5c-9eed-0ef99405d4f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"59d79be762bbc139cdb3f6637b76a61f5f6aa1629319a82a1837ed2383f76b4f","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f9983cbdb2bfc9b3fcf2048cba1b69baaa29a8d995e597ded4203c6dd90f6717"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"6b747126-1475-4eac-bbaa-f08dac9ff3c0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T1kNLDYAyuVgHD46F/4x8t631B34V6quKR+JbS5q0A9kr27ww/rsQ9kUGt08FPGhPWNkhqvCtB7BNBG6/K4qBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:32.464347Z"},"content_sha256":"402a77d42667d3386160e3ce99bd3b4930ab6349a55765d00931e413d408b056","schema_version":"1.0","event_id":"sha256:402a77d42667d3386160e3ce99bd3b4930ab6349a55765d00931e413d408b056"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/bundle.json","state_url":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T18:30:32Z","links":{"resolver":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X","bundle":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/bundle.json","state":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FQMCDKHNVWX7RW6KQIJFTMP55X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f065ef4bf5e68e80903b1ad1da282d69025925c2b3235bae6ac3930ef1d10a4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","title_canon_sha256":"f56516d1ca947cb363110d8bea974c14791c50e9325777e0a715a28c362e970d"},"schema_version":"1.0","source":{"id":"2305.04091","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04091","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04091v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04091","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"FQMCDKHNVWX7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FQMCDKHNVWX7RW6K","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FQMCDKHN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:402a77d42667d3386160e3ce99bd3b4930ab6349a55765d00931e413d408b056","target":"graph","created_at":"2026-05-17T23:38:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning."}],"snapshot_sha256":"8a80f66e3f1f9c1d7f1e6df22f2072c7b98d11e28e71f28b4759a3313000f6ff"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f9983cbdb2bfc9b3fcf2048cba1b69baaa29a8d995e597ded4203c6dd90f6717"},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zero-shot-CoT concatenates the target problem statement with \"Let's think step by step\" as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation erro","authors_text":"Ee-Peng Lim, Lei Wang, Roy Ka-Wei Lee, Wanyu Xu, Yihuai Lan, Yunshi Lan, Zhiqiang Hu","cross_cats":[],"headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models"},"references":{"count":25,"internal_anchors":3,"resolved_work":25,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"On the advance of making language models better reasoners.arXiv preprint arXiv:2206.02336, 2","work_id":"43823128-e3c9-4d2e-8e37-8e23c025e9d0","year":2016},{"cited_arxiv_id":"2304.11477","doi":"","is_internal_anchor":true,"ref_index":2,"title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","work_id":"7226ffd7-2787-4b30-823a-785e230e85d1","year":2019},{"cited_arxiv_id":"2210.03350","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Measuring and Narrowing the Compositionality Gap in Language Models","work_id":"79aa4add-ff4a-4871-9c74-6f473b0579c1","year":2080},{"cited_arxiv_id":"2201.08239","doi":"","is_internal_anchor":true,"ref_index":4,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Convert A cents to dollars","work_id":"20a509f4-362a-4a5c-9eed-0ef99405d4f6","year":null}],"snapshot_sha256":"59d79be762bbc139cdb3f6637b76a61f5f6aa1629319a82a1837ed2383f76b4f"},"source":{"id":"2305.04091","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T08:40:06.485739Z","id":"6b747126-1475-4eac-bbaa-f08dac9ff3c0","model_set":{"reader":"grok-4.3"},"one_line_summary":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","strongest_claim":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem.","weakest_assumption":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors."}},"verdict_id":"6b747126-1475-4eac-bbaa-f08dac9ff3c0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8d82de18bfe0b95ef71d3098f6ccce4f8b0f2d7e3731fbc7ed19965dfa2e3d21","target":"record","created_at":"2026-05-17T23:38:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f065ef4bf5e68e80903b1ad1da282d69025925c2b3235bae6ac3930ef1d10a4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","title_canon_sha256":"f56516d1ca947cb363110d8bea974c14791c50e9325777e0a715a28c362e970d"},"schema_version":"1.0","source":{"id":"2305.04091","kind":"arxiv","version":3}},"canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","first_computed_at":"2026-05-17T23:38:48.467034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.467034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Ezq/Y76dBJPKZ1ZKEfnTACgSNgCoOTBXGKfTiQ7e7KGWekfMamw2n4DHaTTRmrmXZK4uFqalj7dAGYFUCX7DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.467490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04091","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d82de18bfe0b95ef71d3098f6ccce4f8b0f2d7e3731fbc7ed19965dfa2e3d21","sha256:402a77d42667d3386160e3ce99bd3b4930ab6349a55765d00931e413d408b056"],"state_sha256":"260ef4c288ce244b4e0e0473bc27cd4219d9a2fed8f4b6b11c84a4d7d2409a46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLaTIOnR/dQr/QmxgI15GnYb1/9ZKuxsysu8kvSeOuk+cZpKH9AjiuKEf5HYS0oAbnkBQR7QdYKrkIWZjiOZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:30:32.467182Z","bundle_sha256":"7818856f74b5b789f43db3d4239bccdace7256925e57848c981f8e5626034362"}}