{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:35KU37CP6IZF4HF6RGKSM63OGF","short_pith_number":"pith:35KU37CP","schema_version":"1.0","canonical_sha256":"df554dfc4ff2325e1cbe8995267b6e317b130897efbd8e9bdde77935b3428946","source":{"kind":"arxiv","id":"2409.04057","version":2},"attestation_state":"computed","paper":{"title":"Self-Harmonized Chain of Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wei Lu, Ziqi Jin","submitted_at":"2024-09-06T06:57:04Z","abstract_excerpt":"Chain-of-thought (CoT) prompting has demonstrated the capacity of large language models to perform complex reasoning through intermediate steps. While effective, current CoT methods face challenges: Zero-shot-CoT can lead to reasoning errors, and Few-shot-CoT requires labor-intensive manual demonstrations. Auto-CoT attempts to address these issues by automatically generating diverse demonstrations, but this diversity can lead to inconsistent reasoning patterns. We propose ECHO (Self-Harmonized Chain of Thought), a novel method that unifies diverse solution paths into a consistent and effective"},"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":"2409.04057","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T06:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"fed6fca3e171b82cc35f31068babec11b5f004423ad0838b6256e9ea33631bba","abstract_canon_sha256":"93880c860171daff4c7969ce2a1795c0ab089b8b94d28ad2599dce65a8e8967e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:19.603998Z","signature_b64":"EEL2WBe+gH6czmwby1U0UyXccfn/nCKs/YEexAT3v6SWUN8uUI3XKKOBmcdxNye6gzFGWXgstfyO1hvFd1rcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df554dfc4ff2325e1cbe8995267b6e317b130897efbd8e9bdde77935b3428946","last_reissued_at":"2026-07-05T10:12:19.603518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:19.603518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Harmonized Chain of Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wei Lu, Ziqi Jin","submitted_at":"2024-09-06T06:57:04Z","abstract_excerpt":"Chain-of-thought (CoT) prompting has demonstrated the capacity of large language models to perform complex reasoning through intermediate steps. While effective, current CoT methods face challenges: Zero-shot-CoT can lead to reasoning errors, and Few-shot-CoT requires labor-intensive manual demonstrations. Auto-CoT attempts to address these issues by automatically generating diverse demonstrations, but this diversity can lead to inconsistent reasoning patterns. We propose ECHO (Self-Harmonized Chain of Thought), a novel method that unifies diverse solution paths into a consistent and effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04057","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/2409.04057/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":"2409.04057","created_at":"2026-07-05T10:12:19.603576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04057v2","created_at":"2026-07-05T10:12:19.603576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04057","created_at":"2026-07-05T10:12:19.603576+00:00"},{"alias_kind":"pith_short_12","alias_value":"35KU37CP6IZF","created_at":"2026-07-05T10:12:19.603576+00:00"},{"alias_kind":"pith_short_16","alias_value":"35KU37CP6IZF4HF6","created_at":"2026-07-05T10:12:19.603576+00:00"},{"alias_kind":"pith_short_8","alias_value":"35KU37CP","created_at":"2026-07-05T10:12:19.603576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF","json":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF.json","graph_json":"https://pith.science/api/pith-number/35KU37CP6IZF4HF6RGKSM63OGF/graph.json","events_json":"https://pith.science/api/pith-number/35KU37CP6IZF4HF6RGKSM63OGF/events.json","paper":"https://pith.science/paper/35KU37CP"},"agent_actions":{"view_html":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF","download_json":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF.json","view_paper":"https://pith.science/paper/35KU37CP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04057&json=true","fetch_graph":"https://pith.science/api/pith-number/35KU37CP6IZF4HF6RGKSM63OGF/graph.json","fetch_events":"https://pith.science/api/pith-number/35KU37CP6IZF4HF6RGKSM63OGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF/action/storage_attestation","attest_author":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF/action/author_attestation","sign_citation":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF/action/citation_signature","submit_replication":"https://pith.science/pith/35KU37CP6IZF4HF6RGKSM63OGF/action/replication_record"}},"created_at":"2026-07-05T10:12:19.603576+00:00","updated_at":"2026-07-05T10:12:19.603576+00:00"}