{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZRVLEY6U5NQIXVLIU7MOSETPQ","short_pith_number":"pith:FZRVLEY6","schema_version":"1.0","canonical_sha256":"2e6355931ea75b045eab453ec748937c0b580c24108ec52c9c53da60f128cc77","source":{"kind":"arxiv","id":"2304.13911","version":2},"attestation_state":"computed","paper":{"title":"Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyou Fan, Tianqi Pang, Xiangyang Liu","submitted_at":"2023-04-27T01:48:03Z","abstract_excerpt":"We investigate how to enhance answer precision in frequently asked questions posed by distributed users using cloud-based Large Language Models (LLMs). Our study focuses on a typical situations where users ask similar queries that involve identical mathematical reasoning steps and problem-solving procedures. Due to the unsatisfactory accuracy of LLMs' zero-shot prompting with standalone questions, we propose to improve the distributed synonymous questions using Self-Consistency (SC) and Chain-of-Thought (CoT) techniques. Specifically, we first retrieve synonymous questions from a crowd-sourced"},"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":"2304.13911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-04-27T01:48:03Z","cross_cats_sorted":[],"title_canon_sha256":"9f6d688a02c5403a8956daa883380f4aa43af4c477fffcadc5310f4bc679408e","abstract_canon_sha256":"5f856f4dd404ca075798a8809d8c3fc526a357b2d113ef6cf21725d363dc296d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:21.424715Z","signature_b64":"SHMlHBlESSsNoH8OayDw2EA4vlGnOaQrg5/liEylPPjpAWv7FtAkRPUoCuVOVEZrjeRf8yUZxMO2xcKb5La/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6355931ea75b045eab453ec748937c0b580c24108ec52c9c53da60f128cc77","last_reissued_at":"2026-07-05T06:26:21.424171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:21.424171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Prompting and Chain-of-Thought Reasoning for Improving LLMs Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyou Fan, Tianqi Pang, Xiangyang Liu","submitted_at":"2023-04-27T01:48:03Z","abstract_excerpt":"We investigate how to enhance answer precision in frequently asked questions posed by distributed users using cloud-based Large Language Models (LLMs). Our study focuses on a typical situations where users ask similar queries that involve identical mathematical reasoning steps and problem-solving procedures. Due to the unsatisfactory accuracy of LLMs' zero-shot prompting with standalone questions, we propose to improve the distributed synonymous questions using Self-Consistency (SC) and Chain-of-Thought (CoT) techniques. Specifically, we first retrieve synonymous questions from a crowd-sourced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13911","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/2304.13911/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":"2304.13911","created_at":"2026-07-05T06:26:21.424228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13911v2","created_at":"2026-07-05T06:26:21.424228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13911","created_at":"2026-07-05T06:26:21.424228+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZRVLEY6U5NQ","created_at":"2026-07-05T06:26:21.424228+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZRVLEY6U5NQIXVL","created_at":"2026-07-05T06:26:21.424228+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZRVLEY6","created_at":"2026-07-05T06:26:21.424228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ","json":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ.json","graph_json":"https://pith.science/api/pith-number/FZRVLEY6U5NQIXVLIU7MOSETPQ/graph.json","events_json":"https://pith.science/api/pith-number/FZRVLEY6U5NQIXVLIU7MOSETPQ/events.json","paper":"https://pith.science/paper/FZRVLEY6"},"agent_actions":{"view_html":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ","download_json":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ.json","view_paper":"https://pith.science/paper/FZRVLEY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13911&json=true","fetch_graph":"https://pith.science/api/pith-number/FZRVLEY6U5NQIXVLIU7MOSETPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FZRVLEY6U5NQIXVLIU7MOSETPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ/action/storage_attestation","attest_author":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ/action/author_attestation","sign_citation":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ/action/citation_signature","submit_replication":"https://pith.science/pith/FZRVLEY6U5NQIXVLIU7MOSETPQ/action/replication_record"}},"created_at":"2026-07-05T06:26:21.424228+00:00","updated_at":"2026-07-05T06:26:21.424228+00:00"}