{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZPLMAQB32ALWURHMNTN5FWY3J6","short_pith_number":"pith:ZPLMAQB3","schema_version":"1.0","canonical_sha256":"cbd6c0403bd0176a44ec6cdbd2db1b4f9812e92ce441d4253bfcd0c38639ec84","source":{"kind":"arxiv","id":"2410.09780","version":1},"attestation_state":"computed","paper":{"title":"Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Chung, Byungju Kim, Gisang Lee, Junyoung Park, Min-Gyu Cho, Sangwoo Park, Sieun Park, Yoonah Park","submitted_at":"2024-10-13T08:49:22Z","abstract_excerpt":"Large Language Models (LLMs) have exhibited remarkable capabilities in many complex tasks including mathematical reasoning. However, traditional approaches heavily rely on ensuring self-consistency within single prompting method, which limits the exploration of diverse problem-solving strategies. This study addresses these limitations by performing an experimental analysis of distinct prompting methods within the domain of mathematical reasoning. Our findings demonstrate that each method explores a distinct search space, and this differentiation becomes more evident with increasing problem com"},"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":"2410.09780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-13T08:49:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65ac227cf1effa0877acfb226b4d1a9e70281775f5fb35fe49f71b4aa44b4b1b","abstract_canon_sha256":"40dfda7d3ce541525da937fcffcb0d9cfa1f5fdf65b0d0cfccd1f384584d55fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:44.024446Z","signature_b64":"54beEiQBcTy3SDsfDyos8tIjfP3fmBwuWUq3YQlIkev1dW6/fwdDMlTXP3yCbxI1SoGPChRiTNQmzap3rONqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd6c0403bd0176a44ec6cdbd2db1b4f9812e92ce441d4253bfcd0c38639ec84","last_reissued_at":"2026-07-05T09:19:44.023976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:44.023976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Chung, Byungju Kim, Gisang Lee, Junyoung Park, Min-Gyu Cho, Sangwoo Park, Sieun Park, Yoonah Park","submitted_at":"2024-10-13T08:49:22Z","abstract_excerpt":"Large Language Models (LLMs) have exhibited remarkable capabilities in many complex tasks including mathematical reasoning. However, traditional approaches heavily rely on ensuring self-consistency within single prompting method, which limits the exploration of diverse problem-solving strategies. This study addresses these limitations by performing an experimental analysis of distinct prompting methods within the domain of mathematical reasoning. Our findings demonstrate that each method explores a distinct search space, and this differentiation becomes more evident with increasing problem com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09780","kind":"arxiv","version":1},"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/2410.09780/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":"2410.09780","created_at":"2026-07-05T09:19:44.024031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09780v1","created_at":"2026-07-05T09:19:44.024031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09780","created_at":"2026-07-05T09:19:44.024031+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPLMAQB32ALW","created_at":"2026-07-05T09:19:44.024031+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPLMAQB32ALWURHM","created_at":"2026-07-05T09:19:44.024031+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPLMAQB3","created_at":"2026-07-05T09:19:44.024031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":204,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6","json":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6.json","graph_json":"https://pith.science/api/pith-number/ZPLMAQB32ALWURHMNTN5FWY3J6/graph.json","events_json":"https://pith.science/api/pith-number/ZPLMAQB32ALWURHMNTN5FWY3J6/events.json","paper":"https://pith.science/paper/ZPLMAQB3"},"agent_actions":{"view_html":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6","download_json":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6.json","view_paper":"https://pith.science/paper/ZPLMAQB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09780&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPLMAQB32ALWURHMNTN5FWY3J6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPLMAQB32ALWURHMNTN5FWY3J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6/action/storage_attestation","attest_author":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6/action/author_attestation","sign_citation":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6/action/citation_signature","submit_replication":"https://pith.science/pith/ZPLMAQB32ALWURHMNTN5FWY3J6/action/replication_record"}},"created_at":"2026-07-05T09:19:44.024031+00:00","updated_at":"2026-07-05T09:19:44.024031+00:00"}