{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQL26B3GQT2BXNU4NFQTXQBYC7","short_pith_number":"pith:GQL26B3G","schema_version":"1.0","canonical_sha256":"3417af076684f41bb69c69613bc03817d9313432c7ab7ebfaa7994e632e4b76e","source":{"kind":"arxiv","id":"2410.12608","version":2},"attestation_state":"computed","paper":{"title":"Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deepanway Ghosal, Soujanya Poria, Vernon Y.H. Toh","submitted_at":"2024-10-16T14:24:55Z","abstract_excerpt":"Large language models (LLMs) have shown increasing competence in solving mathematical reasoning problems. However, many open-source LLMs still struggle with errors in calculation and semantic understanding during intermediate reasoning steps. In this work, we introduce Prove, a simple yet effective framework that leverages translated programs derived from natural language solutions as a verification mechanism to filter out potentially incorrect reasoning paths before aggregating final answers. Unlike vanilla majority voting, our approach filters out solutions whose corresponding program output"},"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":"2410.12608","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T14:24:55Z","cross_cats_sorted":[],"title_canon_sha256":"4b52cc11000bdea74e8aacac7dc0bcfce8b128c3f2e0ec13e0d0ea483be594cc","abstract_canon_sha256":"bf65fce0a0ea38ea01b8b27b1098adb9822050a60cad82a2dd0e8b4c9b7abc10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:06.185931Z","signature_b64":"8UJIeM2hwveQIRUZw1IZR3uom/DuUGPg2looFdmx3OBGzXZdRF0deI9LRHydKcqzBYl/l5yvSNZJk/NuIR7EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3417af076684f41bb69c69613bc03817d9313432c7ab7ebfaa7994e632e4b76e","last_reissued_at":"2026-07-05T09:50:06.185408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:06.185408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deepanway Ghosal, Soujanya Poria, Vernon Y.H. Toh","submitted_at":"2024-10-16T14:24:55Z","abstract_excerpt":"Large language models (LLMs) have shown increasing competence in solving mathematical reasoning problems. However, many open-source LLMs still struggle with errors in calculation and semantic understanding during intermediate reasoning steps. In this work, we introduce Prove, a simple yet effective framework that leverages translated programs derived from natural language solutions as a verification mechanism to filter out potentially incorrect reasoning paths before aggregating final answers. Unlike vanilla majority voting, our approach filters out solutions whose corresponding program output"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12608","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/2410.12608/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":"2410.12608","created_at":"2026-07-05T09:50:06.185470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12608v2","created_at":"2026-07-05T09:50:06.185470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12608","created_at":"2026-07-05T09:50:06.185470+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQL26B3GQT2B","created_at":"2026-07-05T09:50:06.185470+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQL26B3GQT2BXNU4","created_at":"2026-07-05T09:50:06.185470+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQL26B3G","created_at":"2026-07-05T09:50:06.185470+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/GQL26B3GQT2BXNU4NFQTXQBYC7","json":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7.json","graph_json":"https://pith.science/api/pith-number/GQL26B3GQT2BXNU4NFQTXQBYC7/graph.json","events_json":"https://pith.science/api/pith-number/GQL26B3GQT2BXNU4NFQTXQBYC7/events.json","paper":"https://pith.science/paper/GQL26B3G"},"agent_actions":{"view_html":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7","download_json":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7.json","view_paper":"https://pith.science/paper/GQL26B3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12608&json=true","fetch_graph":"https://pith.science/api/pith-number/GQL26B3GQT2BXNU4NFQTXQBYC7/graph.json","fetch_events":"https://pith.science/api/pith-number/GQL26B3GQT2BXNU4NFQTXQBYC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7/action/storage_attestation","attest_author":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7/action/author_attestation","sign_citation":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7/action/citation_signature","submit_replication":"https://pith.science/pith/GQL26B3GQT2BXNU4NFQTXQBYC7/action/replication_record"}},"created_at":"2026-07-05T09:50:06.185470+00:00","updated_at":"2026-07-05T09:50:06.185470+00:00"}