{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GQL26B3GQT2BXNU4NFQTXQBYC7","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":"bf65fce0a0ea38ea01b8b27b1098adb9822050a60cad82a2dd0e8b4c9b7abc10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T14:24:55Z","title_canon_sha256":"4b52cc11000bdea74e8aacac7dc0bcfce8b128c3f2e0ec13e0d0ea483be594cc"},"schema_version":"1.0","source":{"id":"2410.12608","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12608","created_at":"2026-07-05T09:50:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12608v2","created_at":"2026-07-05T09:50:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12608","created_at":"2026-07-05T09:50:06Z"},{"alias_kind":"pith_short_12","alias_value":"GQL26B3GQT2B","created_at":"2026-07-05T09:50:06Z"},{"alias_kind":"pith_short_16","alias_value":"GQL26B3GQT2BXNU4","created_at":"2026-07-05T09:50:06Z"},{"alias_kind":"pith_short_8","alias_value":"GQL26B3G","created_at":"2026-07-05T09:50:06Z"}],"graph_snapshots":[{"event_id":"sha256:0511b8c8878dc25d6e8ed2b80bb50cee1196cf0dd82a7dd122b2055b0be128ef","target":"graph","created_at":"2026-07-05T09:50:06Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.12608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deepanway Ghosal, Soujanya Poria, Vernon Y.H. Toh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T14:24:55Z","title":"Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12608","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:158070c004046a70973e4adad15a4e752b88471005a6afe2733d0a28d2be1b3a","target":"record","created_at":"2026-07-05T09:50:06Z","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":"bf65fce0a0ea38ea01b8b27b1098adb9822050a60cad82a2dd0e8b4c9b7abc10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T14:24:55Z","title_canon_sha256":"4b52cc11000bdea74e8aacac7dc0bcfce8b128c3f2e0ec13e0d0ea483be594cc"},"schema_version":"1.0","source":{"id":"2410.12608","kind":"arxiv","version":2}},"canonical_sha256":"3417af076684f41bb69c69613bc03817d9313432c7ab7ebfaa7994e632e4b76e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3417af076684f41bb69c69613bc03817d9313432c7ab7ebfaa7994e632e4b76e","first_computed_at":"2026-07-05T09:50:06.185408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:06.185408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8UJIeM2hwveQIRUZw1IZR3uom/DuUGPg2looFdmx3OBGzXZdRF0deI9LRHydKcqzBYl/l5yvSNZJk/NuIR7EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:06.185931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12608","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:158070c004046a70973e4adad15a4e752b88471005a6afe2733d0a28d2be1b3a","sha256:0511b8c8878dc25d6e8ed2b80bb50cee1196cf0dd82a7dd122b2055b0be128ef"],"state_sha256":"dfe801ad88fcf566b30e7147cafff3c4e38519a55c321d2dd0a7a38af4c2be68"}