{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XD6V265GXKXGQNOWKTUN2LFYPX","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":"c8ceb148408532e2087e76ed588e24eb4a289b1decf20043f4f2ebe3e5dcb452","cross_cats_sorted":["cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T09:06:58Z","title_canon_sha256":"ea082268e3ab94b9551ee8eaf8371c6191a11d3a173b63e0c13b5052c12097d2"},"schema_version":"1.0","source":{"id":"2311.07172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07172","created_at":"2026-07-05T08:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07172v2","created_at":"2026-07-05T08:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07172","created_at":"2026-07-05T08:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"XD6V265GXKXG","created_at":"2026-07-05T08:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"XD6V265GXKXGQNOW","created_at":"2026-07-05T08:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"XD6V265G","created_at":"2026-07-05T08:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:35531f7ba9342e16c4589434616da0c73bb9d0523de7215053b81ece93915937","target":"graph","created_at":"2026-07-05T08:46:19Z","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/2311.07172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), combined with program-based solving techniques, are increasingly demonstrating proficiency in mathematical reasoning. For example, closed-source models such as OpenAI GPT-4 and Claude show excellent results in solving math word problems. However, progress in math word problem-solving for open-source LLMs is limited, and the challenges these models face are not well-studied. In this paper, we study the performance of strong open-source LLMs, including Llama 2 (7B), Code Llama (7B), and Mistral (7B) on math word problems using program-based solving techniques. Speci","authors_text":"Nancy F. Chen, Ratish Puduppully, Vernon Toh Yan Han","cross_cats":["cs.PL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T09:06:58Z","title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07172","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":"sha256:1f6d4b025fa6f5f42eced1d274100e423b772335170c15de0ae61d6040ae6372","target":"record","created_at":"2026-07-05T08:46:19Z","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":"c8ceb148408532e2087e76ed588e24eb4a289b1decf20043f4f2ebe3e5dcb452","cross_cats_sorted":["cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T09:06:58Z","title_canon_sha256":"ea082268e3ab94b9551ee8eaf8371c6191a11d3a173b63e0c13b5052c12097d2"},"schema_version":"1.0","source":{"id":"2311.07172","kind":"arxiv","version":2}},"canonical_sha256":"b8fd5d7ba6baae6835d654e8dd2cb87dd46216abdb68e38c1a6556e77cb5e3de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8fd5d7ba6baae6835d654e8dd2cb87dd46216abdb68e38c1a6556e77cb5e3de","first_computed_at":"2026-07-05T08:46:19.386967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:19.386967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t/5/mjZpXIrPVfyDlKB+yxo2W3R5F1JUrfXEIZxKyNt1yNmmg+1inOKjzQR2FrjP0LyxUShL1EubYrAAj5UYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:19.387341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f6d4b025fa6f5f42eced1d274100e423b772335170c15de0ae61d6040ae6372","sha256:35531f7ba9342e16c4589434616da0c73bb9d0523de7215053b81ece93915937"],"state_sha256":"2c249433532b90d8f6160fd8fb04c64ed7c7a8d5e0946647e49cefe875624c1f"}