{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XD6V265GXKXGQNOWKTUN2LFYPX","short_pith_number":"pith:XD6V265G","schema_version":"1.0","canonical_sha256":"b8fd5d7ba6baae6835d654e8dd2cb87dd46216abdb68e38c1a6556e77cb5e3de","source":{"kind":"arxiv","id":"2311.07172","version":2},"attestation_state":"computed","paper":{"title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Nancy F. Chen, Ratish Puduppully, Vernon Toh Yan Han","submitted_at":"2023-11-13T09:06:58Z","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"},"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":"2311.07172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T09:06:58Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"ea082268e3ab94b9551ee8eaf8371c6191a11d3a173b63e0c13b5052c12097d2","abstract_canon_sha256":"c8ceb148408532e2087e76ed588e24eb4a289b1decf20043f4f2ebe3e5dcb452"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:19.387341Z","signature_b64":"t/5/mjZpXIrPVfyDlKB+yxo2W3R5F1JUrfXEIZxKyNt1yNmmg+1inOKjzQR2FrjP0LyxUShL1EubYrAAj5UYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8fd5d7ba6baae6835d654e8dd2cb87dd46216abdb68e38c1a6556e77cb5e3de","last_reissued_at":"2026-07-05T08:46:19.386967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:19.386967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Nancy F. Chen, Ratish Puduppully, Vernon Toh Yan Han","submitted_at":"2023-11-13T09:06:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07172","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/2311.07172/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":"2311.07172","created_at":"2026-07-05T08:46:19.387028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07172v2","created_at":"2026-07-05T08:46:19.387028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07172","created_at":"2026-07-05T08:46:19.387028+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD6V265GXKXG","created_at":"2026-07-05T08:46:19.387028+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD6V265GXKXGQNOW","created_at":"2026-07-05T08:46:19.387028+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD6V265G","created_at":"2026-07-05T08:46:19.387028+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/XD6V265GXKXGQNOWKTUN2LFYPX","json":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX.json","graph_json":"https://pith.science/api/pith-number/XD6V265GXKXGQNOWKTUN2LFYPX/graph.json","events_json":"https://pith.science/api/pith-number/XD6V265GXKXGQNOWKTUN2LFYPX/events.json","paper":"https://pith.science/paper/XD6V265G"},"agent_actions":{"view_html":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX","download_json":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX.json","view_paper":"https://pith.science/paper/XD6V265G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07172&json=true","fetch_graph":"https://pith.science/api/pith-number/XD6V265GXKXGQNOWKTUN2LFYPX/graph.json","fetch_events":"https://pith.science/api/pith-number/XD6V265GXKXGQNOWKTUN2LFYPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX/action/storage_attestation","attest_author":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX/action/author_attestation","sign_citation":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX/action/citation_signature","submit_replication":"https://pith.science/pith/XD6V265GXKXGQNOWKTUN2LFYPX/action/replication_record"}},"created_at":"2026-07-05T08:46:19.387028+00:00","updated_at":"2026-07-05T08:46:19.387028+00:00"}