{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HPFQJ35SWVBIJHZHM6STHUI75M","short_pith_number":"pith:HPFQJ35S","schema_version":"1.0","canonical_sha256":"3bcb04efb2b542849f2767a533d11feb3038b1df236df2cd80b71711bcef376c","source":{"kind":"arxiv","id":"2408.07089","version":1},"attestation_state":"computed","paper":{"title":"InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo-Wen Zhang, Guang Liu, Lin Li, Yan Yan","submitted_at":"2024-08-09T08:18:20Z","abstract_excerpt":"Recent advancements in Chain-of-Thoughts (CoT) and Program-of-Thoughts (PoT) methods have greatly enhanced language models' mathematical reasoning capabilities, facilitating their integration into instruction tuning datasets with LLMs. However, existing methods for large-scale dataset creation require substantial seed data and high computational costs for data synthesis, posing significant challenges for scalability. We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. The construction pipeline emphasizes decoupling numbers from mathematical"},"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":"2408.07089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T08:18:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff51291e7b84741e0d42b99b6f125b987be32fedf48e1f42c13981e986213c60","abstract_canon_sha256":"942ea1cba060680cdd1a4f5ce5bb75e3bb0ee4b2b75a83c913aaed49c90d0df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:10.608517Z","signature_b64":"G+kVQQ2cpfhxMlE/pDrrMYU7+DdLJVDaCLLpxkPVwCY6LlkhIbQSHDyudy5KL/87V1K6xgjlce5T8s9vZKhaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bcb04efb2b542849f2767a533d11feb3038b1df236df2cd80b71711bcef376c","last_reissued_at":"2026-07-05T08:55:10.608139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:10.608139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo-Wen Zhang, Guang Liu, Lin Li, Yan Yan","submitted_at":"2024-08-09T08:18:20Z","abstract_excerpt":"Recent advancements in Chain-of-Thoughts (CoT) and Program-of-Thoughts (PoT) methods have greatly enhanced language models' mathematical reasoning capabilities, facilitating their integration into instruction tuning datasets with LLMs. However, existing methods for large-scale dataset creation require substantial seed data and high computational costs for data synthesis, posing significant challenges for scalability. We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. The construction pipeline emphasizes decoupling numbers from mathematical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07089","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/2408.07089/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":"2408.07089","created_at":"2026-07-05T08:55:10.608188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07089v1","created_at":"2026-07-05T08:55:10.608188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07089","created_at":"2026-07-05T08:55:10.608188+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPFQJ35SWVBI","created_at":"2026-07-05T08:55:10.608188+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPFQJ35SWVBIJHZH","created_at":"2026-07-05T08:55:10.608188+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPFQJ35S","created_at":"2026-07-05T08:55:10.608188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05901","citing_title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M","json":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M.json","graph_json":"https://pith.science/api/pith-number/HPFQJ35SWVBIJHZHM6STHUI75M/graph.json","events_json":"https://pith.science/api/pith-number/HPFQJ35SWVBIJHZHM6STHUI75M/events.json","paper":"https://pith.science/paper/HPFQJ35S"},"agent_actions":{"view_html":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M","download_json":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M.json","view_paper":"https://pith.science/paper/HPFQJ35S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07089&json=true","fetch_graph":"https://pith.science/api/pith-number/HPFQJ35SWVBIJHZHM6STHUI75M/graph.json","fetch_events":"https://pith.science/api/pith-number/HPFQJ35SWVBIJHZHM6STHUI75M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M/action/storage_attestation","attest_author":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M/action/author_attestation","sign_citation":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M/action/citation_signature","submit_replication":"https://pith.science/pith/HPFQJ35SWVBIJHZHM6STHUI75M/action/replication_record"}},"created_at":"2026-07-05T08:55:10.608188+00:00","updated_at":"2026-07-05T08:55:10.608188+00:00"}