{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HH6CAGFUJWSMFAQEREKXANQGHT","short_pith_number":"pith:HH6CAGFU","schema_version":"1.0","canonical_sha256":"39fc2018b44da4c2820489157036063cff2445571d4e02ad42d82246c0fa7549","source":{"kind":"arxiv","id":"2403.02884","version":1},"attestation_state":"computed","paper":{"title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Furu Wei, Xingxing Zhang, Zhengyang Tang","submitted_at":"2024-03-05T11:42:59Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create high-quality mathematical reasoning data using frontier LLMs (e.g., {\\tt GPT-3.5}). Inspired by the cognitive mechanism in human mathematical learning, it first extracts topics and knowledge points from seed math questions and then build a concept graph, which is subsequently used to generate new math questions. MathScale exhibits effective scalability along the siz"},"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":"2403.02884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T11:42:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5392fd0d07037f9d9c813250d26fd1ff9fcaaf746f8c3c7b1a4543b10541e6c0","abstract_canon_sha256":"b836e96909c8b2ea5e9f26101dfcefc378cfbc1e5c6f977cd84e650e582ff90c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:23.838253Z","signature_b64":"XhNqV14eDbWHwIo6xHPbPlDR04WRQ1ookmaSDhPUwPYtZ8YfpD10eDgRrlwdkgSjjLX+pt1HUX2m71ZtUb+VCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39fc2018b44da4c2820489157036063cff2445571d4e02ad42d82246c0fa7549","last_reissued_at":"2026-07-05T07:52:23.837791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:23.837791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Furu Wei, Xingxing Zhang, Zhengyang Tang","submitted_at":"2024-03-05T11:42:59Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create high-quality mathematical reasoning data using frontier LLMs (e.g., {\\tt GPT-3.5}). Inspired by the cognitive mechanism in human mathematical learning, it first extracts topics and knowledge points from seed math questions and then build a concept graph, which is subsequently used to generate new math questions. MathScale exhibits effective scalability along the siz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02884","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/2403.02884/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":"2403.02884","created_at":"2026-07-05T07:52:23.837849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02884v1","created_at":"2026-07-05T07:52:23.837849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02884","created_at":"2026-07-05T07:52:23.837849+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH6CAGFUJWSM","created_at":"2026-07-05T07:52:23.837849+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH6CAGFUJWSMFAQE","created_at":"2026-07-05T07:52:23.837849+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH6CAGFU","created_at":"2026-07-05T07:52:23.837849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04889","citing_title":"GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":229,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18169","citing_title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06799","citing_title":"Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT","json":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT.json","graph_json":"https://pith.science/api/pith-number/HH6CAGFUJWSMFAQEREKXANQGHT/graph.json","events_json":"https://pith.science/api/pith-number/HH6CAGFUJWSMFAQEREKXANQGHT/events.json","paper":"https://pith.science/paper/HH6CAGFU"},"agent_actions":{"view_html":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT","download_json":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT.json","view_paper":"https://pith.science/paper/HH6CAGFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02884&json=true","fetch_graph":"https://pith.science/api/pith-number/HH6CAGFUJWSMFAQEREKXANQGHT/graph.json","fetch_events":"https://pith.science/api/pith-number/HH6CAGFUJWSMFAQEREKXANQGHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT/action/storage_attestation","attest_author":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT/action/author_attestation","sign_citation":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT/action/citation_signature","submit_replication":"https://pith.science/pith/HH6CAGFUJWSMFAQEREKXANQGHT/action/replication_record"}},"created_at":"2026-07-05T07:52:23.837849+00:00","updated_at":"2026-07-05T07:52:23.837849+00:00"}