{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:52VQHBYQHS54XGF3FR5ZHLQAMH","short_pith_number":"pith:52VQHBYQ","schema_version":"1.0","canonical_sha256":"eeab0387103cbbcb98bb2c7b93ae0061f63066d589effefd83a1010d412b7372","source":{"kind":"arxiv","id":"2508.18824","version":1},"attestation_state":"computed","paper":{"title":"Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"BinBin Hu, Changxin Tian, Jun Zhou, Kunlong Chen, Sirui Chen, Zhiqiang Zhang, Ziqi Liu","submitted_at":"2025-08-26T09:01:50Z","abstract_excerpt":"Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose a novel program-assisted synthesis framework that systematically generates a high-quality mathematical corpus with guaranteed diversity, complexity, and correctness. This framework integrates mathematical knowledge systems and domain-specific tools to create executable programs. These programs are then translated into natural language problem-solution pairs "},"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":"2508.18824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T09:01:50Z","cross_cats_sorted":[],"title_canon_sha256":"f3a6b39b2ea879cda6e558198e7fb72208a4e9a68466fc0f67d87e3635180eb3","abstract_canon_sha256":"9e9a7d1f4b9e19cb55f7f69400a5269c1df0b9879b468481e689ecb85d9ee386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:31.779686Z","signature_b64":"0OEs5oUhwUTOXV0ZFW73GK7etID/i0HjS74C2mwCAEToAlWfBTV0N3jhO19NkOPKcQ/mmySR0a95XSd4TVUXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeab0387103cbbcb98bb2c7b93ae0061f63066d589effefd83a1010d412b7372","last_reissued_at":"2026-07-05T11:59:31.779193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:31.779193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"BinBin Hu, Changxin Tian, Jun Zhou, Kunlong Chen, Sirui Chen, Zhiqiang Zhang, Ziqi Liu","submitted_at":"2025-08-26T09:01:50Z","abstract_excerpt":"Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose a novel program-assisted synthesis framework that systematically generates a high-quality mathematical corpus with guaranteed diversity, complexity, and correctness. This framework integrates mathematical knowledge systems and domain-specific tools to create executable programs. These programs are then translated into natural language problem-solution pairs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18824","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/2508.18824/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":"2508.18824","created_at":"2026-07-05T11:59:31.779258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18824v1","created_at":"2026-07-05T11:59:31.779258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18824","created_at":"2026-07-05T11:59:31.779258+00:00"},{"alias_kind":"pith_short_12","alias_value":"52VQHBYQHS54","created_at":"2026-07-05T11:59:31.779258+00:00"},{"alias_kind":"pith_short_16","alias_value":"52VQHBYQHS54XGF3","created_at":"2026-07-05T11:59:31.779258+00:00"},{"alias_kind":"pith_short_8","alias_value":"52VQHBYQ","created_at":"2026-07-05T11:59:31.779258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH","json":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH.json","graph_json":"https://pith.science/api/pith-number/52VQHBYQHS54XGF3FR5ZHLQAMH/graph.json","events_json":"https://pith.science/api/pith-number/52VQHBYQHS54XGF3FR5ZHLQAMH/events.json","paper":"https://pith.science/paper/52VQHBYQ"},"agent_actions":{"view_html":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH","download_json":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH.json","view_paper":"https://pith.science/paper/52VQHBYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18824&json=true","fetch_graph":"https://pith.science/api/pith-number/52VQHBYQHS54XGF3FR5ZHLQAMH/graph.json","fetch_events":"https://pith.science/api/pith-number/52VQHBYQHS54XGF3FR5ZHLQAMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH/action/storage_attestation","attest_author":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH/action/author_attestation","sign_citation":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH/action/citation_signature","submit_replication":"https://pith.science/pith/52VQHBYQHS54XGF3FR5ZHLQAMH/action/replication_record"}},"created_at":"2026-07-05T11:59:31.779258+00:00","updated_at":"2026-07-05T11:59:31.779258+00:00"}