{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N4ORKBJTNLBXZ3SORL2MTPLZB6","short_pith_number":"pith:N4ORKBJT","schema_version":"1.0","canonical_sha256":"6f1d1505336ac37cee4e8af4c9bd790fb142ff83726fe820bff52150ead52179","source":{"kind":"arxiv","id":"2403.02333","version":3},"attestation_state":"computed","paper":{"title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nan Duan, Weizhu Chen, Xiao Liu, Yelong Shen, Yeyun Gong, Yiming Huang, Zhibin Gou","submitted_at":"2024-03-04T18:58:30Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challenge, we propose Key-Point-Driven Data Synthesis (KPDDS), a novel data synthesis framework that synthesizes question-answer pairs by leveraging key points and exemplar practices from authentic data sources. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. As a result, we present KPMath, an extensive synthetic dataset tailo"},"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":"2403.02333","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T18:58:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccf5a77d7cc6fc077c1954b1ba43aaa1f802cf344b546cff91dbacd544647e8b","abstract_canon_sha256":"cda463f2274c1c3d1b2a0193f93a88d57f1d9260c948e237d7c236058e99bdf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:47.765212Z","signature_b64":"Q4IBs9pQvDJMQYOkxi5CIyWlEb6IckxI2qMBlMeMLn1+Nu23GIXx6n7VkLKB/0mQbOI+hJqPK1T2+9+4JSq9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1d1505336ac37cee4e8af4c9bd790fb142ff83726fe820bff52150ead52179","last_reissued_at":"2026-07-05T08:16:47.764750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:47.764750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nan Duan, Weizhu Chen, Xiao Liu, Yelong Shen, Yeyun Gong, Yiming Huang, Zhibin Gou","submitted_at":"2024-03-04T18:58:30Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challenge, we propose Key-Point-Driven Data Synthesis (KPDDS), a novel data synthesis framework that synthesizes question-answer pairs by leveraging key points and exemplar practices from authentic data sources. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. As a result, we present KPMath, an extensive synthetic dataset tailo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02333","kind":"arxiv","version":3},"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/2403.02333/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":"2403.02333","created_at":"2026-07-05T08:16:47.764808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02333v3","created_at":"2026-07-05T08:16:47.764808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02333","created_at":"2026-07-05T08:16:47.764808+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4ORKBJTNLBX","created_at":"2026-07-05T08:16:47.764808+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4ORKBJTNLBXZ3SO","created_at":"2026-07-05T08:16:47.764808+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4ORKBJT","created_at":"2026-07-05T08:16:47.764808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2406.20094","citing_title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":300,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6","json":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6.json","graph_json":"https://pith.science/api/pith-number/N4ORKBJTNLBXZ3SORL2MTPLZB6/graph.json","events_json":"https://pith.science/api/pith-number/N4ORKBJTNLBXZ3SORL2MTPLZB6/events.json","paper":"https://pith.science/paper/N4ORKBJT"},"agent_actions":{"view_html":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6","download_json":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6.json","view_paper":"https://pith.science/paper/N4ORKBJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02333&json=true","fetch_graph":"https://pith.science/api/pith-number/N4ORKBJTNLBXZ3SORL2MTPLZB6/graph.json","fetch_events":"https://pith.science/api/pith-number/N4ORKBJTNLBXZ3SORL2MTPLZB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6/action/storage_attestation","attest_author":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6/action/author_attestation","sign_citation":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6/action/citation_signature","submit_replication":"https://pith.science/pith/N4ORKBJTNLBXZ3SORL2MTPLZB6/action/replication_record"}},"created_at":"2026-07-05T08:16:47.764808+00:00","updated_at":"2026-07-05T08:16:47.764808+00:00"}