{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6T6IEXTHK6EXJF3APJPOBYMB7C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"753ae64a3115c67c17618298f77b0c46d769b984686935924a4ce9da3da54a3a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T11:38:23Z","title_canon_sha256":"1def2c289f6275407a16605a19ec87e877cf696751042f8c89942165a3333ac1"},"schema_version":"1.0","source":{"id":"2506.07664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07664","created_at":"2026-07-05T11:19:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07664v2","created_at":"2026-07-05T11:19:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07664","created_at":"2026-07-05T11:19:28Z"},{"alias_kind":"pith_short_12","alias_value":"6T6IEXTHK6EX","created_at":"2026-07-05T11:19:28Z"},{"alias_kind":"pith_short_16","alias_value":"6T6IEXTHK6EXJF3A","created_at":"2026-07-05T11:19:28Z"},{"alias_kind":"pith_short_8","alias_value":"6T6IEXTH","created_at":"2026-07-05T11:19:28Z"}],"graph_snapshots":[{"event_id":"sha256:cc66dab2986bc1a3c95c0639c0098de52e1742870e037a38278ee1527b91cf88","target":"graph","created_at":"2026-07-05T11:19:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation quality and problem complexity. To address this, we propose to extract structural information with generated problem-solving code from mathematical reasoning and guide data generation with structured solutions. Applied to MATH and GSM8K, our approach produces 39K problems with labeled intermediate steps and a 6.1K-problem benchmark of higher difficulty. Results o","authors_text":"Chaochao Lu, Lei Xu, Sirui Chen, Yuxuan Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T11:38:23Z","title":"Synthesis by Design: Controlled Data Generation via Structural Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07664","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c98a0e1297a1a3fd7a69af7d4e63f6204c38f7d8b0a4b93d2fdff0ff7294d1a","target":"record","created_at":"2026-07-05T11:19:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"753ae64a3115c67c17618298f77b0c46d769b984686935924a4ce9da3da54a3a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T11:38:23Z","title_canon_sha256":"1def2c289f6275407a16605a19ec87e877cf696751042f8c89942165a3333ac1"},"schema_version":"1.0","source":{"id":"2506.07664","kind":"arxiv","version":2}},"canonical_sha256":"f4fc825e6757897497607a5ee0e181f897a15ce8880e46ff62ef5a72a3282399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4fc825e6757897497607a5ee0e181f897a15ce8880e46ff62ef5a72a3282399","first_computed_at":"2026-07-05T11:19:28.820483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:28.820483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qUIgU/mJiLAr5MnvC5kJ4QVHdfvniVsN04oFGS0dmjCrfUSYj6ovOuH1Gq7Aku2Z0/dvnQMiXBcPwki6qKJXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:28.820951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c98a0e1297a1a3fd7a69af7d4e63f6204c38f7d8b0a4b93d2fdff0ff7294d1a","sha256:cc66dab2986bc1a3c95c0639c0098de52e1742870e037a38278ee1527b91cf88"],"state_sha256":"5b17aed2d14b34a5b56c015146bb59379d5af5f3329d0b5da63dc18696fc3585"}