{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VXMMOJTWAOGJLGRUSENHH3IL4J","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":"6ab9df1e98045854807260a69236ea2f7f9f7a50dd757e39f53861a5860c9c5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T06:33:03Z","title_canon_sha256":"96d1fbaaa2af73a90d6e91fc085d302ed29a6f94841f0532b63dd6fd26eb1dfd"},"schema_version":"1.0","source":{"id":"2408.15565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15565","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15565v1","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15565","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"VXMMOJTWAOGJ","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"VXMMOJTWAOGJLGRU","created_at":"2026-07-05T09:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"VXMMOJTW","created_at":"2026-07-05T09:00:13Z"}],"graph_snapshots":[{"event_id":"sha256:da82e16e7554fbd3343cebc49cb74353bbd267b0f47503169fd52e4ca86941fe","target":"graph","created_at":"2026-07-05T09:00:13Z","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/2408.15565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by in-domain data augmentation, equipping LLMs with considerable capabilities for code-aided mathematical reasoning. However, continually training these models on augmented data derived from a few datasets such as GSM8K may impair their generalization abilities and restrict their effectiveness to a narrow range of question types. Conversely, the potential of improving","authors_text":"Baolin Peng, Dian Yu, Dong Yu, Haitao Mi, Linfeng Song, Ye Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T06:33:03Z","title":"SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15565","kind":"arxiv","version":1},"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":"sha256:792cef414081f9f1e9f395bddf076e18c61261caa392714eef9932a01c87916f","target":"record","created_at":"2026-07-05T09:00:13Z","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":"6ab9df1e98045854807260a69236ea2f7f9f7a50dd757e39f53861a5860c9c5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T06:33:03Z","title_canon_sha256":"96d1fbaaa2af73a90d6e91fc085d302ed29a6f94841f0532b63dd6fd26eb1dfd"},"schema_version":"1.0","source":{"id":"2408.15565","kind":"arxiv","version":1}},"canonical_sha256":"add8c72676038c959a34911a73ed0be25a1bffdb1c07db83d113beb310b586db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"add8c72676038c959a34911a73ed0be25a1bffdb1c07db83d113beb310b586db","first_computed_at":"2026-07-05T09:00:13.831116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:13.831116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+EKSIYf3WkOwxx/jIZHdndRjh90KmBmg8Mx02FUoAKb1LLa3EWjoduDsAan7OkO8StscC7uEWikwBeFMn4SMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:13.831573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792cef414081f9f1e9f395bddf076e18c61261caa392714eef9932a01c87916f","sha256:da82e16e7554fbd3343cebc49cb74353bbd267b0f47503169fd52e4ca86941fe"],"state_sha256":"807a998e74b8108527f5321b256511fd935c67212212a19c0957657a1da96411"}