{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H7YCQHAU7JQZ44XIG6WHEPF6IK","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":"de9f6a9db24ab024bf8f9d105274ed769a7981cf0cfe44840cd4f50d5c028048","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T12:14:57Z","title_canon_sha256":"9fcfa235bcd95ec1a8df3a0f4d7630bb2a29fd4e5f8c6eed43947ef7a7d49b27"},"schema_version":"1.0","source":{"id":"2501.14002","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14002","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14002v3","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14002","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"H7YCQHAU7JQZ","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"H7YCQHAU7JQZ44XI","created_at":"2026-07-05T10:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"H7YCQHAU","created_at":"2026-07-05T10:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:5c07edd0a9d714727ad6c6c0aa900afc68d7347a7663781f2db26798b14c6e02","target":"graph","created_at":"2026-07-05T10:37:43Z","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/2501.14002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning remains a challenging area for large language models (LLMs), prompting the development of math-specific LLMs such as LLEMMA, DeepSeekMath, and Qwen2-Math, among others. These models typically follow a two-stage training paradigm: pre-training with math-related corpora and post-training with problem datasets for supervised fine-tuning (SFT). Despite these efforts, the improvements in mathematical reasoning achieved through continued pre-training (CPT) are often less significant compared to those obtained via SFT. This study addresses this discrepancy by exploring alternat","authors_text":"Mi Tian, Qing Tong, Tianqiao Liu, Weiqi Luo, Zitao Liu, Zui Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T12:14:57Z","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14002","kind":"arxiv","version":3},"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":"sha256:5e8bd469e23f502ed89a0a2b456ae78332f17d2da2ed574ee8cd4fbcb96fc33f","target":"record","created_at":"2026-07-05T10:37:43Z","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":"de9f6a9db24ab024bf8f9d105274ed769a7981cf0cfe44840cd4f50d5c028048","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T12:14:57Z","title_canon_sha256":"9fcfa235bcd95ec1a8df3a0f4d7630bb2a29fd4e5f8c6eed43947ef7a7d49b27"},"schema_version":"1.0","source":{"id":"2501.14002","kind":"arxiv","version":3}},"canonical_sha256":"3ff0281c14fa619e72e837ac723cbe428d3aaecda0c012f56345294aada81de0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ff0281c14fa619e72e837ac723cbe428d3aaecda0c012f56345294aada81de0","first_computed_at":"2026-07-05T10:37:43.450343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:43.450343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"inxNf7/lcb2eLWozz0RhdEwmKgktJuD2erAuSFb7H2PCrRLmtU2qosrFpUecUlnOYYi/McdYpLUb+eUAm6h7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:43.450988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14002","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e8bd469e23f502ed89a0a2b456ae78332f17d2da2ed574ee8cd4fbcb96fc33f","sha256:5c07edd0a9d714727ad6c6c0aa900afc68d7347a7663781f2db26798b14c6e02"],"state_sha256":"34b153454ac82d4e4fb2a9fa7c1492d4ff3d7724c86d50a70f88d76679e106d0"}