{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5CA5JGELS3BSRKMYBSFLAO6LEK","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":"e66dafd894277e651b922c8c5ed0626e6f75cdb614f7cef784590121797ea3d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T09:54:42Z","title_canon_sha256":"bb2d98a7b551ed4338d36f72845741f67d22fa11e9aa3f591aa0368946c476b4"},"schema_version":"1.0","source":{"id":"2505.14147","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14147","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14147v3","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14147","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"5CA5JGELS3BS","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"5CA5JGELS3BSRKMY","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"5CA5JGEL","created_at":"2026-07-05T11:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:7ccdf50003c9ca8d1893c92835c70066b0ff66ed2bb2b4b6a769714d904598e9","target":"graph","created_at":"2026-07-05T11:09:14Z","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/2505.14147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large reasoning models (LRMs) with reinforcement learning in STEM domains is hindered by the scarcity of high-quality, diverse, and verifiable problem sets. Existing synthesis methods, such as Chain-of-Thought prompting, often generate oversimplified or uncheckable data, limiting model advancement on complex tasks. To address these challenges, we introduce SHARP, a unified approach to Synthesizing High-quality Aligned Reasoning Problems for LRMs reinforcement learning with verifiable rewards (RLVR). SHARP encompasses a strategic set of self-alignment principles -- targeting graduate a","authors_text":"Cai Chen, Chengfu Tang, Deng Zhao, Dingnan Jin, Jun Zhou, Lei Shi, Qing Cui, Qing Wang, Wang Ren, Xiong Jun Wu, Xudong Han, Zhenduo Zhang, Zhiqiang Zhang, Zujie Wen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T09:54:42Z","title":"SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14147","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":"sha256:5d0adc85575dc2eae95c981ca76ec90a4db5ba2e953483cab8857b37eda9d860","target":"record","created_at":"2026-07-05T11:09:14Z","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":"e66dafd894277e651b922c8c5ed0626e6f75cdb614f7cef784590121797ea3d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T09:54:42Z","title_canon_sha256":"bb2d98a7b551ed4338d36f72845741f67d22fa11e9aa3f591aa0368946c476b4"},"schema_version":"1.0","source":{"id":"2505.14147","kind":"arxiv","version":3}},"canonical_sha256":"e881d4988b96c328a9980c8ab03bcb2284af7e38cf3068e4bc4be721cefc14f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e881d4988b96c328a9980c8ab03bcb2284af7e38cf3068e4bc4be721cefc14f4","first_computed_at":"2026-07-05T11:09:14.366262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:14.366262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJWXLCsZyZBafV5AsiI8OsOnRZMYud5beswZXMYSmOoZfeVwYS18BlYHg9XQY5wMcEvD280wJHUxzfis/GQ/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:14.366741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14147","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d0adc85575dc2eae95c981ca76ec90a4db5ba2e953483cab8857b37eda9d860","sha256:7ccdf50003c9ca8d1893c92835c70066b0ff66ed2bb2b4b6a769714d904598e9"],"state_sha256":"2f9238bca63c8dae4c841b622dd9bc3e87aa80abfd1bdbcc040acc0321bd27f8"}