{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QUJ4RH3B5GSJU2XGIGV3UO37JO","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":"40ebdf4b23742e51aac502484aee55a91f6818496defc8636ba3c2bcddf256f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:02:00Z","title_canon_sha256":"470eeade7f005568053f9606b59a101d157b87f939b33f6cb6b1c600c7387ac7"},"schema_version":"1.0","source":{"id":"2506.08989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08989","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08989v1","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08989","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"QUJ4RH3B5GSJ","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"QUJ4RH3B5GSJU2XG","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"QUJ4RH3B","created_at":"2026-07-05T11:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:cc641e0168a2015d276bb54312d5da21711f2e19dc7f31f751e46a51420dce50","target":"graph","created_at":"2026-07-05T11:19:16Z","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/2506.08989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a high-quality problem set with precise and verifiable answers. However, the scarcity of well-crafted human-labeled math problems and limited-verification answers in existing distillation-oriented synthetic datasets limit their effectiveness in RL. Additionally, most problem synthesis strategies indiscriminately expand the problem set without considering the model's ca","authors_text":"Hengyuan Zhang, Weizhu Chen, Xiao Liang, Yang Wang, Yelong Shen, Yeyun Gong, Ying Nian Wu, Zhong-Zhi Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:02:00Z","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08989","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:f2bb9accc1833ac577c8ee6671681f17c069bcb070ad6d739af0d2b21286dfa3","target":"record","created_at":"2026-07-05T11:19:16Z","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":"40ebdf4b23742e51aac502484aee55a91f6818496defc8636ba3c2bcddf256f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:02:00Z","title_canon_sha256":"470eeade7f005568053f9606b59a101d157b87f939b33f6cb6b1c600c7387ac7"},"schema_version":"1.0","source":{"id":"2506.08989","kind":"arxiv","version":1}},"canonical_sha256":"8513c89f61e9a49a6ae641abba3b7f4b92a49d93c12f41dbf57255a5ee544bd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8513c89f61e9a49a6ae641abba3b7f4b92a49d93c12f41dbf57255a5ee544bd4","first_computed_at":"2026-07-05T11:19:16.493024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:16.493024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vnpfIyCQMYHKsZNdTWPMXrUmXUj/1NxxAg91WJoQsNYwHR1IwTaJe/eQPbXJmOt2/WRes+wpMOg0hqc8rq9jAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:16.493528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2bb9accc1833ac577c8ee6671681f17c069bcb070ad6d739af0d2b21286dfa3","sha256:cc641e0168a2015d276bb54312d5da21711f2e19dc7f31f751e46a51420dce50"],"state_sha256":"2fd0ae1536825c26817573d0b1fc262f2a6454568c1f62272aa6cafb44ca74a1"}