{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QUJ4RH3B5GSJU2XGIGV3UO37JO","short_pith_number":"pith:QUJ4RH3B","schema_version":"1.0","canonical_sha256":"8513c89f61e9a49a6ae641abba3b7f4b92a49d93c12f41dbf57255a5ee544bd4","source":{"kind":"arxiv","id":"2506.08989","version":1},"attestation_state":"computed","paper":{"title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hengyuan Zhang, Weizhu Chen, Xiao Liang, Yang Wang, Yelong Shen, Yeyun Gong, Ying Nian Wu, Zhong-Zhi Li","submitted_at":"2025-06-10T17:02:00Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.08989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:02:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"470eeade7f005568053f9606b59a101d157b87f939b33f6cb6b1c600c7387ac7","abstract_canon_sha256":"40ebdf4b23742e51aac502484aee55a91f6818496defc8636ba3c2bcddf256f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:16.493528Z","signature_b64":"vnpfIyCQMYHKsZNdTWPMXrUmXUj/1NxxAg91WJoQsNYwHR1IwTaJe/eQPbXJmOt2/WRes+wpMOg0hqc8rq9jAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8513c89f61e9a49a6ae641abba3b7f4b92a49d93c12f41dbf57255a5ee544bd4","last_reissued_at":"2026-07-05T11:19:16.493024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:16.493024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hengyuan Zhang, Weizhu Chen, Xiao Liang, Yang Wang, Yelong Shen, Yeyun Gong, Ying Nian Wu, Zhong-Zhi Li","submitted_at":"2025-06-10T17:02:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08989","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.08989/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.08989","created_at":"2026-07-05T11:19:16.493085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08989v1","created_at":"2026-07-05T11:19:16.493085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08989","created_at":"2026-07-05T11:19:16.493085+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUJ4RH3B5GSJ","created_at":"2026-07-05T11:19:16.493085+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUJ4RH3B5GSJU2XG","created_at":"2026-07-05T11:19:16.493085+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUJ4RH3B","created_at":"2026-07-05T11:19:16.493085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":137,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18910","citing_title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":193,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04809","citing_title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14004","citing_title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09959","citing_title":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07353","citing_title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO","json":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO.json","graph_json":"https://pith.science/api/pith-number/QUJ4RH3B5GSJU2XGIGV3UO37JO/graph.json","events_json":"https://pith.science/api/pith-number/QUJ4RH3B5GSJU2XGIGV3UO37JO/events.json","paper":"https://pith.science/paper/QUJ4RH3B"},"agent_actions":{"view_html":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO","download_json":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO.json","view_paper":"https://pith.science/paper/QUJ4RH3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08989&json=true","fetch_graph":"https://pith.science/api/pith-number/QUJ4RH3B5GSJU2XGIGV3UO37JO/graph.json","fetch_events":"https://pith.science/api/pith-number/QUJ4RH3B5GSJU2XGIGV3UO37JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO/action/storage_attestation","attest_author":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO/action/author_attestation","sign_citation":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO/action/citation_signature","submit_replication":"https://pith.science/pith/QUJ4RH3B5GSJU2XGIGV3UO37JO/action/replication_record"}},"created_at":"2026-07-05T11:19:16.493085+00:00","updated_at":"2026-07-05T11:19:16.493085+00:00"}