{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7RRY4RV6SZSYNNXPVF7OME6JLA","short_pith_number":"pith:7RRY4RV6","schema_version":"1.0","canonical_sha256":"fc638e46be966586b6efa97ee613c958354bcdc76130b7ca3b67fd1b586cf3a0","source":{"kind":"arxiv","id":"2602.02979","version":2},"attestation_state":"computed","paper":{"title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A Coach generates tasks and rewards a Player for solving them, improving LLM math reasoning without any external data.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingxiang He, Jiarui Yuan, Jinyi Hu, Maosong Sun, Ran Li, Weize Chen, Yinghao Chen, Zeyuan Liu, Zhiyuan Liu, Zixuan Fu","submitted_at":"2026-02-03T01:38:53Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance on massive high-quality human-curated tasks and labels, either through supervised fine-tuning (SFT) or reinforcement learning (RL) on reasoning-specific data. This dependence renders supervision-heavy training paradigms increasingly unsustainable, with signs of diminishing scalability already evident in practice. To overcome this limitation, we introduce CPM\\\"obius (CPMobius), a collaborative Coach-Player paradigm for data-free reinforcement lea"},"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":true},"canonical_record":{"source":{"id":"2602.02979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T01:38:53Z","cross_cats_sorted":[],"title_canon_sha256":"5600fecc22fcedcfa4335d03307271e53eceb287693b0c06d90137e6baf6dc9c","abstract_canon_sha256":"7f9bb2ed9390126133d2ea896d1f09dbc4f8d2226b8cb7e2deae47b864e9d2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:05.536982Z","signature_b64":"96carS1tTYIwwdIq7Iytgbr0paw3/PkoY0Yh5/ZU5KFU4kLTYkja1nLZ4sgBlPXLM4sTDQ4H9nerKhYpmCskBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc638e46be966586b6efa97ee613c958354bcdc76130b7ca3b67fd1b586cf3a0","last_reissued_at":"2026-05-18T02:45:05.536378Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:05.536378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A Coach generates tasks and rewards a Player for solving them, improving LLM math reasoning without any external data.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingxiang He, Jiarui Yuan, Jinyi Hu, Maosong Sun, Ran Li, Weize Chen, Yinghao Chen, Zeyuan Liu, Zhiyuan Liu, Zixuan Fu","submitted_at":"2026-02-03T01:38:53Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance on massive high-quality human-curated tasks and labels, either through supervised fine-tuning (SFT) or reinforcement learning (RL) on reasoning-specific data. This dependence renders supervision-heavy training paradigms increasingly unsustainable, with signs of diminishing scalability already evident in practice. To overcome this limitation, we introduce CPM\\\"obius (CPMobius), a collaborative Coach-Player paradigm for data-free reinforcement lea"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CPMobius achieves substantial improvement without relying on any external training data, outperforming existing unsupervised approaches. For example, on Qwen2.5-Math-7B-Instruct, our method improves accuracy by an overall average of +4.9 and an out-of-distribution average of +5.4.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The cooperative optimization loop between Coach and Player directly enhances the Player's mathematical reasoning ability without external data or labels.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CPMobius uses iterative coach-player reinforcement learning to improve mathematical reasoning in LLMs without external training data, yielding +4.9 average accuracy gains on Qwen2.5-Math-7B-Instruct.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A Coach generates tasks and rewards a Player for solving them, improving LLM math reasoning without any external data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"af00d8d37100c7ad6926b05a420da03b492af55976d775a2a8bc476119afbf0f"},"source":{"id":"2602.02979","kind":"arxiv","version":2},"verdict":{"id":"06ab818a-5768-49d1-a65f-26930b8497bf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:39:31.999161Z","strongest_claim":"CPMobius achieves substantial improvement without relying on any external training data, outperforming existing unsupervised approaches. For example, on Qwen2.5-Math-7B-Instruct, our method improves accuracy by an overall average of +4.9 and an out-of-distribution average of +5.4.","one_line_summary":"CPMobius uses iterative coach-player reinforcement learning to improve mathematical reasoning in LLMs without external training data, yielding +4.9 average accuracy gains on Qwen2.5-Math-7B-Instruct.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The cooperative optimization loop between Coach and Player directly enhances the Player's mathematical reasoning ability without external data or labels.","pith_extraction_headline":"A Coach generates tasks and rewards a Player for solving them, improving LLM math reasoning without any external data."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6fb6c2b6460be6fc0ec4621098faece13313602a8189bbffeb68cb065a57e60a"},"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":"2602.02979","created_at":"2026-05-18T02:45:05.536473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02979v2","created_at":"2026-05-18T02:45:05.536473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02979","created_at":"2026-05-18T02:45:05.536473+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RRY4RV6SZSY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RRY4RV6SZSYNNXP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RRY4RV6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA","json":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA.json","graph_json":"https://pith.science/api/pith-number/7RRY4RV6SZSYNNXPVF7OME6JLA/graph.json","events_json":"https://pith.science/api/pith-number/7RRY4RV6SZSYNNXPVF7OME6JLA/events.json","paper":"https://pith.science/paper/7RRY4RV6"},"agent_actions":{"view_html":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA","download_json":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA.json","view_paper":"https://pith.science/paper/7RRY4RV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02979&json=true","fetch_graph":"https://pith.science/api/pith-number/7RRY4RV6SZSYNNXPVF7OME6JLA/graph.json","fetch_events":"https://pith.science/api/pith-number/7RRY4RV6SZSYNNXPVF7OME6JLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA/action/storage_attestation","attest_author":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA/action/author_attestation","sign_citation":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA/action/citation_signature","submit_replication":"https://pith.science/pith/7RRY4RV6SZSYNNXPVF7OME6JLA/action/replication_record"}},"created_at":"2026-05-18T02:45:05.536473+00:00","updated_at":"2026-05-18T02:45:05.536473+00:00"}