{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A6DFUSY3HLG3BGNZ6QE4MI3NK3","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":"09f3f85fc938e338d8c42789e3b92e032004073cfa983210ed7e91ca200330f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T09:40:47Z","title_canon_sha256":"a4a13ea8cc97dd3bbd230299a21e01e9543c40a24c8d6dd2e48cf0604beba52f"},"schema_version":"1.0","source":{"id":"2506.04821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04821","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04821v1","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04821","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"A6DFUSY3HLG3","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"A6DFUSY3HLG3BGNZ","created_at":"2026-07-05T11:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"A6DFUSY3","created_at":"2026-07-05T11:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:7c0bc6829c56e5045d67088b8f915a0c7a2d1dcf6190ec59d42b7d3616c79045","target":"graph","created_at":"2026-07-05T11:16:37Z","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/2506.04821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics rather than fostering general-purpose thinking strategies. In this work, we propose a \"play to learn\" framework that fine-tunes LLMs through reinforcement learning on a suite of seven custom logic puzzles, each designed to cultivate distinct reasoning skills such as constraint propagation, spatial consistency, and symbolic deduction. Using a reinforcement lear","authors_text":"Bin Cui, Chengyu Shen, Hao Liang, Hejun Dong, Jingwen Deng, Qijie You, Runming He, Wentao Zhang, Zhen Hao Wong, Zirong Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T09:40:47Z","title":"LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04821","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:a7fef24d8574cf8c3d10974b1653180d704c2f34c70acb06d6711da48b7a214c","target":"record","created_at":"2026-07-05T11:16:37Z","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":"09f3f85fc938e338d8c42789e3b92e032004073cfa983210ed7e91ca200330f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T09:40:47Z","title_canon_sha256":"a4a13ea8cc97dd3bbd230299a21e01e9543c40a24c8d6dd2e48cf0604beba52f"},"schema_version":"1.0","source":{"id":"2506.04821","kind":"arxiv","version":1}},"canonical_sha256":"07865a4b1b3acdb099b9f409c6236d56ed6c48695edfebc04f96dfcf19143174","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07865a4b1b3acdb099b9f409c6236d56ed6c48695edfebc04f96dfcf19143174","first_computed_at":"2026-07-05T11:16:37.253813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:37.253813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nZbM6z1v46gfA0Lxel+MLnhJXgJUdred9DPZwi7Du7RPPwG9MxzwqG5CnMq+yyuFLpnOPOgpmbDIh7qPqer1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:37.254374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7fef24d8574cf8c3d10974b1653180d704c2f34c70acb06d6711da48b7a214c","sha256:7c0bc6829c56e5045d67088b8f915a0c7a2d1dcf6190ec59d42b7d3616c79045"],"state_sha256":"3b67e46a68e2f0c5a0e5d054f0bc0a823e4800f935e78bf0a25d283618643c72"}