{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3XZMI2FZWOJQOYKNFFGFQEYACH","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":"cd9f54ecae566997eb9cb39d76fa69fe6c8400fba578f1071ac1d2673ebe8445","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T09:45:42Z","title_canon_sha256":"280c777ac32bd72e92d9acfb43bc8ea75b183a23537c4e7f0400805bb534c5cb"},"schema_version":"1.0","source":{"id":"2602.09591","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09591","created_at":"2026-06-11T01:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09591v3","created_at":"2026-06-11T01:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09591","created_at":"2026-06-11T01:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"3XZMI2FZWOJQ","created_at":"2026-06-11T01:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"3XZMI2FZWOJQOYKN","created_at":"2026-06-11T01:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"3XZMI2FZ","created_at":"2026-06-11T01:09:30Z"}],"graph_snapshots":[{"event_id":"sha256:f31915b3d841720a95cf51bdac8afa692c9c4a2479c968baf94cdc8c107c9c1b","target":"graph","created_at":"2026-06-11T01:09:30Z","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/2602.09591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain-of-thought outputs and increase computational cost. Although length-control methods have been proposed, the length-accuracy relationship they induce remains unclear. We train policies with several length-control methods on multiple base models in a controlled setup and find that, across both mathematical reasoning and code generation, accuracy is non-monotonic in output length, peaking at an intermediate value. Mode accuracy, however, continues to improve with length even in se","authors_text":"Daisuke Nohara, Rio Yokota, Taishi Nakamura","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T09:45:42Z","title":"On the Optimal Reasoning Length for RL-Trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09591","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":"sha256:6ab66b1b659ede1b471a9a0ca63d2668f28b250ff1589e6beca360821caa1b94","target":"record","created_at":"2026-06-11T01:09:30Z","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":"cd9f54ecae566997eb9cb39d76fa69fe6c8400fba578f1071ac1d2673ebe8445","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T09:45:42Z","title_canon_sha256":"280c777ac32bd72e92d9acfb43bc8ea75b183a23537c4e7f0400805bb534c5cb"},"schema_version":"1.0","source":{"id":"2602.09591","kind":"arxiv","version":3}},"canonical_sha256":"ddf2c468b9b39307614d294c58130011f4ceb07a13721560fd185bf2825dd47e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf2c468b9b39307614d294c58130011f4ceb07a13721560fd185bf2825dd47e","first_computed_at":"2026-06-11T01:09:30.337697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:30.337697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kxwn3NiTMhsO3U/u069GdRUj08/PsdDwDbjUAKq05IpYJdFbejJ/FOfwQsi/mWiayprb2cM0PY+U7LUvD/XLBQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:30.338647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09591","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ab66b1b659ede1b471a9a0ca63d2668f28b250ff1589e6beca360821caa1b94","sha256:f31915b3d841720a95cf51bdac8afa692c9c4a2479c968baf94cdc8c107c9c1b"],"state_sha256":"b6b5526181c2941d5ff871a0efaa42f7dfc2de3e47a307c8fb822f5b1303bdce"}