{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E3KT6VUYT7NSJBNS6DQRRWNLS6","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":"2687ae0eae80439f4d93d4f3f852847612a5ff9050f5597ee2d15621e706193a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T13:10:30Z","title_canon_sha256":"816220773ba06935060d77d0fe260e9723e5572010a2fcfe752e4f202a6172ac"},"schema_version":"1.0","source":{"id":"2606.17890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17890","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17890v1","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17890","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"E3KT6VUYT7NS","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"E3KT6VUYT7NSJBNS","created_at":"2026-06-19T16:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"E3KT6VUY","created_at":"2026-06-19T16:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:c95d24329df15788eeb964a6c0f4a5d1f48d78d80524871633143fa1051ee8bd","target":"graph","created_at":"2026-06-19T16:10:42Z","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/2606.17890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We refer to this behavior as overthinking. We study this phenomenon from the perspective of GRPO-style reinforcement learning (RL) post-training, framing it as a training-time credit-assignment problem rather than merely a decoding-time stopping problem. In rollouts sampled at the onset of GRPO training, we observe that successful trajectories can exhibit a slightly higher degree of overthinking than unsuccessful traje","authors_text":"Huawei Shen, Jiahao Liu, Jingang Wang, Jingcheng Deng, Liang Pang, Shasha Guo, Shicheng Xu, Wenjie Shi, Xueqi Cheng, Zenghao Duan, Zihao Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T13:10:30Z","title":"Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17890","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:b3ccac6bf303034be362fb4f08e95729511f753f0bdf8df04492c1be4f654c98","target":"record","created_at":"2026-06-19T16:10:42Z","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":"2687ae0eae80439f4d93d4f3f852847612a5ff9050f5597ee2d15621e706193a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T13:10:30Z","title_canon_sha256":"816220773ba06935060d77d0fe260e9723e5572010a2fcfe752e4f202a6172ac"},"schema_version":"1.0","source":{"id":"2606.17890","kind":"arxiv","version":1}},"canonical_sha256":"26d53f56989fdb2485b2f0e118d9ab97b70e7588021140eb7cf27e02d223036b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26d53f56989fdb2485b2f0e118d9ab97b70e7588021140eb7cf27e02d223036b","first_computed_at":"2026-06-19T16:10:42.782235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:42.782235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vqgybaxC/u1sEfRtyqgsKgM87hU4HCpbLshfs/Rp0Q5Hua2eKkVi3dsHStoN3j+ErJqU7QFRh4VkKSpPEyZwBw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:42.782662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ccac6bf303034be362fb4f08e95729511f753f0bdf8df04492c1be4f654c98","sha256:c95d24329df15788eeb964a6c0f4a5d1f48d78d80524871633143fa1051ee8bd"],"state_sha256":"7b07270390c797773c6d69a77e223d31a057f5dcc10ad5c51ce4d198b91cf713"}