{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SW2PVQOYYPLFBPAKMY75FNBCE3","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":"9d9444e9470d8b8c1ddcfec46bd535f120908772df5290aff4e7de9d7fa9e0ca","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T01:42:46Z","title_canon_sha256":"48530c9c413889ec8b04ddcd7fcefcd050b0d06467b469db3c68415a1f4c891e"},"schema_version":"1.0","source":{"id":"2508.18588","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18588","created_at":"2026-07-05T11:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18588v1","created_at":"2026-07-05T11:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18588","created_at":"2026-07-05T11:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"SW2PVQOYYPLF","created_at":"2026-07-05T11:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"SW2PVQOYYPLFBPAK","created_at":"2026-07-05T11:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"SW2PVQOY","created_at":"2026-07-05T11:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:43c32b2f1dc6a949338edbdeda961b8fc29a578c4256633c55497e6e5d53b0fa","target":"graph","created_at":"2026-07-05T11:59:27Z","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/2508.18588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancement of large language models (LLMs), reinforcement learning (RL) has emerged as a pivotal methodology for enhancing the reasoning capabilities of LLMs. Unlike traditional pre-training approaches, RL encompasses multiple stages: rollout, reward, and training, which necessitates collaboration among various worker types. However, current RL systems continue to grapple with substantial GPU underutilization, due to two primary factors: (1) The rollout stage dominates the overall RL process due to test-time scaling; (2) Imbalances in rollout lengths (within the same batch) res","authors_text":"Dong Du, Erhu Feng, Haibo Chen, Jingkai He, Qian Liu, Tao Liu, Tianjian Li, Yubin Xia","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T01:42:46Z","title":"History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18588","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":"sha256:27882d107324ca4efaf433028ce89a7d3103864c8037e9e6963bb8de6a9369e9","target":"record","created_at":"2026-07-05T11:59:27Z","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":"9d9444e9470d8b8c1ddcfec46bd535f120908772df5290aff4e7de9d7fa9e0ca","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-26T01:42:46Z","title_canon_sha256":"48530c9c413889ec8b04ddcd7fcefcd050b0d06467b469db3c68415a1f4c891e"},"schema_version":"1.0","source":{"id":"2508.18588","kind":"arxiv","version":1}},"canonical_sha256":"95b4fac1d8c3d650bc0a663fd2b42226e01d52e9cd3fcf04af2a49aee4368b21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95b4fac1d8c3d650bc0a663fd2b42226e01d52e9cd3fcf04af2a49aee4368b21","first_computed_at":"2026-07-05T11:59:27.251636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:27.251636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y8oc/PR0/RpB/ApG1AMQ8MFOnKUzHT39fcvH1qzOPpmwlyCqkVp/0v6kVT4MWO1xkvYtGnshh8+6+hKrB5LXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:27.252054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18588","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27882d107324ca4efaf433028ce89a7d3103864c8037e9e6963bb8de6a9369e9","sha256:43c32b2f1dc6a949338edbdeda961b8fc29a578c4256633c55497e6e5d53b0fa"],"state_sha256":"53bb7923fe41ee004cbbcd557eaa051b3cc2ef98236f35ebba1b47516cf316fa"}