{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7U74AWXTCTGR5JJCZLQZQ55GLD","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":"e7d27e4b8048726d3a7e5403f04d961ce03faccc72225f1d7114945f6224245e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-19T07:31:32Z","title_canon_sha256":"26db37a4e316c63d56dba07e43d1f2ba065b2bfa99887034ce42aa577f3d2f80"},"schema_version":"1.0","source":{"id":"2601.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12784","created_at":"2026-08-04T02:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12784v2","created_at":"2026-08-04T02:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12784","created_at":"2026-08-04T02:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"7U74AWXTCTGR","created_at":"2026-08-04T02:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"7U74AWXTCTGR5JJC","created_at":"2026-08-04T02:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"7U74AWXT","created_at":"2026-08-04T02:09:17Z"}],"graph_snapshots":[{"event_id":"sha256:51d8057393cfc80e2cb237af81ef7386a9b049b53d25aafeb73635862709ff5d","target":"graph","created_at":"2026-08-04T02:09:17Z","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/2601.12784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) post-training has become pivotal for enhancing the capabilities of modern large models. A recent trend is to develop RL systems with a fully disaggregated architecture, which decouples the three RL phases (rollout, reward, and training) onto separate resources and executes them asynchronously. However, two critical data-level concerns arise: (1) asynchronous execution leads to data staleness in trajectories (the data generated by rollout) as the model parameters used in rollout may not be up to date, which impairs RL convergence; and (2) the length variation of traj","authors_text":"Bin Cui, Fangcheng Fu, Haoyang Li, Jie Jiang, Lefeng Wang, Sheng Lin, Xiaodong Ji, Yanfeng Zhao, Yuming Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-19T07:31:32Z","title":"StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12784","kind":"arxiv","version":2},"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:f87492bc64bd8b1e7ea61290f4a35fbe7660cb4363db73332d93b98024c0e1a3","target":"record","created_at":"2026-08-04T02:09:17Z","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":"e7d27e4b8048726d3a7e5403f04d961ce03faccc72225f1d7114945f6224245e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-01-19T07:31:32Z","title_canon_sha256":"26db37a4e316c63d56dba07e43d1f2ba065b2bfa99887034ce42aa577f3d2f80"},"schema_version":"1.0","source":{"id":"2601.12784","kind":"arxiv","version":2}},"canonical_sha256":"fd3fc05af314cd1ea522cae19877a658d61cc0f2cc15a8971e0fccc707130861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd3fc05af314cd1ea522cae19877a658d61cc0f2cc15a8971e0fccc707130861","first_computed_at":"2026-08-04T02:09:17.784545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:09:17.784545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"elii+6X15a0ucHiA2CFftynhM4YSZLkbRhNuZPmB/ogy1J7PA5R/I/bLu8TIz3vrZRuOSuQbYNDJIcVibUqKDw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:09:17.786476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87492bc64bd8b1e7ea61290f4a35fbe7660cb4363db73332d93b98024c0e1a3","sha256:51d8057393cfc80e2cb237af81ef7386a9b049b53d25aafeb73635862709ff5d"],"state_sha256":"e2556d1c901baf26d566d2f59eb35f10c8d66d97124c7ce2b68836740c72ab0d"}