{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A7VYGNGVTJ4XOOZFSKE56Q2N35","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":"8a9762f9ef8ea3e4d08f304d5293d827ba9cf0d7284dc6eaceffc6d72eb94744","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T05:27:50Z","title_canon_sha256":"5596c7a82da4d28eda75ca80f44114b88bcdd4b12624a37f9dc8546e4a3cb3ee"},"schema_version":"1.0","source":{"id":"2607.18722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18722","created_at":"2026-07-22T01:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18722v1","created_at":"2026-07-22T01:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18722","created_at":"2026-07-22T01:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"A7VYGNGVTJ4X","created_at":"2026-07-22T01:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"A7VYGNGVTJ4XOOZF","created_at":"2026-07-22T01:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"A7VYGNGV","created_at":"2026-07-22T01:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:66fdb2841bf8b38bf28afc5aadab9aabb173d676ac878a667aea0beef9b0d877","target":"graph","created_at":"2026-07-22T01:23:08Z","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/2607.18722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing. From a trust-region perspective, this mismatch is critical: training-inference divergence governs approximation error in finite-horizon bounds, whereas PPO clipping only gates sampled outward updates, acting as a sampled surrogate rather than a full-policy constraint. As a result, high-staleness updates remain weakly controlled in the asynchronous regime where stale rollouts ","authors_text":"Haitao Mi, Junyao Yang, Kishan Panaganti, Leowei Liang, Ruhan Wang, Xiangxin Zhou, Yucheng Shi, Zhongzhi Li, Zongxia Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T05:27:50Z","title":"Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18722","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":"sha256:136609aaaa80ca0bc61b9db3e4e769030586df7dc2852b64e2f45630edd140a8","target":"record","created_at":"2026-07-22T01:23:08Z","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":"8a9762f9ef8ea3e4d08f304d5293d827ba9cf0d7284dc6eaceffc6d72eb94744","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T05:27:50Z","title_canon_sha256":"5596c7a82da4d28eda75ca80f44114b88bcdd4b12624a37f9dc8546e4a3cb3ee"},"schema_version":"1.0","source":{"id":"2607.18722","kind":"arxiv","version":1}},"canonical_sha256":"07eb8334d59a79773b259289df434ddf62194727bc1f07e82c9268220a9b7390","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07eb8334d59a79773b259289df434ddf62194727bc1f07e82c9268220a9b7390","first_computed_at":"2026-07-22T01:23:08.485702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:08.485702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K41WG290Dztm1hp613tLLHVc3x1G++OdIf4YqZ8vvgDvorzFUboFM1k79AuD+OMFRV6YbwBVBRleRi0Js9qyAw==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:08.486598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:136609aaaa80ca0bc61b9db3e4e769030586df7dc2852b64e2f45630edd140a8","sha256:66fdb2841bf8b38bf28afc5aadab9aabb173d676ac878a667aea0beef9b0d877"],"state_sha256":"e350623ec61bb95b3c139d347feeef2001e93ec3c252e8182d9d89926fc7f3ba"}