{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A7VYGNGVTJ4XOOZFSKE56Q2N35","short_pith_number":"pith:A7VYGNGV","canonical_record":{"source":{"id":"2607.18722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T05:27:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5596c7a82da4d28eda75ca80f44114b88bcdd4b12624a37f9dc8546e4a3cb3ee","abstract_canon_sha256":"8a9762f9ef8ea3e4d08f304d5293d827ba9cf0d7284dc6eaceffc6d72eb94744"},"schema_version":"1.0"},"canonical_sha256":"07eb8334d59a79773b259289df434ddf62194727bc1f07e82c9268220a9b7390","source":{"kind":"arxiv","id":"2607.18722","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A7VYGNGVTJ4XOOZFSKE56Q2N35","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T05:27:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5596c7a82da4d28eda75ca80f44114b88bcdd4b12624a37f9dc8546e4a3cb3ee","abstract_canon_sha256":"8a9762f9ef8ea3e4d08f304d5293d827ba9cf0d7284dc6eaceffc6d72eb94744"},"schema_version":"1.0"},"canonical_sha256":"07eb8334d59a79773b259289df434ddf62194727bc1f07e82c9268220a9b7390","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:08.486598Z","signature_b64":"K41WG290Dztm1hp613tLLHVc3x1G++OdIf4YqZ8vvgDvorzFUboFM1k79AuD+OMFRV6YbwBVBRleRi0Js9qyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07eb8334d59a79773b259289df434ddf62194727bc1f07e82c9268220a9b7390","last_reissued_at":"2026-07-22T01:23:08.485702Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:08.485702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18722","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56L+pCnM2aIH38MS7Epg4Yr1sB+KZ9r/C4IiTm5szmTA919H6AWXQQGWJLc3kb883pQWNxv5/Unlzr7Ch6EJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:32:27.593440Z"},"content_sha256":"136609aaaa80ca0bc61b9db3e4e769030586df7dc2852b64e2f45630edd140a8","schema_version":"1.0","event_id":"sha256:136609aaaa80ca0bc61b9db3e4e769030586df7dc2852b64e2f45630edd140a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A7VYGNGVTJ4XOOZFSKE56Q2N35","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haitao Mi, Junyao Yang, Kishan Panaganti, Leowei Liang, Ruhan Wang, Xiangxin Zhou, Yucheng Shi, Zhongzhi Li, Zongxia Li","submitted_at":"2026-07-21T05:27:50Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18722","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.18722/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-22T01:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PJYrB6EHuoDGVzQcHnnZh76JfwD4nL9Tz7skuxcx3lpZTWXq+KvoYpCq1BEtYU4ohqJRtrQwe2alMRapc/XRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:32:27.593953Z"},"content_sha256":"66fdb2841bf8b38bf28afc5aadab9aabb173d676ac878a667aea0beef9b0d877","schema_version":"1.0","event_id":"sha256:66fdb2841bf8b38bf28afc5aadab9aabb173d676ac878a667aea0beef9b0d877"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/bundle.json","state_url":"https://pith.science/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T22:32:27Z","links":{"resolver":"https://pith.science/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35","bundle":"https://pith.science/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/bundle.json","state":"https://pith.science/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7VYGNGVTJ4XOOZFSKE56Q2N35/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNagPZA0tz000+xVT8Dj2suDvCuDYlA7yN2pPrX4IxTumFvWN9lWE2MgjBqKqOcUA6psq3rVv2MIvfLftty1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:32:27.598055Z","bundle_sha256":"52c9dac820be9446cc653a26218a36e80383a0c83910335309acfde131e65a9c"}}