{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DWO2LGIPCGJBGRAXWESWP6ZDQ3","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":"2708f2941fe89118537e43b1a26c5fa288c84b67c6256c7303541aade6c0aac9","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T19:37:39Z","title_canon_sha256":"4e6d57915d838058ce480edd740a3cc06a7e6a251982874dc2fa29b91be52a16"},"schema_version":"1.0","source":{"id":"2512.06547","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06547","created_at":"2026-08-13T01:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06547v4","created_at":"2026-08-13T01:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06547","created_at":"2026-08-13T01:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"DWO2LGIPCGJB","created_at":"2026-08-13T01:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"DWO2LGIPCGJBGRAX","created_at":"2026-08-13T01:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"DWO2LGIP","created_at":"2026-08-13T01:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:f17dd43dd21f19b4dc64a301e032b9666f2e8a4e688d35932107b5c9bab5887f","target":"graph","created_at":"2026-08-13T01:29:39Z","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/2512.06547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g., standard PPO, GRPO) learning stability by introducing a proximal policy to decouple the off-policy correction (importance weight) from the policy update constraint (trust region). However, the proximal policy requires an extra forward pass through the model at each training step, creating a computational overhead for large language models training. We observe that ","authors_text":"Shiliang Wu, Xiaocan Li, Zheng Shen","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T19:37:39Z","title":"A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.06547","kind":"arxiv","version":4},"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":"sha256:6b579bc43fbc2c26270e85d573f9d0cf68d152a0fb136631989ac31d7173840b","target":"record","created_at":"2026-08-13T01:29:39Z","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":"2708f2941fe89118537e43b1a26c5fa288c84b67c6256c7303541aade6c0aac9","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T19:37:39Z","title_canon_sha256":"4e6d57915d838058ce480edd740a3cc06a7e6a251982874dc2fa29b91be52a16"},"schema_version":"1.0","source":{"id":"2512.06547","kind":"arxiv","version":4}},"canonical_sha256":"1d9da5990f1192134417b12567fb2386f0968d92947f89c1f944f486f62d9f18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d9da5990f1192134417b12567fb2386f0968d92947f89c1f944f486f62d9f18","first_computed_at":"2026-08-13T01:29:39.210165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:29:39.210165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zP7jeXnNFFc5IPT897Y9EL+/4MvFON90csn8AKHWMeGniMVLmlHTk+HY15Op8pezLdCT0pZi7Hkn8oGEg2TdBg==","signature_status":"signed_v1","signed_at":"2026-08-13T01:29:39.212770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.06547","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b579bc43fbc2c26270e85d573f9d0cf68d152a0fb136631989ac31d7173840b","sha256:f17dd43dd21f19b4dc64a301e032b9666f2e8a4e688d35932107b5c9bab5887f"],"state_sha256":"1a3f3330aa2a95d1fa026bd237168ee7f1ea038f8dbc2b714387ef6924cf5735"}