{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KOVMX3JEOUWMWATOXKQGVJ55Z","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":"ae18d5cae15780264c9fedd4922ab592b899ca04e4d3f841dc7ed565a2f04aee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:00:34Z","title_canon_sha256":"a370bf5dddec016818490cb3694cca5a19e27ace727b434995201e53370a6683"},"schema_version":"1.0","source":{"id":"2606.03070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03070","created_at":"2026-06-03T01:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03070v1","created_at":"2026-06-03T01:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03070","created_at":"2026-06-03T01:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"4KOVMX3JEOUW","created_at":"2026-06-03T01:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"4KOVMX3JEOUWMWAT","created_at":"2026-06-03T01:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"4KOVMX3J","created_at":"2026-06-03T01:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:a0cddbb2a344bff66e86445445936ded7380cb8665db08e506722682c6267e3f","target":"graph","created_at":"2026-06-03T01:05:30Z","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/2606.03070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce distribution drift. Standard behavior-corrected methods control this drift with behavior-policy probabilities, importance ratios, or clipping, which requires token-aligned, versioned, and numerically consistent behavior log-probabilities across rollout and learner systems. We ask whether asynchronous group-relative RL can instead be stabilized using only current-policy probabilities. We identify a scale-imbalance failu","authors_text":"Mingxuan Yuan, Tao Zhong, Xiaojin Fu, Yuxuan Yao, Zehua Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:00:34Z","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03070","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:cc5a2efdfa7558795c607017c623df2d3bdc129f9a2c0702b05a038a2625bf90","target":"record","created_at":"2026-06-03T01:05:30Z","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":"ae18d5cae15780264c9fedd4922ab592b899ca04e4d3f841dc7ed565a2f04aee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:00:34Z","title_canon_sha256":"a370bf5dddec016818490cb3694cca5a19e27ace727b434995201e53370a6683"},"schema_version":"1.0","source":{"id":"2606.03070","kind":"arxiv","version":1}},"canonical_sha256":"e29d565f6923a966581375d503553dee500c6afcf01c8e5532b3b10c4df4b0c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e29d565f6923a966581375d503553dee500c6afcf01c8e5532b3b10c4df4b0c7","first_computed_at":"2026-06-03T01:05:30.858790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:30.858790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVEX7vyW/SmlINfVWzb33u6izxui9P2eei58WXScrBLbf4m56u9OThhNCK+GaEMiQpiq/xxcFpkRyEzsvfyRCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:30.859248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc5a2efdfa7558795c607017c623df2d3bdc129f9a2c0702b05a038a2625bf90","sha256:a0cddbb2a344bff66e86445445936ded7380cb8665db08e506722682c6267e3f"],"state_sha256":"81e866a0d08b64dbd26ea6176a1a5940caea7d1b49e5e25367e2a44f554077eb"}