{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4KOVMX3JEOUWMWATOXKQGVJ55Z","short_pith_number":"pith:4KOVMX3J","canonical_record":{"source":{"id":"2606.03070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:00:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a370bf5dddec016818490cb3694cca5a19e27ace727b434995201e53370a6683","abstract_canon_sha256":"ae18d5cae15780264c9fedd4922ab592b899ca04e4d3f841dc7ed565a2f04aee"},"schema_version":"1.0"},"canonical_sha256":"e29d565f6923a966581375d503553dee500c6afcf01c8e5532b3b10c4df4b0c7","source":{"kind":"arxiv","id":"2606.03070","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4KOVMX3JEOUWMWATOXKQGVJ55Z","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T03:00:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a370bf5dddec016818490cb3694cca5a19e27ace727b434995201e53370a6683","abstract_canon_sha256":"ae18d5cae15780264c9fedd4922ab592b899ca04e4d3f841dc7ed565a2f04aee"},"schema_version":"1.0"},"canonical_sha256":"e29d565f6923a966581375d503553dee500c6afcf01c8e5532b3b10c4df4b0c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:30.859248Z","signature_b64":"WVEX7vyW/SmlINfVWzb33u6izxui9P2eei58WXScrBLbf4m56u9OThhNCK+GaEMiQpiq/xxcFpkRyEzsvfyRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29d565f6923a966581375d503553dee500c6afcf01c8e5532b3b10c4df4b0c7","last_reissued_at":"2026-06-03T01:05:30.858790Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:30.858790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03070","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":"2026-06-03T01:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XJo+gpcBzJpJiFJc5hwJ4NY/kf/QX4eyKgQ8tPpEDu80AmuzKofQ+X7NqSeyM4t2QkFBUxHJd16yBsDlHkAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:28:21.354860Z"},"content_sha256":"cc5a2efdfa7558795c607017c623df2d3bdc129f9a2c0702b05a038a2625bf90","schema_version":"1.0","event_id":"sha256:cc5a2efdfa7558795c607017c623df2d3bdc129f9a2c0702b05a038a2625bf90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4KOVMX3JEOUWMWATOXKQGVJ55Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingxuan Yuan, Tao Zhong, Xiaojin Fu, Yuxuan Yao, Zehua Liu","submitted_at":"2026-06-02T03:00:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03070","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/2606.03070/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":"2026-06-03T01:05:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odW5unBHBJLxwlcVWN49jkRVqgjfbIFDP+irIXZdT5yG1JZt8F+nK66lXNXdR3Wv2J5f/8gRGem+kUg+5JSmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:28:21.355283Z"},"content_sha256":"a0cddbb2a344bff66e86445445936ded7380cb8665db08e506722682c6267e3f","schema_version":"1.0","event_id":"sha256:a0cddbb2a344bff66e86445445936ded7380cb8665db08e506722682c6267e3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/bundle.json","state_url":"https://pith.science/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/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":"2026-07-02T23:28:21Z","links":{"resolver":"https://pith.science/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z","bundle":"https://pith.science/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/bundle.json","state":"https://pith.science/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KOVMX3JEOUWMWATOXKQGVJ55Z/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uI7kOuVnP4atxgwd21oFAk/SsyB1fRidZtRP/7Qp/5ziiwsN1q0kTv8cNCy97O2IPZjP5JJt0DaXF5RD5Xn9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T23:28:21.357294Z","bundle_sha256":"bc24c5dbe817745ed87645351b20e3524fbc946923f1878003500ffe0e10a0e5"}}