{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IE22MEPKVMN7TVPLV7Q6ZZG5VE","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":"9ae4d780e79d948d834998944d94e80b3f15626006a783127c3593f889d2c89a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-10T08:51:14Z","title_canon_sha256":"b4d91c4b6a31ce6826b665aaa04220881cef2cf38859f200f1f02457077ebf95"},"schema_version":"1.0","source":{"id":"2607.09207","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09207","created_at":"2026-07-13T01:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09207v1","created_at":"2026-07-13T01:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09207","created_at":"2026-07-13T01:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"IE22MEPKVMN7","created_at":"2026-07-13T01:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"IE22MEPKVMN7TVPL","created_at":"2026-07-13T01:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"IE22MEPK","created_at":"2026-07-13T01:18:51Z"}],"graph_snapshots":[{"event_id":"sha256:ede8316fdb21abb9b78353d3b6486aecc0ff932df2cf0833a5725ff63e4269b4","target":"graph","created_at":"2026-07-13T01:18:51Z","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/2607.09207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well established that the reasoning capabilities of large language models (LLMs) can be improved by applying reinforcement learning (RL) in a post-training stage. In a standard RL iteration, the current model (the policy) generates experience through rollouts, and the resulting data is then used to update the policy during training. High-performance RL frameworks such as StreamRL and AReaL employ a disaggregated architecture and asynchronous rollouts to better exploit both rollout and training resources, thereby increasing overall system throughput.\n  Nonetheless, across varying RL setup","authors_text":"Chu Xiaowen, Shi Shaohuai, Tan Zhiqiang, Wang Maoxin, Wang Qiang, Wang Sijie, Yin Yiming","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-10T08:51:14Z","title":"Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09207","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:e8b1ae03a97063de46661733f9bc75639f2a47caadaaa5c533ec16a9f6bb1acf","target":"record","created_at":"2026-07-13T01:18:51Z","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":"9ae4d780e79d948d834998944d94e80b3f15626006a783127c3593f889d2c89a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-10T08:51:14Z","title_canon_sha256":"b4d91c4b6a31ce6826b665aaa04220881cef2cf38859f200f1f02457077ebf95"},"schema_version":"1.0","source":{"id":"2607.09207","kind":"arxiv","version":1}},"canonical_sha256":"4135a611eaab1bf9d5ebafe1ece4dda910479941188858f87674c26c19c27f37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4135a611eaab1bf9d5ebafe1ece4dda910479941188858f87674c26c19c27f37","first_computed_at":"2026-07-13T01:18:51.445918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:18:51.445918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vTCvtXWHSM5Y+dCF4vUt2krHMSDRILmCys+CJhv92k+8VLvQ2lK47eOSAbluRPhr2z6JqvUdyWP9y7fesCWVAw==","signature_status":"signed_v1","signed_at":"2026-07-13T01:18:51.447406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09207","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8b1ae03a97063de46661733f9bc75639f2a47caadaaa5c533ec16a9f6bb1acf","sha256:ede8316fdb21abb9b78353d3b6486aecc0ff932df2cf0833a5725ff63e4269b4"],"state_sha256":"01768770cefead38ee5391070ed86412799beec7128935cb87e332061955a276"}