{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B27XQPW7K53XZAU5UROC332AWL","short_pith_number":"pith:B27XQPW7","canonical_record":{"source":{"id":"2504.15930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T14:19:06Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"14ac7d7421a41fa67579cc47bba6e157647e3d0c1b85b5a9d55e2ccac26fe061","abstract_canon_sha256":"e7d439610fa7130e7b8a9458cc64e2c02130ffc1bfd1cb23823d52ec11321414"},"schema_version":"1.0"},"canonical_sha256":"0ebf783edf57777c829da45c2def40b2cabe3ee06cf5a81d5a05757c46733aa2","source":{"kind":"arxiv","id":"2504.15930","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15930","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15930v1","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15930","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_12","alias_value":"B27XQPW7K53X","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_16","alias_value":"B27XQPW7K53XZAU5","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_8","alias_value":"B27XQPW7","created_at":"2026-07-05T10:52:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B27XQPW7K53XZAU5UROC332AWL","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T14:19:06Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"14ac7d7421a41fa67579cc47bba6e157647e3d0c1b85b5a9d55e2ccac26fe061","abstract_canon_sha256":"e7d439610fa7130e7b8a9458cc64e2c02130ffc1bfd1cb23823d52ec11321414"},"schema_version":"1.0"},"canonical_sha256":"0ebf783edf57777c829da45c2def40b2cabe3ee06cf5a81d5a05757c46733aa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:32.090703Z","signature_b64":"CQliIR3yZR7bk/rZihi5cGzFSFH0+UhLvuHaFS3BfNv5gwpBTDDuacrCKW7bZ27D5sdS1PURXCZPA+URwn0MCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ebf783edf57777c829da45c2def40b2cabe3ee06cf5a81d5a05757c46733aa2","last_reissued_at":"2026-07-05T10:52:32.089956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:32.089956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15930","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":"2026-07-05T10:52:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aViGuY7QFqPjKD/NBolC6EtW29z47bFEf1dTtDV9xm02tMdqugk+UwEcpdrRdnd5pNz6gpw4/46Fvj7T27UAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:16.173527Z"},"content_sha256":"ec9503c1c60feb0912d1edb91e5ac2b37d9163847289339dc5f1da4c48e39fc1","schema_version":"1.0","event_id":"sha256:ec9503c1c60feb0912d1edb91e5ac2b37d9163847289339dc5f1da4c48e39fc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B27XQPW7K53XZAU5UROC332AWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bingyang Wu, Changyi Wan, Chao Jin, Daxin Jiang, Hanpeng Hu, Hongyu Zhou, Nuo Chen, Xiaoniu Song, Yibo Zhu, Yimin Jiang, Yinmin Zhong, Yukun Chen, Yu Zhou, Zili Zhang","submitted_at":"2025-04-22T14:19:06Z","abstract_excerpt":"Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive rewards for training. The conventional view holds that the colocated architecture, where the two stages share resources via temporal multiplexing, outperforms the disaggregated architecture, in which dedicated resources are assigned to each stage. However, in real-world deployments, we observe that the colocated architecture suffers from resource coupling, where t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15930","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/2504.15930/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":"2026-07-05T10:52:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yk7apND+qPkAqTmHE5iflOnclI/rjNkXImk2zDzihYumEHD3W6MeqlHi/y1gIzENPVU82M6enkqHU0ERCLNQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:49:16.174037Z"},"content_sha256":"775400ea977ebaceba6e3138b950d49e812725bc133ba3d7e5710aec0486996a","schema_version":"1.0","event_id":"sha256:775400ea977ebaceba6e3138b950d49e812725bc133ba3d7e5710aec0486996a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B27XQPW7K53XZAU5UROC332AWL/bundle.json","state_url":"https://pith.science/pith/B27XQPW7K53XZAU5UROC332AWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B27XQPW7K53XZAU5UROC332AWL/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":"2026-08-04T05:49:16Z","links":{"resolver":"https://pith.science/pith/B27XQPW7K53XZAU5UROC332AWL","bundle":"https://pith.science/pith/B27XQPW7K53XZAU5UROC332AWL/bundle.json","state":"https://pith.science/pith/B27XQPW7K53XZAU5UROC332AWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B27XQPW7K53XZAU5UROC332AWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B27XQPW7K53XZAU5UROC332AWL","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":"e7d439610fa7130e7b8a9458cc64e2c02130ffc1bfd1cb23823d52ec11321414","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T14:19:06Z","title_canon_sha256":"14ac7d7421a41fa67579cc47bba6e157647e3d0c1b85b5a9d55e2ccac26fe061"},"schema_version":"1.0","source":{"id":"2504.15930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15930","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15930v1","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15930","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_12","alias_value":"B27XQPW7K53X","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_16","alias_value":"B27XQPW7K53XZAU5","created_at":"2026-07-05T10:52:32Z"},{"alias_kind":"pith_short_8","alias_value":"B27XQPW7","created_at":"2026-07-05T10:52:32Z"}],"graph_snapshots":[{"event_id":"sha256:775400ea977ebaceba6e3138b950d49e812725bc133ba3d7e5710aec0486996a","target":"graph","created_at":"2026-07-05T10:52:32Z","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/2504.15930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive rewards for training. The conventional view holds that the colocated architecture, where the two stages share resources via temporal multiplexing, outperforms the disaggregated architecture, in which dedicated resources are assigned to each stage. However, in real-world deployments, we observe that the colocated architecture suffers from resource coupling, where t","authors_text":"Bingyang Wu, Changyi Wan, Chao Jin, Daxin Jiang, Hanpeng Hu, Hongyu Zhou, Nuo Chen, Xiaoniu Song, Yibo Zhu, Yimin Jiang, Yinmin Zhong, Yukun Chen, Yu Zhou, Zili Zhang","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T14:19:06Z","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15930","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:ec9503c1c60feb0912d1edb91e5ac2b37d9163847289339dc5f1da4c48e39fc1","target":"record","created_at":"2026-07-05T10:52:32Z","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":"e7d439610fa7130e7b8a9458cc64e2c02130ffc1bfd1cb23823d52ec11321414","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T14:19:06Z","title_canon_sha256":"14ac7d7421a41fa67579cc47bba6e157647e3d0c1b85b5a9d55e2ccac26fe061"},"schema_version":"1.0","source":{"id":"2504.15930","kind":"arxiv","version":1}},"canonical_sha256":"0ebf783edf57777c829da45c2def40b2cabe3ee06cf5a81d5a05757c46733aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ebf783edf57777c829da45c2def40b2cabe3ee06cf5a81d5a05757c46733aa2","first_computed_at":"2026-07-05T10:52:32.089956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:32.089956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CQliIR3yZR7bk/rZihi5cGzFSFH0+UhLvuHaFS3BfNv5gwpBTDDuacrCKW7bZ27D5sdS1PURXCZPA+URwn0MCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:32.090703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec9503c1c60feb0912d1edb91e5ac2b37d9163847289339dc5f1da4c48e39fc1","sha256:775400ea977ebaceba6e3138b950d49e812725bc133ba3d7e5710aec0486996a"],"state_sha256":"bb842ae003c34dd70bd58d62be40cfa9db3e1b930a5fce464404dc6434439b7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcovXrSjoCI6hAXczCU2MgUoksHR9UoLKD0/tmUpOIlE85BuFGLMnMLjGD+OKqJt1kF7RkXIM0sU3egfFk0cAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:49:16.178614Z","bundle_sha256":"959efb2eca5f009838a4f418ad99c34c14240551bf6e7da4c78d91c7c1607f44"}}