{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JBBVU5HSDXAMALWEIU76ZKLN43","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":"13d2e4328a716e499a9bf76c57754a84606318f97f1aa74094b53500b742d02a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T07:11:49Z","title_canon_sha256":"379d4fdf35ab7110f668339844ca2f6c70dd3a174531907a21e9bb542bcda883"},"schema_version":"1.0","source":{"id":"2507.19017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19017","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19017v1","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19017","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_12","alias_value":"JBBVU5HSDXAM","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_16","alias_value":"JBBVU5HSDXAMALWE","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_8","alias_value":"JBBVU5HS","created_at":"2026-07-05T11:43:18Z"}],"graph_snapshots":[{"event_id":"sha256:b0090b9277ba61de9e2bbd8eee3503bc67fb1852d6aa55a16c4b9166619557f2","target":"graph","created_at":"2026-07-05T11:43:18Z","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/2507.19017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each node is the status of a worker and each edge represents dataflow between nodes. Owing to the heavy cross-node dependencies, the RL training system usually suffers from poor cluster scalability and low memory utilization. In this article, we introduce MindSpeed RL, an effective and efficient system for large-scale RL training. Unlike existing centralized methods, MindSpeed RL organizes the essential data dependencies","authors_text":"Beirong Zhou, Benzhe Ning, Bo Wang, Chang Liu, Chenyi Pan, Fei Mei, Guang Yang, Jiangben Wang, Jianxiang Zhang, Laingjun Feng, Xinjie Guo, Xinyang Liu, Zeng Shu, Zhenyu Han","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T07:11:49Z","title":"MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19017","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":"sha256:251209a1e92ff12ac8512c302fa10a123885eee54835ea67d25795af32e6382d","target":"record","created_at":"2026-07-05T11:43:18Z","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":"13d2e4328a716e499a9bf76c57754a84606318f97f1aa74094b53500b742d02a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T07:11:49Z","title_canon_sha256":"379d4fdf35ab7110f668339844ca2f6c70dd3a174531907a21e9bb542bcda883"},"schema_version":"1.0","source":{"id":"2507.19017","kind":"arxiv","version":1}},"canonical_sha256":"48435a74f21dc0c02ec4453feca96de6e080f361226c02f8467c24ab6eca1a4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48435a74f21dc0c02ec4453feca96de6e080f361226c02f8467c24ab6eca1a4e","first_computed_at":"2026-07-05T11:43:18.014488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:18.014488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNDI0kEpBp/3S10wciWpEZVV+M36dMGJ4J+YivIbOawaIsNfApBXBp3+7oLTkp7qjwuupWlk0a9dYciPcRFVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:18.014972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:251209a1e92ff12ac8512c302fa10a123885eee54835ea67d25795af32e6382d","sha256:b0090b9277ba61de9e2bbd8eee3503bc67fb1852d6aa55a16c4b9166619557f2"],"state_sha256":"e60171e816d8e9738c0bbf25e3db1617a96400c50289738173ff294805e9ade9"}