{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O6TNNA4XHFGPSALGBT7UWDA2Z3","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":"85af41e7c693b5763f0d651f59c3f82ddb5241641dd836091b6a943e963c90dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T06:19:59Z","title_canon_sha256":"3ad4478482827b806453d6f0c9a424b386edcd7e21e2c0d35c209a0110c28105"},"schema_version":"1.0","source":{"id":"2509.03047","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03047","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03047v1","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03047","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"O6TNNA4XHFGP","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"O6TNNA4XHFGPSALG","created_at":"2026-07-05T12:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"O6TNNA4X","created_at":"2026-07-05T12:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:45308a59a77e02a4bf871bcadc7b721c6cbf38594da4dd34cefc04f232542dfc","target":"graph","created_at":"2026-07-05T12:04:02Z","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/2509.03047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made a profound impact across various fields due to their advanced capabilities. However, training these models at unprecedented scales requires extensive AI accelerator clusters and sophisticated parallelism strategies, which pose significant challenges in maintaining system reliability over prolonged training periods. A major concern is the substantial loss of training time caused by inevitable hardware and software failures. To address these challenges, we present FlashRecovery, a fast and low-cost failure recovery system comprising three core modules: (1) ","authors_text":"Chunsheng Li, Fei Jie, Haijun Zhang, Hongwei Sun, Hua Xu, Jinxiang Wang, Junhua Cheng, Jun Li, Jun Zhang, Kaining Mao, Shixiong Zhao, Shuwei Wang, Ting Wu, Wei Li, Xiaoming Bao, Xiemin Huang, Xuejie Ji, Yanyong Zhang, Yaqing Zhang, Yi Xiong, Zhenhua Yu, Zhifang Cai, Ziyang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T06:19:59Z","title":"FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03047","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:d0da0263d70ba995bfd78432912865e5232fd2ee4eb13aa43222834b80816965","target":"record","created_at":"2026-07-05T12:04:02Z","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":"85af41e7c693b5763f0d651f59c3f82ddb5241641dd836091b6a943e963c90dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-09-03T06:19:59Z","title_canon_sha256":"3ad4478482827b806453d6f0c9a424b386edcd7e21e2c0d35c209a0110c28105"},"schema_version":"1.0","source":{"id":"2509.03047","kind":"arxiv","version":1}},"canonical_sha256":"77a6d68397394cf901660cff4b0c1acee4353488d83c25f073b40c97fa194f23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77a6d68397394cf901660cff4b0c1acee4353488d83c25f073b40c97fa194f23","first_computed_at":"2026-07-05T12:04:02.842909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:02.842909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XhuPsu0ey2P2TjGQ/X0Q1g8h/ZIjK2gUYP0Fia6+UKnAxHKlncjrTOXzUdf3WJ80w/0XMSY1f3SnRXxWLlMjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:02.843406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03047","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0da0263d70ba995bfd78432912865e5232fd2ee4eb13aa43222834b80816965","sha256:45308a59a77e02a4bf871bcadc7b721c6cbf38594da4dd34cefc04f232542dfc"],"state_sha256":"18b4cdd7b7dc96ca4bf1f487c7860af84aa864ee069809214e6aa6748f88d80a"}