{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:74YUI3NHKFKQT5TSE46Q6SZ36V","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":"3da50343ee4ab8bf03a689b3e3682f7e8e5a187f7b6bcc133ac1ebdadc4aad41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T04:06:52Z","title_canon_sha256":"003881551436091d6e0e5e57164795661a375d0387e5d271f8df2c907111b1a0"},"schema_version":"1.0","source":{"id":"2310.10046","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10046","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10046v3","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10046","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"74YUI3NHKFKQ","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"74YUI3NHKFKQT5TS","created_at":"2026-07-05T07:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"74YUI3NH","created_at":"2026-07-05T07:02:06Z"}],"graph_snapshots":[{"event_id":"sha256:bd726b300f94a83a17ba3ca7ffad3bb4aa0457741d4d3d2003bf440adb775600","target":"graph","created_at":"2026-07-05T07:02:06Z","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/2310.10046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) with hundreds of billions or trillions of parameters, represented by chatGPT, have achieved profound impact on various fields. However, training LLMs with super-large-scale parameters requires large high-performance GPU clusters and long training periods lasting for months. Due to the inevitable hardware and software failures in large-scale clusters, maintaining uninterrupted and long-duration training is extremely challenging. As a result, A substantial amount of training time is devoted to task checkpoint saving and loading, task rescheduling and restart, and tas","authors_text":"Baodong Wu, Kangyu Li, Lei Xia, Qingping Li, Shigang Li, Tieyao Xiang, Xu Chen, Yongqiang Guo, Yuheng Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T04:06:52Z","title":"TRANSOM: An Efficient Fault-Tolerant System for Training LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10046","kind":"arxiv","version":3},"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:bda1274e1613cb2a5de2d106d428e7c21f7cdad048784e26e619f5ca005c2c81","target":"record","created_at":"2026-07-05T07:02:06Z","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":"3da50343ee4ab8bf03a689b3e3682f7e8e5a187f7b6bcc133ac1ebdadc4aad41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T04:06:52Z","title_canon_sha256":"003881551436091d6e0e5e57164795661a375d0387e5d271f8df2c907111b1a0"},"schema_version":"1.0","source":{"id":"2310.10046","kind":"arxiv","version":3}},"canonical_sha256":"ff31446da7515509f672273d0f4b3bf57b93d276573d857d439b48be8a5a7126","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff31446da7515509f672273d0f4b3bf57b93d276573d857d439b48be8a5a7126","first_computed_at":"2026-07-05T07:02:06.437780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:06.437780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfSuRDYo1yUF54i8PV1N4gNtcDQ09s1h6dQtBb/wwKW118aI9h/BUkUpaSvnPf3IcU75jJfXETv1tZGJ1WJlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:06.438292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10046","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bda1274e1613cb2a5de2d106d428e7c21f7cdad048784e26e619f5ca005c2c81","sha256:bd726b300f94a83a17ba3ca7ffad3bb4aa0457741d4d3d2003bf440adb775600"],"state_sha256":"c7aeba96c5e2a78e31760fc2c8c647a1c36aced736fa39ff28d387c483765ef6"}