{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVRHIR5W7FZQ3WO5RYH7SK2BFZ","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":"57af5265de4f544bc78cf589b08b5e097df08b3914bda9d5f0aed05093fb3e14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-08-08T08:40:15Z","title_canon_sha256":"83f536b4da497c776db9cd292166cc636b6e67876053100f94f240437b0980b3"},"schema_version":"1.0","source":{"id":"2408.04307","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04307","created_at":"2026-07-05T10:46:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04307v3","created_at":"2026-07-05T10:46:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04307","created_at":"2026-07-05T10:46:38Z"},{"alias_kind":"pith_short_12","alias_value":"IVRHIR5W7FZQ","created_at":"2026-07-05T10:46:38Z"},{"alias_kind":"pith_short_16","alias_value":"IVRHIR5W7FZQ3WO5","created_at":"2026-07-05T10:46:38Z"},{"alias_kind":"pith_short_8","alias_value":"IVRHIR5W","created_at":"2026-07-05T10:46:38Z"}],"graph_snapshots":[{"event_id":"sha256:868aa13b74911fd9c11e32344a9ebde1e69a0cc68a7e3c33205902bd02f02115","target":"graph","created_at":"2026-07-05T10:46:38Z","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/2408.04307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models continue to scale up, distributed training systems have expanded beyond 10k nodes, intensifying the importance of fault tolerance. Checkpoint has emerged as the predominant fault tolerance strategy, with extensive studies dedicated to optimizing its efficiency. However, the advent of the sparse Mixture-of-Experts (MoE) model presents new challenges due to the substantial increase in model size, despite comparable computational demands to dense models.\n  In this work, we propose the Mixture-of-Checkpoint System (MoC-System) to orchestrate the vast array of checkpoint sh","authors_text":"Jiayi Huang, Le Qin, Weilin Cai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-08-08T08:40:15Z","title":"MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04307","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":"sha256:6f841bca8a8077760f0ca9648a93a4777f5a833b272a6b44c113c576e2badddc","target":"record","created_at":"2026-07-05T10:46:38Z","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":"57af5265de4f544bc78cf589b08b5e097df08b3914bda9d5f0aed05093fb3e14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-08-08T08:40:15Z","title_canon_sha256":"83f536b4da497c776db9cd292166cc636b6e67876053100f94f240437b0980b3"},"schema_version":"1.0","source":{"id":"2408.04307","kind":"arxiv","version":3}},"canonical_sha256":"45627447b6f9730dd9dd8e0ff92b412e71f19f23452acd4b4849529d5343f2e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45627447b6f9730dd9dd8e0ff92b412e71f19f23452acd4b4849529d5343f2e4","first_computed_at":"2026-07-05T10:46:38.040221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:38.040221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0+NMWWcm8/3kDTMrKPk5G6CpBi19/Ox5uwy1Eua5n2SvqnCJBwyCydxpTFqNIhlRbrdo4if8JjJxNVS9bbRFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:38.040681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04307","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f841bca8a8077760f0ca9648a93a4777f5a833b272a6b44c113c576e2badddc","sha256:868aa13b74911fd9c11e32344a9ebde1e69a0cc68a7e3c33205902bd02f02115"],"state_sha256":"083408bb766fab8c658212c6097792aa4f8c3bab88bfce1f947b8394ae5c9690"}