{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UN5V344BBGX35T5AS7XGVER4R4","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":"6d868266ccf118cac3094b63fb4471aaa6ba5041d4a243be1e52aeec5869eed8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-30T04:06:16Z","title_canon_sha256":"5ba39ad3df9bb5ca11cb48f89aa76e85a9230dc32b60240f29f17c6a9cb28cb0"},"schema_version":"1.0","source":{"id":"2401.00134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00134","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00134v1","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00134","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_12","alias_value":"UN5V344BBGX3","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_16","alias_value":"UN5V344BBGX35T5A","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_8","alias_value":"UN5V344B","created_at":"2026-07-05T07:30:24Z"}],"graph_snapshots":[{"event_id":"sha256:aff60344bc2381b00e9b345317fa1163c01a86bf17f32b9f97e3aafab014db7b","target":"graph","created_at":"2026-07-05T07:30:24Z","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/2401.00134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large-scale language models is increasingly critical in various domains, but it is hindered by frequent failures, leading to significant time and economic costs. Current failure recovery methods in cloud-based settings inadequately address the diverse and complex scenarios that arise, focusing narrowly on erasing downtime for individual tasks without considering the overall cost impact on a cluster. We introduce Unicron, a workload manager designed for efficient self-healing in large-scale language model training. Unicron optimizes the training process by minimizing failure-related co","authors_text":"Jingbo Xu, Jingren Zhou, Kun Qian, Tao He, Wenyuan Yu, Xue Li, Zhibin Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-30T04:06:16Z","title":"Unicron: Economizing Self-Healing LLM Training at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00134","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":"sha256:37e9c7d884316d451f7a6b9eb021060274f6972ff16ec867aaa4876194d7410f","target":"record","created_at":"2026-07-05T07:30:24Z","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":"6d868266ccf118cac3094b63fb4471aaa6ba5041d4a243be1e52aeec5869eed8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-12-30T04:06:16Z","title_canon_sha256":"5ba39ad3df9bb5ca11cb48f89aa76e85a9230dc32b60240f29f17c6a9cb28cb0"},"schema_version":"1.0","source":{"id":"2401.00134","kind":"arxiv","version":1}},"canonical_sha256":"a37b5df38109afbecfa097ee6a923c8f0f234d52ddc56fb88f55a1954a8aa3c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37b5df38109afbecfa097ee6a923c8f0f234d52ddc56fb88f55a1954a8aa3c8","first_computed_at":"2026-07-05T07:30:24.476434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:24.476434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c89/npQIjjtKF8xaxWkGRhFrSizsEYT5JJV0ewRuzcDnieJku+XuJzfjZ7aYWKQJ8sBaTYMx9+hsxatrwCskDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:24.476908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37e9c7d884316d451f7a6b9eb021060274f6972ff16ec867aaa4876194d7410f","sha256:aff60344bc2381b00e9b345317fa1163c01a86bf17f32b9f97e3aafab014db7b"],"state_sha256":"b2678d945006509cd8710ae2803f2f61aab3771c202baff30641c4301455a31b"}