{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QUUXD2QVLQ2BT5BIP7VS3AOIIW","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":"1b27e3608eb920df2bd476b586738fd4004189071b797550891b5c39ee71ea60","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T03:17:58Z","title_canon_sha256":"1295ed18056ed5285ec27756ca8e627cb8d29ad5062081e2c5ad785786eccd32"},"schema_version":"1.0","source":{"id":"2607.01646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01646","created_at":"2026-07-03T01:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01646v1","created_at":"2026-07-03T01:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01646","created_at":"2026-07-03T01:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"QUUXD2QVLQ2B","created_at":"2026-07-03T01:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"QUUXD2QVLQ2BT5BI","created_at":"2026-07-03T01:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"QUUXD2QV","created_at":"2026-07-03T01:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:1eb7ea8934f9db9d42129fbbe52cf2a2d80c7beb5d5033395e19b97af45f9323","target":"graph","created_at":"2026-07-03T01:17:04Z","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/2607.01646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack. Existing fault-tolerance mechanisms either impose non-trivial overhead during failure-free execution or suffer from prolonged recovery latency, particularly under scenarios where a small subset of compute nodes experience permanent failures. %The tradeoff between failure-free overhead and recovery latency forms a space forms a Pareto frontier We present DeadPool to simultaneously address both optimization obj","authors_text":"Haotian Xie, Junlin Chen, Lishan Yang, Mingkai Zheng, Zhao Zhang","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T03:17:58Z","title":"DeadPool: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01646","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:b69acadc9633524ea7015daafb63de0ffbbac7c2dd78c0b77731fbc984cd2ace","target":"record","created_at":"2026-07-03T01:17:04Z","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":"1b27e3608eb920df2bd476b586738fd4004189071b797550891b5c39ee71ea60","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T03:17:58Z","title_canon_sha256":"1295ed18056ed5285ec27756ca8e627cb8d29ad5062081e2c5ad785786eccd32"},"schema_version":"1.0","source":{"id":"2607.01646","kind":"arxiv","version":1}},"canonical_sha256":"852971ea155c3419f4287feb2d81c8459b865bd9e938dab17552fcd8d8a54b37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"852971ea155c3419f4287feb2d81c8459b865bd9e938dab17552fcd8d8a54b37","first_computed_at":"2026-07-03T01:17:04.383176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:04.383176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6evRBfqHpYDkRaVRTeHdW+PWA0P/RYqKwovoXkuKUE+BORMlhhHj5R2Pg+w3pwPsySzTnLS6VMf07MdrLt/ZAA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:04.383551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b69acadc9633524ea7015daafb63de0ffbbac7c2dd78c0b77731fbc984cd2ace","sha256:1eb7ea8934f9db9d42129fbbe52cf2a2d80c7beb5d5033395e19b97af45f9323"],"state_sha256":"51fa5a1dad683889738cd7bf9245eb1412fcbfa116139957388e2ed256d72089"}