{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ULXCJOW2J7UWS3CCWCVUCKDDKA","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":"8bbafb845cafdf28755ea30d50431ea73cadd9dc64d3ed70bbeb2c448b98b23b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-18T03:48:32Z","title_canon_sha256":"13878dc0b22a52c2150ee2a233d12231182f864959efa0456fed760d5d42ced4"},"schema_version":"1.0","source":{"id":"2605.17821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17821","created_at":"2026-05-20T00:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17821v1","created_at":"2026-05-20T00:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17821","created_at":"2026-05-20T00:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"ULXCJOW2J7UW","created_at":"2026-05-20T00:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"ULXCJOW2J7UWS3CC","created_at":"2026-05-20T00:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"ULXCJOW2","created_at":"2026-05-20T00:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:db192675d801d889a36220c23047941fb9a4f6e8d3e0f1921937e83508a9b2b8","target":"graph","created_at":"2026-05-20T00:05:00Z","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/2605.17821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster-wide outages. Existing checkpointing systems rely on monolithic, single-tier storage backend, forcing a trade-off between state-saving overhead and recovery speed. We propose TierCheck, a cluster-aware tiered checkpointing system that aligns storage placement with failure heterogeneity. TierCheck adopts a three-tier design that maintains lightweight differential checkpoints in local and peer memory for fast localized recovery, while asynchronous","authors_text":"Feng Jiang, Lichen Pan, Nannan Zhao, Patrick P. C. Lee, Shujie Han, Xiaonan Zhao, Xiao Zhang, Zhijie Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-18T03:48:32Z","title":"TierCheck: Tiered Checkpointing for Fault Tolerance in Large Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17821","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":"sha256:376accfa02ed5a7b3d8f224111df125bdbbaca3ebc19ba507be052ee49ff7e17","target":"record","created_at":"2026-05-20T00:05:00Z","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":"8bbafb845cafdf28755ea30d50431ea73cadd9dc64d3ed70bbeb2c448b98b23b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-18T03:48:32Z","title_canon_sha256":"13878dc0b22a52c2150ee2a233d12231182f864959efa0456fed760d5d42ced4"},"schema_version":"1.0","source":{"id":"2605.17821","kind":"arxiv","version":1}},"canonical_sha256":"a2ee24bada4fe9696c42b0ab41286350348b6c9d1f9b8a153828d1abda93bab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2ee24bada4fe9696c42b0ab41286350348b6c9d1f9b8a153828d1abda93bab2","first_computed_at":"2026-05-20T00:05:00.049075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:00.049075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rTVuEUspuNwnAIBNHEPi8Z3QFCV1m2CTuzzyfBN7vrG/sj72Ci7bkXuGg1Gq0wCkU4tU1iXkXtGh1xlgH8zwBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:00.049934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:376accfa02ed5a7b3d8f224111df125bdbbaca3ebc19ba507be052ee49ff7e17","sha256:db192675d801d889a36220c23047941fb9a4f6e8d3e0f1921937e83508a9b2b8"],"state_sha256":"73b77c250165b164ca346f2a1f5d47beb7a134a99d01c741aa1f79b673878ef8"}