{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5DIHQLLELIUA4RN3PLZA6CNIOS","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":"e8c8ac4850a1a4e8322aa113b3231e236a9cd8d6f4020875a1127aba9577dd4d","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T06:09:55Z","title_canon_sha256":"bed51d8fcab4b892f4a0c3153c846e683b4db40291a8bdc323aaa84ec0583f28"},"schema_version":"1.0","source":{"id":"2503.20263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20263","created_at":"2026-07-05T10:39:35Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20263v1","created_at":"2026-07-05T10:39:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20263","created_at":"2026-07-05T10:39:35Z"},{"alias_kind":"pith_short_12","alias_value":"5DIHQLLELIUA","created_at":"2026-07-05T10:39:35Z"},{"alias_kind":"pith_short_16","alias_value":"5DIHQLLELIUA4RN3","created_at":"2026-07-05T10:39:35Z"},{"alias_kind":"pith_short_8","alias_value":"5DIHQLLE","created_at":"2026-07-05T10:39:35Z"}],"graph_snapshots":[{"event_id":"sha256:cdebfc819b9315e74e001c28990eff6cae8b76491a77b10de58f4f755088b51a","target":"graph","created_at":"2026-07-05T10:39:35Z","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/2503.20263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) show their capabilities across various applications, training customized LLMs has become essential for modern enterprises. However, due to the complexity of LLM training, which requires massive computational resources and extensive training time, failures are inevitable during the training process. These failures result in considerable waste of resource and time, highlighting the critical need for effective and efficient failure diagnosis to reduce the cost of LLM training.\n  In this paper, we present the first empirical study on the failure reports of 428 LLM t","authors_text":"Cong Feng, Guangba Yu, Junjie Huang, Michael R. Lyu, Yichen Li, Yongqiang Yang, Zengyin Yang, Zhihan Jiang, Zhuangbin Chen","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T06:09:55Z","title":"L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20263","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":"sha256:0815b31e6fc2b2364aa3bf6463dceca49b6996427bece4fecae1f955d65c866f","target":"record","created_at":"2026-07-05T10:39:35Z","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":"e8c8ac4850a1a4e8322aa113b3231e236a9cd8d6f4020875a1127aba9577dd4d","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-26T06:09:55Z","title_canon_sha256":"bed51d8fcab4b892f4a0c3153c846e683b4db40291a8bdc323aaa84ec0583f28"},"schema_version":"1.0","source":{"id":"2503.20263","kind":"arxiv","version":1}},"canonical_sha256":"e8d0782d645a280e45bb7af20f09a874aa457c3e63fa24b454f480d0ca6ad868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8d0782d645a280e45bb7af20f09a874aa457c3e63fa24b454f480d0ca6ad868","first_computed_at":"2026-07-05T10:39:35.904657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:35.904657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bd/J7Hz3571uiQ6myH7yaLUvvIh5NyRgRvgAfjp4QZzh11mmF77A0mRbz/YrxrfbBVqMXjSFHlxwUHncPRaVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:35.905260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0815b31e6fc2b2364aa3bf6463dceca49b6996427bece4fecae1f955d65c866f","sha256:cdebfc819b9315e74e001c28990eff6cae8b76491a77b10de58f4f755088b51a"],"state_sha256":"e3766b0c339d99f75415f2ba7c2174b532b67c0f5f9d16064e75f49e10e01946"}