{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HZPTJ74NCKE3C7SO3YYPNSCRAW","short_pith_number":"pith:HZPTJ74N","canonical_record":{"source":{"id":"2502.12340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T22:07:49Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"6b2871fbf08ef54bd10723d4c9875d1386e4bc923bbe809839575c3db6e11e59","abstract_canon_sha256":"1d70e995e96d0171cf81c5a68faa1c252f99d795bd86a3a5504bcdd470ab96d6"},"schema_version":"1.0"},"canonical_sha256":"3e5f34ff8d1289b17e4ede30f6c8510597641b5b7ac4a33227721aaefe05f40b","source":{"kind":"arxiv","id":"2502.12340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12340","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12340v1","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12340","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"HZPTJ74NCKE3","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"HZPTJ74NCKE3C7SO","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"HZPTJ74N","created_at":"2026-07-05T10:15:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HZPTJ74NCKE3C7SO3YYPNSCRAW","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T22:07:49Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"6b2871fbf08ef54bd10723d4c9875d1386e4bc923bbe809839575c3db6e11e59","abstract_canon_sha256":"1d70e995e96d0171cf81c5a68faa1c252f99d795bd86a3a5504bcdd470ab96d6"},"schema_version":"1.0"},"canonical_sha256":"3e5f34ff8d1289b17e4ede30f6c8510597641b5b7ac4a33227721aaefe05f40b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:53.788985Z","signature_b64":"SlUyK4+yoVoGDFwPgHuLI0vcOEzaemc1Il/MH0lG+E9ehJ7c5Hg8/dDuRydbnvpfH/ozU701qjVWJ5R7CkYPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e5f34ff8d1289b17e4ede30f6c8510597641b5b7ac4a33227721aaefe05f40b","last_reissued_at":"2026-07-05T10:15:53.788506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:53.788506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NXdk7G0YIDUvpOSu+CQcbj5W/PU7mbYrU55JEIlTYJDTlgSi1TzQeDuQm/qKNKs0fJ4aVwkIbDmA5yd4RcwoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:52:46.747252Z"},"content_sha256":"7dc4e66bbf8b9c4939a4c72d2b71f4d056217618fa8aeb53d597d5857f72c61f","schema_version":"1.0","event_id":"sha256:7dc4e66bbf8b9c4939a4c72d2b71f4d056217618fa8aeb53d597d5857f72c61f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HZPTJ74NCKE3C7SO3YYPNSCRAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Silent Data Corruption in LLM Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"George Karypis, Hengzhi Pei, Jeffrey Ma, Leonard Lausen","submitted_at":"2025-02-17T22:07:49Z","abstract_excerpt":"As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explicit failure signals. In this work, we are the first to investigate the impact of real-world SDCs on LLM training by comparing model training between healthy production nodes and unhealthy nodes exhibiting SDCs. With the help from a cloud computing platform, we access the unhealthy nodes that were swept out from production by automated fleet management. Using deterministic execution via XLA compiler and our proposed sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12340","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.12340/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PaoQodA3sMQz+HtZdhIFDHZ7MInX60c8sd46tWNRfnnwzEQcPc04pJZsxGi1VQsvbWkSkhsgA0vvnR3zPDqqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:52:46.747761Z"},"content_sha256":"12d87465b6baabf3329745bdc15ee1dc31d4c7c01342ee8d7b63fd8452dccd39","schema_version":"1.0","event_id":"sha256:12d87465b6baabf3329745bdc15ee1dc31d4c7c01342ee8d7b63fd8452dccd39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/bundle.json","state_url":"https://pith.science/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T15:52:46Z","links":{"resolver":"https://pith.science/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW","bundle":"https://pith.science/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/bundle.json","state":"https://pith.science/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZPTJ74NCKE3C7SO3YYPNSCRAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HZPTJ74NCKE3C7SO3YYPNSCRAW","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":"1d70e995e96d0171cf81c5a68faa1c252f99d795bd86a3a5504bcdd470ab96d6","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T22:07:49Z","title_canon_sha256":"6b2871fbf08ef54bd10723d4c9875d1386e4bc923bbe809839575c3db6e11e59"},"schema_version":"1.0","source":{"id":"2502.12340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12340","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12340v1","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12340","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"HZPTJ74NCKE3","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"HZPTJ74NCKE3C7SO","created_at":"2026-07-05T10:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"HZPTJ74N","created_at":"2026-07-05T10:15:53Z"}],"graph_snapshots":[{"event_id":"sha256:12d87465b6baabf3329745bdc15ee1dc31d4c7c01342ee8d7b63fd8452dccd39","target":"graph","created_at":"2026-07-05T10:15:53Z","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/2502.12340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explicit failure signals. In this work, we are the first to investigate the impact of real-world SDCs on LLM training by comparing model training between healthy production nodes and unhealthy nodes exhibiting SDCs. With the help from a cloud computing platform, we access the unhealthy nodes that were swept out from production by automated fleet management. Using deterministic execution via XLA compiler and our proposed sy","authors_text":"George Karypis, Hengzhi Pei, Jeffrey Ma, Leonard Lausen","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T22:07:49Z","title":"Understanding Silent Data Corruption in LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12340","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":"sha256:7dc4e66bbf8b9c4939a4c72d2b71f4d056217618fa8aeb53d597d5857f72c61f","target":"record","created_at":"2026-07-05T10:15:53Z","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":"1d70e995e96d0171cf81c5a68faa1c252f99d795bd86a3a5504bcdd470ab96d6","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T22:07:49Z","title_canon_sha256":"6b2871fbf08ef54bd10723d4c9875d1386e4bc923bbe809839575c3db6e11e59"},"schema_version":"1.0","source":{"id":"2502.12340","kind":"arxiv","version":1}},"canonical_sha256":"3e5f34ff8d1289b17e4ede30f6c8510597641b5b7ac4a33227721aaefe05f40b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e5f34ff8d1289b17e4ede30f6c8510597641b5b7ac4a33227721aaefe05f40b","first_computed_at":"2026-07-05T10:15:53.788506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:53.788506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SlUyK4+yoVoGDFwPgHuLI0vcOEzaemc1Il/MH0lG+E9ehJ7c5Hg8/dDuRydbnvpfH/ozU701qjVWJ5R7CkYPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:53.788985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dc4e66bbf8b9c4939a4c72d2b71f4d056217618fa8aeb53d597d5857f72c61f","sha256:12d87465b6baabf3329745bdc15ee1dc31d4c7c01342ee8d7b63fd8452dccd39"],"state_sha256":"7e585de9926a323f63e94a942cb8e183ef222f735aaa8a9836445a695c785ed0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kyYs0Dr57dFojoNM4upnYT9LJ1rFjA3KvmH8SLAN1v2M/pRKhImgiIqwzYiwPZ/kbN9lCmkCkGVD9EpdIrClCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:52:46.752999Z","bundle_sha256":"1398b8016705b37dd5d2745ff7b6bc7022dfc9fed6e75a8671a747b9a78fb6e5"}}