{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VQLUMH5CHINZYDROH5UJQCPR4K","short_pith_number":"pith:VQLUMH5C","canonical_record":{"source":{"id":"2405.02803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T03:25:25Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"dd347804ee438b44eaca5af1afce1dfff00a074bbff3d33b74820afdd4942343","abstract_canon_sha256":"2180d9772b3587805344c589ed7bee34757565dbc6c52e8987b689eb3a43d8b1"},"schema_version":"1.0"},"canonical_sha256":"ac17461fa23a1b9c0e2e3f689809f1e2a17c80139d4aaccfd2438d0fea655b97","source":{"kind":"arxiv","id":"2405.02803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02803","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02803v1","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02803","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"VQLUMH5CHINZ","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"VQLUMH5CHINZYDRO","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"VQLUMH5C","created_at":"2026-07-05T08:15:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VQLUMH5CHINZYDROH5UJQCPR4K","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T03:25:25Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"dd347804ee438b44eaca5af1afce1dfff00a074bbff3d33b74820afdd4942343","abstract_canon_sha256":"2180d9772b3587805344c589ed7bee34757565dbc6c52e8987b689eb3a43d8b1"},"schema_version":"1.0"},"canonical_sha256":"ac17461fa23a1b9c0e2e3f689809f1e2a17c80139d4aaccfd2438d0fea655b97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:54.059428Z","signature_b64":"KrD6QzxnCWXHcvcYJ9NKFPLKgLfuq68/uuhnRIidKoEA9zig8+Ydejnriuz9yCdPf8lM1WFHVNcNICJaRfERAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac17461fa23a1b9c0e2e3f689809f1e2a17c80139d4aaccfd2438d0fea655b97","last_reissued_at":"2026-07-05T08:15:54.059018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:54.059018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02803","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":"2026-07-05T08:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2uDfwKgn8lxSahL6axftMjG+bJ3KG6OVjL8AqdKGGwMBz7WxtudhPciGE/ypOJ+euN0F2FEonT6LcfM8UAaHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:28:17.835538Z"},"content_sha256":"79249bbba2b0ed75679b672b99e0d04777141def8899f2a87a417a76173248d8","schema_version":"1.0","event_id":"sha256:79249bbba2b0ed75679b672b99e0d04777141def8899f2a87a417a76173248d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VQLUMH5CHINZYDROH5UJQCPR4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Flash Attention Stable?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Alicia Golden, Basil Hosmer, Bilge Acun, Carole-Jean Wu, David Brooks, Fei Sun, Gu-Yeon Wei, Jeff Johnson, Samuel Hsia, Yejin Lee, Zachary DeVito","submitted_at":"2024-05-05T03:25:25Z","abstract_excerpt":"Training large-scale machine learning models poses distinct system challenges, given both the size and complexity of today's workloads. Recently, many organizations training state-of-the-art Generative AI models have reported cases of instability during training, often taking the form of loss spikes. Numeric deviation has emerged as a potential cause of this training instability, although quantifying this is especially challenging given the costly nature of training runs. In this work, we develop a principled approach to understanding the effects of numeric deviation, and construct proxies to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02803","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/2405.02803/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":"2026-07-05T08:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEaTQtJBfTl2p+2OYJzG8d9dlMCExvlDrkC5yTm3zmDFicjo3pH7L7ZWqhSt6VlxAD6EfefFFaZCfG65iwUDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:28:17.836479Z"},"content_sha256":"46007561bd180dbf5c0dc58540515eba3ff43c946addcad55cb3472c5d4b210b","schema_version":"1.0","event_id":"sha256:46007561bd180dbf5c0dc58540515eba3ff43c946addcad55cb3472c5d4b210b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQLUMH5CHINZYDROH5UJQCPR4K/bundle.json","state_url":"https://pith.science/pith/VQLUMH5CHINZYDROH5UJQCPR4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQLUMH5CHINZYDROH5UJQCPR4K/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":"2026-08-03T17:28:17Z","links":{"resolver":"https://pith.science/pith/VQLUMH5CHINZYDROH5UJQCPR4K","bundle":"https://pith.science/pith/VQLUMH5CHINZYDROH5UJQCPR4K/bundle.json","state":"https://pith.science/pith/VQLUMH5CHINZYDROH5UJQCPR4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQLUMH5CHINZYDROH5UJQCPR4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VQLUMH5CHINZYDROH5UJQCPR4K","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":"2180d9772b3587805344c589ed7bee34757565dbc6c52e8987b689eb3a43d8b1","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T03:25:25Z","title_canon_sha256":"dd347804ee438b44eaca5af1afce1dfff00a074bbff3d33b74820afdd4942343"},"schema_version":"1.0","source":{"id":"2405.02803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02803","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02803v1","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02803","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"VQLUMH5CHINZ","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"VQLUMH5CHINZYDRO","created_at":"2026-07-05T08:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"VQLUMH5C","created_at":"2026-07-05T08:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:46007561bd180dbf5c0dc58540515eba3ff43c946addcad55cb3472c5d4b210b","target":"graph","created_at":"2026-07-05T08:15:54Z","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/2405.02803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large-scale machine learning models poses distinct system challenges, given both the size and complexity of today's workloads. Recently, many organizations training state-of-the-art Generative AI models have reported cases of instability during training, often taking the form of loss spikes. Numeric deviation has emerged as a potential cause of this training instability, although quantifying this is especially challenging given the costly nature of training runs. In this work, we develop a principled approach to understanding the effects of numeric deviation, and construct proxies to ","authors_text":"Alicia Golden, Basil Hosmer, Bilge Acun, Carole-Jean Wu, David Brooks, Fei Sun, Gu-Yeon Wei, Jeff Johnson, Samuel Hsia, Yejin Lee, Zachary DeVito","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T03:25:25Z","title":"Is Flash Attention Stable?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02803","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":"sha256:79249bbba2b0ed75679b672b99e0d04777141def8899f2a87a417a76173248d8","target":"record","created_at":"2026-07-05T08:15:54Z","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":"2180d9772b3587805344c589ed7bee34757565dbc6c52e8987b689eb3a43d8b1","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T03:25:25Z","title_canon_sha256":"dd347804ee438b44eaca5af1afce1dfff00a074bbff3d33b74820afdd4942343"},"schema_version":"1.0","source":{"id":"2405.02803","kind":"arxiv","version":1}},"canonical_sha256":"ac17461fa23a1b9c0e2e3f689809f1e2a17c80139d4aaccfd2438d0fea655b97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac17461fa23a1b9c0e2e3f689809f1e2a17c80139d4aaccfd2438d0fea655b97","first_computed_at":"2026-07-05T08:15:54.059018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:54.059018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrD6QzxnCWXHcvcYJ9NKFPLKgLfuq68/uuhnRIidKoEA9zig8+Ydejnriuz9yCdPf8lM1WFHVNcNICJaRfERAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:54.059428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79249bbba2b0ed75679b672b99e0d04777141def8899f2a87a417a76173248d8","sha256:46007561bd180dbf5c0dc58540515eba3ff43c946addcad55cb3472c5d4b210b"],"state_sha256":"e6e002fe59dad3ac19a881fd19f03755b37bf31368c6c2fe752f98480738920f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQIojhmI1dkmDfwJnsL2OJ3nMZc/aWSoiEGxwdV1fKTAIVRkEF2NPxmN+zTZhJrKbU5/0KOLr0H1W8rfU4qyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:28:17.844758Z","bundle_sha256":"07e1880589b3cedc9a892587e1c1ae2441425e6143c3c70459baccba4485c16a"}}