{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F4VYGMQNU5MSRC7FXO2VTWK5CP","short_pith_number":"pith:F4VYGMQN","canonical_record":{"source":{"id":"2402.02447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T11:12:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"16773ec5edad85315bccd3b3a4eb1158576df7e080022be3f1eab725a8f89758","abstract_canon_sha256":"313cf639aa45f73187b8e19f50224502f547dfe14de77f4352b19d721e655971"},"schema_version":"1.0"},"canonical_sha256":"2f2b83320da759288be5bbb559d95d13e265318a124a812280e03ac3ff988db3","source":{"kind":"arxiv","id":"2402.02447","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02447","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02447v1","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02447","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"F4VYGMQNU5MS","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"F4VYGMQNU5MSRC7F","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"F4VYGMQN","created_at":"2026-07-05T07:41:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F4VYGMQNU5MSRC7FXO2VTWK5CP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T11:12:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"16773ec5edad85315bccd3b3a4eb1158576df7e080022be3f1eab725a8f89758","abstract_canon_sha256":"313cf639aa45f73187b8e19f50224502f547dfe14de77f4352b19d721e655971"},"schema_version":"1.0"},"canonical_sha256":"2f2b83320da759288be5bbb559d95d13e265318a124a812280e03ac3ff988db3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:14.399592Z","signature_b64":"eI5guVPA9uOwMkw26F5bU3SPucD3X17M6EBYFYNFcVKzqtkV6S1JMUUA2krPXb8eKTKXcCcA85G3Zzbe6J/aCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f2b83320da759288be5bbb559d95d13e265318a124a812280e03ac3ff988db3","last_reissued_at":"2026-07-05T07:41:14.399172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:14.399172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02447","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":"2026-07-05T07:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLeWmnRRDKXq/iYOWcxxjcqvkp/uFaik6Yxe2FMvOUsdjEVXGxQ0KnSAtNmldtg5SvS5L2i2y7WPJJVAsU8MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:40:09.948973Z"},"content_sha256":"1b501a9e33e0fe7d69ff030cb2d12d4595fa9906781d20d8fd6a00a54bc9607b","schema_version":"1.0","event_id":"sha256:1b501a9e33e0fe7d69ff030cb2d12d4595fa9906781d20d8fd6a00a54bc9607b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F4VYGMQNU5MSRC7FXO2VTWK5CP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking MLPerf Training: A Case Study on Optimizing BERT","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Changin Choi, Heejae Kim, Jaehyung Ahn, Jingkun Ma, Lin Chen, Myeongwoo Kim, Narankhuu Tuvshinjargal, Seungwon Lee, Sungjoo Yoo, Xiongzhan Linghu, Yanzi Zhang, Yongdeok Kim, Yuan Pei, Yuehua Dai","submitted_at":"2024-02-04T11:12:17Z","abstract_excerpt":"Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, etc. We present novel approaches for fast large-scale training of BERT model which individually ameliorates each component thereby leading to a new level of BERT training performance. Load balancing is imperative in distributed BERT training since its training datasets are characterized by samples with various lengths. Communication cost, which is proportional to the scale of distributed training, needs to be hidden by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02447","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/2402.02447/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":"2026-07-05T07:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIXIAWnt5s0Vot4hEWiUcXzCp93vNnMHdasT28j9mvDM3f69wdAVaWukqw9tZIBHDi7fTIA1mVIj7xbrjP4GCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:40:09.949537Z"},"content_sha256":"962b750f83f16843d1f14ee2c77ce9a0f569c98fa5ceeb9bf36e831f90cffd52","schema_version":"1.0","event_id":"sha256:962b750f83f16843d1f14ee2c77ce9a0f569c98fa5ceeb9bf36e831f90cffd52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/bundle.json","state_url":"https://pith.science/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/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":"2026-08-14T22:40:09Z","links":{"resolver":"https://pith.science/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP","bundle":"https://pith.science/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/bundle.json","state":"https://pith.science/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4VYGMQNU5MSRC7FXO2VTWK5CP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4VYGMQNU5MSRC7FXO2VTWK5CP","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":"313cf639aa45f73187b8e19f50224502f547dfe14de77f4352b19d721e655971","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T11:12:17Z","title_canon_sha256":"16773ec5edad85315bccd3b3a4eb1158576df7e080022be3f1eab725a8f89758"},"schema_version":"1.0","source":{"id":"2402.02447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02447","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02447v1","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02447","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"F4VYGMQNU5MS","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"F4VYGMQNU5MSRC7F","created_at":"2026-07-05T07:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"F4VYGMQN","created_at":"2026-07-05T07:41:14Z"}],"graph_snapshots":[{"event_id":"sha256:962b750f83f16843d1f14ee2c77ce9a0f569c98fa5ceeb9bf36e831f90cffd52","target":"graph","created_at":"2026-07-05T07:41:14Z","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/2402.02447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, etc. We present novel approaches for fast large-scale training of BERT model which individually ameliorates each component thereby leading to a new level of BERT training performance. Load balancing is imperative in distributed BERT training since its training datasets are characterized by samples with various lengths. Communication cost, which is proportional to the scale of distributed training, needs to be hidden by","authors_text":"Changin Choi, Heejae Kim, Jaehyung Ahn, Jingkun Ma, Lin Chen, Myeongwoo Kim, Narankhuu Tuvshinjargal, Seungwon Lee, Sungjoo Yoo, Xiongzhan Linghu, Yanzi Zhang, Yongdeok Kim, Yuan Pei, Yuehua Dai","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T11:12:17Z","title":"Breaking MLPerf Training: A Case Study on Optimizing BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02447","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":"sha256:1b501a9e33e0fe7d69ff030cb2d12d4595fa9906781d20d8fd6a00a54bc9607b","target":"record","created_at":"2026-07-05T07:41:14Z","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":"313cf639aa45f73187b8e19f50224502f547dfe14de77f4352b19d721e655971","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-04T11:12:17Z","title_canon_sha256":"16773ec5edad85315bccd3b3a4eb1158576df7e080022be3f1eab725a8f89758"},"schema_version":"1.0","source":{"id":"2402.02447","kind":"arxiv","version":1}},"canonical_sha256":"2f2b83320da759288be5bbb559d95d13e265318a124a812280e03ac3ff988db3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f2b83320da759288be5bbb559d95d13e265318a124a812280e03ac3ff988db3","first_computed_at":"2026-07-05T07:41:14.399172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:14.399172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eI5guVPA9uOwMkw26F5bU3SPucD3X17M6EBYFYNFcVKzqtkV6S1JMUUA2krPXb8eKTKXcCcA85G3Zzbe6J/aCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:14.399592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b501a9e33e0fe7d69ff030cb2d12d4595fa9906781d20d8fd6a00a54bc9607b","sha256:962b750f83f16843d1f14ee2c77ce9a0f569c98fa5ceeb9bf36e831f90cffd52"],"state_sha256":"075498844f8b048f13c2a23addd1a23839a3ef104d877d47988afd77e6ad0d0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+u2hZFz1pBhzrtFJOoWtuxTrlKT17sxl18eKA6Oh9uy9PNduqTjPSBcf/5o2hECubYjRkzXktfI45MVMImz7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:40:09.953792Z","bundle_sha256":"39827f152812cf916337fd8f4ddff4bbb3162473ac8e36b36b0f2e8796e85119"}}