{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VAPVKBU4G4VCWCDQ7ZMMYO43IF","short_pith_number":"pith:VAPVKBU4","canonical_record":{"source":{"id":"2408.10197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-08-19T17:54:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d80436688c89d2f8f660df4522b0f69893e47d514f699a8084578a6ef13a5fd","abstract_canon_sha256":"d1b41527b058b04a3ef6851ab955ba8cb0eed89633fc446c00020c5c3f87baff"},"schema_version":"1.0"},"canonical_sha256":"a81f55069c372a2b0870fe58cc3b9b414db18ead2cf810c4e6a4e1ae7503815e","source":{"kind":"arxiv","id":"2408.10197","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10197","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10197v1","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10197","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"VAPVKBU4G4VC","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"VAPVKBU4G4VCWCDQ","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"VAPVKBU4","created_at":"2026-07-05T08:56:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VAPVKBU4G4VCWCDQ7ZMMYO43IF","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-08-19T17:54:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d80436688c89d2f8f660df4522b0f69893e47d514f699a8084578a6ef13a5fd","abstract_canon_sha256":"d1b41527b058b04a3ef6851ab955ba8cb0eed89633fc446c00020c5c3f87baff"},"schema_version":"1.0"},"canonical_sha256":"a81f55069c372a2b0870fe58cc3b9b414db18ead2cf810c4e6a4e1ae7503815e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:52.992377Z","signature_b64":"9wNJCNvxNcL2byTCvxmP8f9teLCtLl7tuXwT2tTuE/RVRpZdGk4zWaOUpEszFV7rhL0amdMW9O0moAkOknxJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a81f55069c372a2b0870fe58cc3b9b414db18ead2cf810c4e6a4e1ae7503815e","last_reissued_at":"2026-07-05T08:56:52.991909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:52.991909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10197","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":"2026-07-05T08:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nA+jGNVElM0yp19wCZ9SNbWy6/7FNXMbRj/3oqGY61j01gaW/VVcFADksu6G06M2A9h7vSxO2mZ4xkeL4Ai9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:15:18.455897Z"},"content_sha256":"a5e4ea687215360ac780e20759d0a3f64a8b9156df1d399ffb18b10376e978d4","schema_version":"1.0","event_id":"sha256:a5e4ea687215360ac780e20759d0a3f64a8b9156df1d399ffb18b10376e978d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VAPVKBU4G4VCWCDQ7ZMMYO43IF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demystifying the Communication Characteristics for Distributed Transformer Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Aamir Shafi, Benjamin Michalowicz, Dhabaleswar Panda, Hari Subramoni, Jacob Hatef, Lang Xu, Mustafa AbdulJabbar, Quentin Anthony","submitted_at":"2024-08-19T17:54:29Z","abstract_excerpt":"Deep learning (DL) models based on the transformer architecture have revolutionized many DL applications such as large language models (LLMs), vision transformers, audio generation, and time series prediction. Much of this progress has been fueled by distributed training, yet distributed communication remains a substantial bottleneck to training progress. This paper examines the communication behavior of transformer models - that is, how different parallelism schemes used in multi-node/multi-GPU DL Training communicate data in the context of transformers. We use GPT-based language models as a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10197","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/2408.10197/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":"2026-07-05T08:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sW4DMER9VDNYKnDCfediA6iPn1PEPs6y+ZEKpkn9ge6SpykMQas9NYNjdnwMoblSZsh07KEYnX3KK4VwqpcBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:15:18.456816Z"},"content_sha256":"65497874bf657b6a5594a3b839f4aa948f6cbf50eb751a0853f84273f107b380","schema_version":"1.0","event_id":"sha256:65497874bf657b6a5594a3b839f4aa948f6cbf50eb751a0853f84273f107b380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/bundle.json","state_url":"https://pith.science/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/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":"2026-08-22T11:15:18Z","links":{"resolver":"https://pith.science/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF","bundle":"https://pith.science/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/bundle.json","state":"https://pith.science/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VAPVKBU4G4VCWCDQ7ZMMYO43IF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VAPVKBU4G4VCWCDQ7ZMMYO43IF","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":"d1b41527b058b04a3ef6851ab955ba8cb0eed89633fc446c00020c5c3f87baff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-08-19T17:54:29Z","title_canon_sha256":"3d80436688c89d2f8f660df4522b0f69893e47d514f699a8084578a6ef13a5fd"},"schema_version":"1.0","source":{"id":"2408.10197","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10197","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10197v1","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10197","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"VAPVKBU4G4VC","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"VAPVKBU4G4VCWCDQ","created_at":"2026-07-05T08:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"VAPVKBU4","created_at":"2026-07-05T08:56:52Z"}],"graph_snapshots":[{"event_id":"sha256:65497874bf657b6a5594a3b839f4aa948f6cbf50eb751a0853f84273f107b380","target":"graph","created_at":"2026-07-05T08:56:52Z","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/2408.10197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning (DL) models based on the transformer architecture have revolutionized many DL applications such as large language models (LLMs), vision transformers, audio generation, and time series prediction. Much of this progress has been fueled by distributed training, yet distributed communication remains a substantial bottleneck to training progress. This paper examines the communication behavior of transformer models - that is, how different parallelism schemes used in multi-node/multi-GPU DL Training communicate data in the context of transformers. We use GPT-based language models as a ","authors_text":"Aamir Shafi, Benjamin Michalowicz, Dhabaleswar Panda, Hari Subramoni, Jacob Hatef, Lang Xu, Mustafa AbdulJabbar, Quentin Anthony","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-08-19T17:54:29Z","title":"Demystifying the Communication Characteristics for Distributed Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10197","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:a5e4ea687215360ac780e20759d0a3f64a8b9156df1d399ffb18b10376e978d4","target":"record","created_at":"2026-07-05T08:56:52Z","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":"d1b41527b058b04a3ef6851ab955ba8cb0eed89633fc446c00020c5c3f87baff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-08-19T17:54:29Z","title_canon_sha256":"3d80436688c89d2f8f660df4522b0f69893e47d514f699a8084578a6ef13a5fd"},"schema_version":"1.0","source":{"id":"2408.10197","kind":"arxiv","version":1}},"canonical_sha256":"a81f55069c372a2b0870fe58cc3b9b414db18ead2cf810c4e6a4e1ae7503815e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a81f55069c372a2b0870fe58cc3b9b414db18ead2cf810c4e6a4e1ae7503815e","first_computed_at":"2026-07-05T08:56:52.991909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:52.991909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wNJCNvxNcL2byTCvxmP8f9teLCtLl7tuXwT2tTuE/RVRpZdGk4zWaOUpEszFV7rhL0amdMW9O0moAkOknxJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:52.992377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10197","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5e4ea687215360ac780e20759d0a3f64a8b9156df1d399ffb18b10376e978d4","sha256:65497874bf657b6a5594a3b839f4aa948f6cbf50eb751a0853f84273f107b380"],"state_sha256":"b7a6f8c73198cc4f9e5164d964d7e43766fff05f3b02a5fdf0638e08be47d164"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25P+u1clPvhgoFWu02DLIli+45IGqYibjSm/dZa1mQzdtMHwt4ThqzGm7OEgaW9itIbsxqvG+TIviubKcZ8/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:15:18.462214Z","bundle_sha256":"a2f157ef3f6e8b7febf062c9a9af9afabc6650894e52b95469e0cd4b59ad8c25"}}