{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V5TJCKKIQ4ZI5ITRFL73YGNPUQ","short_pith_number":"pith:V5TJCKKI","canonical_record":{"source":{"id":"2501.04266","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-08T04:19:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc0422543c7b698708b542d44ad59323afce8daf81e9fd3987eebac8cd210e1d","abstract_canon_sha256":"1e9cdf2f73b718908712cbaa3af2d5495ccedf74f71db4bac08bc7a34563c524"},"schema_version":"1.0"},"canonical_sha256":"af6691294887328ea2712affbc19afa40251c9a1501307a089528a51bc334b57","source":{"kind":"arxiv","id":"2501.04266","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04266","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04266v2","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04266","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"V5TJCKKIQ4ZI","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"V5TJCKKIQ4ZI5ITR","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"V5TJCKKI","created_at":"2026-07-05T10:09:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V5TJCKKIQ4ZI5ITRFL73YGNPUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04266","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-08T04:19:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc0422543c7b698708b542d44ad59323afce8daf81e9fd3987eebac8cd210e1d","abstract_canon_sha256":"1e9cdf2f73b718908712cbaa3af2d5495ccedf74f71db4bac08bc7a34563c524"},"schema_version":"1.0"},"canonical_sha256":"af6691294887328ea2712affbc19afa40251c9a1501307a089528a51bc334b57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:14.630332Z","signature_b64":"tejzBmvCvZMgZPa7sDeWf95rxJIJISCYUE0zBzd+/WT2Lm+eRJDPqMxtJB3rtS8CB6cjeHEiPsUhv7dKDRJGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af6691294887328ea2712affbc19afa40251c9a1501307a089528a51bc334b57","last_reissued_at":"2026-07-05T10:09:14.629836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:14.629836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04266","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OX6rHF2GHGi5EKeHLkfJqS+RzUFM+FlYjbkrdf+KFk/Ga4swOPTTRH+reQfN6O7smpScNXlNLB6OVm0RRHCdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:24:53.362488Z"},"content_sha256":"6089df5115a71b5430784e48a614a0e143a690bc9d272de0950da03ef073ecdc","schema_version":"1.0","event_id":"sha256:6089df5115a71b5430784e48a614a0e143a690bc9d272de0950da03ef073ecdc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V5TJCKKIQ4ZI5ITRFL73YGNPUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Aamir Shafi, Dhabaleswar K. (DK) Panda, Hari Subramoni, Jacob Hatef, Lang Xu, Quentin Anthony","submitted_at":"2025-01-08T04:19:57Z","abstract_excerpt":"Scaling up Large Language Model(LLM) training involves fitting a tremendous amount of training parameters across a limited number of workers. However, methods like ZeRO-3 that drastically reduce GPU memory pressure often incur heavy communication to ensure global synchronization and consistency. Established efforts such as ZeRO++ use secondary partitions to avoid inter-node communications, given that intra-node GPU-GPU transfer generally has more bandwidth and lower latency than inter-node connections. However, as more capable infrastructure like Frontier, equipped with AMD GPUs, emerged with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04266","kind":"arxiv","version":2},"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/2501.04266/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":"2026-07-05T10:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rkiH7jJtwXjGRyCWIxHZFPOCl/GVd/nNC+A/IRgB0gW4Jd/Bq1BSMID4WYkwGFDKnwBymiO8vpYhNMmPs2sDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:24:53.363428Z"},"content_sha256":"b80ae8c49267b581c73302575696aa1ff3fc911af206cf304db3e1b1ff298f31","schema_version":"1.0","event_id":"sha256:b80ae8c49267b581c73302575696aa1ff3fc911af206cf304db3e1b1ff298f31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/bundle.json","state_url":"https://pith.science/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/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":"2026-08-11T08:24:53Z","links":{"resolver":"https://pith.science/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ","bundle":"https://pith.science/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/bundle.json","state":"https://pith.science/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5TJCKKIQ4ZI5ITRFL73YGNPUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V5TJCKKIQ4ZI5ITRFL73YGNPUQ","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":"1e9cdf2f73b718908712cbaa3af2d5495ccedf74f71db4bac08bc7a34563c524","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-08T04:19:57Z","title_canon_sha256":"dc0422543c7b698708b542d44ad59323afce8daf81e9fd3987eebac8cd210e1d"},"schema_version":"1.0","source":{"id":"2501.04266","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04266","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04266v2","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04266","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"V5TJCKKIQ4ZI","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"V5TJCKKIQ4ZI5ITR","created_at":"2026-07-05T10:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"V5TJCKKI","created_at":"2026-07-05T10:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:b80ae8c49267b581c73302575696aa1ff3fc911af206cf304db3e1b1ff298f31","target":"graph","created_at":"2026-07-05T10:09:14Z","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/2501.04266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up Large Language Model(LLM) training involves fitting a tremendous amount of training parameters across a limited number of workers. However, methods like ZeRO-3 that drastically reduce GPU memory pressure often incur heavy communication to ensure global synchronization and consistency. Established efforts such as ZeRO++ use secondary partitions to avoid inter-node communications, given that intra-node GPU-GPU transfer generally has more bandwidth and lower latency than inter-node connections. However, as more capable infrastructure like Frontier, equipped with AMD GPUs, emerged with ","authors_text":"Aamir Shafi, Dhabaleswar K. (DK) Panda, Hari Subramoni, Jacob Hatef, Lang Xu, Quentin Anthony","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-08T04:19:57Z","title":"Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04266","kind":"arxiv","version":2},"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":"sha256:6089df5115a71b5430784e48a614a0e143a690bc9d272de0950da03ef073ecdc","target":"record","created_at":"2026-07-05T10:09:14Z","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":"1e9cdf2f73b718908712cbaa3af2d5495ccedf74f71db4bac08bc7a34563c524","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-01-08T04:19:57Z","title_canon_sha256":"dc0422543c7b698708b542d44ad59323afce8daf81e9fd3987eebac8cd210e1d"},"schema_version":"1.0","source":{"id":"2501.04266","kind":"arxiv","version":2}},"canonical_sha256":"af6691294887328ea2712affbc19afa40251c9a1501307a089528a51bc334b57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af6691294887328ea2712affbc19afa40251c9a1501307a089528a51bc334b57","first_computed_at":"2026-07-05T10:09:14.629836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:14.629836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tejzBmvCvZMgZPa7sDeWf95rxJIJISCYUE0zBzd+/WT2Lm+eRJDPqMxtJB3rtS8CB6cjeHEiPsUhv7dKDRJGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:14.630332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04266","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6089df5115a71b5430784e48a614a0e143a690bc9d272de0950da03ef073ecdc","sha256:b80ae8c49267b581c73302575696aa1ff3fc911af206cf304db3e1b1ff298f31"],"state_sha256":"9a07d79e6625c23080e46b4c5c1a47c94f5f2f90ffd82bf0f7dca073936861f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qAWLbLtIF2CIUIURF4w8FmyF7ByfJ7hr8AZRIDI8lcBlp/6eRDPUDWGQJN8slDFjTRg0AZHbWkMwaEV0nfhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:24:53.370462Z","bundle_sha256":"af568cdb9f0409d4983defc3a8cd5a76cbd5e55dcc966f761037dd072c863b59"}}