{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R7RTDTYVTZOYCLBCTHRO3UHPUN","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":"219aaf5c8bbf3e116b2e942d92f9a8ee0b0c2e77c4561b5b4d543a4db2289afc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-08T14:35:40Z","title_canon_sha256":"e295cedbd614f7b9dd799eedc6414e5a9a1a68b6c48f14aa8d0ccad571708441"},"schema_version":"1.0","source":{"id":"2504.06095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06095","created_at":"2026-07-05T10:46:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06095v1","created_at":"2026-07-05T10:46:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06095","created_at":"2026-07-05T10:46:15Z"},{"alias_kind":"pith_short_12","alias_value":"R7RTDTYVTZOY","created_at":"2026-07-05T10:46:15Z"},{"alias_kind":"pith_short_16","alias_value":"R7RTDTYVTZOYCLBC","created_at":"2026-07-05T10:46:15Z"},{"alias_kind":"pith_short_8","alias_value":"R7RTDTYV","created_at":"2026-07-05T10:46:15Z"}],"graph_snapshots":[{"event_id":"sha256:bd5dd61866034d7c04b1ec55cdba78ddb8edd40cd42272a3888470e75519b8e3","target":"graph","created_at":"2026-07-05T10:46:15Z","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/2504.06095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM training is scaled up to 10Ks of GPUs by a mix of data-(DP) and model-parallel (MP) execution. Critical to achieving efficiency is tensor-parallel (TP; a form of MP) execution within tightly-coupled subsets of GPUs, referred to as a scale-up domain, and the larger the scale-up domain the better the performance. New datacenter architectures are emerging with more GPUs able to be tightly-coupled in a scale-up domain, such as moving from 8 GPUs to 72 GPUs connected via NVLink. Unfortunately, larger scale-up domains increase the blast-radius of failures, with a failure of single GPU potentiall","authors_text":"Ahmet Inci, Ankit More, Bhargava Gopireddy, Daiyaan Arfeen, Dheevatsa Mudigere, Gregory R. Ganger","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-08T14:35:40Z","title":"Nonuniform-Tensor-Parallelism: Mitigating GPU failure impact for Scaled-up LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06095","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:e96889fd372b72aa6951fb7a6ec3f113b6bb8a8e55e8741e9783b102ebe3e37c","target":"record","created_at":"2026-07-05T10:46:15Z","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":"219aaf5c8bbf3e116b2e942d92f9a8ee0b0c2e77c4561b5b4d543a4db2289afc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-08T14:35:40Z","title_canon_sha256":"e295cedbd614f7b9dd799eedc6414e5a9a1a68b6c48f14aa8d0ccad571708441"},"schema_version":"1.0","source":{"id":"2504.06095","kind":"arxiv","version":1}},"canonical_sha256":"8fe331cf159e5d812c2299e2edd0efa36a83973e370b18081c060e717d3eb57a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe331cf159e5d812c2299e2edd0efa36a83973e370b18081c060e717d3eb57a","first_computed_at":"2026-07-05T10:46:15.362498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:15.362498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcIP+4IZO6Xm52YOnHVYfDSP34OToMoCxrT3GeOCgNqFIDTZmToMGCgqcG2EJcC8W+FcEnCUouawTnU2P2bfDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:15.363084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e96889fd372b72aa6951fb7a6ec3f113b6bb8a8e55e8741e9783b102ebe3e37c","sha256:bd5dd61866034d7c04b1ec55cdba78ddb8edd40cd42272a3888470e75519b8e3"],"state_sha256":"16016f3bedbd22c1fd97379ca1f926ab674427669902fc6cc587742624b16a78"}