{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O2Q6VE6IPXBFTEJ2KWZR664MM3","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":"434cf4dcd16600e574c4876310f49613dc4ec2d9b0014666ac3e08199ece6058","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T23:01:02Z","title_canon_sha256":"97f51caa7359f692ee229bb3f1704255052b13215bccb09d172eac0b47b4d341"},"schema_version":"1.0","source":{"id":"2311.09431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09431","created_at":"2026-07-05T07:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09431v1","created_at":"2026-07-05T07:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09431","created_at":"2026-07-05T07:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"O2Q6VE6IPXBF","created_at":"2026-07-05T07:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"O2Q6VE6IPXBFTEJ2","created_at":"2026-07-05T07:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"O2Q6VE6I","created_at":"2026-07-05T07:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:550c8912f95c77e203e02fd4abf38c66c4dacab237689bd187b4f2addfa4fa76","target":"graph","created_at":"2026-07-05T07:13:27Z","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/2311.09431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of overcoming per-device memory bottle- necks by distributing self-attention across multiple devices. In this paper, we study the performance characteristics of Ring Attention in the important special case of causal transformer models, and identify a key workload imbal- ance due to triangular structure of causal attention computations. We propose a simple extension to Ring Attention, which we call Striped Attention to fix t","authors_text":"Aniruddha Nrusimha, Jonathan Ragan-Kelley, Kevin Qian, Tian Jin, William Brandon, Zachary Ankner, Zhiye Song","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T23:01:02Z","title":"Striped Attention: Faster Ring Attention for Causal Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09431","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":"sha256:5f4f02d4c9ea1ce8015be674e9157b06383c4c79db051a968c15447588e20e2d","target":"record","created_at":"2026-07-05T07:13:27Z","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":"434cf4dcd16600e574c4876310f49613dc4ec2d9b0014666ac3e08199ece6058","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T23:01:02Z","title_canon_sha256":"97f51caa7359f692ee229bb3f1704255052b13215bccb09d172eac0b47b4d341"},"schema_version":"1.0","source":{"id":"2311.09431","kind":"arxiv","version":1}},"canonical_sha256":"76a1ea93c87dc259913a55b31f7b8c66c8db14a24243c3af654f71309de5fba4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76a1ea93c87dc259913a55b31f7b8c66c8db14a24243c3af654f71309de5fba4","first_computed_at":"2026-07-05T07:13:27.911045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:27.911045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QeTeNfTBmhzIepa/w+OaYnXGnZc2aEqBlBEAK1lbnEJKKbfp5giIuULB6F6dNUxP7m+1K2od4di5jgH0xZa7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:27.911669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f4f02d4c9ea1ce8015be674e9157b06383c4c79db051a968c15447588e20e2d","sha256:550c8912f95c77e203e02fd4abf38c66c4dacab237689bd187b4f2addfa4fa76"],"state_sha256":"610e3c2c950f1bd8699d12a613ef804ff2ca20d9a7de070a24b1f24d4a19d25e"}