{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OEVV2BURLATLHK6V5IN6IJ6LLR","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":"a1a91aced1c5a39031c37e899a75ae26f5f21a35e6768f296523eb166a7a667a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-09T22:34:00Z","title_canon_sha256":"c4f44df06b469d96bf3b195577940d92e1f8c2c37e77cec9a9a0c156a925f847"},"schema_version":"1.0","source":{"id":"2607.08973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08973","created_at":"2026-07-13T00:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08973v1","created_at":"2026-07-13T00:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08973","created_at":"2026-07-13T00:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"OEVV2BURLATL","created_at":"2026-07-13T00:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"OEVV2BURLATLHK6V","created_at":"2026-07-13T00:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"OEVV2BUR","created_at":"2026-07-13T00:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:4aeb668548c2ba8586e311c3bc7f004354474f4640c2124c55792f4d51523aba","target":"graph","created_at":"2026-07-13T00:17:31Z","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/2607.08973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of reasoning models and agentic systems has made LLM token-generation latency a key bottleneck. Unlike chatbots, whose latency gains saturate at human reading speed, these systems generate intermediate reasoning tokens not consumed by humans. Thus, per-token latency directly determines end-to-end response time. Low-latency inference uses minimal batching, making token generation bandwidth-bound. Tensor Parallelism addresses this by sharding model weights across GPUs and loading them in parallel. However, scaling to more GPUs introduces All-Reduce overheads that grow with GPU count. Re","authors_text":"Abhishek Revinipati, Anish Saxena, Hritvik Taneja, Jae Hyung Ju, Moinuddin Qureshi, Neal C. Crago","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-09T22:34:00Z","title":"SiFAR: Synchronization-Free All-Reduce for Low-Latency LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08973","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:a0ba521936184d69963074353003f8e6fdb5c73d9c421ed934a25a4f5e048d16","target":"record","created_at":"2026-07-13T00:17:31Z","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":"a1a91aced1c5a39031c37e899a75ae26f5f21a35e6768f296523eb166a7a667a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-09T22:34:00Z","title_canon_sha256":"c4f44df06b469d96bf3b195577940d92e1f8c2c37e77cec9a9a0c156a925f847"},"schema_version":"1.0","source":{"id":"2607.08973","kind":"arxiv","version":1}},"canonical_sha256":"712b5d06915826b3abd5ea1be427cb5c4242327cc5f801e6a7da01603b623a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"712b5d06915826b3abd5ea1be427cb5c4242327cc5f801e6a7da01603b623a2d","first_computed_at":"2026-07-13T00:17:31.164024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:31.164024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jlvxJ9Ik0XMIiwSO/5EFngRrIKFFdilXtOwLLEebkkkbjyLCm0VzcDr3BQoqWjDCGtInILcaNwfnlcgNA2gLCw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:31.165850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0ba521936184d69963074353003f8e6fdb5c73d9c421ed934a25a4f5e048d16","sha256:4aeb668548c2ba8586e311c3bc7f004354474f4640c2124c55792f4d51523aba"],"state_sha256":"2c621a8b85a9216dfd64eda09526b64a3d4a96edc1f2931cc7e552f28e14689a"}