{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z5C2UCO7VZKO4BBTFM7G6KCDIP","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":"32baeeb6922a57bae1d4ce0d48508045ab9661ccfb8922e57961db1e7061ccff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-07-16T01:32:31Z","title_canon_sha256":"9684e498fb62c3c491ebcde34b48a502cd66d7d56f36abcecb9dd861cde5c3c9"},"schema_version":"1.0","source":{"id":"2507.11830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.11830","created_at":"2026-07-05T11:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.11830v1","created_at":"2026-07-05T11:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11830","created_at":"2026-07-05T11:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"Z5C2UCO7VZKO","created_at":"2026-07-05T11:37:51Z"},{"alias_kind":"pith_short_16","alias_value":"Z5C2UCO7VZKO4BBT","created_at":"2026-07-05T11:37:51Z"},{"alias_kind":"pith_short_8","alias_value":"Z5C2UCO7","created_at":"2026-07-05T11:37:51Z"}],"graph_snapshots":[{"event_id":"sha256:aad0076935f9292f718fc432e459230824dacbe43ab674fd80a6893581e6db1f","target":"graph","created_at":"2026-07-05T11:37:51Z","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/2507.11830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference is now the dominant AI workload, yet existing systems force trade-offs between latency, throughput, and cost. Arctic Inference, an open-source vLLM plugin from Snowflake AI Research, introduces Shift Parallelism, a dynamic parallelism strategy that adapts to real-world traffic while integrating speculative decoding, SwiftKV compute reduction, and optimized embedding inference. It achieves up to 3.4 times faster request completion, 1.75 times faster generation, and 1.6M tokens/sec per GPU for embeddings, outperforming both latency- and throughput-optimized deployments. Already powerin","authors_text":"Aurick Qiao, Jeff Rasley, Juncheng Yang, Mert Hidayetoglu, Michael Wyatt, Samyam Rajbhandari, Ye Wang, Yuxiong He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-07-16T01:32:31Z","title":"Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11830","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":"sha256:99539437afe83d9502fc2f937f886016b3b58a094962cb4211b7a348daf52f9e","target":"record","created_at":"2026-07-05T11:37:51Z","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":"32baeeb6922a57bae1d4ce0d48508045ab9661ccfb8922e57961db1e7061ccff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-07-16T01:32:31Z","title_canon_sha256":"9684e498fb62c3c491ebcde34b48a502cd66d7d56f36abcecb9dd861cde5c3c9"},"schema_version":"1.0","source":{"id":"2507.11830","kind":"arxiv","version":1}},"canonical_sha256":"cf45aa09dfae54ee04332b3e6f284343eba24067b842bdae4a7b6834dd8bf3c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf45aa09dfae54ee04332b3e6f284343eba24067b842bdae4a7b6834dd8bf3c2","first_computed_at":"2026-07-05T11:37:51.658165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:51.658165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZLcjKPxlRvgrpLjeiXrFre+WnWwHTuQZkkEBWG8wQHNIItlbuUz2gios6XXUUQAnyS67TFsapAc1dfYckrkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:51.658657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.11830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99539437afe83d9502fc2f937f886016b3b58a094962cb4211b7a348daf52f9e","sha256:aad0076935f9292f718fc432e459230824dacbe43ab674fd80a6893581e6db1f"],"state_sha256":"711cc767c04481040fd0a7bbd6333d019ef8eba0e6c825027ea27ad4b864b1a6"}