{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TULFDY5NNTRN6MMYSQLHZQPX3V","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":"450cd49672b36ebc35074691d8e863ff8384c19eb131a951c679d07c79bb3fbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T17:50:11Z","title_canon_sha256":"66e984959dc596d00fc3068e6d706246fbd1b2fe95d3d54b31e008ff798194ca"},"schema_version":"1.0","source":{"id":"2506.18879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18879","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18879v1","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18879","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_12","alias_value":"TULFDY5NNTRN","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_16","alias_value":"TULFDY5NNTRN6MMY","created_at":"2026-07-05T11:25:57Z"},{"alias_kind":"pith_short_8","alias_value":"TULFDY5N","created_at":"2026-07-05T11:25:57Z"}],"graph_snapshots":[{"event_id":"sha256:70de2dead2c064db1254faf7d51cc9430aea99042696aefffccbb4a762703c25","target":"graph","created_at":"2026-07-05T11:25:57Z","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/2506.18879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector Quantization (CommVQ) to significantly reduce memory usage for long-context LLM inference. We first introduce additive quantization with a lightweight encoder and codebook to compress the KV cache, which can be decoded via simple matrix multiplication. To further reduce computational costs during decoding, we design the codebook to be commutative with Rotary Posi","authors_text":"Chong Wang, Chuang Gan, Colorado Reed, Foroozan Karimzadeh, Junyan Li, Muhammad Yusuf Hassan, Pengsheng Guo, Talha Chafekar, Tianle Cai, Yang Zhang, Zhile Ren","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T17:50:11Z","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18879","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":"sha256:3ae5464bdce653d889585fbdd7255a255d98ccf96dfe52179b6dbe7a178c7749","target":"record","created_at":"2026-07-05T11:25:57Z","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":"450cd49672b36ebc35074691d8e863ff8384c19eb131a951c679d07c79bb3fbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T17:50:11Z","title_canon_sha256":"66e984959dc596d00fc3068e6d706246fbd1b2fe95d3d54b31e008ff798194ca"},"schema_version":"1.0","source":{"id":"2506.18879","kind":"arxiv","version":1}},"canonical_sha256":"9d1651e3ad6ce2df319894167cc1f7dd4d366ebe09b10ca359cddcccf8d859d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d1651e3ad6ce2df319894167cc1f7dd4d366ebe09b10ca359cddcccf8d859d3","first_computed_at":"2026-07-05T11:25:57.425036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:57.425036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kT4CrhtYO/2eudxVGhL/n2nqbpLWlBwS75NLdbDqeArz48FciF7PYZ0NSETIZowP3EtA4ZA18sd8Vdee+vr6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:57.425520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae5464bdce653d889585fbdd7255a255d98ccf96dfe52179b6dbe7a178c7749","sha256:70de2dead2c064db1254faf7d51cc9430aea99042696aefffccbb4a762703c25"],"state_sha256":"cb5504ea177a086dea5aed10f3453b42fbf05e9f6e4eb260dd9a5467d62c6ecf"}