{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EZMF6WORHUDHROLVUD7M4ITYVG","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":"2b090e273cc3624194b511ed4645f47102c242cdb7c9ba4bbbcddaa545471ee0","cross_cats_sorted":["cs.AI","cs.CL","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T17:42:05Z","title_canon_sha256":"d3bd00ea3b46ecba46b9413ddc3898e86beed77fbd1dc6eba98eda4dd2df2cf2"},"schema_version":"1.0","source":{"id":"2406.03482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03482","created_at":"2026-07-05T08:45:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03482v2","created_at":"2026-07-05T08:45:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03482","created_at":"2026-07-05T08:45:29Z"},{"alias_kind":"pith_short_12","alias_value":"EZMF6WORHUDH","created_at":"2026-07-05T08:45:29Z"},{"alias_kind":"pith_short_16","alias_value":"EZMF6WORHUDHROLV","created_at":"2026-07-05T08:45:29Z"},{"alias_kind":"pith_short_8","alias_value":"EZMF6WOR","created_at":"2026-07-05T08:45:29Z"}],"graph_snapshots":[{"event_id":"sha256:d1004ec511e7f53db1ad3530c614f43b4cde955e9b9747b4ec05ca8cc5c4b68e","target":"graph","created_at":"2026-07-05T08:45:29Z","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/2406.03482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional quantization methods face significant memory overhead due to the need to store quantization constants (at least a zero point and a scale) in full precision per data block. Depending on the block size, this overhead can add 1 or 2 bits per quantized number. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss (JL) transform followe","authors_text":"Amir Zandieh, Insu Han, Majid Daliri","cross_cats":["cs.AI","cs.CL","cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T17:42:05Z","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03482","kind":"arxiv","version":2},"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":"sha256:49b96cff516821d2165c61e9461cb81940a6d34d07bda6cf9f017b529ad58708","target":"record","created_at":"2026-07-05T08:45:29Z","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":"2b090e273cc3624194b511ed4645f47102c242cdb7c9ba4bbbcddaa545471ee0","cross_cats_sorted":["cs.AI","cs.CL","cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T17:42:05Z","title_canon_sha256":"d3bd00ea3b46ecba46b9413ddc3898e86beed77fbd1dc6eba98eda4dd2df2cf2"},"schema_version":"1.0","source":{"id":"2406.03482","kind":"arxiv","version":2}},"canonical_sha256":"26585f59d13d0678b975a0fece2278a99b46ea51744f1f435096eaac32dd8368","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26585f59d13d0678b975a0fece2278a99b46ea51744f1f435096eaac32dd8368","first_computed_at":"2026-07-05T08:45:29.300979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:29.300979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzTCrANZ9uCCcMf6JC7gBjUjS+liJpBFxvvR7NOVmyiGLaufR0FzzTuqoi4JrHtebJkUYOVgaY4Z5PB9dnq8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:29.301399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49b96cff516821d2165c61e9461cb81940a6d34d07bda6cf9f017b529ad58708","sha256:d1004ec511e7f53db1ad3530c614f43b4cde955e9b9747b4ec05ca8cc5c4b68e"],"state_sha256":"035633dbeb5e46002b7df5ab9b41cfe0d8d997dfe2e0cd94a9dc27eb49891536"}