{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3CD4KJ2TPNF6CIDIQECBSTRHFJ","short_pith_number":"pith:3CD4KJ2T","canonical_record":{"source":{"id":"2410.00161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:09:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a9ace2844c16e004362f0e067b6ac0265317481313a386f1ed17566c6403c0d","abstract_canon_sha256":"b7b4461cb4b89dd367bf5e225c262e96487533676820203eec725fb30cf87960"},"schema_version":"1.0"},"canonical_sha256":"d887c527537b4be120688104194e272a7d0c536c14c88cbadabd28801f276160","source":{"kind":"arxiv","id":"2410.00161","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00161","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00161v2","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00161","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"3CD4KJ2TPNF6","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"3CD4KJ2TPNF6CIDI","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"3CD4KJ2T","created_at":"2026-07-05T09:16:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3CD4KJ2TPNF6CIDIQECBSTRHFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:09:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a9ace2844c16e004362f0e067b6ac0265317481313a386f1ed17566c6403c0d","abstract_canon_sha256":"b7b4461cb4b89dd367bf5e225c262e96487533676820203eec725fb30cf87960"},"schema_version":"1.0"},"canonical_sha256":"d887c527537b4be120688104194e272a7d0c536c14c88cbadabd28801f276160","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:53.254877Z","signature_b64":"JRSDFtckQMCCm9RKmDwU20WT3pd/4etkJzGp2XxWOQFkEjT2rdcWlA8TiN4eZgDE6TSKLMBMF2EZkwvRqAUGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d887c527537b4be120688104194e272a7d0c536c14c88cbadabd28801f276160","last_reissued_at":"2026-07-05T09:16:53.254381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:53.254381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00161","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnoJyLOiYWibkgdsyf66QnibjEnQgAlWvHDLJv7e8S7PdOR25dzJXbgDWFTBrKJIRUUFlaejfoHTc4jfF2TvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:33:01.343881Z"},"content_sha256":"b8b8f2b56dc229c9678962fa84b187caf74bc61733d3d19f69f54157d809f528","schema_version":"1.0","event_id":"sha256:b8b8f2b56dc229c9678962fa84b187caf74bc61733d3d19f69f54157d809f528"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3CD4KJ2TPNF6CIDIQECBSTRHFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isaac Rehg","submitted_at":"2024-09-30T19:09:13Z","abstract_excerpt":"Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as the memory that must be allocated in key-value (KV) cache for a generation scales with its context length, limiting the number of long-context requests that can be served concurrently under a given memory budget. KV cache compression can mitigate this issue by removing under-utilized KVs from each attention head's cache and reducing its memory footprint. Highe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00161","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.00161/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08KiAP5yPn2/MNhRLqGaI1GCZhi2rGoUXx2Dm4/f3WPMKw4PWrZIIO4v35DCI+eHC1LoRCOCnyvFv4xoOHmbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:33:01.344371Z"},"content_sha256":"b09681dfbb4520225745abec49a04b0753cdc99fc5a07b756bbad322e90b3328","schema_version":"1.0","event_id":"sha256:b09681dfbb4520225745abec49a04b0753cdc99fc5a07b756bbad322e90b3328"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/bundle.json","state_url":"https://pith.science/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T08:33:01Z","links":{"resolver":"https://pith.science/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ","bundle":"https://pith.science/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/bundle.json","state":"https://pith.science/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CD4KJ2TPNF6CIDIQECBSTRHFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3CD4KJ2TPNF6CIDIQECBSTRHFJ","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":"b7b4461cb4b89dd367bf5e225c262e96487533676820203eec725fb30cf87960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:09:13Z","title_canon_sha256":"0a9ace2844c16e004362f0e067b6ac0265317481313a386f1ed17566c6403c0d"},"schema_version":"1.0","source":{"id":"2410.00161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00161","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00161v2","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00161","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"3CD4KJ2TPNF6","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"3CD4KJ2TPNF6CIDI","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"3CD4KJ2T","created_at":"2026-07-05T09:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:b09681dfbb4520225745abec49a04b0753cdc99fc5a07b756bbad322e90b3328","target":"graph","created_at":"2026-07-05T09:16:53Z","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/2410.00161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as the memory that must be allocated in key-value (KV) cache for a generation scales with its context length, limiting the number of long-context requests that can be served concurrently under a given memory budget. KV cache compression can mitigate this issue by removing under-utilized KVs from each attention head's cache and reducing its memory footprint. Highe","authors_text":"Isaac Rehg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:09:13Z","title":"KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00161","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:b8b8f2b56dc229c9678962fa84b187caf74bc61733d3d19f69f54157d809f528","target":"record","created_at":"2026-07-05T09:16:53Z","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":"b7b4461cb4b89dd367bf5e225c262e96487533676820203eec725fb30cf87960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T19:09:13Z","title_canon_sha256":"0a9ace2844c16e004362f0e067b6ac0265317481313a386f1ed17566c6403c0d"},"schema_version":"1.0","source":{"id":"2410.00161","kind":"arxiv","version":2}},"canonical_sha256":"d887c527537b4be120688104194e272a7d0c536c14c88cbadabd28801f276160","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d887c527537b4be120688104194e272a7d0c536c14c88cbadabd28801f276160","first_computed_at":"2026-07-05T09:16:53.254381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:53.254381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRSDFtckQMCCm9RKmDwU20WT3pd/4etkJzGp2XxWOQFkEjT2rdcWlA8TiN4eZgDE6TSKLMBMF2EZkwvRqAUGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:53.254877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8b8f2b56dc229c9678962fa84b187caf74bc61733d3d19f69f54157d809f528","sha256:b09681dfbb4520225745abec49a04b0753cdc99fc5a07b756bbad322e90b3328"],"state_sha256":"242572d7f3b9c3f3c6dea91d4a52eb6499b5ca787f5e1e2665c40802461d4841"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcSceYToNo8Of3lwc0EsIe2byeyUQow/v94Hubr0cV7VRAjqRQRiKRsR+WsgkjvDjUDovpUkldQzLJERbgF7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:33:01.347903Z","bundle_sha256":"465a80f29f6a8926d1290494f8cd4772f27ca801ad2deafe3728f8e84fc533cb"}}