{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LSPXIHOAWBYYTAVPBOGNFXDVPE","short_pith_number":"pith:LSPXIHOA","canonical_record":{"source":{"id":"2402.18096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T06:34:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"010bbfadad32b71b0396bfdba5695a164c3265c1ee4863f33e4a438500a796d4","abstract_canon_sha256":"d78e6b7c0fc7f75315e6de9ed0c65ac6e8cf0fc435aeda1a245caed04fd820d7"},"schema_version":"1.0"},"canonical_sha256":"5c9f741dc0b0718982af0b8cd2dc75792d6a3594b43fcb8e98e874e80ad5d47e","source":{"kind":"arxiv","id":"2402.18096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18096","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18096v1","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18096","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"LSPXIHOAWBYY","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"LSPXIHOAWBYYTAVP","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"LSPXIHOA","created_at":"2026-07-05T07:50:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LSPXIHOAWBYYTAVPBOGNFXDVPE","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T06:34:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"010bbfadad32b71b0396bfdba5695a164c3265c1ee4863f33e4a438500a796d4","abstract_canon_sha256":"d78e6b7c0fc7f75315e6de9ed0c65ac6e8cf0fc435aeda1a245caed04fd820d7"},"schema_version":"1.0"},"canonical_sha256":"5c9f741dc0b0718982af0b8cd2dc75792d6a3594b43fcb8e98e874e80ad5d47e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:12.292162Z","signature_b64":"TscoTGBt8wCvRo6Kk+3X3wFkfIvQxaGJMc7xwgIW5JhtRpnf7zOrnZSakVAnvsRRt7Bpf5pZM31EGV46G9/hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c9f741dc0b0718982af0b8cd2dc75792d6a3594b43fcb8e98e874e80ad5d47e","last_reissued_at":"2026-07-05T07:50:12.291562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:12.291562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18096","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qahISPjIOjKykKXU+uYXGdkqfOaZe2IJEd3nau8HPKutKUAdJvSlSbakasIogzvBrMMwdkLM/olAQ1VziDMyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:47.781540Z"},"content_sha256":"cb4a6dcd9d6e85a0bd0e01a0add80abe9b220aa3d38fcad6cea6d8a561f2e780","schema_version":"1.0","event_id":"sha256:cb4a6dcd9d6e85a0bd0e01a0add80abe9b220aa3d38fcad6cea6d8a561f2e780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LSPXIHOAWBYYTAVPBOGNFXDVPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beomseok Kwon, Byeongwook Kim, Dongsoo Lee, Eunho Yang, Gunho Park, Jeongin Bae, June Yong Yang, Se Jung Kwon","submitted_at":"2024-02-28T06:34:54Z","abstract_excerpt":"Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM deployment as the cache size grows with batch size and sequence length, often surpassing even the size of the model itself. Although recent methods were proposed to select and evict unimportant KV pairs from the cache to reduce memory consumption, the potential ramifications of eviction on the generative process are yet to be thoroughly examined. In this paper, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18096","kind":"arxiv","version":1},"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/2402.18096/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":"2026-07-05T07:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IP3S2bhwL4ysg3ju7cTpVyu+CeMeyTYN0YqMvK0bd3Ghd4CJ0CESmVo454CIvt6+4sxsZQeR8ozbTya3u3WtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:18:47.781926Z"},"content_sha256":"163e2e5a75e3bab43d4f6b2d1e808a78e8de68fc48f5feb2d16bfcf28a980177","schema_version":"1.0","event_id":"sha256:163e2e5a75e3bab43d4f6b2d1e808a78e8de68fc48f5feb2d16bfcf28a980177"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/bundle.json","state_url":"https://pith.science/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/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":"2026-07-06T23:18:47Z","links":{"resolver":"https://pith.science/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE","bundle":"https://pith.science/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/bundle.json","state":"https://pith.science/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSPXIHOAWBYYTAVPBOGNFXDVPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LSPXIHOAWBYYTAVPBOGNFXDVPE","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":"d78e6b7c0fc7f75315e6de9ed0c65ac6e8cf0fc435aeda1a245caed04fd820d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T06:34:54Z","title_canon_sha256":"010bbfadad32b71b0396bfdba5695a164c3265c1ee4863f33e4a438500a796d4"},"schema_version":"1.0","source":{"id":"2402.18096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18096","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18096v1","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18096","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"LSPXIHOAWBYY","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"LSPXIHOAWBYYTAVP","created_at":"2026-07-05T07:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"LSPXIHOA","created_at":"2026-07-05T07:50:12Z"}],"graph_snapshots":[{"event_id":"sha256:163e2e5a75e3bab43d4f6b2d1e808a78e8de68fc48f5feb2d16bfcf28a980177","target":"graph","created_at":"2026-07-05T07:50:12Z","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/2402.18096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM deployment as the cache size grows with batch size and sequence length, often surpassing even the size of the model itself. Although recent methods were proposed to select and evict unimportant KV pairs from the cache to reduce memory consumption, the potential ramifications of eviction on the generative process are yet to be thoroughly examined. In this paper, we","authors_text":"Beomseok Kwon, Byeongwook Kim, Dongsoo Lee, Eunho Yang, Gunho Park, Jeongin Bae, June Yong Yang, Se Jung Kwon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T06:34:54Z","title":"No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18096","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:cb4a6dcd9d6e85a0bd0e01a0add80abe9b220aa3d38fcad6cea6d8a561f2e780","target":"record","created_at":"2026-07-05T07:50:12Z","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":"d78e6b7c0fc7f75315e6de9ed0c65ac6e8cf0fc435aeda1a245caed04fd820d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T06:34:54Z","title_canon_sha256":"010bbfadad32b71b0396bfdba5695a164c3265c1ee4863f33e4a438500a796d4"},"schema_version":"1.0","source":{"id":"2402.18096","kind":"arxiv","version":1}},"canonical_sha256":"5c9f741dc0b0718982af0b8cd2dc75792d6a3594b43fcb8e98e874e80ad5d47e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c9f741dc0b0718982af0b8cd2dc75792d6a3594b43fcb8e98e874e80ad5d47e","first_computed_at":"2026-07-05T07:50:12.291562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:12.291562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TscoTGBt8wCvRo6Kk+3X3wFkfIvQxaGJMc7xwgIW5JhtRpnf7zOrnZSakVAnvsRRt7Bpf5pZM31EGV46G9/hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:12.292162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb4a6dcd9d6e85a0bd0e01a0add80abe9b220aa3d38fcad6cea6d8a561f2e780","sha256:163e2e5a75e3bab43d4f6b2d1e808a78e8de68fc48f5feb2d16bfcf28a980177"],"state_sha256":"113afe78b9bcca970b898f9d2fea0fcd436d61b08fca3ecfe8088a970125659f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MxyM3A7edDzJ1B868ND7gaoiMlGDh5vUcUnqRaOLXhagrxZcjq8SBR0323JAon3L+rK4MIHy8zJSaYjXAlLpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:18:47.783939Z","bundle_sha256":"bece93f8694c612b39138ed8cdd44993887e1dd8ffbdbc8a7ab0f3d51bcaa830"}}