{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KN3WL7MYIKH35QMD5EOATROK2P","short_pith_number":"pith:KN3WL7MY","canonical_record":{"source":{"id":"2410.03065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T01:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"688eb095aec270cf0b413bb24a032bcca4c066110063080f2614295a13f502bb","abstract_canon_sha256":"dcb8332bf234a20baa64e5d53d75210536ae00ecc6d0967b61670d67130f1594"},"schema_version":"1.0"},"canonical_sha256":"537765fd98428fbec183e91c09c5cad3fddb7848cf54b3593c8f1a3aba4c3fc8","source":{"kind":"arxiv","id":"2410.03065","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03065","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03065v2","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03065","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"KN3WL7MYIKH3","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"KN3WL7MYIKH35QMD","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"KN3WL7MY","created_at":"2026-07-05T10:17:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KN3WL7MYIKH35QMD5EOATROK2P","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T01:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"688eb095aec270cf0b413bb24a032bcca4c066110063080f2614295a13f502bb","abstract_canon_sha256":"dcb8332bf234a20baa64e5d53d75210536ae00ecc6d0967b61670d67130f1594"},"schema_version":"1.0"},"canonical_sha256":"537765fd98428fbec183e91c09c5cad3fddb7848cf54b3593c8f1a3aba4c3fc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:50.276221Z","signature_b64":"yFqrL4rDSQV0UinqPxYgdcDoXp1jB3e45Af2fzH/Wmq1ztbVc1to30gE5YlR527+Bhr63BHWWEpbV/KrKQBsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537765fd98428fbec183e91c09c5cad3fddb7848cf54b3593c8f1a3aba4c3fc8","last_reissued_at":"2026-07-05T10:17:50.275743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:50.275743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03065","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":"2026-07-05T10:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0krqGkTcnc2tg9Lak1btInYzZSoiCkcj7oHIN3qsI5ZqKzejxx1g5ewK7wcbxdDQHDygSgX8EnF1/rdijDpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:53:59.307353Z"},"content_sha256":"8050b53faed291fba571a2133c45cb56975d8f92fb438479ea4b14b6a8d598e0","schema_version":"1.0","event_id":"sha256:8050b53faed291fba571a2133c45cb56975d8f92fb438479ea4b14b6a8d598e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KN3WL7MYIKH35QMD5EOATROK2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compute Or Load KV Cache? Why Not Both?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qingzhao Zhang, Shuowei Jin, Xueshen Liu, Z. Morley Mao","submitted_at":"2024-10-04T01:11:09Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major bottleneck, particularly for long-context inputs. Prefix caching mitigates this issue by storing KV caches for reuse, reducing redundant computation. Despite its advantages, prefix caching suffers from high latency due to the limited I/O bandwidth of storage devices, constraining inference efficiency. To address this challenge, we introduce Cake, a novel KV cache "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03065","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/2410.03065/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":"2026-07-05T10:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h7y1a9pKrl3ppOvHZ8bHYtv9+GKCsEhoNacOSItb+eClMPYYgPO+fyRESHcu+/AT3jMeeD6iQe4Fh3DT186JBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:53:59.307853Z"},"content_sha256":"5a62077746b56bf75ce416287e9ebd2c1fcaaf6c40916f9e5cc9152fc6fb5c4e","schema_version":"1.0","event_id":"sha256:5a62077746b56bf75ce416287e9ebd2c1fcaaf6c40916f9e5cc9152fc6fb5c4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN3WL7MYIKH35QMD5EOATROK2P/bundle.json","state_url":"https://pith.science/pith/KN3WL7MYIKH35QMD5EOATROK2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN3WL7MYIKH35QMD5EOATROK2P/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":"2026-08-03T22:53:59Z","links":{"resolver":"https://pith.science/pith/KN3WL7MYIKH35QMD5EOATROK2P","bundle":"https://pith.science/pith/KN3WL7MYIKH35QMD5EOATROK2P/bundle.json","state":"https://pith.science/pith/KN3WL7MYIKH35QMD5EOATROK2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN3WL7MYIKH35QMD5EOATROK2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KN3WL7MYIKH35QMD5EOATROK2P","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":"dcb8332bf234a20baa64e5d53d75210536ae00ecc6d0967b61670d67130f1594","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T01:11:09Z","title_canon_sha256":"688eb095aec270cf0b413bb24a032bcca4c066110063080f2614295a13f502bb"},"schema_version":"1.0","source":{"id":"2410.03065","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03065","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03065v2","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03065","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"KN3WL7MYIKH3","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"KN3WL7MYIKH35QMD","created_at":"2026-07-05T10:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"KN3WL7MY","created_at":"2026-07-05T10:17:50Z"}],"graph_snapshots":[{"event_id":"sha256:5a62077746b56bf75ce416287e9ebd2c1fcaaf6c40916f9e5cc9152fc6fb5c4e","target":"graph","created_at":"2026-07-05T10:17:50Z","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/2410.03065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major bottleneck, particularly for long-context inputs. Prefix caching mitigates this issue by storing KV caches for reuse, reducing redundant computation. Despite its advantages, prefix caching suffers from high latency due to the limited I/O bandwidth of storage devices, constraining inference efficiency. To address this challenge, we introduce Cake, a novel KV cache ","authors_text":"Qingzhao Zhang, Shuowei Jin, Xueshen Liu, Z. Morley Mao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T01:11:09Z","title":"Compute Or Load KV Cache? Why Not Both?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03065","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":"sha256:8050b53faed291fba571a2133c45cb56975d8f92fb438479ea4b14b6a8d598e0","target":"record","created_at":"2026-07-05T10:17:50Z","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":"dcb8332bf234a20baa64e5d53d75210536ae00ecc6d0967b61670d67130f1594","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T01:11:09Z","title_canon_sha256":"688eb095aec270cf0b413bb24a032bcca4c066110063080f2614295a13f502bb"},"schema_version":"1.0","source":{"id":"2410.03065","kind":"arxiv","version":2}},"canonical_sha256":"537765fd98428fbec183e91c09c5cad3fddb7848cf54b3593c8f1a3aba4c3fc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537765fd98428fbec183e91c09c5cad3fddb7848cf54b3593c8f1a3aba4c3fc8","first_computed_at":"2026-07-05T10:17:50.275743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:50.275743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yFqrL4rDSQV0UinqPxYgdcDoXp1jB3e45Af2fzH/Wmq1ztbVc1to30gE5YlR527+Bhr63BHWWEpbV/KrKQBsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:50.276221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03065","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8050b53faed291fba571a2133c45cb56975d8f92fb438479ea4b14b6a8d598e0","sha256:5a62077746b56bf75ce416287e9ebd2c1fcaaf6c40916f9e5cc9152fc6fb5c4e"],"state_sha256":"4138921066a86afa99d286b58d965fa9dfa84efb165f216bd3d0eb78018e6ff1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYF4If1hQEj7o6lPmdbuuPvYaqoCozYk3lSFPaBuu0s5CEOSM/RIEszqHXtm93BqKKyjLcNzmKI2ejXAGB52Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:53:59.312894Z","bundle_sha256":"ca15d9e5f59326ec73d7311a9184a830703b0c2104e3b9284a9166af5a99ec23"}}