{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B3GAJMC555ZVJATBXVYH3LUIAL","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":"9b3a9d09d96ae2fc520edf662641fafb824552a105800ae5ff1ddfb825c0db7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T09:20:59Z","title_canon_sha256":"ebfef38b672d07cfc2f5a3e212346ae6bb92307b6aa3b4eb49ea72dbf65d9a0e"},"schema_version":"1.0","source":{"id":"2402.06262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06262","created_at":"2026-07-05T07:46:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06262v2","created_at":"2026-07-05T07:46:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06262","created_at":"2026-07-05T07:46:31Z"},{"alias_kind":"pith_short_12","alias_value":"B3GAJMC555ZV","created_at":"2026-07-05T07:46:31Z"},{"alias_kind":"pith_short_16","alias_value":"B3GAJMC555ZVJATB","created_at":"2026-07-05T07:46:31Z"},{"alias_kind":"pith_short_8","alias_value":"B3GAJMC5","created_at":"2026-07-05T07:46:31Z"}],"graph_snapshots":[{"event_id":"sha256:7942a7222c5a6224c769eacd0f7540836119326ebe8a7905051c4f3fabbcd6e8","target":"graph","created_at":"2026-07-05T07:46:31Z","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/2402.06262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent success associated with Large Language Models (LLMs), they are notably cost-prohibitive to deploy in resource-constrained environments due to their excessive memory and computational demands. In addition to model parameters, the key-value cache is also stored in GPU memory, growing linearly with batch size and sequence length. As a remedy, recent works have proposed various eviction policies for maintaining the overhead of key-value cache under a given budget. This paper embarks on the efficacy of existing eviction policies in terms of importance score calculation and evicti","authors_text":"Kenny Q. Zhu, Siyu Ren","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T09:20:59Z","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06262","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":"sha256:6eb4eff72444aa285715461e7218173fcd2c541e665cb5a08be21de77335328f","target":"record","created_at":"2026-07-05T07:46:31Z","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":"9b3a9d09d96ae2fc520edf662641fafb824552a105800ae5ff1ddfb825c0db7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T09:20:59Z","title_canon_sha256":"ebfef38b672d07cfc2f5a3e212346ae6bb92307b6aa3b4eb49ea72dbf65d9a0e"},"schema_version":"1.0","source":{"id":"2402.06262","kind":"arxiv","version":2}},"canonical_sha256":"0ecc04b05def73548261bd707dae8802cf6d66a490ce139d9d182f31f5863e83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ecc04b05def73548261bd707dae8802cf6d66a490ce139d9d182f31f5863e83","first_computed_at":"2026-07-05T07:46:31.275479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:31.275479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"APE/tE8gstl6jhsmd5z+U/B8sIvgrJW6Jhm2Gs5QGTxUuUpHmZhtpAIq0NrGRoONdQrbcgHveuwocVeg6w1JAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:31.275990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eb4eff72444aa285715461e7218173fcd2c541e665cb5a08be21de77335328f","sha256:7942a7222c5a6224c769eacd0f7540836119326ebe8a7905051c4f3fabbcd6e8"],"state_sha256":"195dd4723241ff9da28259b79430371319b70fa207a28591051e945406005a17"}