{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7CFGKJQAKR5AD7VY5VHPJMYTYJ","short_pith_number":"pith:7CFGKJQA","schema_version":"1.0","canonical_sha256":"f88a652600547a01feb8ed4ef4b313c275538ad235b66e15520adec83baa7e04","source":{"kind":"arxiv","id":"2605.26678","version":1},"attestation_state":"computed","paper":{"title":"NestedKV: Nested Memory Routing for Long-Context KV Cache Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Hong Chen, Xiang Liu, Xuming Hu, Yuanguo Lin, Yuanlin Chu, Yubo Gao, Yuxuan Fan","submitted_at":"2026-05-26T08:14:39Z","abstract_excerpt":"Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank tokens by one importance signal -- attention, recency, layer-wise allocation, or key distinctiveness -- which becomes brittle when useful context is globally distinctive, locally episodic, or immediately relevant. We introduce NestedKV, a key-only KV cache compression method inspired by the Continuum Memory System in Nested Learning. NestedKV maintains global, block-level, and sliding-window key anchors, scores tokens by multi-time-scale cosin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T08:14:39Z","cross_cats_sorted":[],"title_canon_sha256":"664e76926b06c495fb38206d9ea24891994cbcbbc8492ef53749ab6844651a7d","abstract_canon_sha256":"18aea69452e1f71f72edbc32ade53d30cc7be32bb65a5acf1f3c04190e424f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:05.538740Z","signature_b64":"Fvgi7OpGd1cgydHQBVsQYDH1dyUGT4vyKRhqmXWkCuIERGiX7RKSasEAbZBuwv8q57FB4GhtgCfmvuEZZn3NAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f88a652600547a01feb8ed4ef4b313c275538ad235b66e15520adec83baa7e04","last_reissued_at":"2026-05-27T01:06:05.537944Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:05.537944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NestedKV: Nested Memory Routing for Long-Context KV Cache Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Hong Chen, Xiang Liu, Xuming Hu, Yuanguo Lin, Yuanlin Chu, Yubo Gao, Yuxuan Fan","submitted_at":"2026-05-26T08:14:39Z","abstract_excerpt":"Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank tokens by one importance signal -- attention, recency, layer-wise allocation, or key distinctiveness -- which becomes brittle when useful context is globally distinctive, locally episodic, or immediately relevant. We introduce NestedKV, a key-only KV cache compression method inspired by the Continuum Memory System in Nested Learning. NestedKV maintains global, block-level, and sliding-window key anchors, scores tokens by multi-time-scale cosin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26678","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/2605.26678/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26678","created_at":"2026-05-27T01:06:05.538067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26678v1","created_at":"2026-05-27T01:06:05.538067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26678","created_at":"2026-05-27T01:06:05.538067+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CFGKJQAKR5A","created_at":"2026-05-27T01:06:05.538067+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CFGKJQAKR5AD7VY","created_at":"2026-05-27T01:06:05.538067+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CFGKJQA","created_at":"2026-05-27T01:06:05.538067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ","json":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ.json","graph_json":"https://pith.science/api/pith-number/7CFGKJQAKR5AD7VY5VHPJMYTYJ/graph.json","events_json":"https://pith.science/api/pith-number/7CFGKJQAKR5AD7VY5VHPJMYTYJ/events.json","paper":"https://pith.science/paper/7CFGKJQA"},"agent_actions":{"view_html":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ","download_json":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ.json","view_paper":"https://pith.science/paper/7CFGKJQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26678&json=true","fetch_graph":"https://pith.science/api/pith-number/7CFGKJQAKR5AD7VY5VHPJMYTYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7CFGKJQAKR5AD7VY5VHPJMYTYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ/action/storage_attestation","attest_author":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ/action/author_attestation","sign_citation":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ/action/citation_signature","submit_replication":"https://pith.science/pith/7CFGKJQAKR5AD7VY5VHPJMYTYJ/action/replication_record"}},"created_at":"2026-05-27T01:06:05.538067+00:00","updated_at":"2026-05-27T01:06:05.538067+00:00"}