{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SG6DEQXHKET74ZTAPATDMY46AY","short_pith_number":"pith:SG6DEQXH","schema_version":"1.0","canonical_sha256":"91bc3242e75127fe6660782636639e060c4fcd780e64e1d3b7346a2e7d4ceeb3","source":{"kind":"arxiv","id":"2606.06256","version":1},"attestation_state":"computed","paper":{"title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyu Wang, Guanjie Chen, HuaYi Jin, Junhao Hu, RuoZhou He, Yang Liu, ZhaoKai Luo, Zhiyong Wang","submitted_at":"2026-06-04T14:57:07Z","abstract_excerpt":"As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serving concurrency, cache reuse, and distributed scalability. Several important problems, including position-independent KV cache, prefix KV cache compression, hot/cold KV cache separation, and distributed KV cache management, all depend on how the KV cache is represented and managed. However, existing serving systems largely rely on a monolithic KV cache abstraction, where the KV cache is treated as a homogeneous seque"},"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":"2606.06256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T14:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"3a958ee9628b567704318053aa186b3380b607bbe8e70e07de04e395abfc55e2","abstract_canon_sha256":"57f569e438f4447db4b82212b960bb71986490e08a695a3d5314e6144dd750c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:39.463393Z","signature_b64":"WpymrfIN6MeT7UwDqvkNA9eSszkuamCiPbLPPsl1uXrBrlDg0vZPeDUxXmMuFZBEmf+GPnjF2/LsHWEfzRZZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91bc3242e75127fe6660782636639e060c4fcd780e64e1d3b7346a2e7d4ceeb3","last_reissued_at":"2026-06-05T01:15:39.462986Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:39.462986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boyu Wang, Guanjie Chen, HuaYi Jin, Junhao Hu, RuoZhou He, Yang Liu, ZhaoKai Luo, Zhiyong Wang","submitted_at":"2026-06-04T14:57:07Z","abstract_excerpt":"As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serving concurrency, cache reuse, and distributed scalability. Several important problems, including position-independent KV cache, prefix KV cache compression, hot/cold KV cache separation, and distributed KV cache management, all depend on how the KV cache is represented and managed. However, existing serving systems largely rely on a monolithic KV cache abstraction, where the KV cache is treated as a homogeneous seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06256","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/2606.06256/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":"2606.06256","created_at":"2026-06-05T01:15:39.463047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06256v1","created_at":"2026-06-05T01:15:39.463047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06256","created_at":"2026-06-05T01:15:39.463047+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG6DEQXHKET7","created_at":"2026-06-05T01:15:39.463047+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG6DEQXHKET74ZTA","created_at":"2026-06-05T01:15:39.463047+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG6DEQXH","created_at":"2026-06-05T01:15:39.463047+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/SG6DEQXHKET74ZTAPATDMY46AY","json":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY.json","graph_json":"https://pith.science/api/pith-number/SG6DEQXHKET74ZTAPATDMY46AY/graph.json","events_json":"https://pith.science/api/pith-number/SG6DEQXHKET74ZTAPATDMY46AY/events.json","paper":"https://pith.science/paper/SG6DEQXH"},"agent_actions":{"view_html":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY","download_json":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY.json","view_paper":"https://pith.science/paper/SG6DEQXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06256&json=true","fetch_graph":"https://pith.science/api/pith-number/SG6DEQXHKET74ZTAPATDMY46AY/graph.json","fetch_events":"https://pith.science/api/pith-number/SG6DEQXHKET74ZTAPATDMY46AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY/action/storage_attestation","attest_author":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY/action/author_attestation","sign_citation":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY/action/citation_signature","submit_replication":"https://pith.science/pith/SG6DEQXHKET74ZTAPATDMY46AY/action/replication_record"}},"created_at":"2026-06-05T01:15:39.463047+00:00","updated_at":"2026-06-05T01:15:39.463047+00:00"}