{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HKNIHO4QFLZG2VZKX2YRGXOCFR","short_pith_number":"pith:HKNIHO4Q","schema_version":"1.0","canonical_sha256":"3a9a83bb902af26d572abeb1135dc22c45a496fe6d2f1aed316d8d677dd3a4a6","source":{"kind":"arxiv","id":"2603.22910","version":2},"attestation_state":"computed","paper":{"title":"EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EchoKV compresses the KV cache by reconstructing discarded components from retained ones using attention head similarities.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qingfu Zhu, Shiyu Ji, Wanxiang Che, Yijun Liu, Yixuan Wang","submitted_at":"2026-03-24T07:58:42Z","abstract_excerpt":"The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model projections, limiting the flexibility to switch back to standard full-cache inference when sufficient memory is available. In this paper, we propose EchoKV, a flexible KV cache compression framework that supports on-demand transitions from full KV caching to compressed caching. Unlike traditional compression-decompression paradigms, EchoKV utilizes a lightweight ne"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.22910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-24T07:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"0237fd64785f5c9872c9b505fb8aae054d36de633f147c5171a02e95736711a1","abstract_canon_sha256":"83b6017948d1ddfa7fe6d32c85acbd709353e81c36033790db0a1379dd017175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:22.582638Z","signature_b64":"VCY0D5cElCr4UBL6gtDp8fvwU47kWZc9w318/qI246wjskNSWqE8aOjDLKrmfTDRHxmdhm7W7LIwB32hdKrtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9a83bb902af26d572abeb1135dc22c45a496fe6d2f1aed316d8d677dd3a4a6","last_reissued_at":"2026-05-18T03:09:22.581986Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:22.581986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EchoKV compresses the KV cache by reconstructing discarded components from retained ones using attention head similarities.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qingfu Zhu, Shiyu Ji, Wanxiang Che, Yijun Liu, Yixuan Wang","submitted_at":"2026-03-24T07:58:42Z","abstract_excerpt":"The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model projections, limiting the flexibility to switch back to standard full-cache inference when sufficient memory is available. In this paper, we propose EchoKV, a flexible KV cache compression framework that supports on-demand transitions from full KV caching to compressed caching. Unlike traditional compression-decompression paradigms, EchoKV utilizes a lightweight ne"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EchoKV consistently outperforms existing methods across multiple compression ratios and backbone models while preserving the throughput of full-cache inference in short-context scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That intrinsic inter-layer and intra-layer similarities among attention heads are sufficiently stable and informative for a lightweight network to accurately reconstruct the discarded KV components without introducing errors that degrade downstream performance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EchoKV compresses the KV cache by reconstructing discarded components from retained ones using attention head similarities.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6fda05209f4ea21a0fa3febe88df0a5409a9e2c91b2bdf0973c4c6b145296c55"},"source":{"id":"2603.22910","kind":"arxiv","version":2},"verdict":{"id":"09112ba9-99ed-4b8b-a8e0-b869e68825d5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:05:08.778242Z","strongest_claim":"EchoKV consistently outperforms existing methods across multiple compression ratios and backbone models while preserving the throughput of full-cache inference in short-context scenarios.","one_line_summary":"EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That intrinsic inter-layer and intra-layer similarities among attention heads are sufficiently stable and informative for a lightweight network to accurately reconstruct the discarded KV components without introducing errors that degrade downstream performance.","pith_extraction_headline":"EchoKV compresses the KV cache by reconstructing discarded components from retained ones using attention head similarities."},"references":{"count":22,"sample":[{"doi":"","year":null,"title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","work_id":"b73ad5b2-e553-4c71-b0c9-67e67ba7b158","ref_index":1,"cited_arxiv_id":"2305.13245","is_internal_anchor":true},{"doi":"","year":null,"title":"xkv: Cross-layer svd for kv-cache compression","work_id":"16dc86cb-7b66-400c-be1f-dd459db6f94e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Palu: Compressing kv-cache with low-rank projection.arXiv preprint arXiv:2407.21118","work_id":"dc6247ce-a2da-431d-a935-3fb13543cb13","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","work_id":"0b361fed-cf2a-4b90-b61a-de88de4b8840","ref_index":4,"cited_arxiv_id":"2503.09567","is_internal_anchor":true},{"doi":"","year":null,"title":"Homogeneous keys, heterogeneous values: Exploiting local kv cache asymmetry for long-context llms.arXiv preprint arXiv:2506.05410. Tri Dao","work_id":"4b5ebee2-c5a9-4d4e-a150-51b305167091","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":22,"snapshot_sha256":"037438b6a30a26a8fe206b2768d274d7802774da5a189c9a422e31b3bd371606","internal_anchors":11},"formal_canon":{"evidence_count":2,"snapshot_sha256":"55a2138617dd87589c4dacb9ca17f9f7c2ba662dcb063e4dc87ac0a0f97a0c17"},"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":"2603.22910","created_at":"2026-05-18T03:09:22.582100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.22910v2","created_at":"2026-05-18T03:09:22.582100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22910","created_at":"2026-05-18T03:09:22.582100+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKNIHO4QFLZG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKNIHO4QFLZG2VZK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKNIHO4Q","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR","json":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR.json","graph_json":"https://pith.science/api/pith-number/HKNIHO4QFLZG2VZKX2YRGXOCFR/graph.json","events_json":"https://pith.science/api/pith-number/HKNIHO4QFLZG2VZKX2YRGXOCFR/events.json","paper":"https://pith.science/paper/HKNIHO4Q"},"agent_actions":{"view_html":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR","download_json":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR.json","view_paper":"https://pith.science/paper/HKNIHO4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.22910&json=true","fetch_graph":"https://pith.science/api/pith-number/HKNIHO4QFLZG2VZKX2YRGXOCFR/graph.json","fetch_events":"https://pith.science/api/pith-number/HKNIHO4QFLZG2VZKX2YRGXOCFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR/action/storage_attestation","attest_author":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR/action/author_attestation","sign_citation":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR/action/citation_signature","submit_replication":"https://pith.science/pith/HKNIHO4QFLZG2VZKX2YRGXOCFR/action/replication_record"}},"created_at":"2026-05-18T03:09:22.582100+00:00","updated_at":"2026-05-18T03:09:22.582100+00:00"}