{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XAXYMSNKN7BQQOX2J4XWOZE2VD","short_pith_number":"pith:XAXYMSNK","canonical_record":{"source":{"id":"2508.06297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-08T13:19:30Z","cross_cats_sorted":[],"title_canon_sha256":"a77ee2bec3f3b193c4bed1785550d75302fd1c0e74eb79920d7f774237ce1eed","abstract_canon_sha256":"31459adbb97bd1b58cf7622f145a834729605c92c5d5ce6fbb3e7026344ce8ee"},"schema_version":"1.0"},"canonical_sha256":"b82f8649aa6fc3083afa4f2f67649aa8e6724906df39a7af8374ef3b1c77bc38","source":{"kind":"arxiv","id":"2508.06297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06297","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06297v1","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06297","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"XAXYMSNKN7BQ","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"XAXYMSNKN7BQQOX2","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"XAXYMSNK","created_at":"2026-07-05T11:50:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XAXYMSNKN7BQQOX2J4XWOZE2VD","target":"record","payload":{"canonical_record":{"source":{"id":"2508.06297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-08T13:19:30Z","cross_cats_sorted":[],"title_canon_sha256":"a77ee2bec3f3b193c4bed1785550d75302fd1c0e74eb79920d7f774237ce1eed","abstract_canon_sha256":"31459adbb97bd1b58cf7622f145a834729605c92c5d5ce6fbb3e7026344ce8ee"},"schema_version":"1.0"},"canonical_sha256":"b82f8649aa6fc3083afa4f2f67649aa8e6724906df39a7af8374ef3b1c77bc38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:53.693200Z","signature_b64":"t4dCpQcqjm3JKEKpzr7mRmNDxcJiz2NJZdXu3ZrXxlSZBNXWcqFlaD8XZ+tj2jouWupDnvL2Gqg8gJI/9Mv0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82f8649aa6fc3083afa4f2f67649aa8e6724906df39a7af8374ef3b1c77bc38","last_reissued_at":"2026-07-05T11:50:53.692641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:53.692641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.06297","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFYjuTA+LaRvoNzT7VoWRnDF4UVrjeVok145mK0390F/Wd05O+RDkLwBant1JrF7UUFgtwnkIcOWPlWgyG5WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T08:15:06.289037Z"},"content_sha256":"67403f25c2306f3d03267fa7d9ac351f8f51311f26ff0651871c6747c2460b38","schema_version":"1.0","event_id":"sha256:67403f25c2306f3d03267fa7d9ac351f8f51311f26ff0651871c6747c2460b38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XAXYMSNKN7BQQOX2J4XWOZE2VD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KV Cache Compression for Inference Efficiency in LLMs: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"(2) University of Oulu), Jiehan Zhou (1), Jingying Fu (1), Shouhua Zhang (2) ((1) Shandong University of Science, Sixiang Liu (1), Technology, Yanyu Liu (1), Yitian Zou (1), You Fu (1)","submitted_at":"2025-08-08T13:19:30Z","abstract_excerpt":"Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant memory bottleneck, limiting the inference efficiency and scalability of the models. Therefore, optimizing the KV cache during inference is crucial for enhancing performance and efficiency. This review systematically examines current KV cache optimization techniques, including compression strategies such as selective token strategies, quantization, and attention c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06297","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/2508.06297/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":"2026-07-05T11:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLboNVLSmStosdxZLqvhLQaIUeA7vdNO2/TIyiE1XIVdiTKNJI+cf97NumXAF7sfM4sMA4G70LFE5YnoXjdpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T08:15:06.289448Z"},"content_sha256":"e04f9a5abf3f7192e8ae384e5a0ed933cc88e2694dde167e9ddc419a7db62b61","schema_version":"1.0","event_id":"sha256:e04f9a5abf3f7192e8ae384e5a0ed933cc88e2694dde167e9ddc419a7db62b61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/bundle.json","state_url":"https://pith.science/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/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":"2026-07-28T08:15:06Z","links":{"resolver":"https://pith.science/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD","bundle":"https://pith.science/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/bundle.json","state":"https://pith.science/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XAXYMSNKN7BQQOX2J4XWOZE2VD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XAXYMSNKN7BQQOX2J4XWOZE2VD","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":"31459adbb97bd1b58cf7622f145a834729605c92c5d5ce6fbb3e7026344ce8ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-08T13:19:30Z","title_canon_sha256":"a77ee2bec3f3b193c4bed1785550d75302fd1c0e74eb79920d7f774237ce1eed"},"schema_version":"1.0","source":{"id":"2508.06297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06297","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06297v1","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06297","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"XAXYMSNKN7BQ","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"XAXYMSNKN7BQQOX2","created_at":"2026-07-05T11:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"XAXYMSNK","created_at":"2026-07-05T11:50:53Z"}],"graph_snapshots":[{"event_id":"sha256:e04f9a5abf3f7192e8ae384e5a0ed933cc88e2694dde167e9ddc419a7db62b61","target":"graph","created_at":"2026-07-05T11:50:53Z","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/2508.06297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant memory bottleneck, limiting the inference efficiency and scalability of the models. Therefore, optimizing the KV cache during inference is crucial for enhancing performance and efficiency. This review systematically examines current KV cache optimization techniques, including compression strategies such as selective token strategies, quantization, and attention c","authors_text":"(2) University of Oulu), Jiehan Zhou (1), Jingying Fu (1), Shouhua Zhang (2) ((1) Shandong University of Science, Sixiang Liu (1), Technology, Yanyu Liu (1), Yitian Zou (1), You Fu (1)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-08T13:19:30Z","title":"KV Cache Compression for Inference Efficiency in LLMs: A Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06297","kind":"arxiv","version":1},"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":"sha256:67403f25c2306f3d03267fa7d9ac351f8f51311f26ff0651871c6747c2460b38","target":"record","created_at":"2026-07-05T11:50:53Z","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":"31459adbb97bd1b58cf7622f145a834729605c92c5d5ce6fbb3e7026344ce8ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-08T13:19:30Z","title_canon_sha256":"a77ee2bec3f3b193c4bed1785550d75302fd1c0e74eb79920d7f774237ce1eed"},"schema_version":"1.0","source":{"id":"2508.06297","kind":"arxiv","version":1}},"canonical_sha256":"b82f8649aa6fc3083afa4f2f67649aa8e6724906df39a7af8374ef3b1c77bc38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b82f8649aa6fc3083afa4f2f67649aa8e6724906df39a7af8374ef3b1c77bc38","first_computed_at":"2026-07-05T11:50:53.692641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:53.692641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t4dCpQcqjm3JKEKpzr7mRmNDxcJiz2NJZdXu3ZrXxlSZBNXWcqFlaD8XZ+tj2jouWupDnvL2Gqg8gJI/9Mv0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:53.693200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67403f25c2306f3d03267fa7d9ac351f8f51311f26ff0651871c6747c2460b38","sha256:e04f9a5abf3f7192e8ae384e5a0ed933cc88e2694dde167e9ddc419a7db62b61"],"state_sha256":"e5ad400972a9ab3cd9b3cf3e2c098d6c6f0a517bf094ee1c1d21b1ce711694a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72KEpy9yR3Jh210Ok1kM1E/XJidOxqtGcn11gF+PVf/g516Sn2Y+VuDs0rS8XsWEDyuMeGxGSHXEM/aARMPhCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T08:15:06.291853Z","bundle_sha256":"bd2d7955f4e5005b7afb51e29dd6c1919c380ea05ea97735403711f4ebf49f73"}}