{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PUN4BJJKBJ7B5E3GMP357XHBWQ","short_pith_number":"pith:PUN4BJJK","canonical_record":{"source":{"id":"2412.02252","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T08:29:27Z","cross_cats_sorted":[],"title_canon_sha256":"7411289659b7c5f5a20db115f4fc3b6c6bc3578c8ab452c2057d96711840b270","abstract_canon_sha256":"fbc2a19a440ff8f9fa8c54eadb6e4e15c0d909474375d311a07cb71fd733b1c8"},"schema_version":"1.0"},"canonical_sha256":"7d1bc0a52a0a7e1e936663f7dfdce1b439eada2010ae5b473626233cffb39528","source":{"kind":"arxiv","id":"2412.02252","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02252","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02252v2","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02252","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"PUN4BJJKBJ7B","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"PUN4BJJKBJ7B5E3G","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"PUN4BJJK","created_at":"2026-07-05T11:47:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PUN4BJJKBJ7B5E3GMP357XHBWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.02252","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T08:29:27Z","cross_cats_sorted":[],"title_canon_sha256":"7411289659b7c5f5a20db115f4fc3b6c6bc3578c8ab452c2057d96711840b270","abstract_canon_sha256":"fbc2a19a440ff8f9fa8c54eadb6e4e15c0d909474375d311a07cb71fd733b1c8"},"schema_version":"1.0"},"canonical_sha256":"7d1bc0a52a0a7e1e936663f7dfdce1b439eada2010ae5b473626233cffb39528","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:16.202219Z","signature_b64":"BTwJwaDnI5fMYv12wU033QS35mmoK6RWWKELzkf7BfPR3me1tjsAGh6SkGQsx4aU0MF6MLULILggfND84KreBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d1bc0a52a0a7e1e936663f7dfdce1b439eada2010ae5b473626233cffb39528","last_reissued_at":"2026-07-05T11:47:16.201712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:16.201712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.02252","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KoZLbi76SrRuHpFtZMeceA0mFUQqNraxxZcMYRTG5+8A97mQ37q3WQqFxFSETu8zeYv5FcH68T3leCqX+Pi4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:23.825566Z"},"content_sha256":"4b905965aab2eb52ff52b42e54f73ede65f505b09f301321abd02d755ee53daa","schema_version":"1.0","event_id":"sha256:4b905965aab2eb52ff52b42e54f73ede65f505b09f301321abd02d755ee53daa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PUN4BJJKBJ7B5E3GMP357XHBWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Da Ma, Hanqi Li, Hongshen Xu, Kai Yu, Lei Pan, Lu Chen, Shuai Fan, Situo Zhang, Su Zhu, Yuxun Miao, Zhi Chen","submitted_at":"2024-12-03T08:29:27Z","abstract_excerpt":"The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory usage during inference, primarily due to the linear growth of the key-value~(KV) cache. Existing KV cache compression methods often discard less relevant tokens, which can lead to significant performance degradation when critical information is lost. In this paper, we propose \\textsc{PoD}~(Proximal tokens over Distant tokens), a novel KV cache compression framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02252","kind":"arxiv","version":2},"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/2412.02252/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":"2026-07-05T11:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zs7wWjqPFE4HPtNPTP9FAfCxCryKP+C8Tb3ZgMYcJeUH9UQxV55KbujyfLyIUTamd5k2tLfZHdLOJnmwdvsxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:54:23.830975Z"},"content_sha256":"a5d68cc722bb14647698a45e1f34069a3fae45aabb8c27f895565522b04873ec","schema_version":"1.0","event_id":"sha256:a5d68cc722bb14647698a45e1f34069a3fae45aabb8c27f895565522b04873ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/bundle.json","state_url":"https://pith.science/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/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":"2026-08-07T19:54:23Z","links":{"resolver":"https://pith.science/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ","bundle":"https://pith.science/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/bundle.json","state":"https://pith.science/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PUN4BJJKBJ7B5E3GMP357XHBWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PUN4BJJKBJ7B5E3GMP357XHBWQ","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":"fbc2a19a440ff8f9fa8c54eadb6e4e15c0d909474375d311a07cb71fd733b1c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T08:29:27Z","title_canon_sha256":"7411289659b7c5f5a20db115f4fc3b6c6bc3578c8ab452c2057d96711840b270"},"schema_version":"1.0","source":{"id":"2412.02252","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02252","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02252v2","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02252","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"PUN4BJJKBJ7B","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"PUN4BJJKBJ7B5E3G","created_at":"2026-07-05T11:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"PUN4BJJK","created_at":"2026-07-05T11:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:a5d68cc722bb14647698a45e1f34069a3fae45aabb8c27f895565522b04873ec","target":"graph","created_at":"2026-07-05T11:47:16Z","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/2412.02252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory usage during inference, primarily due to the linear growth of the key-value~(KV) cache. Existing KV cache compression methods often discard less relevant tokens, which can lead to significant performance degradation when critical information is lost. In this paper, we propose \\textsc{PoD}~(Proximal tokens over Distant tokens), a novel KV cache compression framew","authors_text":"Da Ma, Hanqi Li, Hongshen Xu, Kai Yu, Lei Pan, Lu Chen, Shuai Fan, Situo Zhang, Su Zhu, Yuxun Miao, Zhi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T08:29:27Z","title":"Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02252","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":"sha256:4b905965aab2eb52ff52b42e54f73ede65f505b09f301321abd02d755ee53daa","target":"record","created_at":"2026-07-05T11:47:16Z","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":"fbc2a19a440ff8f9fa8c54eadb6e4e15c0d909474375d311a07cb71fd733b1c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T08:29:27Z","title_canon_sha256":"7411289659b7c5f5a20db115f4fc3b6c6bc3578c8ab452c2057d96711840b270"},"schema_version":"1.0","source":{"id":"2412.02252","kind":"arxiv","version":2}},"canonical_sha256":"7d1bc0a52a0a7e1e936663f7dfdce1b439eada2010ae5b473626233cffb39528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d1bc0a52a0a7e1e936663f7dfdce1b439eada2010ae5b473626233cffb39528","first_computed_at":"2026-07-05T11:47:16.201712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:16.201712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BTwJwaDnI5fMYv12wU033QS35mmoK6RWWKELzkf7BfPR3me1tjsAGh6SkGQsx4aU0MF6MLULILggfND84KreBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:16.202219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02252","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b905965aab2eb52ff52b42e54f73ede65f505b09f301321abd02d755ee53daa","sha256:a5d68cc722bb14647698a45e1f34069a3fae45aabb8c27f895565522b04873ec"],"state_sha256":"2b0152ff310fed5d12f27283daecc44378d7d51f0f2dd160cd11fbfbba70664e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMLn/7CmX8qX1UxTv4yd0PqpdlLuLhoTIsw1gd5Nh43fwOfL54tTMfose+yBu8mD1qXmk2wdYMhpKej6jvQOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:54:23.847556Z","bundle_sha256":"2c2f74388a6a42ac679ace31bef8d01cecca04872b92f8db092cc08fb26fb48b"}}