{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSAV3SZGWCFL3LVHCVEO4KMZQA","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":"6aaca9c79365b2fcdcf11a24d3e9beb1b8178d05422c646264165564b51e943c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T11:35:16Z","title_canon_sha256":"795d4874d803c8f70e53092ca8226df61e4c57b9e51784b15e42c2d3f52480f0"},"schema_version":"1.0","source":{"id":"2406.11430","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11430","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11430v4","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11430","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"FSAV3SZGWCFL","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"FSAV3SZGWCFL3LVH","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"FSAV3SZG","created_at":"2026-07-05T09:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:24e93807657addb9ce82334ba34ca34cb17b65892191c777a92dfcad846a7629","target":"graph","created_at":"2026-07-05T09:30:17Z","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/2406.11430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either fine-tuning the model to learn a compression strategy or leveraging attention scores to reduce the sequence length. We analyse the attention distributions in decoder-only Transformers-based models and observe that attention allocation patterns stay consistent across most layers. Surprisingly, we find a clear correlation between the $L_2$ and the attention scores o","authors_text":"Alessio Devoto, Pasquale Minervini, Simone Scardapane, Yu Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T11:35:16Z","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11430","kind":"arxiv","version":4},"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:e66cbe2936436a6ff0f44bce9b70c2abb635d76d087c5efe43c889af144f8311","target":"record","created_at":"2026-07-05T09:30:17Z","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":"6aaca9c79365b2fcdcf11a24d3e9beb1b8178d05422c646264165564b51e943c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T11:35:16Z","title_canon_sha256":"795d4874d803c8f70e53092ca8226df61e4c57b9e51784b15e42c2d3f52480f0"},"schema_version":"1.0","source":{"id":"2406.11430","kind":"arxiv","version":4}},"canonical_sha256":"2c815dcb26b08abdaea71548ee299980103b3e0cc73f4f710190dd622dd97691","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c815dcb26b08abdaea71548ee299980103b3e0cc73f4f710190dd622dd97691","first_computed_at":"2026-07-05T09:30:17.327713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:17.327713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Z9Z1pXy65GeSPXCfgCyTWBC+7eaK1wrCL1tgl/jU7ZzkvHlB+FChMnsCBVX8y8uWs3xnaqggu2PPAXw4kgXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:17.328226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11430","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e66cbe2936436a6ff0f44bce9b70c2abb635d76d087c5efe43c889af144f8311","sha256:24e93807657addb9ce82334ba34ca34cb17b65892191c777a92dfcad846a7629"],"state_sha256":"b8fed05a341f18d08217848f4bea18626085527f50fee2b18049b611f499471a"}