{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:43IXNE4QYHUGSWBKVHYAH4NBNZ","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":"0e563b5be9b8343433ae5ba04527dd746c34bd3718a4c7782f0ff0ff498c7dec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T05:01:19Z","title_canon_sha256":"13bd4ed1800761ac6c04b21806a63e25f0224ef2c60b40bd9697e185a2b2e23d"},"schema_version":"1.0","source":{"id":"2410.12876","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12876","created_at":"2026-07-05T10:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12876v3","created_at":"2026-07-05T10:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12876","created_at":"2026-07-05T10:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"43IXNE4QYHUG","created_at":"2026-07-05T10:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"43IXNE4QYHUGSWBK","created_at":"2026-07-05T10:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"43IXNE4Q","created_at":"2026-07-05T10:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:a995d6b5ff37c2a21273b690a776fbb04a8b40f1ec00108de658ef90679c56d1","target":"graph","created_at":"2026-07-05T10:50:09Z","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/2410.12876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM inference system. This paper enables a novel dynamic KV-Cache eviction policy by injecting a lightweight module called Attention-Gate to the model. It accepts the global context as input and yields eviction flags for each token. The self-attention modules in the model proceed according to the flags and cache only a subset of the KV states for next token prediction. The Attention-Gates can yield various flags for differen","authors_text":"Bokai Lin, Hao Zhang, TianQi Hou, Zhijie Deng, Zihao Zeng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T05:01:19Z","title":"In-context KV-Cache Eviction for LLMs via Attention-Gate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12876","kind":"arxiv","version":3},"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:ba269fe5efe6fd14984bf36b99f127300c7e99579ad79e86755767e57805494c","target":"record","created_at":"2026-07-05T10:50:09Z","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":"0e563b5be9b8343433ae5ba04527dd746c34bd3718a4c7782f0ff0ff498c7dec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T05:01:19Z","title_canon_sha256":"13bd4ed1800761ac6c04b21806a63e25f0224ef2c60b40bd9697e185a2b2e23d"},"schema_version":"1.0","source":{"id":"2410.12876","kind":"arxiv","version":3}},"canonical_sha256":"e6d1769390c1e869582aa9f003f1a16e400c30bc88143780dd876347b02ed20f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6d1769390c1e869582aa9f003f1a16e400c30bc88143780dd876347b02ed20f","first_computed_at":"2026-07-05T10:50:09.746484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:09.746484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uu2pPX00Al8TIYTakn84z4pF9fwyMYaDqW1uyVnSz7KMPqo1wdU5LzypcW/HL9kbT6Vg4VhoCl59fOi9AT2dAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:09.746890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12876","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba269fe5efe6fd14984bf36b99f127300c7e99579ad79e86755767e57805494c","sha256:a995d6b5ff37c2a21273b690a776fbb04a8b40f1ec00108de658ef90679c56d1"],"state_sha256":"05ac20492d8f6db43712e5606807afdb58391a1547eab962ca67b3eb4f4872f5"}