{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ASPX2I5GUITOEUZQF5AEN5MWMS","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":"69fbf54aa143222973a0b192852d4248d85efff078a8f59bf0e7a4f75c0abbca","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-06-01T23:51:37Z","title_canon_sha256":"e821b35ec7a629563fca889dd5d3b49891053a4270cf89b2709e0b780fb072ef"},"schema_version":"1.0","source":{"id":"2606.02964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02964","created_at":"2026-06-03T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02964v1","created_at":"2026-06-03T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02964","created_at":"2026-06-03T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"ASPX2I5GUITO","created_at":"2026-06-03T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"ASPX2I5GUITOEUZQ","created_at":"2026-06-03T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"ASPX2I5G","created_at":"2026-06-03T01:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:8fc75d88e1e1c14ac7827009603fbd4c294c09cebce85d60752bf65e4c960e96","target":"graph","created_at":"2026-06-03T01:05:27Z","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/2606.02964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention techniques reduce memory usage by sacrificing model accuracy, lossless approaches instead evict KV cache blocks from GPU memory and reconstruct them on demand to preserve exact outputs. Existing lossless KV cache management systems primarily base eviction decisions on access frequency or positional heuristics, without considering how different KV cache blocks affect the execution efficiency of GPU attention kernels.\n  In this paper, we propose Asym","authors_text":"Bin Cui, Chunan Shi, Xupeng Miao, Yilei Chen, Yilin Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-06-01T23:51:37Z","title":"Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02964","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:a7c5eb030c3eb7ac519a5dfb44d0f7512a12c24acc864edf52c4560c0903c20c","target":"record","created_at":"2026-06-03T01:05:27Z","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":"69fbf54aa143222973a0b192852d4248d85efff078a8f59bf0e7a4f75c0abbca","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-06-01T23:51:37Z","title_canon_sha256":"e821b35ec7a629563fca889dd5d3b49891053a4270cf89b2709e0b780fb072ef"},"schema_version":"1.0","source":{"id":"2606.02964","kind":"arxiv","version":1}},"canonical_sha256":"049f7d23a6a226e253302f4046f596648bd6c5cfadabb029246f66cdb219a690","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"049f7d23a6a226e253302f4046f596648bd6c5cfadabb029246f66cdb219a690","first_computed_at":"2026-06-03T01:05:27.867961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:27.867961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"frUCJBmL5QCpAPuaU3EH4b659ZwJsBRJFUuZEZgYY0o3ZnGeqZ6lUfosCtd2V97hfWZWhKElDChwFzPCYOqAAA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:27.868386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7c5eb030c3eb7ac519a5dfb44d0f7512a12c24acc864edf52c4560c0903c20c","sha256:8fc75d88e1e1c14ac7827009603fbd4c294c09cebce85d60752bf65e4c960e96"],"state_sha256":"764b955a0f533b48c272a9d166b804ab359d69a69de4b96f4e08360f0a37c4c0"}