{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GNCIWYERHJYEC3XLXP7NBK2ZXJ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a3cea07040a3cd61c3d7902b0b390903a04b97b63604032288551e373660b933","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T02:11:18Z","title_canon_sha256":"233151495571d5519d2ae1533d76932f34aa99a269a6c6f84a751729ecfab04d"},"schema_version":"1.0","source":{"id":"2607.08057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08057","created_at":"2026-07-10T00:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08057v1","created_at":"2026-07-10T00:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08057","created_at":"2026-07-10T00:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"GNCIWYERHJYE","created_at":"2026-07-10T00:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"GNCIWYERHJYEC3XL","created_at":"2026-07-10T00:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"GNCIWYER","created_at":"2026-07-10T00:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:e487952e7fb3f003781de017c0a249eb720c1b45beaf2c95fe65f669e6259a1f","target":"graph","created_at":"2026-07-10T00:19:09Z","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/2607.08057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during autoregressive decoding, is crucial for enabling low-latency, high-throughput LLM inference serving. In this survey, we focus on system-aware KV infrastructure for serving LLMs (abbreviated as sKis). We revisit recent work from a system behavior perspective, organizing existing efforts into three dimensions: execution and scheduling (temporal), placement and migration (spatial), and representation and retention (structu","authors_text":"Feng Liu, Jiantong Jiang, Peiyu Yang, Rui Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T02:11:18Z","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08057","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:cf36da8bc9b5e6f198431336b00ef8c3938e525608c8a4ac6ae8052a8acd3c22","target":"record","created_at":"2026-07-10T00:19:09Z","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":"a3cea07040a3cd61c3d7902b0b390903a04b97b63604032288551e373660b933","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T02:11:18Z","title_canon_sha256":"233151495571d5519d2ae1533d76932f34aa99a269a6c6f84a751729ecfab04d"},"schema_version":"1.0","source":{"id":"2607.08057","kind":"arxiv","version":1}},"canonical_sha256":"33448b60913a70416eebbbfed0ab59ba5a253843514018f4e7e8ae51b87f004f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33448b60913a70416eebbbfed0ab59ba5a253843514018f4e7e8ae51b87f004f","first_computed_at":"2026-07-10T00:19:09.228676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T00:19:09.228676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TV8hj7x8cQl4Yi4CDA8r8kW8Glw0rUzWa7HYm8XCyBj4IAM4bFa5+nNpmOjewK6JyIzjK+NKpJRnzAn+PK4mCA==","signature_status":"signed_v1","signed_at":"2026-07-10T00:19:09.229074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf36da8bc9b5e6f198431336b00ef8c3938e525608c8a4ac6ae8052a8acd3c22","sha256:e487952e7fb3f003781de017c0a249eb720c1b45beaf2c95fe65f669e6259a1f","sha256:e4ac52367bf53a8c5620a3aacf8978234969912109d27426b5dee23d62711285"],"state_sha256":"a4cbbec4b431b0af15c4d1d2f6ae4552f07cb73456e096fc1a67b65fd150fd09"}