{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GNCIWYERHJYEC3XLXP7NBK2ZXJ","short_pith_number":"pith:GNCIWYER","canonical_record":{"source":{"id":"2607.08057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T02:11:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"233151495571d5519d2ae1533d76932f34aa99a269a6c6f84a751729ecfab04d","abstract_canon_sha256":"a3cea07040a3cd61c3d7902b0b390903a04b97b63604032288551e373660b933"},"schema_version":"1.0"},"canonical_sha256":"33448b60913a70416eebbbfed0ab59ba5a253843514018f4e7e8ae51b87f004f","source":{"kind":"arxiv","id":"2607.08057","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GNCIWYERHJYEC3XLXP7NBK2ZXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.08057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T02:11:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"233151495571d5519d2ae1533d76932f34aa99a269a6c6f84a751729ecfab04d","abstract_canon_sha256":"a3cea07040a3cd61c3d7902b0b390903a04b97b63604032288551e373660b933"},"schema_version":"1.0"},"canonical_sha256":"33448b60913a70416eebbbfed0ab59ba5a253843514018f4e7e8ae51b87f004f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T00:19:09.229074Z","signature_b64":"TV8hj7x8cQl4Yi4CDA8r8kW8Glw0rUzWa7HYm8XCyBj4IAM4bFa5+nNpmOjewK6JyIzjK+NKpJRnzAn+PK4mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33448b60913a70416eebbbfed0ab59ba5a253843514018f4e7e8ae51b87f004f","last_reissued_at":"2026-07-10T00:19:09.228676Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T00:19:09.228676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.08057","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T00:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fd5/7lVOCCAkFCvrW5d5Ttnx1thBKQ5jBpplZkUF8RqpX71UmbG18FNfySWrM/oYJ65YVUjJchD5Pa0ipdfmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:53:59.664894Z"},"content_sha256":"cf36da8bc9b5e6f198431336b00ef8c3938e525608c8a4ac6ae8052a8acd3c22","schema_version":"1.0","event_id":"sha256:cf36da8bc9b5e6f198431336b00ef8c3938e525608c8a4ac6ae8052a8acd3c22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GNCIWYERHJYEC3XLXP7NBK2ZXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Feng Liu, Jiantong Jiang, Peiyu Yang, Rui Zhang","submitted_at":"2026-07-09T02:11:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08057","kind":"arxiv","version":1},"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/2607.08057/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":"2026-07-10T00:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dg6FUP0zxQSxfFqDtmQRy+PPPOJ4qOL/q4ItBfTkW+LYMNRKn0YHWWhdV2prpIobjmXIYCDFcip3OK9HB7sJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:53:59.665227Z"},"content_sha256":"e487952e7fb3f003781de017c0a249eb720c1b45beaf2c95fe65f669e6259a1f","schema_version":"1.0","event_id":"sha256:e487952e7fb3f003781de017c0a249eb720c1b45beaf2c95fe65f669e6259a1f"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:GNCIWYERHJYEC3XLXP7NBK2ZXJ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.21203/rs.3.rs-8770196/v1.Ying) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Power-aware deep learning model serving with µ-serve. InUSENIX Annual Technical Conference, pages 75–93. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language under- standing by generative pre-training","arxiv_id":"2607.08057","detector":"doi_compliance","evidence":{"ref_index":9,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Power-aware deep learning model serving with µ-serve. InUSENIX Annual Technical Conference, pages 75–93. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language under- standing by generative pre-training","reconstructed_doi":"10.21203/rs.3.rs-8770196/v1.Ying"},"severity":"advisory","ref_index":9,"audited_at":"2026-07-10T00:56:35.990750Z","event_type":"pith.integrity.v1","detected_doi":"10.21203/rs.3.rs-8770196/v1.Ying","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5850a0a9d99c13ab5f7df800ed5ce4974dda4b9dbf3970132f97e2459d191149","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":11543,"payload_sha256":"aa9904b7bb93576289b3e64f5419abc48fc3c80a19f22be5159c5fe61d5c6750","signature_b64":"ccinQ0ErhqjvOhDljzR9Hw47Y1HZXgSsqgn67zZ7QJolqZ9DC49hKq0me/3P3tFN2oQmHJ6KllST7euZ5er+CQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T00:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8IhSWdeo/5RCLOMyWPL8buUEdOyEtxRyPtlbIgL0A+TFY8wvQOhPQ5HqKOXms/8rM5IYFfKt0F0zldpxfEwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:53:59.675770Z"},"content_sha256":"e4ac52367bf53a8c5620a3aacf8978234969912109d27426b5dee23d62711285","schema_version":"1.0","event_id":"sha256:e4ac52367bf53a8c5620a3aacf8978234969912109d27426b5dee23d62711285"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/bundle.json","state_url":"https://pith.science/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/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":"2026-08-04T14:53:59Z","links":{"resolver":"https://pith.science/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ","bundle":"https://pith.science/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/bundle.json","state":"https://pith.science/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNCIWYERHJYEC3XLXP7NBK2ZXJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NrSYbxpfOErd+lRD8ne8i+Te3m5NP+xkvb5yYuAK+zPVMk5BU+Z/r8qW2LqElcDeoK39vl7EigjaZE2xaiJADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:53:59.677306Z","bundle_sha256":"bbb091e87719a0a931aad17753e81c23b376c2518091579019988fbebc58e938"}}