{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M2FEMTDF3YNZBR4IIBQGJBOYW7","short_pith_number":"pith:M2FEMTDF","canonical_record":{"source":{"id":"2411.07447","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-11-12T00:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57b8c1f1045f2a74301a17cad59d784324cc23a099d3599ab640d76f9686ec62","abstract_canon_sha256":"0b1513dcade1e0aa528018d4cbd221c9b616e673de361698082e9e2fa669ab07"},"schema_version":"1.0"},"canonical_sha256":"668a464c65de1b90c78840606485d8b7d8ba017c7722e04a7a8362ae265daf30","source":{"kind":"arxiv","id":"2411.07447","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07447","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07447v5","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07447","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"M2FEMTDF3YNZ","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"M2FEMTDF3YNZBR4I","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"M2FEMTDF","created_at":"2026-07-07T02:18:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M2FEMTDF3YNZBR4IIBQGJBOYW7","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07447","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-11-12T00:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57b8c1f1045f2a74301a17cad59d784324cc23a099d3599ab640d76f9686ec62","abstract_canon_sha256":"0b1513dcade1e0aa528018d4cbd221c9b616e673de361698082e9e2fa669ab07"},"schema_version":"1.0"},"canonical_sha256":"668a464c65de1b90c78840606485d8b7d8ba017c7722e04a7a8362ae265daf30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:23.174643Z","signature_b64":"EBkWHFMXXRTsok15Ib56wKshjVA5LhczQAt9pBNsaAIuySfwRx81dcQYAskkFn+NGyGelgu9O9NpeN+pkitlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"668a464c65de1b90c78840606485d8b7d8ba017c7722e04a7a8362ae265daf30","last_reissued_at":"2026-07-07T02:18:23.173563Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:23.173563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07447","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOm4whJBD4JAfZ42++iIksGBdgWAsRByNZHJ6oqR1nv6azxQcWh71gErO5vjIb02EtrMrUC6WGByuzKSDt75Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:00:31.982633Z"},"content_sha256":"f8751e0abe37a9aa06423e8a762e839c8b00dfb86c6a912b08e096fa2d430908","schema_version":"1.0","event_id":"sha256:f8751e0abe37a9aa06423e8a762e839c8b00dfb86c6a912b08e096fa2d430908"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M2FEMTDF3YNZBR4IIBQGJBOYW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.PF","authors_text":"Anastasia Ailamaki, Darong Huang, Jiacheng Li, Kijae Hong, Kyoungmin Kim, Qunyou Liu","submitted_at":"2024-11-12T00:10:34Z","abstract_excerpt":"LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. While LLM inference systems are capable of serving millions of requests from multiple users, they often lack theoretical models to determine whether they achieve the performance upper bounds of underlying hardware resources. Beyond online workload serving, merely analyzing existing systems-or developing yet another one-is both GPU-intensive and labor-intensive. This paper provides a comprehensive survey of LLM inference systems, focusing on their cache management p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07447","kind":"arxiv","version":5},"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/2411.07447/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":"2026-07-07T02:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izYzV0wp/rh1DuxXDBqOTomO5CHL1AWLkR8BW/e7zbiNbOWw9Q0dQnCfXlfByfillDpB6edDkV8Mqe5AGQ4fDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:00:31.983565Z"},"content_sha256":"82b32608b576808e62b454e22ef611cfa6926656b962cacadaf5d37109688ac3","schema_version":"1.0","event_id":"sha256:82b32608b576808e62b454e22ef611cfa6926656b962cacadaf5d37109688ac3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/bundle.json","state_url":"https://pith.science/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/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":"2026-08-18T06:00:31Z","links":{"resolver":"https://pith.science/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7","bundle":"https://pith.science/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/bundle.json","state":"https://pith.science/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2FEMTDF3YNZBR4IIBQGJBOYW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M2FEMTDF3YNZBR4IIBQGJBOYW7","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":"0b1513dcade1e0aa528018d4cbd221c9b616e673de361698082e9e2fa669ab07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-11-12T00:10:34Z","title_canon_sha256":"57b8c1f1045f2a74301a17cad59d784324cc23a099d3599ab640d76f9686ec62"},"schema_version":"1.0","source":{"id":"2411.07447","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07447","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07447v5","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07447","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"M2FEMTDF3YNZ","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"M2FEMTDF3YNZBR4I","created_at":"2026-07-07T02:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"M2FEMTDF","created_at":"2026-07-07T02:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:82b32608b576808e62b454e22ef611cfa6926656b962cacadaf5d37109688ac3","target":"graph","created_at":"2026-07-07T02:18:23Z","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/2411.07447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. While LLM inference systems are capable of serving millions of requests from multiple users, they often lack theoretical models to determine whether they achieve the performance upper bounds of underlying hardware resources. Beyond online workload serving, merely analyzing existing systems-or developing yet another one-is both GPU-intensive and labor-intensive. This paper provides a comprehensive survey of LLM inference systems, focusing on their cache management p","authors_text":"Anastasia Ailamaki, Darong Huang, Jiacheng Li, Kijae Hong, Kyoungmin Kim, Qunyou Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-11-12T00:10:34Z","title":"Saving GPU Hours in LLM Inference System Development and Online Workloads with Simulation and DBMS-Inspired Cache Replacement Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07447","kind":"arxiv","version":5},"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:f8751e0abe37a9aa06423e8a762e839c8b00dfb86c6a912b08e096fa2d430908","target":"record","created_at":"2026-07-07T02:18:23Z","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":"0b1513dcade1e0aa528018d4cbd221c9b616e673de361698082e9e2fa669ab07","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2024-11-12T00:10:34Z","title_canon_sha256":"57b8c1f1045f2a74301a17cad59d784324cc23a099d3599ab640d76f9686ec62"},"schema_version":"1.0","source":{"id":"2411.07447","kind":"arxiv","version":5}},"canonical_sha256":"668a464c65de1b90c78840606485d8b7d8ba017c7722e04a7a8362ae265daf30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"668a464c65de1b90c78840606485d8b7d8ba017c7722e04a7a8362ae265daf30","first_computed_at":"2026-07-07T02:18:23.173563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:23.173563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EBkWHFMXXRTsok15Ib56wKshjVA5LhczQAt9pBNsaAIuySfwRx81dcQYAskkFn+NGyGelgu9O9NpeN+pkitlBA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:23.174643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07447","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8751e0abe37a9aa06423e8a762e839c8b00dfb86c6a912b08e096fa2d430908","sha256:82b32608b576808e62b454e22ef611cfa6926656b962cacadaf5d37109688ac3"],"state_sha256":"ae93e4c09fd3cda8443f325e7283edca584023e3617acb42a1dc36aa94f93e62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWRKEqOmvq6Eeb7fRFsLGuGLjKJAnXPA1M1IDB3m4lAU0KjGts5sORHJe1aAy6McbIEqxWSf4zCvqcKpseLAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:00:31.993729Z","bundle_sha256":"5b738485220fafb55b79af16980f81f951a7745b402503eebf65f3dd853eefad"}}