{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5YGN37HHEG7GXKBJ722BEVVMIG","short_pith_number":"pith:5YGN37HH","canonical_record":{"source":{"id":"2406.14424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-20T15:47:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"145b4d0fb4b331bc9e5c3e7c6b21c6e6eabf195651090e0fc1a6b76af02a8fea","abstract_canon_sha256":"78882cc906dcba1a7a3352bf54bf48b2acc4713ad261fb17e0d2067640faf10c"},"schema_version":"1.0"},"canonical_sha256":"ee0cddfce721be6ba829feb41256ac41a3985b16de316f6f083e9fb625aae3ac","source":{"kind":"arxiv","id":"2406.14424","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14424","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14424v1","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14424","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_12","alias_value":"5YGN37HHEG7G","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_16","alias_value":"5YGN37HHEG7GXKBJ","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_8","alias_value":"5YGN37HH","created_at":"2026-07-05T08:34:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5YGN37HHEG7GXKBJ722BEVVMIG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-20T15:47:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"145b4d0fb4b331bc9e5c3e7c6b21c6e6eabf195651090e0fc1a6b76af02a8fea","abstract_canon_sha256":"78882cc906dcba1a7a3352bf54bf48b2acc4713ad261fb17e0d2067640faf10c"},"schema_version":"1.0"},"canonical_sha256":"ee0cddfce721be6ba829feb41256ac41a3985b16de316f6f083e9fb625aae3ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:50.605126Z","signature_b64":"hHJsou11fPdk3TkwDL4/4oAS2oUBEy7mifAuPWrNOif8ZAy0qsOExS3Q2xAhb5rYs49aULYjJXRckf9P6EZbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0cddfce721be6ba829feb41256ac41a3985b16de316f6f083e9fb625aae3ac","last_reissued_at":"2026-07-05T08:34:50.604642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:50.604642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14424","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":"2026-07-05T08:34:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjpNFp+TxguapcXeE6XshrWOxBTVc5Qf+OCS4C3hUCxAb451Nru6eBO3CeFd8qvFqgFIMo8xqkQNlmroNfFuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:52:39.844213Z"},"content_sha256":"85b9db84195b389ab45e65b44b9d1fdda03539e3c545f36c6dd78003de5060d2","schema_version":"1.0","event_id":"sha256:85b9db84195b389ab45e65b44b9d1fdda03539e3c545f36c6dd78003de5060d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5YGN37HHEG7GXKBJ722BEVVMIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CascadeServe: Unlocking Model Cascades for Inference Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Alex Turk, Ferdi Kossmann, Lei Cao, Nesime Tatbul, Samuel Madden, Ziniu Wu","submitted_at":"2024-06-20T15:47:37Z","abstract_excerpt":"Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges: (i) ML models incur high computational costs, and (ii) the request arrival rates of practical applications have frequent, high, and sudden variations which make it hard to correctly provision hardware. Model cascades are positioned to tackle both of these challenges, as they (i) save work while maintaining accuracy, and (ii) expose a high-resolution trade-off between work and accuracy, allowing for fine-grained adju"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14424","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/2406.14424/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":"2026-07-05T08:34:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2j/23Sfu7rUKamrHPlygI3eSJpAAigT7nicwN/1EQp8WW6GfH1q87BioaZ2ukOJUcZBo8zlSf9c0vK3sgBSYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:52:39.845089Z"},"content_sha256":"6cfde7c9c5d12614da40c5bea36b597e1b779fd8c0d017cb0f43e40e119f01a4","schema_version":"1.0","event_id":"sha256:6cfde7c9c5d12614da40c5bea36b597e1b779fd8c0d017cb0f43e40e119f01a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YGN37HHEG7GXKBJ722BEVVMIG/bundle.json","state_url":"https://pith.science/pith/5YGN37HHEG7GXKBJ722BEVVMIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YGN37HHEG7GXKBJ722BEVVMIG/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":"2026-08-09T04:52:39Z","links":{"resolver":"https://pith.science/pith/5YGN37HHEG7GXKBJ722BEVVMIG","bundle":"https://pith.science/pith/5YGN37HHEG7GXKBJ722BEVVMIG/bundle.json","state":"https://pith.science/pith/5YGN37HHEG7GXKBJ722BEVVMIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YGN37HHEG7GXKBJ722BEVVMIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5YGN37HHEG7GXKBJ722BEVVMIG","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":"78882cc906dcba1a7a3352bf54bf48b2acc4713ad261fb17e0d2067640faf10c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-20T15:47:37Z","title_canon_sha256":"145b4d0fb4b331bc9e5c3e7c6b21c6e6eabf195651090e0fc1a6b76af02a8fea"},"schema_version":"1.0","source":{"id":"2406.14424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14424","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14424v1","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14424","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_12","alias_value":"5YGN37HHEG7G","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_16","alias_value":"5YGN37HHEG7GXKBJ","created_at":"2026-07-05T08:34:50Z"},{"alias_kind":"pith_short_8","alias_value":"5YGN37HH","created_at":"2026-07-05T08:34:50Z"}],"graph_snapshots":[{"event_id":"sha256:6cfde7c9c5d12614da40c5bea36b597e1b779fd8c0d017cb0f43e40e119f01a4","target":"graph","created_at":"2026-07-05T08:34:50Z","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/2406.14424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges: (i) ML models incur high computational costs, and (ii) the request arrival rates of practical applications have frequent, high, and sudden variations which make it hard to correctly provision hardware. Model cascades are positioned to tackle both of these challenges, as they (i) save work while maintaining accuracy, and (ii) expose a high-resolution trade-off between work and accuracy, allowing for fine-grained adju","authors_text":"Alex Turk, Ferdi Kossmann, Lei Cao, Nesime Tatbul, Samuel Madden, Ziniu Wu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-20T15:47:37Z","title":"CascadeServe: Unlocking Model Cascades for Inference Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14424","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":"sha256:85b9db84195b389ab45e65b44b9d1fdda03539e3c545f36c6dd78003de5060d2","target":"record","created_at":"2026-07-05T08:34:50Z","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":"78882cc906dcba1a7a3352bf54bf48b2acc4713ad261fb17e0d2067640faf10c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-06-20T15:47:37Z","title_canon_sha256":"145b4d0fb4b331bc9e5c3e7c6b21c6e6eabf195651090e0fc1a6b76af02a8fea"},"schema_version":"1.0","source":{"id":"2406.14424","kind":"arxiv","version":1}},"canonical_sha256":"ee0cddfce721be6ba829feb41256ac41a3985b16de316f6f083e9fb625aae3ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee0cddfce721be6ba829feb41256ac41a3985b16de316f6f083e9fb625aae3ac","first_computed_at":"2026-07-05T08:34:50.604642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:50.604642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hHJsou11fPdk3TkwDL4/4oAS2oUBEy7mifAuPWrNOif8ZAy0qsOExS3Q2xAhb5rYs49aULYjJXRckf9P6EZbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:50.605126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85b9db84195b389ab45e65b44b9d1fdda03539e3c545f36c6dd78003de5060d2","sha256:6cfde7c9c5d12614da40c5bea36b597e1b779fd8c0d017cb0f43e40e119f01a4"],"state_sha256":"6630146a8f23f0f8c660110dda5edd34780fa9a84a8d8c59bbb8147876ea76ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjkVTDH9A/QHl/RGKcuhYMDNF9KjCZLOsgomxBKAQ4J74K/KegvcVjzvWy3CFglmRP9fMQH68n2KeJqDqNugDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:52:39.851852Z","bundle_sha256":"56d1f3d4c008e5c2c3a2980228ce854a388e722f2f5c582711ac93cde21f7ccd"}}