{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3ZIVZHX26K3ZGGJ6JAZQAFVLR3","short_pith_number":"pith:3ZIVZHX2","schema_version":"1.0","canonical_sha256":"de515c9efaf2b793193e48330016ab8ed26e71744d9dcb52099409e539054b99","source":{"kind":"arxiv","id":"2210.05889","version":3},"attestation_state":"computed","paper":{"title":"KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Siddharth Samsi, Vijay Gadepally","submitted_at":"2022-10-12T03:06:51Z","abstract_excerpt":"Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS) and cost budget constraints. This paper introduces KAIROS, a novel runtime framework that maximizes the query throughput while meeting QoS target and a cost budget. KAIROS designs and implements novel techniques to build a pool of heterogeneous compute hardware without online exploration overhead, and distribute inference queries optimally at runtime. Our eva"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.05889","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-10-12T03:06:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e5803ef68fa1dd92b7b04d7e26d30f1905b77a36b3e561ef4903882f33d3b8d","abstract_canon_sha256":"eb7265b83e66bcb2736078fbe89dc48fff4f230ad58d67ba6071d2aabd33c285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:28.930857Z","signature_b64":"V48IfNIUxA8WVCtZzC4uTRfE7I5T1vd53xdEIobSLfh7qzevIG/uH9hvsFVd6uLTtXRrUusin2NGOVBjeTkUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de515c9efaf2b793193e48330016ab8ed26e71744d9dcb52099409e539054b99","last_reissued_at":"2026-07-05T06:06:28.930364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:28.930364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Siddharth Samsi, Vijay Gadepally","submitted_at":"2022-10-12T03:06:51Z","abstract_excerpt":"Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS) and cost budget constraints. This paper introduces KAIROS, a novel runtime framework that maximizes the query throughput while meeting QoS target and a cost budget. KAIROS designs and implements novel techniques to build a pool of heterogeneous compute hardware without online exploration overhead, and distribute inference queries optimally at runtime. Our eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05889","kind":"arxiv","version":3},"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/2210.05889/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.05889","created_at":"2026-07-05T06:06:28.930427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05889v3","created_at":"2026-07-05T06:06:28.930427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05889","created_at":"2026-07-05T06:06:28.930427+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZIVZHX26K3Z","created_at":"2026-07-05T06:06:28.930427+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZIVZHX26K3ZGGJ6","created_at":"2026-07-05T06:06:28.930427+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZIVZHX2","created_at":"2026-07-05T06:06:28.930427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3","json":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3.json","graph_json":"https://pith.science/api/pith-number/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/graph.json","events_json":"https://pith.science/api/pith-number/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/events.json","paper":"https://pith.science/paper/3ZIVZHX2"},"agent_actions":{"view_html":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3","download_json":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3.json","view_paper":"https://pith.science/paper/3ZIVZHX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05889&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/action/storage_attestation","attest_author":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/action/author_attestation","sign_citation":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/action/citation_signature","submit_replication":"https://pith.science/pith/3ZIVZHX26K3ZGGJ6JAZQAFVLR3/action/replication_record"}},"created_at":"2026-07-05T06:06:28.930427+00:00","updated_at":"2026-07-05T06:06:28.930427+00:00"}