{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLJKZO3YDMUMGD5ODKIFE7DULT","short_pith_number":"pith:OLJKZO3Y","schema_version":"1.0","canonical_sha256":"72d2acbb781b28c30fae1a90527c745cd1db9069bcbf2de5ba1eb6973056dfa7","source":{"kind":"arxiv","id":"2207.11434","version":2},"attestation_state":"computed","paper":{"title":"RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Karen Gettings, Rohan Basu Roy, Tirthak Patel, Vijay Gadepally","submitted_at":"2022-07-23T06:45:14Z","abstract_excerpt":"Deep learning model inference is a key service in many businesses and scientific discovery processes. This paper introduces RIBBON, a novel deep learning inference serving system that meets two competing objectives: quality-of-service (QoS) target and cost-effectiveness. The key idea behind RIBBON is to intelligently employ a diverse set of cloud computing instances (heterogeneous instances) to meet the QoS target and maximize cost savings. RIBBON devises a Bayesian Optimization-driven strategy that helps users build the optimal set of heterogeneous instances for their model inference service "},"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":"2207.11434","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2022-07-23T06:45:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ca53dd093d4feac696b4d72f56f43b8814df768e11dbc81142a9477c682f991","abstract_canon_sha256":"9ad3aac0a0c3e48374bcd1b880d6e0e0156ca51c06655cbb6a2359ece656f59b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:21.908725Z","signature_b64":"yyJtHmlaqhA8JDxYrY27JT61xUmunSWwubTbW4pdjURA3oheh9L9QsA6dovBwrN7WAtRPVyVuQkieV2CKjNSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d2acbb781b28c30fae1a90527c745cd1db9069bcbf2de5ba1eb6973056dfa7","last_reissued_at":"2026-07-05T04:44:21.908236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:21.908236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Karen Gettings, Rohan Basu Roy, Tirthak Patel, Vijay Gadepally","submitted_at":"2022-07-23T06:45:14Z","abstract_excerpt":"Deep learning model inference is a key service in many businesses and scientific discovery processes. This paper introduces RIBBON, a novel deep learning inference serving system that meets two competing objectives: quality-of-service (QoS) target and cost-effectiveness. The key idea behind RIBBON is to intelligently employ a diverse set of cloud computing instances (heterogeneous instances) to meet the QoS target and maximize cost savings. RIBBON devises a Bayesian Optimization-driven strategy that helps users build the optimal set of heterogeneous instances for their model inference service "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11434","kind":"arxiv","version":2},"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/2207.11434/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":"2207.11434","created_at":"2026-07-05T04:44:21.908292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11434v2","created_at":"2026-07-05T04:44:21.908292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11434","created_at":"2026-07-05T04:44:21.908292+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLJKZO3YDMUM","created_at":"2026-07-05T04:44:21.908292+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLJKZO3YDMUMGD5O","created_at":"2026-07-05T04:44:21.908292+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLJKZO3Y","created_at":"2026-07-05T04:44:21.908292+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/OLJKZO3YDMUMGD5ODKIFE7DULT","json":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT.json","graph_json":"https://pith.science/api/pith-number/OLJKZO3YDMUMGD5ODKIFE7DULT/graph.json","events_json":"https://pith.science/api/pith-number/OLJKZO3YDMUMGD5ODKIFE7DULT/events.json","paper":"https://pith.science/paper/OLJKZO3Y"},"agent_actions":{"view_html":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT","download_json":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT.json","view_paper":"https://pith.science/paper/OLJKZO3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11434&json=true","fetch_graph":"https://pith.science/api/pith-number/OLJKZO3YDMUMGD5ODKIFE7DULT/graph.json","fetch_events":"https://pith.science/api/pith-number/OLJKZO3YDMUMGD5ODKIFE7DULT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT/action/storage_attestation","attest_author":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT/action/author_attestation","sign_citation":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT/action/citation_signature","submit_replication":"https://pith.science/pith/OLJKZO3YDMUMGD5ODKIFE7DULT/action/replication_record"}},"created_at":"2026-07-05T04:44:21.908292+00:00","updated_at":"2026-07-05T04:44:21.908292+00:00"}