{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A4J4KHDTODO2I36NZXN225LRQV","short_pith_number":"pith:A4J4KHDT","schema_version":"1.0","canonical_sha256":"0713c51c7370dda46fcdcddbad75718553f79c1509467e0fae3e17817b1bd67e","source":{"kind":"arxiv","id":"2304.09781","version":2},"attestation_state":"computed","paper":{"title":"Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Siddharth Samsi, Vijay Gadepally","submitted_at":"2023-04-19T16:07:29Z","abstract_excerpt":"This paper presents a solution to the challenge of mitigating carbon emissions from hosting large-scale machine learning (ML) inference services. ML inference is critical to modern technology products, but it is also a significant contributor to carbon footprint. We introduce Clover, a carbon-friendly ML inference service runtime system that balances performance, accuracy, and carbon emissions through mixed-quality models and GPU resource partitioning. Our experimental results demonstrate that Clover is effective in substantially reducing carbon emissions while maintaining high accuracy and me"},"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":"2304.09781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-19T16:07:29Z","cross_cats_sorted":[],"title_canon_sha256":"a0746a65e29d538d746788ed7f1907f6607a5a58515130f866e122bcba4fab0b","abstract_canon_sha256":"16e9f33f1ccef37500c19b824d2c7965ac68a93704b2a62518abc745531de72e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:47.628057Z","signature_b64":"CPcyab8PcxIqyOc2FPlq036m9Ys7riQH9B9Nsrqvews8gpFQ8FFhcaA4F5UsgfZgwD5SX599ylkEQdUAFXUtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0713c51c7370dda46fcdcddbad75718553f79c1509467e0fae3e17817b1bd67e","last_reissued_at":"2026-07-05T06:46:47.627518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:47.627518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Baolin Li, Devesh Tiwari, Siddharth Samsi, Vijay Gadepally","submitted_at":"2023-04-19T16:07:29Z","abstract_excerpt":"This paper presents a solution to the challenge of mitigating carbon emissions from hosting large-scale machine learning (ML) inference services. ML inference is critical to modern technology products, but it is also a significant contributor to carbon footprint. We introduce Clover, a carbon-friendly ML inference service runtime system that balances performance, accuracy, and carbon emissions through mixed-quality models and GPU resource partitioning. Our experimental results demonstrate that Clover is effective in substantially reducing carbon emissions while maintaining high accuracy and me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09781","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/2304.09781/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":"2304.09781","created_at":"2026-07-05T06:46:47.627579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09781v2","created_at":"2026-07-05T06:46:47.627579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09781","created_at":"2026-07-05T06:46:47.627579+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4J4KHDTODO2","created_at":"2026-07-05T06:46:47.627579+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4J4KHDTODO2I36N","created_at":"2026-07-05T06:46:47.627579+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4J4KHDT","created_at":"2026-07-05T06:46:47.627579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11603","citing_title":"GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV","json":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV.json","graph_json":"https://pith.science/api/pith-number/A4J4KHDTODO2I36NZXN225LRQV/graph.json","events_json":"https://pith.science/api/pith-number/A4J4KHDTODO2I36NZXN225LRQV/events.json","paper":"https://pith.science/paper/A4J4KHDT"},"agent_actions":{"view_html":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV","download_json":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV.json","view_paper":"https://pith.science/paper/A4J4KHDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/A4J4KHDTODO2I36NZXN225LRQV/graph.json","fetch_events":"https://pith.science/api/pith-number/A4J4KHDTODO2I36NZXN225LRQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV/action/storage_attestation","attest_author":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV/action/author_attestation","sign_citation":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV/action/citation_signature","submit_replication":"https://pith.science/pith/A4J4KHDTODO2I36NZXN225LRQV/action/replication_record"}},"created_at":"2026-07-05T06:46:47.627579+00:00","updated_at":"2026-07-05T06:46:47.627579+00:00"}