{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RSPCC6P2KGLYF54S6HSXAJSHSG","short_pith_number":"pith:RSPCC6P2","schema_version":"1.0","canonical_sha256":"8c9e2179fa519782f792f1e5702647918d95653347a4b71f8405b0a52e1cac5c","source":{"kind":"arxiv","id":"2312.16733","version":1},"attestation_state":"computed","paper":{"title":"SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Alexey Tumanov, Alind Khare, Dhruv Garg, Ion Stoica, Snigdha Grandhi, Sukrit Kalra","submitted_at":"2023-12-27T22:24:11Z","abstract_excerpt":"The increasing deployment of ML models on the critical path of production applications in both datacenter and the edge requires ML inference serving systems to serve these models under unpredictable and bursty request arrival rates. Serving models under such conditions requires these systems to strike a careful balance between the latency and accuracy requirements of the application and the overall efficiency of utilization of scarce resources. State-of-the-art systems resolve this tension by either choosing a static point in the latency-accuracy tradeoff space to serve all requests or load sp"},"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":"2312.16733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-27T22:24:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1028e41ad40ffd6d548d383339ae8a4f95639ed36db0a547b3fc91d45190bd65","abstract_canon_sha256":"d52e7350fce398708311af6bc4bdd0291607ab44052e4cc6ea00c3b910266589"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:34.629182Z","signature_b64":"jZ9NHaS6F6gcBrm9Nbvd/ceaAoQjDLlEeu0RBfG58/VO22oI71nCQB0K2CeNnnRfnScVTNTXXsuz78AkzsOMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9e2179fa519782f792f1e5702647918d95653347a4b71f8405b0a52e1cac5c","last_reissued_at":"2026-07-05T07:28:34.628728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:34.628728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Alexey Tumanov, Alind Khare, Dhruv Garg, Ion Stoica, Snigdha Grandhi, Sukrit Kalra","submitted_at":"2023-12-27T22:24:11Z","abstract_excerpt":"The increasing deployment of ML models on the critical path of production applications in both datacenter and the edge requires ML inference serving systems to serve these models under unpredictable and bursty request arrival rates. Serving models under such conditions requires these systems to strike a careful balance between the latency and accuracy requirements of the application and the overall efficiency of utilization of scarce resources. State-of-the-art systems resolve this tension by either choosing a static point in the latency-accuracy tradeoff space to serve all requests or load sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16733","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/2312.16733/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":"2312.16733","created_at":"2026-07-05T07:28:34.628779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16733v1","created_at":"2026-07-05T07:28:34.628779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16733","created_at":"2026-07-05T07:28:34.628779+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSPCC6P2KGLY","created_at":"2026-07-05T07:28:34.628779+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSPCC6P2KGLYF54S","created_at":"2026-07-05T07:28:34.628779+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSPCC6P2","created_at":"2026-07-05T07:28:34.628779+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/RSPCC6P2KGLYF54S6HSXAJSHSG","json":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG.json","graph_json":"https://pith.science/api/pith-number/RSPCC6P2KGLYF54S6HSXAJSHSG/graph.json","events_json":"https://pith.science/api/pith-number/RSPCC6P2KGLYF54S6HSXAJSHSG/events.json","paper":"https://pith.science/paper/RSPCC6P2"},"agent_actions":{"view_html":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG","download_json":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG.json","view_paper":"https://pith.science/paper/RSPCC6P2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16733&json=true","fetch_graph":"https://pith.science/api/pith-number/RSPCC6P2KGLYF54S6HSXAJSHSG/graph.json","fetch_events":"https://pith.science/api/pith-number/RSPCC6P2KGLYF54S6HSXAJSHSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG/action/storage_attestation","attest_author":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG/action/author_attestation","sign_citation":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG/action/citation_signature","submit_replication":"https://pith.science/pith/RSPCC6P2KGLYF54S6HSXAJSHSG/action/replication_record"}},"created_at":"2026-07-05T07:28:34.628779+00:00","updated_at":"2026-07-05T07:28:34.628779+00:00"}