{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SMCPIW6ARLBPKQ6CE5M7OI2POY","short_pith_number":"pith:SMCPIW6A","schema_version":"1.0","canonical_sha256":"9304f45bc08ac2f543c22759f7234f761bdc315bcab2cf9290ed1def899a1e62","source":{"kind":"arxiv","id":"2606.22013","version":1},"attestation_state":"computed","paper":{"title":"Load Testing for Machine Learning Model Serving Systems at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Amr S. Abdelfattah, Dinakar Dhurjati, Eric Sung, Indu Mohanan, Nakul Tirumalai, Pengchao Wang, Xiao Li","submitted_at":"2026-06-20T12:34:27Z","abstract_excerpt":"Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc. Under-provisioning leads to service-level objective (SLO) violations and production incidents, while over-provisioning results in substantial resource waste. This paper presents \\sys, an industrial load testing framework for ML serving systems that systematically estimates serving capacity through an adaptive, feedback-driven search strategy. The approach leverages real-time performance signals, incorporating dampening, spike tolerance, and co"},"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":"2606.22013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-20T12:34:27Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"de1c492e86c3dd21bcb7e0a85f63e2130c9bc655c0adf52640cc0ac79310213b","abstract_canon_sha256":"6e4ba86d6efa1aa7a245e69c20402baa29979fcc85fe5c79440d679e673b32f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:05.563654Z","signature_b64":"aVQdSKkN8fesf1qskv1leR5IXAfBMvoBRCYe92eTWFzGjAcWcNM/FQrq3rxy2nfPSKSkwaqJ+xQ3A312CpY2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9304f45bc08ac2f543c22759f7234f761bdc315bcab2cf9290ed1def899a1e62","last_reissued_at":"2026-06-23T02:13:05.563217Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:05.563217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Load Testing for Machine Learning Model Serving Systems at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Amr S. Abdelfattah, Dinakar Dhurjati, Eric Sung, Indu Mohanan, Nakul Tirumalai, Pengchao Wang, Xiao Li","submitted_at":"2026-06-20T12:34:27Z","abstract_excerpt":"Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc. Under-provisioning leads to service-level objective (SLO) violations and production incidents, while over-provisioning results in substantial resource waste. This paper presents \\sys, an industrial load testing framework for ML serving systems that systematically estimates serving capacity through an adaptive, feedback-driven search strategy. The approach leverages real-time performance signals, incorporating dampening, spike tolerance, and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22013","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/2606.22013/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":"2606.22013","created_at":"2026-06-23T02:13:05.563288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22013v1","created_at":"2026-06-23T02:13:05.563288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22013","created_at":"2026-06-23T02:13:05.563288+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMCPIW6ARLBP","created_at":"2026-06-23T02:13:05.563288+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMCPIW6ARLBPKQ6C","created_at":"2026-06-23T02:13:05.563288+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMCPIW6A","created_at":"2026-06-23T02:13:05.563288+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/SMCPIW6ARLBPKQ6CE5M7OI2POY","json":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY.json","graph_json":"https://pith.science/api/pith-number/SMCPIW6ARLBPKQ6CE5M7OI2POY/graph.json","events_json":"https://pith.science/api/pith-number/SMCPIW6ARLBPKQ6CE5M7OI2POY/events.json","paper":"https://pith.science/paper/SMCPIW6A"},"agent_actions":{"view_html":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY","download_json":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY.json","view_paper":"https://pith.science/paper/SMCPIW6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22013&json=true","fetch_graph":"https://pith.science/api/pith-number/SMCPIW6ARLBPKQ6CE5M7OI2POY/graph.json","fetch_events":"https://pith.science/api/pith-number/SMCPIW6ARLBPKQ6CE5M7OI2POY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY/action/storage_attestation","attest_author":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY/action/author_attestation","sign_citation":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY/action/citation_signature","submit_replication":"https://pith.science/pith/SMCPIW6ARLBPKQ6CE5M7OI2POY/action/replication_record"}},"created_at":"2026-06-23T02:13:05.563288+00:00","updated_at":"2026-06-23T02:13:05.563288+00:00"}