{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LSQW2KXMLMYXYKBPFLDGGHXDXE","short_pith_number":"pith:LSQW2KXM","schema_version":"1.0","canonical_sha256":"5ca16d2aec5b317c282f2ac6631ee3b9031da47e3e477d95ff6ae21907945ebe","source":{"kind":"arxiv","id":"2301.12865","version":3},"attestation_state":"computed","paper":{"title":"SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Jingzhou Sun, Sheng Zhou, Yaodan Xu, Zhisheng Niu","submitted_at":"2023-01-30T13:19:16Z","abstract_excerpt":"In up-to-date machine learning (ML) applications on cloud or edge computing platforms, batching is an important technique for providing efficient and economical services at scale. In particular, parallel computing resources on the platforms, such as graphics processing units (GPUs), have higher computational and energy efficiency with larger batch sizes. However, larger batch sizes may also result in longer response time, and thus it requires a judicious design. This paper aims to provide a dynamic batching policy that strikes a balance between efficiency and latency. The GPU-based inference s"},"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":"2301.12865","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T13:19:16Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"cb3e53ce3aad9903dbeade24856e9bbb4be09a048f4a83995085b36117eaf433","abstract_canon_sha256":"b9d7a9c6b6e1aa3417da0b91056eb2502ce123a2307514801cdfc49cec1785c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:45.558646Z","signature_b64":"aPL3r4o7K2SY4IgXAwTBd61tysv6bUWZgkFc01SYliHtKRmr2jOa9IfPDuiPQKs2dd5b1tWnResMUD4QrNEyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ca16d2aec5b317c282f2ac6631ee3b9031da47e3e477d95ff6ae21907945ebe","last_reissued_at":"2026-07-05T06:46:45.558089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:45.558089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Jingzhou Sun, Sheng Zhou, Yaodan Xu, Zhisheng Niu","submitted_at":"2023-01-30T13:19:16Z","abstract_excerpt":"In up-to-date machine learning (ML) applications on cloud or edge computing platforms, batching is an important technique for providing efficient and economical services at scale. In particular, parallel computing resources on the platforms, such as graphics processing units (GPUs), have higher computational and energy efficiency with larger batch sizes. However, larger batch sizes may also result in longer response time, and thus it requires a judicious design. This paper aims to provide a dynamic batching policy that strikes a balance between efficiency and latency. The GPU-based inference s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12865","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/2301.12865/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":"2301.12865","created_at":"2026-07-05T06:46:45.558150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12865v3","created_at":"2026-07-05T06:46:45.558150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12865","created_at":"2026-07-05T06:46:45.558150+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSQW2KXMLMYX","created_at":"2026-07-05T06:46:45.558150+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSQW2KXMLMYXYKBP","created_at":"2026-07-05T06:46:45.558150+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSQW2KXM","created_at":"2026-07-05T06:46:45.558150+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/LSQW2KXMLMYXYKBPFLDGGHXDXE","json":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE.json","graph_json":"https://pith.science/api/pith-number/LSQW2KXMLMYXYKBPFLDGGHXDXE/graph.json","events_json":"https://pith.science/api/pith-number/LSQW2KXMLMYXYKBPFLDGGHXDXE/events.json","paper":"https://pith.science/paper/LSQW2KXM"},"agent_actions":{"view_html":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE","download_json":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE.json","view_paper":"https://pith.science/paper/LSQW2KXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12865&json=true","fetch_graph":"https://pith.science/api/pith-number/LSQW2KXMLMYXYKBPFLDGGHXDXE/graph.json","fetch_events":"https://pith.science/api/pith-number/LSQW2KXMLMYXYKBPFLDGGHXDXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE/action/storage_attestation","attest_author":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE/action/author_attestation","sign_citation":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE/action/citation_signature","submit_replication":"https://pith.science/pith/LSQW2KXMLMYXYKBPFLDGGHXDXE/action/replication_record"}},"created_at":"2026-07-05T06:46:45.558150+00:00","updated_at":"2026-07-05T06:46:45.558150+00:00"}