{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OPNOUVTAHXDZQN5LRY7XBVIPMA","short_pith_number":"pith:OPNOUVTA","schema_version":"1.0","canonical_sha256":"73daea56603dc79837ab8e3f70d50f6004d04dd51f437ab8abe669d297c03f2c","source":{"kind":"arxiv","id":"2212.07936","version":1},"attestation_state":"computed","paper":{"title":"A Study on the Intersection of GPU Utilization and CNN Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Amar Phanishayee, Jack Kosaian","submitted_at":"2022-12-15T16:11:40Z","abstract_excerpt":"There has been significant progress in developing neural network architectures that both achieve high predictive performance and that also achieve high application-level inference throughput (e.g., frames per second). Another metric of increasing importance is GPU utilization during inference: the measurement of how well a deployed neural network uses the computational capabilities of the GPU on which it runs. Achieving high GPU utilization is critical to increasing application-level throughput and ensuring a good return on investment for deploying GPUs.\n  This paper analyzes the GPU utilizati"},"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":"2212.07936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T16:11:40Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"7504f4f449fad784d70272c5c6ea06167bcf4b08cd8177a472d80380c8150c1a","abstract_canon_sha256":"07f442af058cfa4ce6580fbd5bef7c22f2c493e87b70c5dd51b92bee7d314165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:39.173541Z","signature_b64":"KCr05EOqregL+ziUoKFTwHxj8rtMXEo+k0Urqc9+pgqpm84h7jeXBVazN9B+sRt1WoIYliLhuHf2N5CNnkcqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73daea56603dc79837ab8e3f70d50f6004d04dd51f437ab8abe669d297c03f2c","last_reissued_at":"2026-07-05T05:25:39.173068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:39.173068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study on the Intersection of GPU Utilization and CNN Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Amar Phanishayee, Jack Kosaian","submitted_at":"2022-12-15T16:11:40Z","abstract_excerpt":"There has been significant progress in developing neural network architectures that both achieve high predictive performance and that also achieve high application-level inference throughput (e.g., frames per second). Another metric of increasing importance is GPU utilization during inference: the measurement of how well a deployed neural network uses the computational capabilities of the GPU on which it runs. Achieving high GPU utilization is critical to increasing application-level throughput and ensuring a good return on investment for deploying GPUs.\n  This paper analyzes the GPU utilizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07936","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/2212.07936/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":"2212.07936","created_at":"2026-07-05T05:25:39.173132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07936v1","created_at":"2026-07-05T05:25:39.173132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07936","created_at":"2026-07-05T05:25:39.173132+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPNOUVTAHXDZ","created_at":"2026-07-05T05:25:39.173132+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPNOUVTAHXDZQN5L","created_at":"2026-07-05T05:25:39.173132+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPNOUVTA","created_at":"2026-07-05T05:25:39.173132+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/OPNOUVTAHXDZQN5LRY7XBVIPMA","json":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA.json","graph_json":"https://pith.science/api/pith-number/OPNOUVTAHXDZQN5LRY7XBVIPMA/graph.json","events_json":"https://pith.science/api/pith-number/OPNOUVTAHXDZQN5LRY7XBVIPMA/events.json","paper":"https://pith.science/paper/OPNOUVTA"},"agent_actions":{"view_html":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA","download_json":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA.json","view_paper":"https://pith.science/paper/OPNOUVTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07936&json=true","fetch_graph":"https://pith.science/api/pith-number/OPNOUVTAHXDZQN5LRY7XBVIPMA/graph.json","fetch_events":"https://pith.science/api/pith-number/OPNOUVTAHXDZQN5LRY7XBVIPMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA/action/storage_attestation","attest_author":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA/action/author_attestation","sign_citation":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA/action/citation_signature","submit_replication":"https://pith.science/pith/OPNOUVTAHXDZQN5LRY7XBVIPMA/action/replication_record"}},"created_at":"2026-07-05T05:25:39.173132+00:00","updated_at":"2026-07-05T05:25:39.173132+00:00"}