{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YXAZQW5MKJ7IZUVFCI2WDLVTOU","short_pith_number":"pith:YXAZQW5M","schema_version":"1.0","canonical_sha256":"c5c1985bac527e8cd2a5123561aeb375156d3de3cbcefdd3365d179130e52df3","source":{"kind":"arxiv","id":"2203.12412","version":1},"attestation_state":"computed","paper":{"title":"U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ahmet Caner Y\\\"uz\\\"ug\\\"uler, Nikolaos Dimitriadis, Pascal Frossard","submitted_at":"2022-03-23T13:44:15Z","abstract_excerpt":"Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture search (NAS) methods have omitted resource utilization, preventing DNNs to take full advantage of the target inference platforms. Modeling resource utilization efficiently and accurately is challenging, especially for widely-used array-based inference accelerators such as Google TPU. In this work, we propose a novel hardware-aware NAS framewo"},"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":"2203.12412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T13:44:15Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"456ae0fd8d2eeb4e919f3523ccebc9e2e67c42a14df927a4afed21d04b1e51bf","abstract_canon_sha256":"d48032f0e57b384ddc0c93ec5583ff2340f76a7ab8f36cf0a636a2f3b96b8e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:59.204935Z","signature_b64":"wjf4v4V3V8Nr+Bnfsv7PI+WT8KkLusUsDkIKHKWEIcFediJHWx4Acr5Ccaze933+axD/HVnAiQo1Xp/U8BQLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5c1985bac527e8cd2a5123561aeb375156d3de3cbcefdd3365d179130e52df3","last_reissued_at":"2026-07-05T04:07:59.204560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:59.204560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ahmet Caner Y\\\"uz\\\"ug\\\"uler, Nikolaos Dimitriadis, Pascal Frossard","submitted_at":"2022-03-23T13:44:15Z","abstract_excerpt":"Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture search (NAS) methods have omitted resource utilization, preventing DNNs to take full advantage of the target inference platforms. Modeling resource utilization efficiently and accurately is challenging, especially for widely-used array-based inference accelerators such as Google TPU. In this work, we propose a novel hardware-aware NAS framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12412","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/2203.12412/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":"2203.12412","created_at":"2026-07-05T04:07:59.204616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12412v1","created_at":"2026-07-05T04:07:59.204616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12412","created_at":"2026-07-05T04:07:59.204616+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXAZQW5MKJ7I","created_at":"2026-07-05T04:07:59.204616+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXAZQW5MKJ7IZUVF","created_at":"2026-07-05T04:07:59.204616+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXAZQW5M","created_at":"2026-07-05T04:07:59.204616+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/YXAZQW5MKJ7IZUVFCI2WDLVTOU","json":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU.json","graph_json":"https://pith.science/api/pith-number/YXAZQW5MKJ7IZUVFCI2WDLVTOU/graph.json","events_json":"https://pith.science/api/pith-number/YXAZQW5MKJ7IZUVFCI2WDLVTOU/events.json","paper":"https://pith.science/paper/YXAZQW5M"},"agent_actions":{"view_html":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU","download_json":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU.json","view_paper":"https://pith.science/paper/YXAZQW5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12412&json=true","fetch_graph":"https://pith.science/api/pith-number/YXAZQW5MKJ7IZUVFCI2WDLVTOU/graph.json","fetch_events":"https://pith.science/api/pith-number/YXAZQW5MKJ7IZUVFCI2WDLVTOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU/action/storage_attestation","attest_author":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU/action/author_attestation","sign_citation":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU/action/citation_signature","submit_replication":"https://pith.science/pith/YXAZQW5MKJ7IZUVFCI2WDLVTOU/action/replication_record"}},"created_at":"2026-07-05T04:07:59.204616+00:00","updated_at":"2026-07-05T04:07:59.204616+00:00"}