{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y35CDRTUEHLE4CULYLXLYEA46C","short_pith_number":"pith:Y35CDRTU","schema_version":"1.0","canonical_sha256":"c6fa21c67421d64e0a8bc2eebc101cf0a85ecbce068209c15a46fcf0d1dececb","source":{"kind":"arxiv","id":"2304.01821","version":1},"attestation_state":"computed","paper":{"title":"Data Aware Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Emil Njor, Jan Madsen, Xenofon Fafoutis","submitted_at":"2023-04-04T14:20:36Z","abstract_excerpt":"Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple"},"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":"2304.01821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-04-04T14:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"793f979ee796b725990f1578b5696e6d10fe0baefd60b910a32b228fed8acc38","abstract_canon_sha256":"c0a64d4b5005b5a13158bf5f8a1c86502df5cc2c1eb27fcbdb7d46769f051dcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:45.302284Z","signature_b64":"UqxTiUQ+yK21qlvPdmEjz8dLVB81ayJmulBMOrQweQxG7qTyVifzlhYVAsWc2riW6IRAtdclWeozjwD1VePYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6fa21c67421d64e0a8bc2eebc101cf0a85ecbce068209c15a46fcf0d1dececb","last_reissued_at":"2026-07-05T05:57:45.301824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:45.301824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Aware Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Emil Njor, Jan Madsen, Xenofon Fafoutis","submitted_at":"2023-04-04T14:20:36Z","abstract_excerpt":"Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01821","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/2304.01821/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":"2304.01821","created_at":"2026-07-05T05:57:45.301904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01821v1","created_at":"2026-07-05T05:57:45.301904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01821","created_at":"2026-07-05T05:57:45.301904+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y35CDRTUEHLE","created_at":"2026-07-05T05:57:45.301904+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y35CDRTUEHLE4CUL","created_at":"2026-07-05T05:57:45.301904+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y35CDRTU","created_at":"2026-07-05T05:57:45.301904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.00892","citing_title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C","json":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C.json","graph_json":"https://pith.science/api/pith-number/Y35CDRTUEHLE4CULYLXLYEA46C/graph.json","events_json":"https://pith.science/api/pith-number/Y35CDRTUEHLE4CULYLXLYEA46C/events.json","paper":"https://pith.science/paper/Y35CDRTU"},"agent_actions":{"view_html":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C","download_json":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C.json","view_paper":"https://pith.science/paper/Y35CDRTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01821&json=true","fetch_graph":"https://pith.science/api/pith-number/Y35CDRTUEHLE4CULYLXLYEA46C/graph.json","fetch_events":"https://pith.science/api/pith-number/Y35CDRTUEHLE4CULYLXLYEA46C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C/action/storage_attestation","attest_author":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C/action/author_attestation","sign_citation":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C/action/citation_signature","submit_replication":"https://pith.science/pith/Y35CDRTUEHLE4CULYLXLYEA46C/action/replication_record"}},"created_at":"2026-07-05T05:57:45.301904+00:00","updated_at":"2026-07-05T05:57:45.301904+00:00"}