{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:43Q5W3JVGVIFRLWLMPMTVWUQIP","short_pith_number":"pith:43Q5W3JV","schema_version":"1.0","canonical_sha256":"e6e1db6d35355058aecb63d93ada9043d4be99ebccd36dc64efd64914cea132d","source":{"kind":"arxiv","id":"2304.02845","version":2},"attestation_state":"computed","paper":{"title":"Robust Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jian Li, Weiping Wang, Xunyu Zhu, Yong Liu","submitted_at":"2023-04-06T03:21:24Z","abstract_excerpt":"Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to enhance the robustness of NAS-generated models, however, they neglected the nature accuracy of NAS-generated models. In our paper, we propose a novel NAS method, Robust Neural Architecture Search (RNAS). To design a regularization term to balance accuracy and robustness, RNAS generates architectures with both high accuracy and good robustness. To reduce sear"},"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":"2304.02845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-06T03:21:24Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"4e64c0105a8835dfccc73490fbb387982a66d3da288b32f90dfaa0de3cac88f2","abstract_canon_sha256":"0e5c3ce02bd6eec82f8778f2431680cd7d614d7428d4d6331a2b02d8d67cffe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:24.305299Z","signature_b64":"hfI93Xjr8Vwoj6o33swEvfYnkH8g+3gZ5a7Ud0/r/U6KCMGnWPLwLMa96XpAo1fz/XpuRhCL6YLo7bKbBlxUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e1db6d35355058aecb63d93ada9043d4be99ebccd36dc64efd64914cea132d","last_reissued_at":"2026-07-05T05:59:24.304886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:24.304886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jian Li, Weiping Wang, Xunyu Zhu, Yong Liu","submitted_at":"2023-04-06T03:21:24Z","abstract_excerpt":"Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to enhance the robustness of NAS-generated models, however, they neglected the nature accuracy of NAS-generated models. In our paper, we propose a novel NAS method, Robust Neural Architecture Search (RNAS). To design a regularization term to balance accuracy and robustness, RNAS generates architectures with both high accuracy and good robustness. To reduce sear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02845","kind":"arxiv","version":2},"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/2304.02845/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":"2304.02845","created_at":"2026-07-05T05:59:24.304938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02845v2","created_at":"2026-07-05T05:59:24.304938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02845","created_at":"2026-07-05T05:59:24.304938+00:00"},{"alias_kind":"pith_short_12","alias_value":"43Q5W3JVGVIF","created_at":"2026-07-05T05:59:24.304938+00:00"},{"alias_kind":"pith_short_16","alias_value":"43Q5W3JVGVIFRLWL","created_at":"2026-07-05T05:59:24.304938+00:00"},{"alias_kind":"pith_short_8","alias_value":"43Q5W3JV","created_at":"2026-07-05T05:59:24.304938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13485","citing_title":"Neural Architecture Search with Mixed Bio-inspired Learning Rules","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP","json":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP.json","graph_json":"https://pith.science/api/pith-number/43Q5W3JVGVIFRLWLMPMTVWUQIP/graph.json","events_json":"https://pith.science/api/pith-number/43Q5W3JVGVIFRLWLMPMTVWUQIP/events.json","paper":"https://pith.science/paper/43Q5W3JV"},"agent_actions":{"view_html":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP","download_json":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP.json","view_paper":"https://pith.science/paper/43Q5W3JV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02845&json=true","fetch_graph":"https://pith.science/api/pith-number/43Q5W3JVGVIFRLWLMPMTVWUQIP/graph.json","fetch_events":"https://pith.science/api/pith-number/43Q5W3JVGVIFRLWLMPMTVWUQIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP/action/storage_attestation","attest_author":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP/action/author_attestation","sign_citation":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP/action/citation_signature","submit_replication":"https://pith.science/pith/43Q5W3JVGVIFRLWLMPMTVWUQIP/action/replication_record"}},"created_at":"2026-07-05T05:59:24.304938+00:00","updated_at":"2026-07-05T05:59:24.304938+00:00"}