{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HSL3CLQNEYYJBUAOB5FZ46YZDR","short_pith_number":"pith:HSL3CLQN","schema_version":"1.0","canonical_sha256":"3c97b12e0d263090d00e0f4b9e7b191c49c1236436a9e225aac15b435f4a4805","source":{"kind":"arxiv","id":"2304.10970","version":4},"attestation_state":"computed","paper":{"title":"Can GPT-4 Perform Neural Architecture Search?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Xu, Chen Qian, Fei Wang, Mingkai Zheng, Samuel Albanie, Shan You, Xiu Su","submitted_at":"2023-04-21T14:06:44Z","abstract_excerpt":"We investigate the potential of GPT-4~\\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures. Our proposed approach, \\textbf{G}PT-4 \\textbf{E}nhanced \\textbf{N}eural arch\\textbf{I}tect\\textbf{U}re \\textbf{S}earch (GENIUS), leverages the generative capabilities of GPT-4 as a black-box optimiser to quickly navigate the architecture search space, pinpoint promising candidates, and iteratively refine these candidates to improve performance. We assess GENIUS across several benchmarks, comparing it with existing state-of-the-art NAS techniques"},"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":"2304.10970","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-21T14:06:44Z","cross_cats_sorted":[],"title_canon_sha256":"73f64907a1d8891b585bbc6bc74674e80696be69e873c612c43b7d67f7f570e8","abstract_canon_sha256":"a1a5ff519f08ef0a8b863767c2b946832b49a86e13076b8f3a8ad57c8fc6a191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:54.472260Z","signature_b64":"dtw1r2AdriOoxRiDQQWQJDlzzNkNsHmBWBZMKUrxHEVj/pNLDtpdfD8J4B9jLw+utAH7frzz4q51JRIzc9WbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c97b12e0d263090d00e0f4b9e7b191c49c1236436a9e225aac15b435f4a4805","last_reissued_at":"2026-07-05T06:36:54.471771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:54.471771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GPT-4 Perform Neural Architecture Search?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Xu, Chen Qian, Fei Wang, Mingkai Zheng, Samuel Albanie, Shan You, Xiu Su","submitted_at":"2023-04-21T14:06:44Z","abstract_excerpt":"We investigate the potential of GPT-4~\\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures. Our proposed approach, \\textbf{G}PT-4 \\textbf{E}nhanced \\textbf{N}eural arch\\textbf{I}tect\\textbf{U}re \\textbf{S}earch (GENIUS), leverages the generative capabilities of GPT-4 as a black-box optimiser to quickly navigate the architecture search space, pinpoint promising candidates, and iteratively refine these candidates to improve performance. We assess GENIUS across several benchmarks, comparing it with existing state-of-the-art NAS techniques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10970","kind":"arxiv","version":4},"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/2304.10970/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":"2304.10970","created_at":"2026-07-05T06:36:54.471829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10970v4","created_at":"2026-07-05T06:36:54.471829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10970","created_at":"2026-07-05T06:36:54.471829+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSL3CLQNEYYJ","created_at":"2026-07-05T06:36:54.471829+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSL3CLQNEYYJBUAO","created_at":"2026-07-05T06:36:54.471829+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSL3CLQN","created_at":"2026-07-05T06:36:54.471829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10294","citing_title":"LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07095","citing_title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14434","citing_title":"LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21560","citing_title":"AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26037","citing_title":"CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19247","citing_title":"Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25223","citing_title":"FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2309.08532","citing_title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04903","citing_title":"Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16555","citing_title":"LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR","json":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR.json","graph_json":"https://pith.science/api/pith-number/HSL3CLQNEYYJBUAOB5FZ46YZDR/graph.json","events_json":"https://pith.science/api/pith-number/HSL3CLQNEYYJBUAOB5FZ46YZDR/events.json","paper":"https://pith.science/paper/HSL3CLQN"},"agent_actions":{"view_html":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR","download_json":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR.json","view_paper":"https://pith.science/paper/HSL3CLQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10970&json=true","fetch_graph":"https://pith.science/api/pith-number/HSL3CLQNEYYJBUAOB5FZ46YZDR/graph.json","fetch_events":"https://pith.science/api/pith-number/HSL3CLQNEYYJBUAOB5FZ46YZDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR/action/storage_attestation","attest_author":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR/action/author_attestation","sign_citation":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR/action/citation_signature","submit_replication":"https://pith.science/pith/HSL3CLQNEYYJBUAOB5FZ46YZDR/action/replication_record"}},"created_at":"2026-07-05T06:36:54.471829+00:00","updated_at":"2026-07-05T06:36:54.471829+00:00"}