{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GDV4EO5HJCC5GSK54ZLUACTZRU","short_pith_number":"pith:GDV4EO5H","schema_version":"1.0","canonical_sha256":"30ebc23ba74885d3495de657400a798d04268dc6ce8d4e49d82f565a8bf26cb9","source":{"kind":"arxiv","id":"2306.01102","version":8},"attestation_state":"computed","paper":{"title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.NE","authors_text":"Christopher Cleghorn, Julian Togelius, Muhammad U. Nasir, Sam Earle, Steven James","submitted_at":"2023-06-01T19:33:21Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have made a significant impact is in the domain of code generation. Here, we propose using the coding abilities of LLMs to introduce meaningful variations to code defining neural networks. Meanwhile, Quality-Diversity (QD) algorithms are known to discover diverse and robust solutions. By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \\texttt{LLMatic}, a Neural A"},"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":"2306.01102","kind":"arxiv","version":8},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2023-06-01T19:33:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ffa1d6d89893a3952bfe4c7c3e7fddd53eb22e46af9b5d2573ce496f3bf59ca5","abstract_canon_sha256":"dce5ff9a508f541325e36e42ef04d99347c5f15fc29e3e603b7f0dc841869c18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:48.921589Z","signature_b64":"r3jCy7S7qkKV/EyfApv1tk9FZAxm1qWhpUNv3gQTEcihNbhAClDC2FkQdw59MnQsRewObXW2TAW1RZmA6HfFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30ebc23ba74885d3495de657400a798d04268dc6ce8d4e49d82f565a8bf26cb9","last_reissued_at":"2026-07-05T08:08:48.921125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:48.921125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.NE","authors_text":"Christopher Cleghorn, Julian Togelius, Muhammad U. Nasir, Sam Earle, Steven James","submitted_at":"2023-06-01T19:33:21Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have made a significant impact is in the domain of code generation. Here, we propose using the coding abilities of LLMs to introduce meaningful variations to code defining neural networks. Meanwhile, Quality-Diversity (QD) algorithms are known to discover diverse and robust solutions. By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \\texttt{LLMatic}, a Neural A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01102","kind":"arxiv","version":8},"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/2306.01102/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":"2306.01102","created_at":"2026-07-05T08:08:48.921180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01102v8","created_at":"2026-07-05T08:08:48.921180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01102","created_at":"2026-07-05T08:08:48.921180+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDV4EO5HJCC5","created_at":"2026-07-05T08:08:48.921180+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDV4EO5HJCC5GSK5","created_at":"2026-07-05T08:08:48.921180+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDV4EO5H","created_at":"2026-07-05T08:08:48.921180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05704","citing_title":"LLM-Driven Neural Network Generation with Same-Family Architecture Guidance: Disentangling Transfer and Adaptation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30109","citing_title":"TacEvo: Self-Evolving Architecture Discovery for Robotic Tactile Perception via LLM-Driven Quality-Diversity Search","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08517","citing_title":"Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04903","citing_title":"Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU","json":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU.json","graph_json":"https://pith.science/api/pith-number/GDV4EO5HJCC5GSK54ZLUACTZRU/graph.json","events_json":"https://pith.science/api/pith-number/GDV4EO5HJCC5GSK54ZLUACTZRU/events.json","paper":"https://pith.science/paper/GDV4EO5H"},"agent_actions":{"view_html":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU","download_json":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU.json","view_paper":"https://pith.science/paper/GDV4EO5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01102&json=true","fetch_graph":"https://pith.science/api/pith-number/GDV4EO5HJCC5GSK54ZLUACTZRU/graph.json","fetch_events":"https://pith.science/api/pith-number/GDV4EO5HJCC5GSK54ZLUACTZRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU/action/storage_attestation","attest_author":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU/action/author_attestation","sign_citation":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU/action/citation_signature","submit_replication":"https://pith.science/pith/GDV4EO5HJCC5GSK54ZLUACTZRU/action/replication_record"}},"created_at":"2026-07-05T08:08:48.921180+00:00","updated_at":"2026-07-05T08:08:48.921180+00:00"}