{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GMT5ZAZIDKKOCDX5FK4HP5VYF6","short_pith_number":"pith:GMT5ZAZI","schema_version":"1.0","canonical_sha256":"3327dc83281a94e10efd2ab877f6b82f9d18115851c6c1f262febc56dc3b1d57","source":{"kind":"arxiv","id":"2504.02280","version":1},"attestation_state":"computed","paper":{"title":"LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Jason Zutty, Yiming Yu","submitted_at":"2025-04-03T05:06:06Z","abstract_excerpt":"In machine learning, Neural Architecture Search (NAS) requires domain knowledge of model design and a large amount of trial-and-error to achieve promising performance. Meanwhile, evolutionary algorithms have traditionally relied on fixed rules and pre-defined building blocks. The Large Language Model (LLM)-Guided Evolution (GE) framework transformed this approach by incorporating LLMs to directly modify model source code for image classification algorithms on CIFAR data and intelligently guide mutations and crossovers. A key element of LLM-GE is the \"Evolution of Thought\" (EoT) technique, whic"},"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":"2504.02280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-04-03T05:06:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"37af9657ea3e53e90c292820e37d38019a18f74dc6a82d9994135cef13800822","abstract_canon_sha256":"bd593e75271b6b6d657f5471e8b97aed3bb3641c8f816085bab0071da30db3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:54.043041Z","signature_b64":"Gtw8ciCEShRIuixhVyKzVuaDOCUtTqDK3Jxz5u87tbxnL6Y+Vb2j5JYuxxQGU/YUrZ4VHd01BbU2WKCXxOcvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3327dc83281a94e10efd2ab877f6b82f9d18115851c6c1f262febc56dc3b1d57","last_reissued_at":"2026-07-05T10:43:54.042536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:54.042536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Jason Zutty, Yiming Yu","submitted_at":"2025-04-03T05:06:06Z","abstract_excerpt":"In machine learning, Neural Architecture Search (NAS) requires domain knowledge of model design and a large amount of trial-and-error to achieve promising performance. Meanwhile, evolutionary algorithms have traditionally relied on fixed rules and pre-defined building blocks. The Large Language Model (LLM)-Guided Evolution (GE) framework transformed this approach by incorporating LLMs to directly modify model source code for image classification algorithms on CIFAR data and intelligently guide mutations and crossovers. A key element of LLM-GE is the \"Evolution of Thought\" (EoT) technique, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02280","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/2504.02280/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":"2504.02280","created_at":"2026-07-05T10:43:54.042598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02280v1","created_at":"2026-07-05T10:43:54.042598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02280","created_at":"2026-07-05T10:43:54.042598+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMT5ZAZIDKKO","created_at":"2026-07-05T10:43:54.042598+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMT5ZAZIDKKOCDX5","created_at":"2026-07-05T10:43:54.042598+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMT5ZAZI","created_at":"2026-07-05T10:43:54.042598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21544","citing_title":"Vision Meets Language: A RAG-Augmented YOLOv8 Framework for Coffee Disease Diagnosis and Farmer Assistance","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6","json":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6.json","graph_json":"https://pith.science/api/pith-number/GMT5ZAZIDKKOCDX5FK4HP5VYF6/graph.json","events_json":"https://pith.science/api/pith-number/GMT5ZAZIDKKOCDX5FK4HP5VYF6/events.json","paper":"https://pith.science/paper/GMT5ZAZI"},"agent_actions":{"view_html":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6","download_json":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6.json","view_paper":"https://pith.science/paper/GMT5ZAZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02280&json=true","fetch_graph":"https://pith.science/api/pith-number/GMT5ZAZIDKKOCDX5FK4HP5VYF6/graph.json","fetch_events":"https://pith.science/api/pith-number/GMT5ZAZIDKKOCDX5FK4HP5VYF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6/action/storage_attestation","attest_author":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6/action/author_attestation","sign_citation":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6/action/citation_signature","submit_replication":"https://pith.science/pith/GMT5ZAZIDKKOCDX5FK4HP5VYF6/action/replication_record"}},"created_at":"2026-07-05T10:43:54.042598+00:00","updated_at":"2026-07-05T10:43:54.042598+00:00"}