{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOTKO4QLE4GHGIQMBJIH6IEVLQ","short_pith_number":"pith:TOTKO4QL","schema_version":"1.0","canonical_sha256":"9ba6a7720b270c73220c0a507f20955c0d587acc6b6d2ead30d332ae68f0da08","source":{"kind":"arxiv","id":"2501.00829","version":2},"attestation_state":"computed","paper":{"title":"An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"An Guo, Guoquan Wu, Haoxiang Tian, Jun Wei, Shuo Li, Tianwei Zhang, Xingshuo Han, Yuan Zhou. Jie Zhang","submitted_at":"2025-01-01T13:19:58Z","abstract_excerpt":"Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $\\mu$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $\\mu$MOEA promotes the LLM to comprehend the optimization problem and generat"},"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":"2501.00829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-01-01T13:19:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"659a5373fe9bfd2596aa4542c47844901de50d92d05673055fee1e5f0f7cf0b3","abstract_canon_sha256":"be2f25e15dd5befb86011ce802212d95b3bcdf5a86689fc49d7aa7e464103d7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:23.369955Z","signature_b64":"o5acoKWZ6N8TLBovRpQ6G5pJcUwn+UYB1wHF6aIpwJ6JfNky2gdm1785OynYaeL5O5FYE7IwN/ICzQvtURK9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba6a7720b270c73220c0a507f20955c0d587acc6b6d2ead30d332ae68f0da08","last_reissued_at":"2026-07-05T11:19:23.369518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:23.369518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"An Guo, Guoquan Wu, Haoxiang Tian, Jun Wei, Shuo Li, Tianwei Zhang, Xingshuo Han, Yuan Zhou. Jie Zhang","submitted_at":"2025-01-01T13:19:58Z","abstract_excerpt":"Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $\\mu$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $\\mu$MOEA promotes the LLM to comprehend the optimization problem and generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00829","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/2501.00829/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":"2501.00829","created_at":"2026-07-05T11:19:23.369574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00829v2","created_at":"2026-07-05T11:19:23.369574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00829","created_at":"2026-07-05T11:19:23.369574+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOTKO4QLE4GH","created_at":"2026-07-05T11:19:23.369574+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOTKO4QLE4GHGIQM","created_at":"2026-07-05T11:19:23.369574+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOTKO4QL","created_at":"2026-07-05T11:19:23.369574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ","json":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ.json","graph_json":"https://pith.science/api/pith-number/TOTKO4QLE4GHGIQMBJIH6IEVLQ/graph.json","events_json":"https://pith.science/api/pith-number/TOTKO4QLE4GHGIQMBJIH6IEVLQ/events.json","paper":"https://pith.science/paper/TOTKO4QL"},"agent_actions":{"view_html":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ","download_json":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ.json","view_paper":"https://pith.science/paper/TOTKO4QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00829&json=true","fetch_graph":"https://pith.science/api/pith-number/TOTKO4QLE4GHGIQMBJIH6IEVLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TOTKO4QLE4GHGIQMBJIH6IEVLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ/action/storage_attestation","attest_author":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ/action/author_attestation","sign_citation":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ/action/citation_signature","submit_replication":"https://pith.science/pith/TOTKO4QLE4GHGIQMBJIH6IEVLQ/action/replication_record"}},"created_at":"2026-07-05T11:19:23.369574+00:00","updated_at":"2026-07-05T11:19:23.369574+00:00"}