{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5FT7OKK7HTB7YPKHBYW4MNYZIR","short_pith_number":"pith:5FT7OKK7","schema_version":"1.0","canonical_sha256":"e967f7295f3cc3fc3d470e2dc63719447abdd69075e43ce36517cdfed77cd979","source":{"kind":"arxiv","id":"2402.03921","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models to Enhance Bayesian Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Nabeel Seedat, Nicol\\'as Astorga, Tennison Liu","submitted_at":"2024-02-06T11:44:06Z","abstract_excerpt":"Bayesian optimization (BO) is a powerful approach for optimizing complex and expensive-to-evaluate black-box functions. Its importance is underscored in many applications, notably including hyperparameter tuning, but its efficacy depends on efficiently balancing exploration and exploitation. While there has been substantial progress in BO methods, striking this balance remains a delicate process. In this light, we present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within BO. At a high level, we frame the BO problem in natural language, enabling LLM"},"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":"2402.03921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T11:44:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a4ecd822252611fe62d96ad3660633255c604df828399611c4942463aaaa293","abstract_canon_sha256":"139f6e63c6068bbb99de894aec17b28317c6642bd3f0d18f44f7d16f2d8c3dd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:50.294480Z","signature_b64":"D31h+6JucVsBa95Dwu0nm5LGFU1PkiTBocEpd0AgZa6JXuZU/yC5gAzw0VV816bm6dQ2hftorBwWffH4wxNSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e967f7295f3cc3fc3d470e2dc63719447abdd69075e43ce36517cdfed77cd979","last_reissued_at":"2026-07-05T07:53:50.293970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:50.293970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models to Enhance Bayesian Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Nabeel Seedat, Nicol\\'as Astorga, Tennison Liu","submitted_at":"2024-02-06T11:44:06Z","abstract_excerpt":"Bayesian optimization (BO) is a powerful approach for optimizing complex and expensive-to-evaluate black-box functions. Its importance is underscored in many applications, notably including hyperparameter tuning, but its efficacy depends on efficiently balancing exploration and exploitation. While there has been substantial progress in BO methods, striking this balance remains a delicate process. In this light, we present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within BO. At a high level, we frame the BO problem in natural language, enabling LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03921","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/2402.03921/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":"2402.03921","created_at":"2026-07-05T07:53:50.294030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03921v2","created_at":"2026-07-05T07:53:50.294030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03921","created_at":"2026-07-05T07:53:50.294030+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FT7OKK7HTB7","created_at":"2026-07-05T07:53:50.294030+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FT7OKK7HTB7YPKH","created_at":"2026-07-05T07:53:50.294030+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FT7OKK7","created_at":"2026-07-05T07:53:50.294030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25207","citing_title":"ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23299","citing_title":"GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs","ref_index":45,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25404","citing_title":"SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08332","citing_title":"ORFS-agent: Tool-Using Agents for Chip Design Optimization","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22653","citing_title":"URSA: The Universal Research and Scientific Agent","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17671","citing_title":"LILO: Bayesian Optimization with Natural Language Feedback","ref_index":13,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01328","citing_title":"Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04764","citing_title":"Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02933","citing_title":"Relation Reasoning with LLMs in Expensive Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07863","citing_title":"ADKO: Agentic Decentralized Knowledge Optimization","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR","json":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR.json","graph_json":"https://pith.science/api/pith-number/5FT7OKK7HTB7YPKHBYW4MNYZIR/graph.json","events_json":"https://pith.science/api/pith-number/5FT7OKK7HTB7YPKHBYW4MNYZIR/events.json","paper":"https://pith.science/paper/5FT7OKK7"},"agent_actions":{"view_html":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR","download_json":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR.json","view_paper":"https://pith.science/paper/5FT7OKK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03921&json=true","fetch_graph":"https://pith.science/api/pith-number/5FT7OKK7HTB7YPKHBYW4MNYZIR/graph.json","fetch_events":"https://pith.science/api/pith-number/5FT7OKK7HTB7YPKHBYW4MNYZIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR/action/storage_attestation","attest_author":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR/action/author_attestation","sign_citation":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR/action/citation_signature","submit_replication":"https://pith.science/pith/5FT7OKK7HTB7YPKHBYW4MNYZIR/action/replication_record"}},"created_at":"2026-07-05T07:53:50.294030+00:00","updated_at":"2026-07-05T07:53:50.294030+00:00"}