{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Q5272JG7K6DA35O7OF3MPP3MV","short_pith_number":"pith:7Q5272JG","schema_version":"1.0","canonical_sha256":"fc3bafe926fabc306faefb8bb63dfb657f963ec286fafdb20b60c6f7dc941dc5","source":{"kind":"arxiv","id":"2402.05015","version":2},"attestation_state":"computed","paper":{"title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Al\\'an Aspuru-Guzik, Felix Strieth-Kalthoff, Geoff Pleiss, Marta Skreta, Pascal Poupart","submitted_at":"2024-02-07T16:32:58Z","abstract_excerpt":"Automation is one of the cornerstones of contemporary material discovery. Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space. While such prior knowledge can take many forms, there has been significant fanfare around the ancillary scientific knowledge encapsulated in large language models (LLMs). However, existing work thus far has only explored LLMs for heuristic materials searches. Indeed, recent work obtains the uncertainty estimate -- an integral part of BO -- from po"},"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":"2402.05015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"d470996a2c36c21c9b439f9dd6648dcaa1eb6b6845af0ef7252fd9027657b808","abstract_canon_sha256":"20cfd0f2a7c49023c48a038cd2142603e83429f5f15de3a1ad0f023f130bddfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:23.916109Z","signature_b64":"6BIiGlIH6AufGxfukLk63OobZ69VKK+ZG8hLCfjf4Za+UAcu6RPrv9fcqvWkMckJ9fmOO2XjkqWcJOY4m3eQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3bafe926fabc306faefb8bb63dfb657f963ec286fafdb20b60c6f7dc941dc5","last_reissued_at":"2026-07-05T08:24:23.915602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:23.915602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Agustinus Kristiadi, Al\\'an Aspuru-Guzik, Felix Strieth-Kalthoff, Geoff Pleiss, Marta Skreta, Pascal Poupart","submitted_at":"2024-02-07T16:32:58Z","abstract_excerpt":"Automation is one of the cornerstones of contemporary material discovery. Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space. While such prior knowledge can take many forms, there has been significant fanfare around the ancillary scientific knowledge encapsulated in large language models (LLMs). However, existing work thus far has only explored LLMs for heuristic materials searches. Indeed, recent work obtains the uncertainty estimate -- an integral part of BO -- from po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05015","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/2402.05015/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":"2402.05015","created_at":"2026-07-05T08:24:23.915668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05015v2","created_at":"2026-07-05T08:24:23.915668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05015","created_at":"2026-07-05T08:24:23.915668+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q5272JG7K6D","created_at":"2026-07-05T08:24:23.915668+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q5272JG7K6DA35O","created_at":"2026-07-05T08:24:23.915668+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q5272JG","created_at":"2026-07-05T08:24:23.915668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26657","citing_title":"Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17671","citing_title":"LILO: Bayesian Optimization with Natural Language Feedback","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV","json":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV.json","graph_json":"https://pith.science/api/pith-number/7Q5272JG7K6DA35O7OF3MPP3MV/graph.json","events_json":"https://pith.science/api/pith-number/7Q5272JG7K6DA35O7OF3MPP3MV/events.json","paper":"https://pith.science/paper/7Q5272JG"},"agent_actions":{"view_html":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV","download_json":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV.json","view_paper":"https://pith.science/paper/7Q5272JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05015&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q5272JG7K6DA35O7OF3MPP3MV/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q5272JG7K6DA35O7OF3MPP3MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV/action/storage_attestation","attest_author":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV/action/author_attestation","sign_citation":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV/action/citation_signature","submit_replication":"https://pith.science/pith/7Q5272JG7K6DA35O7OF3MPP3MV/action/replication_record"}},"created_at":"2026-07-05T08:24:23.915668+00:00","updated_at":"2026-07-05T08:24:23.915668+00:00"}