{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HJR45IXYM2CP3OCZ6RDGY5AFKA","short_pith_number":"pith:HJR45IXY","schema_version":"1.0","canonical_sha256":"3a63cea2f86684fdb859f4466c7405502264455985219df7b3b400b29e20a828","source":{"kind":"arxiv","id":"2203.12597","version":1},"attestation_state":"computed","paper":{"title":"High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Marianne Liu, Sterling G. Baird, Taylor D. Sparks","submitted_at":"2022-03-19T03:52:22Z","abstract_excerpt":"Expensive-to-train deep learning models can benefit from an optimization of the hyperparameters that determine the model architecture. We optimize 23 hyperparameters of a materials informatics model, Compositionally-Restricted Attention-Based Network (CrabNet), over 100 adaptive design iterations using two models within the Adaptive Experimentation (Ax) Platform. This includes a recently developed Bayesian optimization (BO) algorithm, sparse axis-aligned subspaces Bayesian optimization (SAASBO), which has shown exciting performance on high-dimensional optimization tasks. Using SAASBO to optimi"},"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":"2203.12597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-03-19T03:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"af17a06a188cec8fc14ee6664adbeb095cb6f8657358ee0e0578b01585d7df2b","abstract_canon_sha256":"b0e69e98fdc0521558adb01ea974c7b97ccd623a286a5a2bbed66a7f2ec4501e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:55.632899Z","signature_b64":"QQgB4/o57BqRqEAGOM9+CE24QKFwxThlYVXjOJgbGn5Y1kizUulXREf96XJ6qTpZgCVfdAm3pxiIkCe3Pa2wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a63cea2f86684fdb859f4466c7405502264455985219df7b3b400b29e20a828","last_reissued_at":"2026-07-05T05:51:55.632455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:55.632455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Marianne Liu, Sterling G. Baird, Taylor D. Sparks","submitted_at":"2022-03-19T03:52:22Z","abstract_excerpt":"Expensive-to-train deep learning models can benefit from an optimization of the hyperparameters that determine the model architecture. We optimize 23 hyperparameters of a materials informatics model, Compositionally-Restricted Attention-Based Network (CrabNet), over 100 adaptive design iterations using two models within the Adaptive Experimentation (Ax) Platform. This includes a recently developed Bayesian optimization (BO) algorithm, sparse axis-aligned subspaces Bayesian optimization (SAASBO), which has shown exciting performance on high-dimensional optimization tasks. Using SAASBO to optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12597","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/2203.12597/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":"2203.12597","created_at":"2026-07-05T05:51:55.632513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12597v1","created_at":"2026-07-05T05:51:55.632513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12597","created_at":"2026-07-05T05:51:55.632513+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJR45IXYM2CP","created_at":"2026-07-05T05:51:55.632513+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJR45IXYM2CP3OCZ","created_at":"2026-07-05T05:51:55.632513+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJR45IXY","created_at":"2026-07-05T05:51:55.632513+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/HJR45IXYM2CP3OCZ6RDGY5AFKA","json":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA.json","graph_json":"https://pith.science/api/pith-number/HJR45IXYM2CP3OCZ6RDGY5AFKA/graph.json","events_json":"https://pith.science/api/pith-number/HJR45IXYM2CP3OCZ6RDGY5AFKA/events.json","paper":"https://pith.science/paper/HJR45IXY"},"agent_actions":{"view_html":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA","download_json":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA.json","view_paper":"https://pith.science/paper/HJR45IXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12597&json=true","fetch_graph":"https://pith.science/api/pith-number/HJR45IXYM2CP3OCZ6RDGY5AFKA/graph.json","fetch_events":"https://pith.science/api/pith-number/HJR45IXYM2CP3OCZ6RDGY5AFKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA/action/storage_attestation","attest_author":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA/action/author_attestation","sign_citation":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA/action/citation_signature","submit_replication":"https://pith.science/pith/HJR45IXYM2CP3OCZ6RDGY5AFKA/action/replication_record"}},"created_at":"2026-07-05T05:51:55.632513+00:00","updated_at":"2026-07-05T05:51:55.632513+00:00"}