{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KFEEAAWX7KZHVOSSTI67ANKYA2","short_pith_number":"pith:KFEEAAWX","schema_version":"1.0","canonical_sha256":"51484002d7fab27aba529a3df03558068675ffe36a58378932ab51e4c4829dc9","source":{"kind":"arxiv","id":"2209.12466","version":1},"attestation_state":"computed","paper":{"title":"Learned Force Fields Are Ready For Ground State Catalyst Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alexander L. Gaunt, Alex M. Ganose, James Kirkpatrick, James S. Spencer, Jonathan Godwin, Michael Schaarschmidt, Morgane Riviere, Peter W. Battaglia, Simon Axelrod","submitted_at":"2022-09-26T07:16:43Z","abstract_excerpt":"We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces from a learned potential yields structures with similar or lower energy to those relaxed using the RPBE functional in over 50\\% of evaluated systems, despite the fact that the predicted forces differ significantly from the ground truth. This has the surprising implication that learned potentials may be ready for replacing DFT in challenging catalytic systems such as those found in the Open Catalyst 2020 dataset. Further"},"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":"2209.12466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-09-26T07:16:43Z","cross_cats_sorted":["cs.LG","physics.comp-ph"],"title_canon_sha256":"af4804c8130661280179fe5019dd3bd9c1fe2ba83663f4ce5bbc5047f3aee969","abstract_canon_sha256":"9dedffc6587ddcff02da961d35f0c71c30bd98eee01ff264be3aa7245d2f2360"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:52.808514Z","signature_b64":"aLjGam44FAYmSn+/WnuyevxXEDQ6/Crw7FQcpbWuycmla1WH6qdV2wzMGnyYcGavdnfVROVIEPuuc7ESAn90Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51484002d7fab27aba529a3df03558068675ffe36a58378932ab51e4c4829dc9","last_reissued_at":"2026-07-05T05:00:52.808110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:52.808110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Force Fields Are Ready For Ground State Catalyst Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Alexander L. Gaunt, Alex M. Ganose, James Kirkpatrick, James S. Spencer, Jonathan Godwin, Michael Schaarschmidt, Morgane Riviere, Peter W. Battaglia, Simon Axelrod","submitted_at":"2022-09-26T07:16:43Z","abstract_excerpt":"We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces from a learned potential yields structures with similar or lower energy to those relaxed using the RPBE functional in over 50\\% of evaluated systems, despite the fact that the predicted forces differ significantly from the ground truth. This has the surprising implication that learned potentials may be ready for replacing DFT in challenging catalytic systems such as those found in the Open Catalyst 2020 dataset. Further"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12466","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/2209.12466/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":"2209.12466","created_at":"2026-07-05T05:00:52.808164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12466v1","created_at":"2026-07-05T05:00:52.808164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12466","created_at":"2026-07-05T05:00:52.808164+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFEEAAWX7KZH","created_at":"2026-07-05T05:00:52.808164+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFEEAAWX7KZHVOSS","created_at":"2026-07-05T05:00:52.808164+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFEEAAWX","created_at":"2026-07-05T05:00:52.808164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.00944","citing_title":"Training speedups via batching for geometric learning: an analysis of static and dynamic algorithms","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2","json":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2.json","graph_json":"https://pith.science/api/pith-number/KFEEAAWX7KZHVOSSTI67ANKYA2/graph.json","events_json":"https://pith.science/api/pith-number/KFEEAAWX7KZHVOSSTI67ANKYA2/events.json","paper":"https://pith.science/paper/KFEEAAWX"},"agent_actions":{"view_html":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2","download_json":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2.json","view_paper":"https://pith.science/paper/KFEEAAWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12466&json=true","fetch_graph":"https://pith.science/api/pith-number/KFEEAAWX7KZHVOSSTI67ANKYA2/graph.json","fetch_events":"https://pith.science/api/pith-number/KFEEAAWX7KZHVOSSTI67ANKYA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2/action/storage_attestation","attest_author":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2/action/author_attestation","sign_citation":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2/action/citation_signature","submit_replication":"https://pith.science/pith/KFEEAAWX7KZHVOSSTI67ANKYA2/action/replication_record"}},"created_at":"2026-07-05T05:00:52.808164+00:00","updated_at":"2026-07-05T05:00:52.808164+00:00"}