{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6QGEPDCROKLAL2JPL6YLDNZWDV","short_pith_number":"pith:6QGEPDCR","schema_version":"1.0","canonical_sha256":"f40c478c51729605e92f5fb0b1b7361d5a760749e60edf94bc7ec51df6b9fabf","source":{"kind":"arxiv","id":"2206.08744","version":1},"attestation_state":"computed","paper":{"title":"Improved uncertainty quantification for Gaussian process regression based interatomic potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Albert P. Bart\\'ok, James. R. Kermode","submitted_at":"2022-06-17T12:59:44Z","abstract_excerpt":"The error estimation capability of machine learning interatomic potentials (MLIPs) based on probabilistic learning methods such as Gaussian process regression (GPR) is currently under-exploited, because of the tendancy of the predicted errors to overestimate the true error. We present approaches based on maximising either the marginal likelihood or an alternative likelihood constructed using leave-one-out cross validation to provide improved error estimates for interatomic potentials based on GPR. We benchmarked these approaches on models representing the Ar trimer, showing significant improve"},"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":"2206.08744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-06-17T12:59:44Z","cross_cats_sorted":["physics.chem-ph"],"title_canon_sha256":"4172664e289c0a2cc64de0b08a5c4b10f308b23eb7f619367d9464f0b60d2c0e","abstract_canon_sha256":"75d79e6d97444d5642866f43db19158c007bb68ab892b858dc8f7a63b100b294"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:42.918772Z","signature_b64":"D2lI901LNbAfLk2+E4TJgtSy2+WsQxfOtnrlSxBXa8CrtQ9UiPXIcMgMN6ACeUloFs8ugF3bzV/3nHKSVdgwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f40c478c51729605e92f5fb0b1b7361d5a760749e60edf94bc7ec51df6b9fabf","last_reissued_at":"2026-07-05T04:32:42.918278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:42.918278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved uncertainty quantification for Gaussian process regression based interatomic potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.chem-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Albert P. Bart\\'ok, James. R. Kermode","submitted_at":"2022-06-17T12:59:44Z","abstract_excerpt":"The error estimation capability of machine learning interatomic potentials (MLIPs) based on probabilistic learning methods such as Gaussian process regression (GPR) is currently under-exploited, because of the tendancy of the predicted errors to overestimate the true error. We present approaches based on maximising either the marginal likelihood or an alternative likelihood constructed using leave-one-out cross validation to provide improved error estimates for interatomic potentials based on GPR. We benchmarked these approaches on models representing the Ar trimer, showing significant improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08744","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/2206.08744/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":"2206.08744","created_at":"2026-07-05T04:32:42.918345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08744v1","created_at":"2026-07-05T04:32:42.918345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08744","created_at":"2026-07-05T04:32:42.918345+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QGEPDCROKLA","created_at":"2026-07-05T04:32:42.918345+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QGEPDCROKLAL2JP","created_at":"2026-07-05T04:32:42.918345+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QGEPDCR","created_at":"2026-07-05T04:32:42.918345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00640","citing_title":"Knowing when to trust machine-learned interatomic potentials","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV","json":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV.json","graph_json":"https://pith.science/api/pith-number/6QGEPDCROKLAL2JPL6YLDNZWDV/graph.json","events_json":"https://pith.science/api/pith-number/6QGEPDCROKLAL2JPL6YLDNZWDV/events.json","paper":"https://pith.science/paper/6QGEPDCR"},"agent_actions":{"view_html":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV","download_json":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV.json","view_paper":"https://pith.science/paper/6QGEPDCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08744&json=true","fetch_graph":"https://pith.science/api/pith-number/6QGEPDCROKLAL2JPL6YLDNZWDV/graph.json","fetch_events":"https://pith.science/api/pith-number/6QGEPDCROKLAL2JPL6YLDNZWDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV/action/storage_attestation","attest_author":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV/action/author_attestation","sign_citation":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV/action/citation_signature","submit_replication":"https://pith.science/pith/6QGEPDCROKLAL2JPL6YLDNZWDV/action/replication_record"}},"created_at":"2026-07-05T04:32:42.918345+00:00","updated_at":"2026-07-05T04:32:42.918345+00:00"}