{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K7GWA2JNFA3ZQLCJVJPUURD7O4","short_pith_number":"pith:K7GWA2JN","schema_version":"1.0","canonical_sha256":"57cd60692d2837982c49aa5f4a447f7712b95589681b403e1f056f0126b325e3","source":{"kind":"arxiv","id":"2508.17792","version":1},"attestation_state":"computed","paper":{"title":"Universal Machine Learning Potentials under Pressure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Antoine Loew, Jonathan Schmidt, Miguel A. L. Marques, Silvana Botti","submitted_at":"2025-08-25T08:37:03Z","abstract_excerpt":"Universal machine learning interatomic potentials (uMLIPs) represent arguably the most successful application of machine learning to materials science, demonstrating remarkable performance across diverse applications. However, critical blind spots in their reliability persist. Here, we address one such significant gap by systematically investigating the accuracy of uMLIPs under extreme pressure conditions from 0 to 150 GPa. Our benchmark reveals that while these models excel at standard pressure, their predictive accuracy deteriorates considerably as pressure increases. This decline in perform"},"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":"2508.17792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-08-25T08:37:03Z","cross_cats_sorted":[],"title_canon_sha256":"c2eb207035f7fa56515815e051965bbff847d1c2bee0ede49baee3bc397b7c18","abstract_canon_sha256":"94b7f0030c5f535ba7872e7973e96b56fd15d12f00c3c134f9c15d0e5cb21acb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:47.873005Z","signature_b64":"IBgwD5RMR6q2qYM2e6ecTR1ywTBg1fEgLpuZ5bchpZHFGusA4bfAh9x5DKOPHypfRhrHay6vmiQNXJvV4XGsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57cd60692d2837982c49aa5f4a447f7712b95589681b403e1f056f0126b325e3","last_reissued_at":"2026-07-05T11:58:47.872510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:47.872510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Machine Learning Potentials under Pressure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Antoine Loew, Jonathan Schmidt, Miguel A. L. Marques, Silvana Botti","submitted_at":"2025-08-25T08:37:03Z","abstract_excerpt":"Universal machine learning interatomic potentials (uMLIPs) represent arguably the most successful application of machine learning to materials science, demonstrating remarkable performance across diverse applications. However, critical blind spots in their reliability persist. Here, we address one such significant gap by systematically investigating the accuracy of uMLIPs under extreme pressure conditions from 0 to 150 GPa. Our benchmark reveals that while these models excel at standard pressure, their predictive accuracy deteriorates considerably as pressure increases. This decline in perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17792","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/2508.17792/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":"2508.17792","created_at":"2026-07-05T11:58:47.872574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17792v1","created_at":"2026-07-05T11:58:47.872574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17792","created_at":"2026-07-05T11:58:47.872574+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7GWA2JNFA3Z","created_at":"2026-07-05T11:58:47.872574+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7GWA2JNFA3ZQLCJ","created_at":"2026-07-05T11:58:47.872574+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7GWA2JN","created_at":"2026-07-05T11:58:47.872574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.09169","citing_title":"AI-Driven Expansion and Application of the Alexandria Database","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4","json":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4.json","graph_json":"https://pith.science/api/pith-number/K7GWA2JNFA3ZQLCJVJPUURD7O4/graph.json","events_json":"https://pith.science/api/pith-number/K7GWA2JNFA3ZQLCJVJPUURD7O4/events.json","paper":"https://pith.science/paper/K7GWA2JN"},"agent_actions":{"view_html":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4","download_json":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4.json","view_paper":"https://pith.science/paper/K7GWA2JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17792&json=true","fetch_graph":"https://pith.science/api/pith-number/K7GWA2JNFA3ZQLCJVJPUURD7O4/graph.json","fetch_events":"https://pith.science/api/pith-number/K7GWA2JNFA3ZQLCJVJPUURD7O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4/action/storage_attestation","attest_author":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4/action/author_attestation","sign_citation":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4/action/citation_signature","submit_replication":"https://pith.science/pith/K7GWA2JNFA3ZQLCJVJPUURD7O4/action/replication_record"}},"created_at":"2026-07-05T11:58:47.872574+00:00","updated_at":"2026-07-05T11:58:47.872574+00:00"}