{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMC6LRTRND76SIU5BO3VHI2FM2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e27c597acd6413fc86aac33981d2831742fba7dc0b31413419b4e00b32426a55","cross_cats_sorted":["cs.LG","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-09-11T20:45:44Z","title_canon_sha256":"a9803437bde23c71e6722c84e235073fae30008cc36a296233da07674f68ec50"},"schema_version":"1.0","source":{"id":"2409.07610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07610","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07610v1","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07610","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"FMC6LRTRND76","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"FMC6LRTRND76SIU5","created_at":"2026-07-05T09:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"FMC6LRTR","created_at":"2026-07-05T09:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:dcae468e1f356ec5f7e5706afda90881c482083caf1aabeaa3a56c7138d6181a","target":"graph","created_at":"2026-07-05T09:06:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.07610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parameterize the MLIPs remains a significant challenge. This is because MLIPs can fail when encountering local enviroments too different from those present in the training data. The difficulty of determining \\textit{a priori} the environments that will be encountered during molecular dynamics (MD) simulation necessitates diverse, high-quality training data. This study investigates how training data diversity affects the performance of ","authors_text":"Ajinkya C. Hire, Chris Bishop, Jason B. Gibson, J. Matthew D. Lane, Richard G. Hennig, Tesia D. Janicki","cross_cats":["cs.LG","physics.comp-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-09-11T20:45:44Z","title":"When More Data Hurts: Optimizing Data Coverage While Mitigating Diversity Induced Underfitting in an Ultra-Fast Machine-Learned Potential"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07610","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12445d8d24284e185fd02fcc3e8d27a21a2bd5ca2082549faf6f348a9d1ad65f","target":"record","created_at":"2026-07-05T09:06:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e27c597acd6413fc86aac33981d2831742fba7dc0b31413419b4e00b32426a55","cross_cats_sorted":["cs.LG","physics.comp-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-09-11T20:45:44Z","title_canon_sha256":"a9803437bde23c71e6722c84e235073fae30008cc36a296233da07674f68ec50"},"schema_version":"1.0","source":{"id":"2409.07610","kind":"arxiv","version":1}},"canonical_sha256":"2b05e5c67168ffe9229d0bb753a3456686001961fd559b34e2e3454fe58d58f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b05e5c67168ffe9229d0bb753a3456686001961fd559b34e2e3454fe58d58f2","first_computed_at":"2026-07-05T09:06:12.574584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:12.574584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wm3YUcoXRl7kqiMxSXeQTpaitqRTGF84b6wJAK+9hfTj3H0618KqVLM+V2be0mrgmcq3QM0ko5S2gnbukVIAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:12.575037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12445d8d24284e185fd02fcc3e8d27a21a2bd5ca2082549faf6f348a9d1ad65f","sha256:dcae468e1f356ec5f7e5706afda90881c482083caf1aabeaa3a56c7138d6181a"],"state_sha256":"d5c251f859f48aeff12da1414c71a880be410bc5b35b2b5512c817a9c1c530f3"}