{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EEDQ5BR63EPAYC33OVXMKFRZLN","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":"69c875f3777b7319c0be6f79d63c1f65bbb00446b9bf0d1509f77a7fd74a34e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-07-20T21:35:06Z","title_canon_sha256":"52a6e1c5bd45b6513c3ec9894f0b19ef59a12dc810b175ccddf900c894b1a8d0"},"schema_version":"1.0","source":{"id":"2607.18524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18524","created_at":"2026-07-22T00:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18524v1","created_at":"2026-07-22T00:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18524","created_at":"2026-07-22T00:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"EEDQ5BR63EPA","created_at":"2026-07-22T00:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"EEDQ5BR63EPAYC33","created_at":"2026-07-22T00:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"EEDQ5BR6","created_at":"2026-07-22T00:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:279d96be5b99026f404120ca864531b9be9f821891e630eb6da6102c0ca08eef","target":"graph","created_at":"2026-07-22T00:22:52Z","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/2607.18524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The construction of machine-learned interatomic potentials (MLIPs) is often limited by the cost of generating large density-functional-theory (DFT) training datasets. For systematically generated structure pools such as ASSYST, a central practical question is how many configurations must be labeled to achieve reliable accuracy. Here we assess geometry-based, label-free subset selection for training linear Atomic Cluster Expansion (ACE) potentials. Using statistical leverage scores and CUR-type sampling, we compare leverage-guided selection against random, energy-based, and force-based baseline","authors_text":"Aynour Khosravi, Chad Sinclair, J\\\"org Neugebauer, Marvin Poul","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-07-20T21:35:06Z","title":"Data-Efficient Training of Linear ACE Potentials through Leverage-Guided Subset Selection of ASSYST Structure Pools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18524","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":"sha256:3e53b05a841a04583498a3acf82de845372a90ab5c01dbe55b10d207fe9bebe4","target":"record","created_at":"2026-07-22T00:22:52Z","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":"69c875f3777b7319c0be6f79d63c1f65bbb00446b9bf0d1509f77a7fd74a34e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-07-20T21:35:06Z","title_canon_sha256":"52a6e1c5bd45b6513c3ec9894f0b19ef59a12dc810b175ccddf900c894b1a8d0"},"schema_version":"1.0","source":{"id":"2607.18524","kind":"arxiv","version":1}},"canonical_sha256":"21070e863ed91e0c0b7b756ec516395b5c4e99df8b837a11464f524976131146","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21070e863ed91e0c0b7b756ec516395b5c4e99df8b837a11464f524976131146","first_computed_at":"2026-07-22T00:22:52.776584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:52.776584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PacBP+rYIyBUhMoblTa2j9pEkuHDyx14hrEOJSaAwde5D1m6I+lRdMUWEg44nEs4+Ty/wtK1N958jIw3gomPBQ==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:52.777340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e53b05a841a04583498a3acf82de845372a90ab5c01dbe55b10d207fe9bebe4","sha256:279d96be5b99026f404120ca864531b9be9f821891e630eb6da6102c0ca08eef"],"state_sha256":"666ddc132505e78158e6d2243c67c96de5c96335beab572d3c7b74d2097cb1e5"}