{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ZRP6HFXCQZIWQRZMX3NSLT4MH","short_pith_number":"pith:4ZRP6HFX","schema_version":"1.0","canonical_sha256":"e662ff1cb714328b423965f6d92e7c61fd7ddb8709d3e1d4f124ea3fa065e06d","source":{"kind":"arxiv","id":"2407.10361","version":2},"attestation_state":"computed","paper":{"title":"Information-entropy-driven generation of material-agnostic datasets for machine-learning interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aparna P. A. Subramanyam, Danny Perez","submitted_at":"2024-07-14T23:41:26Z","abstract_excerpt":"In contrast to their empirical counterparts, machine-learning interatomic potentials (MLIAPs) promise to deliver near-quantum accuracy over broad regions of configuration space. However, due to their generic functional forms and extreme flexibility, they can catastrophically fail to capture the properties of novel, out-of-sample configurations, making the quality of the training set a determining factor, especially when investigating materials under extreme conditions. We propose a novel automated dataset generation method based on the maximization of the information entropy of the feature dis"},"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":"2407.10361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-07-14T23:41:26Z","cross_cats_sorted":[],"title_canon_sha256":"2b4f1f18707cb5115def6e42d65ccbc35a74a82cab2d8ca7180f35db80c291ad","abstract_canon_sha256":"96a0861fabe19dc167331a0d59d4f4bb49575e156884d420e232b9df64963dc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:53.043050Z","signature_b64":"fMySeKXGY0ROSYhwn9b+F/IC88kmeylyv922EXDTpcQd/tPmNDSinnZqOZFf+xUtfS2mRe4dyDfdpXwIxWksBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e662ff1cb714328b423965f6d92e7c61fd7ddb8709d3e1d4f124ea3fa065e06d","last_reissued_at":"2026-07-05T10:08:53.042626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:53.042626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-entropy-driven generation of material-agnostic datasets for machine-learning interatomic potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aparna P. A. Subramanyam, Danny Perez","submitted_at":"2024-07-14T23:41:26Z","abstract_excerpt":"In contrast to their empirical counterparts, machine-learning interatomic potentials (MLIAPs) promise to deliver near-quantum accuracy over broad regions of configuration space. However, due to their generic functional forms and extreme flexibility, they can catastrophically fail to capture the properties of novel, out-of-sample configurations, making the quality of the training set a determining factor, especially when investigating materials under extreme conditions. We propose a novel automated dataset generation method based on the maximization of the information entropy of the feature dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10361","kind":"arxiv","version":2},"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/2407.10361/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":"2407.10361","created_at":"2026-07-05T10:08:53.042685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10361v2","created_at":"2026-07-05T10:08:53.042685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10361","created_at":"2026-07-05T10:08:53.042685+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZRP6HFXCQZI","created_at":"2026-07-05T10:08:53.042685+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZRP6HFXCQZIWQRZ","created_at":"2026-07-05T10:08:53.042685+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZRP6HFX","created_at":"2026-07-05T10:08:53.042685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH","json":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH.json","graph_json":"https://pith.science/api/pith-number/4ZRP6HFXCQZIWQRZMX3NSLT4MH/graph.json","events_json":"https://pith.science/api/pith-number/4ZRP6HFXCQZIWQRZMX3NSLT4MH/events.json","paper":"https://pith.science/paper/4ZRP6HFX"},"agent_actions":{"view_html":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH","download_json":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH.json","view_paper":"https://pith.science/paper/4ZRP6HFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10361&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZRP6HFXCQZIWQRZMX3NSLT4MH/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZRP6HFXCQZIWQRZMX3NSLT4MH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH/action/storage_attestation","attest_author":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH/action/author_attestation","sign_citation":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH/action/citation_signature","submit_replication":"https://pith.science/pith/4ZRP6HFXCQZIWQRZMX3NSLT4MH/action/replication_record"}},"created_at":"2026-07-05T10:08:53.042685+00:00","updated_at":"2026-07-05T10:08:53.042685+00:00"}