{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:64WFTEJZMLEJ7BQ6EBSOXIT4ID","short_pith_number":"pith:64WFTEJZ","schema_version":"1.0","canonical_sha256":"f72c59913962c89f861e2064eba27c40fd91942492f5356096a37c065b731c32","source":{"kind":"arxiv","id":"2311.00862","version":1},"attestation_state":"computed","paper":{"title":"Role of Structural and Conformational Diversity for Machine Learning Potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Dominique Beaini, Emmanuel Noutahi, Hadrien Mary, Jiarui Ding, Nikhil Shenoy, Prudencio Tossou","submitted_at":"2023-10-30T19:33:12Z","abstract_excerpt":"In the field of Machine Learning Interatomic Potentials (MLIPs), understanding the intricate relationship between data biases, specifically conformational and structural diversity, and model generalization is critical in improving the quality of Quantum Mechanics (QM) data generation efforts. We investigate these dynamics through two distinct experiments: a fixed budget one, where the dataset size remains constant, and a fixed molecular set one, which focuses on fixed structural diversity while varying conformational diversity. Our results reveal nuanced patterns in generalization metrics. Not"},"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":"2311.00862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-10-30T19:33:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c84781ad788a5f01f33a0551ba002a911864706c4b68757ca168bbef6b23dc8","abstract_canon_sha256":"a0266183c9d33d09778ab0ccb51bcd867be07be6b29c4d6494ad96cc78362881"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:16.698422Z","signature_b64":"NtEQf1pk/Qcm2WQ9TGmeq2oDd1gVl3muHd3fc2Tl78p1ule+ZNJwTpSfuASKwBOlg8T4JMyylJaYtoanDaQBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f72c59913962c89f861e2064eba27c40fd91942492f5356096a37c065b731c32","last_reissued_at":"2026-07-05T07:08:16.697929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:16.697929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Role of Structural and Conformational Diversity for Machine Learning Potentials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Dominique Beaini, Emmanuel Noutahi, Hadrien Mary, Jiarui Ding, Nikhil Shenoy, Prudencio Tossou","submitted_at":"2023-10-30T19:33:12Z","abstract_excerpt":"In the field of Machine Learning Interatomic Potentials (MLIPs), understanding the intricate relationship between data biases, specifically conformational and structural diversity, and model generalization is critical in improving the quality of Quantum Mechanics (QM) data generation efforts. We investigate these dynamics through two distinct experiments: a fixed budget one, where the dataset size remains constant, and a fixed molecular set one, which focuses on fixed structural diversity while varying conformational diversity. Our results reveal nuanced patterns in generalization metrics. Not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00862","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/2311.00862/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":"2311.00862","created_at":"2026-07-05T07:08:16.697988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00862v1","created_at":"2026-07-05T07:08:16.697988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00862","created_at":"2026-07-05T07:08:16.697988+00:00"},{"alias_kind":"pith_short_12","alias_value":"64WFTEJZMLEJ","created_at":"2026-07-05T07:08:16.697988+00:00"},{"alias_kind":"pith_short_16","alias_value":"64WFTEJZMLEJ7BQ6","created_at":"2026-07-05T07:08:16.697988+00:00"},{"alias_kind":"pith_short_8","alias_value":"64WFTEJZ","created_at":"2026-07-05T07:08:16.697988+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/64WFTEJZMLEJ7BQ6EBSOXIT4ID","json":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID.json","graph_json":"https://pith.science/api/pith-number/64WFTEJZMLEJ7BQ6EBSOXIT4ID/graph.json","events_json":"https://pith.science/api/pith-number/64WFTEJZMLEJ7BQ6EBSOXIT4ID/events.json","paper":"https://pith.science/paper/64WFTEJZ"},"agent_actions":{"view_html":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID","download_json":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID.json","view_paper":"https://pith.science/paper/64WFTEJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00862&json=true","fetch_graph":"https://pith.science/api/pith-number/64WFTEJZMLEJ7BQ6EBSOXIT4ID/graph.json","fetch_events":"https://pith.science/api/pith-number/64WFTEJZMLEJ7BQ6EBSOXIT4ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID/action/storage_attestation","attest_author":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID/action/author_attestation","sign_citation":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID/action/citation_signature","submit_replication":"https://pith.science/pith/64WFTEJZMLEJ7BQ6EBSOXIT4ID/action/replication_record"}},"created_at":"2026-07-05T07:08:16.697988+00:00","updated_at":"2026-07-05T07:08:16.697988+00:00"}