{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3S7A7UBY2VOPZQNYS4R2ICQOSL","short_pith_number":"pith:3S7A7UBY","schema_version":"1.0","canonical_sha256":"dcbe0fd038d55cfcc1b89723a40a0e92ff8c7a7e5c5c7d56d814b4b1e6bdf101","source":{"kind":"arxiv","id":"2402.03753","version":1},"attestation_state":"computed","paper":{"title":"Enhanced sampling of robust molecular datasets with uncertainty-based collective variables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Aik Rui Tan, Johannes C. B. Dietschreit, Rafael Gomez-Bombarelli","submitted_at":"2024-02-06T06:42:51Z","abstract_excerpt":"Generating a data set that is representative of the accessible configuration space of a molecular system is crucial for the robustness of machine learned interatomic potentials (MLIP). However, the complexity of molecular systems, characterized by intricate potential energy surfaces (PESs) with numerous local minima and energy barriers, presents a significant challenge. Traditional methods of data generation, such as random sampling or exhaustive exploration, are either intractable or may not capture rare, but highly informative configurations. In this study, we propose a method that leverages"},"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":"2402.03753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T06:42:51Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"a0910cee3c241929668947cedb3b8639e5b4b1d086160663cc0321ee7af2055e","abstract_canon_sha256":"c01d014226b38d9c0918304e972f09c80d220e178f2bbc08aa96bf995779d709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:08.976607Z","signature_b64":"wd7bWWlNwfF7GOGK2Ki40GnDWo7HV4UWdwGirJyFQz9dHu764MURbec/wMsPdQbYrin4HofOR9HALOtzycvoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbe0fd038d55cfcc1b89723a40a0e92ff8c7a7e5c5c7d56d814b4b1e6bdf101","last_reissued_at":"2026-07-05T10:05:08.976085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:08.976085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced sampling of robust molecular datasets with uncertainty-based collective variables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Aik Rui Tan, Johannes C. B. Dietschreit, Rafael Gomez-Bombarelli","submitted_at":"2024-02-06T06:42:51Z","abstract_excerpt":"Generating a data set that is representative of the accessible configuration space of a molecular system is crucial for the robustness of machine learned interatomic potentials (MLIP). However, the complexity of molecular systems, characterized by intricate potential energy surfaces (PESs) with numerous local minima and energy barriers, presents a significant challenge. Traditional methods of data generation, such as random sampling or exhaustive exploration, are either intractable or may not capture rare, but highly informative configurations. In this study, we propose a method that leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03753","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/2402.03753/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":"2402.03753","created_at":"2026-07-05T10:05:08.976151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03753v1","created_at":"2026-07-05T10:05:08.976151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03753","created_at":"2026-07-05T10:05:08.976151+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S7A7UBY2VOP","created_at":"2026-07-05T10:05:08.976151+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S7A7UBY2VOPZQNY","created_at":"2026-07-05T10:05:08.976151+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S7A7UBY","created_at":"2026-07-05T10:05:08.976151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07927","citing_title":"MatterSim-MT: A multi-task foundation model for in silico materials characterization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2405.04967","citing_title":"MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07927","citing_title":"MatterSim-MT: A multi-task foundation model for in silico materials characterization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL","json":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL.json","graph_json":"https://pith.science/api/pith-number/3S7A7UBY2VOPZQNYS4R2ICQOSL/graph.json","events_json":"https://pith.science/api/pith-number/3S7A7UBY2VOPZQNYS4R2ICQOSL/events.json","paper":"https://pith.science/paper/3S7A7UBY"},"agent_actions":{"view_html":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL","download_json":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL.json","view_paper":"https://pith.science/paper/3S7A7UBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03753&json=true","fetch_graph":"https://pith.science/api/pith-number/3S7A7UBY2VOPZQNYS4R2ICQOSL/graph.json","fetch_events":"https://pith.science/api/pith-number/3S7A7UBY2VOPZQNYS4R2ICQOSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL/action/storage_attestation","attest_author":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL/action/author_attestation","sign_citation":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL/action/citation_signature","submit_replication":"https://pith.science/pith/3S7A7UBY2VOPZQNYS4R2ICQOSL/action/replication_record"}},"created_at":"2026-07-05T10:05:08.976151+00:00","updated_at":"2026-07-05T10:05:08.976151+00:00"}