{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DOPIJFFNE44PUK742YKUVQBBLI","short_pith_number":"pith:DOPIJFFN","schema_version":"1.0","canonical_sha256":"1b9e8494ad2738fa2bfcd6154ac0215a1938433968a3f817c3791f0f9af50415","source":{"kind":"arxiv","id":"2306.03109","version":1},"attestation_state":"computed","paper":{"title":"Machine Learning Force Fields with Data Cost Aware Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"q-bio.QM","authors_text":"Alexander Bukharin, Shengjie Wang, Simiao Zuo, Tianyi Liu, Tuo Zhao, Weihao Gao, Wen Yan","submitted_at":"2023-06-05T04:34:54Z","abstract_excerpt":"Machine learning force fields (MLFF) have been proposed to accelerate molecular dynamics (MD) simulation, which finds widespread applications in chemistry and biomedical research. Even for the most data-efficient MLFFs, reaching chemical accuracy can require hundreds of frames of force and energy labels generated by expensive quantum mechanical algorithms, which may scale as $O(n^3)$ to $O(n^7)$, with $n$ proportional to the number of basis functions. To address this issue, we propose a multi-stage computational framework -- ASTEROID, which lowers the data cost of MLFFs by leveraging a combina"},"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":"2306.03109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-05T04:34:54Z","cross_cats_sorted":["cs.LG","physics.chem-ph"],"title_canon_sha256":"181333d8f83ba52825937f00df6e1f222590e1e01206d27672cca9988693613f","abstract_canon_sha256":"a72e513ba1198d8881781da73925d3afbf4c77cd96594e5343af79d48940eb0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:53.935852Z","signature_b64":"p0FsAOrv8OdPcxcB8VeqNd46jPtIEPYY6lsxYttUKFkBJO/Ohdnl3gKJiifJZqXE9BdzCgXn/L64gsRhA6fQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b9e8494ad2738fa2bfcd6154ac0215a1938433968a3f817c3791f0f9af50415","last_reissued_at":"2026-07-05T06:17:53.935338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:53.935338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Force Fields with Data Cost Aware Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"q-bio.QM","authors_text":"Alexander Bukharin, Shengjie Wang, Simiao Zuo, Tianyi Liu, Tuo Zhao, Weihao Gao, Wen Yan","submitted_at":"2023-06-05T04:34:54Z","abstract_excerpt":"Machine learning force fields (MLFF) have been proposed to accelerate molecular dynamics (MD) simulation, which finds widespread applications in chemistry and biomedical research. Even for the most data-efficient MLFFs, reaching chemical accuracy can require hundreds of frames of force and energy labels generated by expensive quantum mechanical algorithms, which may scale as $O(n^3)$ to $O(n^7)$, with $n$ proportional to the number of basis functions. To address this issue, we propose a multi-stage computational framework -- ASTEROID, which lowers the data cost of MLFFs by leveraging a combina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03109","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/2306.03109/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":"2306.03109","created_at":"2026-07-05T06:17:53.935403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03109v1","created_at":"2026-07-05T06:17:53.935403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03109","created_at":"2026-07-05T06:17:53.935403+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOPIJFFNE44P","created_at":"2026-07-05T06:17:53.935403+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOPIJFFNE44PUK74","created_at":"2026-07-05T06:17:53.935403+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOPIJFFN","created_at":"2026-07-05T06:17:53.935403+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/DOPIJFFNE44PUK742YKUVQBBLI","json":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI.json","graph_json":"https://pith.science/api/pith-number/DOPIJFFNE44PUK742YKUVQBBLI/graph.json","events_json":"https://pith.science/api/pith-number/DOPIJFFNE44PUK742YKUVQBBLI/events.json","paper":"https://pith.science/paper/DOPIJFFN"},"agent_actions":{"view_html":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI","download_json":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI.json","view_paper":"https://pith.science/paper/DOPIJFFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03109&json=true","fetch_graph":"https://pith.science/api/pith-number/DOPIJFFNE44PUK742YKUVQBBLI/graph.json","fetch_events":"https://pith.science/api/pith-number/DOPIJFFNE44PUK742YKUVQBBLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI/action/storage_attestation","attest_author":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI/action/author_attestation","sign_citation":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI/action/citation_signature","submit_replication":"https://pith.science/pith/DOPIJFFNE44PUK742YKUVQBBLI/action/replication_record"}},"created_at":"2026-07-05T06:17:53.935403+00:00","updated_at":"2026-07-05T06:17:53.935403+00:00"}