{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H6XEB5T2APDEAZVDBL3C2DGIC2","short_pith_number":"pith:H6XEB5T2","schema_version":"1.0","canonical_sha256":"3fae40f67a03c64066a30af62d0cc816a45db83b5e969e45e2c1c29a4f0efc95","source":{"kind":"arxiv","id":"2210.07237","version":2},"attestation_state":"computed","paper":{"title":"Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Rafael Gomez-Bombarelli, Sinan Keten, Tian Xie, Tommi Jaakkola, Wujie Wang, Xiang Fu, Zhenghao Wu","submitted_at":"2022-10-13T17:59:03Z","abstract_excerpt":"Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for learned MD simulation. We curate representative MD systems, includin"},"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":"2210.07237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2022-10-13T17:59:03Z","cross_cats_sorted":["cs.LG","physics.chem-ph"],"title_canon_sha256":"fc403b3a1b23a569121e3724652559963174707c9e7cacf0ad734a217c307d51","abstract_canon_sha256":"ed64cbd020b3330ff9b5bf8e4c432bc64b0ae50a26a982a3e5d8b92f77e405b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:46.600837Z","signature_b64":"/9avDBP/7qqQP+TRB/wpuAK8YkDQIXIrKIdwfpii7cLjLe/JFdz1LL7UHuP4XpRW4nDk5VbrBOXhiplR0B/lAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fae40f67a03c64066a30af62d0cc816a45db83b5e969e45e2c1c29a4f0efc95","last_reissued_at":"2026-07-05T06:44:46.600341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:46.600341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Rafael Gomez-Bombarelli, Sinan Keten, Tian Xie, Tommi Jaakkola, Wujie Wang, Xiang Fu, Zhenghao Wu","submitted_at":"2022-10-13T17:59:03Z","abstract_excerpt":"Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for learned MD simulation. We curate representative MD systems, includin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07237","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/2210.07237/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":"2210.07237","created_at":"2026-07-05T06:44:46.600397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07237v2","created_at":"2026-07-05T06:44:46.600397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07237","created_at":"2026-07-05T06:44:46.600397+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6XEB5T2APDE","created_at":"2026-07-05T06:44:46.600397+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6XEB5T2APDEAZVD","created_at":"2026-07-05T06:44:46.600397+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6XEB5T2","created_at":"2026-07-05T06:44:46.600397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18163","citing_title":"Dynamical properties of ab initio water from machine-learning potentials","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02499","citing_title":"Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00540","citing_title":"A general-purpose atomic cluster expansion interatomic potential for niobium","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24002","citing_title":"Harnessing AtomisticSkills for Agentic Atomistic Research","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29100","citing_title":"Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29584","citing_title":"Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23214","citing_title":"Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16018","citing_title":"Benchmarking empirical and machine-learned interatomic potentials using phase diagram predictions for Lead","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2405.04967","citing_title":"MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11189","citing_title":"Deep Learning for Protein Complex Prediction and Design","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07979","citing_title":"Differentiable hybrid force fields support scalable autonomous electrolyte discovery","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13848","citing_title":"NEPMaker: Active learning of neuroevolution machine learning potential for large cells","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2","json":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2.json","graph_json":"https://pith.science/api/pith-number/H6XEB5T2APDEAZVDBL3C2DGIC2/graph.json","events_json":"https://pith.science/api/pith-number/H6XEB5T2APDEAZVDBL3C2DGIC2/events.json","paper":"https://pith.science/paper/H6XEB5T2"},"agent_actions":{"view_html":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2","download_json":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2.json","view_paper":"https://pith.science/paper/H6XEB5T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07237&json=true","fetch_graph":"https://pith.science/api/pith-number/H6XEB5T2APDEAZVDBL3C2DGIC2/graph.json","fetch_events":"https://pith.science/api/pith-number/H6XEB5T2APDEAZVDBL3C2DGIC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2/action/storage_attestation","attest_author":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2/action/author_attestation","sign_citation":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2/action/citation_signature","submit_replication":"https://pith.science/pith/H6XEB5T2APDEAZVDBL3C2DGIC2/action/replication_record"}},"created_at":"2026-07-05T06:44:46.600397+00:00","updated_at":"2026-07-05T06:44:46.600397+00:00"}