{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MJJ5WQZSEF2Y3HBOSD6QRKYCSY","short_pith_number":"pith:MJJ5WQZS","schema_version":"1.0","canonical_sha256":"6253db433221758d9c2e90fd08ab029636a268d990fd72736cacdb026bc3a85e","source":{"kind":"arxiv","id":"2506.04055","version":1},"attestation_state":"computed","paper":{"title":"chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Julija Zavadlav, Paul Fuchs, Stephan Thaler, Weilong Chen","submitted_at":"2025-06-04T15:19:26Z","abstract_excerpt":"Machine learning potentials (MLPs) have advanced rapidly and show great promise to transform molecular dynamics (MD) simulations. However, most existing software tools are tied to specific MLP architectures, lack integration with standard MD packages, or are not parallelizable across GPUs. To address these challenges, we present chemtrain-deploy, a framework that enables model-agnostic deployment of MLPs in LAMMPS. chemtrain-deploy supports any JAX-defined semi-local potential, allowing users to exploit the functionality of LAMMPS and perform large-scale MLP-based MD simulations on multiple GP"},"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":"2506.04055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.comp-ph","submitted_at":"2025-06-04T15:19:26Z","cross_cats_sorted":["cs.LG","physics.chem-ph"],"title_canon_sha256":"d082c562b1f3076012a37bca11da83eb73d15f167922504a6df2a92f468bfe23","abstract_canon_sha256":"b5c14e3bdbb5149e815d41752dc26b36e3d8deeec4449fc86ab95c7d014a245e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:56.276153Z","signature_b64":"G/Rk/nNk4iG50zTwes/ll7QJrZ9mhkCBrChjIRqpAfAeY+3NHz9tXBywZrlE1FbpnJGuRntY5WIsluRnjVjnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6253db433221758d9c2e90fd08ab029636a268d990fd72736cacdb026bc3a85e","last_reissued_at":"2026-07-05T11:15:56.275696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:56.275696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.chem-ph"],"primary_cat":"physics.comp-ph","authors_text":"Julija Zavadlav, Paul Fuchs, Stephan Thaler, Weilong Chen","submitted_at":"2025-06-04T15:19:26Z","abstract_excerpt":"Machine learning potentials (MLPs) have advanced rapidly and show great promise to transform molecular dynamics (MD) simulations. However, most existing software tools are tied to specific MLP architectures, lack integration with standard MD packages, or are not parallelizable across GPUs. To address these challenges, we present chemtrain-deploy, a framework that enables model-agnostic deployment of MLPs in LAMMPS. chemtrain-deploy supports any JAX-defined semi-local potential, allowing users to exploit the functionality of LAMMPS and perform large-scale MLP-based MD simulations on multiple GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04055","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/2506.04055/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":"2506.04055","created_at":"2026-07-05T11:15:56.275759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04055v1","created_at":"2026-07-05T11:15:56.275759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04055","created_at":"2026-07-05T11:15:56.275759+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJJ5WQZSEF2Y","created_at":"2026-07-05T11:15:56.275759+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJJ5WQZSEF2Y3HBO","created_at":"2026-07-05T11:15:56.275759+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJJ5WQZS","created_at":"2026-07-05T11:15:56.275759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07276","citing_title":"Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY","json":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY.json","graph_json":"https://pith.science/api/pith-number/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/graph.json","events_json":"https://pith.science/api/pith-number/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/events.json","paper":"https://pith.science/paper/MJJ5WQZS"},"agent_actions":{"view_html":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY","download_json":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY.json","view_paper":"https://pith.science/paper/MJJ5WQZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04055&json=true","fetch_graph":"https://pith.science/api/pith-number/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/graph.json","fetch_events":"https://pith.science/api/pith-number/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/action/storage_attestation","attest_author":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/action/author_attestation","sign_citation":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/action/citation_signature","submit_replication":"https://pith.science/pith/MJJ5WQZSEF2Y3HBOSD6QRKYCSY/action/replication_record"}},"created_at":"2026-07-05T11:15:56.275759+00:00","updated_at":"2026-07-05T11:15:56.275759+00:00"}