{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GBEK6UEASNLAZ4E2BFTMNRCZVR","short_pith_number":"pith:GBEK6UEA","schema_version":"1.0","canonical_sha256":"3048af508093560cf09a0966c6c459ac6a31f684e2646811ed1493076f1627c1","source":{"kind":"arxiv","id":"2506.15337","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Meguru Yamazaki, Naoki Matsumura, Yasufumi Sakai, Yuta Yoshimoto, Yuto Iwasaki","submitted_at":"2025-06-18T10:32:26Z","abstract_excerpt":"Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data encompassing both low-energy stable structures and high-energy structures. Conventional knowledge distillation (KD) methods fine-tune a pre-trained NNP as a teacher model to generate training data for a student model. However, in material-specific models, this fine-tuning process increases energy barriers, making it difficult to create training data containing high"},"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":"2506.15337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T10:32:26Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.comp-ph"],"title_canon_sha256":"e9b43db1bf757490b8f2eac96bd65fe10316fe5650cd80aa5508612696c5001a","abstract_canon_sha256":"0eabd21c07afa0e0a10c17b26c0448de9db4dc99e72c42936416e1f5ebfaa31b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:24.927657Z","signature_b64":"ilM38Z2EwwvyqdNMdznc4QyKrkZm5B22+TojkhQJOT1J4BBwsVoCQ0gh7MXbtwcGnZpDYNgbZjgsoLHzm391CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3048af508093560cf09a0966c6c459ac6a31f684e2646811ed1493076f1627c1","last_reissued_at":"2026-07-05T11:24:24.927068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:24.927068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Meguru Yamazaki, Naoki Matsumura, Yasufumi Sakai, Yuta Yoshimoto, Yuto Iwasaki","submitted_at":"2025-06-18T10:32:26Z","abstract_excerpt":"Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data encompassing both low-energy stable structures and high-energy structures. Conventional knowledge distillation (KD) methods fine-tune a pre-trained NNP as a teacher model to generate training data for a student model. However, in material-specific models, this fine-tuning process increases energy barriers, making it difficult to create training data containing high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15337","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/2506.15337/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":"2506.15337","created_at":"2026-07-05T11:24:24.927134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15337v2","created_at":"2026-07-05T11:24:24.927134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15337","created_at":"2026-07-05T11:24:24.927134+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBEK6UEASNLA","created_at":"2026-07-05T11:24:24.927134+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBEK6UEASNLAZ4E2","created_at":"2026-07-05T11:24:24.927134+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBEK6UEA","created_at":"2026-07-05T11:24:24.927134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06848","citing_title":"Distilling first-principles accuracy into compact machine learning potentials for condensed-phase chemistry","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14527","citing_title":"Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR","json":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR.json","graph_json":"https://pith.science/api/pith-number/GBEK6UEASNLAZ4E2BFTMNRCZVR/graph.json","events_json":"https://pith.science/api/pith-number/GBEK6UEASNLAZ4E2BFTMNRCZVR/events.json","paper":"https://pith.science/paper/GBEK6UEA"},"agent_actions":{"view_html":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR","download_json":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR.json","view_paper":"https://pith.science/paper/GBEK6UEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15337&json=true","fetch_graph":"https://pith.science/api/pith-number/GBEK6UEASNLAZ4E2BFTMNRCZVR/graph.json","fetch_events":"https://pith.science/api/pith-number/GBEK6UEASNLAZ4E2BFTMNRCZVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR/action/storage_attestation","attest_author":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR/action/author_attestation","sign_citation":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR/action/citation_signature","submit_replication":"https://pith.science/pith/GBEK6UEASNLAZ4E2BFTMNRCZVR/action/replication_record"}},"created_at":"2026-07-05T11:24:24.927134+00:00","updated_at":"2026-07-05T11:24:24.927134+00:00"}