{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OK4Y3XM2VTR4MQKMVBXG4EXOME","short_pith_number":"pith:OK4Y3XM2","schema_version":"1.0","canonical_sha256":"72b98ddd9aace3c6414ca86e6e12ee6109af91c94e189eb34f8dfa804e63d79b","source":{"kind":"arxiv","id":"2505.05652","version":1},"attestation_state":"computed","paper":{"title":"Fast and Fourier Features for Transfer Learning of Interatomic Potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.comp-ph","authors_text":"Giacomo Meanti, Lorenzo Rosasco, Luigi Bonati, Massimiliano Pontil, Michele Parrinello, Pedro J. Buigues, Pietro Novelli","submitted_at":"2025-05-08T21:18:10Z","abstract_excerpt":"Training machine learning interatomic potentials that are both computationally and data-efficient is a key challenge for enabling their routine use in atomistic simulations. To this effect, we introduce franken, a scalable and lightweight transfer learning framework that extracts atomic descriptors from pretrained graph neural networks and transfer them to new systems using random Fourier features-an efficient and scalable approximation of kernel methods. Franken enables fast and accurate adaptation of general-purpose potentials to new systems or levels of quantum mechanical theory without req"},"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":"2505.05652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2025-05-08T21:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"37de23462b5adb1bc70ab7198c4caaa212510f7e2b7d7d6c279684d501afb487","abstract_canon_sha256":"68d44869bc1214ee2bd2129214c89c12aef445cacdaa1725bb41c3f0cc75973c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:45.365369Z","signature_b64":"PyFayjkqeusmH+Bx6iglq4TZq83TfeTsUUyKJjSAyXmWUbrx5SaetH95qf/CAW/H+KcN3X8w5y6DLb2yIILUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72b98ddd9aace3c6414ca86e6e12ee6109af91c94e189eb34f8dfa804e63d79b","last_reissued_at":"2026-07-05T11:00:45.364867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:45.364867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Fourier Features for Transfer Learning of Interatomic Potentials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.comp-ph","authors_text":"Giacomo Meanti, Lorenzo Rosasco, Luigi Bonati, Massimiliano Pontil, Michele Parrinello, Pedro J. Buigues, Pietro Novelli","submitted_at":"2025-05-08T21:18:10Z","abstract_excerpt":"Training machine learning interatomic potentials that are both computationally and data-efficient is a key challenge for enabling their routine use in atomistic simulations. To this effect, we introduce franken, a scalable and lightweight transfer learning framework that extracts atomic descriptors from pretrained graph neural networks and transfer them to new systems using random Fourier features-an efficient and scalable approximation of kernel methods. Franken enables fast and accurate adaptation of general-purpose potentials to new systems or levels of quantum mechanical theory without req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05652","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/2505.05652/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":"2505.05652","created_at":"2026-07-05T11:00:45.364929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05652v1","created_at":"2026-07-05T11:00:45.364929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05652","created_at":"2026-07-05T11:00:45.364929+00:00"},{"alias_kind":"pith_short_12","alias_value":"OK4Y3XM2VTR4","created_at":"2026-07-05T11:00:45.364929+00:00"},{"alias_kind":"pith_short_16","alias_value":"OK4Y3XM2VTR4MQKM","created_at":"2026-07-05T11:00:45.364929+00:00"},{"alias_kind":"pith_short_8","alias_value":"OK4Y3XM2","created_at":"2026-07-05T11:00:45.364929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.03433","citing_title":"Dyna-Mat: End-to-end benchmarking of foundation machine learning interatomic potentials in finite-temperature ensembles","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME","json":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME.json","graph_json":"https://pith.science/api/pith-number/OK4Y3XM2VTR4MQKMVBXG4EXOME/graph.json","events_json":"https://pith.science/api/pith-number/OK4Y3XM2VTR4MQKMVBXG4EXOME/events.json","paper":"https://pith.science/paper/OK4Y3XM2"},"agent_actions":{"view_html":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME","download_json":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME.json","view_paper":"https://pith.science/paper/OK4Y3XM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05652&json=true","fetch_graph":"https://pith.science/api/pith-number/OK4Y3XM2VTR4MQKMVBXG4EXOME/graph.json","fetch_events":"https://pith.science/api/pith-number/OK4Y3XM2VTR4MQKMVBXG4EXOME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME/action/storage_attestation","attest_author":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME/action/author_attestation","sign_citation":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME/action/citation_signature","submit_replication":"https://pith.science/pith/OK4Y3XM2VTR4MQKMVBXG4EXOME/action/replication_record"}},"created_at":"2026-07-05T11:00:45.364929+00:00","updated_at":"2026-07-05T11:00:45.364929+00:00"}