{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FUUIHUN3GQRCLXLSRUZ5Z47TEG","short_pith_number":"pith:FUUIHUN3","schema_version":"1.0","canonical_sha256":"2d2883d1bb342225dd728d33dcf3f321a1e0999e88de91d13aaf7e3bb4e20e9e","source":{"kind":"arxiv","id":"2605.24073","version":1},"attestation_state":"computed","paper":{"title":"Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Ihor Neporozhnii, Oleksandr Voznyy, Sjoerd Hoogland","submitted_at":"2026-05-22T14:12:27Z","abstract_excerpt":"Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorporating electronic structure information using multitask learning improves sample efficiency, however, training on full Hamiltonian matrices, which scale quadratically with the number of atoms, is intractable for large datasets. In this work, we show that multitask learning utilizing orbitally resolved semiempirical charges significantly improves sample efficiency and accuracy in MLIPs. To efficiently predict orbital c"},"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":"2605.24073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2026-05-22T14:12:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"182b80f544564f8cd99fa37a13e423146899d287d04e5ed96bb2dc5bd5ee895e","abstract_canon_sha256":"18d58da6256e9f9dcbaf536862a6413aaf16fb6da3fd9f453a015e965f112788"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:43.939926Z","signature_b64":"CAwErRnl2Y0d2OED8dzjZm2OPq0NcKRpoMIksFAoZl1U2YYGKS7S2LikBkrvRoRVm4v7NxVyUxZ2uZMOpiUwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d2883d1bb342225dd728d33dcf3f321a1e0999e88de91d13aaf7e3bb4e20e9e","last_reissued_at":"2026-05-26T01:02:43.939058Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:43.939058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Ihor Neporozhnii, Oleksandr Voznyy, Sjoerd Hoogland","submitted_at":"2026-05-22T14:12:27Z","abstract_excerpt":"Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorporating electronic structure information using multitask learning improves sample efficiency, however, training on full Hamiltonian matrices, which scale quadratically with the number of atoms, is intractable for large datasets. In this work, we show that multitask learning utilizing orbitally resolved semiempirical charges significantly improves sample efficiency and accuracy in MLIPs. To efficiently predict orbital c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24073","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/2605.24073/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":"2605.24073","created_at":"2026-05-26T01:02:43.939204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24073v1","created_at":"2026-05-26T01:02:43.939204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24073","created_at":"2026-05-26T01:02:43.939204+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUUIHUN3GQRC","created_at":"2026-05-26T01:02:43.939204+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUUIHUN3GQRCLXLS","created_at":"2026-05-26T01:02:43.939204+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUUIHUN3","created_at":"2026-05-26T01:02:43.939204+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/FUUIHUN3GQRCLXLSRUZ5Z47TEG","json":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG.json","graph_json":"https://pith.science/api/pith-number/FUUIHUN3GQRCLXLSRUZ5Z47TEG/graph.json","events_json":"https://pith.science/api/pith-number/FUUIHUN3GQRCLXLSRUZ5Z47TEG/events.json","paper":"https://pith.science/paper/FUUIHUN3"},"agent_actions":{"view_html":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG","download_json":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG.json","view_paper":"https://pith.science/paper/FUUIHUN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24073&json=true","fetch_graph":"https://pith.science/api/pith-number/FUUIHUN3GQRCLXLSRUZ5Z47TEG/graph.json","fetch_events":"https://pith.science/api/pith-number/FUUIHUN3GQRCLXLSRUZ5Z47TEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG/action/storage_attestation","attest_author":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG/action/author_attestation","sign_citation":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG/action/citation_signature","submit_replication":"https://pith.science/pith/FUUIHUN3GQRCLXLSRUZ5Z47TEG/action/replication_record"}},"created_at":"2026-05-26T01:02:43.939204+00:00","updated_at":"2026-05-26T01:02:43.939204+00:00"}