{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:47KHNEZVXM4X27YDSKNAO5OPY6","short_pith_number":"pith:47KHNEZV","schema_version":"1.0","canonical_sha256":"e7d4769335bb397d7f03929a0775cfc7969be86060c4c818fc4ac3b4061d5ee1","source":{"kind":"arxiv","id":"1909.02041","version":4},"attestation_state":"computed","paper":{"title":"Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Lixue Cheng, Matthew Welborn, Nikola B. Kovachki, Thomas F. Miller III","submitted_at":"2019-09-04T18:29:30Z","abstract_excerpt":"Machine learning (ML) in the representation of molecular-orbital-based (MOB) features has been shown to be an accurate and transferable approach to the prediction of post-Hartree-Fock correlation energies. Previous applications of MOB-ML employed Gaussian Process Regression (GPR), which provides good prediction accuracy with small training sets; however, the cost of GPR training scales cubically with the amount of data and becomes a computational bottleneck for large training sets. In the current work, we address this problem by introducing a clustering/regression/classification implementation"},"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":"1909.02041","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-09-04T18:29:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7934f6e432741b9229aec86eef1935a51a605c94414c50874f792fca9013a8fb","abstract_canon_sha256":"9a00d9f280bddf5ba03f05ac96e0b345d6848b8daa441e8f16c2566c355974e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:25.126435Z","signature_b64":"NCn/FSlMEYPvIAmYIa/cXPo2L0TbZ5+cuExX4KHpEucjPi+HqnB6bHtVQMfwL/WPpGLFChEbsTVr1ZCqKmwjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7d4769335bb397d7f03929a0775cfc7969be86060c4c818fc4ac3b4061d5ee1","last_reissued_at":"2026-07-05T05:54:25.125827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:25.125827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Lixue Cheng, Matthew Welborn, Nikola B. Kovachki, Thomas F. Miller III","submitted_at":"2019-09-04T18:29:30Z","abstract_excerpt":"Machine learning (ML) in the representation of molecular-orbital-based (MOB) features has been shown to be an accurate and transferable approach to the prediction of post-Hartree-Fock correlation energies. Previous applications of MOB-ML employed Gaussian Process Regression (GPR), which provides good prediction accuracy with small training sets; however, the cost of GPR training scales cubically with the amount of data and becomes a computational bottleneck for large training sets. In the current work, we address this problem by introducing a clustering/regression/classification implementation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02041","kind":"arxiv","version":4},"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/1909.02041/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":"1909.02041","created_at":"2026-07-05T05:54:25.125888+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02041v4","created_at":"2026-07-05T05:54:25.125888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02041","created_at":"2026-07-05T05:54:25.125888+00:00"},{"alias_kind":"pith_short_12","alias_value":"47KHNEZVXM4X","created_at":"2026-07-05T05:54:25.125888+00:00"},{"alias_kind":"pith_short_16","alias_value":"47KHNEZVXM4X27YD","created_at":"2026-07-05T05:54:25.125888+00:00"},{"alias_kind":"pith_short_8","alias_value":"47KHNEZV","created_at":"2026-07-05T05:54:25.125888+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/47KHNEZVXM4X27YDSKNAO5OPY6","json":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6.json","graph_json":"https://pith.science/api/pith-number/47KHNEZVXM4X27YDSKNAO5OPY6/graph.json","events_json":"https://pith.science/api/pith-number/47KHNEZVXM4X27YDSKNAO5OPY6/events.json","paper":"https://pith.science/paper/47KHNEZV"},"agent_actions":{"view_html":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6","download_json":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6.json","view_paper":"https://pith.science/paper/47KHNEZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02041&json=true","fetch_graph":"https://pith.science/api/pith-number/47KHNEZVXM4X27YDSKNAO5OPY6/graph.json","fetch_events":"https://pith.science/api/pith-number/47KHNEZVXM4X27YDSKNAO5OPY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6/action/storage_attestation","attest_author":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6/action/author_attestation","sign_citation":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6/action/citation_signature","submit_replication":"https://pith.science/pith/47KHNEZVXM4X27YDSKNAO5OPY6/action/replication_record"}},"created_at":"2026-07-05T05:54:25.125888+00:00","updated_at":"2026-07-05T05:54:25.125888+00:00"}