{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:47KHNEZVXM4X27YDSKNAO5OPY6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a00d9f280bddf5ba03f05ac96e0b345d6848b8daa441e8f16c2566c355974e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-09-04T18:29:30Z","title_canon_sha256":"7934f6e432741b9229aec86eef1935a51a605c94414c50874f792fca9013a8fb"},"schema_version":"1.0","source":{"id":"1909.02041","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02041","created_at":"2026-07-05T05:54:25Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02041v4","created_at":"2026-07-05T05:54:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02041","created_at":"2026-07-05T05:54:25Z"},{"alias_kind":"pith_short_12","alias_value":"47KHNEZVXM4X","created_at":"2026-07-05T05:54:25Z"},{"alias_kind":"pith_short_16","alias_value":"47KHNEZVXM4X27YD","created_at":"2026-07-05T05:54:25Z"},{"alias_kind":"pith_short_8","alias_value":"47KHNEZV","created_at":"2026-07-05T05:54:25Z"}],"graph_snapshots":[{"event_id":"sha256:a2579240e7469f82319e868ff02a4bd0d1983808273a13d3c925965f01ed2ea3","target":"graph","created_at":"2026-07-05T05:54:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.02041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lixue Cheng, Matthew Welborn, Nikola B. Kovachki, Thomas F. Miller III","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-09-04T18:29:30Z","title":"Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02041","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3d7c283f0ecd2c6a67d2a4dd39b106f253c17189f19b0a4ad24e32a1835d3026","target":"record","created_at":"2026-07-05T05:54:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9a00d9f280bddf5ba03f05ac96e0b345d6848b8daa441e8f16c2566c355974e4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2019-09-04T18:29:30Z","title_canon_sha256":"7934f6e432741b9229aec86eef1935a51a605c94414c50874f792fca9013a8fb"},"schema_version":"1.0","source":{"id":"1909.02041","kind":"arxiv","version":4}},"canonical_sha256":"e7d4769335bb397d7f03929a0775cfc7969be86060c4c818fc4ac3b4061d5ee1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7d4769335bb397d7f03929a0775cfc7969be86060c4c818fc4ac3b4061d5ee1","first_computed_at":"2026-07-05T05:54:25.125827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:25.125827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCn/FSlMEYPvIAmYIa/cXPo2L0TbZ5+cuExX4KHpEucjPi+HqnB6bHtVQMfwL/WPpGLFChEbsTVr1ZCqKmwjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:25.126435Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02041","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d7c283f0ecd2c6a67d2a4dd39b106f253c17189f19b0a4ad24e32a1835d3026","sha256:a2579240e7469f82319e868ff02a4bd0d1983808273a13d3c925965f01ed2ea3"],"state_sha256":"28826766b79c1c4d6b7ffd739869475baa8ade11aba178032f629abd14198960"}