{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X4ZBJ7PJA4NNKVV5SLLRMW7HYE","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":"a766e8c664e73c3adabc462e26582a83341fbfc3aa94517f89b9db5aab04c344","cross_cats_sorted":["physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2019-06-25T00:26:40Z","title_canon_sha256":"d6762229168af633662195c57d00a825eaf1acdf516e1742dad244e3626bdf22"},"schema_version":"1.0","source":{"id":"1906.10273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10273","created_at":"2026-05-17T23:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10273v1","created_at":"2026-05-17T23:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10273","created_at":"2026-05-17T23:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"X4ZBJ7PJA4NN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X4ZBJ7PJA4NNKVV5","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X4ZBJ7PJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6c380d0fbe3af0f367fddc67960698e79a3bd0b77e3088f0f993345757202acb","target":"graph","created_at":"2026-05-17T23:42:31Z","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"},"paper":{"abstract_excerpt":"In this paper, we consider the problem of designing a training set using the most informative molecules from a specified library to build data-driven molecular property models. Specifically, we use (i) sparse generalized group additivity and (ii) kernel ridge regression as two representative classes of models, we propose a method combining rigorous model-based design of experiments and cheminformatics-based diversity-maximizing subset selection within the epsilon--greedy framework to systematically minimize the amount of data needed to train these models. We demonstrate the effectiveness of th","authors_text":"Bowen Li, Srinivas Rangarajan","cross_cats":["physics.comp-ph"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2019-06-25T00:26:40Z","title":"Designing compact training sets for data-driven molecular property prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10273","kind":"arxiv","version":1},"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":"sha256:794299bd4d5371cd0f289a469724c4f3260ac0422fbb360c7e2eb4d19e4c5b6d","target":"record","created_at":"2026-05-17T23:42:31Z","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":"a766e8c664e73c3adabc462e26582a83341fbfc3aa94517f89b9db5aab04c344","cross_cats_sorted":["physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2019-06-25T00:26:40Z","title_canon_sha256":"d6762229168af633662195c57d00a825eaf1acdf516e1742dad244e3626bdf22"},"schema_version":"1.0","source":{"id":"1906.10273","kind":"arxiv","version":1}},"canonical_sha256":"bf3214fde9071ad556bd92d7165be7c13349624f7192de00ae5a1a3eb30dc7e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf3214fde9071ad556bd92d7165be7c13349624f7192de00ae5a1a3eb30dc7e3","first_computed_at":"2026-05-17T23:42:31.770280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:31.770280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZkcG1/tipKi2baSXrbRLpVmK+BmDMFtHrGZRDZHYSH9YVInAtUEM9XfMdx6viyqrOYGrpoIqMan1BRIBntFZCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:31.771056Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:794299bd4d5371cd0f289a469724c4f3260ac0422fbb360c7e2eb4d19e4c5b6d","sha256:6c380d0fbe3af0f367fddc67960698e79a3bd0b77e3088f0f993345757202acb"],"state_sha256":"73ba00a14a34983882a59b3360ae167d87c0eea1211ac57373daff4e6de39f37"}