{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X4ZBJ7PJA4NNKVV5SLLRMW7HYE","short_pith_number":"pith:X4ZBJ7PJ","schema_version":"1.0","canonical_sha256":"bf3214fde9071ad556bd92d7165be7c13349624f7192de00ae5a1a3eb30dc7e3","source":{"kind":"arxiv","id":"1906.10273","version":1},"attestation_state":"computed","paper":{"title":"Designing compact training sets for data-driven molecular property prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.data-an","authors_text":"Bowen Li, Srinivas Rangarajan","submitted_at":"2019-06-25T00:26:40Z","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"},"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":"1906.10273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2019-06-25T00:26:40Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"d6762229168af633662195c57d00a825eaf1acdf516e1742dad244e3626bdf22","abstract_canon_sha256":"a766e8c664e73c3adabc462e26582a83341fbfc3aa94517f89b9db5aab04c344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:31.771056Z","signature_b64":"ZkcG1/tipKi2baSXrbRLpVmK+BmDMFtHrGZRDZHYSH9YVInAtUEM9XfMdx6viyqrOYGrpoIqMan1BRIBntFZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3214fde9071ad556bd92d7165be7c13349624f7192de00ae5a1a3eb30dc7e3","last_reissued_at":"2026-05-17T23:42:31.770280Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:31.770280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing compact training sets for data-driven molecular property prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.data-an","authors_text":"Bowen Li, Srinivas Rangarajan","submitted_at":"2019-06-25T00:26:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10273","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":""},"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":"1906.10273","created_at":"2026-05-17T23:42:31.770428+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10273v1","created_at":"2026-05-17T23:42:31.770428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10273","created_at":"2026-05-17T23:42:31.770428+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4ZBJ7PJA4NN","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4ZBJ7PJA4NNKVV5","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4ZBJ7PJ","created_at":"2026-05-18T12:33:33.725879+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/X4ZBJ7PJA4NNKVV5SLLRMW7HYE","json":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE.json","graph_json":"https://pith.science/api/pith-number/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/graph.json","events_json":"https://pith.science/api/pith-number/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/events.json","paper":"https://pith.science/paper/X4ZBJ7PJ"},"agent_actions":{"view_html":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE","download_json":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE.json","view_paper":"https://pith.science/paper/X4ZBJ7PJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10273&json=true","fetch_graph":"https://pith.science/api/pith-number/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/graph.json","fetch_events":"https://pith.science/api/pith-number/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/action/storage_attestation","attest_author":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/action/author_attestation","sign_citation":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/action/citation_signature","submit_replication":"https://pith.science/pith/X4ZBJ7PJA4NNKVV5SLLRMW7HYE/action/replication_record"}},"created_at":"2026-05-17T23:42:31.770428+00:00","updated_at":"2026-05-17T23:42:31.770428+00:00"}