{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y3PJSEPBH5A5Q75NSRHJVMGICR","short_pith_number":"pith:Y3PJSEPB","schema_version":"1.0","canonical_sha256":"c6de9911e13f41d87fad944e9ab0c814737682c090f260ddd4f9ab22d461e21e","source":{"kind":"arxiv","id":"2212.01574","version":2},"attestation_state":"computed","paper":{"title":"Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Afshan Mohajeri, Alan Aspuru-Guzik, Aniket Zinzuwadia, Benjamin Sanchez-Lengeling, Gary Tom, Riley J. Hickman","submitted_at":"2022-12-03T08:19:06Z","abstract_excerpt":"Deep learning models that leverage large datasets are often the state of the art for modelling molecular properties. When the datasets are smaller (< 2000 molecules), it is not clear that deep learning approaches are the right modelling tool. In this work we perform an extensive study of the calibration and generalizability of probabilistic machine learning models on small chemical datasets. Using different molecular representations and models, we analyse the quality of their predictions and uncertainties in a variety of tasks (binary, regression) and datasets. We also introduce two simulated "},"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":"2212.01574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2022-12-03T08:19:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"759ab282f6de00cddd08d49e055339255f63fc2ce4ec1ab995e37ca6bcebf674","abstract_canon_sha256":"268d1366b20e9045be9b7f0b76796d8327b6f0d192267bc082889de514fded33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:02.311330Z","signature_b64":"vt1JcCaxzP7YAP1GShrR+jTTYlw4vd340zFWKwOY439deqvevdVbwmpXnzukYa9F/1Ian7eFY2QBuyrLEjq6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6de9911e13f41d87fad944e9ab0c814737682c090f260ddd4f9ab22d461e21e","last_reissued_at":"2026-07-05T05:23:02.310901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:02.310901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Afshan Mohajeri, Alan Aspuru-Guzik, Aniket Zinzuwadia, Benjamin Sanchez-Lengeling, Gary Tom, Riley J. Hickman","submitted_at":"2022-12-03T08:19:06Z","abstract_excerpt":"Deep learning models that leverage large datasets are often the state of the art for modelling molecular properties. When the datasets are smaller (< 2000 molecules), it is not clear that deep learning approaches are the right modelling tool. In this work we perform an extensive study of the calibration and generalizability of probabilistic machine learning models on small chemical datasets. Using different molecular representations and models, we analyse the quality of their predictions and uncertainties in a variety of tasks (binary, regression) and datasets. We also introduce two simulated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01574","kind":"arxiv","version":2},"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/2212.01574/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":"2212.01574","created_at":"2026-07-05T05:23:02.310965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01574v2","created_at":"2026-07-05T05:23:02.310965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01574","created_at":"2026-07-05T05:23:02.310965+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3PJSEPBH5A5","created_at":"2026-07-05T05:23:02.310965+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3PJSEPBH5A5Q75N","created_at":"2026-07-05T05:23:02.310965+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3PJSEPB","created_at":"2026-07-05T05:23:02.310965+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/Y3PJSEPBH5A5Q75NSRHJVMGICR","json":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR.json","graph_json":"https://pith.science/api/pith-number/Y3PJSEPBH5A5Q75NSRHJVMGICR/graph.json","events_json":"https://pith.science/api/pith-number/Y3PJSEPBH5A5Q75NSRHJVMGICR/events.json","paper":"https://pith.science/paper/Y3PJSEPB"},"agent_actions":{"view_html":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR","download_json":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR.json","view_paper":"https://pith.science/paper/Y3PJSEPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01574&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3PJSEPBH5A5Q75NSRHJVMGICR/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3PJSEPBH5A5Q75NSRHJVMGICR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR/action/storage_attestation","attest_author":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR/action/author_attestation","sign_citation":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR/action/citation_signature","submit_replication":"https://pith.science/pith/Y3PJSEPBH5A5Q75NSRHJVMGICR/action/replication_record"}},"created_at":"2026-07-05T05:23:02.310965+00:00","updated_at":"2026-07-05T05:23:02.310965+00:00"}