{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J6DAO7UGEVJOS7OXAEMLJ6JLJE","short_pith_number":"pith:J6DAO7UG","schema_version":"1.0","canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","source":{"kind":"arxiv","id":"2211.02657","version":1},"attestation_state":"computed","paper":{"title":"MolE: a molecular foundation model for drug discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Berton Earnshaw, Christos Nicolaou, Oscar M\\'endez-Lucio","submitted_at":"2022-11-03T21:22:05Z","abstract_excerpt":"Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a "},"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":"2211.02657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-03T21:22:05Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"c746ad6a75f4dbdb6e9d823c220b01587b3ead733c2a7312a00d49f0284d31ba","abstract_canon_sha256":"5b990e2ab3b82b8e1cb4e3a1af7c329fe6b1154c09ab88367ed526b68915c28b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:20.160292Z","signature_b64":"3ZTsb/OxHPyhWjsoqsvwHykWHCWKajv0QkMZ24d9Sn5+u3roEpzzfpDHcvSA7SLJ8mdaKftmK9seOyi60mYmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f86077e862552e97dd70118b4f92b490995c543223ccbbee0c06d9eb38e0f7e","last_reissued_at":"2026-07-05T05:13:20.159905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:20.159905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolE: a molecular foundation model for drug discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Berton Earnshaw, Christos Nicolaou, Oscar M\\'endez-Lucio","submitted_at":"2022-11-03T21:22:05Z","abstract_excerpt":"Models that accurately predict properties based on chemical structure are valuable tools in drug discovery. However, for many properties, public and private training sets are typically small, and it is difficult for the models to generalize well outside of the training data. Recently, large language models have addressed this problem by using self-supervised pretraining on large unlabeled datasets, followed by fine-tuning on smaller, labeled datasets. In this paper, we report MolE, a molecular foundation model that adapts the DeBERTa architecture to be used on molecular graphs together with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02657","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.02657/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":"2211.02657","created_at":"2026-07-05T05:13:20.159962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02657v1","created_at":"2026-07-05T05:13:20.159962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02657","created_at":"2026-07-05T05:13:20.159962+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6DAO7UGEVJO","created_at":"2026-07-05T05:13:20.159962+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6DAO7UGEVJOS7OX","created_at":"2026-07-05T05:13:20.159962+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6DAO7UG","created_at":"2026-07-05T05:13:20.159962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20497","citing_title":"Interpretable Meta-Learning for Multi-Objective Chemical Search","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12639","citing_title":"The Metric Picks the Winner: Evaluation Choice Flips Model Rankings for Drug-Response Prediction in Unseen Chemistry","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19752","citing_title":"MSAlign: Aligning Molecule and Mass Spectra Foundation Models for Metabolite Identification","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE","json":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE.json","graph_json":"https://pith.science/api/pith-number/J6DAO7UGEVJOS7OXAEMLJ6JLJE/graph.json","events_json":"https://pith.science/api/pith-number/J6DAO7UGEVJOS7OXAEMLJ6JLJE/events.json","paper":"https://pith.science/paper/J6DAO7UG"},"agent_actions":{"view_html":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE","download_json":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE.json","view_paper":"https://pith.science/paper/J6DAO7UG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02657&json=true","fetch_graph":"https://pith.science/api/pith-number/J6DAO7UGEVJOS7OXAEMLJ6JLJE/graph.json","fetch_events":"https://pith.science/api/pith-number/J6DAO7UGEVJOS7OXAEMLJ6JLJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/action/storage_attestation","attest_author":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/action/author_attestation","sign_citation":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/action/citation_signature","submit_replication":"https://pith.science/pith/J6DAO7UGEVJOS7OXAEMLJ6JLJE/action/replication_record"}},"created_at":"2026-07-05T05:13:20.159962+00:00","updated_at":"2026-07-05T05:13:20.159962+00:00"}