{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPB7D2MKPTDM625VLBYSQLJE32","short_pith_number":"pith:XPB7D2MK","schema_version":"1.0","canonical_sha256":"bbc3f1e98a7cc6cf6bb55871282d24de91ad025a529ccda9acc33b439bef6352","source":{"kind":"arxiv","id":"2505.12913","version":1},"attestation_state":"computed","paper":{"title":"Active Learning on Synthons for Molecular Design","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Adam Taouil, Dominique Sydow, Liam Wilbraham, Mason Burlage, Oliver Brook Scott, Tom George Grigg","submitted_at":"2025-05-19T09:48:02Z","abstract_excerpt":"Exhaustive virtual screening is highly informative but often intractable against the expensive objective functions involved in modern drug discovery. This problem is exacerbated in combinatorial contexts such as multi-vector expansion, where molecular spaces can quickly become ultra-large. Here, we introduce Scalable Active Learning via Synthon Acquisition (SALSA): a simple algorithm applicable to multi-vector expansion which extends pool-based active learning to non-enumerable spaces by factoring modeling and acquisition over synthon or fragment choices. Through experiments on ligand- and str"},"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":"2505.12913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T09:48:02Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"e4a044f4ce09ef07e01b35d0d02247f656831d1380d565a679301ddf43952118","abstract_canon_sha256":"b66114c98be428a27b2fd0a5f8aed5f547fda1faf4c3aa354ae752a32598011a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:11.762549Z","signature_b64":"Mxne126ceVyv5GJV7HWsPUJFyQ73sb884dPfR+H0Xd08uU0ZOHrCWrINMWIx0t21j5TXaMRztGSAcBHWhcVLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc3f1e98a7cc6cf6bb55871282d24de91ad025a529ccda9acc33b439bef6352","last_reissued_at":"2026-07-05T11:05:11.762078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:11.762078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning on Synthons for Molecular Design","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Adam Taouil, Dominique Sydow, Liam Wilbraham, Mason Burlage, Oliver Brook Scott, Tom George Grigg","submitted_at":"2025-05-19T09:48:02Z","abstract_excerpt":"Exhaustive virtual screening is highly informative but often intractable against the expensive objective functions involved in modern drug discovery. This problem is exacerbated in combinatorial contexts such as multi-vector expansion, where molecular spaces can quickly become ultra-large. Here, we introduce Scalable Active Learning via Synthon Acquisition (SALSA): a simple algorithm applicable to multi-vector expansion which extends pool-based active learning to non-enumerable spaces by factoring modeling and acquisition over synthon or fragment choices. Through experiments on ligand- and str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12913","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/2505.12913/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":"2505.12913","created_at":"2026-07-05T11:05:11.762135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12913v1","created_at":"2026-07-05T11:05:11.762135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12913","created_at":"2026-07-05T11:05:11.762135+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPB7D2MKPTDM","created_at":"2026-07-05T11:05:11.762135+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPB7D2MKPTDM625V","created_at":"2026-07-05T11:05:11.762135+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPB7D2MK","created_at":"2026-07-05T11:05:11.762135+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/XPB7D2MKPTDM625VLBYSQLJE32","json":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32.json","graph_json":"https://pith.science/api/pith-number/XPB7D2MKPTDM625VLBYSQLJE32/graph.json","events_json":"https://pith.science/api/pith-number/XPB7D2MKPTDM625VLBYSQLJE32/events.json","paper":"https://pith.science/paper/XPB7D2MK"},"agent_actions":{"view_html":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32","download_json":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32.json","view_paper":"https://pith.science/paper/XPB7D2MK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12913&json=true","fetch_graph":"https://pith.science/api/pith-number/XPB7D2MKPTDM625VLBYSQLJE32/graph.json","fetch_events":"https://pith.science/api/pith-number/XPB7D2MKPTDM625VLBYSQLJE32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32/action/storage_attestation","attest_author":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32/action/author_attestation","sign_citation":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32/action/citation_signature","submit_replication":"https://pith.science/pith/XPB7D2MKPTDM625VLBYSQLJE32/action/replication_record"}},"created_at":"2026-07-05T11:05:11.762135+00:00","updated_at":"2026-07-05T11:05:11.762135+00:00"}