{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPB7D2MKPTDM625VLBYSQLJE32","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":"b66114c98be428a27b2fd0a5f8aed5f547fda1faf4c3aa354ae752a32598011a","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T09:48:02Z","title_canon_sha256":"e4a044f4ce09ef07e01b35d0d02247f656831d1380d565a679301ddf43952118"},"schema_version":"1.0","source":{"id":"2505.12913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12913","created_at":"2026-07-05T11:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12913v1","created_at":"2026-07-05T11:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12913","created_at":"2026-07-05T11:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"XPB7D2MKPTDM","created_at":"2026-07-05T11:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"XPB7D2MKPTDM625V","created_at":"2026-07-05T11:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"XPB7D2MK","created_at":"2026-07-05T11:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:d5f2d89cd3d46b66abfe8c3e4b119c1287d91edc10a622f3867148f2931afcbb","target":"graph","created_at":"2026-07-05T11:05:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.12913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adam Taouil, Dominique Sydow, Liam Wilbraham, Mason Burlage, Oliver Brook Scott, Tom George Grigg","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T09:48:02Z","title":"Active Learning on Synthons for Molecular Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12913","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:a83a21ab3ddbfce928538a3d22097191264ad7004bf13b23a69fcc3b992c6c66","target":"record","created_at":"2026-07-05T11:05:11Z","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":"b66114c98be428a27b2fd0a5f8aed5f547fda1faf4c3aa354ae752a32598011a","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T09:48:02Z","title_canon_sha256":"e4a044f4ce09ef07e01b35d0d02247f656831d1380d565a679301ddf43952118"},"schema_version":"1.0","source":{"id":"2505.12913","kind":"arxiv","version":1}},"canonical_sha256":"bbc3f1e98a7cc6cf6bb55871282d24de91ad025a529ccda9acc33b439bef6352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbc3f1e98a7cc6cf6bb55871282d24de91ad025a529ccda9acc33b439bef6352","first_computed_at":"2026-07-05T11:05:11.762078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:11.762078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mxne126ceVyv5GJV7HWsPUJFyQ73sb884dPfR+H0Xd08uU0ZOHrCWrINMWIx0t21j5TXaMRztGSAcBHWhcVLDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:11.762549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a83a21ab3ddbfce928538a3d22097191264ad7004bf13b23a69fcc3b992c6c66","sha256:d5f2d89cd3d46b66abfe8c3e4b119c1287d91edc10a622f3867148f2931afcbb"],"state_sha256":"880c48402375e290cec7a294eefc422bfcf6ea1769440b739c9dfddf61bd06e8"}