{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NDUFPPE6BUZVWQXLDIPMDUND7H","short_pith_number":"pith:NDUFPPE6","schema_version":"1.0","canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","source":{"kind":"arxiv","id":"2604.24474","version":2},"attestation_state":"computed","paper":{"title":"Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shiyun Wa, Simone Sciabola, Ye Wang, Yifei Wang","submitted_at":"2026-04-27T13:43:20Z","abstract_excerpt":"Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular generation. However, traditional similarity measures, ranging from fingerprint-based Tanimoto coefficients to 3D shape overlays, are often computationally expensive at scale or rely on hand-crafted molecular descriptors. Meanwhile, many deep learning approaches to similarity-aware design still depend on similarity-specific supervision or costly data curation, limiting their generality across targets. In this work, we propose pretrained embedding dis"},"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":"2604.24474","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T13:43:20Z","cross_cats_sorted":[],"title_canon_sha256":"7d9661b1176009947aba37348c4e01aab75d5ae5d5dbdb744cb2278628bc30a3","abstract_canon_sha256":"3d0c638a16fbbb7270cf248c3f6dea40ce840f80c0f6b9c18dedce0418f647c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:43.145981Z","signature_b64":"6i97dhAfrIeuke2Ql4PSMS70E3UyUq9IX/C3farm4w6ueTWSxJXt4jyPyLTb0jciquUaGPc9OBfNo60Bt78KAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","last_reissued_at":"2026-06-09T01:04:43.145553Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:43.145553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shiyun Wa, Simone Sciabola, Ye Wang, Yifei Wang","submitted_at":"2026-04-27T13:43:20Z","abstract_excerpt":"Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular generation. However, traditional similarity measures, ranging from fingerprint-based Tanimoto coefficients to 3D shape overlays, are often computationally expensive at scale or rely on hand-crafted molecular descriptors. Meanwhile, many deep learning approaches to similarity-aware design still depend on similarity-specific supervision or costly data curation, limiting their generality across targets. In this work, we propose pretrained embedding dis"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"pretrained embedding distance (PED) ... exhibits distinct correlations with traditional similarity metrics, and performs effectively in both ranking molecules for virtual screening and guiding molecular generation via reward design.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings from general pretrained molecular models already capture the structural information needed for effective similarity measurement across targets, without requiring task-specific supervision or data curation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pretrained molecular embedding distances provide an effective similarity metric for ligand-based virtual screening and molecular generation without task-specific training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ac7258a12070b22ffdbcf4b5de50cbeec7a0a425d0ec7fe65daba0cd3f585195"},"source":{"id":"2604.24474","kind":"arxiv","version":2},"verdict":{"id":"cec7f059-88f4-4cd8-8e13-1034409184de","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T04:00:37.208696Z","strongest_claim":"pretrained embedding distance (PED) ... exhibits distinct correlations with traditional similarity metrics, and performs effectively in both ranking molecules for virtual screening and guiding molecular generation via reward design.","one_line_summary":"Pretrained molecular embedding distances provide an effective similarity metric for ligand-based virtual screening and molecular generation without task-specific training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings from general pretrained molecular models already capture the structural information needed for effective similarity measurement across targets, without requiring task-specific supervision or data curation.","pith_extraction_headline":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24474/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T06:39:47.405703Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:03:38.125400Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1fb529372e33ec1760357765bdc04df50ce403fbfc3e38846e3485244e43f43e"},"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":"2604.24474","created_at":"2026-06-09T01:04:43.145607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.24474v2","created_at":"2026-06-09T01:04:43.145607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24474","created_at":"2026-06-09T01:04:43.145607+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDUFPPE6BUZV","created_at":"2026-06-09T01:04:43.145607+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDUFPPE6BUZVWQXL","created_at":"2026-06-09T01:04:43.145607+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDUFPPE6","created_at":"2026-06-09T01:04:43.145607+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/NDUFPPE6BUZVWQXLDIPMDUND7H","json":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H.json","graph_json":"https://pith.science/api/pith-number/NDUFPPE6BUZVWQXLDIPMDUND7H/graph.json","events_json":"https://pith.science/api/pith-number/NDUFPPE6BUZVWQXLDIPMDUND7H/events.json","paper":"https://pith.science/paper/NDUFPPE6"},"agent_actions":{"view_html":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H","download_json":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H.json","view_paper":"https://pith.science/paper/NDUFPPE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.24474&json=true","fetch_graph":"https://pith.science/api/pith-number/NDUFPPE6BUZVWQXLDIPMDUND7H/graph.json","fetch_events":"https://pith.science/api/pith-number/NDUFPPE6BUZVWQXLDIPMDUND7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/action/storage_attestation","attest_author":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/action/author_attestation","sign_citation":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/action/citation_signature","submit_replication":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/action/replication_record"}},"created_at":"2026-06-09T01:04:43.145607+00:00","updated_at":"2026-06-09T01:04:43.145607+00:00"}