{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDUFPPE6BUZVWQXLDIPMDUND7H","short_pith_number":"pith:NDUFPPE6","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"},"canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","source":{"kind":"arxiv","id":"2604.24474","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24474","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24474v2","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24474","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"NDUFPPE6BUZV","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"NDUFPPE6BUZVWQXL","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"NDUFPPE6","created_at":"2026-06-09T01:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDUFPPE6BUZVWQXLDIPMDUND7H","target":"record","payload":{"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"},"canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","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"},"source_kind":"arxiv","source_id":"2604.24474","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cN43Pfc4/1SK/AQfS5RXBJ8MUYaSVFR5OaiY/oJ2yHAzblzAoX/glEP6fM2Qvwpl2eqbRIjKfXXzAbAPVstVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:56:57.094418Z"},"content_sha256":"4362f0868a08058c4c0e212e3e430b86935335976c1f919cd9c091a3bbe67a0a","schema_version":"1.0","event_id":"sha256:4362f0868a08058c4c0e212e3e430b86935335976c1f919cd9c091a3bbe67a0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDUFPPE6BUZVWQXLDIPMDUND7H","target":"graph","payload":{"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"},"verdict_id":"cec7f059-88f4-4cd8-8e13-1034409184de"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Qd47HgNTJCIowNPBYaAfDEpWN/j3gWXRiij4aUo2qDKPJl4vickMXIdEARF9heGSRzQLgz+QYLUHnDJtyfqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:56:57.095515Z"},"content_sha256":"e228ca0155c6f97f7b17b9f9361473776f068f8c3d45b01b8438f43f9d358697","schema_version":"1.0","event_id":"sha256:e228ca0155c6f97f7b17b9f9361473776f068f8c3d45b01b8438f43f9d358697"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/bundle.json","state_url":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-12T00:56:57Z","links":{"resolver":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H","bundle":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/bundle.json","state":"https://pith.science/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDUFPPE6BUZVWQXLDIPMDUND7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDUFPPE6BUZVWQXLDIPMDUND7H","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":"3d0c638a16fbbb7270cf248c3f6dea40ce840f80c0f6b9c18dedce0418f647c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T13:43:20Z","title_canon_sha256":"7d9661b1176009947aba37348c4e01aab75d5ae5d5dbdb744cb2278628bc30a3"},"schema_version":"1.0","source":{"id":"2604.24474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24474","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24474v2","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24474","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"NDUFPPE6BUZV","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"NDUFPPE6BUZVWQXL","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"NDUFPPE6","created_at":"2026-06-09T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:e228ca0155c6f97f7b17b9f9361473776f068f8c3d45b01b8438f43f9d358697","target":"graph","created_at":"2026-06-09T01:04:43Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Pretrained molecular embedding distances provide an effective similarity metric for ligand-based virtual screening and molecular generation without task-specific training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation."}],"snapshot_sha256":"ac7258a12070b22ffdbcf4b5de50cbeec7a0a425d0ec7fe65daba0cd3f585195"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.24474/integrity.json","findings":[],"snapshot_sha256":"1fb529372e33ec1760357765bdc04df50ce403fbfc3e38846e3485244e43f43e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shiyun Wa, Simone Sciabola, Ye Wang, Yifei Wang","cross_cats":[],"headline":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T13:43:20Z","title":"Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.24474","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T04:00:37.208696Z","id":"cec7f059-88f4-4cd8-8e13-1034409184de","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Pretrained embedding distances serve as an effective training-free measure of molecular similarity for virtual screening and generation.","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.","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."}},"verdict_id":"cec7f059-88f4-4cd8-8e13-1034409184de"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4362f0868a08058c4c0e212e3e430b86935335976c1f919cd9c091a3bbe67a0a","target":"record","created_at":"2026-06-09T01:04:43Z","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":"3d0c638a16fbbb7270cf248c3f6dea40ce840f80c0f6b9c18dedce0418f647c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T13:43:20Z","title_canon_sha256":"7d9661b1176009947aba37348c4e01aab75d5ae5d5dbdb744cb2278628bc30a3"},"schema_version":"1.0","source":{"id":"2604.24474","kind":"arxiv","version":2}},"canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68e857bc9e0d335b42eb1a1ec1d1a3f9f595fbc2c9585cc47f89f7fe58c32310","first_computed_at":"2026-06-09T01:04:43.145553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:43.145553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6i97dhAfrIeuke2Ql4PSMS70E3UyUq9IX/C3farm4w6ueTWSxJXt4jyPyLTb0jciquUaGPc9OBfNo60Bt78KAg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:43.145981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.24474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4362f0868a08058c4c0e212e3e430b86935335976c1f919cd9c091a3bbe67a0a","sha256:e228ca0155c6f97f7b17b9f9361473776f068f8c3d45b01b8438f43f9d358697"],"state_sha256":"b1aa29afee904ac4cc3df3c92af900082574b964ffed2038f38d21bfc58ee49f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wI4/HWMzNblqbvhsPKwXtVIJ+lF/6zTxE4CNPfK4dVOvzvUWjTJ+gsiHPPaReJLN2q9ezsPze6I7MC8HQ/uHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T00:56:57.099617Z","bundle_sha256":"499e152781d31e4ae1ae2294691d536b9940a8e7273fc0d7e8a7d67b1896f7c6"}}