{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QVX3LYADHBN3VY3VN5HNXOCIXV","short_pith_number":"pith:QVX3LYAD","schema_version":"1.0","canonical_sha256":"856fb5e003385bbae3756f4edbb848bd67f377f037c138520e9c02a57aeebac5","source":{"kind":"arxiv","id":"2211.09086","version":1},"attestation_state":"computed","paper":{"title":"Molecular Fingerprints for Robust and Efficient ML-Driven Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jacob Oppenheim, Joshua Schiller, Max Winston, Ruslan N. Tazhigulov","submitted_at":"2022-11-16T18:07:43Z","abstract_excerpt":"We propose a novel molecular fingerprint-based variational autoencoder applied for molecular generation on real-world drug molecules. We define more suitable and pharma-relevant baseline metrics and tests, focusing on the generation of diverse, drug-like, novel small molecules and scaffolds. When we apply these molecular generation metrics to our novel model, we observe a substantial improvement in chemical synthetic accessibility ($\\Delta\\bar{{SAS}}$ = -0.83) and in computational efficiency up to 5.9x in comparison to an existing state-of-the-art SMILES-based architecture."},"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":"2211.09086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-16T18:07:43Z","cross_cats_sorted":[],"title_canon_sha256":"33c630b3f52d459bc76d8f0085f354041815320506f7074a2890cc744d67dec7","abstract_canon_sha256":"444c09623483ac61d546206dd6aa6d817a0b3757cd845cdafd821c754d8bfe78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:47.562704Z","signature_b64":"AGo+FATdccWiuNUYprWvORhCb86i5bMMxoxBmTgkp0ofPVccFdW0F/DdkyKRWczIeY+jB1orcj+M4g6V21OQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"856fb5e003385bbae3756f4edbb848bd67f377f037c138520e9c02a57aeebac5","last_reissued_at":"2026-07-05T05:16:47.562216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:47.562216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Molecular Fingerprints for Robust and Efficient ML-Driven Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jacob Oppenheim, Joshua Schiller, Max Winston, Ruslan N. Tazhigulov","submitted_at":"2022-11-16T18:07:43Z","abstract_excerpt":"We propose a novel molecular fingerprint-based variational autoencoder applied for molecular generation on real-world drug molecules. We define more suitable and pharma-relevant baseline metrics and tests, focusing on the generation of diverse, drug-like, novel small molecules and scaffolds. When we apply these molecular generation metrics to our novel model, we observe a substantial improvement in chemical synthetic accessibility ($\\Delta\\bar{{SAS}}$ = -0.83) and in computational efficiency up to 5.9x in comparison to an existing state-of-the-art SMILES-based architecture."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09086","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/2211.09086/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":"2211.09086","created_at":"2026-07-05T05:16:47.562270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09086v1","created_at":"2026-07-05T05:16:47.562270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09086","created_at":"2026-07-05T05:16:47.562270+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVX3LYADHBN3","created_at":"2026-07-05T05:16:47.562270+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVX3LYADHBN3VY3V","created_at":"2026-07-05T05:16:47.562270+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVX3LYAD","created_at":"2026-07-05T05:16:47.562270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.13408","citing_title":"NovoMolGen: Rethinking Molecular Language Model Pretraining","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV","json":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV.json","graph_json":"https://pith.science/api/pith-number/QVX3LYADHBN3VY3VN5HNXOCIXV/graph.json","events_json":"https://pith.science/api/pith-number/QVX3LYADHBN3VY3VN5HNXOCIXV/events.json","paper":"https://pith.science/paper/QVX3LYAD"},"agent_actions":{"view_html":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV","download_json":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV.json","view_paper":"https://pith.science/paper/QVX3LYAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09086&json=true","fetch_graph":"https://pith.science/api/pith-number/QVX3LYADHBN3VY3VN5HNXOCIXV/graph.json","fetch_events":"https://pith.science/api/pith-number/QVX3LYADHBN3VY3VN5HNXOCIXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV/action/storage_attestation","attest_author":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV/action/author_attestation","sign_citation":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV/action/citation_signature","submit_replication":"https://pith.science/pith/QVX3LYADHBN3VY3VN5HNXOCIXV/action/replication_record"}},"created_at":"2026-07-05T05:16:47.562270+00:00","updated_at":"2026-07-05T05:16:47.562270+00:00"}