{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:53DITCADZ53HPSQVAHQJY2RNK7","short_pith_number":"pith:53DITCAD","schema_version":"1.0","canonical_sha256":"eec6898803cf7677ca1501e09c6a2d57e1cdc7cd5bceee0b1c71f9a45f0d9450","source":{"kind":"arxiv","id":"2405.17066","version":1},"attestation_state":"computed","paper":{"title":"Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jeff Guo, Philippe Schwaller","submitted_at":"2024-05-27T11:37:36Z","abstract_excerpt":"Generative molecular design for drug discovery has very recently achieved a wave of experimental validation, with language-based backbones being the most common architectures employed. The most important factor for downstream success is whether an in silico oracle is well correlated with the desired end-point. To this end, current methods use cheaper proxy oracles with higher throughput before evaluating the most promising subset with high-fidelity oracles. The ability to directly optimize high-fidelity oracles would greatly enhance generative design and be expected to improve hit rates. Howev"},"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":"2405.17066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-05-27T11:37:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdcc0555a01472db11c21ee673dac19d01e09a5c9c3a31120bdf00b95e40efae","abstract_canon_sha256":"15c438c3f1206f287404d6ec1413f0e9da0ddabf72c7d33345a195807031202d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:39.447508Z","signature_b64":"V5Nfze8ivaZXwmFph84G+87gdeglJVhGDhX4Y01KwoaJwTDIb/CFcN9VPgiDOYhB/ULWe9jVA8GQRTmeLOD0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eec6898803cf7677ca1501e09c6a2d57e1cdc7cd5bceee0b1c71f9a45f0d9450","last_reissued_at":"2026-07-05T08:23:39.447042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:39.447042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jeff Guo, Philippe Schwaller","submitted_at":"2024-05-27T11:37:36Z","abstract_excerpt":"Generative molecular design for drug discovery has very recently achieved a wave of experimental validation, with language-based backbones being the most common architectures employed. The most important factor for downstream success is whether an in silico oracle is well correlated with the desired end-point. To this end, current methods use cheaper proxy oracles with higher throughput before evaluating the most promising subset with high-fidelity oracles. The ability to directly optimize high-fidelity oracles would greatly enhance generative design and be expected to improve hit rates. Howev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17066","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/2405.17066/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":"2405.17066","created_at":"2026-07-05T08:23:39.447100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17066v1","created_at":"2026-07-05T08:23:39.447100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17066","created_at":"2026-07-05T08:23:39.447100+00:00"},{"alias_kind":"pith_short_12","alias_value":"53DITCADZ53H","created_at":"2026-07-05T08:23:39.447100+00:00"},{"alias_kind":"pith_short_16","alias_value":"53DITCADZ53HPSQV","created_at":"2026-07-05T08:23:39.447100+00:00"},{"alias_kind":"pith_short_8","alias_value":"53DITCAD","created_at":"2026-07-05T08:23:39.447100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27467","citing_title":"Multi-Objective Molecular Generation with Frequency-Controlled Evolutionary Dynamics","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7","json":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7.json","graph_json":"https://pith.science/api/pith-number/53DITCADZ53HPSQVAHQJY2RNK7/graph.json","events_json":"https://pith.science/api/pith-number/53DITCADZ53HPSQVAHQJY2RNK7/events.json","paper":"https://pith.science/paper/53DITCAD"},"agent_actions":{"view_html":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7","download_json":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7.json","view_paper":"https://pith.science/paper/53DITCAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17066&json=true","fetch_graph":"https://pith.science/api/pith-number/53DITCADZ53HPSQVAHQJY2RNK7/graph.json","fetch_events":"https://pith.science/api/pith-number/53DITCADZ53HPSQVAHQJY2RNK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7/action/storage_attestation","attest_author":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7/action/author_attestation","sign_citation":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7/action/citation_signature","submit_replication":"https://pith.science/pith/53DITCADZ53HPSQVAHQJY2RNK7/action/replication_record"}},"created_at":"2026-07-05T08:23:39.447100+00:00","updated_at":"2026-07-05T08:23:39.447100+00:00"}