{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHJLBDYRIRNTFKQYKC4IR5XN6N","short_pith_number":"pith:NHJLBDYR","schema_version":"1.0","canonical_sha256":"69d2b08f11445b32aa1850b888f6edf36ac509d6e3b2943889122737a99ace27","source":{"kind":"arxiv","id":"2501.06158","version":3},"attestation_state":"computed","paper":{"title":"GenMol: A Drug Discovery Generalist with Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Danny Reidenbach, Karsten Kreis, Meng Liu, Saee Paliwal, Seul Lee, Srimukh Prasad Veccham, Weili Nie, Yuxing Peng","submitted_at":"2025-01-10T18:30:05Z","abstract_excerpt":"Drug discovery is a complex process that involves multiple stages and tasks. However, existing molecular generative models can only tackle some of these tasks. We present Generalist Molecular generative model (GenMol), a versatile framework that uses only a single discrete diffusion model to handle diverse drug discovery scenarios. GenMol generates Sequential Attachment-based Fragment Embedding (SAFE) sequences through non-autoregressive bidirectional parallel decoding, thereby allowing the utilization of a molecular context that does not rely on the specific token ordering while having better"},"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":"2501.06158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-10T18:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"1fdfb923395c9cbe6c86dfc0429601c1fe86e6d047fa1e38c891b16babe47f8e","abstract_canon_sha256":"08612ec753ae7b712aa1cc8c0084c755470daa343ba2f7ca8258a71f42f6a265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:38.098575Z","signature_b64":"ST0uBYrVS/0+VY+wLl0HlO6jiF47b9Wqvz1CMBDUranjU4kJ9GG/7Ujr+SIWMHAfABFxHeTuMs+Rm/CLQxeMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d2b08f11445b32aa1850b888f6edf36ac509d6e3b2943889122737a99ace27","last_reissued_at":"2026-07-05T11:41:38.097961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:38.097961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenMol: A Drug Discovery Generalist with Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arash Vahdat, Danny Reidenbach, Karsten Kreis, Meng Liu, Saee Paliwal, Seul Lee, Srimukh Prasad Veccham, Weili Nie, Yuxing Peng","submitted_at":"2025-01-10T18:30:05Z","abstract_excerpt":"Drug discovery is a complex process that involves multiple stages and tasks. However, existing molecular generative models can only tackle some of these tasks. We present Generalist Molecular generative model (GenMol), a versatile framework that uses only a single discrete diffusion model to handle diverse drug discovery scenarios. GenMol generates Sequential Attachment-based Fragment Embedding (SAFE) sequences through non-autoregressive bidirectional parallel decoding, thereby allowing the utilization of a molecular context that does not rely on the specific token ordering while having better"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06158","kind":"arxiv","version":3},"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/2501.06158/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":"2501.06158","created_at":"2026-07-05T11:41:38.098033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06158v3","created_at":"2026-07-05T11:41:38.098033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06158","created_at":"2026-07-05T11:41:38.098033+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHJLBDYRIRNT","created_at":"2026-07-05T11:41:38.098033+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHJLBDYRIRNTFKQY","created_at":"2026-07-05T11:41:38.098033+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHJLBDYR","created_at":"2026-07-05T11:41:38.098033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02133","citing_title":"Variational Learning for Insertion-based Generation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02241","citing_title":"BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28226","citing_title":"PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08659","citing_title":"Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03304","citing_title":"Generative Chemical Language Models for Energetic Materials Discovery","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08659","citing_title":"Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10230","citing_title":"FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26985","citing_title":"Simple Self-Conditioning Adaptation for Masked Diffusion Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16648","citing_title":"FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N","json":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N.json","graph_json":"https://pith.science/api/pith-number/NHJLBDYRIRNTFKQYKC4IR5XN6N/graph.json","events_json":"https://pith.science/api/pith-number/NHJLBDYRIRNTFKQYKC4IR5XN6N/events.json","paper":"https://pith.science/paper/NHJLBDYR"},"agent_actions":{"view_html":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N","download_json":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N.json","view_paper":"https://pith.science/paper/NHJLBDYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06158&json=true","fetch_graph":"https://pith.science/api/pith-number/NHJLBDYRIRNTFKQYKC4IR5XN6N/graph.json","fetch_events":"https://pith.science/api/pith-number/NHJLBDYRIRNTFKQYKC4IR5XN6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N/action/storage_attestation","attest_author":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N/action/author_attestation","sign_citation":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N/action/citation_signature","submit_replication":"https://pith.science/pith/NHJLBDYRIRNTFKQYKC4IR5XN6N/action/replication_record"}},"created_at":"2026-07-05T11:41:38.098033+00:00","updated_at":"2026-07-05T11:41:38.098033+00:00"}