{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUIBOKG7NOZWPUGPBJLGARS7WS","short_pith_number":"pith:YUIBOKG7","schema_version":"1.0","canonical_sha256":"c5101728df6bb367d0cf0a5660465fb4a8143042d3b5a8055b3eb8431ea5f13e","source":{"kind":"arxiv","id":"2409.09828","version":2},"attestation_state":"computed","paper":{"title":"Latent Diffusion Models for Controllable RNA Sequence Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Kaidi Fu, Kaixuan Huang, Le Cong, Mengdi Wang, Yanyi Chu, Yukang Yang","submitted_at":"2024-09-15T19:04:50Z","abstract_excerpt":"This work presents RNAdiffusion, a latent diffusion model for generating and optimizing discrete RNA sequences of variable lengths. RNA is a key intermediary between DNA and protein, exhibiting high sequence diversity and complex three-dimensional structures to support a wide range of functions. We utilize pretrained BERT-type models to encode raw RNA sequences into token-level, biologically meaningful representations. A Query Transformer is employed to compress such representations into a set of fixed-length latent vectors, with an autoregressive decoder trained to reconstruct RNA sequences f"},"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":"2409.09828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-15T19:04:50Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"812a71e288d6bbf9b1890ff9a6c6ff89e01c9655495613718269f85b82a9cedd","abstract_canon_sha256":"5af53eac128b194f90e1733724bdbeda12abca9ba464959a06cbd8df240c10bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:38.380408Z","signature_b64":"iz+o69gAmioHBuVn4bpiLYZZcxRyvqY0A/GOq4vecLTihCyi1+8dzX0vtcIV6+qmyuu4hINVm3gqs8PCl0BdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5101728df6bb367d0cf0a5660465fb4a8143042d3b5a8055b3eb8431ea5f13e","last_reissued_at":"2026-07-05T09:14:38.379961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:38.379961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Diffusion Models for Controllable RNA Sequence Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Kaidi Fu, Kaixuan Huang, Le Cong, Mengdi Wang, Yanyi Chu, Yukang Yang","submitted_at":"2024-09-15T19:04:50Z","abstract_excerpt":"This work presents RNAdiffusion, a latent diffusion model for generating and optimizing discrete RNA sequences of variable lengths. RNA is a key intermediary between DNA and protein, exhibiting high sequence diversity and complex three-dimensional structures to support a wide range of functions. We utilize pretrained BERT-type models to encode raw RNA sequences into token-level, biologically meaningful representations. A Query Transformer is employed to compress such representations into a set of fixed-length latent vectors, with an autoregressive decoder trained to reconstruct RNA sequences f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09828","kind":"arxiv","version":2},"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/2409.09828/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":"2409.09828","created_at":"2026-07-05T09:14:38.380027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09828v2","created_at":"2026-07-05T09:14:38.380027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09828","created_at":"2026-07-05T09:14:38.380027+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUIBOKG7NOZW","created_at":"2026-07-05T09:14:38.380027+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUIBOKG7NOZWPUGP","created_at":"2026-07-05T09:14:38.380027+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUIBOKG7","created_at":"2026-07-05T09:14:38.380027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06805","citing_title":"Efficient Diffusion Models: A Survey","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS","json":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS.json","graph_json":"https://pith.science/api/pith-number/YUIBOKG7NOZWPUGPBJLGARS7WS/graph.json","events_json":"https://pith.science/api/pith-number/YUIBOKG7NOZWPUGPBJLGARS7WS/events.json","paper":"https://pith.science/paper/YUIBOKG7"},"agent_actions":{"view_html":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS","download_json":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS.json","view_paper":"https://pith.science/paper/YUIBOKG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09828&json=true","fetch_graph":"https://pith.science/api/pith-number/YUIBOKG7NOZWPUGPBJLGARS7WS/graph.json","fetch_events":"https://pith.science/api/pith-number/YUIBOKG7NOZWPUGPBJLGARS7WS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS/action/storage_attestation","attest_author":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS/action/author_attestation","sign_citation":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS/action/citation_signature","submit_replication":"https://pith.science/pith/YUIBOKG7NOZWPUGPBJLGARS7WS/action/replication_record"}},"created_at":"2026-07-05T09:14:38.380027+00:00","updated_at":"2026-07-05T09:14:38.380027+00:00"}