{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OYBHDKCAYD7SP3RGTIRUXUGIEE","short_pith_number":"pith:OYBHDKCA","schema_version":"1.0","canonical_sha256":"760271a840c0ff27ee269a234bd0c82127a8625140c4db4439dd0f007ef357b6","source":{"kind":"arxiv","id":"2302.04611","version":4},"attestation_state":"computed","paper":{"title":"A Text-guided Protein Design Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Anthony Gitter, Arvind Ramanathan, Chaowei Xiao, Hongyu Guo, Jian Tang, Jiarui Lu, Shengchao Liu, Weili Nie, Yanjing Li, Yutao Zhu, Zhao Xu, Zhuoxinran Li","submitted_at":"2023-02-09T12:59:16Z","abstract_excerpt":"Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level functionalities. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP which aligns the representation of two modalities, a facilitator that generates the prote"},"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":"2302.04611","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T12:59:16Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"cb625f5f7b7a48d9f36525cdd9153b1386db8027bc35770a8ebdc588c33f4dbb","abstract_canon_sha256":"f317242088ac218949411a09eb1b0e89da81e1587c189123a3f040bd82356781"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:42.042233Z","signature_b64":"V2KIlDkr//Kr/61hhWY8L3Z4OuM5ihPVnwMwwDFTvvSGwrnou6vr2qVCa6WShthXkrxHIUqnM+aIoc9dI5//BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760271a840c0ff27ee269a234bd0c82127a8625140c4db4439dd0f007ef357b6","last_reissued_at":"2026-07-05T11:20:42.041836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:42.041836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Text-guided Protein Design Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Anthony Gitter, Arvind Ramanathan, Chaowei Xiao, Hongyu Guo, Jian Tang, Jiarui Lu, Shengchao Liu, Weili Nie, Yanjing Li, Yutao Zhu, Zhao Xu, Zhuoxinran Li","submitted_at":"2023-02-09T12:59:16Z","abstract_excerpt":"Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level functionalities. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP which aligns the representation of two modalities, a facilitator that generates the prote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04611","kind":"arxiv","version":4},"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/2302.04611/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":"2302.04611","created_at":"2026-07-05T11:20:42.041899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04611v4","created_at":"2026-07-05T11:20:42.041899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04611","created_at":"2026-07-05T11:20:42.041899+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYBHDKCAYD7S","created_at":"2026-07-05T11:20:42.041899+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYBHDKCAYD7SP3RG","created_at":"2026-07-05T11:20:42.041899+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYBHDKCA","created_at":"2026-07-05T11:20:42.041899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22138","citing_title":"BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03800","citing_title":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE","json":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE.json","graph_json":"https://pith.science/api/pith-number/OYBHDKCAYD7SP3RGTIRUXUGIEE/graph.json","events_json":"https://pith.science/api/pith-number/OYBHDKCAYD7SP3RGTIRUXUGIEE/events.json","paper":"https://pith.science/paper/OYBHDKCA"},"agent_actions":{"view_html":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE","download_json":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE.json","view_paper":"https://pith.science/paper/OYBHDKCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04611&json=true","fetch_graph":"https://pith.science/api/pith-number/OYBHDKCAYD7SP3RGTIRUXUGIEE/graph.json","fetch_events":"https://pith.science/api/pith-number/OYBHDKCAYD7SP3RGTIRUXUGIEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE/action/storage_attestation","attest_author":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE/action/author_attestation","sign_citation":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE/action/citation_signature","submit_replication":"https://pith.science/pith/OYBHDKCAYD7SP3RGTIRUXUGIEE/action/replication_record"}},"created_at":"2026-07-05T11:20:42.041899+00:00","updated_at":"2026-07-05T11:20:42.041899+00:00"}