{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OYBHDKCAYD7SP3RGTIRUXUGIEE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f317242088ac218949411a09eb1b0e89da81e1587c189123a3f040bd82356781","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T12:59:16Z","title_canon_sha256":"cb625f5f7b7a48d9f36525cdd9153b1386db8027bc35770a8ebdc588c33f4dbb"},"schema_version":"1.0","source":{"id":"2302.04611","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04611","created_at":"2026-07-05T11:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04611v4","created_at":"2026-07-05T11:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04611","created_at":"2026-07-05T11:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"OYBHDKCAYD7S","created_at":"2026-07-05T11:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"OYBHDKCAYD7SP3RG","created_at":"2026-07-05T11:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"OYBHDKCA","created_at":"2026-07-05T11:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:d85f0b3739f83873565e66a0f1237b7b1726d7b208993891170ea53c902291b5","target":"graph","created_at":"2026-07-05T11:20:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.04611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T12:59:16Z","title":"A Text-guided Protein Design Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04611","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d24d98eb4ff49de8f05adfcfa69eb9440ef83a9b050ce2c65887c96d12709629","target":"record","created_at":"2026-07-05T11:20:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f317242088ac218949411a09eb1b0e89da81e1587c189123a3f040bd82356781","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T12:59:16Z","title_canon_sha256":"cb625f5f7b7a48d9f36525cdd9153b1386db8027bc35770a8ebdc588c33f4dbb"},"schema_version":"1.0","source":{"id":"2302.04611","kind":"arxiv","version":4}},"canonical_sha256":"760271a840c0ff27ee269a234bd0c82127a8625140c4db4439dd0f007ef357b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"760271a840c0ff27ee269a234bd0c82127a8625140c4db4439dd0f007ef357b6","first_computed_at":"2026-07-05T11:20:42.041836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:42.041836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V2KIlDkr//Kr/61hhWY8L3Z4OuM5ihPVnwMwwDFTvvSGwrnou6vr2qVCa6WShthXkrxHIUqnM+aIoc9dI5//BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:42.042233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04611","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d24d98eb4ff49de8f05adfcfa69eb9440ef83a9b050ce2c65887c96d12709629","sha256:d85f0b3739f83873565e66a0f1237b7b1726d7b208993891170ea53c902291b5"],"state_sha256":"17dc642a532a25ad705c2008a82f006b829a8f0324c406e5943e61d89d46d449"}