{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EKJNR26E4MHVTV76SYP4UPEOAC","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":"b1a41be18df24b1822081e5e505de6211da560af35a76c6af54980acaed9c8dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T11:05:46Z","title_canon_sha256":"1c7107218072bc6d6f7ae1aca03b8721ae82b4cc1bdbcb5563af30fe23e454e8"},"schema_version":"1.0","source":{"id":"2412.04069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04069","created_at":"2026-07-05T09:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04069v1","created_at":"2026-07-05T09:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04069","created_at":"2026-07-05T09:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"EKJNR26E4MHV","created_at":"2026-07-05T09:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"EKJNR26E4MHVTV76","created_at":"2026-07-05T09:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"EKJNR26E","created_at":"2026-07-05T09:44:58Z"}],"graph_snapshots":[{"event_id":"sha256:78be8faefe4b189080692cbf25e8002ee216011721b619e5450148edf2e1356d","target":"graph","created_at":"2026-07-05T09:44:58Z","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/2412.04069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering. However, protein design methods utilizing large language models with solely pretraining and fine-tuning struggle to capture relationships in multi-modal protein data. To address this, we propose ProtDAT, a de novo fine-grained framework capable of designing proteins from any descriptive protein text input. ProtDAT builds upon the inherent characteristics of protein data to unify sequences and text as a cohesive whole rather than separate entit","authors_text":"Hong-Bin Shen, Xiaoyong Pan, Xiao-Yu Guo, Yi-Fan Li, Yuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T11:05:46Z","title":"ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04069","kind":"arxiv","version":1},"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":"sha256:3b8b37094d5c1f449716aa2c1a3552bb8e9c5f77a4e48d6900dd7c609af6e274","target":"record","created_at":"2026-07-05T09:44:58Z","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":"b1a41be18df24b1822081e5e505de6211da560af35a76c6af54980acaed9c8dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T11:05:46Z","title_canon_sha256":"1c7107218072bc6d6f7ae1aca03b8721ae82b4cc1bdbcb5563af30fe23e454e8"},"schema_version":"1.0","source":{"id":"2412.04069","kind":"arxiv","version":1}},"canonical_sha256":"2292d8ebc4e30f59d7fe961fca3c8e009296979f8163eaa9480e1f158bbe9d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2292d8ebc4e30f59d7fe961fca3c8e009296979f8163eaa9480e1f158bbe9d5c","first_computed_at":"2026-07-05T09:44:58.680716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:58.680716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t94sDnwmFp9KrncScwdDe/kf/z4PqvDC7RMO+CNKDgs8jJdux/G4DpTcAUUjCZxUl7kZQHNfwJWKCF61kx98DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:58.681199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b8b37094d5c1f449716aa2c1a3552bb8e9c5f77a4e48d6900dd7c609af6e274","sha256:78be8faefe4b189080692cbf25e8002ee216011721b619e5450148edf2e1356d"],"state_sha256":"d3340f7821ce219e90852c9a0a26d36b930672642e06c86b9ddf251aaddd1a5b"}