{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EKJNR26E4MHVTV76SYP4UPEOAC","short_pith_number":"pith:EKJNR26E","canonical_record":{"source":{"id":"2412.04069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T11:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"1c7107218072bc6d6f7ae1aca03b8721ae82b4cc1bdbcb5563af30fe23e454e8","abstract_canon_sha256":"b1a41be18df24b1822081e5e505de6211da560af35a76c6af54980acaed9c8dc"},"schema_version":"1.0"},"canonical_sha256":"2292d8ebc4e30f59d7fe961fca3c8e009296979f8163eaa9480e1f158bbe9d5c","source":{"kind":"arxiv","id":"2412.04069","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EKJNR26E4MHVTV76SYP4UPEOAC","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-05T11:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"1c7107218072bc6d6f7ae1aca03b8721ae82b4cc1bdbcb5563af30fe23e454e8","abstract_canon_sha256":"b1a41be18df24b1822081e5e505de6211da560af35a76c6af54980acaed9c8dc"},"schema_version":"1.0"},"canonical_sha256":"2292d8ebc4e30f59d7fe961fca3c8e009296979f8163eaa9480e1f158bbe9d5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:58.681199Z","signature_b64":"t94sDnwmFp9KrncScwdDe/kf/z4PqvDC7RMO+CNKDgs8jJdux/G4DpTcAUUjCZxUl7kZQHNfwJWKCF61kx98DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2292d8ebc4e30f59d7fe961fca3c8e009296979f8163eaa9480e1f158bbe9d5c","last_reissued_at":"2026-07-05T09:44:58.680716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:58.680716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04069","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmpBjKx5mWFx8JVQIBKubAH1yDxG9sGnDN4Cakybg/N0gBPyPJTBKIyP0fNF9cMcrykdsqVVDEBA9owUI3t3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:08:38.361453Z"},"content_sha256":"3b8b37094d5c1f449716aa2c1a3552bb8e9c5f77a4e48d6900dd7c609af6e274","schema_version":"1.0","event_id":"sha256:3b8b37094d5c1f449716aa2c1a3552bb8e9c5f77a4e48d6900dd7c609af6e274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EKJNR26E4MHVTV76SYP4UPEOAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hong-Bin Shen, Xiaoyong Pan, Xiao-Yu Guo, Yi-Fan Li, Yuan Liu","submitted_at":"2024-12-05T11:05:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04069","kind":"arxiv","version":1},"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/2412.04069/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OC+krkh83+Le2Ao1gujscnbbBH1cqNvEAtCH/otiFhTg3PV99T5e0GKKrKRF6n9SMVUO+PLgQcGsazz0j560Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:08:38.361994Z"},"content_sha256":"78be8faefe4b189080692cbf25e8002ee216011721b619e5450148edf2e1356d","schema_version":"1.0","event_id":"sha256:78be8faefe4b189080692cbf25e8002ee216011721b619e5450148edf2e1356d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKJNR26E4MHVTV76SYP4UPEOAC/bundle.json","state_url":"https://pith.science/pith/EKJNR26E4MHVTV76SYP4UPEOAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKJNR26E4MHVTV76SYP4UPEOAC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:08:38Z","links":{"resolver":"https://pith.science/pith/EKJNR26E4MHVTV76SYP4UPEOAC","bundle":"https://pith.science/pith/EKJNR26E4MHVTV76SYP4UPEOAC/bundle.json","state":"https://pith.science/pith/EKJNR26E4MHVTV76SYP4UPEOAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKJNR26E4MHVTV76SYP4UPEOAC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYTr89ZBHATojAEnXxgk14JbYK9d/GMliiYr71BIddRyeA2ZLjrIYI1izCy/6C/kz7G+r4H8Cv8b0MKqC0sFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:08:38.366368Z","bundle_sha256":"171405a67a6d1a93f89b5fb2fd384c18bd45d040bc566a969cd871591e3d1b5e"}}