{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K4SL2I2M7ZFYB7S66N74JUPA2F","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":"6a51767b4427b17a365b198033b8eec88c79b336aa9ce9844f49865df64e286d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-08-12T08:17:27Z","title_canon_sha256":"5a0161566be043ab7736411feb4a9a9782351f696d44c48b9b06db5f8ddf0033"},"schema_version":"1.0","source":{"id":"2408.06396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06396","created_at":"2026-07-05T08:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06396v1","created_at":"2026-07-05T08:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06396","created_at":"2026-07-05T08:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"K4SL2I2M7ZFY","created_at":"2026-07-05T08:54:56Z"},{"alias_kind":"pith_short_16","alias_value":"K4SL2I2M7ZFYB7S6","created_at":"2026-07-05T08:54:56Z"},{"alias_kind":"pith_short_8","alias_value":"K4SL2I2M","created_at":"2026-07-05T08:54:56Z"}],"graph_snapshots":[{"event_id":"sha256:f86a44496282c826d9619b20b1edbea8095620135c5d16de39d8a911fb133e20","target":"graph","created_at":"2026-07-05T08:54:56Z","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/2408.06396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained LLMs have demonstrated substantial capabilities across a range of conventional natural language processing (NLP) tasks, such as summarization and entity recognition. In this paper, we explore the application of LLMs in the generation of high-quality protein sequences. Specifically, we adopt a suite of pre-trained LLMs, including Mistral-7B1, Llama-2-7B2, Llama-3-8B3, and gemma-7B4, to produce valid protein sequences. All of these models are publicly available.5 Unlike previous work in this field, our approach utilizes a relatively small dataset comprising 42,000 distinct human prot","authors_text":"Kamyar Zeinalipour, Marco Gori, Marco Maggini, Monica Bianchini, Neda Jamshidi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-08-12T08:17:27Z","title":"Design Proteins Using Large Language Models: Enhancements and Comparative Analyses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06396","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":"sha256:07d96d0b4cb8065ecaaa096aa8b6a36838d55af8c4252b1e680937a8447eae78","target":"record","created_at":"2026-07-05T08:54:56Z","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":"6a51767b4427b17a365b198033b8eec88c79b336aa9ce9844f49865df64e286d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-08-12T08:17:27Z","title_canon_sha256":"5a0161566be043ab7736411feb4a9a9782351f696d44c48b9b06db5f8ddf0033"},"schema_version":"1.0","source":{"id":"2408.06396","kind":"arxiv","version":1}},"canonical_sha256":"5724bd234cfe4b80fe5ef37fc4d1e0d15a16b7106928eb5a438114a863c57a9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5724bd234cfe4b80fe5ef37fc4d1e0d15a16b7106928eb5a438114a863c57a9d","first_computed_at":"2026-07-05T08:54:56.424111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:56.424111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z0OmkSRXzMztzHVGYlr06TlSxqapQt/UJkAoSPp3uKPdS/T/KRu++gHkc1G911fbp+bGmlM72eQ088KwayHeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:56.424535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07d96d0b4cb8065ecaaa096aa8b6a36838d55af8c4252b1e680937a8447eae78","sha256:f86a44496282c826d9619b20b1edbea8095620135c5d16de39d8a911fb133e20"],"state_sha256":"95a6e2c7a0776d2ad6eea22966caef9220cd9151a689d650433099b7f7c70b07"}