{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K4SL2I2M7ZFYB7S66N74JUPA2F","short_pith_number":"pith:K4SL2I2M","schema_version":"1.0","canonical_sha256":"5724bd234cfe4b80fe5ef37fc4d1e0d15a16b7106928eb5a438114a863c57a9d","source":{"kind":"arxiv","id":"2408.06396","version":1},"attestation_state":"computed","paper":{"title":"Design Proteins Using Large Language Models: Enhancements and Comparative Analyses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Kamyar Zeinalipour, Marco Gori, Marco Maggini, Monica Bianchini, Neda Jamshidi","submitted_at":"2024-08-12T08:17:27Z","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"},"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":"2408.06396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-08-12T08:17:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5a0161566be043ab7736411feb4a9a9782351f696d44c48b9b06db5f8ddf0033","abstract_canon_sha256":"6a51767b4427b17a365b198033b8eec88c79b336aa9ce9844f49865df64e286d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:56.424535Z","signature_b64":"z0OmkSRXzMztzHVGYlr06TlSxqapQt/UJkAoSPp3uKPdS/T/KRu++gHkc1G911fbp+bGmlM72eQ088KwayHeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5724bd234cfe4b80fe5ef37fc4d1e0d15a16b7106928eb5a438114a863c57a9d","last_reissued_at":"2026-07-05T08:54:56.424111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:56.424111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design Proteins Using Large Language Models: Enhancements and Comparative Analyses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Kamyar Zeinalipour, Marco Gori, Marco Maggini, Monica Bianchini, Neda Jamshidi","submitted_at":"2024-08-12T08:17:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06396","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/2408.06396/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":"2408.06396","created_at":"2026-07-05T08:54:56.424169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06396v1","created_at":"2026-07-05T08:54:56.424169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06396","created_at":"2026-07-05T08:54:56.424169+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4SL2I2M7ZFY","created_at":"2026-07-05T08:54:56.424169+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4SL2I2M7ZFYB7S6","created_at":"2026-07-05T08:54:56.424169+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4SL2I2M","created_at":"2026-07-05T08:54:56.424169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F","json":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F.json","graph_json":"https://pith.science/api/pith-number/K4SL2I2M7ZFYB7S66N74JUPA2F/graph.json","events_json":"https://pith.science/api/pith-number/K4SL2I2M7ZFYB7S66N74JUPA2F/events.json","paper":"https://pith.science/paper/K4SL2I2M"},"agent_actions":{"view_html":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F","download_json":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F.json","view_paper":"https://pith.science/paper/K4SL2I2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06396&json=true","fetch_graph":"https://pith.science/api/pith-number/K4SL2I2M7ZFYB7S66N74JUPA2F/graph.json","fetch_events":"https://pith.science/api/pith-number/K4SL2I2M7ZFYB7S66N74JUPA2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F/action/storage_attestation","attest_author":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F/action/author_attestation","sign_citation":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F/action/citation_signature","submit_replication":"https://pith.science/pith/K4SL2I2M7ZFYB7S66N74JUPA2F/action/replication_record"}},"created_at":"2026-07-05T08:54:56.424169+00:00","updated_at":"2026-07-05T08:54:56.424169+00:00"}