{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ALZDSFBP4MYGKZVDM646F47U25","short_pith_number":"pith:ALZDSFBP","schema_version":"1.0","canonical_sha256":"02f239142fe3306566a367b9e2f3f4d7545fdada9b1254260b61214141c2e3db","source":{"kind":"arxiv","id":"2408.11363","version":2},"attestation_state":"computed","paper":{"title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.LG","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Edward Sun, Qifan Wang, Wei Wang, Yijia Xiao, Yiqiao Jin","submitted_at":"2024-08-21T06:16:22Z","abstract_excerpt":"Understanding biological processes, drug development, and biotechnological advancements requires a detailed analysis of protein structures and functions, a task that is inherently complex and time-consuming in traditional protein research. To streamline this process, we introduce ProteinGPT, a state-of-the-art multimodal large language model for proteins that enables users to upload protein sequences and/or structures for comprehensive analysis and responsive inquiries. ProteinGPT integrates protein sequence and structure encoders with linear projection layers to ensure precise representation "},"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":"2408.11363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:16:22Z","cross_cats_sorted":["cs.CE","cs.LG","q-bio.BM"],"title_canon_sha256":"705b3b114b311b28d65af26b9edc21de68ba6c37b44fc2220e90f728868a59a2","abstract_canon_sha256":"988efc587882627e6ead1b841f3073cfb15d51a62e5706696f73f389ac3c4725"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:43.532146Z","signature_b64":"WfLC+E8PiwCaEz25Ub0BceXtnA6sQf4kR8qPbahSj+R0FJh7uyIEAiXq8W6WNZLOWN+v8ECrflF+hTcV2vOkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f239142fe3306566a367b9e2f3f4d7545fdada9b1254260b61214141c2e3db","last_reissued_at":"2026-07-05T10:50:43.531638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:43.531638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.LG","q-bio.BM"],"primary_cat":"cs.AI","authors_text":"Edward Sun, Qifan Wang, Wei Wang, Yijia Xiao, Yiqiao Jin","submitted_at":"2024-08-21T06:16:22Z","abstract_excerpt":"Understanding biological processes, drug development, and biotechnological advancements requires a detailed analysis of protein structures and functions, a task that is inherently complex and time-consuming in traditional protein research. To streamline this process, we introduce ProteinGPT, a state-of-the-art multimodal large language model for proteins that enables users to upload protein sequences and/or structures for comprehensive analysis and responsive inquiries. ProteinGPT integrates protein sequence and structure encoders with linear projection layers to ensure precise representation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11363","kind":"arxiv","version":2},"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/2408.11363/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":"2408.11363","created_at":"2026-07-05T10:50:43.531697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11363v2","created_at":"2026-07-05T10:50:43.531697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11363","created_at":"2026-07-05T10:50:43.531697+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALZDSFBP4MYG","created_at":"2026-07-05T10:50:43.531697+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALZDSFBP4MYGKZVD","created_at":"2026-07-05T10:50:43.531697+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALZDSFBP","created_at":"2026-07-05T10:50:43.531697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00451","citing_title":"ProtStructQA: A Denotation Threshold in Protein Structural Reasoning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08723","citing_title":"From Text to Discovery: How Large Language Models Are Reshaping Research Across Scientific and Humanistic Disciplines","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17261","citing_title":"Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03800","citing_title":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10978","citing_title":"VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10978","citing_title":"VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25","json":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25.json","graph_json":"https://pith.science/api/pith-number/ALZDSFBP4MYGKZVDM646F47U25/graph.json","events_json":"https://pith.science/api/pith-number/ALZDSFBP4MYGKZVDM646F47U25/events.json","paper":"https://pith.science/paper/ALZDSFBP"},"agent_actions":{"view_html":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25","download_json":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25.json","view_paper":"https://pith.science/paper/ALZDSFBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11363&json=true","fetch_graph":"https://pith.science/api/pith-number/ALZDSFBP4MYGKZVDM646F47U25/graph.json","fetch_events":"https://pith.science/api/pith-number/ALZDSFBP4MYGKZVDM646F47U25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25/action/storage_attestation","attest_author":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25/action/author_attestation","sign_citation":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25/action/citation_signature","submit_replication":"https://pith.science/pith/ALZDSFBP4MYGKZVDM646F47U25/action/replication_record"}},"created_at":"2026-07-05T10:50:43.531697+00:00","updated_at":"2026-07-05T10:50:43.531697+00:00"}