{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PEWSSTG7KWFEU2OKVBUROVBJJA","short_pith_number":"pith:PEWSSTG7","schema_version":"1.0","canonical_sha256":"792d294cdf558a4a69caa8691754294814f41eeac1bc6b9c0720b2741ba03144","source":{"kind":"arxiv","id":"2502.06846","version":2},"attestation_state":"computed","paper":{"title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Changlong Zhou, Jun Zhang, Yiqin Gao, Zhicong Wang, Zicheng Ma, Ziqiang Cao","submitted_at":"2025-02-07T05:23:16Z","abstract_excerpt":"Motivation: Proteins are of great significance in living organisms. However, understanding their functions encounters numerous challenges, such as insufficient integration of multimodal information, a large number of training parameters, limited flexibility of classification-based methods, and the lack of systematic evaluation metrics for protein Q&A systems. To tackle these issues, we propose the Prot2Chat framework. Results: We modified ProteinMPNN to encode protein sequence and structural information in a unified way. We used a large language model (LLM) to encode questions into vectors and"},"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":"2502.06846","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T05:23:16Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"eb673db1b707a1ad8a4b4c3057677174830052e96aa6a4570d9eeffe5e0f7405","abstract_canon_sha256":"ab0500633c0715f0180e8c942fc3770ce0a38fc4502868ac10ccd2477f51b17a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:20.286002Z","signature_b64":"Z0CEOPCboZ6R7iUZjtKpvYer4+ZuYjITpz0tnS8b5NKJKBMX3M5rBoXB30Nwt7FKYHRme2twrQbb0rXdXb+/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792d294cdf558a4a69caa8691754294814f41eeac1bc6b9c0720b2741ba03144","last_reissued_at":"2026-07-05T11:07:20.285542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:20.285542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Changlong Zhou, Jun Zhang, Yiqin Gao, Zhicong Wang, Zicheng Ma, Ziqiang Cao","submitted_at":"2025-02-07T05:23:16Z","abstract_excerpt":"Motivation: Proteins are of great significance in living organisms. However, understanding their functions encounters numerous challenges, such as insufficient integration of multimodal information, a large number of training parameters, limited flexibility of classification-based methods, and the lack of systematic evaluation metrics for protein Q&A systems. To tackle these issues, we propose the Prot2Chat framework. Results: We modified ProteinMPNN to encode protein sequence and structural information in a unified way. We used a large language model (LLM) to encode questions into vectors and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06846","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/2502.06846/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":"2502.06846","created_at":"2026-07-05T11:07:20.285597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06846v2","created_at":"2026-07-05T11:07:20.285597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06846","created_at":"2026-07-05T11:07:20.285597+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEWSSTG7KWFE","created_at":"2026-07-05T11:07:20.285597+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEWSSTG7KWFEU2OK","created_at":"2026-07-05T11:07:20.285597+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEWSSTG7","created_at":"2026-07-05T11:07:20.285597+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/PEWSSTG7KWFEU2OKVBUROVBJJA","json":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA.json","graph_json":"https://pith.science/api/pith-number/PEWSSTG7KWFEU2OKVBUROVBJJA/graph.json","events_json":"https://pith.science/api/pith-number/PEWSSTG7KWFEU2OKVBUROVBJJA/events.json","paper":"https://pith.science/paper/PEWSSTG7"},"agent_actions":{"view_html":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA","download_json":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA.json","view_paper":"https://pith.science/paper/PEWSSTG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06846&json=true","fetch_graph":"https://pith.science/api/pith-number/PEWSSTG7KWFEU2OKVBUROVBJJA/graph.json","fetch_events":"https://pith.science/api/pith-number/PEWSSTG7KWFEU2OKVBUROVBJJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA/action/storage_attestation","attest_author":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA/action/author_attestation","sign_citation":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA/action/citation_signature","submit_replication":"https://pith.science/pith/PEWSSTG7KWFEU2OKVBUROVBJJA/action/replication_record"}},"created_at":"2026-07-05T11:07:20.285597+00:00","updated_at":"2026-07-05T11:07:20.285597+00:00"}