{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6X5E25F22DWISO4PGM6RX7OHH","short_pith_number":"pith:H6X5E25F","schema_version":"1.0","canonical_sha256":"3fafd26ba5d6876449dc7999e8dfee39fb0ae311d4585c502c3a5f2e6c515138","source":{"kind":"arxiv","id":"2402.16445","version":3},"attestation_state":"computed","paper":{"title":"ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.CE","authors_text":"Calvin Yu-Chian Chen, Hao Li, Jiaxi Cui, Liuzhenghao Lv, Li Yuan, Yonghong Tian, Yuyang Liu, Zongying Lin","submitted_at":"2024-02-26T09:43:52Z","abstract_excerpt":"Recent advances in Protein Language Models (PLMs) have transformed protein engineering, yet unlike their counterparts in Natural Language Processing (NLP), current PLMs exhibit a fundamental limitation: they excel in either Protein Language Understanding (PLU) or Protein Language Generation (PLG), but rarely both. This fragmentation hinders progress in protein engineering. To bridge this gap, we introduce ProLLaMA, a multitask protein language model enhanced by the Evolutionary Protein Generation Framework (EPGF). We construct a comprehensive instruction dataset containing approximately 13 mil"},"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":"2402.16445","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2024-02-26T09:43:52Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"4d37f1a22297e668fd832d7e89fb032ccaf85e84d1ea1a2c5d9acbec5e4f471f","abstract_canon_sha256":"2f96b2bcf71ce9e8ab684f8954f423fa07737e2574b19db15709d78ec330149e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:12.508246Z","signature_b64":"0P7grZi9pnQYat9VUbw7pVF51+W3KM/OF++7ttRhSXML3s3vdZfsvBqZ47gwd65NP1gW9O3oFGfO9X7C38pRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fafd26ba5d6876449dc7999e8dfee39fb0ae311d4585c502c3a5f2e6c515138","last_reissued_at":"2026-07-05T12:11:12.507676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:12.507676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.CE","authors_text":"Calvin Yu-Chian Chen, Hao Li, Jiaxi Cui, Liuzhenghao Lv, Li Yuan, Yonghong Tian, Yuyang Liu, Zongying Lin","submitted_at":"2024-02-26T09:43:52Z","abstract_excerpt":"Recent advances in Protein Language Models (PLMs) have transformed protein engineering, yet unlike their counterparts in Natural Language Processing (NLP), current PLMs exhibit a fundamental limitation: they excel in either Protein Language Understanding (PLU) or Protein Language Generation (PLG), but rarely both. This fragmentation hinders progress in protein engineering. To bridge this gap, we introduce ProLLaMA, a multitask protein language model enhanced by the Evolutionary Protein Generation Framework (EPGF). We construct a comprehensive instruction dataset containing approximately 13 mil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16445","kind":"arxiv","version":3},"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/2402.16445/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":"2402.16445","created_at":"2026-07-05T12:11:12.507736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16445v3","created_at":"2026-07-05T12:11:12.507736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16445","created_at":"2026-07-05T12:11:12.507736+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6X5E25F22DW","created_at":"2026-07-05T12:11:12.507736+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6X5E25F22DWISO4","created_at":"2026-07-05T12:11:12.507736+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6X5E25F","created_at":"2026-07-05T12:11:12.507736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10075","citing_title":"Teaching LLMs to Speak Spectroscopy","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH","json":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH.json","graph_json":"https://pith.science/api/pith-number/H6X5E25F22DWISO4PGM6RX7OHH/graph.json","events_json":"https://pith.science/api/pith-number/H6X5E25F22DWISO4PGM6RX7OHH/events.json","paper":"https://pith.science/paper/H6X5E25F"},"agent_actions":{"view_html":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH","download_json":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH.json","view_paper":"https://pith.science/paper/H6X5E25F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16445&json=true","fetch_graph":"https://pith.science/api/pith-number/H6X5E25F22DWISO4PGM6RX7OHH/graph.json","fetch_events":"https://pith.science/api/pith-number/H6X5E25F22DWISO4PGM6RX7OHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH/action/storage_attestation","attest_author":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH/action/author_attestation","sign_citation":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH/action/citation_signature","submit_replication":"https://pith.science/pith/H6X5E25F22DWISO4PGM6RX7OHH/action/replication_record"}},"created_at":"2026-07-05T12:11:12.507736+00:00","updated_at":"2026-07-05T12:11:12.507736+00:00"}