{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6GWN3UDIA7J6BYNZ3F3BA6FTPH","short_pith_number":"pith:6GWN3UDI","schema_version":"1.0","canonical_sha256":"f1acddd06807d3e0e1b9d9761078b379d16d0c41535d2666ab18db7afab46adc","source":{"kind":"arxiv","id":"2401.06199","version":2},"attestation_state":"computed","paper":{"title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Aohan Zeng, Bo Chen, Boyan Wang, Chiming Liu, Jie Tang, Jing Gong, Le Song, Pan Li, Shen Li, Xingyi Cheng, Xin Zeng, Xu Tan, Yangli-ao Geng, Yuxiao Dong, Zhilei Bei","submitted_at":"2024-01-11T15:03:17Z","abstract_excerpt":"Protein language models have shown remarkable success in learning biological information from protein sequences. However, most existing models are limited by either autoencoding or autoregressive pre-training objectives, which makes them struggle to handle protein understanding and generation tasks concurrently. We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework. Our key technical contribution is an exploration of the compatibility and the potential for joint optimization of the two types of o"},"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":"2401.06199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-01-11T15:03:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ebafc72e828f44f05c195ee6eb24d7098ee8e8d154627ab929db45a39a9b6841","abstract_canon_sha256":"c3c2be914b356c92ffa3edbda1b8402d1cc0b6f31916fb570cbdb7594515722c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:43.128974Z","signature_b64":"LZCrqeTHIi1xAioPkDF6ufWfga0/bBRwXWRDUTxVT1NtaimHVCsYK0e6/plnSKL+CxWy9nUSQmilTK0dt+SAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1acddd06807d3e0e1b9d9761078b379d16d0c41535d2666ab18db7afab46adc","last_reissued_at":"2026-07-05T09:45:43.128310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:43.128310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Aohan Zeng, Bo Chen, Boyan Wang, Chiming Liu, Jie Tang, Jing Gong, Le Song, Pan Li, Shen Li, Xingyi Cheng, Xin Zeng, Xu Tan, Yangli-ao Geng, Yuxiao Dong, Zhilei Bei","submitted_at":"2024-01-11T15:03:17Z","abstract_excerpt":"Protein language models have shown remarkable success in learning biological information from protein sequences. However, most existing models are limited by either autoencoding or autoregressive pre-training objectives, which makes them struggle to handle protein understanding and generation tasks concurrently. We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework. Our key technical contribution is an exploration of the compatibility and the potential for joint optimization of the two types of o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06199","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/2401.06199/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":"2401.06199","created_at":"2026-07-05T09:45:43.128402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06199v2","created_at":"2026-07-05T09:45:43.128402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06199","created_at":"2026-07-05T09:45:43.128402+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GWN3UDIA7J6","created_at":"2026-07-05T09:45:43.128402+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GWN3UDIA7J6BYNZ","created_at":"2026-07-05T09:45:43.128402+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GWN3UDI","created_at":"2026-07-05T09:45:43.128402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.03800","citing_title":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17330","citing_title":"SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24506","citing_title":"MIMIC: A Generative Multimodal Foundation Model for Biomolecules","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH","json":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH.json","graph_json":"https://pith.science/api/pith-number/6GWN3UDIA7J6BYNZ3F3BA6FTPH/graph.json","events_json":"https://pith.science/api/pith-number/6GWN3UDIA7J6BYNZ3F3BA6FTPH/events.json","paper":"https://pith.science/paper/6GWN3UDI"},"agent_actions":{"view_html":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH","download_json":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH.json","view_paper":"https://pith.science/paper/6GWN3UDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06199&json=true","fetch_graph":"https://pith.science/api/pith-number/6GWN3UDIA7J6BYNZ3F3BA6FTPH/graph.json","fetch_events":"https://pith.science/api/pith-number/6GWN3UDIA7J6BYNZ3F3BA6FTPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH/action/storage_attestation","attest_author":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH/action/author_attestation","sign_citation":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH/action/citation_signature","submit_replication":"https://pith.science/pith/6GWN3UDIA7J6BYNZ3F3BA6FTPH/action/replication_record"}},"created_at":"2026-07-05T09:45:43.128402+00:00","updated_at":"2026-07-05T09:45:43.128402+00:00"}