{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6GWN3UDIA7J6BYNZ3F3BA6FTPH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c3c2be914b356c92ffa3edbda1b8402d1cc0b6f31916fb570cbdb7594515722c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-01-11T15:03:17Z","title_canon_sha256":"ebafc72e828f44f05c195ee6eb24d7098ee8e8d154627ab929db45a39a9b6841"},"schema_version":"1.0","source":{"id":"2401.06199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06199","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06199v2","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06199","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"6GWN3UDIA7J6","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"6GWN3UDIA7J6BYNZ","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"6GWN3UDI","created_at":"2026-07-05T09:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:47230e0c187893b1cfae2a41ddaff8776236a1ed92b07a9607e9cf49686ee034","target":"graph","created_at":"2026-07-05T09:45:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.06199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-01-11T15:03:17Z","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06199","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f6a63de06b70cef4294acb94f495150e3175983882969d9039e6c6a475b543ad","target":"record","created_at":"2026-07-05T09:45:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c3c2be914b356c92ffa3edbda1b8402d1cc0b6f31916fb570cbdb7594515722c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-01-11T15:03:17Z","title_canon_sha256":"ebafc72e828f44f05c195ee6eb24d7098ee8e8d154627ab929db45a39a9b6841"},"schema_version":"1.0","source":{"id":"2401.06199","kind":"arxiv","version":2}},"canonical_sha256":"f1acddd06807d3e0e1b9d9761078b379d16d0c41535d2666ab18db7afab46adc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1acddd06807d3e0e1b9d9761078b379d16d0c41535d2666ab18db7afab46adc","first_computed_at":"2026-07-05T09:45:43.128310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:43.128310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZCrqeTHIi1xAioPkDF6ufWfga0/bBRwXWRDUTxVT1NtaimHVCsYK0e6/plnSKL+CxWy9nUSQmilTK0dt+SAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:43.128974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6a63de06b70cef4294acb94f495150e3175983882969d9039e6c6a475b543ad","sha256:47230e0c187893b1cfae2a41ddaff8776236a1ed92b07a9607e9cf49686ee034"],"state_sha256":"93369c695a995fec29c1a76ae279791e3937c9f56d9095688f18cefef3a0d258"}