{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7TNLI6TYEAKTM3ARTYAXU6V4UH","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":"b4b1b429a71a08d1f54cb887c0176daea99477635c27a3250030a226f5c3dae6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T04:01:32Z","title_canon_sha256":"7a250b24bc8311b134d05efdef0249a9f40ab1e0979129b278132f904d99ba23"},"schema_version":"1.0","source":{"id":"2110.15527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15527","created_at":"2026-07-05T03:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15527v1","created_at":"2026-07-05T03:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15527","created_at":"2026-07-05T03:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"7TNLI6TYEAKT","created_at":"2026-07-05T03:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"7TNLI6TYEAKTM3AR","created_at":"2026-07-05T03:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"7TNLI6TY","created_at":"2026-07-05T03:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:a20c8f5c117dfda793af1b567638938ffaf42f177ec5a176b0738185b3faa906","target":"graph","created_at":"2026-07-05T03:27:10Z","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/2110.15527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding protein sequences is vital and urgent for biology, healthcare, and medicine. Labeling approaches are expensive yet time-consuming, while the amount of unlabeled data is increasing quite faster than that of the labeled data due to low-cost, high-throughput sequencing methods. In order to extract knowledge from these unlabeled data, representation learning is of significant value for protein-related tasks and has great potential for helping us learn more about protein functions and structures. The key problem in the protein sequence representation learning is to capture the co-evol","authors_text":"Bin Shao, Fusong Ju, He Zhang, Huanhuan Xia, Jianwei Zhu, Liang He, Lijun Wu, Pan Deng, Shizhuo Zhang, Siyuan Liu, Tao Qin, Tie-Yan Liu, Yingce Xia","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T04:01:32Z","title":"Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15527","kind":"arxiv","version":1},"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":"sha256:465f9779fba1a55060ce0222fae500485fd55773bb6b8451e21f238c61300613","target":"record","created_at":"2026-07-05T03:27:10Z","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":"b4b1b429a71a08d1f54cb887c0176daea99477635c27a3250030a226f5c3dae6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T04:01:32Z","title_canon_sha256":"7a250b24bc8311b134d05efdef0249a9f40ab1e0979129b278132f904d99ba23"},"schema_version":"1.0","source":{"id":"2110.15527","kind":"arxiv","version":1}},"canonical_sha256":"fcdab47a782015366c119e017a7abca1d742daeba754b4022fbda9a4692e6c39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcdab47a782015366c119e017a7abca1d742daeba754b4022fbda9a4692e6c39","first_computed_at":"2026-07-05T03:27:10.852089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:10.852089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SnVahYfZzHyZs6xGh7muTlSwSUoCxiNU8OOe3BsP9IP+Dxx72xW4RpzhQeqA+8Z/QryjSwr4SWIRnxnfcD3vDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:10.852514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:465f9779fba1a55060ce0222fae500485fd55773bb6b8451e21f238c61300613","sha256:a20c8f5c117dfda793af1b567638938ffaf42f177ec5a176b0738185b3faa906"],"state_sha256":"a3afe9c2af32a31f82f0f23782003c3811204d152e13f2a8a97e47193fb5affe"}