{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7TNLI6TYEAKTM3ARTYAXU6V4UH","short_pith_number":"pith:7TNLI6TY","schema_version":"1.0","canonical_sha256":"fcdab47a782015366c119e017a7abca1d742daeba754b4022fbda9a4692e6c39","source":{"kind":"arxiv","id":"2110.15527","version":1},"attestation_state":"computed","paper":{"title":"Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","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","submitted_at":"2021-10-29T04:01:32Z","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"},"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":"2110.15527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T04:01:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a250b24bc8311b134d05efdef0249a9f40ab1e0979129b278132f904d99ba23","abstract_canon_sha256":"b4b1b429a71a08d1f54cb887c0176daea99477635c27a3250030a226f5c3dae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:10.852514Z","signature_b64":"SnVahYfZzHyZs6xGh7muTlSwSUoCxiNU8OOe3BsP9IP+Dxx72xW4RpzhQeqA+8Z/QryjSwr4SWIRnxnfcD3vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcdab47a782015366c119e017a7abca1d742daeba754b4022fbda9a4692e6c39","last_reissued_at":"2026-07-05T03:27:10.852089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:10.852089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","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","submitted_at":"2021-10-29T04:01:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15527","kind":"arxiv","version":1},"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/2110.15527/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":"2110.15527","created_at":"2026-07-05T03:27:10.852157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15527v1","created_at":"2026-07-05T03:27:10.852157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15527","created_at":"2026-07-05T03:27:10.852157+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TNLI6TYEAKT","created_at":"2026-07-05T03:27:10.852157+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TNLI6TYEAKTM3AR","created_at":"2026-07-05T03:27:10.852157+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TNLI6TY","created_at":"2026-07-05T03:27:10.852157+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/7TNLI6TYEAKTM3ARTYAXU6V4UH","json":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH.json","graph_json":"https://pith.science/api/pith-number/7TNLI6TYEAKTM3ARTYAXU6V4UH/graph.json","events_json":"https://pith.science/api/pith-number/7TNLI6TYEAKTM3ARTYAXU6V4UH/events.json","paper":"https://pith.science/paper/7TNLI6TY"},"agent_actions":{"view_html":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH","download_json":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH.json","view_paper":"https://pith.science/paper/7TNLI6TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15527&json=true","fetch_graph":"https://pith.science/api/pith-number/7TNLI6TYEAKTM3ARTYAXU6V4UH/graph.json","fetch_events":"https://pith.science/api/pith-number/7TNLI6TYEAKTM3ARTYAXU6V4UH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH/action/storage_attestation","attest_author":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH/action/author_attestation","sign_citation":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH/action/citation_signature","submit_replication":"https://pith.science/pith/7TNLI6TYEAKTM3ARTYAXU6V4UH/action/replication_record"}},"created_at":"2026-07-05T03:27:10.852157+00:00","updated_at":"2026-07-05T03:27:10.852157+00:00"}