{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y5USYC2S4M4UPI2NY4YDDLQE74","short_pith_number":"pith:Y5USYC2S","schema_version":"1.0","canonical_sha256":"c7692c0b52e33947a34dc73031ae04ff33fc670044b2b4935ea1b809de80647c","source":{"kind":"arxiv","id":"2211.16742","version":1},"attestation_state":"computed","paper":{"title":"Protein Language Models and Structure Prediction: Connection and Progression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bozhen Hu, Cheng Tan, Jiangbin Zheng, Jun Xia, Stan Z. Li, Yongjie Xu, Yufei Huang","submitted_at":"2022-11-30T04:58:54Z","abstract_excerpt":"The prediction of protein structures from sequences is an important task for function prediction, drug design, and related biological processes understanding. Recent advances have proved the power of language models (LMs) in processing the protein sequence databases, which inherit the advantages of attention networks and capture useful information in learning representations for proteins. The past two years have witnessed remarkable success in tertiary protein structure prediction (PSP), including evolution-based and single-sequence-based PSP. It seems that instead of using energy-based models"},"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":"2211.16742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-11-30T04:58:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"821f82d2c8b4ac572edf4b72fddebfbaa2981a3ea2964738654beeb744651317","abstract_canon_sha256":"a40dfe0635db2b314eb5ee592f63276b5b45512da5198111ee265bd36cc572be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:10.454852Z","signature_b64":"P44qZ830dtDS4To+sUqrTWey1fLhCsNrQvBunYU/hQ2TrELdE+yMI1Kph9Mwg1xOpxDQYwyeF/5JWGyHjVbLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7692c0b52e33947a34dc73031ae04ff33fc670044b2b4935ea1b809de80647c","last_reissued_at":"2026-07-05T05:21:10.454468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:10.454468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protein Language Models and Structure Prediction: Connection and Progression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bozhen Hu, Cheng Tan, Jiangbin Zheng, Jun Xia, Stan Z. Li, Yongjie Xu, Yufei Huang","submitted_at":"2022-11-30T04:58:54Z","abstract_excerpt":"The prediction of protein structures from sequences is an important task for function prediction, drug design, and related biological processes understanding. Recent advances have proved the power of language models (LMs) in processing the protein sequence databases, which inherit the advantages of attention networks and capture useful information in learning representations for proteins. The past two years have witnessed remarkable success in tertiary protein structure prediction (PSP), including evolution-based and single-sequence-based PSP. It seems that instead of using energy-based models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16742","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/2211.16742/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":"2211.16742","created_at":"2026-07-05T05:21:10.454519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16742v1","created_at":"2026-07-05T05:21:10.454519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16742","created_at":"2026-07-05T05:21:10.454519+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5USYC2S4M4U","created_at":"2026-07-05T05:21:10.454519+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5USYC2S4M4UPI2N","created_at":"2026-07-05T05:21:10.454519+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5USYC2S","created_at":"2026-07-05T05:21:10.454519+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/Y5USYC2S4M4UPI2NY4YDDLQE74","json":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74.json","graph_json":"https://pith.science/api/pith-number/Y5USYC2S4M4UPI2NY4YDDLQE74/graph.json","events_json":"https://pith.science/api/pith-number/Y5USYC2S4M4UPI2NY4YDDLQE74/events.json","paper":"https://pith.science/paper/Y5USYC2S"},"agent_actions":{"view_html":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74","download_json":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74.json","view_paper":"https://pith.science/paper/Y5USYC2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16742&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5USYC2S4M4UPI2NY4YDDLQE74/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5USYC2S4M4UPI2NY4YDDLQE74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74/action/storage_attestation","attest_author":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74/action/author_attestation","sign_citation":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74/action/citation_signature","submit_replication":"https://pith.science/pith/Y5USYC2S4M4UPI2NY4YDDLQE74/action/replication_record"}},"created_at":"2026-07-05T05:21:10.454519+00:00","updated_at":"2026-07-05T05:21:10.454519+00:00"}