{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N3MXYRJHSKGVFP7E7C3MQAHRL4","short_pith_number":"pith:N3MXYRJH","schema_version":"1.0","canonical_sha256":"6ed97c4527928d52bfe4f8b6c800f15f2b66e77de038c849cca6e31d66a3d0e6","source":{"kind":"arxiv","id":"2203.06125","version":5},"attestation_state":"computed","paper":{"title":"Protein Representation Learning by Geometric Structure Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arian Jamasb, Aurelie Lozano, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2022-03-11T17:52:13Z","abstract_excerpt":"Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein function or structure. Existing approaches usually pretrain protein language models on a large number of unlabeled amino acid sequences and then finetune the models with some labeled data in downstream tasks. Despite the effectiveness of sequence-based approaches, the power of pretraining on known protein structures, which are available in smaller numbers only, has not been explored for protein property prediction, though protein structures are known to be determinants of protein "},"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":"2203.06125","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-11T17:52:13Z","cross_cats_sorted":[],"title_canon_sha256":"8e1c5e04ff549d63eeafbb17575f77778ee4695a4d75e578d49bcd29d7c88fad","abstract_canon_sha256":"c466d62980bf5bb3e71293c47a9ce02491ce8de0765d506fab9926affcee6ff0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:29.898794Z","signature_b64":"ejg2+Qn9FtuZS8F/u0jQ6hE/9s577QKDLb1mcOWgua/3hnkJgNEuhiQ3NSLsDyEkWUPd/9EHGtDFbWTN4yCnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ed97c4527928d52bfe4f8b6c800f15f2b66e77de038c849cca6e31d66a3d0e6","last_reissued_at":"2026-07-05T05:36:29.898320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:29.898320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protein Representation Learning by Geometric Structure Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arian Jamasb, Aurelie Lozano, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2022-03-11T17:52:13Z","abstract_excerpt":"Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein function or structure. Existing approaches usually pretrain protein language models on a large number of unlabeled amino acid sequences and then finetune the models with some labeled data in downstream tasks. Despite the effectiveness of sequence-based approaches, the power of pretraining on known protein structures, which are available in smaller numbers only, has not been explored for protein property prediction, though protein structures are known to be determinants of protein "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06125","kind":"arxiv","version":5},"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/2203.06125/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":"2203.06125","created_at":"2026-07-05T05:36:29.898386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06125v5","created_at":"2026-07-05T05:36:29.898386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06125","created_at":"2026-07-05T05:36:29.898386+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3MXYRJHSKGV","created_at":"2026-07-05T05:36:29.898386+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3MXYRJHSKGVFP7E","created_at":"2026-07-05T05:36:29.898386+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3MXYRJH","created_at":"2026-07-05T05:36:29.898386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23830","citing_title":"Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04154","citing_title":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07567","citing_title":"SurfDesign: Effective Protein Design on Molecular Surfaces","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00955","citing_title":"CryoProt: A Protein Pretraining Framework with Cross-Box Interactions on Cryo-EM Density Maps","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01632","citing_title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21485","citing_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03800","citing_title":"STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01632","citing_title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10985","citing_title":"Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09964","citing_title":"Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09981","citing_title":"Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09964","citing_title":"Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01625","citing_title":"PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4","json":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4.json","graph_json":"https://pith.science/api/pith-number/N3MXYRJHSKGVFP7E7C3MQAHRL4/graph.json","events_json":"https://pith.science/api/pith-number/N3MXYRJHSKGVFP7E7C3MQAHRL4/events.json","paper":"https://pith.science/paper/N3MXYRJH"},"agent_actions":{"view_html":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4","download_json":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4.json","view_paper":"https://pith.science/paper/N3MXYRJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06125&json=true","fetch_graph":"https://pith.science/api/pith-number/N3MXYRJHSKGVFP7E7C3MQAHRL4/graph.json","fetch_events":"https://pith.science/api/pith-number/N3MXYRJHSKGVFP7E7C3MQAHRL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4/action/storage_attestation","attest_author":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4/action/author_attestation","sign_citation":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4/action/citation_signature","submit_replication":"https://pith.science/pith/N3MXYRJHSKGVFP7E7C3MQAHRL4/action/replication_record"}},"created_at":"2026-07-05T05:36:29.898386+00:00","updated_at":"2026-07-05T05:36:29.898386+00:00"}