{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B6PWGOOENLQQSTXAC7OFHLKYMF","short_pith_number":"pith:B6PWGOOE","schema_version":"1.0","canonical_sha256":"0f9f6339c46ae1094ee017dc53ad58617204041eb317cc08942cc70b3ad4581a","source":{"kind":"arxiv","id":"2406.14142","version":3},"attestation_state":"computed","paper":{"title":"Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"George Dasoulas, Michail Chatzianastasis, Michalis Vazirgiannis, Yang Zhang","submitted_at":"2024-06-20T09:34:31Z","abstract_excerpt":"Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction. Although sequence-based transformer models have shown promising results by leveraging the vast amount of protein sequence data in a self-supervised way, there is still a gap in exploiting the available 3D protein structures. In this work, we propose a pre-training scheme going beyond trivial masking methods leveraging 3D and hierarchical structures of proteins. We propose a novel self-supervised method to pretrain 3D graph neural "},"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":"2406.14142","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-06-20T09:34:31Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"c6d9fcc28e89df7f94ac06952c08a74e1c76a87624403acc559882afd164ff3d","abstract_canon_sha256":"c597f774dd455f424402a87911478e54a60734f0ea8d75c6dd52c522fa9091e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:40.748808Z","signature_b64":"MS49BZe0eO+dgEUGNYW0H4kOBDcWqO4gC+s4ObzxDvP6457cuaLWe5E98k4iUvk8Hf4kcSe13YkA4Xh1t5+/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f9f6339c46ae1094ee017dc53ad58617204041eb317cc08942cc70b3ad4581a","last_reissued_at":"2026-07-05T09:22:40.748155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:40.748155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"George Dasoulas, Michail Chatzianastasis, Michalis Vazirgiannis, Yang Zhang","submitted_at":"2024-06-20T09:34:31Z","abstract_excerpt":"Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction. Although sequence-based transformer models have shown promising results by leveraging the vast amount of protein sequence data in a self-supervised way, there is still a gap in exploiting the available 3D protein structures. In this work, we propose a pre-training scheme going beyond trivial masking methods leveraging 3D and hierarchical structures of proteins. We propose a novel self-supervised method to pretrain 3D graph neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14142","kind":"arxiv","version":3},"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/2406.14142/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":"2406.14142","created_at":"2026-07-05T09:22:40.748211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14142v3","created_at":"2026-07-05T09:22:40.748211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14142","created_at":"2026-07-05T09:22:40.748211+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6PWGOOENLQQ","created_at":"2026-07-05T09:22:40.748211+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6PWGOOENLQQSTXA","created_at":"2026-07-05T09:22:40.748211+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6PWGOOE","created_at":"2026-07-05T09:22:40.748211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04154","citing_title":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":208,"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":208,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF","json":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF.json","graph_json":"https://pith.science/api/pith-number/B6PWGOOENLQQSTXAC7OFHLKYMF/graph.json","events_json":"https://pith.science/api/pith-number/B6PWGOOENLQQSTXAC7OFHLKYMF/events.json","paper":"https://pith.science/paper/B6PWGOOE"},"agent_actions":{"view_html":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF","download_json":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF.json","view_paper":"https://pith.science/paper/B6PWGOOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14142&json=true","fetch_graph":"https://pith.science/api/pith-number/B6PWGOOENLQQSTXAC7OFHLKYMF/graph.json","fetch_events":"https://pith.science/api/pith-number/B6PWGOOENLQQSTXAC7OFHLKYMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF/action/storage_attestation","attest_author":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF/action/author_attestation","sign_citation":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF/action/citation_signature","submit_replication":"https://pith.science/pith/B6PWGOOENLQQSTXAC7OFHLKYMF/action/replication_record"}},"created_at":"2026-07-05T09:22:40.748211+00:00","updated_at":"2026-07-05T09:22:40.748211+00:00"}