{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BHIPTV42GH4HW35UVIFGHGU6IJ","short_pith_number":"pith:BHIPTV42","schema_version":"1.0","canonical_sha256":"09d0f9d79a31f87b6fb4aa0a639a9e425f76da3498b37ec36801c7282be614c6","source":{"kind":"arxiv","id":"2302.10888","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Ge Wang, Haitao Lin, Jiangbin Zheng, Lirong Wu, Stan Z. Li, Yufei Huang","submitted_at":"2023-02-05T14:13:32Z","abstract_excerpt":"Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design. Having witnessed the success of protein sequence pretraining, pretraining for structural data which is more informative has become a promising research topic. However, there are three major challenges facing protein structure pretraining: insufficient sample diversity, physically unrealistic modeling, and the lack of protein-specific pretext tasks. To try to address these challenges, we present the 3D Geometric Pretraining. In this paper, we propose a unifie"},"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":"2302.10888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T14:13:32Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"87f2d70a0f4a22259bd37dca8dd08a58c6e27c965ee7526f6794ed7d2fb4fdc7","abstract_canon_sha256":"8d8fee7fed9762f3d012de04b90247b34aa3f6e1432760ea9c7dd29e510854bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:40.678956Z","signature_b64":"VMe8drpWo68JFpXlF2BNNyXpQR6YQRZjiL6lwwWAFvkNkSzz1OUwSQzi7pdVtpL6LfCm9HqBXgDU3LtIja7mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09d0f9d79a31f87b6fb4aa0a639a9e425f76da3498b37ec36801c7282be614c6","last_reissued_at":"2026-07-05T05:44:40.678517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:40.678517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Ge Wang, Haitao Lin, Jiangbin Zheng, Lirong Wu, Stan Z. Li, Yufei Huang","submitted_at":"2023-02-05T14:13:32Z","abstract_excerpt":"Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design. Having witnessed the success of protein sequence pretraining, pretraining for structural data which is more informative has become a promising research topic. However, there are three major challenges facing protein structure pretraining: insufficient sample diversity, physically unrealistic modeling, and the lack of protein-specific pretext tasks. To try to address these challenges, we present the 3D Geometric Pretraining. In this paper, we propose a unifie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10888","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/2302.10888/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":"2302.10888","created_at":"2026-07-05T05:44:40.678578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10888v1","created_at":"2026-07-05T05:44:40.678578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10888","created_at":"2026-07-05T05:44:40.678578+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHIPTV42GH4H","created_at":"2026-07-05T05:44:40.678578+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHIPTV42GH4HW35U","created_at":"2026-07-05T05:44:40.678578+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHIPTV42","created_at":"2026-07-05T05:44:40.678578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17798","citing_title":"DapPep: Domain Adaptive Peptide-agnostic Learning for Universal T-cell Receptor-antigen Binding Affinity Prediction","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ","json":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ.json","graph_json":"https://pith.science/api/pith-number/BHIPTV42GH4HW35UVIFGHGU6IJ/graph.json","events_json":"https://pith.science/api/pith-number/BHIPTV42GH4HW35UVIFGHGU6IJ/events.json","paper":"https://pith.science/paper/BHIPTV42"},"agent_actions":{"view_html":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ","download_json":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ.json","view_paper":"https://pith.science/paper/BHIPTV42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10888&json=true","fetch_graph":"https://pith.science/api/pith-number/BHIPTV42GH4HW35UVIFGHGU6IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BHIPTV42GH4HW35UVIFGHGU6IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ/action/storage_attestation","attest_author":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ/action/author_attestation","sign_citation":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ/action/citation_signature","submit_replication":"https://pith.science/pith/BHIPTV42GH4HW35UVIFGHGU6IJ/action/replication_record"}},"created_at":"2026-07-05T05:44:40.678578+00:00","updated_at":"2026-07-05T05:44:40.678578+00:00"}