{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PQAZI4QGSCSZKCDUYDC36DWKJX","short_pith_number":"pith:PQAZI4QG","schema_version":"1.0","canonical_sha256":"7c0194720690a5950874c0c5bf0eca4de2dddd90b5b5aef538062cd879e35b04","source":{"kind":"arxiv","id":"2205.15675","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Representation Learning for 3D Protein Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Pedro Hermosilla, Timo Ropinski","submitted_at":"2022-05-31T10:33:06Z","abstract_excerpt":"Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics. Unfortunately, the number of available structures is orders of magnitude lower than the training data sizes commonly used in computer vision and machine learning. Moreover, this number is reduced even further, when only annotated protein structures can be considered, making the training of existing models difficult and prone to over-fitting. To address this challenge, we introduce a new representation learning framework for 3D protein structures. Our framework uses unsupervised contr"},"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":"2205.15675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-05-31T10:33:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"74d7cb3a12f4dae4863c10f610369431e3cb213a2c8db57029e193bbd092eeb9","abstract_canon_sha256":"04492bf66f961f7ac54cac0b1d7585c23e12cc701b98c14acb43b7ad7db3e4da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:01.353103Z","signature_b64":"dNlDjU/9F1uGey2YiR/nLz6yItId5+aF57e60YhTcN2f0IpjZrIfi1K705alrwNeUVfg+4jFTRJ0EtrK3P8cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c0194720690a5950874c0c5bf0eca4de2dddd90b5b5aef538062cd879e35b04","last_reissued_at":"2026-07-05T04:28:01.352483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:01.352483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Representation Learning for 3D Protein Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Pedro Hermosilla, Timo Ropinski","submitted_at":"2022-05-31T10:33:06Z","abstract_excerpt":"Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics. Unfortunately, the number of available structures is orders of magnitude lower than the training data sizes commonly used in computer vision and machine learning. Moreover, this number is reduced even further, when only annotated protein structures can be considered, making the training of existing models difficult and prone to over-fitting. To address this challenge, we introduce a new representation learning framework for 3D protein structures. Our framework uses unsupervised contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15675","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/2205.15675/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":"2205.15675","created_at":"2026-07-05T04:28:01.352571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15675v1","created_at":"2026-07-05T04:28:01.352571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15675","created_at":"2026-07-05T04:28:01.352571+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQAZI4QGSCSZ","created_at":"2026-07-05T04:28:01.352571+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQAZI4QGSCSZKCDU","created_at":"2026-07-05T04:28:01.352571+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQAZI4QG","created_at":"2026-07-05T04:28:01.352571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22307","citing_title":"Enhancing Protein Representation Learning via Manifold Restore Mixing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19374","citing_title":"Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs","ref_index":22,"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":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX","json":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX.json","graph_json":"https://pith.science/api/pith-number/PQAZI4QGSCSZKCDUYDC36DWKJX/graph.json","events_json":"https://pith.science/api/pith-number/PQAZI4QGSCSZKCDUYDC36DWKJX/events.json","paper":"https://pith.science/paper/PQAZI4QG"},"agent_actions":{"view_html":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX","download_json":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX.json","view_paper":"https://pith.science/paper/PQAZI4QG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15675&json=true","fetch_graph":"https://pith.science/api/pith-number/PQAZI4QGSCSZKCDUYDC36DWKJX/graph.json","fetch_events":"https://pith.science/api/pith-number/PQAZI4QGSCSZKCDUYDC36DWKJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX/action/storage_attestation","attest_author":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX/action/author_attestation","sign_citation":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX/action/citation_signature","submit_replication":"https://pith.science/pith/PQAZI4QGSCSZKCDUYDC36DWKJX/action/replication_record"}},"created_at":"2026-07-05T04:28:01.352571+00:00","updated_at":"2026-07-05T04:28:01.352571+00:00"}