{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J4O5OA6WBQGTRJO5ABOLKSAI4K","short_pith_number":"pith:J4O5OA6W","schema_version":"1.0","canonical_sha256":"4f1dd703d60c0d38a5dd005cb54808e2bcd2c8421098409b9a152ca37e316f9d","source":{"kind":"arxiv","id":"2509.03885","version":1},"attestation_state":"computed","paper":{"title":"Topotein: Topological Deep Learning for Protein Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Morehead, Arian Jamasb, Luke Braithwaite, Mustafa Hajij, Pietro Li\\`o, Zhiyu Wang","submitted_at":"2025-09-04T04:58:20Z","abstract_excerpt":"Protein representation learning (PRL) is crucial for understanding structure-function relationships, yet current sequence- and graph-based methods fail to capture the hierarchical organization inherent in protein structures. We introduce Topotein, a comprehensive framework that applies topological deep learning to PRL through the novel Protein Combinatorial Complex (PCC) and Topology-Complete Perceptron Network (TCPNet). Our PCC represents proteins at multiple hierarchical levels -- from residues to secondary structures to complete proteins -- while preserving geometric information at each lev"},"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":"2509.03885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T04:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"8f1e9cfaf2be3a568b54feee60f47e2bf99e5b55147df9c67aa9bc977feb1eb6","abstract_canon_sha256":"4108187bcc23540f9556922a494ad67aa4be4724faf1b4463752868380f30ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:49.004481Z","signature_b64":"gyVS6XIGpGxptiOJzMzOxepATvU6D6g/kNVvkznSWoXYtxZsZGiJ4sNXiGMDIj4cK5kmFjBiv27flSLFAjfNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f1dd703d60c0d38a5dd005cb54808e2bcd2c8421098409b9a152ca37e316f9d","last_reissued_at":"2026-07-05T12:04:49.003974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:49.003974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topotein: Topological Deep Learning for Protein Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Morehead, Arian Jamasb, Luke Braithwaite, Mustafa Hajij, Pietro Li\\`o, Zhiyu Wang","submitted_at":"2025-09-04T04:58:20Z","abstract_excerpt":"Protein representation learning (PRL) is crucial for understanding structure-function relationships, yet current sequence- and graph-based methods fail to capture the hierarchical organization inherent in protein structures. We introduce Topotein, a comprehensive framework that applies topological deep learning to PRL through the novel Protein Combinatorial Complex (PCC) and Topology-Complete Perceptron Network (TCPNet). Our PCC represents proteins at multiple hierarchical levels -- from residues to secondary structures to complete proteins -- while preserving geometric information at each lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03885","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/2509.03885/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":"2509.03885","created_at":"2026-07-05T12:04:49.004032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03885v1","created_at":"2026-07-05T12:04:49.004032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03885","created_at":"2026-07-05T12:04:49.004032+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4O5OA6WBQGT","created_at":"2026-07-05T12:04:49.004032+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4O5OA6WBQGTRJO5","created_at":"2026-07-05T12:04:49.004032+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4O5OA6W","created_at":"2026-07-05T12:04:49.004032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23517","citing_title":"Collapsed Effective Operators for Higher-order Structures","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11911","citing_title":"From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01632","citing_title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01632","citing_title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K","json":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K.json","graph_json":"https://pith.science/api/pith-number/J4O5OA6WBQGTRJO5ABOLKSAI4K/graph.json","events_json":"https://pith.science/api/pith-number/J4O5OA6WBQGTRJO5ABOLKSAI4K/events.json","paper":"https://pith.science/paper/J4O5OA6W"},"agent_actions":{"view_html":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K","download_json":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K.json","view_paper":"https://pith.science/paper/J4O5OA6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03885&json=true","fetch_graph":"https://pith.science/api/pith-number/J4O5OA6WBQGTRJO5ABOLKSAI4K/graph.json","fetch_events":"https://pith.science/api/pith-number/J4O5OA6WBQGTRJO5ABOLKSAI4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K/action/storage_attestation","attest_author":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K/action/author_attestation","sign_citation":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K/action/citation_signature","submit_replication":"https://pith.science/pith/J4O5OA6WBQGTRJO5ABOLKSAI4K/action/replication_record"}},"created_at":"2026-07-05T12:04:49.004032+00:00","updated_at":"2026-07-05T12:04:49.004032+00:00"}