{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BC4C3EHE3MFUJBGME7FIVRQTZP","short_pith_number":"pith:BC4C3EHE","schema_version":"1.0","canonical_sha256":"08b82d90e4db0b4484cc27ca8ac613cbd5f6f30cbf0dd949956a07265de9e801","source":{"kind":"arxiv","id":"2605.23960","version":1},"attestation_state":"computed","paper":{"title":"Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Athanasios V. Vasilakos, Mingqing Wang, Yonghong He, Zhiwei Nie, Zhixiang Ren","submitted_at":"2026-05-12T07:12:12Z","abstract_excerpt":"Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, an"},"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":"2605.23960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-12T07:12:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e1ea3a3f985072df1d91e13d5ed0a380c3631f748a94e932118e0d2101357f20","abstract_canon_sha256":"27942f5a9642f46f558b8724a83eec7057379e2d3e0f58f77d74eba887036458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T00:02:24.056599Z","signature_b64":"yC8jsmoGrUSRetLMt9bWd/p7FOrEGSqWH+7iSzVGt8xaeSl8Qid/z7RCB878Em5ER1qQz068kbVd5wRqsqV3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b82d90e4db0b4484cc27ca8ac613cbd5f6f30cbf0dd949956a07265de9e801","last_reissued_at":"2026-05-26T00:02:24.055847Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T00:02:24.055847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Athanasios V. Vasilakos, Mingqing Wang, Yonghong He, Zhiwei Nie, Zhixiang Ren","submitted_at":"2026-05-12T07:12:12Z","abstract_excerpt":"Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23960","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/2605.23960/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":"2605.23960","created_at":"2026-05-26T00:02:24.055964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23960v1","created_at":"2026-05-26T00:02:24.055964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23960","created_at":"2026-05-26T00:02:24.055964+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC4C3EHE3MFU","created_at":"2026-05-26T00:02:24.055964+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC4C3EHE3MFUJBGM","created_at":"2026-05-26T00:02:24.055964+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC4C3EHE","created_at":"2026-05-26T00:02:24.055964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP","json":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP.json","graph_json":"https://pith.science/api/pith-number/BC4C3EHE3MFUJBGME7FIVRQTZP/graph.json","events_json":"https://pith.science/api/pith-number/BC4C3EHE3MFUJBGME7FIVRQTZP/events.json","paper":"https://pith.science/paper/BC4C3EHE"},"agent_actions":{"view_html":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP","download_json":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP.json","view_paper":"https://pith.science/paper/BC4C3EHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23960&json=true","fetch_graph":"https://pith.science/api/pith-number/BC4C3EHE3MFUJBGME7FIVRQTZP/graph.json","fetch_events":"https://pith.science/api/pith-number/BC4C3EHE3MFUJBGME7FIVRQTZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP/action/storage_attestation","attest_author":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP/action/author_attestation","sign_citation":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP/action/citation_signature","submit_replication":"https://pith.science/pith/BC4C3EHE3MFUJBGME7FIVRQTZP/action/replication_record"}},"created_at":"2026-05-26T00:02:24.055964+00:00","updated_at":"2026-05-26T00:02:24.055964+00:00"}