{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RHXYNWLJFXKJWPHGBX3X6WRTZQ","short_pith_number":"pith:RHXYNWLJ","schema_version":"1.0","canonical_sha256":"89ef86d9692dd49b3ce60df77f5a33cc22abbe32a44dadef56b58042de5c7e6c","source":{"kind":"arxiv","id":"2303.06275","version":2},"attestation_state":"computed","paper":{"title":"A Systematic Study of Joint Representation Learning on Protein Sequences and Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Aur\\'elie Lozano, Chuanrui Wang, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2023-03-11T01:24:10Z","abstract_excerpt":"Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein functions. Recent sequence representation learning methods based on Protein Language Models (PLMs) excel in sequence-based tasks, but their direct adaptation to tasks involving protein structures remains a challenge. In contrast, structure-based methods leverage 3D structural information with graph neural networks and geometric pre-training methods show potential in function prediction tasks, but still suffers from the limited number of available structures. To bridge this gap, ou"},"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":"2303.06275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-03-11T01:24:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"003d860eeed8ddfae3f2c0adf4fc2bdc296bc03cd9d7d67591a76886bb7e193c","abstract_canon_sha256":"c32ce5a339dcb4ec1641fd60d7d8a3067da3b50b82f322398e8cfb7bf8a216bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:59.691137Z","signature_b64":"iD6l0RJSGNn+AATOwC7wF5SKDMn4P27c8EHrHyzjJPM5rsg9GKAhCItcakaiWQ5Eeh+bIEURCtKdH42tN7TYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ef86d9692dd49b3ce60df77f5a33cc22abbe32a44dadef56b58042de5c7e6c","last_reissued_at":"2026-07-05T07:01:59.690591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:59.690591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Study of Joint Representation Learning on Protein Sequences and Structures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Aur\\'elie Lozano, Chuanrui Wang, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2023-03-11T01:24:10Z","abstract_excerpt":"Learning effective protein representations is critical in a variety of tasks in biology such as predicting protein functions. Recent sequence representation learning methods based on Protein Language Models (PLMs) excel in sequence-based tasks, but their direct adaptation to tasks involving protein structures remains a challenge. In contrast, structure-based methods leverage 3D structural information with graph neural networks and geometric pre-training methods show potential in function prediction tasks, but still suffers from the limited number of available structures. To bridge this gap, ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06275","kind":"arxiv","version":2},"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/2303.06275/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":"2303.06275","created_at":"2026-07-05T07:01:59.690651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06275v2","created_at":"2026-07-05T07:01:59.690651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06275","created_at":"2026-07-05T07:01:59.690651+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHXYNWLJFXKJ","created_at":"2026-07-05T07:01:59.690651+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHXYNWLJFXKJWPHG","created_at":"2026-07-05T07:01:59.690651+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHXYNWLJ","created_at":"2026-07-05T07:01:59.690651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22307","citing_title":"Enhancing Protein Representation Learning via Manifold Restore Mixing","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ","json":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ.json","graph_json":"https://pith.science/api/pith-number/RHXYNWLJFXKJWPHGBX3X6WRTZQ/graph.json","events_json":"https://pith.science/api/pith-number/RHXYNWLJFXKJWPHGBX3X6WRTZQ/events.json","paper":"https://pith.science/paper/RHXYNWLJ"},"agent_actions":{"view_html":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ","download_json":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ.json","view_paper":"https://pith.science/paper/RHXYNWLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06275&json=true","fetch_graph":"https://pith.science/api/pith-number/RHXYNWLJFXKJWPHGBX3X6WRTZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RHXYNWLJFXKJWPHGBX3X6WRTZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ/action/storage_attestation","attest_author":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ/action/author_attestation","sign_citation":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ/action/citation_signature","submit_replication":"https://pith.science/pith/RHXYNWLJFXKJWPHGBX3X6WRTZQ/action/replication_record"}},"created_at":"2026-07-05T07:01:59.690651+00:00","updated_at":"2026-07-05T07:01:59.690651+00:00"}