{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SNCVTUOMGFUIODLC2Q7PHN57HP","short_pith_number":"pith:SNCVTUOM","schema_version":"1.0","canonical_sha256":"934559d1cc3168870d62d43ef3b7bf3bd1d56cd43334f58ebc4bba6aad21d0ca","source":{"kind":"arxiv","id":"2301.12068","version":2},"attestation_state":"computed","paper":{"title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aur\\'elie Lozano, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2023-01-28T02:48:20Z","abstract_excerpt":"Self-supervised pre-training methods on proteins have recently gained attention, with most approaches focusing on either protein sequences or structures, neglecting the exploration of their joint distribution, which is crucial for a comprehensive understanding of protein functions by integrating co-evolutionary information and structural characteristics. In this work, inspired by the success of denoising diffusion models in generative tasks, we propose the DiffPreT approach to pre-train a protein encoder by sequence-structure joint diffusion modeling. DiffPreT guides the encoder to recover the"},"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":"2301.12068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:48:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd9457ff56d6f461e33797e8c8dc3213b8dbc436ae449bd84e704a2d07253ab3","abstract_canon_sha256":"505bf4dfa944f4cdba2447c1404ccb1080d39016db9a8eddff9e422c0f6d3a4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:58.519759Z","signature_b64":"NfF0k94De+8dG31XP9SVrH0wDlsFlXQ7etp/kOQKz2OoaqKQWvqjZM1uq+MrCr7tlUQ0HyqRCWqeVSQmb0gkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934559d1cc3168870d62d43ef3b7bf3bd1d56cd43334f58ebc4bba6aad21d0ca","last_reissued_at":"2026-07-05T06:28:58.519270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:58.519270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aur\\'elie Lozano, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","submitted_at":"2023-01-28T02:48:20Z","abstract_excerpt":"Self-supervised pre-training methods on proteins have recently gained attention, with most approaches focusing on either protein sequences or structures, neglecting the exploration of their joint distribution, which is crucial for a comprehensive understanding of protein functions by integrating co-evolutionary information and structural characteristics. In this work, inspired by the success of denoising diffusion models in generative tasks, we propose the DiffPreT approach to pre-train a protein encoder by sequence-structure joint diffusion modeling. DiffPreT guides the encoder to recover the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12068","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/2301.12068/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":"2301.12068","created_at":"2026-07-05T06:28:58.519339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12068v2","created_at":"2026-07-05T06:28:58.519339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12068","created_at":"2026-07-05T06:28:58.519339+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNCVTUOMGFUI","created_at":"2026-07-05T06:28:58.519339+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNCVTUOMGFUIODLC","created_at":"2026-07-05T06:28:58.519339+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNCVTUOM","created_at":"2026-07-05T06:28:58.519339+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/SNCVTUOMGFUIODLC2Q7PHN57HP","json":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP.json","graph_json":"https://pith.science/api/pith-number/SNCVTUOMGFUIODLC2Q7PHN57HP/graph.json","events_json":"https://pith.science/api/pith-number/SNCVTUOMGFUIODLC2Q7PHN57HP/events.json","paper":"https://pith.science/paper/SNCVTUOM"},"agent_actions":{"view_html":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP","download_json":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP.json","view_paper":"https://pith.science/paper/SNCVTUOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12068&json=true","fetch_graph":"https://pith.science/api/pith-number/SNCVTUOMGFUIODLC2Q7PHN57HP/graph.json","fetch_events":"https://pith.science/api/pith-number/SNCVTUOMGFUIODLC2Q7PHN57HP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP/action/storage_attestation","attest_author":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP/action/author_attestation","sign_citation":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP/action/citation_signature","submit_replication":"https://pith.science/pith/SNCVTUOMGFUIODLC2Q7PHN57HP/action/replication_record"}},"created_at":"2026-07-05T06:28:58.519339+00:00","updated_at":"2026-07-05T06:28:58.519339+00:00"}