{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SNCVTUOMGFUIODLC2Q7PHN57HP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"505bf4dfa944f4cdba2447c1404ccb1080d39016db9a8eddff9e422c0f6d3a4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:48:20Z","title_canon_sha256":"dd9457ff56d6f461e33797e8c8dc3213b8dbc436ae449bd84e704a2d07253ab3"},"schema_version":"1.0","source":{"id":"2301.12068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12068","created_at":"2026-07-05T06:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12068v2","created_at":"2026-07-05T06:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12068","created_at":"2026-07-05T06:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"SNCVTUOMGFUI","created_at":"2026-07-05T06:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"SNCVTUOMGFUIODLC","created_at":"2026-07-05T06:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"SNCVTUOM","created_at":"2026-07-05T06:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:ce2fe74a7668a1f623a897eb23754e1c62dc41b39cf187d6048bc69e4e182e5e","target":"graph","created_at":"2026-07-05T06:28:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.12068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aur\\'elie Lozano, Jian Tang, Minghao Xu, Payel Das, Vijil Chenthamarakshan, Zuobai Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:48:20Z","title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12068","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6383e3e275f796b135d174facbd9cfbd3539d5297ca44dd34af0eb61478bc3d1","target":"record","created_at":"2026-07-05T06:28:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"505bf4dfa944f4cdba2447c1404ccb1080d39016db9a8eddff9e422c0f6d3a4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:48:20Z","title_canon_sha256":"dd9457ff56d6f461e33797e8c8dc3213b8dbc436ae449bd84e704a2d07253ab3"},"schema_version":"1.0","source":{"id":"2301.12068","kind":"arxiv","version":2}},"canonical_sha256":"934559d1cc3168870d62d43ef3b7bf3bd1d56cd43334f58ebc4bba6aad21d0ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"934559d1cc3168870d62d43ef3b7bf3bd1d56cd43334f58ebc4bba6aad21d0ca","first_computed_at":"2026-07-05T06:28:58.519270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:58.519270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NfF0k94De+8dG31XP9SVrH0wDlsFlXQ7etp/kOQKz2OoaqKQWvqjZM1uq+MrCr7tlUQ0HyqRCWqeVSQmb0gkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:58.519759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6383e3e275f796b135d174facbd9cfbd3539d5297ca44dd34af0eb61478bc3d1","sha256:ce2fe74a7668a1f623a897eb23754e1c62dc41b39cf187d6048bc69e4e182e5e"],"state_sha256":"4832c084772ad8ee4762c08ffab4a03f9eb1396a3a3279c79a615739f54664d1"}