{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2X72XCI2FY7EADDGP2I6MR2PFW","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":"146fd4a92d631d7c1958096d83901210d574a6f274d39b726ee5ff8696498a5d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-05-24T16:03:47Z","title_canon_sha256":"fb876a2f7ff58f8a323efdae68bcff234619cd1013a652e81786db31158622bd"},"schema_version":"1.0","source":{"id":"2405.15840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15840","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15840v2","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15840","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"2X72XCI2FY7E","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"2X72XCI2FY7EADDG","created_at":"2026-07-05T09:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"2X72XCI2","created_at":"2026-07-05T09:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:12035b72119302dc372bc283c8c5b4dbf05cb2fa480c0f3b4f3943eaf5f3e723","target":"graph","created_at":"2026-07-05T09:57:42Z","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/2405.15840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation learning and \\emph{de novo} generation of proteins are pivotal computational biology tasks. Whilst natural language processing (NLP) techniques have proven highly effective for protein sequence modelling, structure modelling presents a complex challenge, primarily due to its continuous and three-dimensional nature. Motivated by this discrepancy, we introduce an approach using a vector-quantized autoencoder that effectively tokenizes protein structures into discrete representations. This method transforms the continuous, complex space of protein structures into a manageable, disc","authors_text":"Benoit Gaujac, J\\'er\\'emie Don\\`a, Liviu Copoiu, Thomas D. Barrett, Thomas Pierrot, Timothy Atkinson","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-05-24T16:03:47Z","title":"Learning the Language of Protein Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15840","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":"sha256:462f1ee911c956aa0e558c685001f829440cd8491c1caa8bc9ab742b63b62475","target":"record","created_at":"2026-07-05T09:57:42Z","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":"146fd4a92d631d7c1958096d83901210d574a6f274d39b726ee5ff8696498a5d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.QM","submitted_at":"2024-05-24T16:03:47Z","title_canon_sha256":"fb876a2f7ff58f8a323efdae68bcff234619cd1013a652e81786db31158622bd"},"schema_version":"1.0","source":{"id":"2405.15840","kind":"arxiv","version":2}},"canonical_sha256":"d5ffab891a2e3e400c667e91e6474f2dbda004af31d5983b5832c472855071c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5ffab891a2e3e400c667e91e6474f2dbda004af31d5983b5832c472855071c1","first_computed_at":"2026-07-05T09:57:42.921912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:42.921912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Izdijl7H8BATWlXpvb25sseFkMtgiZb6b6ZPbDZFrznKyzG9PIkCZ781gOhhsbvOCAvEFlGPlgQtnLlJDJfhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:42.922389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:462f1ee911c956aa0e558c685001f829440cd8491c1caa8bc9ab742b63b62475","sha256:12035b72119302dc372bc283c8c5b4dbf05cb2fa480c0f3b4f3943eaf5f3e723"],"state_sha256":"1012204caaa77883cdd34575556031dde73d83fa316866171f43c1e7ec1e6a3b"}