{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TYWO6PNZO34JG5KPNH54MJORS","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":"1430a178b73658ae90591008390c6bb296dc0f1e49f8540ca103bb2e1fd99930","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-04T12:18:51Z","title_canon_sha256":"f099d3f48f5b8ec817d60963bfc888bc8311ebbe03f73c652f6bc2931ea55981"},"schema_version":"1.0","source":{"id":"2403.09673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09673","created_at":"2026-07-05T07:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09673v2","created_at":"2026-07-05T07:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09673","created_at":"2026-07-05T07:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"3TYWO6PNZO34","created_at":"2026-07-05T07:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"3TYWO6PNZO34JG5K","created_at":"2026-07-05T07:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"3TYWO6PN","created_at":"2026-07-05T07:57:51Z"}],"graph_snapshots":[{"event_id":"sha256:e6c37078288722821b4a5dfba1ffca31c69c316456420e925028e7c97a612ffc","target":"graph","created_at":"2026-07-05T07:57:51Z","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/2403.09673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of discrete sequences. We introduce \\textbf{FoldTokenizer} to represent protein sequence-structure as discrete symbols. This innovative approach involves projecting residue types and structures into a discrete space, guided by a reconstruction loss for information preservation. We refer to the learned discrete symbols as \\textbf{FoldToken}, and the sequence of FoldTokens serves as a","authors_text":"Cheng Tan, Jue Wang, Lirong Wu, Stan Z. Li, Yufei Huang, Zhangyang Gao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-04T12:18:51Z","title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09673","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":"sha256:8f7d1443609a11b2877a3c73de060f23a5f88556c3fc1e9ae9a18ae68e7fabea","target":"record","created_at":"2026-07-05T07:57:51Z","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":"1430a178b73658ae90591008390c6bb296dc0f1e49f8540ca103bb2e1fd99930","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-04T12:18:51Z","title_canon_sha256":"f099d3f48f5b8ec817d60963bfc888bc8311ebbe03f73c652f6bc2931ea55981"},"schema_version":"1.0","source":{"id":"2403.09673","kind":"arxiv","version":2}},"canonical_sha256":"dcf16779edcbb7c49baa7b4fde312e8c91cdd4bbf68145ae19d5e7519ac2c810","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcf16779edcbb7c49baa7b4fde312e8c91cdd4bbf68145ae19d5e7519ac2c810","first_computed_at":"2026-07-05T07:57:51.485020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:51.485020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ius3JW5mQ+o9osoH/qXTKfDh+DuqLFglLPkVvymDQegN2n8yRzKVj4C1U6f7AANSIaA7gbunJnqsLDJvtqqPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:51.485522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f7d1443609a11b2877a3c73de060f23a5f88556c3fc1e9ae9a18ae68e7fabea","sha256:e6c37078288722821b4a5dfba1ffca31c69c316456420e925028e7c97a612ffc"],"state_sha256":"fb67728fca15e61a559458b55db51274cd507737a896f17e7dbee24c61a4d504"}