{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TYWO6PNZO34JG5KPNH54MJORS","short_pith_number":"pith:3TYWO6PN","schema_version":"1.0","canonical_sha256":"dcf16779edcbb7c49baa7b4fde312e8c91cdd4bbf68145ae19d5e7519ac2c810","source":{"kind":"arxiv","id":"2403.09673","version":2},"attestation_state":"computed","paper":{"title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Cheng Tan, Jue Wang, Lirong Wu, Stan Z. Li, Yufei Huang, Zhangyang Gao","submitted_at":"2024-02-04T12:18:51Z","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"},"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":"2403.09673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-02-04T12:18:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f099d3f48f5b8ec817d60963bfc888bc8311ebbe03f73c652f6bc2931ea55981","abstract_canon_sha256":"1430a178b73658ae90591008390c6bb296dc0f1e49f8540ca103bb2e1fd99930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:51.485522Z","signature_b64":"ius3JW5mQ+o9osoH/qXTKfDh+DuqLFglLPkVvymDQegN2n8yRzKVj4C1U6f7AANSIaA7gbunJnqsLDJvtqqPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcf16779edcbb7c49baa7b4fde312e8c91cdd4bbf68145ae19d5e7519ac2c810","last_reissued_at":"2026-07-05T07:57:51.485020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:51.485020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Cheng Tan, Jue Wang, Lirong Wu, Stan Z. Li, Yufei Huang, Zhangyang Gao","submitted_at":"2024-02-04T12:18:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09673","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/2403.09673/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":"2403.09673","created_at":"2026-07-05T07:57:51.485074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09673v2","created_at":"2026-07-05T07:57:51.485074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09673","created_at":"2026-07-05T07:57:51.485074+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TYWO6PNZO34","created_at":"2026-07-05T07:57:51.485074+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TYWO6PNZO34JG5K","created_at":"2026-07-05T07:57:51.485074+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TYWO6PN","created_at":"2026-07-05T07:57:51.485074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01564","citing_title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS","json":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS.json","graph_json":"https://pith.science/api/pith-number/3TYWO6PNZO34JG5KPNH54MJORS/graph.json","events_json":"https://pith.science/api/pith-number/3TYWO6PNZO34JG5KPNH54MJORS/events.json","paper":"https://pith.science/paper/3TYWO6PN"},"agent_actions":{"view_html":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS","download_json":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS.json","view_paper":"https://pith.science/paper/3TYWO6PN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09673&json=true","fetch_graph":"https://pith.science/api/pith-number/3TYWO6PNZO34JG5KPNH54MJORS/graph.json","fetch_events":"https://pith.science/api/pith-number/3TYWO6PNZO34JG5KPNH54MJORS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS/action/storage_attestation","attest_author":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS/action/author_attestation","sign_citation":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS/action/citation_signature","submit_replication":"https://pith.science/pith/3TYWO6PNZO34JG5KPNH54MJORS/action/replication_record"}},"created_at":"2026-07-05T07:57:51.485074+00:00","updated_at":"2026-07-05T07:57:51.485074+00:00"}