{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E26YW6YXDXISN5AU3V4YPKFILE","short_pith_number":"pith:E26YW6YX","schema_version":"1.0","canonical_sha256":"26bd8b7b171dd126f414dd7987a8a85934a6b813129bd8a1ef51bc28717ef0c6","source":{"kind":"arxiv","id":"2402.18567","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Language Models Are Versatile Protein Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dongyu Xue, Fei Ye, Quanquan Gu, Shujian Huang, Xinyou Wang, Zaixiang Zheng","submitted_at":"2024-02-28T18:57:56Z","abstract_excerpt":"This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. We first pre-train scalable DPLMs from evolutionary-scale protein sequences within a generative self-supervised discrete diffusion probabilistic framework, which generalizes language modeling for proteins in a principled way. After pre-training, DPLM exhibits the ability to generate structurally plausible, novel, and diverse protein sequences for unconditional generation. We further demonstrate the proposed diff"},"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":"2402.18567","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:57:56Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"cdd969e3a213209b8e1a211a139c2c3862c3998a1c08f95ef2bd27fdf0ec48a0","abstract_canon_sha256":"18f09e262e1beaac81ebaa2fd6bde9aafc1f6747e4c6179a6e094a195ccee158"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:25.860490Z","signature_b64":"jNdDZ5HtoYqJVUOYj6vfIIryKT7ZWHmZLPYs8eJps08tnFWIO3yMJ9gOxkl5bquvsao0zH5tJz8BkrjsSVrtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26bd8b7b171dd126f414dd7987a8a85934a6b813129bd8a1ef51bc28717ef0c6","last_reissued_at":"2026-07-05T09:21:25.859979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:25.859979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Language Models Are Versatile Protein Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dongyu Xue, Fei Ye, Quanquan Gu, Shujian Huang, Xinyou Wang, Zaixiang Zheng","submitted_at":"2024-02-28T18:57:56Z","abstract_excerpt":"This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. We first pre-train scalable DPLMs from evolutionary-scale protein sequences within a generative self-supervised discrete diffusion probabilistic framework, which generalizes language modeling for proteins in a principled way. After pre-training, DPLM exhibits the ability to generate structurally plausible, novel, and diverse protein sequences for unconditional generation. We further demonstrate the proposed diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18567","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/2402.18567/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":"2402.18567","created_at":"2026-07-05T09:21:25.860038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18567v2","created_at":"2026-07-05T09:21:25.860038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18567","created_at":"2026-07-05T09:21:25.860038+00:00"},{"alias_kind":"pith_short_12","alias_value":"E26YW6YXDXIS","created_at":"2026-07-05T09:21:25.860038+00:00"},{"alias_kind":"pith_short_16","alias_value":"E26YW6YXDXISN5AU","created_at":"2026-07-05T09:21:25.860038+00:00"},{"alias_kind":"pith_short_8","alias_value":"E26YW6YX","created_at":"2026-07-05T09:21:25.860038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10543","citing_title":"Flexible Flows for Biological Sequence Design","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07567","citing_title":"SurfDesign: Effective Protein Design on Molecular Surfaces","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30963","citing_title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15923","citing_title":"A Unification of Discrete, Gaussian, and Simplicial Diffusion","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03360","citing_title":"A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09981","citing_title":"Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09749","citing_title":"Primal-Dual Guided Decoding for Constrained Discrete Diffusion","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05829","citing_title":"MP2D: Constrained Monte Carlo Tree-Guided Diffusion for Multi-Objective Protein Sequence Design","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24506","citing_title":"MIMIC: A Generative Multimodal Foundation Model for Biomolecules","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00948","citing_title":"Co-Generative De Novo Functional Protein Design","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00182","citing_title":"Towards A Generative Protein Evolution Machine with DPLM-Evo","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07193","citing_title":"Coupling Models for One-Step Discrete Generation","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18603","citing_title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE","json":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE.json","graph_json":"https://pith.science/api/pith-number/E26YW6YXDXISN5AU3V4YPKFILE/graph.json","events_json":"https://pith.science/api/pith-number/E26YW6YXDXISN5AU3V4YPKFILE/events.json","paper":"https://pith.science/paper/E26YW6YX"},"agent_actions":{"view_html":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE","download_json":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE.json","view_paper":"https://pith.science/paper/E26YW6YX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18567&json=true","fetch_graph":"https://pith.science/api/pith-number/E26YW6YXDXISN5AU3V4YPKFILE/graph.json","fetch_events":"https://pith.science/api/pith-number/E26YW6YXDXISN5AU3V4YPKFILE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE/action/storage_attestation","attest_author":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE/action/author_attestation","sign_citation":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE/action/citation_signature","submit_replication":"https://pith.science/pith/E26YW6YXDXISN5AU3V4YPKFILE/action/replication_record"}},"created_at":"2026-07-05T09:21:25.860038+00:00","updated_at":"2026-07-05T09:21:25.860038+00:00"}