{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E26YW6YXDXISN5AU3V4YPKFILE","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":"18f09e262e1beaac81ebaa2fd6bde9aafc1f6747e4c6179a6e094a195ccee158","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:57:56Z","title_canon_sha256":"cdd969e3a213209b8e1a211a139c2c3862c3998a1c08f95ef2bd27fdf0ec48a0"},"schema_version":"1.0","source":{"id":"2402.18567","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18567","created_at":"2026-07-05T09:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18567v2","created_at":"2026-07-05T09:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18567","created_at":"2026-07-05T09:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"E26YW6YXDXIS","created_at":"2026-07-05T09:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"E26YW6YXDXISN5AU","created_at":"2026-07-05T09:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"E26YW6YX","created_at":"2026-07-05T09:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:ab5df91985e041add3db3bcfe13a76b4095c2af97a4872c8a0e7d3aa7a796311","target":"graph","created_at":"2026-07-05T09:21:25Z","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/2402.18567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongyu Xue, Fei Ye, Quanquan Gu, Shujian Huang, Xinyou Wang, Zaixiang Zheng","cross_cats":["q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:57:56Z","title":"Diffusion Language Models Are Versatile Protein Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18567","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":"sha256:2ea7b06b1445bb5a7b7a975af5059c36c47be8952864f6e6b5cdbc2dc494eef8","target":"record","created_at":"2026-07-05T09:21:25Z","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":"18f09e262e1beaac81ebaa2fd6bde9aafc1f6747e4c6179a6e094a195ccee158","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:57:56Z","title_canon_sha256":"cdd969e3a213209b8e1a211a139c2c3862c3998a1c08f95ef2bd27fdf0ec48a0"},"schema_version":"1.0","source":{"id":"2402.18567","kind":"arxiv","version":2}},"canonical_sha256":"26bd8b7b171dd126f414dd7987a8a85934a6b813129bd8a1ef51bc28717ef0c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26bd8b7b171dd126f414dd7987a8a85934a6b813129bd8a1ef51bc28717ef0c6","first_computed_at":"2026-07-05T09:21:25.859979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:25.859979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jNdDZ5HtoYqJVUOYj6vfIIryKT7ZWHmZLPYs8eJps08tnFWIO3yMJ9gOxkl5bquvsao0zH5tJz8BkrjsSVrtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:25.860490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18567","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ea7b06b1445bb5a7b7a975af5059c36c47be8952864f6e6b5cdbc2dc494eef8","sha256:ab5df91985e041add3db3bcfe13a76b4095c2af97a4872c8a0e7d3aa7a796311"],"state_sha256":"11dba2aadc4d92f4a18106caf6d13e422755311a290ed6283fd070bf5b7af642"}