{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7QR5RDTOGUBLRGFRGGW4CFKIKZ","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":"71bf226813c5d59c369294f9a93b14b22690d16cb9977c50b3ac2201147239c0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:15:59Z","title_canon_sha256":"0ab650c6f7ad0e8a6b4fdbc5564021e3e4f38603a125faddf03d20d2b32c3eae"},"schema_version":"1.0","source":{"id":"2605.23605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23605","created_at":"2026-05-25T02:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23605v1","created_at":"2026-05-25T02:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23605","created_at":"2026-05-25T02:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"7QR5RDTOGUBL","created_at":"2026-05-25T02:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"7QR5RDTOGUBLRGFR","created_at":"2026-05-25T02:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"7QR5RDTO","created_at":"2026-05-25T02:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:f030ace580d0fc7baec9e836d18672a058e246d4224356b0a444d4c649c997b7","target":"graph","created_at":"2026-05-25T02:02:21Z","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/2605.23605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion language models with three components: (1) a continuous latent space with semantic capabilities, learned by an auto-encoder fine-tuned from an existing masked diffusion language model; (2) a latent diffusion model learning the prior over the encoder distribution; (3) a consistency model distilling the learned prior into a few-step latent generative model. We ","authors_text":"Ante Juki\\'c, Arash Vahdat, Jean-Marie Lemercier, Karsten Kreis, Morteza Mardani, Tomas Geffner","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:15:59Z","title":"DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23605","kind":"arxiv","version":1},"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:ea7c3c2a3be602e5fd7bdea3e5a301b66848a25d32bb301669397f0075cae80c","target":"record","created_at":"2026-05-25T02:02:21Z","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":"71bf226813c5d59c369294f9a93b14b22690d16cb9977c50b3ac2201147239c0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T13:15:59Z","title_canon_sha256":"0ab650c6f7ad0e8a6b4fdbc5564021e3e4f38603a125faddf03d20d2b32c3eae"},"schema_version":"1.0","source":{"id":"2605.23605","kind":"arxiv","version":1}},"canonical_sha256":"fc23d88e6e3502b898b131adc11548567bdf515812b5bbe1af2b8108e9c94cf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc23d88e6e3502b898b131adc11548567bdf515812b5bbe1af2b8108e9c94cf7","first_computed_at":"2026-05-25T02:02:21.814282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:21.814282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HYiqsdI7hUr02d1EJDfmuorIFqxFqyqpQXFIU0H9p/OBrwrC/ky3zflWzwqG82iflex3wF+RU2hREhhabf2+CA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:21.815091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea7c3c2a3be602e5fd7bdea3e5a301b66848a25d32bb301669397f0075cae80c","sha256:f030ace580d0fc7baec9e836d18672a058e246d4224356b0a444d4c649c997b7"],"state_sha256":"a8f98e5639410030e90d857099f4a23adbdf0a5359d7a24718f9ee21cf45d2c4"}