{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2QE6QNTDI65RMVQU5EJIT46YX7","short_pith_number":"pith:2QE6QNTD","schema_version":"1.0","canonical_sha256":"d409e8366347bb165614e91289f3d8bfc2c0edc97263657e02de7754b6cfecf7","source":{"kind":"arxiv","id":"2605.27352","version":1},"attestation_state":"computed","paper":{"title":"From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ness Shroff, Yingbin Liang, Yuchen Liang","submitted_at":"2026-05-26T17:52:28Z","abstract_excerpt":"Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow mixing. In this work, we propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD). GADD leverages the structure of the concrete score function to construct Gibbs posterior likelihoods directly, without requiring any additional training "},"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":"2605.27352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T17:52:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d7ab308a2da8a7e3c0b33a8114c8e1fe368fb0094f2fe8a1fec01138df828289","abstract_canon_sha256":"64e19b0248abf5cb487745807e3048b781f98e61d7b9ad0030f4a5746dfe0956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:19.328328Z","signature_b64":"pTWJ/O2Ez4gA3udKcyzr+Cke3y/y3y2FAH2R7BZP059d3FzeJukoQapnBtpo7U0FjHVpcVHvixRtzzYJJ4IHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d409e8366347bb165614e91289f3d8bfc2c0edc97263657e02de7754b6cfecf7","last_reissued_at":"2026-05-27T02:06:19.327525Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:19.327525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ness Shroff, Yingbin Liang, Yuchen Liang","submitted_at":"2026-05-26T17:52:28Z","abstract_excerpt":"Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow mixing. In this work, we propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD). GADD leverages the structure of the concrete score function to construct Gibbs posterior likelihoods directly, without requiring any additional training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27352","kind":"arxiv","version":1},"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/2605.27352/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":"2605.27352","created_at":"2026-05-27T02:06:19.327693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27352v1","created_at":"2026-05-27T02:06:19.327693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27352","created_at":"2026-05-27T02:06:19.327693+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QE6QNTDI65R","created_at":"2026-05-27T02:06:19.327693+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QE6QNTDI65RMVQU","created_at":"2026-05-27T02:06:19.327693+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QE6QNTD","created_at":"2026-05-27T02:06:19.327693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7","json":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7.json","graph_json":"https://pith.science/api/pith-number/2QE6QNTDI65RMVQU5EJIT46YX7/graph.json","events_json":"https://pith.science/api/pith-number/2QE6QNTDI65RMVQU5EJIT46YX7/events.json","paper":"https://pith.science/paper/2QE6QNTD"},"agent_actions":{"view_html":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7","download_json":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7.json","view_paper":"https://pith.science/paper/2QE6QNTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27352&json=true","fetch_graph":"https://pith.science/api/pith-number/2QE6QNTDI65RMVQU5EJIT46YX7/graph.json","fetch_events":"https://pith.science/api/pith-number/2QE6QNTDI65RMVQU5EJIT46YX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7/action/storage_attestation","attest_author":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7/action/author_attestation","sign_citation":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7/action/citation_signature","submit_replication":"https://pith.science/pith/2QE6QNTDI65RMVQU5EJIT46YX7/action/replication_record"}},"created_at":"2026-05-27T02:06:19.327693+00:00","updated_at":"2026-05-27T02:06:19.327693+00:00"}