{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UEZNNZF3ATMTLJLJG7QR3LMFV5","short_pith_number":"pith:UEZNNZF3","schema_version":"1.0","canonical_sha256":"a132d6e4bb04d935a56937e11dad85af7569fd40f3253324a2d48fa4f6cd66d1","source":{"kind":"arxiv","id":"2605.26582","version":1},"attestation_state":"computed","paper":{"title":"On the Error-Correcting Effects of Stochasticity in Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amirali Aghazadeh, Sungwon Jeong, William Yuan","submitted_at":"2026-05-26T05:58:46Z","abstract_excerpt":"Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling efficiency and sample quality. In this work, we present a systematic study of how the \\emph{degree of stochasticity} in Markov transitions governs the sampling tradeoff. We show that highly deterministic transitions converge rapidly but suffer from error accumulation, while more stochastic transitions converge more slowly yet can achieve higher final sample quality. Using an information-theoretic analysis, we identify the underlying mechanism "},"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":"2605.26582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T05:58:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9444b2e5e1f8e5aaec26f697bbbb68f3defbb839d77a3870117fcb2e69c52bc7","abstract_canon_sha256":"12af8638c999d17d16a3ea181d0f479791d0eb74a523b2f147e3196329591e7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:27.210059Z","signature_b64":"nwt6VALT0/iOz5UNsHSbCf6//7HGLBjPYISmMrDxJhFAlu1jkeThx9/UM6yoQAtEI0Rz/C/k9NueAhPvQsEZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a132d6e4bb04d935a56937e11dad85af7569fd40f3253324a2d48fa4f6cd66d1","last_reissued_at":"2026-05-27T01:05:27.209603Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:27.209603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Error-Correcting Effects of Stochasticity in Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amirali Aghazadeh, Sungwon Jeong, William Yuan","submitted_at":"2026-05-26T05:58:46Z","abstract_excerpt":"Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling efficiency and sample quality. In this work, we present a systematic study of how the \\emph{degree of stochasticity} in Markov transitions governs the sampling tradeoff. We show that highly deterministic transitions converge rapidly but suffer from error accumulation, while more stochastic transitions converge more slowly yet can achieve higher final sample quality. Using an information-theoretic analysis, we identify the underlying mechanism "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26582","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/2605.26582/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":"2605.26582","created_at":"2026-05-27T01:05:27.209667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26582v1","created_at":"2026-05-27T01:05:27.209667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26582","created_at":"2026-05-27T01:05:27.209667+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEZNNZF3ATMT","created_at":"2026-05-27T01:05:27.209667+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEZNNZF3ATMTLJLJ","created_at":"2026-05-27T01:05:27.209667+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEZNNZF3","created_at":"2026-05-27T01:05:27.209667+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/UEZNNZF3ATMTLJLJG7QR3LMFV5","json":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5.json","graph_json":"https://pith.science/api/pith-number/UEZNNZF3ATMTLJLJG7QR3LMFV5/graph.json","events_json":"https://pith.science/api/pith-number/UEZNNZF3ATMTLJLJG7QR3LMFV5/events.json","paper":"https://pith.science/paper/UEZNNZF3"},"agent_actions":{"view_html":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5","download_json":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5.json","view_paper":"https://pith.science/paper/UEZNNZF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26582&json=true","fetch_graph":"https://pith.science/api/pith-number/UEZNNZF3ATMTLJLJG7QR3LMFV5/graph.json","fetch_events":"https://pith.science/api/pith-number/UEZNNZF3ATMTLJLJG7QR3LMFV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5/action/storage_attestation","attest_author":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5/action/author_attestation","sign_citation":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5/action/citation_signature","submit_replication":"https://pith.science/pith/UEZNNZF3ATMTLJLJG7QR3LMFV5/action/replication_record"}},"created_at":"2026-05-27T01:05:27.209667+00:00","updated_at":"2026-05-27T01:05:27.209667+00:00"}