{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G44RAA6EUOMSC2JMZNFSKX265V","short_pith_number":"pith:G44RAA6E","schema_version":"1.0","canonical_sha256":"37391003c4a39921692ccb4b255f5eed7f961a7290cc531918af05d1ec798fea","source":{"kind":"arxiv","id":"2601.22519","version":2},"attestation_state":"computed","paper":{"title":"Corrected Samplers for Discrete Flow Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fang Fang, Guang Cheng, Hongyuan Zha, Liyan Xie, Yidong Ouyang, Zhengyan Wan","submitted_at":"2026-01-30T03:53:22Z","abstract_excerpt":"Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for discrete diffusion models, such as tau-leaping and Euler solver. However, these samplers require a large number of iterations to control discretization error, since the transition rates are frozen in time and evaluated at the initial state within each time interval. Moreover, theoretical results for these samplers often require boundedness conditions of the transition rat"},"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":"2601.22519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-01-30T03:53:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"535c374e4a56c6486c1aaab2300c16d7caa955c936c2e876f62324f99f50cfe0","abstract_canon_sha256":"a538d234f26743973e115b9459d97c44f66a3fae23d7645550ce9923ba28f1ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:11.220207Z","signature_b64":"2v+sfhUmSM9JZp1ofRZ1xZ1jyz8E/vkvIwJgT5tFg7j/5L3hpw51BwBhetGw/p8pzy/vMbkClqHIUTgTjgShAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37391003c4a39921692ccb4b255f5eed7f961a7290cc531918af05d1ec798fea","last_reissued_at":"2026-05-27T02:05:11.219421Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:11.219421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corrected Samplers for Discrete Flow Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fang Fang, Guang Cheng, Hongyuan Zha, Liyan Xie, Yidong Ouyang, Zhengyan Wan","submitted_at":"2026-01-30T03:53:22Z","abstract_excerpt":"Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A line of recent work has studied samplers for discrete diffusion models, such as tau-leaping and Euler solver. However, these samplers require a large number of iterations to control discretization error, since the transition rates are frozen in time and evaluated at the initial state within each time interval. Moreover, theoretical results for these samplers often require boundedness conditions of the transition rat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22519","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/2601.22519/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":"2601.22519","created_at":"2026-05-27T02:05:11.219542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22519v2","created_at":"2026-05-27T02:05:11.219542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22519","created_at":"2026-05-27T02:05:11.219542+00:00"},{"alias_kind":"pith_short_12","alias_value":"G44RAA6EUOMS","created_at":"2026-05-27T02:05:11.219542+00:00"},{"alias_kind":"pith_short_16","alias_value":"G44RAA6EUOMSC2JM","created_at":"2026-05-27T02:05:11.219542+00:00"},{"alias_kind":"pith_short_8","alias_value":"G44RAA6E","created_at":"2026-05-27T02:05:11.219542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V","json":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V.json","graph_json":"https://pith.science/api/pith-number/G44RAA6EUOMSC2JMZNFSKX265V/graph.json","events_json":"https://pith.science/api/pith-number/G44RAA6EUOMSC2JMZNFSKX265V/events.json","paper":"https://pith.science/paper/G44RAA6E"},"agent_actions":{"view_html":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V","download_json":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V.json","view_paper":"https://pith.science/paper/G44RAA6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22519&json=true","fetch_graph":"https://pith.science/api/pith-number/G44RAA6EUOMSC2JMZNFSKX265V/graph.json","fetch_events":"https://pith.science/api/pith-number/G44RAA6EUOMSC2JMZNFSKX265V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V/action/storage_attestation","attest_author":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V/action/author_attestation","sign_citation":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V/action/citation_signature","submit_replication":"https://pith.science/pith/G44RAA6EUOMSC2JMZNFSKX265V/action/replication_record"}},"created_at":"2026-05-27T02:05:11.219542+00:00","updated_at":"2026-05-27T02:05:11.219542+00:00"}