{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PI3EJ2L4V7LTZR77USSNAYYCUV","short_pith_number":"pith:PI3EJ2L4","schema_version":"1.0","canonical_sha256":"7a3644e97cafd73cc7ffa4a4d06302a551a900dc88b7e2814e9f9c9e1ad273c5","source":{"kind":"arxiv","id":"2410.02321","version":2},"attestation_state":"computed","paper":{"title":"Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Quanquan Gu, Zikun Zhang, Zixiang Chen","submitted_at":"2024-10-03T09:07:13Z","abstract_excerpt":"Diffusion models have achieved great success in generating high-dimensional samples across various applications. While the theoretical guarantees for continuous-state diffusion models have been extensively studied, the convergence analysis of the discrete-state counterparts remains under-explored. In this paper, we study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework. We introduce a discrete-time sampling algorithm in the general state space $[S]^d$ that utilizes score estimators at predefined time points. We derive conv"},"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":"2410.02321","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T09:07:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90dfa82115f517ac350121d32f1ae013ca76dcd0bbca71afbdcbf1277d8f2d8b","abstract_canon_sha256":"1035a75a458084fb41d752ea9af7f7bfa6622c68b66acaeb945f029875146c4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:55.526495Z","signature_b64":"AAiu2iyCHOX4h/GLbbiXacIf6/85pIgCvfBtw7JibsEDJOcOVQqhM65Bdid4D8rKirgK1Q3wcVQtF6UdGGLpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a3644e97cafd73cc7ffa4a4d06302a551a900dc88b7e2814e9f9c9e1ad273c5","last_reissued_at":"2026-07-05T10:47:55.526000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:55.526000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Quanquan Gu, Zikun Zhang, Zixiang Chen","submitted_at":"2024-10-03T09:07:13Z","abstract_excerpt":"Diffusion models have achieved great success in generating high-dimensional samples across various applications. While the theoretical guarantees for continuous-state diffusion models have been extensively studied, the convergence analysis of the discrete-state counterparts remains under-explored. In this paper, we study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework. We introduce a discrete-time sampling algorithm in the general state space $[S]^d$ that utilizes score estimators at predefined time points. We derive conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02321","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/2410.02321/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":"2410.02321","created_at":"2026-07-05T10:47:55.526062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02321v2","created_at":"2026-07-05T10:47:55.526062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02321","created_at":"2026-07-05T10:47:55.526062+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI3EJ2L4V7LT","created_at":"2026-07-05T10:47:55.526062+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI3EJ2L4V7LTZR77","created_at":"2026-07-05T10:47:55.526062+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI3EJ2L4","created_at":"2026-07-05T10:47:55.526062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV","json":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV.json","graph_json":"https://pith.science/api/pith-number/PI3EJ2L4V7LTZR77USSNAYYCUV/graph.json","events_json":"https://pith.science/api/pith-number/PI3EJ2L4V7LTZR77USSNAYYCUV/events.json","paper":"https://pith.science/paper/PI3EJ2L4"},"agent_actions":{"view_html":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV","download_json":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV.json","view_paper":"https://pith.science/paper/PI3EJ2L4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02321&json=true","fetch_graph":"https://pith.science/api/pith-number/PI3EJ2L4V7LTZR77USSNAYYCUV/graph.json","fetch_events":"https://pith.science/api/pith-number/PI3EJ2L4V7LTZR77USSNAYYCUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV/action/storage_attestation","attest_author":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV/action/author_attestation","sign_citation":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV/action/citation_signature","submit_replication":"https://pith.science/pith/PI3EJ2L4V7LTZR77USSNAYYCUV/action/replication_record"}},"created_at":"2026-07-05T10:47:55.526062+00:00","updated_at":"2026-07-05T10:47:55.526062+00:00"}