{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QDX6DSBYYPHLDBLELKLAEC4YAG","short_pith_number":"pith:QDX6DSBY","schema_version":"1.0","canonical_sha256":"80efe1c838c3ceb185645a96020b98019b415b50d0ab535d36002ab328a3d37c","source":{"kind":"arxiv","id":"2509.21906","version":3},"attestation_state":"computed","paper":{"title":"Error Analysis of Discrete Flow with Generator Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Fang Fang, Guang Cheng, Hongyuan Zha, Liyan Xie, Qiang Yao, Yidong Ouyang, Zhengyan Wan","submitted_at":"2025-09-26T05:41:45Z","abstract_excerpt":"Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence properties and error analysis remain largely unexplored. In this work, we develop a unified framework grounded in stochastic calculus theory to systematically investigate the theoretical properties of discrete flow models. Specifically, by leveraging a Girsanov-type theorem for the path measures of two continuous-time Markov chains (CTMCs), we present a comprehensive error analysis "},"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":"2509.21906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-09-26T05:41:45Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"0f7e22dc09061907417413bd41ff02a9f57b1f2ed4bdd4ca25d1294d1af2e857","abstract_canon_sha256":"01bad207e2c203f6f5fd32ce863ca5d22f4b7aeb9f02f75e443d7dc350f62739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:06.029666Z","signature_b64":"B0SWWcRoBaMFXJPlVsyX8WJ511U0DzcOM63DSK6gixHSbpoFwnDiEqnoEFw7ftYbe3aJMmypSSBi69kKCFVdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80efe1c838c3ceb185645a96020b98019b415b50d0ab535d36002ab328a3d37c","last_reissued_at":"2026-05-27T02:05:06.029047Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:06.029047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Analysis of Discrete Flow with Generator Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Fang Fang, Guang Cheng, Hongyuan Zha, Liyan Xie, Qiang Yao, Yidong Ouyang, Zhengyan Wan","submitted_at":"2025-09-26T05:41:45Z","abstract_excerpt":"Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence properties and error analysis remain largely unexplored. In this work, we develop a unified framework grounded in stochastic calculus theory to systematically investigate the theoretical properties of discrete flow models. Specifically, by leveraging a Girsanov-type theorem for the path measures of two continuous-time Markov chains (CTMCs), we present a comprehensive error analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21906","kind":"arxiv","version":3},"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/2509.21906/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":"2509.21906","created_at":"2026-05-27T02:05:06.029123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.21906v3","created_at":"2026-05-27T02:05:06.029123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21906","created_at":"2026-05-27T02:05:06.029123+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDX6DSBYYPHL","created_at":"2026-05-27T02:05:06.029123+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDX6DSBYYPHLDBLE","created_at":"2026-05-27T02:05:06.029123+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDX6DSBY","created_at":"2026-05-27T02:05:06.029123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09291","citing_title":"dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models","ref_index":106,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG","json":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG.json","graph_json":"https://pith.science/api/pith-number/QDX6DSBYYPHLDBLELKLAEC4YAG/graph.json","events_json":"https://pith.science/api/pith-number/QDX6DSBYYPHLDBLELKLAEC4YAG/events.json","paper":"https://pith.science/paper/QDX6DSBY"},"agent_actions":{"view_html":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG","download_json":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG.json","view_paper":"https://pith.science/paper/QDX6DSBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.21906&json=true","fetch_graph":"https://pith.science/api/pith-number/QDX6DSBYYPHLDBLELKLAEC4YAG/graph.json","fetch_events":"https://pith.science/api/pith-number/QDX6DSBYYPHLDBLELKLAEC4YAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG/action/storage_attestation","attest_author":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG/action/author_attestation","sign_citation":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG/action/citation_signature","submit_replication":"https://pith.science/pith/QDX6DSBYYPHLDBLELKLAEC4YAG/action/replication_record"}},"created_at":"2026-05-27T02:05:06.029123+00:00","updated_at":"2026-05-27T02:05:06.029123+00:00"}