{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3K6WDTWBAU2VBV7QVESGE5HRQB","short_pith_number":"pith:3K6WDTWB","schema_version":"1.0","canonical_sha256":"dabd61cec1053550d7f0a9246274f1807655efcbade9dd779f38fc4ba46d53ca","source":{"kind":"arxiv","id":"2607.00773","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Andi Han, Huanjian Zhou, Masashi Sugiyama, Wei Huang, Yu Yao","submitted_at":"2026-07-01T10:59:33Z","abstract_excerpt":"Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we parallelize the mainstream $\\tau$-leaping algorithm for absorbing discrete diffusion in a Continuous-Time Markov Chain (CTMC) framework. By leveraging the continuous-time stochastic integral form of the $\\tau$-leaping algorithm and the Picard iteration method, we achieve parallel-in-time sampling acceleration and provide a proof of exponential-factorial convergence for our al"},"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":"2607.00773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T10:59:33Z","cross_cats_sorted":["cs.DC","cs.DS","cs.NA","math.NA"],"title_canon_sha256":"2679fec7d9ded4fecf9ff7633807f4e2fb82b5e669a7f06626df6614a9841986","abstract_canon_sha256":"f55bb40a94719ed8b5168c9bafa2612f45f9ab077a0bd4476b4fc84d234edb87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:55.053592Z","signature_b64":"KvcnmKlH7NNHeBpsPSNBTfOU+CAV1hH6L+RhBu5KMTacVpJ69a7zi0sndOjnrC/JM04z/X0pBKkyfcKVUjhXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dabd61cec1053550d7f0a9246274f1807655efcbade9dd779f38fc4ba46d53ca","last_reissued_at":"2026-07-02T01:17:55.053057Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:55.053057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Andi Han, Huanjian Zhou, Masashi Sugiyama, Wei Huang, Yu Yao","submitted_at":"2026-07-01T10:59:33Z","abstract_excerpt":"Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we parallelize the mainstream $\\tau$-leaping algorithm for absorbing discrete diffusion in a Continuous-Time Markov Chain (CTMC) framework. By leveraging the continuous-time stochastic integral form of the $\\tau$-leaping algorithm and the Picard iteration method, we achieve parallel-in-time sampling acceleration and provide a proof of exponential-factorial convergence for our al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00773","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/2607.00773/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":"2607.00773","created_at":"2026-07-02T01:17:55.053124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00773v1","created_at":"2026-07-02T01:17:55.053124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00773","created_at":"2026-07-02T01:17:55.053124+00:00"},{"alias_kind":"pith_short_12","alias_value":"3K6WDTWBAU2V","created_at":"2026-07-02T01:17:55.053124+00:00"},{"alias_kind":"pith_short_16","alias_value":"3K6WDTWBAU2VBV7Q","created_at":"2026-07-02T01:17:55.053124+00:00"},{"alias_kind":"pith_short_8","alias_value":"3K6WDTWB","created_at":"2026-07-02T01:17:55.053124+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/3K6WDTWBAU2VBV7QVESGE5HRQB","json":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB.json","graph_json":"https://pith.science/api/pith-number/3K6WDTWBAU2VBV7QVESGE5HRQB/graph.json","events_json":"https://pith.science/api/pith-number/3K6WDTWBAU2VBV7QVESGE5HRQB/events.json","paper":"https://pith.science/paper/3K6WDTWB"},"agent_actions":{"view_html":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB","download_json":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB.json","view_paper":"https://pith.science/paper/3K6WDTWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00773&json=true","fetch_graph":"https://pith.science/api/pith-number/3K6WDTWBAU2VBV7QVESGE5HRQB/graph.json","fetch_events":"https://pith.science/api/pith-number/3K6WDTWBAU2VBV7QVESGE5HRQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB/action/storage_attestation","attest_author":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB/action/author_attestation","sign_citation":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB/action/citation_signature","submit_replication":"https://pith.science/pith/3K6WDTWBAU2VBV7QVESGE5HRQB/action/replication_record"}},"created_at":"2026-07-02T01:17:55.053124+00:00","updated_at":"2026-07-02T01:17:55.053124+00:00"}