{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GEY2JBYJ7VEKPPDMVN6B4JBOJP","short_pith_number":"pith:GEY2JBYJ","schema_version":"1.0","canonical_sha256":"3131a48709fd48a7bc6cab7c1e242e4bd2554ec45a1e75e2bf7b4a02ca4180f5","source":{"kind":"arxiv","id":"2607.26285","version":1},"attestation_state":"computed","paper":{"title":"Denoising growth complexity: Data geometry and certified schedules for diffusion sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Martin J. Wainwright","submitted_at":"2026-07-28T21:26:16Z","abstract_excerpt":"Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional settings, and the practical one of designing algorithms with certified performance guarantees. We show that these questions are intimately connected via the \\emph{denoising growth complexity} ($\\mathsf{DGC}$). It is a geometric measure defined by a log-time weighted integral of the derivative of the denoising mean-squared error along the Gaussian heat flow. We show how the $\\mathsf{DGC}$ increments lead to a simple and explicit bound on the KL erro"},"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":"2607.26285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2026-07-28T21:26:16Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.ML","stat.TH"],"title_canon_sha256":"b62909b38a10a759353e91b267bc148a49aae3c92ce8fca5e0784e36203384de","abstract_canon_sha256":"e9f3908f7855f3fa9048ba1f68906032d372b55d23766556f3a9551e577b1989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3131a48709fd48a7bc6cab7c1e242e4bd2554ec45a1e75e2bf7b4a02ca4180f5","last_reissued_at":"2026-07-30T01:17:55.149289Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:17:55.149289Z"},"graph_snapshot":{"paper":{"title":"Denoising growth complexity: Data geometry and certified schedules for diffusion sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Martin J. Wainwright","submitted_at":"2026-07-28T21:26:16Z","abstract_excerpt":"Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional settings, and the practical one of designing algorithms with certified performance guarantees. We show that these questions are intimately connected via the \\emph{denoising growth complexity} ($\\mathsf{DGC}$). It is a geometric measure defined by a log-time weighted integral of the derivative of the denoising mean-squared error along the Gaussian heat flow. We show how the $\\mathsf{DGC}$ increments lead to a simple and explicit bound on the KL erro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26285","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/2607.26285/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":"2607.26285","created_at":"2026-07-30T01:17:55.154323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26285v1","created_at":"2026-07-30T01:17:55.154323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26285","created_at":"2026-07-30T01:17:55.154323+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEY2JBYJ7VEK","created_at":"2026-07-30T01:17:55.154323+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEY2JBYJ7VEKPPDM","created_at":"2026-07-30T01:17:55.154323+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEY2JBYJ","created_at":"2026-07-30T01:17:55.154323+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/GEY2JBYJ7VEKPPDMVN6B4JBOJP","json":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP.json","graph_json":"https://pith.science/api/pith-number/GEY2JBYJ7VEKPPDMVN6B4JBOJP/graph.json","events_json":"https://pith.science/api/pith-number/GEY2JBYJ7VEKPPDMVN6B4JBOJP/events.json","paper":"https://pith.science/paper/GEY2JBYJ"},"agent_actions":{"view_html":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP","download_json":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP.json","view_paper":"https://pith.science/paper/GEY2JBYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26285&json=true","fetch_graph":"https://pith.science/api/pith-number/GEY2JBYJ7VEKPPDMVN6B4JBOJP/graph.json","fetch_events":"https://pith.science/api/pith-number/GEY2JBYJ7VEKPPDMVN6B4JBOJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP/action/storage_attestation","attest_author":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP/action/author_attestation","sign_citation":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP/action/citation_signature","submit_replication":"https://pith.science/pith/GEY2JBYJ7VEKPPDMVN6B4JBOJP/action/replication_record"}},"created_at":"2026-07-30T01:17:55.154323+00:00","updated_at":"2026-07-30T01:17:55.154323+00:00"}