{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GMRPA43MFG7FCJS63QGNN64SQV","short_pith_number":"pith:GMRPA43M","schema_version":"1.0","canonical_sha256":"3322f0736c29be51265edc0cd6fb92857eb1140c3865ec89861a0cd4515f2264","source":{"kind":"arxiv","id":"2607.23226","version":1},"attestation_state":"computed","paper":{"title":"From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Chunlin Wu, Jinshu Huang, Yiming Jiang","submitted_at":"2026-07-25T14:24:38Z","abstract_excerpt":"Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped. Existing sampling analyses often evaluate the generative performance conditional on an oracle score or a pre-specified error threshold. In this work, we establish a unified convergence and generalization framework for score-based diffusion models parameterized by practical ResNet-type architectures. We analyze the generalization and convergence properti"},"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":"2607.23226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-25T14:24:38Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"087448b1bd6e15d9e43f3dd1ddb359443814d10a94d5747c1eb63de0f8390657","abstract_canon_sha256":"13c007a828d54e8edb362196b9e9e0847d0bfd4eba3564e7ef81e877267acda1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:42.903298Z","signature_b64":"lLqfniiKjBSJu2yJaRw1RTWQCeONjIKvEzuYZH+87WgM23rca7LNJVeUU/vkEBYKwtgKicI4z5tk9LMP/xe7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3322f0736c29be51265edc0cd6fb92857eb1140c3865ec89861a0cd4515f2264","last_reissued_at":"2026-07-28T01:22:42.902521Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:42.902521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Chunlin Wu, Jinshu Huang, Yiming Jiang","submitted_at":"2026-07-25T14:24:38Z","abstract_excerpt":"Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped. Existing sampling analyses often evaluate the generative performance conditional on an oracle score or a pre-specified error threshold. In this work, we establish a unified convergence and generalization framework for score-based diffusion models parameterized by practical ResNet-type architectures. We analyze the generalization and convergence properti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23226","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/2607.23226/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":"2607.23226","created_at":"2026-07-28T01:22:42.902906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23226v1","created_at":"2026-07-28T01:22:42.902906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23226","created_at":"2026-07-28T01:22:42.902906+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMRPA43MFG7F","created_at":"2026-07-28T01:22:42.902906+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMRPA43MFG7FCJS6","created_at":"2026-07-28T01:22:42.902906+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMRPA43M","created_at":"2026-07-28T01:22:42.902906+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/GMRPA43MFG7FCJS63QGNN64SQV","json":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV.json","graph_json":"https://pith.science/api/pith-number/GMRPA43MFG7FCJS63QGNN64SQV/graph.json","events_json":"https://pith.science/api/pith-number/GMRPA43MFG7FCJS63QGNN64SQV/events.json","paper":"https://pith.science/paper/GMRPA43M"},"agent_actions":{"view_html":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV","download_json":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV.json","view_paper":"https://pith.science/paper/GMRPA43M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23226&json=true","fetch_graph":"https://pith.science/api/pith-number/GMRPA43MFG7FCJS63QGNN64SQV/graph.json","fetch_events":"https://pith.science/api/pith-number/GMRPA43MFG7FCJS63QGNN64SQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV/action/storage_attestation","attest_author":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV/action/author_attestation","sign_citation":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV/action/citation_signature","submit_replication":"https://pith.science/pith/GMRPA43MFG7FCJS63QGNN64SQV/action/replication_record"}},"created_at":"2026-07-28T01:22:42.902906+00:00","updated_at":"2026-07-28T01:22:42.902906+00:00"}