{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RAXJMKPODJO3DTVVMLCT6WHEQK","short_pith_number":"pith:RAXJMKPO","schema_version":"1.0","canonical_sha256":"882e9629ee1a5db1ceb562c53f58e482a7ac6ccec5dcbd023471e642fff6ed6c","source":{"kind":"arxiv","id":"2309.11420","version":1},"attestation_state":"computed","paper":{"title":"Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Song Mei, Yuchen Wu","submitted_at":"2023-09-20T15:51:10Z","abstract_excerpt":"We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of dimensionality for intrinsically high-dimensional data. This limitation is pronounced in graphical models such as Markov random fields, common for image distributions, where the approximation efficiency of score functions remains unestablished.\n  To address this, we observe score functions can often be well-approximated in graphical models through variational "},"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":"2309.11420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-20T15:51:10Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"5044e95cbaca8f7a031f4b4626bb377efa328f43d13820e25b27819e1540f313","abstract_canon_sha256":"6d5265e343d85c08628d915a057deef61e8ec71e0e5b77bc239452e2bcb19dd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:35.996046Z","signature_b64":"bCLbu55PXr+O9GAc7wQjOxnK+BvyxTFaxp4g/W5lwplVo/LVBE1olmJ0avIqg5xpOgFjNapd97Krop70IVrvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"882e9629ee1a5db1ceb562c53f58e482a7ac6ccec5dcbd023471e642fff6ed6c","last_reissued_at":"2026-07-05T06:52:35.995553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:35.995553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Song Mei, Yuchen Wu","submitted_at":"2023-09-20T15:51:10Z","abstract_excerpt":"We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of dimensionality for intrinsically high-dimensional data. This limitation is pronounced in graphical models such as Markov random fields, common for image distributions, where the approximation efficiency of score functions remains unestablished.\n  To address this, we observe score functions can often be well-approximated in graphical models through variational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11420","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/2309.11420/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":"2309.11420","created_at":"2026-07-05T06:52:35.995613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11420v1","created_at":"2026-07-05T06:52:35.995613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11420","created_at":"2026-07-05T06:52:35.995613+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAXJMKPODJO3","created_at":"2026-07-05T06:52:35.995613+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAXJMKPODJO3DTVV","created_at":"2026-07-05T06:52:35.995613+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAXJMKPO","created_at":"2026-07-05T06:52:35.995613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":266,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK","json":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK.json","graph_json":"https://pith.science/api/pith-number/RAXJMKPODJO3DTVVMLCT6WHEQK/graph.json","events_json":"https://pith.science/api/pith-number/RAXJMKPODJO3DTVVMLCT6WHEQK/events.json","paper":"https://pith.science/paper/RAXJMKPO"},"agent_actions":{"view_html":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK","download_json":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK.json","view_paper":"https://pith.science/paper/RAXJMKPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11420&json=true","fetch_graph":"https://pith.science/api/pith-number/RAXJMKPODJO3DTVVMLCT6WHEQK/graph.json","fetch_events":"https://pith.science/api/pith-number/RAXJMKPODJO3DTVVMLCT6WHEQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK/action/storage_attestation","attest_author":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK/action/author_attestation","sign_citation":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK/action/citation_signature","submit_replication":"https://pith.science/pith/RAXJMKPODJO3DTVVMLCT6WHEQK/action/replication_record"}},"created_at":"2026-07-05T06:52:35.995613+00:00","updated_at":"2026-07-05T06:52:35.995613+00:00"}