{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AJXEAR3WWTXUV2XASDTCWJBNEH","short_pith_number":"pith:AJXEAR3W","schema_version":"1.0","canonical_sha256":"026e404776b4ef4aeae090e62b242d21c58f33de6de022004ede9a9715fd5858","source":{"kind":"arxiv","id":"2303.02984","version":1},"attestation_state":"computed","paper":{"title":"Learning multi-scale local conditional probability models of images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eero P Simoncelli, Florentin Guth, St\\'ephane Mallat, Zahra Kadkhodaie","submitted_at":"2023-03-06T09:23:14Z","abstract_excerpt":"Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods. But the means by which these networks capture complex global statistical structure, apparently without suffering from the curse of dimensionality, remain a mystery. To study this, we incorporate diffusion methods into a multi-scale decomposition, reducing dimensionality by assuming a stationary local Markov model for wavelet coefficients conditioned on coarser-scale coefficients. We instantiate this model using convolution"},"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":"2303.02984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-06T09:23:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55f268e54c278f450a63eaef16d080b78800a97e42ed43c74251acb506a6385e","abstract_canon_sha256":"c220bae2ab1373422f61a0c078a98c2568be69162de8f8ba0a6164894f2588d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:17.942198Z","signature_b64":"WTMkGGrAfli9WmW25jf4wDwWEEcGILJKiykQnKcAFSXH9DA7oso6HdT6Hnv2Lu5nuX6RWUYvQLLmXGsHSjIDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"026e404776b4ef4aeae090e62b242d21c58f33de6de022004ede9a9715fd5858","last_reissued_at":"2026-07-05T05:48:17.941633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:17.941633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning multi-scale local conditional probability models of images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eero P Simoncelli, Florentin Guth, St\\'ephane Mallat, Zahra Kadkhodaie","submitted_at":"2023-03-06T09:23:14Z","abstract_excerpt":"Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods. But the means by which these networks capture complex global statistical structure, apparently without suffering from the curse of dimensionality, remain a mystery. To study this, we incorporate diffusion methods into a multi-scale decomposition, reducing dimensionality by assuming a stationary local Markov model for wavelet coefficients conditioned on coarser-scale coefficients. We instantiate this model using convolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02984","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/2303.02984/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":"2303.02984","created_at":"2026-07-05T05:48:17.941692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02984v1","created_at":"2026-07-05T05:48:17.941692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02984","created_at":"2026-07-05T05:48:17.941692+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJXEAR3WWTXU","created_at":"2026-07-05T05:48:17.941692+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJXEAR3WWTXUV2XA","created_at":"2026-07-05T05:48:17.941692+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJXEAR3W","created_at":"2026-07-05T05:48:17.941692+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":248,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":248,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH","json":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH.json","graph_json":"https://pith.science/api/pith-number/AJXEAR3WWTXUV2XASDTCWJBNEH/graph.json","events_json":"https://pith.science/api/pith-number/AJXEAR3WWTXUV2XASDTCWJBNEH/events.json","paper":"https://pith.science/paper/AJXEAR3W"},"agent_actions":{"view_html":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH","download_json":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH.json","view_paper":"https://pith.science/paper/AJXEAR3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02984&json=true","fetch_graph":"https://pith.science/api/pith-number/AJXEAR3WWTXUV2XASDTCWJBNEH/graph.json","fetch_events":"https://pith.science/api/pith-number/AJXEAR3WWTXUV2XASDTCWJBNEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH/action/storage_attestation","attest_author":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH/action/author_attestation","sign_citation":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH/action/citation_signature","submit_replication":"https://pith.science/pith/AJXEAR3WWTXUV2XASDTCWJBNEH/action/replication_record"}},"created_at":"2026-07-05T05:48:17.941692+00:00","updated_at":"2026-07-05T05:48:17.941692+00:00"}