{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ZI5H6IB3HV56VVFYJDCWINYI4","short_pith_number":"pith:4ZI5H6IB","schema_version":"1.0","canonical_sha256":"e651d3f901d9ebdf56a5c2462b21b8472709d4f29e712447614ddbcd67dfcef2","source":{"kind":"arxiv","id":"2412.09726","version":1},"attestation_state":"computed","paper":{"title":"The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Binxu Wang, John J. Vastola","submitted_at":"2024-12-12T21:31:27Z","abstract_excerpt":"By learning the gradient of smoothed data distributions, diffusion models can iteratively generate samples from complex distributions. The learned score function enables their generalization capabilities, but how the learned score relates to the score of the underlying data manifold remains largely unclear. Here, we aim to elucidate this relationship by comparing learned neural scores to the scores of two kinds of analytically tractable distributions: Gaussians and Gaussian mixtures. The simplicity of the Gaussian model makes it theoretically attractive, and we show that it admits a closed-for"},"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":"2412.09726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T21:31:27Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"7814d561715de3877815dae02ff86ca4582d21f11122f414fc3166c6b7c72984","abstract_canon_sha256":"e675cba7ebb0fbd3c1701dac380a431fb1d2e05bd3a044395d92cde23912584b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:40.572797Z","signature_b64":"Nf6DsHLqYppz9EuvInBhB25rw0EAlZjT2hiQ6tUzg868tUi38qSMcY03OOyng5wW10FotdFRmOjYXFiriUtICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e651d3f901d9ebdf56a5c2462b21b8472709d4f29e712447614ddbcd67dfcef2","last_reissued_at":"2026-07-05T09:48:40.572329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:40.572329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Binxu Wang, John J. Vastola","submitted_at":"2024-12-12T21:31:27Z","abstract_excerpt":"By learning the gradient of smoothed data distributions, diffusion models can iteratively generate samples from complex distributions. The learned score function enables their generalization capabilities, but how the learned score relates to the score of the underlying data manifold remains largely unclear. Here, we aim to elucidate this relationship by comparing learned neural scores to the scores of two kinds of analytically tractable distributions: Gaussians and Gaussian mixtures. The simplicity of the Gaussian model makes it theoretically attractive, and we show that it admits a closed-for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09726","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/2412.09726/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":"2412.09726","created_at":"2026-07-05T09:48:40.572385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09726v1","created_at":"2026-07-05T09:48:40.572385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09726","created_at":"2026-07-05T09:48:40.572385+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZI5H6IB3HV5","created_at":"2026-07-05T09:48:40.572385+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZI5H6IB3HV56VVF","created_at":"2026-07-05T09:48:40.572385+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZI5H6IB","created_at":"2026-07-05T09:48:40.572385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08041","citing_title":"An exact information theory of generalization phase transitions in Bayesian diffusion models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2503.03206","citing_title":"An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.11615","citing_title":"From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04358","citing_title":"Score-based generative emulation of impact-relevant Earth system model outputs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08392","citing_title":"Geometry-Aware Discretization Error of Diffusion Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4","json":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4.json","graph_json":"https://pith.science/api/pith-number/4ZI5H6IB3HV56VVFYJDCWINYI4/graph.json","events_json":"https://pith.science/api/pith-number/4ZI5H6IB3HV56VVFYJDCWINYI4/events.json","paper":"https://pith.science/paper/4ZI5H6IB"},"agent_actions":{"view_html":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4","download_json":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4.json","view_paper":"https://pith.science/paper/4ZI5H6IB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09726&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZI5H6IB3HV56VVFYJDCWINYI4/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZI5H6IB3HV56VVFYJDCWINYI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4/action/storage_attestation","attest_author":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4/action/author_attestation","sign_citation":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4/action/citation_signature","submit_replication":"https://pith.science/pith/4ZI5H6IB3HV56VVFYJDCWINYI4/action/replication_record"}},"created_at":"2026-07-05T09:48:40.572385+00:00","updated_at":"2026-07-05T09:48:40.572385+00:00"}