{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DUZJ2TDPDYJGHRUMPJZGILTZR7","short_pith_number":"pith:DUZJ2TDP","schema_version":"1.0","canonical_sha256":"1d329d4c6f1e1263c68c7a72642e798ffdeb51dbd81a61f18e08bd82bd74fd7f","source":{"kind":"arxiv","id":"2402.01965","version":3},"attestation_state":"computed","paper":{"title":"Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Fangzhao Zhang, Mert Pilanci","submitted_at":"2024-02-03T00:20:25Z","abstract_excerpt":"Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In this study, we present a theoretical framework to analyze two-layer neural network-based diffusion models by reframing score matching and denoising score matching as convex optimization. We prove that training shallow neural networks for score prediction can be done by solving a single convex program. Although most analyses of diffusion models operate in the a"},"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":"2402.01965","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T00:20:25Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c1b4181552f8b85a38110acc02cd26c3a392cb24992fe2db95f2609e6dc34859","abstract_canon_sha256":"0ea3e7ab0929a91e33f4a517ad8e1c0d1ea8abf347b953f9e708d7f517083363"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:49.160942Z","signature_b64":"spqnInFHlZ6446gecQ1dNUg0u3Cqz+JttP4XoBBHJjRvNrwBXOfwJ0eoZC0CoIvYAo89hRGJVBIGEDPwl+VwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d329d4c6f1e1263c68c7a72642e798ffdeb51dbd81a61f18e08bd82bd74fd7f","last_reissued_at":"2026-07-05T08:21:49.160456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:49.160456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Fangzhao Zhang, Mert Pilanci","submitted_at":"2024-02-03T00:20:25Z","abstract_excerpt":"Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In this study, we present a theoretical framework to analyze two-layer neural network-based diffusion models by reframing score matching and denoising score matching as convex optimization. We prove that training shallow neural networks for score prediction can be done by solving a single convex program. Although most analyses of diffusion models operate in the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01965","kind":"arxiv","version":3},"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/2402.01965/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":"2402.01965","created_at":"2026-07-05T08:21:49.160517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01965v3","created_at":"2026-07-05T08:21:49.160517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01965","created_at":"2026-07-05T08:21:49.160517+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUZJ2TDPDYJG","created_at":"2026-07-05T08:21:49.160517+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUZJ2TDPDYJGHRUM","created_at":"2026-07-05T08:21:49.160517+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUZJ2TDP","created_at":"2026-07-05T08:21:49.160517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18344","citing_title":"Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7","json":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7.json","graph_json":"https://pith.science/api/pith-number/DUZJ2TDPDYJGHRUMPJZGILTZR7/graph.json","events_json":"https://pith.science/api/pith-number/DUZJ2TDPDYJGHRUMPJZGILTZR7/events.json","paper":"https://pith.science/paper/DUZJ2TDP"},"agent_actions":{"view_html":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7","download_json":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7.json","view_paper":"https://pith.science/paper/DUZJ2TDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01965&json=true","fetch_graph":"https://pith.science/api/pith-number/DUZJ2TDPDYJGHRUMPJZGILTZR7/graph.json","fetch_events":"https://pith.science/api/pith-number/DUZJ2TDPDYJGHRUMPJZGILTZR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7/action/storage_attestation","attest_author":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7/action/author_attestation","sign_citation":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7/action/citation_signature","submit_replication":"https://pith.science/pith/DUZJ2TDPDYJGHRUMPJZGILTZR7/action/replication_record"}},"created_at":"2026-07-05T08:21:49.160517+00:00","updated_at":"2026-07-05T08:21:49.160517+00:00"}