{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6XEMAKQAAQZRHT3NKYE3MJGCNJ","short_pith_number":"pith:6XEMAKQA","schema_version":"1.0","canonical_sha256":"f5c8c02a00043313cf6d5609b624c26a6feab427fea7d3b615b36685d291e164","source":{"kind":"arxiv","id":"2504.03821","version":1},"attestation_state":"computed","paper":{"title":"A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Lemos, Andrew Kiruluta","submitted_at":"2025-04-04T17:11:04Z","abstract_excerpt":"We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial localization. In contrast to conventional diffusion models that rely exclusively on additive noise in pixel space, our approach leverages a multi-transform that combines wavelet sub-band decomposition with partial Fourier steps. This strategy progressively degrades and then reconstructs images in a hybrid spectral domain during the forward and reverse diffusion processe"},"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":"2504.03821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-04T17:11:04Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ff8a12d3544bfdc813e04cf6b4ebbf40e4c317af123c9d772e9ed38c781a6be9","abstract_canon_sha256":"02f41f43e64d999f652fee651d3f698e977498c6e73e7bb40bb791626f943513"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:49.196482Z","signature_b64":"Y/v0b0v9N6lLSd8q64DNhOgFiVBqvVvpshuzJ1KGPXwLobmXL+F3WafSQDLSOYb4mIQIEwEP7xlSSO964qn1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c8c02a00043313cf6d5609b624c26a6feab427fea7d3b615b36685d291e164","last_reissued_at":"2026-07-05T10:44:49.196009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:49.196009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas Lemos, Andrew Kiruluta","submitted_at":"2025-04-04T17:11:04Z","abstract_excerpt":"We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial localization. In contrast to conventional diffusion models that rely exclusively on additive noise in pixel space, our approach leverages a multi-transform that combines wavelet sub-band decomposition with partial Fourier steps. This strategy progressively degrades and then reconstructs images in a hybrid spectral domain during the forward and reverse diffusion processe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03821","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/2504.03821/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":"2504.03821","created_at":"2026-07-05T10:44:49.196063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03821v1","created_at":"2026-07-05T10:44:49.196063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03821","created_at":"2026-07-05T10:44:49.196063+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XEMAKQAAQZR","created_at":"2026-07-05T10:44:49.196063+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XEMAKQAAQZRHT3N","created_at":"2026-07-05T10:44:49.196063+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XEMAKQA","created_at":"2026-07-05T10:44:49.196063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19514","citing_title":"Wavelet Logic Machines: Learning and Reasoning in the Spectral Domain Without Neural Networks","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ","json":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ.json","graph_json":"https://pith.science/api/pith-number/6XEMAKQAAQZRHT3NKYE3MJGCNJ/graph.json","events_json":"https://pith.science/api/pith-number/6XEMAKQAAQZRHT3NKYE3MJGCNJ/events.json","paper":"https://pith.science/paper/6XEMAKQA"},"agent_actions":{"view_html":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ","download_json":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ.json","view_paper":"https://pith.science/paper/6XEMAKQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03821&json=true","fetch_graph":"https://pith.science/api/pith-number/6XEMAKQAAQZRHT3NKYE3MJGCNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6XEMAKQAAQZRHT3NKYE3MJGCNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ/action/storage_attestation","attest_author":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ/action/author_attestation","sign_citation":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ/action/citation_signature","submit_replication":"https://pith.science/pith/6XEMAKQAAQZRHT3NKYE3MJGCNJ/action/replication_record"}},"created_at":"2026-07-05T10:44:49.196063+00:00","updated_at":"2026-07-05T10:44:49.196063+00:00"}