{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N6N2FHNEBSNLLYKDWCEAAVUUKS","short_pith_number":"pith:N6N2FHNE","schema_version":"1.0","canonical_sha256":"6f9ba29da40c9ab5e143b088005694548840c2392d297bebaf56d3d409ae8f2a","source":{"kind":"arxiv","id":"2505.11278","version":1},"attestation_state":"computed","paper":{"title":"A Fourier Space Perspective on Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Edward Meeds, Fabian Falck, Javier Zazo, Kiarash Zahirnia, Rachel Lawrence, Richard Turner, Sushrut Karmalkar, Teodora Pandeva","submitted_at":"2025-05-16T14:13:02Z","abstract_excerpt":"Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials. These modalities share the property of exponentially decaying variance and magnitude in the Fourier domain. Under the standard Denoising Diffusion Probabilistic Models (DDPM) forward process of additive white noise, this property results in high-frequency components being corrupted faster and earlier in terms of their Signal-to-Noise Ratio (SNR) than low-frequency ones. The reverse process then generates low-frequency information before high-frequency details. In this work,"},"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":"2505.11278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-16T14:13:02Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ME"],"title_canon_sha256":"b2e72bafdb08fa0f725d46db4e5f63996a819a0c9c6848631db39b44fc21ddf2","abstract_canon_sha256":"5256953bf20869dcec9687fbefab61e6b5ffa559d48802d6f0cef3d41104a91e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:13.820602Z","signature_b64":"wvrYUVnr2sBlTtEqkk0XjJkTVB4X+j14AyWeEbGuZ7Mz9IdUkGNmq0UBSrS0x/II+hajb7qi3/PxGSWo0ygdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f9ba29da40c9ab5e143b088005694548840c2392d297bebaf56d3d409ae8f2a","last_reissued_at":"2026-07-05T11:04:13.820052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:13.820052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fourier Space Perspective on Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Edward Meeds, Fabian Falck, Javier Zazo, Kiarash Zahirnia, Rachel Lawrence, Richard Turner, Sushrut Karmalkar, Teodora Pandeva","submitted_at":"2025-05-16T14:13:02Z","abstract_excerpt":"Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials. These modalities share the property of exponentially decaying variance and magnitude in the Fourier domain. Under the standard Denoising Diffusion Probabilistic Models (DDPM) forward process of additive white noise, this property results in high-frequency components being corrupted faster and earlier in terms of their Signal-to-Noise Ratio (SNR) than low-frequency ones. The reverse process then generates low-frequency information before high-frequency details. In this work,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11278","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/2505.11278/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":"2505.11278","created_at":"2026-07-05T11:04:13.820112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11278v1","created_at":"2026-07-05T11:04:13.820112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11278","created_at":"2026-07-05T11:04:13.820112+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6N2FHNEBSNL","created_at":"2026-07-05T11:04:13.820112+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6N2FHNEBSNLLYKD","created_at":"2026-07-05T11:04:13.820112+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6N2FHNE","created_at":"2026-07-05T11:04:13.820112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08196","citing_title":"A First-Principles Theory of Slow Thinking and Active Perception","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18765","citing_title":"SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08833","citing_title":"CSFlow: Aligning Flow Matching with Human Contrast Sensitivity","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05239","citing_title":"HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02177","citing_title":"Low-Pass Flow Matching","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26032","citing_title":"Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30387","citing_title":"Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27919","citing_title":"Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30332","citing_title":"Colored Noise Diffusion Sampling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03393","citing_title":"Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18736","citing_title":"Spectral Progressive Diffusion for Efficient Image and Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18736","citing_title":"Spectral Progressive Diffusion for Efficient Image and Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01390","citing_title":"FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10023","citing_title":"FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS","json":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS.json","graph_json":"https://pith.science/api/pith-number/N6N2FHNEBSNLLYKDWCEAAVUUKS/graph.json","events_json":"https://pith.science/api/pith-number/N6N2FHNEBSNLLYKDWCEAAVUUKS/events.json","paper":"https://pith.science/paper/N6N2FHNE"},"agent_actions":{"view_html":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS","download_json":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS.json","view_paper":"https://pith.science/paper/N6N2FHNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11278&json=true","fetch_graph":"https://pith.science/api/pith-number/N6N2FHNEBSNLLYKDWCEAAVUUKS/graph.json","fetch_events":"https://pith.science/api/pith-number/N6N2FHNEBSNLLYKDWCEAAVUUKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS/action/storage_attestation","attest_author":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS/action/author_attestation","sign_citation":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS/action/citation_signature","submit_replication":"https://pith.science/pith/N6N2FHNEBSNLLYKDWCEAAVUUKS/action/replication_record"}},"created_at":"2026-07-05T11:04:13.820112+00:00","updated_at":"2026-07-05T11:04:13.820112+00:00"}