{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R5OOHUE7RKKSPKIJRBB3PWKSBY","short_pith_number":"pith:R5OOHUE7","schema_version":"1.0","canonical_sha256":"8f5ce3d09f8a9527a9098843b7d9520e1559f75a9cbcf57c81f7e679b8046006","source":{"kind":"arxiv","id":"2504.17804","version":1},"attestation_state":"computed","paper":{"title":"Spectral Dictionary Learning for Generative Image Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Kiruluta","submitted_at":"2025-04-21T01:11:17Z","abstract_excerpt":"We propose a novel spectral generative model for image synthesis that departs radically from the common variational, adversarial, and diffusion paradigms. In our approach, images, after being flattened into one-dimensional signals, are reconstructed as linear combinations of a set of learned spectral basis functions, where each basis is explicitly parameterized in terms of frequency, phase, and amplitude. The model jointly learns a global spectral dictionary with time-varying modulations and per-image mixing coefficients that quantify the contributions of each spectral component. Subsequently,"},"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":"2504.17804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T01:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"ca0e4802146069cac674b688f5a96cb8a1fad1e3a3dd5ad370752d9f6e387809","abstract_canon_sha256":"103eeb190d060350c16e160505cb4cc589c743dbcda921868894fb7a55f2a546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:56.258049Z","signature_b64":"uYl/w8sLNvmRA7yB3Ty0uj3FGV+b4OB31dFtxdaZ59rBUIo5ZORRwqTs9rP76OiWnssbKQrnDywXJe8Sa1+KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f5ce3d09f8a9527a9098843b7d9520e1559f75a9cbcf57c81f7e679b8046006","last_reissued_at":"2026-07-05T10:53:56.257545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:56.257545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Dictionary Learning for Generative Image Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Kiruluta","submitted_at":"2025-04-21T01:11:17Z","abstract_excerpt":"We propose a novel spectral generative model for image synthesis that departs radically from the common variational, adversarial, and diffusion paradigms. In our approach, images, after being flattened into one-dimensional signals, are reconstructed as linear combinations of a set of learned spectral basis functions, where each basis is explicitly parameterized in terms of frequency, phase, and amplitude. The model jointly learns a global spectral dictionary with time-varying modulations and per-image mixing coefficients that quantify the contributions of each spectral component. Subsequently,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17804","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/2504.17804/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":"2504.17804","created_at":"2026-07-05T10:53:56.257603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17804v1","created_at":"2026-07-05T10:53:56.257603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17804","created_at":"2026-07-05T10:53:56.257603+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5OOHUE7RKKS","created_at":"2026-07-05T10:53:56.257603+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5OOHUE7RKKSPKIJ","created_at":"2026-07-05T10:53:56.257603+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5OOHUE7","created_at":"2026-07-05T10:53:56.257603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18943","citing_title":"From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY","json":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY.json","graph_json":"https://pith.science/api/pith-number/R5OOHUE7RKKSPKIJRBB3PWKSBY/graph.json","events_json":"https://pith.science/api/pith-number/R5OOHUE7RKKSPKIJRBB3PWKSBY/events.json","paper":"https://pith.science/paper/R5OOHUE7"},"agent_actions":{"view_html":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY","download_json":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY.json","view_paper":"https://pith.science/paper/R5OOHUE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17804&json=true","fetch_graph":"https://pith.science/api/pith-number/R5OOHUE7RKKSPKIJRBB3PWKSBY/graph.json","fetch_events":"https://pith.science/api/pith-number/R5OOHUE7RKKSPKIJRBB3PWKSBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY/action/storage_attestation","attest_author":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY/action/author_attestation","sign_citation":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY/action/citation_signature","submit_replication":"https://pith.science/pith/R5OOHUE7RKKSPKIJRBB3PWKSBY/action/replication_record"}},"created_at":"2026-07-05T10:53:56.257603+00:00","updated_at":"2026-07-05T10:53:56.257603+00:00"}