{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LYRT3A4NTP2O3SHWMHGKQMDBQ7","short_pith_number":"pith:LYRT3A4N","schema_version":"1.0","canonical_sha256":"5e233d838d9bf4edc8f661cca8306187c3e05fa02f725c88519dfe5082768ac6","source":{"kind":"arxiv","id":"2410.02667","version":1},"attestation_state":"computed","paper":{"title":"GUD: Generation with Unified Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mathis Gerdes, Max Welling, Miranda C. N. Cheng","submitted_at":"2024-10-03T16:51:14Z","abstract_excerpt":"Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we revisit diffusion models by exploring three key design aspects: 1) the choice of representation in which the diffusion process operates (e.g. pixel-, PCA-, Fourier-, or wavelet-basis), 2) the prior distribution that data is transformed into during diffusion (e.g. Gaussian with covariance $\\Sigma$), and 3) the scheduling of noise levels applied separately to d"},"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":"2410.02667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T16:51:14Z","cross_cats_sorted":["hep-th","stat.ML"],"title_canon_sha256":"e9266de1d991ee1998e9b386d45920c124ee4c84244ad5c7af4502cbab3b098c","abstract_canon_sha256":"474f97deb37d058c50c62e8e1842ab7b6e38f264c1e2aaedd2194226baeb2f93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:23.958580Z","signature_b64":"ga7LJeqJBPUCMBM/kk/o5Sn+KEf0n/EKpzMxLsbCDGmL5LbAVRMV5qxOd/CRDLkYRe/Skycrxkw41URMvgrECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e233d838d9bf4edc8f661cca8306187c3e05fa02f725c88519dfe5082768ac6","last_reissued_at":"2026-07-05T09:15:23.958125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:23.958125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUD: Generation with Unified Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["hep-th","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mathis Gerdes, Max Welling, Miranda C. N. Cheng","submitted_at":"2024-10-03T16:51:14Z","abstract_excerpt":"Diffusion generative models transform noise into data by inverting a process that progressively adds noise to data samples. Inspired by concepts from the renormalization group in physics, which analyzes systems across different scales, we revisit diffusion models by exploring three key design aspects: 1) the choice of representation in which the diffusion process operates (e.g. pixel-, PCA-, Fourier-, or wavelet-basis), 2) the prior distribution that data is transformed into during diffusion (e.g. Gaussian with covariance $\\Sigma$), and 3) the scheduling of noise levels applied separately to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02667","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/2410.02667/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":"2410.02667","created_at":"2026-07-05T09:15:23.958184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02667v1","created_at":"2026-07-05T09:15:23.958184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02667","created_at":"2026-07-05T09:15:23.958184+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYRT3A4NTP2O","created_at":"2026-07-05T09:15:23.958184+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYRT3A4NTP2O3SHW","created_at":"2026-07-05T09:15:23.958184+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYRT3A4N","created_at":"2026-07-05T09:15:23.958184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07079","citing_title":"AsyncPatch Diffusion: spatially-flexible image generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02177","citing_title":"Low-Pass Flow Matching","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7","json":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7.json","graph_json":"https://pith.science/api/pith-number/LYRT3A4NTP2O3SHWMHGKQMDBQ7/graph.json","events_json":"https://pith.science/api/pith-number/LYRT3A4NTP2O3SHWMHGKQMDBQ7/events.json","paper":"https://pith.science/paper/LYRT3A4N"},"agent_actions":{"view_html":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7","download_json":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7.json","view_paper":"https://pith.science/paper/LYRT3A4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02667&json=true","fetch_graph":"https://pith.science/api/pith-number/LYRT3A4NTP2O3SHWMHGKQMDBQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/LYRT3A4NTP2O3SHWMHGKQMDBQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7/action/storage_attestation","attest_author":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7/action/author_attestation","sign_citation":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7/action/citation_signature","submit_replication":"https://pith.science/pith/LYRT3A4NTP2O3SHWMHGKQMDBQ7/action/replication_record"}},"created_at":"2026-07-05T09:15:23.958184+00:00","updated_at":"2026-07-05T09:15:23.958184+00:00"}