{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CK5GBS5VD2R5OG3K6IV4YZIMQJ","short_pith_number":"pith:CK5GBS5V","schema_version":"1.0","canonical_sha256":"12ba60cbb51ea3d71b6af22bcc650c8253bec126eb4844872f354f24a6cb89b7","source":{"kind":"arxiv","id":"2308.12355","version":2},"attestation_state":"computed","paper":{"title":"Renormalizing Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-lat"],"primary_cat":"hep-th","authors_text":"Jordan Cotler, Semon Rezchikov","submitted_at":"2023-08-23T18:02:31Z","abstract_excerpt":"We explain how to use diffusion models to learn inverse renormalization group flows of statistical and quantum field theories. Diffusion models are a class of machine learning models which have been used to generate samples from complex distributions, such as the distribution of natural images. These models achieve sample generation by learning the inverse process to a diffusion process which adds noise to the data until the distribution of the data is pure noise. Nonperturbative renormalization group schemes in physics can naturally be written as diffusion processes in the space of fields. We"},"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":"2308.12355","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-th","submitted_at":"2023-08-23T18:02:31Z","cross_cats_sorted":["cs.LG","hep-lat"],"title_canon_sha256":"e821cf6b2f607f3d10b68a3efe212683a64c44136bbdc24bb63cb998659eec6f","abstract_canon_sha256":"bf7854c96caea3aad84e04ca019d7b97b00915810fae7bc183f9a606dd2e0367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:10.953093Z","signature_b64":"D8UqPifUedtvQjQOFpxeq57sKIKh3LHlR8TxIOBaFwndI2VwhufyqZ3NV6DWj63HM6OPG5HwbxkvQr7tRKEMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ba60cbb51ea3d71b6af22bcc650c8253bec126eb4844872f354f24a6cb89b7","last_reissued_at":"2026-07-05T06:48:10.952614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:10.952614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Renormalizing Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-lat"],"primary_cat":"hep-th","authors_text":"Jordan Cotler, Semon Rezchikov","submitted_at":"2023-08-23T18:02:31Z","abstract_excerpt":"We explain how to use diffusion models to learn inverse renormalization group flows of statistical and quantum field theories. Diffusion models are a class of machine learning models which have been used to generate samples from complex distributions, such as the distribution of natural images. These models achieve sample generation by learning the inverse process to a diffusion process which adds noise to the data until the distribution of the data is pure noise. Nonperturbative renormalization group schemes in physics can naturally be written as diffusion processes in the space of fields. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12355","kind":"arxiv","version":2},"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/2308.12355/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":"2308.12355","created_at":"2026-07-05T06:48:10.952670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12355v2","created_at":"2026-07-05T06:48:10.952670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12355","created_at":"2026-07-05T06:48:10.952670+00:00"},{"alias_kind":"pith_short_12","alias_value":"CK5GBS5VD2R5","created_at":"2026-07-05T06:48:10.952670+00:00"},{"alias_kind":"pith_short_16","alias_value":"CK5GBS5VD2R5OG3K","created_at":"2026-07-05T06:48:10.952670+00:00"},{"alias_kind":"pith_short_8","alias_value":"CK5GBS5V","created_at":"2026-07-05T06:48:10.952670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26032","citing_title":"Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12597","citing_title":"The critical slowing down in diffusion models","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ","json":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ.json","graph_json":"https://pith.science/api/pith-number/CK5GBS5VD2R5OG3K6IV4YZIMQJ/graph.json","events_json":"https://pith.science/api/pith-number/CK5GBS5VD2R5OG3K6IV4YZIMQJ/events.json","paper":"https://pith.science/paper/CK5GBS5V"},"agent_actions":{"view_html":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ","download_json":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ.json","view_paper":"https://pith.science/paper/CK5GBS5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12355&json=true","fetch_graph":"https://pith.science/api/pith-number/CK5GBS5VD2R5OG3K6IV4YZIMQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CK5GBS5VD2R5OG3K6IV4YZIMQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ/action/storage_attestation","attest_author":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ/action/author_attestation","sign_citation":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ/action/citation_signature","submit_replication":"https://pith.science/pith/CK5GBS5VD2R5OG3K6IV4YZIMQJ/action/replication_record"}},"created_at":"2026-07-05T06:48:10.952670+00:00","updated_at":"2026-07-05T06:48:10.952670+00:00"}