{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AFNTN6HINHJ5X6A7X432XR37L6","short_pith_number":"pith:AFNTN6HI","schema_version":"1.0","canonical_sha256":"015b36f8e869d3dbf81fbf37abc77f5f8be8984534bab12cf6e8dc5795840964","source":{"kind":"arxiv","id":"2208.09392","version":1},"attestation_state":"computed","paper":{"title":"Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arpit Bansal, Eitan Borgnia, Furong Huang, Hamid Kazemi, Hong-Min Chu, Jie S. Li, Jonas Geiping, Micah Goldblum, Tom Goldstein","submitted_at":"2022-08-19T15:18:39Z","abstract_excerpt":"Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully"},"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":"2208.09392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T15:18:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6d03a42c3617a9cff45df0774d410676710d7dbf093bf8f4b9a50f76d95d61c","abstract_canon_sha256":"ebb8e5030355fb93000e11480cf2e0381a3660ca88b25eac2cb6848e271cffd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:59.496071Z","signature_b64":"Teq60EOPU2reNhjQlSD957AG1GBon2ka+KEPu2GilRT6PrklbhgtO/41jWNSv7rRE7sxCZOT2zUjKdD2u2bNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"015b36f8e869d3dbf81fbf37abc77f5f8be8984534bab12cf6e8dc5795840964","last_reissued_at":"2026-07-05T04:49:59.495647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:59.495647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arpit Bansal, Eitan Borgnia, Furong Huang, Hamid Kazemi, Hong-Min Chu, Jie S. Li, Jonas Geiping, Micah Goldblum, Tom Goldstein","submitted_at":"2022-08-19T15:18:39Z","abstract_excerpt":"Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09392","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/2208.09392/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":"2208.09392","created_at":"2026-07-05T04:49:59.495707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09392v1","created_at":"2026-07-05T04:49:59.495707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09392","created_at":"2026-07-05T04:49:59.495707+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFNTN6HINHJ5","created_at":"2026-07-05T04:49:59.495707+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFNTN6HINHJ5X6A7","created_at":"2026-07-05T04:49:59.495707+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFNTN6HI","created_at":"2026-07-05T04:49:59.495707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04165","citing_title":"CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26446","citing_title":"DDGAD: Trajectory Dynamics for Diffusion-Based Graph Anomaly Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01048","citing_title":"Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2312.03798","citing_title":"Single Image Reflection Removal with Patch Reflectance Prior","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22397","citing_title":"HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2209.15571","citing_title":"Building Normalizing Flows with Stochastic Interpolants","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2209.15571","citing_title":"Building Normalizing Flows with Stochastic Interpolants","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6","json":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6.json","graph_json":"https://pith.science/api/pith-number/AFNTN6HINHJ5X6A7X432XR37L6/graph.json","events_json":"https://pith.science/api/pith-number/AFNTN6HINHJ5X6A7X432XR37L6/events.json","paper":"https://pith.science/paper/AFNTN6HI"},"agent_actions":{"view_html":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6","download_json":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6.json","view_paper":"https://pith.science/paper/AFNTN6HI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09392&json=true","fetch_graph":"https://pith.science/api/pith-number/AFNTN6HINHJ5X6A7X432XR37L6/graph.json","fetch_events":"https://pith.science/api/pith-number/AFNTN6HINHJ5X6A7X432XR37L6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6/action/storage_attestation","attest_author":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6/action/author_attestation","sign_citation":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6/action/citation_signature","submit_replication":"https://pith.science/pith/AFNTN6HINHJ5X6A7X432XR37L6/action/replication_record"}},"created_at":"2026-07-05T04:49:59.495707+00:00","updated_at":"2026-07-05T04:49:59.495707+00:00"}