{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2HYRX3DCXRHA5OCAUY6JOUGD3Y","short_pith_number":"pith:2HYRX3DC","schema_version":"1.0","canonical_sha256":"d1f11bec62bc4e0eb840a63c9750c3de009c1b94b6e0f1df3633b71628e21ddc","source":{"kind":"arxiv","id":"2211.09795","version":1},"attestation_state":"computed","paper":{"title":"Conffusion: Confidence Intervals for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eliahu Horwitz, Yedid Hoshen","submitted_at":"2022-11-17T18:58:15Z","abstract_excerpt":"Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees regarding the generated results, often preventing their use in high-stakes situations. To bridge this gap, we construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way o"},"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":"2211.09795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:58:15Z","cross_cats_sorted":[],"title_canon_sha256":"1765150153c236fea09420253755153c1112ef41e948df94245ad90be43cc189","abstract_canon_sha256":"4d6f4b24cab7f0bc35f02dae13d4b5992ff28758ef8562c6e81175ab55558a1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:06.548737Z","signature_b64":"v3hERL4bpuMf12vor1rLnqHuyMHrgPY6UKFeF0LY/nGUTXPewrTiodX1AnD3ZLuINBYAX5u1Q9M2Tu7qH6c3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1f11bec62bc4e0eb840a63c9750c3de009c1b94b6e0f1df3633b71628e21ddc","last_reissued_at":"2026-07-05T05:17:06.548312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:06.548312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conffusion: Confidence Intervals for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eliahu Horwitz, Yedid Hoshen","submitted_at":"2022-11-17T18:58:15Z","abstract_excerpt":"Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion-based methods do not provide statistical guarantees regarding the generated results, often preventing their use in high-stakes situations. To bridge this gap, we construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09795","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/2211.09795/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":"2211.09795","created_at":"2026-07-05T05:17:06.548383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09795v1","created_at":"2026-07-05T05:17:06.548383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09795","created_at":"2026-07-05T05:17:06.548383+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HYRX3DCXRHA","created_at":"2026-07-05T05:17:06.548383+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HYRX3DCXRHA5OCA","created_at":"2026-07-05T05:17:06.548383+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HYRX3DC","created_at":"2026-07-05T05:17:06.548383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23189","citing_title":"Empirical Bayes Conformal Prediction for Vision and Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y","json":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y.json","graph_json":"https://pith.science/api/pith-number/2HYRX3DCXRHA5OCAUY6JOUGD3Y/graph.json","events_json":"https://pith.science/api/pith-number/2HYRX3DCXRHA5OCAUY6JOUGD3Y/events.json","paper":"https://pith.science/paper/2HYRX3DC"},"agent_actions":{"view_html":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y","download_json":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y.json","view_paper":"https://pith.science/paper/2HYRX3DC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09795&json=true","fetch_graph":"https://pith.science/api/pith-number/2HYRX3DCXRHA5OCAUY6JOUGD3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2HYRX3DCXRHA5OCAUY6JOUGD3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y/action/storage_attestation","attest_author":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y/action/author_attestation","sign_citation":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y/action/citation_signature","submit_replication":"https://pith.science/pith/2HYRX3DCXRHA5OCAUY6JOUGD3Y/action/replication_record"}},"created_at":"2026-07-05T05:17:06.548383+00:00","updated_at":"2026-07-05T05:17:06.548383+00:00"}