{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JMOQW2K5UUHG2DULYDQLV7QI7B","short_pith_number":"pith:JMOQW2K5","schema_version":"1.0","canonical_sha256":"4b1d0b695da50e6d0e8bc0e0bafe08f85b128320acabbddd114afcb01d0c6a41","source":{"kind":"arxiv","id":"2503.17488","version":1},"attestation_state":"computed","paper":{"title":"ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Kuanhong Xu, Songtao Wu, Tianwen Zhou","submitted_at":"2025-03-21T18:56:50Z","abstract_excerpt":"Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehazed image to the original one. To mitigate this, we propose ProDehaze, a framework that employs internal image priors to direct external priors encoded in pretrained models. We introduce two types of \\textit{selective} internal priors that prompt the model to concentrate on critical image areas: a Structure-Prompted Restorer in the latent space that emphasizes structure-rich regions, and a Haze-Aware Self-Correcting R"},"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":"2503.17488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T18:56:50Z","cross_cats_sorted":[],"title_canon_sha256":"31835133d9cfc9cacf5c9816654de2cc3eb8d7eabdaec8e5cf0e01e3d81dfc30","abstract_canon_sha256":"55a7a882ae17e67d6404f82dc85d5ff25f3985703b948370f8383e7445a22571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:10.434515Z","signature_b64":"Y8vBAb6ToxZVnblutkNBNasPx2Np/A6bozlhVwt8837a+ExhLqgmBmI9YQtusJl/anIF7WAtauVCuskSCEcyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b1d0b695da50e6d0e8bc0e0bafe08f85b128320acabbddd114afcb01d0c6a41","last_reissued_at":"2026-07-05T10:37:10.433776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:10.433776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Wang, Kuanhong Xu, Songtao Wu, Tianwen Zhou","submitted_at":"2025-03-21T18:56:50Z","abstract_excerpt":"Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehazed image to the original one. To mitigate this, we propose ProDehaze, a framework that employs internal image priors to direct external priors encoded in pretrained models. We introduce two types of \\textit{selective} internal priors that prompt the model to concentrate on critical image areas: a Structure-Prompted Restorer in the latent space that emphasizes structure-rich regions, and a Haze-Aware Self-Correcting R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17488","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/2503.17488/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":"2503.17488","created_at":"2026-07-05T10:37:10.433852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17488v1","created_at":"2026-07-05T10:37:10.433852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17488","created_at":"2026-07-05T10:37:10.433852+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMOQW2K5UUHG","created_at":"2026-07-05T10:37:10.433852+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMOQW2K5UUHG2DUL","created_at":"2026-07-05T10:37:10.433852+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMOQW2K5","created_at":"2026-07-05T10:37:10.433852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B","json":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B.json","graph_json":"https://pith.science/api/pith-number/JMOQW2K5UUHG2DULYDQLV7QI7B/graph.json","events_json":"https://pith.science/api/pith-number/JMOQW2K5UUHG2DULYDQLV7QI7B/events.json","paper":"https://pith.science/paper/JMOQW2K5"},"agent_actions":{"view_html":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B","download_json":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B.json","view_paper":"https://pith.science/paper/JMOQW2K5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17488&json=true","fetch_graph":"https://pith.science/api/pith-number/JMOQW2K5UUHG2DULYDQLV7QI7B/graph.json","fetch_events":"https://pith.science/api/pith-number/JMOQW2K5UUHG2DULYDQLV7QI7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B/action/storage_attestation","attest_author":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B/action/author_attestation","sign_citation":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B/action/citation_signature","submit_replication":"https://pith.science/pith/JMOQW2K5UUHG2DULYDQLV7QI7B/action/replication_record"}},"created_at":"2026-07-05T10:37:10.433852+00:00","updated_at":"2026-07-05T10:37:10.433852+00:00"}