{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X65R4RV75II36JG4E4CC7QZ4UV","short_pith_number":"pith:X65R4RV7","schema_version":"1.0","canonical_sha256":"bfbb1e46bfea11bf24dc27042fc33ca571e8ee30bcdf7a23a814bbc72c964dae","source":{"kind":"arxiv","id":"2303.08714","version":3},"attestation_state":"computed","paper":{"title":"ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangxing Liu, Jinglin Zhang, LunQian Wang, Shuyao Shang, Xinghua Wang, Zekai Zhang, Zhengyang Shan","submitted_at":"2023-03-15T15:50:11Z","abstract_excerpt":"Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR images"},"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":"2303.08714","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-15T15:50:11Z","cross_cats_sorted":[],"title_canon_sha256":"41e4bbe74132c4d9b040710fbf4bdbde96c175bbcd9681b40f388b549dea1ef7","abstract_canon_sha256":"4e8b25e6323a19391b520b6eca8351606d4f158166e6eff3ee3bb1727f92aae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:20.616262Z","signature_b64":"Kw46AL43BNTH2ArKBfefSnrJQuCMGRBboHEjasoP+nC7gJLe/WEB7sw4OabVZn6lhMv06ekvHqgkJozdE57/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfbb1e46bfea11bf24dc27042fc33ca571e8ee30bcdf7a23a814bbc72c964dae","last_reissued_at":"2026-07-05T07:40:20.615830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:20.615830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangxing Liu, Jinglin Zhang, LunQian Wang, Shuyao Shang, Xinghua Wang, Zekai Zhang, Zhengyang Shan","submitted_at":"2023-03-15T15:50:11Z","abstract_excerpt":"Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08714","kind":"arxiv","version":3},"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/2303.08714/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":"2303.08714","created_at":"2026-07-05T07:40:20.615901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08714v3","created_at":"2026-07-05T07:40:20.615901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08714","created_at":"2026-07-05T07:40:20.615901+00:00"},{"alias_kind":"pith_short_12","alias_value":"X65R4RV75II3","created_at":"2026-07-05T07:40:20.615901+00:00"},{"alias_kind":"pith_short_16","alias_value":"X65R4RV75II36JG4","created_at":"2026-07-05T07:40:20.615901+00:00"},{"alias_kind":"pith_short_8","alias_value":"X65R4RV7","created_at":"2026-07-05T07:40:20.615901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19459","citing_title":"Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines","ref_index":105,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV","json":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV.json","graph_json":"https://pith.science/api/pith-number/X65R4RV75II36JG4E4CC7QZ4UV/graph.json","events_json":"https://pith.science/api/pith-number/X65R4RV75II36JG4E4CC7QZ4UV/events.json","paper":"https://pith.science/paper/X65R4RV7"},"agent_actions":{"view_html":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV","download_json":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV.json","view_paper":"https://pith.science/paper/X65R4RV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08714&json=true","fetch_graph":"https://pith.science/api/pith-number/X65R4RV75II36JG4E4CC7QZ4UV/graph.json","fetch_events":"https://pith.science/api/pith-number/X65R4RV75II36JG4E4CC7QZ4UV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV/action/storage_attestation","attest_author":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV/action/author_attestation","sign_citation":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV/action/citation_signature","submit_replication":"https://pith.science/pith/X65R4RV75II36JG4E4CC7QZ4UV/action/replication_record"}},"created_at":"2026-07-05T07:40:20.615901+00:00","updated_at":"2026-07-05T07:40:20.615901+00:00"}