{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QJSYDMWESLMEZYRC7K5W7AN7YO","short_pith_number":"pith:QJSYDMWE","schema_version":"1.0","canonical_sha256":"826581b2c492d84ce222fabb6f81bfc3ac21933892d9da3d9a132b9710de2ad4","source":{"kind":"arxiv","id":"2307.12348","version":3},"attestation_state":"computed","paper":{"title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Jianyi Wang, Zongsheng Yue","submitted_at":"2023-07-23T15:10:02Z","abstract_excerpt":"Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice performance to some extent, leading to over-blurry SR results. To address this issue, we propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps, thereby eliminating the need for post-acceleration during inference and its associated performance deterioration. Our method constructs a Markov chain that transfers "},"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":"2307.12348","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-23T15:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"8c2ca18cb8a9f27c6d24b8bf15b6f086441b7d9e1cb84a7d6c40ded9f90fc9fe","abstract_canon_sha256":"07f2047c8bd6684d257aee8f7f1d22b1173b6c6cec82c02b0868fe6dd18c55c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:03.658371Z","signature_b64":"B9WKKy1K/DlQlxQALAsUyAvFI1IPg1XIrLs4iTZkBbK41QH87eRKTiZbT2gk7PyRxEqkCpS6qWXdhW0b4gsrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"826581b2c492d84ce222fabb6f81bfc3ac21933892d9da3d9a132b9710de2ad4","last_reissued_at":"2026-07-05T07:02:03.657878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:03.657878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Jianyi Wang, Zongsheng Yue","submitted_at":"2023-07-23T15:10:02Z","abstract_excerpt":"Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice performance to some extent, leading to over-blurry SR results. To address this issue, we propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps, thereby eliminating the need for post-acceleration during inference and its associated performance deterioration. Our method constructs a Markov chain that transfers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12348","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/2307.12348/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":"2307.12348","created_at":"2026-07-05T07:02:03.657931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12348v3","created_at":"2026-07-05T07:02:03.657931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12348","created_at":"2026-07-05T07:02:03.657931+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJSYDMWESLME","created_at":"2026-07-05T07:02:03.657931+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJSYDMWESLMEZYRC","created_at":"2026-07-05T07:02:03.657931+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJSYDMWE","created_at":"2026-07-05T07:02:03.657931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23902","citing_title":"PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03225","citing_title":"VOSR: A Vision-Only Generative Model for Image Super-Resolution","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26244","citing_title":"MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10439","citing_title":"Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO","json":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO.json","graph_json":"https://pith.science/api/pith-number/QJSYDMWESLMEZYRC7K5W7AN7YO/graph.json","events_json":"https://pith.science/api/pith-number/QJSYDMWESLMEZYRC7K5W7AN7YO/events.json","paper":"https://pith.science/paper/QJSYDMWE"},"agent_actions":{"view_html":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO","download_json":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO.json","view_paper":"https://pith.science/paper/QJSYDMWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12348&json=true","fetch_graph":"https://pith.science/api/pith-number/QJSYDMWESLMEZYRC7K5W7AN7YO/graph.json","fetch_events":"https://pith.science/api/pith-number/QJSYDMWESLMEZYRC7K5W7AN7YO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO/action/storage_attestation","attest_author":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO/action/author_attestation","sign_citation":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO/action/citation_signature","submit_replication":"https://pith.science/pith/QJSYDMWESLMEZYRC7K5W7AN7YO/action/replication_record"}},"created_at":"2026-07-05T07:02:03.657931+00:00","updated_at":"2026-07-05T07:02:03.657931+00:00"}