{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MLXMEZOQ4DZF2CXPD6VABLUVRF","short_pith_number":"pith:MLXMEZOQ","schema_version":"1.0","canonical_sha256":"62eec265d0e0f25d0aef1faa00ae95896a637b02a86807c18db75e58d1cc64b3","source":{"kind":"arxiv","id":"2505.00687","version":1},"attestation_state":"computed","paper":{"title":"GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aditya Arora, Jian Wang, Ruizheng Bai, Sizhuo Ma, Yufei Wang, Zhengzhong Tu","submitted_at":"2025-05-01T17:48:25Z","abstract_excerpt":"In this paper, we propose GuideSR, a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity. Existing diffusion-based SR approaches typically adapt pre-trained generative models to image restoration tasks by adding extra conditioning on a VAE-downsampled representation of the degraded input, which often compromises structural fidelity. GuideSR addresses this limitation by introducing a dual-branch architecture comprising: (1) a Guidance Branch that preserves high-fidelity structures from the original-resolution degraded input, and (2"},"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":"2505.00687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-01T17:48:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9ac1bb946c9157bff2e510305de8eca3d43c1d542385dba48ee9dfd0096c6fe4","abstract_canon_sha256":"2fd8fa9496bc9c6b1f8d8b4b0f3bceb61446eef0664f61a07bb4f1a458458ebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:24.089609Z","signature_b64":"3qVUG7uR/XhxB/5zztGKXFq+K7szY20eps/ERaq5hiKTHEbi+9y36ssePnTJAfbtfH6ktnBxgDBooVuFw87lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62eec265d0e0f25d0aef1faa00ae95896a637b02a86807c18db75e58d1cc64b3","last_reissued_at":"2026-07-05T10:57:24.089129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:24.089129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Aditya Arora, Jian Wang, Ruizheng Bai, Sizhuo Ma, Yufei Wang, Zhengzhong Tu","submitted_at":"2025-05-01T17:48:25Z","abstract_excerpt":"In this paper, we propose GuideSR, a novel single-step diffusion-based image super-resolution (SR) model specifically designed to enhance image fidelity. Existing diffusion-based SR approaches typically adapt pre-trained generative models to image restoration tasks by adding extra conditioning on a VAE-downsampled representation of the degraded input, which often compromises structural fidelity. GuideSR addresses this limitation by introducing a dual-branch architecture comprising: (1) a Guidance Branch that preserves high-fidelity structures from the original-resolution degraded input, and (2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00687","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/2505.00687/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":"2505.00687","created_at":"2026-07-05T10:57:24.089185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00687v1","created_at":"2026-07-05T10:57:24.089185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00687","created_at":"2026-07-05T10:57:24.089185+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLXMEZOQ4DZF","created_at":"2026-07-05T10:57:24.089185+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLXMEZOQ4DZF2CXP","created_at":"2026-07-05T10:57:24.089185+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLXMEZOQ","created_at":"2026-07-05T10:57:24.089185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25457","citing_title":"GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF","json":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF.json","graph_json":"https://pith.science/api/pith-number/MLXMEZOQ4DZF2CXPD6VABLUVRF/graph.json","events_json":"https://pith.science/api/pith-number/MLXMEZOQ4DZF2CXPD6VABLUVRF/events.json","paper":"https://pith.science/paper/MLXMEZOQ"},"agent_actions":{"view_html":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF","download_json":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF.json","view_paper":"https://pith.science/paper/MLXMEZOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00687&json=true","fetch_graph":"https://pith.science/api/pith-number/MLXMEZOQ4DZF2CXPD6VABLUVRF/graph.json","fetch_events":"https://pith.science/api/pith-number/MLXMEZOQ4DZF2CXPD6VABLUVRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF/action/storage_attestation","attest_author":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF/action/author_attestation","sign_citation":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF/action/citation_signature","submit_replication":"https://pith.science/pith/MLXMEZOQ4DZF2CXPD6VABLUVRF/action/replication_record"}},"created_at":"2026-07-05T10:57:24.089185+00:00","updated_at":"2026-07-05T10:57:24.089185+00:00"}