{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OKMYQVURNEFWTRIHOQAIIRE3TN","short_pith_number":"pith:OKMYQVUR","schema_version":"1.0","canonical_sha256":"7299885691690b69c507740084449b9b7af34ad6dd74e4075ea8d49df7866ba9","source":{"kind":"arxiv","id":"2506.21722","version":1},"attestation_state":"computed","paper":{"title":"Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Xiao, Xin Lu, Xueyang Fu, Yurui Zhu, Zheng-Jun Zha, Zihao Fan","submitted_at":"2025-06-26T19:14:27Z","abstract_excerpt":"While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical application compared to mainstream reconstruction-based general ordinary IR networks. Existing approaches primarily focus on optimizing network architecture and diffusion paths but overlook the integration of the diffusion training paradigm within general ordinary IR frameworks. To address these challenges, this paper elucidates key principles for adapting the diffusion training paradigm to general IR training through syste"},"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":"2506.21722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T19:14:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6868f5771a816817d70195643bb6c086b05990bd11ad997d3089cab887571491","abstract_canon_sha256":"4d2361b063efd2a57861ae87f31851e9ae2152541d5ae9277163adc3cc41efbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:00.076223Z","signature_b64":"fDVMk9YtIS//RNMWbo6e0B4BRBbDVW8zczW+05yw/U2X0rohF305J5YBDAA+FksSz1JbPKfC5apxVZs2cSSbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7299885691690b69c507740084449b9b7af34ad6dd74e4075ea8d49df7866ba9","last_reissued_at":"2026-07-05T11:28:00.075763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:00.075763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Xiao, Xin Lu, Xueyang Fu, Yurui Zhu, Zheng-Jun Zha, Zihao Fan","submitted_at":"2025-06-26T19:14:27Z","abstract_excerpt":"While diffusion models demonstrate strong generative capabilities in image restoration (IR) tasks, their complex architectures and iterative processes limit their practical application compared to mainstream reconstruction-based general ordinary IR networks. Existing approaches primarily focus on optimizing network architecture and diffusion paths but overlook the integration of the diffusion training paradigm within general ordinary IR frameworks. To address these challenges, this paper elucidates key principles for adapting the diffusion training paradigm to general IR training through syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21722","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/2506.21722/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":"2506.21722","created_at":"2026-07-05T11:28:00.075819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21722v1","created_at":"2026-07-05T11:28:00.075819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21722","created_at":"2026-07-05T11:28:00.075819+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKMYQVURNEFW","created_at":"2026-07-05T11:28:00.075819+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKMYQVURNEFWTRIH","created_at":"2026-07-05T11:28:00.075819+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKMYQVUR","created_at":"2026-07-05T11:28:00.075819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06793","citing_title":"AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN","json":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN.json","graph_json":"https://pith.science/api/pith-number/OKMYQVURNEFWTRIHOQAIIRE3TN/graph.json","events_json":"https://pith.science/api/pith-number/OKMYQVURNEFWTRIHOQAIIRE3TN/events.json","paper":"https://pith.science/paper/OKMYQVUR"},"agent_actions":{"view_html":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN","download_json":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN.json","view_paper":"https://pith.science/paper/OKMYQVUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21722&json=true","fetch_graph":"https://pith.science/api/pith-number/OKMYQVURNEFWTRIHOQAIIRE3TN/graph.json","fetch_events":"https://pith.science/api/pith-number/OKMYQVURNEFWTRIHOQAIIRE3TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN/action/storage_attestation","attest_author":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN/action/author_attestation","sign_citation":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN/action/citation_signature","submit_replication":"https://pith.science/pith/OKMYQVURNEFWTRIHOQAIIRE3TN/action/replication_record"}},"created_at":"2026-07-05T11:28:00.075819+00:00","updated_at":"2026-07-05T11:28:00.075819+00:00"}