{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MLTTOECLL5AFTZZLTL6IR6EKB7","short_pith_number":"pith:MLTTOECL","schema_version":"1.0","canonical_sha256":"62e737104b5f4059e72b9afc88f88a0fd6bf681b0db16a4cce3d13d8a7652f77","source":{"kind":"arxiv","id":"2605.24593","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henan Liu, HuaQiu Li, Jing Yang, Mai Xu, XiaoWan Hu","submitted_at":"2026-05-23T14:08:23Z","abstract_excerpt":"Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while overlooking physically consistent priors. The insufficient degradation prompts impose the heavy training burden and high sampling costs during zero-shot diffusion. Moreover, the fixed inference trajectory often collapses to suboptimal solutions under complex corruptions. We observe that heterogeneous degradations can be reparameterized into a minimal set of p"},"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":"2605.24593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T14:08:23Z","cross_cats_sorted":[],"title_canon_sha256":"07ae1a03bf43f66a97028ba71cf55612cd0c50215e913e8a3f81b7ffba00a423","abstract_canon_sha256":"0bb78bad5236c4daecac2fb554e76f649af312477078c5d9cbb79e5d1cc0bbc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:48.033949Z","signature_b64":"kNCEVEzasA7kWBwaJU4jB7xfPkugrTbyFWEaGAXMlrtdXjIbTexYcIY0lmsp2X+Uqzxjv+ZaSynnTm2cvE3UCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62e737104b5f4059e72b9afc88f88a0fd6bf681b0db16a4cce3d13d8a7652f77","last_reissued_at":"2026-05-26T01:03:48.033271Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:48.033271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Henan Liu, HuaQiu Li, Jing Yang, Mai Xu, XiaoWan Hu","submitted_at":"2026-05-23T14:08:23Z","abstract_excerpt":"Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while overlooking physically consistent priors. The insufficient degradation prompts impose the heavy training burden and high sampling costs during zero-shot diffusion. Moreover, the fixed inference trajectory often collapses to suboptimal solutions under complex corruptions. We observe that heterogeneous degradations can be reparameterized into a minimal set of p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24593","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/2605.24593/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":"2605.24593","created_at":"2026-05-26T01:03:48.033389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24593v1","created_at":"2026-05-26T01:03:48.033389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24593","created_at":"2026-05-26T01:03:48.033389+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLTTOECLL5AF","created_at":"2026-05-26T01:03:48.033389+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLTTOECLL5AFTZZL","created_at":"2026-05-26T01:03:48.033389+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLTTOECL","created_at":"2026-05-26T01:03:48.033389+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/MLTTOECLL5AFTZZLTL6IR6EKB7","json":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7.json","graph_json":"https://pith.science/api/pith-number/MLTTOECLL5AFTZZLTL6IR6EKB7/graph.json","events_json":"https://pith.science/api/pith-number/MLTTOECLL5AFTZZLTL6IR6EKB7/events.json","paper":"https://pith.science/paper/MLTTOECL"},"agent_actions":{"view_html":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7","download_json":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7.json","view_paper":"https://pith.science/paper/MLTTOECL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24593&json=true","fetch_graph":"https://pith.science/api/pith-number/MLTTOECLL5AFTZZLTL6IR6EKB7/graph.json","fetch_events":"https://pith.science/api/pith-number/MLTTOECLL5AFTZZLTL6IR6EKB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7/action/storage_attestation","attest_author":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7/action/author_attestation","sign_citation":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7/action/citation_signature","submit_replication":"https://pith.science/pith/MLTTOECLL5AFTZZLTL6IR6EKB7/action/replication_record"}},"created_at":"2026-05-26T01:03:48.033389+00:00","updated_at":"2026-05-26T01:03:48.033389+00:00"}