{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PCLHJCOOT7R6OJW4Q7GOOV4JDL","short_pith_number":"pith:PCLHJCOO","schema_version":"1.0","canonical_sha256":"78967489ce9fe3e726dc87cce757891adec64a05d3c6dde4bcd55b4cd14182dd","source":{"kind":"arxiv","id":"2401.16468","version":5},"attestation_state":"computed","paper":{"title":"InstructIR: High-Quality Image Restoration Following Human Instructions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gregor Geigle, Marcos V. Conde, Radu Timofte","submitted_at":"2024-01-29T18:53:33Z","abstract_excerpt":"Image restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, I"},"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":"2401.16468","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T18:53:33Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"a86379c2d2ee45eacfa35c4b1038e878f38879eb59db42684208401412428648","abstract_canon_sha256":"11f6c3020c3620d80715bfa57643533ba24daa1e0b40e9770458933f3219abe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:46.563502Z","signature_b64":"NhR/stkfknQ1EsCZf4Np/rYhwSWNDur5BEde0HcppWxp2RlbATlaX4sOX5pwXvh66VDXglVjQUa7pJxra6YiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78967489ce9fe3e726dc87cce757891adec64a05d3c6dde4bcd55b4cd14182dd","last_reissued_at":"2026-07-05T09:11:46.562875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:46.562875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructIR: High-Quality Image Restoration Following Human Instructions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gregor Geigle, Marcos V. Conde, Radu Timofte","submitted_at":"2024-01-29T18:53:33Z","abstract_excerpt":"Image restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16468","kind":"arxiv","version":5},"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/2401.16468/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":"2401.16468","created_at":"2026-07-05T09:11:46.562955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16468v5","created_at":"2026-07-05T09:11:46.562955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16468","created_at":"2026-07-05T09:11:46.562955+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCLHJCOOT7R6","created_at":"2026-07-05T09:11:46.562955+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCLHJCOOT7R6OJW4","created_at":"2026-07-05T09:11:46.562955+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCLHJCOO","created_at":"2026-07-05T09:11:46.562955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04055","citing_title":"Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL","json":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL.json","graph_json":"https://pith.science/api/pith-number/PCLHJCOOT7R6OJW4Q7GOOV4JDL/graph.json","events_json":"https://pith.science/api/pith-number/PCLHJCOOT7R6OJW4Q7GOOV4JDL/events.json","paper":"https://pith.science/paper/PCLHJCOO"},"agent_actions":{"view_html":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL","download_json":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL.json","view_paper":"https://pith.science/paper/PCLHJCOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16468&json=true","fetch_graph":"https://pith.science/api/pith-number/PCLHJCOOT7R6OJW4Q7GOOV4JDL/graph.json","fetch_events":"https://pith.science/api/pith-number/PCLHJCOOT7R6OJW4Q7GOOV4JDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL/action/storage_attestation","attest_author":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL/action/author_attestation","sign_citation":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL/action/citation_signature","submit_replication":"https://pith.science/pith/PCLHJCOOT7R6OJW4Q7GOOV4JDL/action/replication_record"}},"created_at":"2026-07-05T09:11:46.562955+00:00","updated_at":"2026-07-05T09:11:46.562955+00:00"}