{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LPZK7BAYX2BQWMOWJUQCLMOHFV","short_pith_number":"pith:LPZK7BAY","schema_version":"1.0","canonical_sha256":"5bf2af8418be830b31d64d2025b1c72d78c8032ba121eff3069c1bb56c8384dd","source":{"kind":"arxiv","id":"2310.01018","version":2},"attestation_state":"computed","paper":{"title":"Controlling Vision-Language Models for Multi-Task Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fredrik K. Gustafsson, Jens Sj\\\"olund, Thomas B. Sch\\\"on, Zheng Zhao, Ziwei Luo","submitted_at":"2023-10-02T09:10:16Z","abstract_excerpt":"Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates dramatically due to corrupted inputs. In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration. More specifically, DA-CLIP trains an additional controller that adapts the fixed CLIP image encoder to predict high-quality fea"},"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":"2310.01018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T09:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"640bafc3f11cb9b8ef2d3097b025bd3b95d4d2375b5237fbdd9e094082a5407f","abstract_canon_sha256":"4e5cba17bd6f79a218bb614a59bc5b37eb59daeff845f45bdf7ad46538097d31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:03.633720Z","signature_b64":"aDXWjv22TpKrNF2OXISXIqPbVI/ZECkeeTMGG+z4UI9Y67wyUCaK/s26d5o8zx7MTy92SDSmhpLIZJpe3v+RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf2af8418be830b31d64d2025b1c72d78c8032ba121eff3069c1bb56c8384dd","last_reissued_at":"2026-07-05T07:50:03.633203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:03.633203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Vision-Language Models for Multi-Task Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fredrik K. Gustafsson, Jens Sj\\\"olund, Thomas B. Sch\\\"on, Zheng Zhao, Ziwei Luo","submitted_at":"2023-10-02T09:10:16Z","abstract_excerpt":"Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates dramatically due to corrupted inputs. In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration. More specifically, DA-CLIP trains an additional controller that adapts the fixed CLIP image encoder to predict high-quality fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01018","kind":"arxiv","version":2},"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/2310.01018/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":"2310.01018","created_at":"2026-07-05T07:50:03.633263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01018v2","created_at":"2026-07-05T07:50:03.633263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01018","created_at":"2026-07-05T07:50:03.633263+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPZK7BAYX2BQ","created_at":"2026-07-05T07:50:03.633263+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPZK7BAYX2BQWMOW","created_at":"2026-07-05T07:50:03.633263+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPZK7BAY","created_at":"2026-07-05T07:50:03.633263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19097","citing_title":"DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02535","citing_title":"LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22208","citing_title":"EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22894","citing_title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07148","citing_title":"Q-Agent: Quality-Driven Chain-of-Thought Image Restoration Agent through Robust Multimodal Large Language Model","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22208","citing_title":"EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20306","citing_title":"TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17506","citing_title":"Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.18064","citing_title":"Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22844","citing_title":"PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01236","citing_title":"Degradation-Aware Adaptive Context Gating for Unified Image Restoration","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV","json":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV.json","graph_json":"https://pith.science/api/pith-number/LPZK7BAYX2BQWMOWJUQCLMOHFV/graph.json","events_json":"https://pith.science/api/pith-number/LPZK7BAYX2BQWMOWJUQCLMOHFV/events.json","paper":"https://pith.science/paper/LPZK7BAY"},"agent_actions":{"view_html":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV","download_json":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV.json","view_paper":"https://pith.science/paper/LPZK7BAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01018&json=true","fetch_graph":"https://pith.science/api/pith-number/LPZK7BAYX2BQWMOWJUQCLMOHFV/graph.json","fetch_events":"https://pith.science/api/pith-number/LPZK7BAYX2BQWMOWJUQCLMOHFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV/action/storage_attestation","attest_author":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV/action/author_attestation","sign_citation":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV/action/citation_signature","submit_replication":"https://pith.science/pith/LPZK7BAYX2BQWMOWJUQCLMOHFV/action/replication_record"}},"created_at":"2026-07-05T07:50:03.633263+00:00","updated_at":"2026-07-05T07:50:03.633263+00:00"}