{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6GSRLPWRSNAUWOP5TEWWZUOWZC","short_pith_number":"pith:6GSRLPWR","schema_version":"1.0","canonical_sha256":"f1a515bed193414b39fd992d6cd1d6c889e272a8ab59a8159a7ed8cd37cf920b","source":{"kind":"arxiv","id":"2503.09403","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agent Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Gehui Li, Jian Zhang, Xu Jiang","submitted_at":"2025-03-12T13:53:57Z","abstract_excerpt":"Image restoration (IR) is challenging due to the complexity of real-world degradations. While many specialized and all-in-one IR models have been developed, they fail to effectively handle complex, mixed degradations. Recent agentic methods RestoreAgent and AgenticIR leverage intelligent, autonomous workflows to alleviate this issue, yet they suffer from suboptimal results and inefficiency due to their resource-intensive finetunings, and ineffective searches and tool execution trials for satisfactory outputs. In this paper, we propose MAIR, a novel Multi-Agent approach for complex IR problems."},"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":"2503.09403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T13:53:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84ab5659c8f6cf162440b8ca9362820225bb27687e6f754b0bb0edd13ccd939c","abstract_canon_sha256":"d4d142b3f0141f3ecfc2411e1f29ea5bb085db17d84ca40082b14b3e82d55c87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:41.271888Z","signature_b64":"M9xqpJkXlm6dgiGmf2BkdPsxMkgoWggFW0LAyTk5anQdU5L+WwUpvMRFJJ4BvSwf+feKbQTAhZzOgqj5/YcfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1a515bed193414b39fd992d6cd1d6c889e272a8ab59a8159a7ed8cd37cf920b","last_reissued_at":"2026-07-05T10:32:41.271400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:41.271400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Gehui Li, Jian Zhang, Xu Jiang","submitted_at":"2025-03-12T13:53:57Z","abstract_excerpt":"Image restoration (IR) is challenging due to the complexity of real-world degradations. While many specialized and all-in-one IR models have been developed, they fail to effectively handle complex, mixed degradations. Recent agentic methods RestoreAgent and AgenticIR leverage intelligent, autonomous workflows to alleviate this issue, yet they suffer from suboptimal results and inefficiency due to their resource-intensive finetunings, and ineffective searches and tool execution trials for satisfactory outputs. In this paper, we propose MAIR, a novel Multi-Agent approach for complex IR problems."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09403","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/2503.09403/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":"2503.09403","created_at":"2026-07-05T10:32:41.271461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09403v2","created_at":"2026-07-05T10:32:41.271461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09403","created_at":"2026-07-05T10:32:41.271461+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GSRLPWRSNAU","created_at":"2026-07-05T10:32:41.271461+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GSRLPWRSNAUWOP5","created_at":"2026-07-05T10:32:41.271461+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GSRLPWR","created_at":"2026-07-05T10:32:41.271461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09110","citing_title":"HDRAgent: An Agentic Framework for Multi-Exposure HDR Imaging","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01803","citing_title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","ref_index":21,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28971","citing_title":"Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30915","citing_title":"DiTTo: Scalable Order-aware All-in-One Image Restoration Agent","ref_index":11,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22104","citing_title":"OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18599","citing_title":"Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09367","citing_title":"EpiAgent: An Agent-Centric System for Ancient Inscription Restoration","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC","json":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC.json","graph_json":"https://pith.science/api/pith-number/6GSRLPWRSNAUWOP5TEWWZUOWZC/graph.json","events_json":"https://pith.science/api/pith-number/6GSRLPWRSNAUWOP5TEWWZUOWZC/events.json","paper":"https://pith.science/paper/6GSRLPWR"},"agent_actions":{"view_html":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC","download_json":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC.json","view_paper":"https://pith.science/paper/6GSRLPWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09403&json=true","fetch_graph":"https://pith.science/api/pith-number/6GSRLPWRSNAUWOP5TEWWZUOWZC/graph.json","fetch_events":"https://pith.science/api/pith-number/6GSRLPWRSNAUWOP5TEWWZUOWZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC/action/storage_attestation","attest_author":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC/action/author_attestation","sign_citation":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC/action/citation_signature","submit_replication":"https://pith.science/pith/6GSRLPWRSNAUWOP5TEWWZUOWZC/action/replication_record"}},"created_at":"2026-07-05T10:32:41.271461+00:00","updated_at":"2026-07-05T10:32:41.271461+00:00"}