{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZMCH7H46ZZ2PUG3S5Y72JM42BJ","short_pith_number":"pith:ZMCH7H46","schema_version":"1.0","canonical_sha256":"cb047f9f9ece74fa1b72ee3fa4b39a0a41ebceaac5a46393444f29c726569f4f","source":{"kind":"arxiv","id":"2410.17809","version":2},"attestation_state":"computed","paper":{"title":"An Intelligent Agentic System for Complex Image Restoration Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinjin Gu, Kaiwen Zhu, Yu Qiao, Zhiyuan You","submitted_at":"2024-10-23T12:11:26Z","abstract_excerpt":"Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving, we propose AgenticIR, an agentic system that mimics the human approach to image processing by following five key stages: Perception, Scheduling, Execution, Reflection, and Rescheduling. AgenticIR leverages large language models (LLMs) and vision-language models (VLMs) that interact via text generation to dynamically operate a toolbox of IR models. We fine-tune VLMs for image quality analysis and employ LLMs for reas"},"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":"2410.17809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T12:11:26Z","cross_cats_sorted":[],"title_canon_sha256":"cc3809549bb3ce7444575bfad24089ced473c20caf033e51d4ff914d6ebca047","abstract_canon_sha256":"d5f805d2b4c932327d97f7e4907367db1ce0e1aace90d7c9b94dee7ef4ddac51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:47.003469Z","signature_b64":"jNMKDFxdq47sZaj2XDXvc7MW/HR00EgL/BXx5Vg1GRG6nNfIkwMpx8ZrEtGiV3AXg+WlzbeNtI30AcftRpSgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb047f9f9ece74fa1b72ee3fa4b39a0a41ebceaac5a46393444f29c726569f4f","last_reissued_at":"2026-07-05T10:14:47.002985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:47.002985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Intelligent Agentic System for Complex Image Restoration Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinjin Gu, Kaiwen Zhu, Yu Qiao, Zhiyuan You","submitted_at":"2024-10-23T12:11:26Z","abstract_excerpt":"Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving, we propose AgenticIR, an agentic system that mimics the human approach to image processing by following five key stages: Perception, Scheduling, Execution, Reflection, and Rescheduling. AgenticIR leverages large language models (LLMs) and vision-language models (VLMs) that interact via text generation to dynamically operate a toolbox of IR models. We fine-tune VLMs for image quality analysis and employ LLMs for reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17809","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/2410.17809/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":"2410.17809","created_at":"2026-07-05T10:14:47.003034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17809v2","created_at":"2026-07-05T10:14:47.003034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17809","created_at":"2026-07-05T10:14:47.003034+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMCH7H46ZZ2P","created_at":"2026-07-05T10:14:47.003034+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMCH7H46ZZ2PUG3S","created_at":"2026-07-05T10:14:47.003034+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMCH7H46","created_at":"2026-07-05T10:14:47.003034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20306","citing_title":"TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09228","citing_title":"Clear Roads, Clear Vision: Advancements in Multi-Weather Restoration for Smart Transportation","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16300","citing_title":"Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02409","citing_title":"LumiVideo: An Intelligent Agentic System for Video Color Grading","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07457","citing_title":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16858","citing_title":"Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ","json":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ.json","graph_json":"https://pith.science/api/pith-number/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/graph.json","events_json":"https://pith.science/api/pith-number/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/events.json","paper":"https://pith.science/paper/ZMCH7H46"},"agent_actions":{"view_html":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ","download_json":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ.json","view_paper":"https://pith.science/paper/ZMCH7H46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17809&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZMCH7H46ZZ2PUG3S5Y72JM42BJ/action/replication_record"}},"created_at":"2026-07-05T10:14:47.003034+00:00","updated_at":"2026-07-05T10:14:47.003034+00:00"}