{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZYPS2EZMOI2LU5HK7V7FP3STR","short_pith_number":"pith:NZYPS2EZ","schema_version":"1.0","canonical_sha256":"6e70f968996391a5d3a757ebf2bf729c411cc5accff6128f5c764a318845f681","source":{"kind":"arxiv","id":"2411.18588","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Ren, Jingyun Liang, Luca Benini, Mengyuan Liu, Ming-Hsuan Yang, Nicu Sebe, Rakesh Ranjan, Yawei Li","submitted_at":"2024-11-27T18:30:08Z","abstract_excerpt":"While vision transformers show promise in numerous image restoration (IR) tasks, the challenge remains in efficiently generalizing and scaling up a model for multiple IR tasks. To strike a balance between efficiency and model capacity for a generalized transformer-based IR method, we propose a hierarchical information flow mechanism for image restoration, dubbed Hi-IR, which progressively propagates information among pixels in a bottom-up manner. Hi-IR constructs a hierarchical information tree representing the degraded image across three levels. Each level encapsulates different types of info"},"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":"2411.18588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"a7dda0d0df2dc29058102556602b5ade0151a17c49a5fd5ec3165e4244cbdf75","abstract_canon_sha256":"76098898e7b66ce2a126fcd606dd9bb0b74b9114a63e96708f852d4e8ee3a639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:23.911893Z","signature_b64":"pmdWbYKArUXGRHlmYVI2GVkvohD/+yhb+bXllnXM5A1BvnA3s+bp2JWpNc3rK8eDMtGWZ9DJSo3eXA0xaktCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e70f968996391a5d3a757ebf2bf729c411cc5accff6128f5c764a318845f681","last_reissued_at":"2026-07-05T09:41:23.911392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:23.911392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Information Flow for Generalized Efficient Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Ren, Jingyun Liang, Luca Benini, Mengyuan Liu, Ming-Hsuan Yang, Nicu Sebe, Rakesh Ranjan, Yawei Li","submitted_at":"2024-11-27T18:30:08Z","abstract_excerpt":"While vision transformers show promise in numerous image restoration (IR) tasks, the challenge remains in efficiently generalizing and scaling up a model for multiple IR tasks. To strike a balance between efficiency and model capacity for a generalized transformer-based IR method, we propose a hierarchical information flow mechanism for image restoration, dubbed Hi-IR, which progressively propagates information among pixels in a bottom-up manner. Hi-IR constructs a hierarchical information tree representing the degraded image across three levels. Each level encapsulates different types of info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18588","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/2411.18588/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":"2411.18588","created_at":"2026-07-05T09:41:23.911449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18588v1","created_at":"2026-07-05T09:41:23.911449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18588","created_at":"2026-07-05T09:41:23.911449+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZYPS2EZMOI2","created_at":"2026-07-05T09:41:23.911449+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZYPS2EZMOI2LU5H","created_at":"2026-07-05T09:41:23.911449+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZYPS2EZ","created_at":"2026-07-05T09:41:23.911449+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/NZYPS2EZMOI2LU5HK7V7FP3STR","json":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR.json","graph_json":"https://pith.science/api/pith-number/NZYPS2EZMOI2LU5HK7V7FP3STR/graph.json","events_json":"https://pith.science/api/pith-number/NZYPS2EZMOI2LU5HK7V7FP3STR/events.json","paper":"https://pith.science/paper/NZYPS2EZ"},"agent_actions":{"view_html":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR","download_json":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR.json","view_paper":"https://pith.science/paper/NZYPS2EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18588&json=true","fetch_graph":"https://pith.science/api/pith-number/NZYPS2EZMOI2LU5HK7V7FP3STR/graph.json","fetch_events":"https://pith.science/api/pith-number/NZYPS2EZMOI2LU5HK7V7FP3STR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR/action/storage_attestation","attest_author":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR/action/author_attestation","sign_citation":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR/action/citation_signature","submit_replication":"https://pith.science/pith/NZYPS2EZMOI2LU5HK7V7FP3STR/action/replication_record"}},"created_at":"2026-07-05T09:41:23.911449+00:00","updated_at":"2026-07-05T09:41:23.911449+00:00"}