{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ABV2PWXX72HWUXBOKRWR7TPEXA","short_pith_number":"pith:ABV2PWXX","schema_version":"1.0","canonical_sha256":"006ba7daf7fe8f6a5c2e546d1fcde4b81403693c994296c2cfaaa507bf3b9e06","source":{"kind":"arxiv","id":"2402.02634","version":1},"attestation_state":"computed","paper":{"title":"Key-Graph Transformer for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Jingyun Liang, Luc Van Gool, Mengyuan Liu, Nicu Sebe, Rakesh Ranjan, Rita Cucchiara, Yawei Li","submitted_at":"2024-02-04T23:00:24Z","abstract_excerpt":"While it is crucial to capture global information for effective image restoration (IR), integrating such cues into transformer-based methods becomes computationally expensive, especially with high input resolution. Furthermore, the self-attention mechanism in transformers is prone to considering unnecessary global cues from unrelated objects or regions, introducing computational inefficiencies. In response to these challenges, we introduce the Key-Graph Transformer (KGT) in this paper. Specifically, KGT views patch features as graph nodes. The proposed Key-Graph Constructor efficiently forms a"},"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":"2402.02634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T23:00:24Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"d4336ac0591ffe8c277fc8a6366a131e76b4b41e07db006eaf9fc6a115175310","abstract_canon_sha256":"13a6ffb6502bab9040d1fc2df0176a03c440875633e4bb1c0c5435a7d7365cfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:49.436900Z","signature_b64":"c0wvrrzMiQRyFpmSUPbW4h4fvqXtKiNvCiuVPepr5NI/SztU7tXofDo1tmT9FsF5U2RJFjF/hCIYojafhSuCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"006ba7daf7fe8f6a5c2e546d1fcde4b81403693c994296c2cfaaa507bf3b9e06","last_reissued_at":"2026-07-05T07:41:49.436475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:49.436475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Key-Graph Transformer for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bin Ren, Jingyun Liang, Luc Van Gool, Mengyuan Liu, Nicu Sebe, Rakesh Ranjan, Rita Cucchiara, Yawei Li","submitted_at":"2024-02-04T23:00:24Z","abstract_excerpt":"While it is crucial to capture global information for effective image restoration (IR), integrating such cues into transformer-based methods becomes computationally expensive, especially with high input resolution. Furthermore, the self-attention mechanism in transformers is prone to considering unnecessary global cues from unrelated objects or regions, introducing computational inefficiencies. In response to these challenges, we introduce the Key-Graph Transformer (KGT) in this paper. Specifically, KGT views patch features as graph nodes. The proposed Key-Graph Constructor efficiently forms a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02634","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/2402.02634/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":"2402.02634","created_at":"2026-07-05T07:41:49.436537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02634v1","created_at":"2026-07-05T07:41:49.436537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02634","created_at":"2026-07-05T07:41:49.436537+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABV2PWXX72HW","created_at":"2026-07-05T07:41:49.436537+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABV2PWXX72HWUXBO","created_at":"2026-07-05T07:41:49.436537+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABV2PWXX","created_at":"2026-07-05T07:41:49.436537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17343","citing_title":"GraphMAR: Geometry-Aware Graph Learning Framework for Spatially Adaptive CT Metal Artifact Reduction","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA","json":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA.json","graph_json":"https://pith.science/api/pith-number/ABV2PWXX72HWUXBOKRWR7TPEXA/graph.json","events_json":"https://pith.science/api/pith-number/ABV2PWXX72HWUXBOKRWR7TPEXA/events.json","paper":"https://pith.science/paper/ABV2PWXX"},"agent_actions":{"view_html":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA","download_json":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA.json","view_paper":"https://pith.science/paper/ABV2PWXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02634&json=true","fetch_graph":"https://pith.science/api/pith-number/ABV2PWXX72HWUXBOKRWR7TPEXA/graph.json","fetch_events":"https://pith.science/api/pith-number/ABV2PWXX72HWUXBOKRWR7TPEXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA/action/storage_attestation","attest_author":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA/action/author_attestation","sign_citation":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA/action/citation_signature","submit_replication":"https://pith.science/pith/ABV2PWXX72HWUXBOKRWR7TPEXA/action/replication_record"}},"created_at":"2026-07-05T07:41:49.436537+00:00","updated_at":"2026-07-05T07:41:49.436537+00:00"}