{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3ZXRQPQTFXXCTKRV7QASLLS5GH","short_pith_number":"pith:3ZXRQPQT","schema_version":"1.0","canonical_sha256":"de6f183e132dee29aa35fc0125ae5d31ea6d5954175e9d1eb822d289cde7fb0d","source":{"kind":"arxiv","id":"2412.03814","version":2},"attestation_state":"computed","paper":{"title":"Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghao Luo, Jiangning Zhang, Kai Wu, Lizhuang Ma, Ran Yi Chengming Xu, Teng Hu, Xiaobin Hu, Yabiao Wang, Yuzhen Du","submitted_at":"2024-12-05T02:11:51Z","abstract_excerpt":"Image restoration (IR) aims to recover high-quality images from degraded inputs, with recent deep learning advancements significantly enhancing performance. However, existing methods lack a unified training benchmark for iterations and configurations. We also identify a bias in image complexity distributions between commonly used IR training and testing datasets, resulting in suboptimal restoration outcomes. To address this, we introduce a large-scale IR dataset called ReSyn, which employs a novel image filtering method based on image complexity to ensure a balanced distribution and includes b"},"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":"2412.03814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T02:11:51Z","cross_cats_sorted":[],"title_canon_sha256":"b52bcbe243bd30063bcddf5bc98d4880623c2723a85b57b7e1f51295d277106f","abstract_canon_sha256":"684082b0e4cd23140b0f6041a107897e61c7628ef97d99273ac35747192a0ab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:37.259073Z","signature_b64":"KU01vI+cgg8St+6zbJ/gotapund5mll0wAh97KMzWaJMvA8kLyrHqdze3gs4y+vb0YK+RQOEQ+UTRZFL8TMkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6f183e132dee29aa35fc0125ae5d31ea6d5954175e9d1eb822d289cde7fb0d","last_reissued_at":"2026-07-05T09:47:37.258577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:37.258577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghao Luo, Jiangning Zhang, Kai Wu, Lizhuang Ma, Ran Yi Chengming Xu, Teng Hu, Xiaobin Hu, Yabiao Wang, Yuzhen Du","submitted_at":"2024-12-05T02:11:51Z","abstract_excerpt":"Image restoration (IR) aims to recover high-quality images from degraded inputs, with recent deep learning advancements significantly enhancing performance. However, existing methods lack a unified training benchmark for iterations and configurations. We also identify a bias in image complexity distributions between commonly used IR training and testing datasets, resulting in suboptimal restoration outcomes. To address this, we introduce a large-scale IR dataset called ReSyn, which employs a novel image filtering method based on image complexity to ensure a balanced distribution and includes b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03814","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/2412.03814/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":"2412.03814","created_at":"2026-07-05T09:47:37.258636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03814v2","created_at":"2026-07-05T09:47:37.258636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03814","created_at":"2026-07-05T09:47:37.258636+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZXRQPQTFXXC","created_at":"2026-07-05T09:47:37.258636+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZXRQPQTFXXCTKRV","created_at":"2026-07-05T09:47:37.258636+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZXRQPQT","created_at":"2026-07-05T09:47:37.258636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17278","citing_title":"PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH","json":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH.json","graph_json":"https://pith.science/api/pith-number/3ZXRQPQTFXXCTKRV7QASLLS5GH/graph.json","events_json":"https://pith.science/api/pith-number/3ZXRQPQTFXXCTKRV7QASLLS5GH/events.json","paper":"https://pith.science/paper/3ZXRQPQT"},"agent_actions":{"view_html":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH","download_json":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH.json","view_paper":"https://pith.science/paper/3ZXRQPQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03814&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZXRQPQTFXXCTKRV7QASLLS5GH/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZXRQPQTFXXCTKRV7QASLLS5GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH/action/storage_attestation","attest_author":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH/action/author_attestation","sign_citation":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH/action/citation_signature","submit_replication":"https://pith.science/pith/3ZXRQPQTFXXCTKRV7QASLLS5GH/action/replication_record"}},"created_at":"2026-07-05T09:47:37.258636+00:00","updated_at":"2026-07-05T09:47:37.258636+00:00"}