{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZQXEBBOZ423EYRM772XZEKFEYU","short_pith_number":"pith:ZQXEBBOZ","schema_version":"1.0","canonical_sha256":"cc2e4085d9e6b64c459ffeaf9228a4c5061f38abaa84d3a3c28decb2e9af206a","source":{"kind":"arxiv","id":"2303.11950","version":1},"attestation_state":"computed","paper":{"title":"Learning A Sparse Transformer Network for Effective Image Deraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Jinshan Pan, Mingqiang Li, Xiang Chen","submitted_at":"2023-03-21T15:41:57Z","abstract_excerpt":"Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers usually use all similarities of the tokens from the query-key pairs for the feature aggregation. However, if the tokens from the query are different from those of the key, the self-attention values estimated from these tokens also involve in feature aggregation, which accordingly interferes with the clear image restoration. To overcome this problem, we propose "},"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":"2303.11950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T15:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"020460be579f18942a3355d181bb9cc87e7e96f8823e7a010aefc87d30b96d80","abstract_canon_sha256":"ab088e2ccd8eae67f38f6d06d99f0ac8e33e1730f41825b5a177d1560f68ce3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:23.997031Z","signature_b64":"8DEzL8s2AoeH0VcTXLd+KbavG/I9UbnhX+sD23tk2ShGdvx7V+QkNJ2WzGGBYQtJfGKRuEZQB3MV2Xo6iMMGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2e4085d9e6b64c459ffeaf9228a4c5061f38abaa84d3a3c28decb2e9af206a","last_reissued_at":"2026-07-05T05:53:23.996643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:23.996643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning A Sparse Transformer Network for Effective Image Deraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Jinshan Pan, Mingqiang Li, Xiang Chen","submitted_at":"2023-03-21T15:41:57Z","abstract_excerpt":"Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers usually use all similarities of the tokens from the query-key pairs for the feature aggregation. However, if the tokens from the query are different from those of the key, the self-attention values estimated from these tokens also involve in feature aggregation, which accordingly interferes with the clear image restoration. To overcome this problem, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11950","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/2303.11950/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":"2303.11950","created_at":"2026-07-05T05:53:23.996701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11950v1","created_at":"2026-07-05T05:53:23.996701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11950","created_at":"2026-07-05T05:53:23.996701+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQXEBBOZ423E","created_at":"2026-07-05T05:53:23.996701+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQXEBBOZ423EYRM7","created_at":"2026-07-05T05:53:23.996701+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQXEBBOZ","created_at":"2026-07-05T05:53:23.996701+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/ZQXEBBOZ423EYRM772XZEKFEYU","json":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU.json","graph_json":"https://pith.science/api/pith-number/ZQXEBBOZ423EYRM772XZEKFEYU/graph.json","events_json":"https://pith.science/api/pith-number/ZQXEBBOZ423EYRM772XZEKFEYU/events.json","paper":"https://pith.science/paper/ZQXEBBOZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU","download_json":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU.json","view_paper":"https://pith.science/paper/ZQXEBBOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11950&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQXEBBOZ423EYRM772XZEKFEYU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQXEBBOZ423EYRM772XZEKFEYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU/action/storage_attestation","attest_author":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU/action/author_attestation","sign_citation":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU/action/citation_signature","submit_replication":"https://pith.science/pith/ZQXEBBOZ423EYRM772XZEKFEYU/action/replication_record"}},"created_at":"2026-07-05T05:53:23.996701+00:00","updated_at":"2026-07-05T05:53:23.996701+00:00"}