{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EQ3MUJSXXPYRJJW5WDNCNVQ3T","short_pith_number":"pith:6EQ3MUJS","schema_version":"1.0","canonical_sha256":"f121b65132bddf88a536ed86d136b0dcd19d059718723fb009dd0d7acf7bb4e8","source":{"kind":"arxiv","id":"2401.04680","version":1},"attestation_state":"computed","paper":{"title":"CoordGate: Efficiently Computing Spatially-Varying Convolutions in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas D\\\"opp, Peter Norreys, Sunny Howard","submitted_at":"2024-01-09T17:13:58Z","abstract_excerpt":"Optical imaging systems are inherently limited in their resolution due to the point spread function (PSF), which applies a static, yet spatially-varying, convolution to the image. This degradation can be addressed via Convolutional Neural Networks (CNNs), particularly through deblurring techniques. However, current solutions face certain limitations in efficiently computing spatially-varying convolutions. In this paper we propose CoordGate, a novel lightweight module that uses a multiplicative gate and a coordinate encoding network to enable efficient computation of spatially-varying convoluti"},"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":"2401.04680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T17:13:58Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"01e58dcbf1bede872cb88092b0088e1d1cea0b5341e6983485dd9c9fee1a4242","abstract_canon_sha256":"814ed67b4abd9c5ae5ce290e71af34327531c021d30c1ddf53c49455114c6b4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:48.927961Z","signature_b64":"M3tA2r5sjhKHBeui3xAi1tFcVWblp5inH4E8CWrP2bILdw2JCf+lPXnR/IUXcGf+0xgbO0G62xLVC7k30PfQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f121b65132bddf88a536ed86d136b0dcd19d059718723fb009dd0d7acf7bb4e8","last_reissued_at":"2026-07-05T07:31:48.927562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:48.927562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoordGate: Efficiently Computing Spatially-Varying Convolutions in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Andreas D\\\"opp, Peter Norreys, Sunny Howard","submitted_at":"2024-01-09T17:13:58Z","abstract_excerpt":"Optical imaging systems are inherently limited in their resolution due to the point spread function (PSF), which applies a static, yet spatially-varying, convolution to the image. This degradation can be addressed via Convolutional Neural Networks (CNNs), particularly through deblurring techniques. However, current solutions face certain limitations in efficiently computing spatially-varying convolutions. In this paper we propose CoordGate, a novel lightweight module that uses a multiplicative gate and a coordinate encoding network to enable efficient computation of spatially-varying convoluti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04680","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/2401.04680/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":"2401.04680","created_at":"2026-07-05T07:31:48.927616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04680v1","created_at":"2026-07-05T07:31:48.927616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04680","created_at":"2026-07-05T07:31:48.927616+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EQ3MUJSXXPY","created_at":"2026-07-05T07:31:48.927616+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EQ3MUJSXXPYRJJW","created_at":"2026-07-05T07:31:48.927616+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EQ3MUJS","created_at":"2026-07-05T07:31:48.927616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00029","citing_title":"Broadband Wide Field of View Imaging with Computational Mirrors","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T","json":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T.json","graph_json":"https://pith.science/api/pith-number/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/graph.json","events_json":"https://pith.science/api/pith-number/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/events.json","paper":"https://pith.science/paper/6EQ3MUJS"},"agent_actions":{"view_html":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T","download_json":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T.json","view_paper":"https://pith.science/paper/6EQ3MUJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04680&json=true","fetch_graph":"https://pith.science/api/pith-number/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/action/storage_attestation","attest_author":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/action/author_attestation","sign_citation":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/action/citation_signature","submit_replication":"https://pith.science/pith/6EQ3MUJSXXPYRJJW5WDNCNVQ3T/action/replication_record"}},"created_at":"2026-07-05T07:31:48.927616+00:00","updated_at":"2026-07-05T07:31:48.927616+00:00"}