{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WLARTAXX37ZUEUOSU4K6XPQQH7","short_pith_number":"pith:WLARTAXX","schema_version":"1.0","canonical_sha256":"b2c11982f7dff34251d2a715ebbe103ffe658f618b5373e7703ef77975d690c1","source":{"kind":"arxiv","id":"2309.01439","version":3},"attestation_state":"computed","paper":{"title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kin Wai Lau, Lai-Man Po, Yasar Abbas Ur Rehman","submitted_at":"2023-09-04T08:38:11Z","abstract_excerpt":"Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs), on a range of vision-based tasks. However, the depth-wise convolutional layer in these LKA modules incurs a quadratic increase in the computational and memory footprints with increasing convolutional kernel size. To mitigate these problems and to enable the use of extremely large convolutional kernels in the attention modules of VAN, we propose a family of Large Separable Kernel Attention modules, termed LSKA. LSKA decomposes th"},"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":"2309.01439","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T08:38:11Z","cross_cats_sorted":[],"title_canon_sha256":"030d30539afe73f75b190cf721c81f3b9b89af09be2dc9f68f0e021f10ea06af","abstract_canon_sha256":"dc5a3e0c1edd0d4841f0b373d71ab20c68bf33dd5f19d3f9dd1d4e9d178f3190"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:53.332749Z","signature_b64":"pQWZNjq2A+3t/j7dkwxRycMQM/Cyx0J8pwNlhchoulBYu06nKYw2JVCQocSjKkzFInTZB1lGZ62Hs792ZB3GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c11982f7dff34251d2a715ebbe103ffe658f618b5373e7703ef77975d690c1","last_reissued_at":"2026-07-05T07:02:53.332306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:53.332306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kin Wai Lau, Lai-Man Po, Yasar Abbas Ur Rehman","submitted_at":"2023-09-04T08:38:11Z","abstract_excerpt":"Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs), on a range of vision-based tasks. However, the depth-wise convolutional layer in these LKA modules incurs a quadratic increase in the computational and memory footprints with increasing convolutional kernel size. To mitigate these problems and to enable the use of extremely large convolutional kernels in the attention modules of VAN, we propose a family of Large Separable Kernel Attention modules, termed LSKA. LSKA decomposes th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01439","kind":"arxiv","version":3},"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/2309.01439/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":"2309.01439","created_at":"2026-07-05T07:02:53.332381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01439v3","created_at":"2026-07-05T07:02:53.332381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01439","created_at":"2026-07-05T07:02:53.332381+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLARTAXX37ZU","created_at":"2026-07-05T07:02:53.332381+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLARTAXX37ZUEUOS","created_at":"2026-07-05T07:02:53.332381+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLARTAXX","created_at":"2026-07-05T07:02:53.332381+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/WLARTAXX37ZUEUOSU4K6XPQQH7","json":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7.json","graph_json":"https://pith.science/api/pith-number/WLARTAXX37ZUEUOSU4K6XPQQH7/graph.json","events_json":"https://pith.science/api/pith-number/WLARTAXX37ZUEUOSU4K6XPQQH7/events.json","paper":"https://pith.science/paper/WLARTAXX"},"agent_actions":{"view_html":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7","download_json":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7.json","view_paper":"https://pith.science/paper/WLARTAXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01439&json=true","fetch_graph":"https://pith.science/api/pith-number/WLARTAXX37ZUEUOSU4K6XPQQH7/graph.json","fetch_events":"https://pith.science/api/pith-number/WLARTAXX37ZUEUOSU4K6XPQQH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7/action/storage_attestation","attest_author":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7/action/author_attestation","sign_citation":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7/action/citation_signature","submit_replication":"https://pith.science/pith/WLARTAXX37ZUEUOSU4K6XPQQH7/action/replication_record"}},"created_at":"2026-07-05T07:02:53.332381+00:00","updated_at":"2026-07-05T07:02:53.332381+00:00"}