{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OFR23JYBKS55ETJOBNOMTXJAMC","short_pith_number":"pith:OFR23JYB","schema_version":"1.0","canonical_sha256":"7163ada70154bbd24d2e0b5cc9dd2060a49f6c69a65ff96f8663b38909cd6a9e","source":{"kind":"arxiv","id":"2207.03620","version":3},"attestation_state":"computed","paper":{"title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqian Wu, Decebal Mocanu, Mykola Pechenizkiy, Qiao Xiao, Shiwei Liu, Tianlong Chen, Tommi K\\\"arkk\\\"ainen, Xiaohan Chen, Xuxi Chen, Zhangyang Wang","submitted_at":"2022-07-07T23:55:52Z","abstract_excerpt":"Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based models. Very recently, a couple of advanced convolutional models strike back with large kernels motivated by the local-window attention mechanism, showing appealing performance and efficiency. While one of them, i.e. RepLKNet, impressively manages to scale the kernel size to 31x31 with improved performance, the performance starts to saturate as the kernel size"},"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":"2207.03620","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T23:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"795fbcf88f59f94a41878051e3dc2148e70742e589a1df880e2fc6feb571faf1","abstract_canon_sha256":"3e565e1016f52b85e43cffc8c229f0b307296bda9febef87c6e90e907ade9c29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:00.108738Z","signature_b64":"zO3lKqNStz0VrhNNTJSxIV638osPn7F/bRDwsmuBoI6cb4ew43kJeiUrnq6U2tzTJCYqLzKZjV1DmENnX9msAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7163ada70154bbd24d2e0b5cc9dd2060a49f6c69a65ff96f8663b38909cd6a9e","last_reissued_at":"2026-07-05T05:48:00.108203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:00.108203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqian Wu, Decebal Mocanu, Mykola Pechenizkiy, Qiao Xiao, Shiwei Liu, Tianlong Chen, Tommi K\\\"arkk\\\"ainen, Xiaohan Chen, Xuxi Chen, Zhangyang Wang","submitted_at":"2022-07-07T23:55:52Z","abstract_excerpt":"Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based models. Very recently, a couple of advanced convolutional models strike back with large kernels motivated by the local-window attention mechanism, showing appealing performance and efficiency. While one of them, i.e. RepLKNet, impressively manages to scale the kernel size to 31x31 with improved performance, the performance starts to saturate as the kernel size"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03620","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/2207.03620/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":"2207.03620","created_at":"2026-07-05T05:48:00.108262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03620v3","created_at":"2026-07-05T05:48:00.108262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03620","created_at":"2026-07-05T05:48:00.108262+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFR23JYBKS55","created_at":"2026-07-05T05:48:00.108262+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFR23JYBKS55ETJO","created_at":"2026-07-05T05:48:00.108262+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFR23JYB","created_at":"2026-07-05T05:48:00.108262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.09417","citing_title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23320","citing_title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC","json":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC.json","graph_json":"https://pith.science/api/pith-number/OFR23JYBKS55ETJOBNOMTXJAMC/graph.json","events_json":"https://pith.science/api/pith-number/OFR23JYBKS55ETJOBNOMTXJAMC/events.json","paper":"https://pith.science/paper/OFR23JYB"},"agent_actions":{"view_html":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC","download_json":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC.json","view_paper":"https://pith.science/paper/OFR23JYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03620&json=true","fetch_graph":"https://pith.science/api/pith-number/OFR23JYBKS55ETJOBNOMTXJAMC/graph.json","fetch_events":"https://pith.science/api/pith-number/OFR23JYBKS55ETJOBNOMTXJAMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC/action/storage_attestation","attest_author":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC/action/author_attestation","sign_citation":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC/action/citation_signature","submit_replication":"https://pith.science/pith/OFR23JYBKS55ETJOBNOMTXJAMC/action/replication_record"}},"created_at":"2026-07-05T05:48:00.108262+00:00","updated_at":"2026-07-05T05:48:00.108262+00:00"}