{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IUDK5LZDUL5VSFFWJYKSRZ2UP5","short_pith_number":"pith:IUDK5LZD","canonical_record":{"source":{"id":"2203.06717","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-13T17:22:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49023e7ed18465790dadf46a933dd4fbc03b8c6ba8f78cbe477b6bc22679e397","abstract_canon_sha256":"54b8d9f3dab3c83c3571628e0620236f42c75e30b9c31f97f080067dcc7aa867"},"schema_version":"1.0"},"canonical_sha256":"4506aeaf23a2fb5914b64e1528e7547f70031001eac282dc7bcb7fa34f397a3b","source":{"kind":"arxiv","id":"2203.06717","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06717","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06717v4","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06717","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"IUDK5LZDUL5V","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"IUDK5LZDUL5VSFFW","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"IUDK5LZD","created_at":"2026-07-05T04:10:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IUDK5LZDUL5VSFFWJYKSRZ2UP5","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06717","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-13T17:22:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49023e7ed18465790dadf46a933dd4fbc03b8c6ba8f78cbe477b6bc22679e397","abstract_canon_sha256":"54b8d9f3dab3c83c3571628e0620236f42c75e30b9c31f97f080067dcc7aa867"},"schema_version":"1.0"},"canonical_sha256":"4506aeaf23a2fb5914b64e1528e7547f70031001eac282dc7bcb7fa34f397a3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:53.696178Z","signature_b64":"Z8dyZI6KHPGBtVLH5PP7srF98TRPCdg8r5dUOGN3Wb/vqzOTZqoXT65Cabgwj0xYkgt/HHwqHWWKo2/GZGwRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4506aeaf23a2fb5914b64e1528e7547f70031001eac282dc7bcb7fa34f397a3b","last_reissued_at":"2026-07-05T04:10:53.695764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:53.695764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06717","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNFNbJKgdfZDy1nZtJkOidpr8LQ5FNMYhwotIEIf4iyeRlmQsa821NV99NulWRDqObJkwwdi0ONfDYfcmA2HCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:35.940848Z"},"content_sha256":"a25e6e6610a0fa0d73ae1a0e2c15a76cba4c0eaee52ae53580f1be6df7478bd1","schema_version":"1.0","event_id":"sha256:a25e6e6610a0fa0d73ae1a0e2c15a76cba4c0eaee52ae53580f1be6df7478bd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IUDK5LZDUL5VSFFWJYKSRZ2UP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guiguang Ding, Jian Sun, Jungong Han, Xiangyu Zhang, Xiaohan Ding, Yizhuang Zhou","submitted_at":"2022-03-13T17:22:44Z","abstract_excerpt":"We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly close"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06717","kind":"arxiv","version":4},"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/2203.06717/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWgKS12ATLQdx5RreKtqMbWtMu9try6w2Pye9kJZHMTZxE6L5IEXtvx9pj2yhSd8xxC9A9MZHPRUXpmS8JX2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:47:35.941779Z"},"content_sha256":"a5d7865d4ffbf9f05e1d326f49748b2a67eb2cd4c7d9ec985211be41cc3bfecd","schema_version":"1.0","event_id":"sha256:a5d7865d4ffbf9f05e1d326f49748b2a67eb2cd4c7d9ec985211be41cc3bfecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/bundle.json","state_url":"https://pith.science/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T01:47:35Z","links":{"resolver":"https://pith.science/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5","bundle":"https://pith.science/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/bundle.json","state":"https://pith.science/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUDK5LZDUL5VSFFWJYKSRZ2UP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IUDK5LZDUL5VSFFWJYKSRZ2UP5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"54b8d9f3dab3c83c3571628e0620236f42c75e30b9c31f97f080067dcc7aa867","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-13T17:22:44Z","title_canon_sha256":"49023e7ed18465790dadf46a933dd4fbc03b8c6ba8f78cbe477b6bc22679e397"},"schema_version":"1.0","source":{"id":"2203.06717","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06717","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06717v4","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06717","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"IUDK5LZDUL5V","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"IUDK5LZDUL5VSFFW","created_at":"2026-07-05T04:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"IUDK5LZD","created_at":"2026-07-05T04:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:a5d7865d4ffbf9f05e1d326f49748b2a67eb2cd4c7d9ec985211be41cc3bfecd","target":"graph","created_at":"2026-07-05T04:10:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.06717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly close","authors_text":"Guiguang Ding, Jian Sun, Jungong Han, Xiangyu Zhang, Xiaohan Ding, Yizhuang Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-13T17:22:44Z","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06717","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a25e6e6610a0fa0d73ae1a0e2c15a76cba4c0eaee52ae53580f1be6df7478bd1","target":"record","created_at":"2026-07-05T04:10:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"54b8d9f3dab3c83c3571628e0620236f42c75e30b9c31f97f080067dcc7aa867","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-13T17:22:44Z","title_canon_sha256":"49023e7ed18465790dadf46a933dd4fbc03b8c6ba8f78cbe477b6bc22679e397"},"schema_version":"1.0","source":{"id":"2203.06717","kind":"arxiv","version":4}},"canonical_sha256":"4506aeaf23a2fb5914b64e1528e7547f70031001eac282dc7bcb7fa34f397a3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4506aeaf23a2fb5914b64e1528e7547f70031001eac282dc7bcb7fa34f397a3b","first_computed_at":"2026-07-05T04:10:53.695764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:53.695764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z8dyZI6KHPGBtVLH5PP7srF98TRPCdg8r5dUOGN3Wb/vqzOTZqoXT65Cabgwj0xYkgt/HHwqHWWKo2/GZGwRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:53.696178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06717","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a25e6e6610a0fa0d73ae1a0e2c15a76cba4c0eaee52ae53580f1be6df7478bd1","sha256:a5d7865d4ffbf9f05e1d326f49748b2a67eb2cd4c7d9ec985211be41cc3bfecd"],"state_sha256":"dd56355a664f3e689874cd750b6398650abf85888fe21372a02d2d1787f93db3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w2AAZB1Wzdib4v2WooM/yoIcKYrlGFB+EeQSCzkykD+WbhCrmOEdABAhyyoJhOTf/s7r5egMKqT6z5hXIwwOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:47:35.948785Z","bundle_sha256":"6f49b1fd8eee7333fc876293864797ee33ccec66d282837c447626cfdec63696"}}