{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7X72PJG2HAERNB4T6WF5KPTEL","short_pith_number":"pith:H7X72PJG","schema_version":"1.0","canonical_sha256":"3feffd3d26d1c048b43c9fac5ea9f322daafae4474bf277253964e6d8a9298a6","source":{"kind":"arxiv","id":"2401.12736","version":2},"attestation_state":"computed","paper":{"title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dachong Li, Jianqiang Li, Li Li, ZhuangZhuang Chen","submitted_at":"2024-01-23T13:13:45Z","abstract_excerpt":"Large kernels make standard convolutional neural networks (CNNs) great again over transformer architectures in various vision tasks. Nonetheless, recent studies meticulously designed around increasing kernel size have shown diminishing returns or stagnation in performance. Thus, the hidden factors of large kernel convolution that affect model performance remain unexplored. In this paper, we reveal that the key hidden factors of large kernels can be summarized as two separate components: extracting features at a certain granularity and fusing features by multiple pathways. To this end, we lever"},"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":"2401.12736","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T13:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"6526d72b539488189bfa189944ea0d4597a8c7ca1372c84a7a44a10562175ad0","abstract_canon_sha256":"c4fe9b344fd13c9f159b4d8cd236df9777c76b8429ced634a5262d6ff5d3ae11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:19.164046Z","signature_b64":"hjeSTF4EmFr8iFOffZIoKtoA77okjCdWqToo7mLPf443c5TDPxZNxddYpni8LfNNsu1Fe/p8roEJvcvpTZroCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3feffd3d26d1c048b43c9fac5ea9f322daafae4474bf277253964e6d8a9298a6","last_reissued_at":"2026-07-05T10:30:19.163589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:19.163589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dachong Li, Jianqiang Li, Li Li, ZhuangZhuang Chen","submitted_at":"2024-01-23T13:13:45Z","abstract_excerpt":"Large kernels make standard convolutional neural networks (CNNs) great again over transformer architectures in various vision tasks. Nonetheless, recent studies meticulously designed around increasing kernel size have shown diminishing returns or stagnation in performance. Thus, the hidden factors of large kernel convolution that affect model performance remain unexplored. In this paper, we reveal that the key hidden factors of large kernels can be summarized as two separate components: extracting features at a certain granularity and fusing features by multiple pathways. To this end, we lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12736","kind":"arxiv","version":2},"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/2401.12736/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":"2401.12736","created_at":"2026-07-05T10:30:19.163649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12736v2","created_at":"2026-07-05T10:30:19.163649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12736","created_at":"2026-07-05T10:30:19.163649+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7X72PJG2HAE","created_at":"2026-07-05T10:30:19.163649+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7X72PJG2HAERNB4","created_at":"2026-07-05T10:30:19.163649+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7X72PJG","created_at":"2026-07-05T10:30:19.163649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06054","citing_title":"FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasound","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL","json":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL.json","graph_json":"https://pith.science/api/pith-number/H7X72PJG2HAERNB4T6WF5KPTEL/graph.json","events_json":"https://pith.science/api/pith-number/H7X72PJG2HAERNB4T6WF5KPTEL/events.json","paper":"https://pith.science/paper/H7X72PJG"},"agent_actions":{"view_html":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL","download_json":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL.json","view_paper":"https://pith.science/paper/H7X72PJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12736&json=true","fetch_graph":"https://pith.science/api/pith-number/H7X72PJG2HAERNB4T6WF5KPTEL/graph.json","fetch_events":"https://pith.science/api/pith-number/H7X72PJG2HAERNB4T6WF5KPTEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL/action/storage_attestation","attest_author":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL/action/author_attestation","sign_citation":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL/action/citation_signature","submit_replication":"https://pith.science/pith/H7X72PJG2HAERNB4T6WF5KPTEL/action/replication_record"}},"created_at":"2026-07-05T10:30:19.163649+00:00","updated_at":"2026-07-05T10:30:19.163649+00:00"}