{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O23VHYPGTIPQJP4MXVOB4LF3V5","short_pith_number":"pith:O23VHYPG","schema_version":"1.0","canonical_sha256":"76b753e1e69a1f04bf8cbd5c1e2cbbaf51b05ed1a7d840498577929d4ab8721b","source":{"kind":"arxiv","id":"2406.16004","version":2},"attestation_state":"computed","paper":{"title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingshu Zhao, Yi Luo, Yong Ouyang","submitted_at":"2024-06-23T04:11:12Z","abstract_excerpt":"In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tail"},"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":"2406.16004","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-23T04:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"4a44a54b0cac0e93c74d91b94a74af25c925c1b16634993106872b56e519f62b","abstract_canon_sha256":"389a4a9e4375d8e4a04e029f8deb9ca8d382083dac0dce659220c597f85b08d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:26.309801Z","signature_b64":"pAGN3lQZo6sfu5RUugjFWIjGuAVh1GgC2h31oRwCf7trPKLX+dxLNKjL8Cl6t9r9mZfKHSdGNH8tRMS5AK58Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76b753e1e69a1f04bf8cbd5c1e2cbbaf51b05ed1a7d840498577929d4ab8721b","last_reissued_at":"2026-07-05T08:46:26.309378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:26.309378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingshu Zhao, Yi Luo, Yong Ouyang","submitted_at":"2024-06-23T04:11:12Z","abstract_excerpt":"In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16004","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/2406.16004/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":"2406.16004","created_at":"2026-07-05T08:46:26.309436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16004v2","created_at":"2026-07-05T08:46:26.309436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16004","created_at":"2026-07-05T08:46:26.309436+00:00"},{"alias_kind":"pith_short_12","alias_value":"O23VHYPGTIPQ","created_at":"2026-07-05T08:46:26.309436+00:00"},{"alias_kind":"pith_short_16","alias_value":"O23VHYPGTIPQJP4M","created_at":"2026-07-05T08:46:26.309436+00:00"},{"alias_kind":"pith_short_8","alias_value":"O23VHYPG","created_at":"2026-07-05T08:46:26.309436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15369","citing_title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5","json":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5.json","graph_json":"https://pith.science/api/pith-number/O23VHYPGTIPQJP4MXVOB4LF3V5/graph.json","events_json":"https://pith.science/api/pith-number/O23VHYPGTIPQJP4MXVOB4LF3V5/events.json","paper":"https://pith.science/paper/O23VHYPG"},"agent_actions":{"view_html":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5","download_json":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5.json","view_paper":"https://pith.science/paper/O23VHYPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16004&json=true","fetch_graph":"https://pith.science/api/pith-number/O23VHYPGTIPQJP4MXVOB4LF3V5/graph.json","fetch_events":"https://pith.science/api/pith-number/O23VHYPGTIPQJP4MXVOB4LF3V5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5/action/storage_attestation","attest_author":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5/action/author_attestation","sign_citation":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5/action/citation_signature","submit_replication":"https://pith.science/pith/O23VHYPGTIPQJP4MXVOB4LF3V5/action/replication_record"}},"created_at":"2026-07-05T08:46:26.309436+00:00","updated_at":"2026-07-05T08:46:26.309436+00:00"}