{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAXCLRDQZVB2DEF3IRYLUNMZOG","short_pith_number":"pith:FAXCLRDQ","schema_version":"1.0","canonical_sha256":"282e25c470cd43a190bb4470ba359971b077f61b96eaf8504bf7c4578d9f2dbb","source":{"kind":"arxiv","id":"2403.02308","version":3},"attestation_state":"computed","paper":{"title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yuchen Duan, Yu Qiao, Zhe Chen","submitted_at":"2024-03-04T18:46:20Z","abstract_excerpt":"Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks. Similar to the Vision Transformer (ViT), our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, while also scaling up effectively, accommodating both large-scale parameters and extensi"},"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":"2403.02308","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:46:20Z","cross_cats_sorted":[],"title_canon_sha256":"f20b53ed05c0d822eed3fffc79229e7fa799029182ea229a7d2f72aa4c258f4e","abstract_canon_sha256":"e08d12bf35243fd4401e2eb74161890bc8dccbb45767c6db23883f89c7bb53ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:45.693551Z","signature_b64":"rb59NT9Tmr7QiQXeGG8FOpB54UkAogQr3tRVZdPFkYk9BVqWF70yme3LsyjKs9/S+Te4sc8unttVJey08YeeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282e25c470cd43a190bb4470ba359971b077f61b96eaf8504bf7c4578d9f2dbb","last_reissued_at":"2026-07-05T10:41:45.693032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:45.693032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yuchen Duan, Yu Qiao, Zhe Chen","submitted_at":"2024-03-04T18:46:20Z","abstract_excerpt":"Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model adapted from the RWKV model used in the NLP field with necessary modifications for vision tasks. Similar to the Vision Transformer (ViT), our model is designed to efficiently handle sparse inputs and demonstrate robust global processing capabilities, while also scaling up effectively, accommodating both large-scale parameters and extensi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02308","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/2403.02308/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":"2403.02308","created_at":"2026-07-05T10:41:45.693088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02308v3","created_at":"2026-07-05T10:41:45.693088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02308","created_at":"2026-07-05T10:41:45.693088+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAXCLRDQZVB2","created_at":"2026-07-05T10:41:45.693088+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAXCLRDQZVB2DEF3","created_at":"2026-07-05T10:41:45.693088+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAXCLRDQ","created_at":"2026-07-05T10:41:45.693088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30027","citing_title":"Cross-Modal Iteration Distillation for Robust IHD Screening: The IDNet Framework and A New Benchmark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14926","citing_title":"SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03633","citing_title":"MFC-RFNet: A Multi-scale Guided Rectified Flow Network for Radar Sequence Prediction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10341","citing_title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17278","citing_title":"PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG","json":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG.json","graph_json":"https://pith.science/api/pith-number/FAXCLRDQZVB2DEF3IRYLUNMZOG/graph.json","events_json":"https://pith.science/api/pith-number/FAXCLRDQZVB2DEF3IRYLUNMZOG/events.json","paper":"https://pith.science/paper/FAXCLRDQ"},"agent_actions":{"view_html":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG","download_json":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG.json","view_paper":"https://pith.science/paper/FAXCLRDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02308&json=true","fetch_graph":"https://pith.science/api/pith-number/FAXCLRDQZVB2DEF3IRYLUNMZOG/graph.json","fetch_events":"https://pith.science/api/pith-number/FAXCLRDQZVB2DEF3IRYLUNMZOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG/action/storage_attestation","attest_author":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG/action/author_attestation","sign_citation":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG/action/citation_signature","submit_replication":"https://pith.science/pith/FAXCLRDQZVB2DEF3IRYLUNMZOG/action/replication_record"}},"created_at":"2026-07-05T10:41:45.693088+00:00","updated_at":"2026-07-05T10:41:45.693088+00:00"}