{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MI3U65ZH7PHTQUVPDQWXL6ZDEJ","short_pith_number":"pith:MI3U65ZH","schema_version":"1.0","canonical_sha256":"62374f7727fbcf3852af1c2d75fb2322405253bcc19fa522bfb89f7d5e8d640d","source":{"kind":"arxiv","id":"2307.00395","version":1},"attestation_state":"computed","paper":{"title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mustafa Munir, Radu Marculescu, William Avery","submitted_at":"2023-07-01T17:49:12Z","abstract_excerpt":"Traditionally, convolutional neural networks (CNN) and vision transformers (ViT) have dominated computer vision. However, recently proposed vision graph neural networks (ViG) provide a new avenue for exploration. Unfortunately, for mobile applications, ViGs are computationally expensive due to the overhead of representing images as graph structures. In this work, we propose a new graph-based sparse attention mechanism, Sparse Vision Graph Attention (SVGA), that is designed for ViGs running on mobile devices. Additionally, we propose the first hybrid CNN-GNN architecture for vision tasks on mob"},"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":"2307.00395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-01T17:49:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c30a466f167353627c73e73620d1e5cfe21c9ab8ed0a839032f6ee30a753c50","abstract_canon_sha256":"7f59af5589cf7fa9fb9f65f6095658d54611643802509b866933c99e9a3edd20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:55.588703Z","signature_b64":"/qX7/q3xRX2xAM6hNDy6VkstWOCYvVv0wmHDrh9skv/fzLVHdxTpRqAHCpXjRkgt8+BIOp2YopXx3/CudRiCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62374f7727fbcf3852af1c2d75fb2322405253bcc19fa522bfb89f7d5e8d640d","last_reissued_at":"2026-07-05T06:26:55.588357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:55.588357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mustafa Munir, Radu Marculescu, William Avery","submitted_at":"2023-07-01T17:49:12Z","abstract_excerpt":"Traditionally, convolutional neural networks (CNN) and vision transformers (ViT) have dominated computer vision. However, recently proposed vision graph neural networks (ViG) provide a new avenue for exploration. Unfortunately, for mobile applications, ViGs are computationally expensive due to the overhead of representing images as graph structures. In this work, we propose a new graph-based sparse attention mechanism, Sparse Vision Graph Attention (SVGA), that is designed for ViGs running on mobile devices. Additionally, we propose the first hybrid CNN-GNN architecture for vision tasks on mob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00395","kind":"arxiv","version":1},"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/2307.00395/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":"2307.00395","created_at":"2026-07-05T06:26:55.588418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00395v1","created_at":"2026-07-05T06:26:55.588418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00395","created_at":"2026-07-05T06:26:55.588418+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI3U65ZH7PHT","created_at":"2026-07-05T06:26:55.588418+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI3U65ZH7PHTQUVP","created_at":"2026-07-05T06:26:55.588418+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI3U65ZH","created_at":"2026-07-05T06:26:55.588418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21290","citing_title":"GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ","json":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ.json","graph_json":"https://pith.science/api/pith-number/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/graph.json","events_json":"https://pith.science/api/pith-number/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/events.json","paper":"https://pith.science/paper/MI3U65ZH"},"agent_actions":{"view_html":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ","download_json":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ.json","view_paper":"https://pith.science/paper/MI3U65ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00395&json=true","fetch_graph":"https://pith.science/api/pith-number/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/action/storage_attestation","attest_author":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/action/author_attestation","sign_citation":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/action/citation_signature","submit_replication":"https://pith.science/pith/MI3U65ZH7PHTQUVPDQWXL6ZDEJ/action/replication_record"}},"created_at":"2026-07-05T06:26:55.588418+00:00","updated_at":"2026-07-05T06:26:55.588418+00:00"}