{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PBUTI2CC2AWYJHQVA6NW73PJ45","short_pith_number":"pith:PBUTI2CC","schema_version":"1.0","canonical_sha256":"7869346842d02d849e15079b6fede9e76fa41532a0b42755b3c49b3a5aeafa96","source":{"kind":"arxiv","id":"2206.00272","version":3},"attestation_state":"computed","paper":{"title":"Vision GNN: An Image is Worth Graph of Nodes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang","submitted_at":"2022-06-01T07:01:04Z","abstract_excerpt":"Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex objects. In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. We first split the image to a number of patches which are viewed as nodes, and construct a graph by connecting the nearest neighbors. Based on the graph representation "},"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":"2206.00272","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T07:01:04Z","cross_cats_sorted":[],"title_canon_sha256":"d180fda46296189ae57c63f3f9edf3479c693174107e4e6732b3809a976f4aad","abstract_canon_sha256":"3fed43ef9d413a957a13d892d2b9585611dc16ac6f643be370c172797131e0f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:07.154291Z","signature_b64":"gmGMc01Nh4QDuZUI6hOxRZte+mog487K9lShzEVCvos5ney/AsnvCviHL63FcD5+njcN48fM9VqnLaDygjSfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7869346842d02d849e15079b6fede9e76fa41532a0b42755b3c49b3a5aeafa96","last_reissued_at":"2026-07-05T05:13:07.153805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:07.153805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision GNN: An Image is Worth Graph of Nodes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enhua Wu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang","submitted_at":"2022-06-01T07:01:04Z","abstract_excerpt":"Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex objects. In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. We first split the image to a number of patches which are viewed as nodes, and construct a graph by connecting the nearest neighbors. Based on the graph representation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00272","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/2206.00272/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":"2206.00272","created_at":"2026-07-05T05:13:07.153867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00272v3","created_at":"2026-07-05T05:13:07.153867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00272","created_at":"2026-07-05T05:13:07.153867+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBUTI2CC2AWY","created_at":"2026-07-05T05:13:07.153867+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBUTI2CC2AWYJHQV","created_at":"2026-07-05T05:13:07.153867+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBUTI2CC","created_at":"2026-07-05T05:13:07.153867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13131","citing_title":"ERPPO: Entropy Regularization-based Proximal Policy Optimization","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21290","citing_title":"GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45","json":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45.json","graph_json":"https://pith.science/api/pith-number/PBUTI2CC2AWYJHQVA6NW73PJ45/graph.json","events_json":"https://pith.science/api/pith-number/PBUTI2CC2AWYJHQVA6NW73PJ45/events.json","paper":"https://pith.science/paper/PBUTI2CC"},"agent_actions":{"view_html":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45","download_json":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45.json","view_paper":"https://pith.science/paper/PBUTI2CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00272&json=true","fetch_graph":"https://pith.science/api/pith-number/PBUTI2CC2AWYJHQVA6NW73PJ45/graph.json","fetch_events":"https://pith.science/api/pith-number/PBUTI2CC2AWYJHQVA6NW73PJ45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45/action/storage_attestation","attest_author":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45/action/author_attestation","sign_citation":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45/action/citation_signature","submit_replication":"https://pith.science/pith/PBUTI2CC2AWYJHQVA6NW73PJ45/action/replication_record"}},"created_at":"2026-07-05T05:13:07.153867+00:00","updated_at":"2026-07-05T05:13:07.153867+00:00"}