{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LF3X5ODT6ZBYKNHDJWB7TQNB7W","short_pith_number":"pith:LF3X5ODT","schema_version":"1.0","canonical_sha256":"59777eb873f6438534e34d83f9c1a1fd954083b93f5df2a80e1ef8fac4667bf5","source":{"kind":"arxiv","id":"2002.05544","version":2},"attestation_state":"computed","paper":{"title":"Superpixel Image Classification with Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anderson R. Tavares, Cl\\'audio R. Jung, Lu\\'is C. Lamb, Pedro H. C. Avelar, Thiago L. T. da Silveira","submitted_at":"2020-02-13T14:52:32Z","abstract_excerpt":"This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models. Although raw image classifiers perform better than GATs due to information loss during the RAG generation, our methodology opens an interesting avenue of research on deep learning beyond rectangular-g"},"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":"2002.05544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T14:52:32Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"af35a30fff9671b670cdcc84d093fb9508838c88d07686a14601e51743b0f685","abstract_canon_sha256":"a5ba74d9ce433999ff0089d4057ec67743a3d35b11fa17d5fa4ca927b845a56c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:39.394890Z","signature_b64":"TR9sQU8gwkOMVU1JT62hoczz6ga6fAZ7Mz2K9HgfDc4C89FizAZTu7nzflB+E7FxaS5OTUYqRbISUjNWj5VtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59777eb873f6438534e34d83f9c1a1fd954083b93f5df2a80e1ef8fac4667bf5","last_reissued_at":"2026-07-05T01:51:39.394444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:39.394444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Superpixel Image Classification with Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anderson R. Tavares, Cl\\'audio R. Jung, Lu\\'is C. Lamb, Pedro H. C. Avelar, Thiago L. T. da Silveira","submitted_at":"2020-02-13T14:52:32Z","abstract_excerpt":"This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models. Although raw image classifiers perform better than GATs due to information loss during the RAG generation, our methodology opens an interesting avenue of research on deep learning beyond rectangular-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05544","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/2002.05544/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":"2002.05544","created_at":"2026-07-05T01:51:39.394504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05544v2","created_at":"2026-07-05T01:51:39.394504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05544","created_at":"2026-07-05T01:51:39.394504+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF3X5ODT6ZBY","created_at":"2026-07-05T01:51:39.394504+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF3X5ODT6ZBYKNHD","created_at":"2026-07-05T01:51:39.394504+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF3X5ODT","created_at":"2026-07-05T01:51:39.394504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W","json":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W.json","graph_json":"https://pith.science/api/pith-number/LF3X5ODT6ZBYKNHDJWB7TQNB7W/graph.json","events_json":"https://pith.science/api/pith-number/LF3X5ODT6ZBYKNHDJWB7TQNB7W/events.json","paper":"https://pith.science/paper/LF3X5ODT"},"agent_actions":{"view_html":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W","download_json":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W.json","view_paper":"https://pith.science/paper/LF3X5ODT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05544&json=true","fetch_graph":"https://pith.science/api/pith-number/LF3X5ODT6ZBYKNHDJWB7TQNB7W/graph.json","fetch_events":"https://pith.science/api/pith-number/LF3X5ODT6ZBYKNHDJWB7TQNB7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W/action/storage_attestation","attest_author":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W/action/author_attestation","sign_citation":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W/action/citation_signature","submit_replication":"https://pith.science/pith/LF3X5ODT6ZBYKNHDJWB7TQNB7W/action/replication_record"}},"created_at":"2026-07-05T01:51:39.394504+00:00","updated_at":"2026-07-05T01:51:39.394504+00:00"}