{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ECFBY4VXC272QBK4E4P2TSHRDE","short_pith_number":"pith:ECFBY4VX","schema_version":"1.0","canonical_sha256":"208a1c72b716bfa8055c271fa9c8f1190727b6e9ed9c5139892eccb72eb925e8","source":{"kind":"arxiv","id":"2407.14772","version":2},"attestation_state":"computed","paper":{"title":"Subgraph Clustering and Atom Learning for Improved Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aryan Singh, Ciar\\'an Eising, Patrick Denny, Pepijn Van de Ven","submitted_at":"2024-07-20T06:32:00Z","abstract_excerpt":"In this study, we present the Graph Sub-Graph Network (GSN), a novel hybrid image classification model merging the strengths of Convolutional Neural Networks (CNNs) for feature extraction and Graph Neural Networks (GNNs) for structural modeling. GSN employs k-means clustering to group graph nodes into clusters, facilitating the creation of subgraphs. These subgraphs are then utilized to learn representative `atoms` for dictionary learning, enabling the identification of sparse, class-distinguishable features. This integrated approach is particularly relevant in domains like medical imaging, wh"},"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":"2407.14772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-20T06:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"6cb3f4739aa8f5f706d4b11e7e9ccd440a717e103abb55a2849e9e2553b77018","abstract_canon_sha256":"9344276cf421e3941749adb5e537b9a270a67e86eba55761740b69063bdd2e72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:37.715549Z","signature_b64":"QTN82VebVpDM+DDHzHMLBUkslw6+BSBHFAnB3ZiD9zGygCXGllk8SVMY5xaJd1OGz8yUCMUcGLzQTkEQgwujAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208a1c72b716bfa8055c271fa9c8f1190727b6e9ed9c5139892eccb72eb925e8","last_reissued_at":"2026-07-05T09:13:37.715004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:37.715004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subgraph Clustering and Atom Learning for Improved Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aryan Singh, Ciar\\'an Eising, Patrick Denny, Pepijn Van de Ven","submitted_at":"2024-07-20T06:32:00Z","abstract_excerpt":"In this study, we present the Graph Sub-Graph Network (GSN), a novel hybrid image classification model merging the strengths of Convolutional Neural Networks (CNNs) for feature extraction and Graph Neural Networks (GNNs) for structural modeling. GSN employs k-means clustering to group graph nodes into clusters, facilitating the creation of subgraphs. These subgraphs are then utilized to learn representative `atoms` for dictionary learning, enabling the identification of sparse, class-distinguishable features. This integrated approach is particularly relevant in domains like medical imaging, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14772","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/2407.14772/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":"2407.14772","created_at":"2026-07-05T09:13:37.715073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14772v2","created_at":"2026-07-05T09:13:37.715073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14772","created_at":"2026-07-05T09:13:37.715073+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECFBY4VXC272","created_at":"2026-07-05T09:13:37.715073+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECFBY4VXC272QBK4","created_at":"2026-07-05T09:13:37.715073+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECFBY4VX","created_at":"2026-07-05T09:13:37.715073+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/ECFBY4VXC272QBK4E4P2TSHRDE","json":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE.json","graph_json":"https://pith.science/api/pith-number/ECFBY4VXC272QBK4E4P2TSHRDE/graph.json","events_json":"https://pith.science/api/pith-number/ECFBY4VXC272QBK4E4P2TSHRDE/events.json","paper":"https://pith.science/paper/ECFBY4VX"},"agent_actions":{"view_html":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE","download_json":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE.json","view_paper":"https://pith.science/paper/ECFBY4VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14772&json=true","fetch_graph":"https://pith.science/api/pith-number/ECFBY4VXC272QBK4E4P2TSHRDE/graph.json","fetch_events":"https://pith.science/api/pith-number/ECFBY4VXC272QBK4E4P2TSHRDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE/action/storage_attestation","attest_author":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE/action/author_attestation","sign_citation":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE/action/citation_signature","submit_replication":"https://pith.science/pith/ECFBY4VXC272QBK4E4P2TSHRDE/action/replication_record"}},"created_at":"2026-07-05T09:13:37.715073+00:00","updated_at":"2026-07-05T09:13:37.715073+00:00"}