{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BSRVU7GTB3YNHFPPVRJRSNL4XD","short_pith_number":"pith:BSRVU7GT","schema_version":"1.0","canonical_sha256":"0ca35a7cd30ef0d395efac5319357cb8d03184f332dd8a0be5fe4856041611a8","source":{"kind":"arxiv","id":"1905.05178","version":1},"attestation_state":"computed","paper":{"title":"Graph U-Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyang Gao, Shuiwang Ji","submitted_at":"2019-05-11T14:10:04Z","abstract_excerpt":"We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operat"},"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":"1905.05178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-11T14:10:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7d8eb56d1fe3edbcd450fa4c9d5ed9ea77073767b7df9efada93886f51e61900","abstract_canon_sha256":"1785fa406731049642770f269bbb3e0a63fcc93e61c46815d5fc1fc5e86f9d43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:17.233988Z","signature_b64":"nWyMxI6gZVDmKyKm2z63MMte+i5lJrrcgFfbTX3onsGnZh6x8WbtucH0E/aKJTElErClVQ1BGU5bp1xoR6YnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca35a7cd30ef0d395efac5319357cb8d03184f332dd8a0be5fe4856041611a8","last_reissued_at":"2026-05-17T23:46:17.233264Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:17.233264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph U-Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyang Gao, Shuiwang Ji","submitted_at":"2019-05-11T14:10:04Z","abstract_excerpt":"We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05178","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":""},"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":"1905.05178","created_at":"2026-05-17T23:46:17.233392+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05178v1","created_at":"2026-05-17T23:46:17.233392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05178","created_at":"2026-05-17T23:46:17.233392+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSRVU7GTB3YN","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSRVU7GTB3YNHFPP","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSRVU7GT","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2003.03485","citing_title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD","json":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD.json","graph_json":"https://pith.science/api/pith-number/BSRVU7GTB3YNHFPPVRJRSNL4XD/graph.json","events_json":"https://pith.science/api/pith-number/BSRVU7GTB3YNHFPPVRJRSNL4XD/events.json","paper":"https://pith.science/paper/BSRVU7GT"},"agent_actions":{"view_html":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD","download_json":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD.json","view_paper":"https://pith.science/paper/BSRVU7GT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05178&json=true","fetch_graph":"https://pith.science/api/pith-number/BSRVU7GTB3YNHFPPVRJRSNL4XD/graph.json","fetch_events":"https://pith.science/api/pith-number/BSRVU7GTB3YNHFPPVRJRSNL4XD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD/action/storage_attestation","attest_author":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD/action/author_attestation","sign_citation":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD/action/citation_signature","submit_replication":"https://pith.science/pith/BSRVU7GTB3YNHFPPVRJRSNL4XD/action/replication_record"}},"created_at":"2026-05-17T23:46:17.233392+00:00","updated_at":"2026-05-17T23:46:17.233392+00:00"}