{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E6J2WK7EQ36J6YG6L2BFN367OE","short_pith_number":"pith:E6J2WK7E","schema_version":"1.0","canonical_sha256":"2793ab2be486fc9f60de5e8256efdf71308d939018592ae2aaae841a0f3d435d","source":{"kind":"arxiv","id":"2305.06142","version":2},"attestation_state":"computed","paper":{"title":"Feature Expansion for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guangyi Chen, Jiaqi Sun, Kun Zhang, Lin Zhang, Peng Xu, Yujiu Yang","submitted_at":"2023-05-10T13:45:57Z","abstract_excerpt":"Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification. Recently, many methods have studied the representations of GNNs from the perspective of optimization goals and spectral graph theory. However, the feature space that dominates representation learning has not been systematically studied in graph neural networks. In this paper, we propose to fill this gap by analyzing the feature space of both spatial and spectral models. We decompose graph neural networks into determined feature spaces and trainable "},"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":"2305.06142","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T13:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"3f5c33dfdf11b7b492fb009aba4d89084c79800477a6901c1aec9993b1cdce7a","abstract_canon_sha256":"aa7d6abe308c3c5ed817016a624db98ba8241eb9f972be7e2f979310910f1895"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:42.747482Z","signature_b64":"vRTWTRDUZa/hxWzjSXC1lvRnqG1Za5qQjHE9PGrJIweNGKQRZ2eexoEGWK5oakoifQBirjeRxrfBqSkdPNuDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2793ab2be486fc9f60de5e8256efdf71308d939018592ae2aaae841a0f3d435d","last_reissued_at":"2026-07-05T06:14:42.746950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:42.746950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Expansion for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guangyi Chen, Jiaqi Sun, Kun Zhang, Lin Zhang, Peng Xu, Yujiu Yang","submitted_at":"2023-05-10T13:45:57Z","abstract_excerpt":"Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification. Recently, many methods have studied the representations of GNNs from the perspective of optimization goals and spectral graph theory. However, the feature space that dominates representation learning has not been systematically studied in graph neural networks. In this paper, we propose to fill this gap by analyzing the feature space of both spatial and spectral models. We decompose graph neural networks into determined feature spaces and trainable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06142","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/2305.06142/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":"2305.06142","created_at":"2026-07-05T06:14:42.747002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06142v2","created_at":"2026-07-05T06:14:42.747002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06142","created_at":"2026-07-05T06:14:42.747002+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6J2WK7EQ36J","created_at":"2026-07-05T06:14:42.747002+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6J2WK7EQ36J6YG6","created_at":"2026-07-05T06:14:42.747002+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6J2WK7E","created_at":"2026-07-05T06:14:42.747002+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/E6J2WK7EQ36J6YG6L2BFN367OE","json":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE.json","graph_json":"https://pith.science/api/pith-number/E6J2WK7EQ36J6YG6L2BFN367OE/graph.json","events_json":"https://pith.science/api/pith-number/E6J2WK7EQ36J6YG6L2BFN367OE/events.json","paper":"https://pith.science/paper/E6J2WK7E"},"agent_actions":{"view_html":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE","download_json":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE.json","view_paper":"https://pith.science/paper/E6J2WK7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06142&json=true","fetch_graph":"https://pith.science/api/pith-number/E6J2WK7EQ36J6YG6L2BFN367OE/graph.json","fetch_events":"https://pith.science/api/pith-number/E6J2WK7EQ36J6YG6L2BFN367OE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE/action/storage_attestation","attest_author":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE/action/author_attestation","sign_citation":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE/action/citation_signature","submit_replication":"https://pith.science/pith/E6J2WK7EQ36J6YG6L2BFN367OE/action/replication_record"}},"created_at":"2026-07-05T06:14:42.747002+00:00","updated_at":"2026-07-05T06:14:42.747002+00:00"}