{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ONYPPE5QCPEVCHBZ32J6NOZVG7","short_pith_number":"pith:ONYPPE5Q","schema_version":"1.0","canonical_sha256":"7370f793b013c9511c39de93e6bb3537cf7e56b435a71ba29b91f68fdbea454b","source":{"kind":"arxiv","id":"2310.09202","version":2},"attestation_state":"computed","paper":{"title":"Graph Distillation with Eigenbasis Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Deyu Bo, Yang Liu","submitted_at":"2023-10-13T15:48:12Z","abstract_excerpt":"The increasing amount of graph data places requirements on the efficient training of graph neural networks (GNNs). The emerging graph distillation (GD) tackles this challenge by distilling a small synthetic graph to replace the real large graph, ensuring GNNs trained on real and synthetic graphs exhibit comparable performance. However, existing methods rely on GNN-related information as supervision, including gradients, representations, and trajectories, which have two limitations. First, GNNs can affect the spectrum (i.e., eigenvalues) of the real graph, causing spectrum bias in the synthetic"},"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":"2310.09202","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T15:48:12Z","cross_cats_sorted":[],"title_canon_sha256":"1c37bf366bc65ed6ebf2bee355dc5575dd3a80c216e7aa9231a34a88477d3b43","abstract_canon_sha256":"bd4cd8ff53fcd451834df7344605b92da740f5b933476c38a7fb9901f548e260"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:45.101150Z","signature_b64":"frdET6Mhx/NTK6IqdtG3riZ9fLktqBy3KY4SXSx3kYb/ExYZobDFBgV527P1kUDN/X8ofb6h+EkUksHPWcj+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7370f793b013c9511c39de93e6bb3537cf7e56b435a71ba29b91f68fdbea454b","last_reissued_at":"2026-07-05T08:18:45.100595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:45.100595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Distillation with Eigenbasis Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Deyu Bo, Yang Liu","submitted_at":"2023-10-13T15:48:12Z","abstract_excerpt":"The increasing amount of graph data places requirements on the efficient training of graph neural networks (GNNs). The emerging graph distillation (GD) tackles this challenge by distilling a small synthetic graph to replace the real large graph, ensuring GNNs trained on real and synthetic graphs exhibit comparable performance. However, existing methods rely on GNN-related information as supervision, including gradients, representations, and trajectories, which have two limitations. First, GNNs can affect the spectrum (i.e., eigenvalues) of the real graph, causing spectrum bias in the synthetic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09202","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/2310.09202/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":"2310.09202","created_at":"2026-07-05T08:18:45.100676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09202v2","created_at":"2026-07-05T08:18:45.100676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09202","created_at":"2026-07-05T08:18:45.100676+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONYPPE5QCPEV","created_at":"2026-07-05T08:18:45.100676+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONYPPE5QCPEVCHBZ","created_at":"2026-07-05T08:18:45.100676+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONYPPE5Q","created_at":"2026-07-05T08:18:45.100676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03154","citing_title":"DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06814","citing_title":"From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7","json":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7.json","graph_json":"https://pith.science/api/pith-number/ONYPPE5QCPEVCHBZ32J6NOZVG7/graph.json","events_json":"https://pith.science/api/pith-number/ONYPPE5QCPEVCHBZ32J6NOZVG7/events.json","paper":"https://pith.science/paper/ONYPPE5Q"},"agent_actions":{"view_html":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7","download_json":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7.json","view_paper":"https://pith.science/paper/ONYPPE5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09202&json=true","fetch_graph":"https://pith.science/api/pith-number/ONYPPE5QCPEVCHBZ32J6NOZVG7/graph.json","fetch_events":"https://pith.science/api/pith-number/ONYPPE5QCPEVCHBZ32J6NOZVG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7/action/storage_attestation","attest_author":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7/action/author_attestation","sign_citation":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7/action/citation_signature","submit_replication":"https://pith.science/pith/ONYPPE5QCPEVCHBZ32J6NOZVG7/action/replication_record"}},"created_at":"2026-07-05T08:18:45.100676+00:00","updated_at":"2026-07-05T08:18:45.100676+00:00"}