{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ULAXHJTRHXVPE52SBIHZ2MOPJL","short_pith_number":"pith:ULAXHJTR","schema_version":"1.0","canonical_sha256":"a2c173a6713deaf277520a0f9d31cf4ad3721d4c60a881c78e01a2150656be48","source":{"kind":"arxiv","id":"2202.03580","version":5},"attestation_state":"computed","paper":{"title":"Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ji-Rong Wen, Mingguo He, Zhewei Wei","submitted_at":"2022-02-04T09:11:13Z","abstract_excerpt":"Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Cheb"},"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":"2202.03580","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T09:11:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69fe1ac3ff117a731741400ec35f6bd5b424cc75f4580e8c391a59a2dbfe8c1a","abstract_canon_sha256":"790fa7fba6128b9c867482d344f72ca8633affddf62d04eaeadf1f9fb4f45909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:46.568434Z","signature_b64":"3hmPZBQQvPegbz0M8Qfjgebo2HE1cUIUsWNGoROlW2L3cQwCdSvyrBCyF0tRjjCC7KqI+yZlS2xgW+UaYgyQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2c173a6713deaf277520a0f9d31cf4ad3721d4c60a881c78e01a2150656be48","last_reissued_at":"2026-07-05T07:54:46.568041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:46.568041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ji-Rong Wen, Mingguo He, Zhewei Wei","submitted_at":"2022-02-04T09:11:13Z","abstract_excerpt":"Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Cheb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03580","kind":"arxiv","version":5},"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/2202.03580/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":"2202.03580","created_at":"2026-07-05T07:54:46.568099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03580v5","created_at":"2026-07-05T07:54:46.568099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03580","created_at":"2026-07-05T07:54:46.568099+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULAXHJTRHXVP","created_at":"2026-07-05T07:54:46.568099+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULAXHJTRHXVPE52S","created_at":"2026-07-05T07:54:46.568099+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULAXHJTR","created_at":"2026-07-05T07:54:46.568099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.07420","citing_title":"KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL","json":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL.json","graph_json":"https://pith.science/api/pith-number/ULAXHJTRHXVPE52SBIHZ2MOPJL/graph.json","events_json":"https://pith.science/api/pith-number/ULAXHJTRHXVPE52SBIHZ2MOPJL/events.json","paper":"https://pith.science/paper/ULAXHJTR"},"agent_actions":{"view_html":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL","download_json":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL.json","view_paper":"https://pith.science/paper/ULAXHJTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03580&json=true","fetch_graph":"https://pith.science/api/pith-number/ULAXHJTRHXVPE52SBIHZ2MOPJL/graph.json","fetch_events":"https://pith.science/api/pith-number/ULAXHJTRHXVPE52SBIHZ2MOPJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL/action/storage_attestation","attest_author":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL/action/author_attestation","sign_citation":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL/action/citation_signature","submit_replication":"https://pith.science/pith/ULAXHJTRHXVPE52SBIHZ2MOPJL/action/replication_record"}},"created_at":"2026-07-05T07:54:46.568099+00:00","updated_at":"2026-07-05T07:54:46.568099+00:00"}