{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YWSTFKIG36Q6TT6OUUIQF4WN6A","short_pith_number":"pith:YWSTFKIG","schema_version":"1.0","canonical_sha256":"c5a532a906dfa1e9cfcea51102f2cdf0166b49591fc5e0ad7a1af7d5054d1c78","source":{"kind":"arxiv","id":"2406.04336","version":1},"attestation_state":"computed","paper":{"title":"On the Expressive Power of Spectral Invariant Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DM","cs.DS","math.CO","math.SP"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Haggai Maron, Lingxiao Zhao","submitted_at":"2024-06-06T17:59:41Z","abstract_excerpt":"Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvectors. Various architectures have been proposed to address this ambiguity, referred to as spectral invariant architectures. Notable examples include GNNs and Graph Transformers that use spectral distances, spectral projection matrices, or other invariant spectral features. However, the potential expressive power of these spectral invariant architectures remains largely unclear. The goal of this work is to gain a deep t"},"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":"2406.04336","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T17:59:41Z","cross_cats_sorted":["cs.DM","cs.DS","math.CO","math.SP"],"title_canon_sha256":"51b7ace5dd94b56af5462dca635ba57cd42277bf130e0da9911b51c1138f7311","abstract_canon_sha256":"b9a3605835e1f302066950e5af13d100c36dde2cc6c237ff7c4b1f7bc6ed796b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:29.588343Z","signature_b64":"T0ryiDKg28ghArO/3uz40V4Tu1Zk8ZUsTl4ErAE48DOms3QAlBXLXhpXSwgXFl8Ihp3KQGkZXRatpizhuyBrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a532a906dfa1e9cfcea51102f2cdf0166b49591fc5e0ad7a1af7d5054d1c78","last_reissued_at":"2026-07-05T08:28:29.587924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:29.587924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Expressive Power of Spectral Invariant Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DM","cs.DS","math.CO","math.SP"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Haggai Maron, Lingxiao Zhao","submitted_at":"2024-06-06T17:59:41Z","abstract_excerpt":"Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvectors. Various architectures have been proposed to address this ambiguity, referred to as spectral invariant architectures. Notable examples include GNNs and Graph Transformers that use spectral distances, spectral projection matrices, or other invariant spectral features. However, the potential expressive power of these spectral invariant architectures remains largely unclear. The goal of this work is to gain a deep t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04336","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.04336/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":"2406.04336","created_at":"2026-07-05T08:28:29.587980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04336v1","created_at":"2026-07-05T08:28:29.587980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04336","created_at":"2026-07-05T08:28:29.587980+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWSTFKIG36Q6","created_at":"2026-07-05T08:28:29.587980+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWSTFKIG36Q6TT6O","created_at":"2026-07-05T08:28:29.587980+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWSTFKIG","created_at":"2026-07-05T08:28:29.587980+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/YWSTFKIG36Q6TT6OUUIQF4WN6A","json":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A.json","graph_json":"https://pith.science/api/pith-number/YWSTFKIG36Q6TT6OUUIQF4WN6A/graph.json","events_json":"https://pith.science/api/pith-number/YWSTFKIG36Q6TT6OUUIQF4WN6A/events.json","paper":"https://pith.science/paper/YWSTFKIG"},"agent_actions":{"view_html":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A","download_json":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A.json","view_paper":"https://pith.science/paper/YWSTFKIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04336&json=true","fetch_graph":"https://pith.science/api/pith-number/YWSTFKIG36Q6TT6OUUIQF4WN6A/graph.json","fetch_events":"https://pith.science/api/pith-number/YWSTFKIG36Q6TT6OUUIQF4WN6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A/action/storage_attestation","attest_author":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A/action/author_attestation","sign_citation":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A/action/citation_signature","submit_replication":"https://pith.science/pith/YWSTFKIG36Q6TT6OUUIQF4WN6A/action/replication_record"}},"created_at":"2026-07-05T08:28:29.587980+00:00","updated_at":"2026-07-05T08:28:29.587980+00:00"}