{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5Y2MDWCAT2STAF6JS4GURMSBVT","short_pith_number":"pith:5Y2MDWCA","schema_version":"1.0","canonical_sha256":"ee34c1d8409ea53017c9970d48b241aceeb7b03e14d53b736ea6b7056a735f3d","source":{"kind":"arxiv","id":"2404.04612","version":2},"attestation_state":"computed","paper":{"title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz","submitted_at":"2024-04-06T12:40:21Z","abstract_excerpt":"Message Passing Graph Neural Networks are known to suffer from two problems that are sometimes believed to be diametrically opposed: over-squashing and over-smoothing. The former results from topological bottlenecks that hamper the information flow from distant nodes and are mitigated by spectral gap maximization, primarily, by means of edge additions. However, such additions often promote over-smoothing that renders nodes of different classes less distinguishable. Inspired by the Braess phenomenon, we argue that deleting edges can address over-squashing and over-smoothing simultaneously. This"},"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":"2404.04612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T12:40:21Z","cross_cats_sorted":["eess.SP","stat.ML"],"title_canon_sha256":"3964e02654b4cab86db371277725e74a65554a71d9f0a192e1c81c901d90e955","abstract_canon_sha256":"d474cf18a381203a27450b01045ab7d617b43a05b81568e9713dc3b5507c5f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:29.908066Z","signature_b64":"wKxQwvsPlxl9a+RpS7sdJ25VhZ3LI4PJsR+k1Z3RhhIdfzIMVmjUeEm1luBIPHAkzga9y4uXN0ylAsVgh5Z6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee34c1d8409ea53017c9970d48b241aceeb7b03e14d53b736ea6b7056a735f3d","last_reissued_at":"2026-07-05T09:28:29.907529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:29.907529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz","submitted_at":"2024-04-06T12:40:21Z","abstract_excerpt":"Message Passing Graph Neural Networks are known to suffer from two problems that are sometimes believed to be diametrically opposed: over-squashing and over-smoothing. The former results from topological bottlenecks that hamper the information flow from distant nodes and are mitigated by spectral gap maximization, primarily, by means of edge additions. However, such additions often promote over-smoothing that renders nodes of different classes less distinguishable. Inspired by the Braess phenomenon, we argue that deleting edges can address over-squashing and over-smoothing simultaneously. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04612","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/2404.04612/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":"2404.04612","created_at":"2026-07-05T09:28:29.907602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04612v2","created_at":"2026-07-05T09:28:29.907602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04612","created_at":"2026-07-05T09:28:29.907602+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y2MDWCAT2ST","created_at":"2026-07-05T09:28:29.907602+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y2MDWCAT2STAF6J","created_at":"2026-07-05T09:28:29.907602+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y2MDWCA","created_at":"2026-07-05T09:28:29.907602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16110","citing_title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT","json":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT.json","graph_json":"https://pith.science/api/pith-number/5Y2MDWCAT2STAF6JS4GURMSBVT/graph.json","events_json":"https://pith.science/api/pith-number/5Y2MDWCAT2STAF6JS4GURMSBVT/events.json","paper":"https://pith.science/paper/5Y2MDWCA"},"agent_actions":{"view_html":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT","download_json":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT.json","view_paper":"https://pith.science/paper/5Y2MDWCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04612&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y2MDWCAT2STAF6JS4GURMSBVT/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y2MDWCAT2STAF6JS4GURMSBVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT/action/storage_attestation","attest_author":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT/action/author_attestation","sign_citation":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT/action/citation_signature","submit_replication":"https://pith.science/pith/5Y2MDWCAT2STAF6JS4GURMSBVT/action/replication_record"}},"created_at":"2026-07-05T09:28:29.907602+00:00","updated_at":"2026-07-05T09:28:29.907602+00:00"}