{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UVN2P32IDZMIPR772RISXPGA3P","short_pith_number":"pith:UVN2P32I","schema_version":"1.0","canonical_sha256":"a55ba7ef481e5887c7ffd4512bbcc0dbd5c6c18a3596bf7b19910b045c62424b","source":{"kind":"arxiv","id":"2608.09596","version":1},"attestation_state":"computed","paper":{"title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Killian Cressant, Pedro B. Velloso","submitted_at":"2026-08-10T13:30:46Z","abstract_excerpt":"Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long-range information is compressed through limited message-passing channels. Existing metrics such as Dirichlet energy provide global characterizations of over-smoothing but lack the resolution to analyze node-level behavior and guide architectural improvements. In this paper, we propose LEED (Local Embedding Evolution Distance), a novel local metric that quantifies over-smoothing by tracking the evolution of individua"},"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":"2608.09596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T13:30:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21ebfa1833c9c9176a04b10f05f2c6ed74c5a3a18dbec29eaa215a8de07a534e","abstract_canon_sha256":"02bd1f3bc848f7b168e983b6272aad41209291e54d199245e52524d8d66ad3ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:34.820623Z","signature_b64":"BHiljKgM++g12XwTV/NOX/+cnU+S2ghsAHlucK+ZMd2zcc+euK5fcZCszXORsVAb88lzDW/33JDWZrM2a12ABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a55ba7ef481e5887c7ffd4512bbcc0dbd5c6c18a3596bf7b19910b045c62424b","last_reissued_at":"2026-08-11T02:24:34.818994Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:34.818994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Killian Cressant, Pedro B. Velloso","submitted_at":"2026-08-10T13:30:46Z","abstract_excerpt":"Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long-range information is compressed through limited message-passing channels. Existing metrics such as Dirichlet energy provide global characterizations of over-smoothing but lack the resolution to analyze node-level behavior and guide architectural improvements. In this paper, we propose LEED (Local Embedding Evolution Distance), a novel local metric that quantifies over-smoothing by tracking the evolution of individua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09596","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/2608.09596/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":"2608.09596","created_at":"2026-08-11T02:24:34.819625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09596v1","created_at":"2026-08-11T02:24:34.819625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09596","created_at":"2026-08-11T02:24:34.819625+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVN2P32IDZMI","created_at":"2026-08-11T02:24:34.819625+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVN2P32IDZMIPR77","created_at":"2026-08-11T02:24:34.819625+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVN2P32I","created_at":"2026-08-11T02:24:34.819625+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/UVN2P32IDZMIPR772RISXPGA3P","json":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P.json","graph_json":"https://pith.science/api/pith-number/UVN2P32IDZMIPR772RISXPGA3P/graph.json","events_json":"https://pith.science/api/pith-number/UVN2P32IDZMIPR772RISXPGA3P/events.json","paper":"https://pith.science/paper/UVN2P32I"},"agent_actions":{"view_html":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P","download_json":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P.json","view_paper":"https://pith.science/paper/UVN2P32I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09596&json=true","fetch_graph":"https://pith.science/api/pith-number/UVN2P32IDZMIPR772RISXPGA3P/graph.json","fetch_events":"https://pith.science/api/pith-number/UVN2P32IDZMIPR772RISXPGA3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P/action/storage_attestation","attest_author":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P/action/author_attestation","sign_citation":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P/action/citation_signature","submit_replication":"https://pith.science/pith/UVN2P32IDZMIPR772RISXPGA3P/action/replication_record"}},"created_at":"2026-08-11T02:24:34.819625+00:00","updated_at":"2026-08-11T02:24:34.819625+00:00"}