{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7BRDMLYN4BW7ZPIAXKHECRH5XE","short_pith_number":"pith:7BRDMLYN","schema_version":"1.0","canonical_sha256":"f862362f0de06dfcbd00ba8e4144fdb9213c4eab8a68b27fa75377986d26b16b","source":{"kind":"arxiv","id":"2510.10101","version":4},"attestation_state":"computed","paper":{"title":"On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caio F. Deberaldini Netto, Caterina Graziani, Ehimare Okoyomon, Martin Carrasco, Vahan A. Martirosyan","submitted_at":"2025-10-11T08:24:07Z","abstract_excerpt":"Understanding the interplay between generalization, expressivity, and the geometry of the input space is a central challenge in graph learning. The expressivity of Graph Neural Networks (GNNs) is typically characterized through their correspondence with graph invariants, such as those from the Weisfeiler-Leman (WL) hierarchy. While more expressive GNNs can distinguish a richer set of graphs, they are also associated with weaker generalization guarantees. Previous works have addressed this trade-off using the VC dimension, a purely combinatorial measure, independent of the training data. In thi"},"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":"2510.10101","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T08:24:07Z","cross_cats_sorted":[],"title_canon_sha256":"191e117b323c53f7ad95b0aacc17daf4e1d4092e931863d9f0c50a884e5d074e","abstract_canon_sha256":"74dfdbc81b1cd5318ed095bac4de9f2c0664995849bbae701c9133e0cf8569bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f862362f0de06dfcbd00ba8e4144fdb9213c4eab8a68b27fa75377986d26b16b","last_reissued_at":"2026-07-30T01:19:13.072400Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:13.072400Z"},"graph_snapshot":{"paper":{"title":"On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caio F. Deberaldini Netto, Caterina Graziani, Ehimare Okoyomon, Martin Carrasco, Vahan A. Martirosyan","submitted_at":"2025-10-11T08:24:07Z","abstract_excerpt":"Understanding the interplay between generalization, expressivity, and the geometry of the input space is a central challenge in graph learning. The expressivity of Graph Neural Networks (GNNs) is typically characterized through their correspondence with graph invariants, such as those from the Weisfeiler-Leman (WL) hierarchy. While more expressive GNNs can distinguish a richer set of graphs, they are also associated with weaker generalization guarantees. Previous works have addressed this trade-off using the VC dimension, a purely combinatorial measure, independent of the training data. In thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10101","kind":"arxiv","version":4},"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/2510.10101/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":"2510.10101","created_at":"2026-07-30T01:19:13.077554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10101v4","created_at":"2026-07-30T01:19:13.077554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10101","created_at":"2026-07-30T01:19:13.077554+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BRDMLYN4BW7","created_at":"2026-07-30T01:19:13.077554+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BRDMLYN4BW7ZPIA","created_at":"2026-07-30T01:19:13.077554+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BRDMLYN","created_at":"2026-07-30T01:19:13.077554+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/7BRDMLYN4BW7ZPIAXKHECRH5XE","json":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE.json","graph_json":"https://pith.science/api/pith-number/7BRDMLYN4BW7ZPIAXKHECRH5XE/graph.json","events_json":"https://pith.science/api/pith-number/7BRDMLYN4BW7ZPIAXKHECRH5XE/events.json","paper":"https://pith.science/paper/7BRDMLYN"},"agent_actions":{"view_html":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE","download_json":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE.json","view_paper":"https://pith.science/paper/7BRDMLYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10101&json=true","fetch_graph":"https://pith.science/api/pith-number/7BRDMLYN4BW7ZPIAXKHECRH5XE/graph.json","fetch_events":"https://pith.science/api/pith-number/7BRDMLYN4BW7ZPIAXKHECRH5XE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE/action/storage_attestation","attest_author":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE/action/author_attestation","sign_citation":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE/action/citation_signature","submit_replication":"https://pith.science/pith/7BRDMLYN4BW7ZPIAXKHECRH5XE/action/replication_record"}},"created_at":"2026-07-30T01:19:13.077554+00:00","updated_at":"2026-07-30T01:19:13.077554+00:00"}