{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DNPPLJFVLBCVLR7S55MWUIKNE","short_pith_number":"pith:4DNPPLJF","schema_version":"1.0","canonical_sha256":"e0daf7ad25aac22aae3f977acb510a6910ca49903f222ce5e769796c75f244f0","source":{"kind":"arxiv","id":"2502.02479","version":1},"attestation_state":"computed","paper":{"title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Muhan Zhang, Xiyuan Wang","submitted_at":"2025-02-04T16:54:28Z","abstract_excerpt":"Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures tailored to exploit noise for specific tasks excel yet lack broad applicability. This paper tackles these issues by laying down a theoretical framework that elucidates the increased sample complexity when introducing random noise into GNNs without careful design. We further propose Equivariant Noise GNN (ENGNN), a novel architecture that harnesses the symmet"},"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":"2502.02479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T16:54:28Z","cross_cats_sorted":[],"title_canon_sha256":"a34dbefc8b777c4dbc4003e7334b03bf8ae0a096af3d3bab004d7c36f082ada6","abstract_canon_sha256":"f9be74c5c500ef2dee28fccd8fafb45ebd1d1861d486dea0af296d81619342a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:29.255780Z","signature_b64":"cLcvqhKUvr/0OMz9esatnh7AagC438EPTc9sVfbbpipylTYSBMhsvzrYMIBzbDQaGAWojh8XMXG5dmW9JeFwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0daf7ad25aac22aae3f977acb510a6910ca49903f222ce5e769796c75f244f0","last_reissued_at":"2026-07-05T10:09:29.255224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:29.255224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Muhan Zhang, Xiyuan Wang","submitted_at":"2025-02-04T16:54:28Z","abstract_excerpt":"Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures tailored to exploit noise for specific tasks excel yet lack broad applicability. This paper tackles these issues by laying down a theoretical framework that elucidates the increased sample complexity when introducing random noise into GNNs without careful design. We further propose Equivariant Noise GNN (ENGNN), a novel architecture that harnesses the symmet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02479","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/2502.02479/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":"2502.02479","created_at":"2026-07-05T10:09:29.255288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02479v1","created_at":"2026-07-05T10:09:29.255288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02479","created_at":"2026-07-05T10:09:29.255288+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DNPPLJFVLBC","created_at":"2026-07-05T10:09:29.255288+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DNPPLJFVLBCVLR7","created_at":"2026-07-05T10:09:29.255288+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DNPPLJF","created_at":"2026-07-05T10:09:29.255288+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/4DNPPLJFVLBCVLR7S55MWUIKNE","json":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE.json","graph_json":"https://pith.science/api/pith-number/4DNPPLJFVLBCVLR7S55MWUIKNE/graph.json","events_json":"https://pith.science/api/pith-number/4DNPPLJFVLBCVLR7S55MWUIKNE/events.json","paper":"https://pith.science/paper/4DNPPLJF"},"agent_actions":{"view_html":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE","download_json":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE.json","view_paper":"https://pith.science/paper/4DNPPLJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02479&json=true","fetch_graph":"https://pith.science/api/pith-number/4DNPPLJFVLBCVLR7S55MWUIKNE/graph.json","fetch_events":"https://pith.science/api/pith-number/4DNPPLJFVLBCVLR7S55MWUIKNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE/action/storage_attestation","attest_author":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE/action/author_attestation","sign_citation":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE/action/citation_signature","submit_replication":"https://pith.science/pith/4DNPPLJFVLBCVLR7S55MWUIKNE/action/replication_record"}},"created_at":"2026-07-05T10:09:29.255288+00:00","updated_at":"2026-07-05T10:09:29.255288+00:00"}