{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4U3BKXEURWWGGGY5XF4FMCOGG","short_pith_number":"pith:W4U3BKXE","schema_version":"1.0","canonical_sha256":"b729b0aae4a46d6318d8edcbc2b04e31b3fb826038d7a8be77ee104e34a1cb16","source":{"kind":"arxiv","id":"2502.07364","version":2},"attestation_state":"computed","paper":{"title":"Effects of Dropout on Performance in Long-range Graph Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brooks Paige, Jasraj Singh, Keyue Jiang, Laura Toni","submitted_at":"2025-02-11T08:36:38Z","abstract_excerpt":"Message Passing Neural Networks (MPNNs) are a class of Graph Neural Networks (GNNs) that propagate information across the graph via local neighborhoods. The scheme gives rise to two key challenges: over-smoothing and over-squashing. While several Dropout-style algorithms, such as DropEdge and DropMessage, have successfully addressed over-smoothing, their impact on over-squashing remains largely unexplored. This represents a critical gap in the literature, as failure to mitigate over-squashing would make these methods unsuitable for long-range tasks -- the intended use case of deep MPNNs. In th"},"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":"2502.07364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T08:36:38Z","cross_cats_sorted":[],"title_canon_sha256":"e1c9f1315925bb462d91c0d4d0ccc039666cb60ad24bf8118f5c076cf00c72ad","abstract_canon_sha256":"67170ce2c3c3f05f5c2faafbcce50b21f498d4b81aa8c26446d9ce0041b5332a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:41.131673Z","signature_b64":"xYsjlQD6f+XuMnJeemOxJgXJY+8qAW1BMz92hAjxcctMdn/mBYBhGXT4pcJiECYTPSGz8zpUHB8MwLcXa9/7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b729b0aae4a46d6318d8edcbc2b04e31b3fb826038d7a8be77ee104e34a1cb16","last_reissued_at":"2026-07-05T11:11:41.131173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:41.131173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effects of Dropout on Performance in Long-range Graph Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brooks Paige, Jasraj Singh, Keyue Jiang, Laura Toni","submitted_at":"2025-02-11T08:36:38Z","abstract_excerpt":"Message Passing Neural Networks (MPNNs) are a class of Graph Neural Networks (GNNs) that propagate information across the graph via local neighborhoods. The scheme gives rise to two key challenges: over-smoothing and over-squashing. While several Dropout-style algorithms, such as DropEdge and DropMessage, have successfully addressed over-smoothing, their impact on over-squashing remains largely unexplored. This represents a critical gap in the literature, as failure to mitigate over-squashing would make these methods unsuitable for long-range tasks -- the intended use case of deep MPNNs. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07364","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/2502.07364/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":"2502.07364","created_at":"2026-07-05T11:11:41.131227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07364v2","created_at":"2026-07-05T11:11:41.131227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07364","created_at":"2026-07-05T11:11:41.131227+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4U3BKXEURWW","created_at":"2026-07-05T11:11:41.131227+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4U3BKXEURWWGGGY","created_at":"2026-07-05T11:11:41.131227+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4U3BKXE","created_at":"2026-07-05T11:11:41.131227+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/W4U3BKXEURWWGGGY5XF4FMCOGG","json":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG.json","graph_json":"https://pith.science/api/pith-number/W4U3BKXEURWWGGGY5XF4FMCOGG/graph.json","events_json":"https://pith.science/api/pith-number/W4U3BKXEURWWGGGY5XF4FMCOGG/events.json","paper":"https://pith.science/paper/W4U3BKXE"},"agent_actions":{"view_html":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG","download_json":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG.json","view_paper":"https://pith.science/paper/W4U3BKXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07364&json=true","fetch_graph":"https://pith.science/api/pith-number/W4U3BKXEURWWGGGY5XF4FMCOGG/graph.json","fetch_events":"https://pith.science/api/pith-number/W4U3BKXEURWWGGGY5XF4FMCOGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG/action/storage_attestation","attest_author":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG/action/author_attestation","sign_citation":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG/action/citation_signature","submit_replication":"https://pith.science/pith/W4U3BKXEURWWGGGY5XF4FMCOGG/action/replication_record"}},"created_at":"2026-07-05T11:11:41.131227+00:00","updated_at":"2026-07-05T11:11:41.131227+00:00"}