{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W35ONVIT3J7H2FBRY56WR6UZWC","short_pith_number":"pith:W35ONVIT","schema_version":"1.0","canonical_sha256":"b6fae6d513da7e7d1431c77d68fa99b09e4d5c752611af47f58627ce525c6401","source":{"kind":"arxiv","id":"2311.07073","version":2},"attestation_state":"computed","paper":{"title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andi Han, Dai Shi, Junbin Gao, Lequan Lin, Yi Guo","submitted_at":"2023-11-13T04:40:13Z","abstract_excerpt":"Graph-based message-passing neural networks (MPNNs) have achieved remarkable success in both node and graph-level learning tasks. However, several identified problems, including over-smoothing (OSM), limited expressive power, and over-squashing (OSQ), still limit the performance of MPNNs. In particular, OSQ serves as the latest identified problem, where MPNNs gradually lose their learning accuracy when long-range dependencies between graph nodes are required. In this work, we provide an exposition on the OSQ problem by summarizing different formulations of OSQ from current literature, as well "},"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":"2311.07073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-13T04:40:13Z","cross_cats_sorted":[],"title_canon_sha256":"49619c50b85797f00f705a1b8c0b535b5ce2f5c2f2385d23fb51a58e01d2dc18","abstract_canon_sha256":"aae9474a6ea64c2fd222a1905275e10c26b7ec4246f5ea2fe644a94673d63947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:20.971525Z","signature_b64":"kYy6FGKymdFqGgjHeDBZkJ8mQSu65z4xIAsOqEdFfNvxa+6WGobwFv3h+coeauMXv2RkjWU/wHm32u10nd+HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6fae6d513da7e7d1431c77d68fa99b09e4d5c752611af47f58627ce525c6401","last_reissued_at":"2026-07-05T07:14:20.971041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:20.971041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andi Han, Dai Shi, Junbin Gao, Lequan Lin, Yi Guo","submitted_at":"2023-11-13T04:40:13Z","abstract_excerpt":"Graph-based message-passing neural networks (MPNNs) have achieved remarkable success in both node and graph-level learning tasks. However, several identified problems, including over-smoothing (OSM), limited expressive power, and over-squashing (OSQ), still limit the performance of MPNNs. In particular, OSQ serves as the latest identified problem, where MPNNs gradually lose their learning accuracy when long-range dependencies between graph nodes are required. In this work, we provide an exposition on the OSQ problem by summarizing different formulations of OSQ from current literature, as well "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07073","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/2311.07073/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":"2311.07073","created_at":"2026-07-05T07:14:20.971099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07073v2","created_at":"2026-07-05T07:14:20.971099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07073","created_at":"2026-07-05T07:14:20.971099+00:00"},{"alias_kind":"pith_short_12","alias_value":"W35ONVIT3J7H","created_at":"2026-07-05T07:14:20.971099+00:00"},{"alias_kind":"pith_short_16","alias_value":"W35ONVIT3J7H2FBR","created_at":"2026-07-05T07:14:20.971099+00:00"},{"alias_kind":"pith_short_8","alias_value":"W35ONVIT","created_at":"2026-07-05T07:14:20.971099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23467","citing_title":"S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC","json":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC.json","graph_json":"https://pith.science/api/pith-number/W35ONVIT3J7H2FBRY56WR6UZWC/graph.json","events_json":"https://pith.science/api/pith-number/W35ONVIT3J7H2FBRY56WR6UZWC/events.json","paper":"https://pith.science/paper/W35ONVIT"},"agent_actions":{"view_html":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC","download_json":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC.json","view_paper":"https://pith.science/paper/W35ONVIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07073&json=true","fetch_graph":"https://pith.science/api/pith-number/W35ONVIT3J7H2FBRY56WR6UZWC/graph.json","fetch_events":"https://pith.science/api/pith-number/W35ONVIT3J7H2FBRY56WR6UZWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC/action/storage_attestation","attest_author":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC/action/author_attestation","sign_citation":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC/action/citation_signature","submit_replication":"https://pith.science/pith/W35ONVIT3J7H2FBRY56WR6UZWC/action/replication_record"}},"created_at":"2026-07-05T07:14:20.971099+00:00","updated_at":"2026-07-05T07:14:20.971099+00:00"}