{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K73TEPT4EJ4K7SWA6UGS65FPDE","short_pith_number":"pith:K73TEPT4","schema_version":"1.0","canonical_sha256":"57f7323e7c2278afcac0f50d2f74af1905192c8725da615d62848f904d2bda42","source":{"kind":"arxiv","id":"2302.02941","version":3},"attestation_state":"computed","paper":{"title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Federico Barbero, Francesco Di Giovanni, Giulia Luise, Lorenzo Giusti, Michael Bronstein, Pietro Lio'","submitted_at":"2023-02-06T17:16:42Z","abstract_excerpt":"Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon known as over-squashing, where a node feature is insensitive to information contained at distant nodes. Despite recent methods introduced to mitigate this issue, an understanding of the causes for over-squashing and of possible solutions are lacking. In this theoretical work, we prove that: (i) Neural network width can mitigate over-squashing, but at the cost of making the whole network more sensitive; (ii) Conversely,"},"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":"2302.02941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:16:42Z","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"title_canon_sha256":"90c8af60b2365618def19731427d13c7367eb4a4c6740b1129f6c75918d5b911","abstract_canon_sha256":"a7f6c20e6738daaac0d281f5cba72d5e1774f64afa9422b896a4d68a07dd0b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:19.381120Z","signature_b64":"uM6UTYjkH+1o43Ui/9knrxZuliugR589XAscF8lVxXefeoNdBVKe7hHDuXpED6gSg4I3LKYlHJVE4njl769NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57f7323e7c2278afcac0f50d2f74af1905192c8725da615d62848f904d2bda42","last_reissued_at":"2026-07-05T06:13:19.380617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:19.380617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Federico Barbero, Francesco Di Giovanni, Giulia Luise, Lorenzo Giusti, Michael Bronstein, Pietro Lio'","submitted_at":"2023-02-06T17:16:42Z","abstract_excerpt":"Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon known as over-squashing, where a node feature is insensitive to information contained at distant nodes. Despite recent methods introduced to mitigate this issue, an understanding of the causes for over-squashing and of possible solutions are lacking. In this theoretical work, we prove that: (i) Neural network width can mitigate over-squashing, but at the cost of making the whole network more sensitive; (ii) Conversely,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02941","kind":"arxiv","version":3},"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/2302.02941/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":"2302.02941","created_at":"2026-07-05T06:13:19.380677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02941v3","created_at":"2026-07-05T06:13:19.380677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02941","created_at":"2026-07-05T06:13:19.380677+00:00"},{"alias_kind":"pith_short_12","alias_value":"K73TEPT4EJ4K","created_at":"2026-07-05T06:13:19.380677+00:00"},{"alias_kind":"pith_short_16","alias_value":"K73TEPT4EJ4K7SWA","created_at":"2026-07-05T06:13:19.380677+00:00"},{"alias_kind":"pith_short_8","alias_value":"K73TEPT4","created_at":"2026-07-05T06:13:19.380677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE","json":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE.json","graph_json":"https://pith.science/api/pith-number/K73TEPT4EJ4K7SWA6UGS65FPDE/graph.json","events_json":"https://pith.science/api/pith-number/K73TEPT4EJ4K7SWA6UGS65FPDE/events.json","paper":"https://pith.science/paper/K73TEPT4"},"agent_actions":{"view_html":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE","download_json":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE.json","view_paper":"https://pith.science/paper/K73TEPT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02941&json=true","fetch_graph":"https://pith.science/api/pith-number/K73TEPT4EJ4K7SWA6UGS65FPDE/graph.json","fetch_events":"https://pith.science/api/pith-number/K73TEPT4EJ4K7SWA6UGS65FPDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE/action/storage_attestation","attest_author":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE/action/author_attestation","sign_citation":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE/action/citation_signature","submit_replication":"https://pith.science/pith/K73TEPT4EJ4K7SWA6UGS65FPDE/action/replication_record"}},"created_at":"2026-07-05T06:13:19.380677+00:00","updated_at":"2026-07-05T06:13:19.380677+00:00"}