{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YBJAKX5XQYFENIIFEBR4C7QBUH","short_pith_number":"pith:YBJAKX5X","schema_version":"1.0","canonical_sha256":"c052055fb7860a46a1052063c17e01a1d09d6a612bfbf2ef59d4f23e29967ef6","source":{"kind":"arxiv","id":"2607.22381","version":1},"attestation_state":"computed","paper":{"title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rachid Caich, Yassine Abbahaddou","submitted_at":"2026-07-24T15:07:37Z","abstract_excerpt":"Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how information actually propagates over long distances. We introduce Entropic Curvature, a global, transport-based curvature obtained by extending the Lott-Sturm-Villani framework to graphs through the displacement convexity of entropy along Wasserstein geodesics. We define a tractable Weak Entropic C"},"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":"2607.22381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T15:07:37Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"c954edbe63838a8044101051c4379036460d70cd5c3efe98e20beb98b321e8a8","abstract_canon_sha256":"13cb29d5bb220d67366130c73c0ad109bdf7f916095f33c4596aa1ffe40d8e67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:21:17.577150Z","signature_b64":"tl3kb6sO6Yp8lXCvs87bUP8HBumbgMvi/sBS29BhASyZsGDG4wbtVKTA+LQXH8OIrH4iJezzKsRr8wMvUHCXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c052055fb7860a46a1052063c17e01a1d09d6a612bfbf2ef59d4f23e29967ef6","last_reissued_at":"2026-07-27T01:21:17.576289Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:21:17.576289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rachid Caich, Yassine Abbahaddou","submitted_at":"2026-07-24T15:07:37Z","abstract_excerpt":"Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how information actually propagates over long distances. We introduce Entropic Curvature, a global, transport-based curvature obtained by extending the Lott-Sturm-Villani framework to graphs through the displacement convexity of entropy along Wasserstein geodesics. We define a tractable Weak Entropic C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22381","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/2607.22381/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":"2607.22381","created_at":"2026-07-27T01:21:17.576741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22381v1","created_at":"2026-07-27T01:21:17.576741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22381","created_at":"2026-07-27T01:21:17.576741+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBJAKX5XQYFE","created_at":"2026-07-27T01:21:17.576741+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBJAKX5XQYFENIIF","created_at":"2026-07-27T01:21:17.576741+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBJAKX5X","created_at":"2026-07-27T01:21:17.576741+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/YBJAKX5XQYFENIIFEBR4C7QBUH","json":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH.json","graph_json":"https://pith.science/api/pith-number/YBJAKX5XQYFENIIFEBR4C7QBUH/graph.json","events_json":"https://pith.science/api/pith-number/YBJAKX5XQYFENIIFEBR4C7QBUH/events.json","paper":"https://pith.science/paper/YBJAKX5X"},"agent_actions":{"view_html":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH","download_json":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH.json","view_paper":"https://pith.science/paper/YBJAKX5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22381&json=true","fetch_graph":"https://pith.science/api/pith-number/YBJAKX5XQYFENIIFEBR4C7QBUH/graph.json","fetch_events":"https://pith.science/api/pith-number/YBJAKX5XQYFENIIFEBR4C7QBUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH/action/storage_attestation","attest_author":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH/action/author_attestation","sign_citation":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH/action/citation_signature","submit_replication":"https://pith.science/pith/YBJAKX5XQYFENIIFEBR4C7QBUH/action/replication_record"}},"created_at":"2026-07-27T01:21:17.576741+00:00","updated_at":"2026-07-27T01:21:17.576741+00:00"}