{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N3ARXH7JARMQGEKMGU2QSNL3E7","short_pith_number":"pith:N3ARXH7J","schema_version":"1.0","canonical_sha256":"6ec11b9fe9045903114c353509357b27e05bfbf11f35e8ffbd52f40fb915d1fc","source":{"kind":"arxiv","id":"1905.02296","version":2},"attestation_state":"computed","paper":{"title":"Are Graph Neural Networks Miscalibrated?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brian Jalaian, Bruno Ribeiro, Leonardo Teixeira","submitted_at":"2019-05-07T00:05:31Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For this purpose, obtaining calibrated models is essential. In this work, we perform an empirical evaluation of the calibration of state-of-the-art GNNs on multiple datasets. Our experiments show that GNNs can be calibrated in some datasets but also badly miscalibrated in others, and"},"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":"1905.02296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-07T00:05:31Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0b3363f134c4132c8d12313d56fdc8366de8af9b6f3416175a87b47f54eefe35","abstract_canon_sha256":"44e7aee7ef09713fcb8fd88b66826bc97e64b2e23cf9aa4be1ad95f14c288290"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.639205Z","signature_b64":"wIVljK6pHwUA+NwdJnZUHbHE6v9KR6CKuH0mrAhm0UBAVb5YgyQjSkUjEQJZsyLqXjFm8t0S+i7oXtjP/JgcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec11b9fe9045903114c353509357b27e05bfbf11f35e8ffbd52f40fb915d1fc","last_reissued_at":"2026-05-17T23:44:28.638596Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.638596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Graph Neural Networks Miscalibrated?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brian Jalaian, Bruno Ribeiro, Leonardo Teixeira","submitted_at":"2019-05-07T00:05:31Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For this purpose, obtaining calibrated models is essential. In this work, we perform an empirical evaluation of the calibration of state-of-the-art GNNs on multiple datasets. Our experiments show that GNNs can be calibrated in some datasets but also badly miscalibrated in others, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02296","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":""},"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":"1905.02296","created_at":"2026-05-17T23:44:28.638681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02296v2","created_at":"2026-05-17T23:44:28.638681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02296","created_at":"2026-05-17T23:44:28.638681+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3ARXH7JARMQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3ARXH7JARMQGEKM","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3ARXH7J","created_at":"2026-05-18T12:33:24.271573+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/N3ARXH7JARMQGEKMGU2QSNL3E7","json":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7.json","graph_json":"https://pith.science/api/pith-number/N3ARXH7JARMQGEKMGU2QSNL3E7/graph.json","events_json":"https://pith.science/api/pith-number/N3ARXH7JARMQGEKMGU2QSNL3E7/events.json","paper":"https://pith.science/paper/N3ARXH7J"},"agent_actions":{"view_html":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7","download_json":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7.json","view_paper":"https://pith.science/paper/N3ARXH7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02296&json=true","fetch_graph":"https://pith.science/api/pith-number/N3ARXH7JARMQGEKMGU2QSNL3E7/graph.json","fetch_events":"https://pith.science/api/pith-number/N3ARXH7JARMQGEKMGU2QSNL3E7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7/action/storage_attestation","attest_author":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7/action/author_attestation","sign_citation":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7/action/citation_signature","submit_replication":"https://pith.science/pith/N3ARXH7JARMQGEKMGU2QSNL3E7/action/replication_record"}},"created_at":"2026-05-17T23:44:28.638681+00:00","updated_at":"2026-05-17T23:44:28.638681+00:00"}