{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XWCDPEZ7VOIDIV4VUQUS7WZLWC","short_pith_number":"pith:XWCDPEZ7","schema_version":"1.0","canonical_sha256":"bd8437933fab90345795a4292fdb2bb0a433be48888f216c0f69ea2ea187f2a4","source":{"kind":"arxiv","id":"2305.14535","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Quantification over Graph with Conformalized Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emmanuel Cand\\`es, Jure Leskovec, Kexin Huang, Ying Jin","submitted_at":"2023-05-23T21:38:23Z","abstract_excerpt":"Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data. However, GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant. We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates. Given an entity in the graph, CF-GNN produces a prediction set/interval that provably contains the true label with pre-defined coverage probability (e.g. 90%). We establish a permutation invariance condition that enables 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":"2305.14535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T21:38:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ee09a060438597bd076fc46d131ce2caed64aaac141e9cccf7b79da624c62300","abstract_canon_sha256":"e031386f9f1888c956abc6e624d9d78bc918a8d6ac8e11c3287a6db91bccad40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:10.399034Z","signature_b64":"oEojrJYDBiteK0WMPKhQqQhdyMhYKWxdpwRjeZHwnVcTKVsApm2kUAAPQxPMUlZIdcnOGe9YvldgN1S0rVXDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8437933fab90345795a4292fdb2bb0a433be48888f216c0f69ea2ea187f2a4","last_reissued_at":"2026-07-05T07:07:10.398479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:10.398479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Quantification over Graph with Conformalized Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emmanuel Cand\\`es, Jure Leskovec, Kexin Huang, Ying Jin","submitted_at":"2023-05-23T21:38:23Z","abstract_excerpt":"Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data. However, GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant. We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates. Given an entity in the graph, CF-GNN produces a prediction set/interval that provably contains the true label with pre-defined coverage probability (e.g. 90%). We establish a permutation invariance condition that enables th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14535","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/2305.14535/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":"2305.14535","created_at":"2026-07-05T07:07:10.398546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14535v2","created_at":"2026-07-05T07:07:10.398546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14535","created_at":"2026-07-05T07:07:10.398546+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWCDPEZ7VOID","created_at":"2026-07-05T07:07:10.398546+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWCDPEZ7VOIDIV4V","created_at":"2026-07-05T07:07:10.398546+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWCDPEZ7","created_at":"2026-07-05T07:07:10.398546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08404","citing_title":"Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC","json":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC.json","graph_json":"https://pith.science/api/pith-number/XWCDPEZ7VOIDIV4VUQUS7WZLWC/graph.json","events_json":"https://pith.science/api/pith-number/XWCDPEZ7VOIDIV4VUQUS7WZLWC/events.json","paper":"https://pith.science/paper/XWCDPEZ7"},"agent_actions":{"view_html":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC","download_json":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC.json","view_paper":"https://pith.science/paper/XWCDPEZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14535&json=true","fetch_graph":"https://pith.science/api/pith-number/XWCDPEZ7VOIDIV4VUQUS7WZLWC/graph.json","fetch_events":"https://pith.science/api/pith-number/XWCDPEZ7VOIDIV4VUQUS7WZLWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC/action/storage_attestation","attest_author":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC/action/author_attestation","sign_citation":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC/action/citation_signature","submit_replication":"https://pith.science/pith/XWCDPEZ7VOIDIV4VUQUS7WZLWC/action/replication_record"}},"created_at":"2026-07-05T07:07:10.398546+00:00","updated_at":"2026-07-05T07:07:10.398546+00:00"}