{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3X4RC74IDTCQ5TSTNIDL7F2XER","short_pith_number":"pith:3X4RC74I","schema_version":"1.0","canonical_sha256":"ddf9117f881cc50ece536a06bf975724707bb81088a1c67b53079fe90aeaab4c","source":{"kind":"arxiv","id":"2503.13050","version":3},"attestation_state":"computed","paper":{"title":"E-Values Expand the Scope of Conformal Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Etienne Gauthier, Francis Bach, Michael I. Jordan","submitted_at":"2025-03-17T10:54:30Z","abstract_excerpt":"Conformal prediction is a powerful framework for distribution-free uncertainty quantification. The standard approach to conformal prediction relies on comparing the ranks of prediction scores: under exchangeability, the rank of a future test point cannot be too extreme relative to a calibration set. This rank-based method can be reformulated in terms of p-values. In this paper, we explore an alternative approach based on e-values, known as conformal e-prediction. E-values offer key advantages that cannot be achieved with p-values, enabling new theoretical and practical capabilities. In particu"},"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":"2503.13050","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-03-17T10:54:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0eba49a2c95e2f22e6478e594f4b261a3c7be3b78dc5695e00669d9216d63264","abstract_canon_sha256":"f90a40efb7428aa4012250d3f767583720e85282e3c41975df51f0e4c7192f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:07.509539Z","signature_b64":"jO/ZAsYeeF8SBVFaONkpCDQtekNQ+/sVwdt7PGZA8zMe0lo6kXQKOgArfYxQaB+Tt0AmOosOO09YMg62QcpDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf9117f881cc50ece536a06bf975724707bb81088a1c67b53079fe90aeaab4c","last_reissued_at":"2026-07-05T10:59:07.508922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:07.508922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E-Values Expand the Scope of Conformal Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Etienne Gauthier, Francis Bach, Michael I. Jordan","submitted_at":"2025-03-17T10:54:30Z","abstract_excerpt":"Conformal prediction is a powerful framework for distribution-free uncertainty quantification. The standard approach to conformal prediction relies on comparing the ranks of prediction scores: under exchangeability, the rank of a future test point cannot be too extreme relative to a calibration set. This rank-based method can be reformulated in terms of p-values. In this paper, we explore an alternative approach based on e-values, known as conformal e-prediction. E-values offer key advantages that cannot be achieved with p-values, enabling new theoretical and practical capabilities. In particu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13050","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/2503.13050/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":"2503.13050","created_at":"2026-07-05T10:59:07.508999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13050v3","created_at":"2026-07-05T10:59:07.508999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13050","created_at":"2026-07-05T10:59:07.508999+00:00"},{"alias_kind":"pith_short_12","alias_value":"3X4RC74IDTCQ","created_at":"2026-07-05T10:59:07.508999+00:00"},{"alias_kind":"pith_short_16","alias_value":"3X4RC74IDTCQ5TST","created_at":"2026-07-05T10:59:07.508999+00:00"},{"alias_kind":"pith_short_8","alias_value":"3X4RC74I","created_at":"2026-07-05T10:59:07.508999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06332","citing_title":"Bentkus-type asymptotic e-values","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03600","citing_title":"Set-Preserving Calibration from Conformal P-Values to E-Values","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18202","citing_title":"Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11305","citing_title":"Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15740","citing_title":"Evidence Sufficiency Under Delayed Ground Truth: Proxy Monitoring for Risk Decision Systems","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02486","citing_title":"Reliable Narrowband Interference Detection via Backward Conformal Prediction","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER","json":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER.json","graph_json":"https://pith.science/api/pith-number/3X4RC74IDTCQ5TSTNIDL7F2XER/graph.json","events_json":"https://pith.science/api/pith-number/3X4RC74IDTCQ5TSTNIDL7F2XER/events.json","paper":"https://pith.science/paper/3X4RC74I"},"agent_actions":{"view_html":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER","download_json":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER.json","view_paper":"https://pith.science/paper/3X4RC74I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13050&json=true","fetch_graph":"https://pith.science/api/pith-number/3X4RC74IDTCQ5TSTNIDL7F2XER/graph.json","fetch_events":"https://pith.science/api/pith-number/3X4RC74IDTCQ5TSTNIDL7F2XER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER/action/storage_attestation","attest_author":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER/action/author_attestation","sign_citation":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER/action/citation_signature","submit_replication":"https://pith.science/pith/3X4RC74IDTCQ5TSTNIDL7F2XER/action/replication_record"}},"created_at":"2026-07-05T10:59:07.508999+00:00","updated_at":"2026-07-05T10:59:07.508999+00:00"}