{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KBXDRNJGSVTQB4GAXTJFOOG3J7","short_pith_number":"pith:KBXDRNJG","schema_version":"1.0","canonical_sha256":"506e38b526956700f0c0bcd25738db4fc2767945ef0c48110244523ef244c795","source":{"kind":"arxiv","id":"2405.02140","version":3},"attestation_state":"computed","paper":{"title":"An Information Theoretic Perspective on Conformal Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro H.C. Correia, Arash Behboodi, Christos Louizos, Fabio Valerio Massoli","submitted_at":"2024-05-03T14:43:07Z","abstract_excerpt":"Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a general notion of uncertainty, with larger sets associated with higher degrees of uncertainty. In this work, we leverage information theory to connect conformal prediction to other notions of uncertainty. More precisely, we prove three different ways to upper bound the intrinsic uncertainty, as described by the conditional entropy of the target variable giv"},"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":"2405.02140","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T14:43:07Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"666d49877ad809d2348be35400213ef878d1cd302c8ee457e9aa02e29caa5c71","abstract_canon_sha256":"fc1d16c00a1573d58e0d499f92e5a443fcf5309d9ec99c164055ca8707493295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:39.897689Z","signature_b64":"JzFtIfjkw1/wx4IgyT1+kshbqQlUvBNB4uupMfFLShFCEEIfvBMEXjZlOOWKQivCD5EE3Mjf/F93hivxhHzLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"506e38b526956700f0c0bcd25738db4fc2767945ef0c48110244523ef244c795","last_reissued_at":"2026-07-05T10:14:39.897183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:39.897183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information Theoretic Perspective on Conformal Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvaro H.C. Correia, Arash Behboodi, Christos Louizos, Fabio Valerio Massoli","submitted_at":"2024-05-03T14:43:07Z","abstract_excerpt":"Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a general notion of uncertainty, with larger sets associated with higher degrees of uncertainty. In this work, we leverage information theory to connect conformal prediction to other notions of uncertainty. More precisely, we prove three different ways to upper bound the intrinsic uncertainty, as described by the conditional entropy of the target variable giv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02140","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/2405.02140/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":"2405.02140","created_at":"2026-07-05T10:14:39.897238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02140v3","created_at":"2026-07-05T10:14:39.897238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02140","created_at":"2026-07-05T10:14:39.897238+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBXDRNJGSVTQ","created_at":"2026-07-05T10:14:39.897238+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBXDRNJGSVTQB4GA","created_at":"2026-07-05T10:14:39.897238+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBXDRNJG","created_at":"2026-07-05T10:14:39.897238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19024","citing_title":"Conformal Prediction via Transported Beta Laws","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7","json":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7.json","graph_json":"https://pith.science/api/pith-number/KBXDRNJGSVTQB4GAXTJFOOG3J7/graph.json","events_json":"https://pith.science/api/pith-number/KBXDRNJGSVTQB4GAXTJFOOG3J7/events.json","paper":"https://pith.science/paper/KBXDRNJG"},"agent_actions":{"view_html":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7","download_json":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7.json","view_paper":"https://pith.science/paper/KBXDRNJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02140&json=true","fetch_graph":"https://pith.science/api/pith-number/KBXDRNJGSVTQB4GAXTJFOOG3J7/graph.json","fetch_events":"https://pith.science/api/pith-number/KBXDRNJGSVTQB4GAXTJFOOG3J7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7/action/storage_attestation","attest_author":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7/action/author_attestation","sign_citation":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7/action/citation_signature","submit_replication":"https://pith.science/pith/KBXDRNJGSVTQB4GAXTJFOOG3J7/action/replication_record"}},"created_at":"2026-07-05T10:14:39.897238+00:00","updated_at":"2026-07-05T10:14:39.897238+00:00"}