{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z75KHAEWSJBLB5SUW6AXMRMIS5","short_pith_number":"pith:Z75KHAEW","schema_version":"1.0","canonical_sha256":"cffaa380969242b0f654b7817645889775b0b1c08d27bd8fec023bdc8a225e8b","source":{"kind":"arxiv","id":"2412.20892","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Aleatoric and Epistemic Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Foster, Eleanor Trollope, Freddie Bickford Smith, Jannik Kossen, Mark van der Wilk, Tom Rainforth","submitted_at":"2024-12-30T12:04:36Z","abstract_excerpt":"The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the aleatoric-epistemic view being insufficiently expressive to capture all the distinct quantities that researchers are interested in. To address this we present a decision-theoretic perspective that relates rigorous notions of uncertainty, predictive performance and statistical dispersion in data. This serves to support clearer thinking as the field moves forward. A"},"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":"2412.20892","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-30T12:04:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87b3fab73912c75fcafe1878f79c13d24375a248f93bc8e7eceab24c59de2403","abstract_canon_sha256":"701a2e4a67ff1c7d21edddc75e8fb3917706d93163515859136cd8d765ddbabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:16.009602Z","signature_b64":"RM9HTcRHa/ndRwVL7fYvZn3j5hY5XnZKHX3b+SvWFrmxCYFy2bi+n2z9162jSDXsReF4xq6qBZJ4FuwCgONbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cffaa380969242b0f654b7817645889775b0b1c08d27bd8fec023bdc8a225e8b","last_reissued_at":"2026-07-05T11:55:16.009123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:16.009123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Aleatoric and Epistemic Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Foster, Eleanor Trollope, Freddie Bickford Smith, Jannik Kossen, Mark van der Wilk, Tom Rainforth","submitted_at":"2024-12-30T12:04:36Z","abstract_excerpt":"The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the aleatoric-epistemic view being insufficiently expressive to capture all the distinct quantities that researchers are interested in. To address this we present a decision-theoretic perspective that relates rigorous notions of uncertainty, predictive performance and statistical dispersion in data. This serves to support clearer thinking as the field moves forward. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20892","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/2412.20892/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":"2412.20892","created_at":"2026-07-05T11:55:16.009183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20892v3","created_at":"2026-07-05T11:55:16.009183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20892","created_at":"2026-07-05T11:55:16.009183+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z75KHAEWSJBL","created_at":"2026-07-05T11:55:16.009183+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z75KHAEWSJBLB5SU","created_at":"2026-07-05T11:55:16.009183+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z75KHAEW","created_at":"2026-07-05T11:55:16.009183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10136","citing_title":"iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2507.03622","citing_title":"Localising Dropout Variance in Twin Networks","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17480","citing_title":"Trustworthy deep domain adaptation for wearable photoplethysmography signal analysis with decision-theoretic uncertainty quantification","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5","json":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5.json","graph_json":"https://pith.science/api/pith-number/Z75KHAEWSJBLB5SUW6AXMRMIS5/graph.json","events_json":"https://pith.science/api/pith-number/Z75KHAEWSJBLB5SUW6AXMRMIS5/events.json","paper":"https://pith.science/paper/Z75KHAEW"},"agent_actions":{"view_html":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5","download_json":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5.json","view_paper":"https://pith.science/paper/Z75KHAEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20892&json=true","fetch_graph":"https://pith.science/api/pith-number/Z75KHAEWSJBLB5SUW6AXMRMIS5/graph.json","fetch_events":"https://pith.science/api/pith-number/Z75KHAEWSJBLB5SUW6AXMRMIS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5/action/storage_attestation","attest_author":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5/action/author_attestation","sign_citation":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5/action/citation_signature","submit_replication":"https://pith.science/pith/Z75KHAEWSJBLB5SUW6AXMRMIS5/action/replication_record"}},"created_at":"2026-07-05T11:55:16.009183+00:00","updated_at":"2026-07-05T11:55:16.009183+00:00"}