{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GJZOKFVPKJ6C53HUGUBOMAIQ6J","short_pith_number":"pith:GJZOKFVP","schema_version":"1.0","canonical_sha256":"3272e516af527c2eecf43502e60110f26e0d8dea1e14edbc8f62952f6c715afc","source":{"kind":"arxiv","id":"2204.09308","version":1},"attestation_state":"computed","paper":{"title":"A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Saromo, Matias Valdenegro-Toro","submitted_at":"2022-04-20T08:41:37Z","abstract_excerpt":"Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, som"},"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":"2204.09308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-20T08:41:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e2eb9181559203d5068d7e49a3d1e303b9dd8edb6654ebb58f21f49a8244ee03","abstract_canon_sha256":"04c54c5edaa2440f882858f6b84e3fdedfa19ff982d7b23fc71b6da6144b0b89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:23.130780Z","signature_b64":"pFWKAWxKwx+O9BLb9Vdo8k1kUrLvotKKI65QXNr329sa/1dcO7gy0Rh3EQzuyREbGDywY63Nl14UIV6RwPPxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3272e516af527c2eecf43502e60110f26e0d8dea1e14edbc8f62952f6c715afc","last_reissued_at":"2026-07-05T04:16:23.130298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:23.130298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Saromo, Matias Valdenegro-Toro","submitted_at":"2022-04-20T08:41:37Z","abstract_excerpt":"Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, som"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09308","kind":"arxiv","version":1},"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/2204.09308/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":"2204.09308","created_at":"2026-07-05T04:16:23.130362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09308v1","created_at":"2026-07-05T04:16:23.130362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09308","created_at":"2026-07-05T04:16:23.130362+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJZOKFVPKJ6C","created_at":"2026-07-05T04:16:23.130362+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJZOKFVPKJ6C53HU","created_at":"2026-07-05T04:16:23.130362+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJZOKFVP","created_at":"2026-07-05T04:16:23.130362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24053","citing_title":"Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J","json":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J.json","graph_json":"https://pith.science/api/pith-number/GJZOKFVPKJ6C53HUGUBOMAIQ6J/graph.json","events_json":"https://pith.science/api/pith-number/GJZOKFVPKJ6C53HUGUBOMAIQ6J/events.json","paper":"https://pith.science/paper/GJZOKFVP"},"agent_actions":{"view_html":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J","download_json":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J.json","view_paper":"https://pith.science/paper/GJZOKFVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09308&json=true","fetch_graph":"https://pith.science/api/pith-number/GJZOKFVPKJ6C53HUGUBOMAIQ6J/graph.json","fetch_events":"https://pith.science/api/pith-number/GJZOKFVPKJ6C53HUGUBOMAIQ6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J/action/storage_attestation","attest_author":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J/action/author_attestation","sign_citation":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J/action/citation_signature","submit_replication":"https://pith.science/pith/GJZOKFVPKJ6C53HUGUBOMAIQ6J/action/replication_record"}},"created_at":"2026-07-05T04:16:23.130362+00:00","updated_at":"2026-07-05T04:16:23.130362+00:00"}