{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJE4TCFQNAQPEPMXBRVBYFWBM3","short_pith_number":"pith:FJE4TCFQ","schema_version":"1.0","canonical_sha256":"2a49c988b06820f23d970c6a1c16c166fb1ef2482e6c601036fd7d0046ff7cca","source":{"kind":"arxiv","id":"2507.12913","version":1},"attestation_state":"computed","paper":{"title":"Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Hoarau, Chenrui Zhu, Louenas Bounia, S\\'ebastien Destercke, Vu Linh Nguyen","submitted_at":"2025-07-17T09:00:05Z","abstract_excerpt":"Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insu"},"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":"2507.12913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T09:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"3ea7cb15f2e16735272666998f219700aaddb221aefa62d4808f18a7c6c53622","abstract_canon_sha256":"db20251fc13fa0af087dac819cd00d757e11db7614d4f2e77a8540910a9b45f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:41.357509Z","signature_b64":"2zJcWRthfQ7tK5mZUoTqhb3gAAvnOysZ4vXJG5jKEidchcjhPsMqXB/+2gbJu9VWkOfVppnyzgwq0BwyB1SpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a49c988b06820f23d970c6a1c16c166fb1ef2482e6c601036fd7d0046ff7cca","last_reissued_at":"2026-07-05T11:38:41.357018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:41.357018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Hoarau, Chenrui Zhu, Louenas Bounia, S\\'ebastien Destercke, Vu Linh Nguyen","submitted_at":"2025-07-17T09:00:05Z","abstract_excerpt":"Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12913","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/2507.12913/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":"2507.12913","created_at":"2026-07-05T11:38:41.357083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12913v1","created_at":"2026-07-05T11:38:41.357083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12913","created_at":"2026-07-05T11:38:41.357083+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJE4TCFQNAQP","created_at":"2026-07-05T11:38:41.357083+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJE4TCFQNAQPEPMX","created_at":"2026-07-05T11:38:41.357083+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJE4TCFQ","created_at":"2026-07-05T11:38:41.357083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3","json":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3.json","graph_json":"https://pith.science/api/pith-number/FJE4TCFQNAQPEPMXBRVBYFWBM3/graph.json","events_json":"https://pith.science/api/pith-number/FJE4TCFQNAQPEPMXBRVBYFWBM3/events.json","paper":"https://pith.science/paper/FJE4TCFQ"},"agent_actions":{"view_html":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3","download_json":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3.json","view_paper":"https://pith.science/paper/FJE4TCFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12913&json=true","fetch_graph":"https://pith.science/api/pith-number/FJE4TCFQNAQPEPMXBRVBYFWBM3/graph.json","fetch_events":"https://pith.science/api/pith-number/FJE4TCFQNAQPEPMXBRVBYFWBM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3/action/storage_attestation","attest_author":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3/action/author_attestation","sign_citation":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3/action/citation_signature","submit_replication":"https://pith.science/pith/FJE4TCFQNAQPEPMXBRVBYFWBM3/action/replication_record"}},"created_at":"2026-07-05T11:38:41.357083+00:00","updated_at":"2026-07-05T11:38:41.357083+00:00"}