{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2XC6ACOZLNTXHA3RK5W7OEAHVR","short_pith_number":"pith:2XC6ACOZ","schema_version":"1.0","canonical_sha256":"d5c5e009d95b67738371576df71007ac7fab1f7c68d115f51d5431ed1c2fe7fb","source":{"kind":"arxiv","id":"2306.05724","version":2},"attestation_state":"computed","paper":{"title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David S. Watson, Ido Guy, Joshua O'Hara, Niek Tax, Richard Mudd","submitted_at":"2023-06-09T07:43:46Z","abstract_excerpt":"Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\\textit{uncertainty}$ of model outputs has received relatively little attention. We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs. We consider games with modified characteristic functions and find deep connections between the resulting Shapley values and fundam"},"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":"2306.05724","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-09T07:43:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"942b612dc7a6fe1be3ad0eed346f57cfbc739a12e952df8ac7162f51797feb0a","abstract_canon_sha256":"dd03246e741232c345a59b2253c4c237e65ec97d240a1368d57525353607dea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:11.956407Z","signature_b64":"z1g6RoAGxj1QqCrq26IPhrK7roVKoo31L1YP9iNnlre43aaYN0mRwAOZ/GLGSAXnf0QRiLnViIsS4I+ovxiZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c5e009d95b67738371576df71007ac7fab1f7c68d115f51d5431ed1c2fe7fb","last_reissued_at":"2026-07-05T07:07:11.955899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:11.955899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David S. Watson, Ido Guy, Joshua O'Hara, Niek Tax, Richard Mudd","submitted_at":"2023-06-09T07:43:46Z","abstract_excerpt":"Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\\textit{uncertainty}$ of model outputs has received relatively little attention. We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs. We consider games with modified characteristic functions and find deep connections between the resulting Shapley values and fundam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05724","kind":"arxiv","version":2},"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/2306.05724/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":"2306.05724","created_at":"2026-07-05T07:07:11.955961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05724v2","created_at":"2026-07-05T07:07:11.955961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05724","created_at":"2026-07-05T07:07:11.955961+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XC6ACOZLNTX","created_at":"2026-07-05T07:07:11.955961+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XC6ACOZLNTXHA3R","created_at":"2026-07-05T07:07:11.955961+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XC6ACOZ","created_at":"2026-07-05T07:07:11.955961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00867","citing_title":"Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21023","citing_title":"On Using the Shapley Value for Anomaly Localization: A Statistical Investigation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR","json":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR.json","graph_json":"https://pith.science/api/pith-number/2XC6ACOZLNTXHA3RK5W7OEAHVR/graph.json","events_json":"https://pith.science/api/pith-number/2XC6ACOZLNTXHA3RK5W7OEAHVR/events.json","paper":"https://pith.science/paper/2XC6ACOZ"},"agent_actions":{"view_html":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR","download_json":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR.json","view_paper":"https://pith.science/paper/2XC6ACOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05724&json=true","fetch_graph":"https://pith.science/api/pith-number/2XC6ACOZLNTXHA3RK5W7OEAHVR/graph.json","fetch_events":"https://pith.science/api/pith-number/2XC6ACOZLNTXHA3RK5W7OEAHVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR/action/storage_attestation","attest_author":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR/action/author_attestation","sign_citation":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR/action/citation_signature","submit_replication":"https://pith.science/pith/2XC6ACOZLNTXHA3RK5W7OEAHVR/action/replication_record"}},"created_at":"2026-07-05T07:07:11.955961+00:00","updated_at":"2026-07-05T07:07:11.955961+00:00"}