{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JFA6OOJICITL4PNCGTZBVBWAFS","short_pith_number":"pith:JFA6OOJI","schema_version":"1.0","canonical_sha256":"4941e739281226be3da234f21a86c02c801040bf606773a67bf6f3244549095c","source":{"kind":"arxiv","id":"2602.11219","version":2},"attestation_state":"computed","paper":{"title":"Structurally Separated Uncertainty in Supervised Latent Variable Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Marius Kloft, Pierre Marquis, Tanmoy Mukherjee, Zied Bouraoui","submitted_at":"2026-02-11T10:54:57Z","abstract_excerpt":"Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated estimates because both quantities are derived from the same predictive distribution. We study an alternative design principle, \\emph{structural separation}, which assigns epistemic and aleatoric uncertainty to disjoint parameter paths trained with distinct supervision targets: reducible prediction error for epistemic uncertainty and persistent label ambiguity for aleatoric uncertainty. We instantiate this principle in two supervised latent-variabl"},"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":"2602.11219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T10:54:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f9915e179233804605ff9e8ad59e8651ace3981c39827b09edb0ef35028d2181","abstract_canon_sha256":"77fb83d28a2c8f4b51390f9122ed124a312a7831e4c55becada78d62c47b3ff6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4941e739281226be3da234f21a86c02c801040bf606773a67bf6f3244549095c","last_reissued_at":"2026-07-30T01:19:33.544852Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:33.544852Z"},"graph_snapshot":{"paper":{"title":"Structurally Separated Uncertainty in Supervised Latent Variable Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Marius Kloft, Pierre Marquis, Tanmoy Mukherjee, Zied Bouraoui","submitted_at":"2026-02-11T10:54:57Z","abstract_excerpt":"Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated estimates because both quantities are derived from the same predictive distribution. We study an alternative design principle, \\emph{structural separation}, which assigns epistemic and aleatoric uncertainty to disjoint parameter paths trained with distinct supervision targets: reducible prediction error for epistemic uncertainty and persistent label ambiguity for aleatoric uncertainty. We instantiate this principle in two supervised latent-variabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11219","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/2602.11219/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":"2602.11219","created_at":"2026-07-30T01:19:33.549949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11219v2","created_at":"2026-07-30T01:19:33.549949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11219","created_at":"2026-07-30T01:19:33.549949+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFA6OOJICITL","created_at":"2026-07-30T01:19:33.549949+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFA6OOJICITL4PNC","created_at":"2026-07-30T01:19:33.549949+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFA6OOJI","created_at":"2026-07-30T01:19:33.549949+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/JFA6OOJICITL4PNCGTZBVBWAFS","json":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS.json","graph_json":"https://pith.science/api/pith-number/JFA6OOJICITL4PNCGTZBVBWAFS/graph.json","events_json":"https://pith.science/api/pith-number/JFA6OOJICITL4PNCGTZBVBWAFS/events.json","paper":"https://pith.science/paper/JFA6OOJI"},"agent_actions":{"view_html":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS","download_json":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS.json","view_paper":"https://pith.science/paper/JFA6OOJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11219&json=true","fetch_graph":"https://pith.science/api/pith-number/JFA6OOJICITL4PNCGTZBVBWAFS/graph.json","fetch_events":"https://pith.science/api/pith-number/JFA6OOJICITL4PNCGTZBVBWAFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS/action/storage_attestation","attest_author":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS/action/author_attestation","sign_citation":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS/action/citation_signature","submit_replication":"https://pith.science/pith/JFA6OOJICITL4PNCGTZBVBWAFS/action/replication_record"}},"created_at":"2026-07-30T01:19:33.549949+00:00","updated_at":"2026-07-30T01:19:33.549949+00:00"}