{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2Y7UDU4266PGMMNXJP3MPBWBST","short_pith_number":"pith:2Y7UDU42","schema_version":"1.0","canonical_sha256":"d63f41d39af79e6631b74bf6c786c194fbf89e85d47b80afffb11739c441406a","source":{"kind":"arxiv","id":"2312.08083","version":4},"attestation_state":"computed","paper":{"title":"Training of Neural Networks with Uncertain Data: A Mixture of Experts Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lucas Luttner","submitted_at":"2023-12-13T11:57:15Z","abstract_excerpt":"This paper introduces the \"Uncertainty-aware Mixture of Experts\" (uMoE), a novel solution aimed at addressing aleatoric uncertainty within Neural Network (NN) based predictive models. While existing methodologies primarily concentrate on managing uncertainty during inference, uMoE uniquely embeds uncertainty into the training phase. Employing a \"Divide and Conquer\" strategy, uMoE strategically partitions the uncertain input space into more manageable subspaces. It comprises Expert components, individually trained on their respective subspace uncertainties. Overarching the Experts, a Gating Uni"},"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":"2312.08083","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-13T11:57:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d5edeee9952fe5ea72d0cfc23b2d87eca1d404589cd395b9a500238749fb140","abstract_canon_sha256":"fa2816a0198a54f0d754328cc92f9dce6869dba8a8311fb464665fdc3065d3e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:56.369320Z","signature_b64":"f3R886xD5emGhkTD0uofevM1kL3nUK28D8HBlY8n6layEYtGGKvkCiTrqX7r4BXtdmLo2bCxdLARd4VvQ4ECDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d63f41d39af79e6631b74bf6c786c194fbf89e85d47b80afffb11739c441406a","last_reissued_at":"2026-07-05T08:11:56.368801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:56.368801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training of Neural Networks with Uncertain Data: A Mixture of Experts Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lucas Luttner","submitted_at":"2023-12-13T11:57:15Z","abstract_excerpt":"This paper introduces the \"Uncertainty-aware Mixture of Experts\" (uMoE), a novel solution aimed at addressing aleatoric uncertainty within Neural Network (NN) based predictive models. While existing methodologies primarily concentrate on managing uncertainty during inference, uMoE uniquely embeds uncertainty into the training phase. Employing a \"Divide and Conquer\" strategy, uMoE strategically partitions the uncertain input space into more manageable subspaces. It comprises Expert components, individually trained on their respective subspace uncertainties. Overarching the Experts, a Gating Uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08083","kind":"arxiv","version":4},"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/2312.08083/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":"2312.08083","created_at":"2026-07-05T08:11:56.368857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08083v4","created_at":"2026-07-05T08:11:56.368857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08083","created_at":"2026-07-05T08:11:56.368857+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Y7UDU4266PG","created_at":"2026-07-05T08:11:56.368857+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Y7UDU4266PGMMNX","created_at":"2026-07-05T08:11:56.368857+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Y7UDU42","created_at":"2026-07-05T08:11:56.368857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04816","citing_title":"Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST","json":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST.json","graph_json":"https://pith.science/api/pith-number/2Y7UDU4266PGMMNXJP3MPBWBST/graph.json","events_json":"https://pith.science/api/pith-number/2Y7UDU4266PGMMNXJP3MPBWBST/events.json","paper":"https://pith.science/paper/2Y7UDU42"},"agent_actions":{"view_html":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST","download_json":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST.json","view_paper":"https://pith.science/paper/2Y7UDU42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08083&json=true","fetch_graph":"https://pith.science/api/pith-number/2Y7UDU4266PGMMNXJP3MPBWBST/graph.json","fetch_events":"https://pith.science/api/pith-number/2Y7UDU4266PGMMNXJP3MPBWBST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST/action/storage_attestation","attest_author":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST/action/author_attestation","sign_citation":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST/action/citation_signature","submit_replication":"https://pith.science/pith/2Y7UDU4266PGMMNXJP3MPBWBST/action/replication_record"}},"created_at":"2026-07-05T08:11:56.368857+00:00","updated_at":"2026-07-05T08:11:56.368857+00:00"}