{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QRGYWJPC2SX5QTOFZHZ4VCQLLG","short_pith_number":"pith:QRGYWJPC","schema_version":"1.0","canonical_sha256":"844d8b25e2d4afd84dc5c9f3ca8a0b599080b7991392e2ccabc66c1ab169badf","source":{"kind":"arxiv","id":"2212.07328","version":2},"attestation_state":"computed","paper":{"title":"Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuyu Zhang, Xuming He, Yucong Chen, Zhitong Gao","submitted_at":"2022-12-14T16:48:21Z","abstract_excerpt":"Equipping predicted segmentation with calibrated uncertainty is essential for safety-critical applications. In this work, we focus on capturing the data-inherent uncertainty (aka aleatoric uncertainty) in segmentation, typically when ambiguities exist in input images. Due to the high-dimensional output space and potential multiple modes in segmenting ambiguous images, it remains challenging to predict well-calibrated uncertainty for segmentation. To tackle this problem, we propose a novel mixture of stochastic experts (MoSE) model, where each expert network estimates a distinct mode of the ale"},"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":"2212.07328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T16:48:21Z","cross_cats_sorted":[],"title_canon_sha256":"99f3e49c3ecb35827eb76caad2dca65ddb597b166ebbb43994f54403e07a9583","abstract_canon_sha256":"bccfd6adb91430181b2ca1f9cb1b7e84647b8c3343fedfeee4b14eea36e12eb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:36.259305Z","signature_b64":"DiKrpR7H7W+R199VB1XLuHRREc+lTKjvgHaXPaUovqwN3pvcBLJfEU38LDZmI1WQ0uA9Ysx9Auom9yVMHVirAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"844d8b25e2d4afd84dc5c9f3ca8a0b599080b7991392e2ccabc66c1ab169badf","last_reissued_at":"2026-07-05T05:45:36.258754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:36.258754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuyu Zhang, Xuming He, Yucong Chen, Zhitong Gao","submitted_at":"2022-12-14T16:48:21Z","abstract_excerpt":"Equipping predicted segmentation with calibrated uncertainty is essential for safety-critical applications. In this work, we focus on capturing the data-inherent uncertainty (aka aleatoric uncertainty) in segmentation, typically when ambiguities exist in input images. Due to the high-dimensional output space and potential multiple modes in segmenting ambiguous images, it remains challenging to predict well-calibrated uncertainty for segmentation. To tackle this problem, we propose a novel mixture of stochastic experts (MoSE) model, where each expert network estimates a distinct mode of the ale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07328","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/2212.07328/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":"2212.07328","created_at":"2026-07-05T05:45:36.258815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07328v2","created_at":"2026-07-05T05:45:36.258815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07328","created_at":"2026-07-05T05:45:36.258815+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRGYWJPC2SX5","created_at":"2026-07-05T05:45:36.258815+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRGYWJPC2SX5QTOF","created_at":"2026-07-05T05:45:36.258815+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRGYWJPC","created_at":"2026-07-05T05:45:36.258815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21061","citing_title":"Neural Architecture Distributions: A New Paradigm for Stochastic Segmentation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12709","citing_title":"Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG","json":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG.json","graph_json":"https://pith.science/api/pith-number/QRGYWJPC2SX5QTOFZHZ4VCQLLG/graph.json","events_json":"https://pith.science/api/pith-number/QRGYWJPC2SX5QTOFZHZ4VCQLLG/events.json","paper":"https://pith.science/paper/QRGYWJPC"},"agent_actions":{"view_html":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG","download_json":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG.json","view_paper":"https://pith.science/paper/QRGYWJPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07328&json=true","fetch_graph":"https://pith.science/api/pith-number/QRGYWJPC2SX5QTOFZHZ4VCQLLG/graph.json","fetch_events":"https://pith.science/api/pith-number/QRGYWJPC2SX5QTOFZHZ4VCQLLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG/action/storage_attestation","attest_author":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG/action/author_attestation","sign_citation":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG/action/citation_signature","submit_replication":"https://pith.science/pith/QRGYWJPC2SX5QTOFZHZ4VCQLLG/action/replication_record"}},"created_at":"2026-07-05T05:45:36.258815+00:00","updated_at":"2026-07-05T05:45:36.258815+00:00"}