{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6XBMN62Y7IM5SPT4PNOGFHXMEY","short_pith_number":"pith:6XBMN62Y","schema_version":"1.0","canonical_sha256":"f5c2c6fb58fa19d93e7c7b5c629eec2637e61ce2951a41de923ff8ca5904ea9d","source":{"kind":"arxiv","id":"2603.14418","version":2},"attestation_state":"computed","paper":{"title":"Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dean Barratt, Mark Emberton, Natasha Thorley, Shiqi Huang, Vasilis Stavrinides, Wen Yan, Yipei Wang, Yipeng Hu","submitted_at":"2026-03-15T15:03:20Z","abstract_excerpt":"Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentation networks to overfit to local styles and generalise poorly to unseen sites in inference. We treat each observed annotation as a noisy observation of an underlying latent 'clean' lesion mask, and propose a hierarchical expectation-maximisation (HierEM) framework that alternates between: (1) inferring a voxel-wise posterior distribution over the latent mask, and (2) training a CNN using this posterior as a soft target"},"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":"2603.14418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-15T15:03:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d63df80e14ee13911bea79aba69a4af32b104a6a15f35b34c41145461e66ae6d","abstract_canon_sha256":"411f51de28d755ef00f0753418fd5ba3dfae33c498fb9d05d2e2059f9a156b41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:47.970759Z","signature_b64":"v3mpkzNVnb8Dw4j8cbMrjh7yBmfc1+iK9ajziVVl5IbM/9RIehsi0W/8YnFlc0WjFTreUgiQPwuXG9tIjlRYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c2c6fb58fa19d93e7c7b5c629eec2637e61ce2951a41de923ff8ca5904ea9d","last_reissued_at":"2026-06-23T02:12:47.970267Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:47.970267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dean Barratt, Mark Emberton, Natasha Thorley, Shiqi Huang, Vasilis Stavrinides, Wen Yan, Yipei Wang, Yipeng Hu","submitted_at":"2026-03-15T15:03:20Z","abstract_excerpt":"Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentation networks to overfit to local styles and generalise poorly to unseen sites in inference. We treat each observed annotation as a noisy observation of an underlying latent 'clean' lesion mask, and propose a hierarchical expectation-maximisation (HierEM) framework that alternates between: (1) inferring a voxel-wise posterior distribution over the latent mask, and (2) training a CNN using this posterior as a soft target"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14418","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/2603.14418/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":"2603.14418","created_at":"2026-06-23T02:12:47.970326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14418v2","created_at":"2026-06-23T02:12:47.970326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14418","created_at":"2026-06-23T02:12:47.970326+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XBMN62Y7IM5","created_at":"2026-06-23T02:12:47.970326+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XBMN62Y7IM5SPT4","created_at":"2026-06-23T02:12:47.970326+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XBMN62Y","created_at":"2026-06-23T02:12:47.970326+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/6XBMN62Y7IM5SPT4PNOGFHXMEY","json":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY.json","graph_json":"https://pith.science/api/pith-number/6XBMN62Y7IM5SPT4PNOGFHXMEY/graph.json","events_json":"https://pith.science/api/pith-number/6XBMN62Y7IM5SPT4PNOGFHXMEY/events.json","paper":"https://pith.science/paper/6XBMN62Y"},"agent_actions":{"view_html":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY","download_json":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY.json","view_paper":"https://pith.science/paper/6XBMN62Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14418&json=true","fetch_graph":"https://pith.science/api/pith-number/6XBMN62Y7IM5SPT4PNOGFHXMEY/graph.json","fetch_events":"https://pith.science/api/pith-number/6XBMN62Y7IM5SPT4PNOGFHXMEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY/action/storage_attestation","attest_author":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY/action/author_attestation","sign_citation":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY/action/citation_signature","submit_replication":"https://pith.science/pith/6XBMN62Y7IM5SPT4PNOGFHXMEY/action/replication_record"}},"created_at":"2026-06-23T02:12:47.970326+00:00","updated_at":"2026-06-23T02:12:47.970326+00:00"}