{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G6RPATXBHYOWJMFLSMCR4XLESX","short_pith_number":"pith:G6RPATXB","schema_version":"1.0","canonical_sha256":"37a2f04ee13e1d64b0ab93051e5d6495edb51154507ae702e2d70935e4a547bb","source":{"kind":"arxiv","id":"1908.06683","version":1},"attestation_state":"computed","paper":{"title":"A unified representation network for segmentation with missing modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jens Sj\\\"olund, Jonas Adler, Kenneth Lau","submitted_at":"2019-08-19T10:31:59Z","abstract_excerpt":"Over the last few years machine learning has demonstrated groundbreaking results in many areas of medical image analysis, including segmentation. A key assumption, however, is that the train- and test distributions match. We study a realistic scenario where this assumption is clearly violated, namely segmentation with missing input modalities. We describe two neural network approaches that can handle a variable number of input modalities. The first is modality dropout: a simple but surprisingly effective modification of the training. The second is the unified representation network: a network "},"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":"1908.06683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-19T10:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"49ea10fcdf62c5869e3bfccc3bef3f6e7332e8f92d72dc3d36a4a95f90dc65fd","abstract_canon_sha256":"cf70a20606b96f889f36a7cd9cc742d084b1f49fc5a14cb333bcb6aa123a54bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:18.460510Z","signature_b64":"ArfJeoWBF6MqQawmJJPXOflRXhQltFNYyI1sDSEKenyjQZJEe4SAJQvrlcTDktwN/wSzwWpV+Psymn4hCmORBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37a2f04ee13e1d64b0ab93051e5d6495edb51154507ae702e2d70935e4a547bb","last_reissued_at":"2026-07-04T23:58:18.460104Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:18.460104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A unified representation network for segmentation with missing modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jens Sj\\\"olund, Jonas Adler, Kenneth Lau","submitted_at":"2019-08-19T10:31:59Z","abstract_excerpt":"Over the last few years machine learning has demonstrated groundbreaking results in many areas of medical image analysis, including segmentation. A key assumption, however, is that the train- and test distributions match. We study a realistic scenario where this assumption is clearly violated, namely segmentation with missing input modalities. We describe two neural network approaches that can handle a variable number of input modalities. The first is modality dropout: a simple but surprisingly effective modification of the training. The second is the unified representation network: a network "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06683","kind":"arxiv","version":1},"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/1908.06683/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":"1908.06683","created_at":"2026-07-04T23:58:18.460168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06683v1","created_at":"2026-07-04T23:58:18.460168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06683","created_at":"2026-07-04T23:58:18.460168+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6RPATXBHYOW","created_at":"2026-07-04T23:58:18.460168+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6RPATXBHYOWJMFL","created_at":"2026-07-04T23:58:18.460168+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6RPATXB","created_at":"2026-07-04T23:58:18.460168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06633","citing_title":"ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX","json":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX.json","graph_json":"https://pith.science/api/pith-number/G6RPATXBHYOWJMFLSMCR4XLESX/graph.json","events_json":"https://pith.science/api/pith-number/G6RPATXBHYOWJMFLSMCR4XLESX/events.json","paper":"https://pith.science/paper/G6RPATXB"},"agent_actions":{"view_html":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX","download_json":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX.json","view_paper":"https://pith.science/paper/G6RPATXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06683&json=true","fetch_graph":"https://pith.science/api/pith-number/G6RPATXBHYOWJMFLSMCR4XLESX/graph.json","fetch_events":"https://pith.science/api/pith-number/G6RPATXBHYOWJMFLSMCR4XLESX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX/action/storage_attestation","attest_author":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX/action/author_attestation","sign_citation":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX/action/citation_signature","submit_replication":"https://pith.science/pith/G6RPATXBHYOWJMFLSMCR4XLESX/action/replication_record"}},"created_at":"2026-07-04T23:58:18.460168+00:00","updated_at":"2026-07-04T23:58:18.460168+00:00"}