{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OERKIYCCMQWMOAT7H2MM42XOYZ","short_pith_number":"pith:OERKIYCC","schema_version":"1.0","canonical_sha256":"7122a46042642cc7027f3e98ce6aeec665f5d12805b9fc5256ad5568da52a2e5","source":{"kind":"arxiv","id":"2412.04106","version":3},"attestation_state":"computed","paper":{"title":"MRGen: Segmentation Data Engine for Underrepresented MRI Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoning Wu, Weidi Xie, Yanfeng Wang, Ya Zhang, Ziheng Zhao","submitted_at":"2024-12-04T16:34:22Z","abstract_excerpt":"Training medical image segmentation models for rare yet clinically important imaging modalities is challenging due to the scarcity of annotated data, and manual mask annotations can be costly and labor-intensive to acquire. This paper investigates leveraging generative models to synthesize data, for training segmentation models for underrepresented modalities, particularly on annotation-scarce MRI. Concretely, our contributions are threefold: (i) we introduce MRGen-DB, a large-scale radiology image-text dataset comprising extensive samples with rich metadata, including modality labels, attribu"},"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":"2412.04106","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T16:34:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b440d8d6a4550679a117ffdcbee1a29ca6e7269849fbf6095e954dd73dcd9aa3","abstract_canon_sha256":"599137cef25d22d6c69c09a4116f6a0f40ab40596a54e9bf41c5f166b517d453"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:25.695096Z","signature_b64":"vMKbSyNizci2PxT/VIreVzsOmAxPLwfiQ1L+JgRK7V7dfCPw5KMAATz/Vi6W2+Fm2kN8d7ur9jtCk2+BxZivDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7122a46042642cc7027f3e98ce6aeec665f5d12805b9fc5256ad5568da52a2e5","last_reissued_at":"2026-07-05T11:38:25.694521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:25.694521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRGen: Segmentation Data Engine for Underrepresented MRI Modalities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoning Wu, Weidi Xie, Yanfeng Wang, Ya Zhang, Ziheng Zhao","submitted_at":"2024-12-04T16:34:22Z","abstract_excerpt":"Training medical image segmentation models for rare yet clinically important imaging modalities is challenging due to the scarcity of annotated data, and manual mask annotations can be costly and labor-intensive to acquire. This paper investigates leveraging generative models to synthesize data, for training segmentation models for underrepresented modalities, particularly on annotation-scarce MRI. Concretely, our contributions are threefold: (i) we introduce MRGen-DB, a large-scale radiology image-text dataset comprising extensive samples with rich metadata, including modality labels, attribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04106","kind":"arxiv","version":3},"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/2412.04106/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":"2412.04106","created_at":"2026-07-05T11:38:25.694584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04106v3","created_at":"2026-07-05T11:38:25.694584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04106","created_at":"2026-07-05T11:38:25.694584+00:00"},{"alias_kind":"pith_short_12","alias_value":"OERKIYCCMQWM","created_at":"2026-07-05T11:38:25.694584+00:00"},{"alias_kind":"pith_short_16","alias_value":"OERKIYCCMQWMOAT7","created_at":"2026-07-05T11:38:25.694584+00:00"},{"alias_kind":"pith_short_8","alias_value":"OERKIYCC","created_at":"2026-07-05T11:38:25.694584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07647","citing_title":"Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ","json":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ.json","graph_json":"https://pith.science/api/pith-number/OERKIYCCMQWMOAT7H2MM42XOYZ/graph.json","events_json":"https://pith.science/api/pith-number/OERKIYCCMQWMOAT7H2MM42XOYZ/events.json","paper":"https://pith.science/paper/OERKIYCC"},"agent_actions":{"view_html":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ","download_json":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ.json","view_paper":"https://pith.science/paper/OERKIYCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04106&json=true","fetch_graph":"https://pith.science/api/pith-number/OERKIYCCMQWMOAT7H2MM42XOYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OERKIYCCMQWMOAT7H2MM42XOYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ/action/storage_attestation","attest_author":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ/action/author_attestation","sign_citation":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ/action/citation_signature","submit_replication":"https://pith.science/pith/OERKIYCCMQWMOAT7H2MM42XOYZ/action/replication_record"}},"created_at":"2026-07-05T11:38:25.694584+00:00","updated_at":"2026-07-05T11:38:25.694584+00:00"}