{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQ6BXKQMPHSFSEMAQE6B3T6ZFM","short_pith_number":"pith:VQ6BXKQM","schema_version":"1.0","canonical_sha256":"ac3c1baa0c79e4591180813c1dcfd92b00c8da7296d41077ac4d48ec5b76d08b","source":{"kind":"arxiv","id":"2312.17183","version":5},"attestation_state":"computed","paper":{"title":"Large-Vocabulary Segmentation for Medical Images with Text Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chaoyi Wu, Weidi Xie, Xiaoman Zhang, Xiao Zhou, Yanfeng Wang, Yao Zhang, Ya Zhang, Ziheng Zhao","submitted_at":"2023-12-28T18:16:00Z","abstract_excerpt":"This paper aims to build a model that can Segment Anything in 3D medical images, driven by medical terminologies as Text prompts, termed as SAT. Our main contributions are three-fold: (i) We construct the first multimodal knowledge tree on human anatomy, including 6502 anatomical terminologies; Then, we build the largest and most comprehensive segmentation dataset for training, collecting over 22K 3D scans from 72 datasets, across 497 classes, with careful standardization on both image and label space; (ii) We propose to inject medical knowledge into a text encoder via contrastive learning and"},"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":"2312.17183","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-12-28T18:16:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2cc02a3d7eaf0c20f425eaba1855fcf3d66253f741ab16caa9134b256ee197c6","abstract_canon_sha256":"8ce5f589ed187ca4b2b49ec51bf46ba6c2c26d39fa64c5075481d0f1d99f7f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:01.833876Z","signature_b64":"X7zDcBExvYaoHlw7jAsq8XL0fzXcCTAOPseYeetvx8fJA+j0SFSYFrEAOLFUD0PKZTlPf6EKtj0h1LQvzQotCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac3c1baa0c79e4591180813c1dcfd92b00c8da7296d41077ac4d48ec5b76d08b","last_reissued_at":"2026-07-05T11:39:01.833373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:01.833373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Vocabulary Segmentation for Medical Images with Text Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chaoyi Wu, Weidi Xie, Xiaoman Zhang, Xiao Zhou, Yanfeng Wang, Yao Zhang, Ya Zhang, Ziheng Zhao","submitted_at":"2023-12-28T18:16:00Z","abstract_excerpt":"This paper aims to build a model that can Segment Anything in 3D medical images, driven by medical terminologies as Text prompts, termed as SAT. Our main contributions are three-fold: (i) We construct the first multimodal knowledge tree on human anatomy, including 6502 anatomical terminologies; Then, we build the largest and most comprehensive segmentation dataset for training, collecting over 22K 3D scans from 72 datasets, across 497 classes, with careful standardization on both image and label space; (ii) We propose to inject medical knowledge into a text encoder via contrastive learning and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17183","kind":"arxiv","version":5},"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/2312.17183/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":"2312.17183","created_at":"2026-07-05T11:39:01.833436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17183v5","created_at":"2026-07-05T11:39:01.833436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17183","created_at":"2026-07-05T11:39:01.833436+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ6BXKQMPHSF","created_at":"2026-07-05T11:39:01.833436+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ6BXKQMPHSFSEMA","created_at":"2026-07-05T11:39:01.833436+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ6BXKQM","created_at":"2026-07-05T11:39:01.833436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24876","citing_title":"ESICA: A Scalable Framework for Text-Guided 3D Medical Image Segmentation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01266","citing_title":"Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04447","citing_title":"Deep Reprogramming Distillation for Medical Foundation Models","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM","json":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM.json","graph_json":"https://pith.science/api/pith-number/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/graph.json","events_json":"https://pith.science/api/pith-number/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/events.json","paper":"https://pith.science/paper/VQ6BXKQM"},"agent_actions":{"view_html":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM","download_json":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM.json","view_paper":"https://pith.science/paper/VQ6BXKQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17183&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/action/storage_attestation","attest_author":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/action/author_attestation","sign_citation":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/action/citation_signature","submit_replication":"https://pith.science/pith/VQ6BXKQMPHSFSEMAQE6B3T6ZFM/action/replication_record"}},"created_at":"2026-07-05T11:39:01.833436+00:00","updated_at":"2026-07-05T11:39:01.833436+00:00"}