{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JXSABO3E3FULYF2PHYNC3PEWTZ","short_pith_number":"pith:JXSABO3E","schema_version":"1.0","canonical_sha256":"4de400bb64d968bc174f3e1a2dbc969e57166eefd409a25751a61eba6976d93b","source":{"kind":"arxiv","id":"2306.04811","version":1},"attestation_state":"computed","paper":{"title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Che Liu, Rossella Arcucci, Sibo Cheng, Wei Huang, Yinda Chen, Zhiwei Xiong","submitted_at":"2023-06-07T22:20:51Z","abstract_excerpt":"Vision-Language Pretraining (VLP) has demonstrated remarkable capabilities in learning visual representations from textual descriptions of images without annotations. Yet, effective VLP demands large-scale image-text pairs, a resource that suffers scarcity in the medical domain. Moreover, conventional VLP is limited to 2D images while medical images encompass diverse modalities, often in 3D, making the learning process more challenging. To address these challenges, we present Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation (GTGM), a framework that e"},"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":"2306.04811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T22:20:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e18dfb241e90b10b377ae07d6d2e44dee2de930e02c9f28cf4f93abeff5e247","abstract_canon_sha256":"febb69c4881d6ba1f34f048b71d031d1a1af5a9289f07edcb472bab3b031af5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:42.292082Z","signature_b64":"+b2tU5ANHr2GaSEAv5InW1u9hnaF5qwRbsx9TgaCZBkTzer4V72yrYG5UfHW2RUu1UsYWKhIL15w02HkhMTdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de400bb64d968bc174f3e1a2dbc969e57166eefd409a25751a61eba6976d93b","last_reissued_at":"2026-07-05T06:18:42.291608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:42.291608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Che Liu, Rossella Arcucci, Sibo Cheng, Wei Huang, Yinda Chen, Zhiwei Xiong","submitted_at":"2023-06-07T22:20:51Z","abstract_excerpt":"Vision-Language Pretraining (VLP) has demonstrated remarkable capabilities in learning visual representations from textual descriptions of images without annotations. Yet, effective VLP demands large-scale image-text pairs, a resource that suffers scarcity in the medical domain. Moreover, conventional VLP is limited to 2D images while medical images encompass diverse modalities, often in 3D, making the learning process more challenging. To address these challenges, we present Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation (GTGM), a framework that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04811","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/2306.04811/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":"2306.04811","created_at":"2026-07-05T06:18:42.291667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04811v1","created_at":"2026-07-05T06:18:42.291667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04811","created_at":"2026-07-05T06:18:42.291667+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXSABO3E3FUL","created_at":"2026-07-05T06:18:42.291667+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXSABO3E3FULYF2P","created_at":"2026-07-05T06:18:42.291667+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXSABO3E","created_at":"2026-07-05T06:18:42.291667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.13215","citing_title":"DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05782","citing_title":"TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12315","citing_title":"GTPBD-MM: A Global Terraced Parcel and Boundary Dataset with Multi-Modality","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ","json":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ.json","graph_json":"https://pith.science/api/pith-number/JXSABO3E3FULYF2PHYNC3PEWTZ/graph.json","events_json":"https://pith.science/api/pith-number/JXSABO3E3FULYF2PHYNC3PEWTZ/events.json","paper":"https://pith.science/paper/JXSABO3E"},"agent_actions":{"view_html":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ","download_json":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ.json","view_paper":"https://pith.science/paper/JXSABO3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04811&json=true","fetch_graph":"https://pith.science/api/pith-number/JXSABO3E3FULYF2PHYNC3PEWTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JXSABO3E3FULYF2PHYNC3PEWTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ/action/storage_attestation","attest_author":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ/action/author_attestation","sign_citation":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ/action/citation_signature","submit_replication":"https://pith.science/pith/JXSABO3E3FULYF2PHYNC3PEWTZ/action/replication_record"}},"created_at":"2026-07-05T06:18:42.291667+00:00","updated_at":"2026-07-05T06:18:42.291667+00:00"}