{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4P3HLOYTQEJPNV7EKU6PEEJW7","short_pith_number":"pith:D4P3HLOY","schema_version":"1.0","canonical_sha256":"1f1fb3add89c0897b6bf22a9e79089b7e148a56c684f1afda93beee1c0ece626","source":{"kind":"arxiv","id":"2402.15759","version":2},"attestation_state":"computed","paper":{"title":"TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdullaev Bakhrom Ismoilovich, Bekchanov Habibullo, Defu Tang, Dongjie Cheng, Jun Gao, Kang Li, Le Zhang, LinJing Wei, Qicheng Lao, Urazboev Gayrat, Yuldashov Elyorbek, Zekun Jiang, Ziyuan Qin","submitted_at":"2024-02-24T08:10:54Z","abstract_excerpt":"This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can "},"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":"2402.15759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-24T08:10:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f18bf7f16daa9a24f33ee3d2f8efa60ad81a0b4441e137d09dd1c50aaf53a824","abstract_canon_sha256":"04fb36984c6cde47a8f3efc02a468a9c476d15ad6d5ac13cc986585b801d5e90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:54.375031Z","signature_b64":"qDMTq0m4rKfD2UMiCf9hHKm3VOwFVk0dDD5glH0HOzi/uOZWeJOPhW19cGe4wKC4NYYeRjBaHYpCzy9T+oNeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f1fb3add89c0897b6bf22a9e79089b7e148a56c684f1afda93beee1c0ece626","last_reissued_at":"2026-07-05T09:19:54.374551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:54.374551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abdullaev Bakhrom Ismoilovich, Bekchanov Habibullo, Defu Tang, Dongjie Cheng, Jun Gao, Kang Li, Le Zhang, LinJing Wei, Qicheng Lao, Urazboev Gayrat, Yuldashov Elyorbek, Zekun Jiang, Ziyuan Qin","submitted_at":"2024-02-24T08:10:54Z","abstract_excerpt":"This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15759","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/2402.15759/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":"2402.15759","created_at":"2026-07-05T09:19:54.374606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15759v2","created_at":"2026-07-05T09:19:54.374606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15759","created_at":"2026-07-05T09:19:54.374606+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4P3HLOYTQEJ","created_at":"2026-07-05T09:19:54.374606+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4P3HLOYTQEJPNV7","created_at":"2026-07-05T09:19:54.374606+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4P3HLOY","created_at":"2026-07-05T09:19:54.374606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7","json":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7.json","graph_json":"https://pith.science/api/pith-number/D4P3HLOYTQEJPNV7EKU6PEEJW7/graph.json","events_json":"https://pith.science/api/pith-number/D4P3HLOYTQEJPNV7EKU6PEEJW7/events.json","paper":"https://pith.science/paper/D4P3HLOY"},"agent_actions":{"view_html":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7","download_json":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7.json","view_paper":"https://pith.science/paper/D4P3HLOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15759&json=true","fetch_graph":"https://pith.science/api/pith-number/D4P3HLOYTQEJPNV7EKU6PEEJW7/graph.json","fetch_events":"https://pith.science/api/pith-number/D4P3HLOYTQEJPNV7EKU6PEEJW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7/action/storage_attestation","attest_author":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7/action/author_attestation","sign_citation":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7/action/citation_signature","submit_replication":"https://pith.science/pith/D4P3HLOYTQEJPNV7EKU6PEEJW7/action/replication_record"}},"created_at":"2026-07-05T09:19:54.374606+00:00","updated_at":"2026-07-05T09:19:54.374606+00:00"}