{"paper":{"title":"TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"TSegAgent achieves zero-shot tooth segmentation in 3D dental scans by turning the task into geometry-grounded reasoning with vision-language agents.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangshun Wei, Lu Yin, Shaojie Zhuang, Xilu Wang, Yuanfeng Zhou, Yunpeng Li","submitted_at":"2026-03-20T06:32:16Z","abstract_excerpt":"Automatic tooth segmentation and identification from intra-oral scanned 3D models are fundamental problems in digital dentistry, yet most existing approaches rely on task-specific 3D neural networks trained with densely annotated datasets, resulting in high annotation cost and limited generalization to scans from unseen sources. Thus, we propose TSegAgent, which addresses these challenges by reformulating dental analysis as a zero-shot geometric reasoning problem rather than a purely data-driven recognition task. The key idea is to combine the representational capacity of general-purpose found"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That multi-view visual abstraction combined with geometry-grounded reasoning from general foundation models can reliably infer tooth instances and identities solely from encoded dental anatomy constraints such as arch organization and volumetric relationships, without any task-specific training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TSegAgent achieves accurate zero-shot tooth segmentation on 3D dental scans via geometry-aware vision-language reasoning without task-specific training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TSegAgent achieves zero-shot tooth segmentation in 3D dental scans by turning the task into geometry-grounded reasoning with vision-language agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5d06aa2fe25d116a67a8b12c294650943e2c208becee15128961edb54a254be6"},"source":{"id":"2603.19684","kind":"arxiv","version":3},"verdict":{"id":"e4f249f4-7f4b-4fe7-90bc-be5ec3f261ba","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:58:50.866656Z","strongest_claim":"Experimental results demonstrate that this reasoning-oriented formulation enables accurate and reliable tooth segmentation and identification with low computational and annotation cost, while exhibiting strong generalization across diverse and previously unseen dental scans.","one_line_summary":"TSegAgent achieves accurate zero-shot tooth segmentation on 3D dental scans via geometry-aware vision-language reasoning without task-specific training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That multi-view visual abstraction combined with geometry-grounded reasoning from general foundation models can reliably infer tooth instances and identities solely from encoded dental anatomy constraints such as arch organization and volumetric relationships, without any task-specific training.","pith_extraction_headline":"TSegAgent achieves zero-shot tooth segmentation in 3D dental scans by turning the task into geometry-grounded reasoning with vision-language agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.19684/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":2,"snapshot_sha256":"d9049d77db4e4ab6deaa775d9bd417d599979a1bb352a664e09f380c8d7311f2"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}