{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DLLRZEVW2F3XTT7YN2AB6D4ZI","short_pith_number":"pith:4DLLRZEV","schema_version":"1.0","canonical_sha256":"e0d6b8e495b68bbbce7fc37400f87cca183ff296d329c253c96bfb0adca99385","source":{"kind":"arxiv","id":"2512.14157","version":2},"attestation_state":"computed","paper":{"title":"Ophiuchus: Incentivizing Tool-augmented \"Think with Images\" for Joint Medical Segmentation, Understanding and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jintai Chen, Peng Zhang, Shihui Zhen, Wenjie Li, Xiaoming Shi, Yankai Jiang, Yichen Li, Yujie Zhang","submitted_at":"2025-12-16T07:37:23Z","abstract_excerpt":"Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains. However, they still struggle with complex clinical tasks that necessitate dynamic and iterative focusing on fine-grained visual regions. To close this gap, we introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when fine-grained visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought for precise segment"},"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":"2512.14157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-12-16T07:37:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"944c99378bb02ee588bdb48f0d14ebe53fdf3cb6c8e705e99444d9159c04b5f4","abstract_canon_sha256":"d658766cb8e2ad1417c3ad45ead976b34bada6e2d6e7171e58fffd015dc128fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:15.676131Z","signature_b64":"b/XYTECpu2/L3VJlcvLu5jOf0nKF7cV9y6lLLbes5+0/O3FYfYukPG9LChO8IIaEitlB5xAqRnr/tzcYwbP/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d6b8e495b68bbbce7fc37400f87cca183ff296d329c253c96bfb0adca99385","last_reissued_at":"2026-07-03T01:17:15.675629Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:15.675629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ophiuchus: Incentivizing Tool-augmented \"Think with Images\" for Joint Medical Segmentation, Understanding and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jintai Chen, Peng Zhang, Shihui Zhen, Wenjie Li, Xiaoming Shi, Yankai Jiang, Yichen Li, Yujie Zhang","submitted_at":"2025-12-16T07:37:23Z","abstract_excerpt":"Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains. However, they still struggle with complex clinical tasks that necessitate dynamic and iterative focusing on fine-grained visual regions. To close this gap, we introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when fine-grained visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought for precise segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14157","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/2512.14157/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":"2512.14157","created_at":"2026-07-03T01:17:15.675691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14157v2","created_at":"2026-07-03T01:17:15.675691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14157","created_at":"2026-07-03T01:17:15.675691+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DLLRZEVW2F3","created_at":"2026-07-03T01:17:15.675691+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DLLRZEVW2F3XTT7","created_at":"2026-07-03T01:17:15.675691+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DLLRZEV","created_at":"2026-07-03T01:17:15.675691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":278,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09679","citing_title":"DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01779","citing_title":"MedScribe: Clinically Grounded CT Reporting through Agentic Workflows","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI","json":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI.json","graph_json":"https://pith.science/api/pith-number/4DLLRZEVW2F3XTT7YN2AB6D4ZI/graph.json","events_json":"https://pith.science/api/pith-number/4DLLRZEVW2F3XTT7YN2AB6D4ZI/events.json","paper":"https://pith.science/paper/4DLLRZEV"},"agent_actions":{"view_html":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI","download_json":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI.json","view_paper":"https://pith.science/paper/4DLLRZEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14157&json=true","fetch_graph":"https://pith.science/api/pith-number/4DLLRZEVW2F3XTT7YN2AB6D4ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/4DLLRZEVW2F3XTT7YN2AB6D4ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI/action/storage_attestation","attest_author":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI/action/author_attestation","sign_citation":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI/action/citation_signature","submit_replication":"https://pith.science/pith/4DLLRZEVW2F3XTT7YN2AB6D4ZI/action/replication_record"}},"created_at":"2026-07-03T01:17:15.675691+00:00","updated_at":"2026-07-03T01:17:15.675691+00:00"}