{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TCQKABR3EDTYVUWVJLN34547UI","short_pith_number":"pith:TCQKABR3","schema_version":"1.0","canonical_sha256":"98a0a0063b20e78ad2d54adbbe779fa2374f45ddef2b9e47d63394027a784b57","source":{"kind":"arxiv","id":"2603.13800","version":2},"attestation_state":"computed","paper":{"title":"Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea M. Bejar, Gorkem Durak, Halil Ertugrul Aktas, Min Xu, Quoc-Huy Trinh, Ulas Bagci, Xi Ding, Xingjian Li, Yang Liu, Zhenyue Qin","submitted_at":"2026-03-14T07:17:45Z","abstract_excerpt":"Visual spatial intelligence is critical for medical image interpretation, yet remains largely unexplored in Multimodal Large Language Models (MLLMs) for 3D imaging. This gap persists due to a systemic lack of datasets featuring structured 3D spatial annotations beyond basic labels. In this study, we introduce an agentic pipeline that autonomously synthesizes spatial visual question-answering (VQA) data by orchestrating computational tools such as volume estimation and bounding boxes extraction with multi-agent collaboration and expert radiologist validation. We present SpatialMed, the first co"},"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":"2603.13800","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-14T07:17:45Z","cross_cats_sorted":[],"title_canon_sha256":"91abf861281295e8b9d06a1ab8b51e6aad6535d84ad29b6c5853c877124148a9","abstract_canon_sha256":"44220384516610005ad17ad5f0e05e54d88bc8086f1fdec5726153c92a5295c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:20:47.384735Z","signature_b64":"GkIj3JkWWPegAMKLHKzf/xA+HUZdIPEZrobNZA2hQDpIaNmGwZqDuYiVFmgb/FDO1ofOWAzRDAu4yrHLUJQMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98a0a0063b20e78ad2d54adbbe779fa2374f45ddef2b9e47d63394027a784b57","last_reissued_at":"2026-07-17T01:20:47.381582Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:20:47.381582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea M. Bejar, Gorkem Durak, Halil Ertugrul Aktas, Min Xu, Quoc-Huy Trinh, Ulas Bagci, Xi Ding, Xingjian Li, Yang Liu, Zhenyue Qin","submitted_at":"2026-03-14T07:17:45Z","abstract_excerpt":"Visual spatial intelligence is critical for medical image interpretation, yet remains largely unexplored in Multimodal Large Language Models (MLLMs) for 3D imaging. This gap persists due to a systemic lack of datasets featuring structured 3D spatial annotations beyond basic labels. In this study, we introduce an agentic pipeline that autonomously synthesizes spatial visual question-answering (VQA) data by orchestrating computational tools such as volume estimation and bounding boxes extraction with multi-agent collaboration and expert radiologist validation. We present SpatialMed, the first co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.13800","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/2603.13800/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":"2603.13800","created_at":"2026-07-17T01:20:47.382575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.13800v2","created_at":"2026-07-17T01:20:47.382575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.13800","created_at":"2026-07-17T01:20:47.382575+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCQKABR3EDTY","created_at":"2026-07-17T01:20:47.382575+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCQKABR3EDTYVUWV","created_at":"2026-07-17T01:20:47.382575+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCQKABR3","created_at":"2026-07-17T01:20:47.382575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI","json":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI.json","graph_json":"https://pith.science/api/pith-number/TCQKABR3EDTYVUWVJLN34547UI/graph.json","events_json":"https://pith.science/api/pith-number/TCQKABR3EDTYVUWVJLN34547UI/events.json","paper":"https://pith.science/paper/TCQKABR3"},"agent_actions":{"view_html":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI","download_json":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI.json","view_paper":"https://pith.science/paper/TCQKABR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.13800&json=true","fetch_graph":"https://pith.science/api/pith-number/TCQKABR3EDTYVUWVJLN34547UI/graph.json","fetch_events":"https://pith.science/api/pith-number/TCQKABR3EDTYVUWVJLN34547UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI/action/storage_attestation","attest_author":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI/action/author_attestation","sign_citation":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI/action/citation_signature","submit_replication":"https://pith.science/pith/TCQKABR3EDTYVUWVJLN34547UI/action/replication_record"}},"created_at":"2026-07-17T01:20:47.382575+00:00","updated_at":"2026-07-17T01:20:47.382575+00:00"}