{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ETH3GI5PZZRYCL3L2VIZLT5ANG","short_pith_number":"pith:ETH3GI5P","schema_version":"1.0","canonical_sha256":"24cfb323afce63812f6bd55195cfa0699aa9978ac4a85d34edffe45bad0e066d","source":{"kind":"arxiv","id":"2606.11740","version":1},"attestation_state":"computed","paper":{"title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bryan Dai, Chi Liu, Derek Li, Hongming Piao, Mengzhuo Chen, Xidong Wang, Yan Shu","submitted_at":"2026-06-10T07:16:27Z","abstract_excerpt":"We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a common reasoning interface. We introduce UniReason-Med, a single-checkpoint framework that processes either a 2D image or a slice-serialized 3D volume at inference time, generating interleaved textual reasoning and localized visual evidence through shared box syntax, region-token injection, and a common grounded reasoning policy. To train this interface, we construct UniMed-CoT, a 220K instruction-tuning dataset with interleaved textual reasonin"},"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":"2606.11740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T07:16:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"298cf33a82fa471a37169aff2ac02198515350bd221652d4afad41e1dd7cc0ee","abstract_canon_sha256":"42db56e0b4269debf93b2d8068929e67f250ec5eccffbe64e6803a7ff8e394fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:05.603027Z","signature_b64":"79xUPIoUJCNgfCiMr5tfb+zgjoNXB+PCrJSZ6vLNEU1aj/uweQToJqMRS0wi4GPeekkpkyUqua8yeq5pAZYWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cfb323afce63812f6bd55195cfa0699aa9978ac4a85d34edffe45bad0e066d","last_reissued_at":"2026-06-11T01:10:05.602191Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:05.602191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bryan Dai, Chi Liu, Derek Li, Hongming Piao, Mengzhuo Chen, Xidong Wang, Yan Shu","submitted_at":"2026-06-10T07:16:27Z","abstract_excerpt":"We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a common reasoning interface. We introduce UniReason-Med, a single-checkpoint framework that processes either a 2D image or a slice-serialized 3D volume at inference time, generating interleaved textual reasoning and localized visual evidence through shared box syntax, region-token injection, and a common grounded reasoning policy. To train this interface, we construct UniMed-CoT, a 220K instruction-tuning dataset with interleaved textual reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11740","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/2606.11740/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":"2606.11740","created_at":"2026-06-11T01:10:05.602339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11740v1","created_at":"2026-06-11T01:10:05.602339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11740","created_at":"2026-06-11T01:10:05.602339+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETH3GI5PZZRY","created_at":"2026-06-11T01:10:05.602339+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETH3GI5PZZRYCL3L","created_at":"2026-06-11T01:10:05.602339+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETH3GI5P","created_at":"2026-06-11T01:10:05.602339+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/ETH3GI5PZZRYCL3L2VIZLT5ANG","json":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG.json","graph_json":"https://pith.science/api/pith-number/ETH3GI5PZZRYCL3L2VIZLT5ANG/graph.json","events_json":"https://pith.science/api/pith-number/ETH3GI5PZZRYCL3L2VIZLT5ANG/events.json","paper":"https://pith.science/paper/ETH3GI5P"},"agent_actions":{"view_html":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG","download_json":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG.json","view_paper":"https://pith.science/paper/ETH3GI5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11740&json=true","fetch_graph":"https://pith.science/api/pith-number/ETH3GI5PZZRYCL3L2VIZLT5ANG/graph.json","fetch_events":"https://pith.science/api/pith-number/ETH3GI5PZZRYCL3L2VIZLT5ANG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG/action/storage_attestation","attest_author":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG/action/author_attestation","sign_citation":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG/action/citation_signature","submit_replication":"https://pith.science/pith/ETH3GI5PZZRYCL3L2VIZLT5ANG/action/replication_record"}},"created_at":"2026-06-11T01:10:05.602339+00:00","updated_at":"2026-06-11T01:10:05.602339+00:00"}