{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PI2XRGYY4CJPDWNRVEJBY7MXSL","short_pith_number":"pith:PI2XRGYY","schema_version":"1.0","canonical_sha256":"7a35789b18e092f1d9b1a9121c7d9792f784e6990d48736a017a8ae0166764c6","source":{"kind":"arxiv","id":"2605.21652","version":1},"attestation_state":"computed","paper":{"title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Erxuan Wu, Hongjoo Lee, Huixiong Xu, Yikang Sun, Yuan Bi, Yue Zhou, Zhongliang Jiang","submitted_at":"2026-05-20T19:06:34Z","abstract_excerpt":"Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal. In clinical practice, sonographers explicitly focus on lesion regions to formulate reports, though diagnostic interpretations sometimes vary due to inherent subjectivity. However, existing VLMs are not explicitly structured to interactively zoom into lesions prior to diagnosis; moreover, they typically treat annotations as unbiased ground truths, failing to account for their inherent subjectivity and ambiguity. In this paper, we propose a framewor"},"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":"2605.21652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T19:06:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1768bebcb6151e8d7e273968e0762621fac9c392a43006128ababa4e15ebddae","abstract_canon_sha256":"67abbcd697e06af76759f63808aab9a7b86708695235705b94c24fefaa89cb13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:26.936275Z","signature_b64":"2CsInKz6Lzr1ym9GFKtk8MbjbMGPybULO8GppY1H8rK2hCfNHjIsvMk5qskL4ABs6auwq8cVbWSz6FvVKi/EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a35789b18e092f1d9b1a9121c7d9792f784e6990d48736a017a8ae0166764c6","last_reissued_at":"2026-05-22T01:03:26.935710Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:26.935710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Erxuan Wu, Hongjoo Lee, Huixiong Xu, Yikang Sun, Yuan Bi, Yue Zhou, Zhongliang Jiang","submitted_at":"2026-05-20T19:06:34Z","abstract_excerpt":"Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal. In clinical practice, sonographers explicitly focus on lesion regions to formulate reports, though diagnostic interpretations sometimes vary due to inherent subjectivity. However, existing VLMs are not explicitly structured to interactively zoom into lesions prior to diagnosis; moreover, they typically treat annotations as unbiased ground truths, failing to account for their inherent subjectivity and ambiguity. In this paper, we propose a framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21652","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/2605.21652/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":"2605.21652","created_at":"2026-05-22T01:03:26.935812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21652v1","created_at":"2026-05-22T01:03:26.935812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21652","created_at":"2026-05-22T01:03:26.935812+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI2XRGYY4CJP","created_at":"2026-05-22T01:03:26.935812+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI2XRGYY4CJPDWNR","created_at":"2026-05-22T01:03:26.935812+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI2XRGYY","created_at":"2026-05-22T01:03:26.935812+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/PI2XRGYY4CJPDWNRVEJBY7MXSL","json":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL.json","graph_json":"https://pith.science/api/pith-number/PI2XRGYY4CJPDWNRVEJBY7MXSL/graph.json","events_json":"https://pith.science/api/pith-number/PI2XRGYY4CJPDWNRVEJBY7MXSL/events.json","paper":"https://pith.science/paper/PI2XRGYY"},"agent_actions":{"view_html":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL","download_json":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL.json","view_paper":"https://pith.science/paper/PI2XRGYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21652&json=true","fetch_graph":"https://pith.science/api/pith-number/PI2XRGYY4CJPDWNRVEJBY7MXSL/graph.json","fetch_events":"https://pith.science/api/pith-number/PI2XRGYY4CJPDWNRVEJBY7MXSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL/action/storage_attestation","attest_author":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL/action/author_attestation","sign_citation":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL/action/citation_signature","submit_replication":"https://pith.science/pith/PI2XRGYY4CJPDWNRVEJBY7MXSL/action/replication_record"}},"created_at":"2026-05-22T01:03:26.935812+00:00","updated_at":"2026-05-22T01:03:26.935812+00:00"}