{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EFG6OK32SMNKVGHE6NTF67FRZU","short_pith_number":"pith:EFG6OK32","schema_version":"1.0","canonical_sha256":"214de72b7a931aaa98e4f3665f7cb1cd0844a31c64e846be710beef0e6593709","source":{"kind":"arxiv","id":"2303.07618","version":1},"attestation_state":"computed","paper":{"title":"Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tran, Choon Hua Thng, Gideon Ooi, Huazhu Fu, Junting Zhao, Liang Wan, Lionel Cheng, Xinxing Xu, Yang Zhou, Yong Liu, Zhihao Chen","submitted_at":"2023-03-14T03:57:16Z","abstract_excerpt":"Medical phrase grounding (MPG) aims to locate the most relevant region in a medical image, given a phrase query describing certain medical findings, which is an important task for medical image analysis and radiological diagnosis. However, existing visual grounding methods rely on general visual features for identifying objects in natural images and are not capable of capturing the subtle and specialized features of medical findings, leading to sub-optimal performance in MPG. In this paper, we propose MedRPG, an end-to-end approach for MPG. MedRPG is built on a lightweight vision-language tran"},"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":"2303.07618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T03:57:16Z","cross_cats_sorted":[],"title_canon_sha256":"0fe8c0bbc0b4b69004e6931ac619522a7df81835e298766b5f7154c684c5ac11","abstract_canon_sha256":"90224c379a605debac86c02f43585e198e0826e68362e12119641e7cd1c3c0d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:09.035665Z","signature_b64":"ozGgYifqJQmNzbSCigZvRSZ5c25yxjzt/YToV0Y3CxtRL740zeSrVxal4Ql/jBX7VQBCaMI7ep8fR3cE0eqnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"214de72b7a931aaa98e4f3665f7cb1cd0844a31c64e846be710beef0e6593709","last_reissued_at":"2026-07-05T05:51:09.035227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:09.035227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tran, Choon Hua Thng, Gideon Ooi, Huazhu Fu, Junting Zhao, Liang Wan, Lionel Cheng, Xinxing Xu, Yang Zhou, Yong Liu, Zhihao Chen","submitted_at":"2023-03-14T03:57:16Z","abstract_excerpt":"Medical phrase grounding (MPG) aims to locate the most relevant region in a medical image, given a phrase query describing certain medical findings, which is an important task for medical image analysis and radiological diagnosis. However, existing visual grounding methods rely on general visual features for identifying objects in natural images and are not capable of capturing the subtle and specialized features of medical findings, leading to sub-optimal performance in MPG. In this paper, we propose MedRPG, an end-to-end approach for MPG. MedRPG is built on a lightweight vision-language tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07618","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/2303.07618/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":"2303.07618","created_at":"2026-07-05T05:51:09.035288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07618v1","created_at":"2026-07-05T05:51:09.035288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07618","created_at":"2026-07-05T05:51:09.035288+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFG6OK32SMNK","created_at":"2026-07-05T05:51:09.035288+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFG6OK32SMNKVGHE","created_at":"2026-07-05T05:51:09.035288+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFG6OK32","created_at":"2026-07-05T05:51:09.035288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15593","citing_title":"Medillustrator: Improving Retrospective Learning in Physicians' Continuous Medical Education via Multimodal Diagnostic Data Alignment and Representation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU","json":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU.json","graph_json":"https://pith.science/api/pith-number/EFG6OK32SMNKVGHE6NTF67FRZU/graph.json","events_json":"https://pith.science/api/pith-number/EFG6OK32SMNKVGHE6NTF67FRZU/events.json","paper":"https://pith.science/paper/EFG6OK32"},"agent_actions":{"view_html":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU","download_json":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU.json","view_paper":"https://pith.science/paper/EFG6OK32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07618&json=true","fetch_graph":"https://pith.science/api/pith-number/EFG6OK32SMNKVGHE6NTF67FRZU/graph.json","fetch_events":"https://pith.science/api/pith-number/EFG6OK32SMNKVGHE6NTF67FRZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU/action/storage_attestation","attest_author":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU/action/author_attestation","sign_citation":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU/action/citation_signature","submit_replication":"https://pith.science/pith/EFG6OK32SMNKVGHE6NTF67FRZU/action/replication_record"}},"created_at":"2026-07-05T05:51:09.035288+00:00","updated_at":"2026-07-05T05:51:09.035288+00:00"}