{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XN6M3JVNBKI6FHSKEB4LHTIUGN","short_pith_number":"pith:XN6M3JVN","schema_version":"1.0","canonical_sha256":"bb7ccda6ad0a91e29e4a2078b3cd143354ba06f45da38f334d6c2d7c58af928a","source":{"kind":"arxiv","id":"2605.15561","version":1},"attestation_state":"computed","paper":{"title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayan Yang, Wenqi Fang, Zhuoyu Wu","submitted_at":"2026-05-15T03:07:52Z","abstract_excerpt":"Vision-Language Models (VLMs) facilitate medical visual question answering (MedVQA) by jointly interpreting images and text. However, existing models typically depend on large architectures and closed-set answers, which limits their efficiency and potential clinical applicability. To overcome these shortcomings, we introduce RoiMAM, an efficient VLM. It integrates a training-free ROI Generation Module with Semantic Selective Suppression to focus on lesion-relevant regions, alongside a Text Prompt Enhancer module that provides modality-specific context without introducing training parameters. C"},"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":"2605.15561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T03:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"da478872720aac82141588d663684b4031c0d56816d57d106c3b5c299c07b471","abstract_canon_sha256":"79553230ceef788c2f854099112f38020258e79e1e5d8d16b176ab332f3dcccf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:05.429922Z","signature_b64":"gcns4Nhk2vuTQA08GsKwOVuRl4lnZcyGLLrr0fBS9g4hfl954ua2O2ovMFSLsw8D2BRDuvEPM9Z0O/TICBnZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7ccda6ad0a91e29e4a2078b3cd143354ba06f45da38f334d6c2d7c58af928a","last_reissued_at":"2026-05-20T00:01:05.429042Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:05.429042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayan Yang, Wenqi Fang, Zhuoyu Wu","submitted_at":"2026-05-15T03:07:52Z","abstract_excerpt":"Vision-Language Models (VLMs) facilitate medical visual question answering (MedVQA) by jointly interpreting images and text. However, existing models typically depend on large architectures and closed-set answers, which limits their efficiency and potential clinical applicability. To overcome these shortcomings, we introduce RoiMAM, an efficient VLM. It integrates a training-free ROI Generation Module with Semantic Selective Suppression to focus on lesion-relevant regions, alongside a Text Prompt Enhancer module that provides modality-specific context without introducing training parameters. C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15561","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/2605.15561/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.260710Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.086949Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"71e1a7f11d71e04b7515b6343b590dd1d5c48a19550cca7f12115ff6749a9436"},"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":"2605.15561","created_at":"2026-05-20T00:01:05.429183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15561v1","created_at":"2026-05-20T00:01:05.429183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15561","created_at":"2026-05-20T00:01:05.429183+00:00"},{"alias_kind":"pith_short_12","alias_value":"XN6M3JVNBKI6","created_at":"2026-05-20T00:01:05.429183+00:00"},{"alias_kind":"pith_short_16","alias_value":"XN6M3JVNBKI6FHSK","created_at":"2026-05-20T00:01:05.429183+00:00"},{"alias_kind":"pith_short_8","alias_value":"XN6M3JVN","created_at":"2026-05-20T00:01:05.429183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15561","citing_title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN","json":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN.json","graph_json":"https://pith.science/api/pith-number/XN6M3JVNBKI6FHSKEB4LHTIUGN/graph.json","events_json":"https://pith.science/api/pith-number/XN6M3JVNBKI6FHSKEB4LHTIUGN/events.json","paper":"https://pith.science/paper/XN6M3JVN"},"agent_actions":{"view_html":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN","download_json":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN.json","view_paper":"https://pith.science/paper/XN6M3JVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15561&json=true","fetch_graph":"https://pith.science/api/pith-number/XN6M3JVNBKI6FHSKEB4LHTIUGN/graph.json","fetch_events":"https://pith.science/api/pith-number/XN6M3JVNBKI6FHSKEB4LHTIUGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN/action/storage_attestation","attest_author":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN/action/author_attestation","sign_citation":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN/action/citation_signature","submit_replication":"https://pith.science/pith/XN6M3JVNBKI6FHSKEB4LHTIUGN/action/replication_record"}},"created_at":"2026-05-20T00:01:05.429183+00:00","updated_at":"2026-05-20T00:01:05.429183+00:00"}