{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQNMXKTGEJTPJCX5RYWFCGXIWX","short_pith_number":"pith:ZQNMXKTG","schema_version":"1.0","canonical_sha256":"cc1acbaa662266f48afd8e2c511ae8b5e8b7a9b665cbbf9b34054e4ab4d5f2f3","source":{"kind":"arxiv","id":"2505.14726","version":1},"attestation_state":"computed","paper":{"title":"MedBLIP: Fine-tuning BLIP for Medical Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Diwita Banerjee, Manshi Limbu","submitted_at":"2025-05-20T00:49:08Z","abstract_excerpt":"Medical image captioning is a challenging task that requires generating clinically accurate and semantically meaningful descriptions of radiology images. While recent vision-language models (VLMs) such as BLIP, BLIP2, Gemini and ViT-GPT2 show strong performance on natural image datasets, they often produce generic or imprecise captions when applied to specialized medical domains. In this project, we explore the effectiveness of fine-tuning the BLIP model on the ROCO dataset for improved radiology captioning. We compare the fine-tuned BLIP against its zero-shot version, BLIP-2 base, BLIP-2 Inst"},"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":"2505.14726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-20T00:49:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"510f44e69c79b94b7350140135fe03463edc65cb489620ed4d2c06561e463cf9","abstract_canon_sha256":"10eede2664d8359d7fa2bb0be95a92d41a3b66884714bf06fc70e952a6f1bde6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:34.475134Z","signature_b64":"nkJYK6cizLoX4oPYw7Pm3RPaGblVLd3Kj5dgQxR4+T3Skg+rWivbguDlxqYmPodxkaSnNoOv0JCxRzGI8347Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1acbaa662266f48afd8e2c511ae8b5e8b7a9b665cbbf9b34054e4ab4d5f2f3","last_reissued_at":"2026-07-05T11:06:34.474688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:34.474688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedBLIP: Fine-tuning BLIP for Medical Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Diwita Banerjee, Manshi Limbu","submitted_at":"2025-05-20T00:49:08Z","abstract_excerpt":"Medical image captioning is a challenging task that requires generating clinically accurate and semantically meaningful descriptions of radiology images. While recent vision-language models (VLMs) such as BLIP, BLIP2, Gemini and ViT-GPT2 show strong performance on natural image datasets, they often produce generic or imprecise captions when applied to specialized medical domains. In this project, we explore the effectiveness of fine-tuning the BLIP model on the ROCO dataset for improved radiology captioning. We compare the fine-tuned BLIP against its zero-shot version, BLIP-2 base, BLIP-2 Inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14726","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/2505.14726/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":"2505.14726","created_at":"2026-07-05T11:06:34.474748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14726v1","created_at":"2026-07-05T11:06:34.474748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14726","created_at":"2026-07-05T11:06:34.474748+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQNMXKTGEJTP","created_at":"2026-07-05T11:06:34.474748+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQNMXKTGEJTPJCX5","created_at":"2026-07-05T11:06:34.474748+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQNMXKTG","created_at":"2026-07-05T11:06:34.474748+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/ZQNMXKTGEJTPJCX5RYWFCGXIWX","json":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX.json","graph_json":"https://pith.science/api/pith-number/ZQNMXKTGEJTPJCX5RYWFCGXIWX/graph.json","events_json":"https://pith.science/api/pith-number/ZQNMXKTGEJTPJCX5RYWFCGXIWX/events.json","paper":"https://pith.science/paper/ZQNMXKTG"},"agent_actions":{"view_html":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX","download_json":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX.json","view_paper":"https://pith.science/paper/ZQNMXKTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14726&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQNMXKTGEJTPJCX5RYWFCGXIWX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQNMXKTGEJTPJCX5RYWFCGXIWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX/action/storage_attestation","attest_author":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX/action/author_attestation","sign_citation":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX/action/citation_signature","submit_replication":"https://pith.science/pith/ZQNMXKTGEJTPJCX5RYWFCGXIWX/action/replication_record"}},"created_at":"2026-07-05T11:06:34.474748+00:00","updated_at":"2026-07-05T11:06:34.474748+00:00"}