{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AS7NIPNVA3HT6BIVAPZKRBE5WE","short_pith_number":"pith:AS7NIPNV","schema_version":"1.0","canonical_sha256":"04bed43db506cf3f051503f2a8849db1267907d7240774cd3f190f0f1544b304","source":{"kind":"arxiv","id":"2305.10799","version":1},"attestation_state":"computed","paper":{"title":"MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiuhui Chen, Xinyue Hu, Yi Hong, Zirui Wang","submitted_at":"2023-05-18T08:19:33Z","abstract_excerpt":"Vision-language pre-training (VLP) models have been demonstrated to be effective in many computer vision applications. In this paper, we consider developing a VLP model in the medical domain for making computer-aided diagnoses (CAD) based on image scans and text descriptions in electronic health records, as done in practice. To achieve our goal, we present a lightweight CAD system MedBLIP, a new paradigm for bootstrapping VLP from off-the-shelf frozen pre-trained image encoders and frozen large language models. We design a MedQFormer module to bridge the gap between 3D medical images and 2D pr"},"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":"2305.10799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T08:19:33Z","cross_cats_sorted":[],"title_canon_sha256":"ae1080bcc8afa9b97e4a702b5c1756189a54e3da97a203fbcd05fba2f661daa8","abstract_canon_sha256":"535470187f3de29936943f53f302d8a3642014d93060e14f06e65fe4449c62ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:26.700280Z","signature_b64":"QHzBDVTw1/53xSKv7Bzs2AtT820asts+8dRxZer98lZHeLnP9+RP+F6oJV++m/d2vwxaKF0wf6M7Ezp66V1oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04bed43db506cf3f051503f2a8849db1267907d7240774cd3f190f0f1544b304","last_reissued_at":"2026-07-05T06:11:26.699878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:26.699878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiuhui Chen, Xinyue Hu, Yi Hong, Zirui Wang","submitted_at":"2023-05-18T08:19:33Z","abstract_excerpt":"Vision-language pre-training (VLP) models have been demonstrated to be effective in many computer vision applications. In this paper, we consider developing a VLP model in the medical domain for making computer-aided diagnoses (CAD) based on image scans and text descriptions in electronic health records, as done in practice. To achieve our goal, we present a lightweight CAD system MedBLIP, a new paradigm for bootstrapping VLP from off-the-shelf frozen pre-trained image encoders and frozen large language models. We design a MedQFormer module to bridge the gap between 3D medical images and 2D pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10799","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/2305.10799/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":"2305.10799","created_at":"2026-07-05T06:11:26.699932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10799v1","created_at":"2026-07-05T06:11:26.699932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10799","created_at":"2026-07-05T06:11:26.699932+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS7NIPNVA3HT","created_at":"2026-07-05T06:11:26.699932+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS7NIPNVA3HT6BIV","created_at":"2026-07-05T06:11:26.699932+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS7NIPNV","created_at":"2026-07-05T06:11:26.699932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.00915","citing_title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE","json":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE.json","graph_json":"https://pith.science/api/pith-number/AS7NIPNVA3HT6BIVAPZKRBE5WE/graph.json","events_json":"https://pith.science/api/pith-number/AS7NIPNVA3HT6BIVAPZKRBE5WE/events.json","paper":"https://pith.science/paper/AS7NIPNV"},"agent_actions":{"view_html":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE","download_json":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE.json","view_paper":"https://pith.science/paper/AS7NIPNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10799&json=true","fetch_graph":"https://pith.science/api/pith-number/AS7NIPNVA3HT6BIVAPZKRBE5WE/graph.json","fetch_events":"https://pith.science/api/pith-number/AS7NIPNVA3HT6BIVAPZKRBE5WE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE/action/storage_attestation","attest_author":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE/action/author_attestation","sign_citation":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE/action/citation_signature","submit_replication":"https://pith.science/pith/AS7NIPNVA3HT6BIVAPZKRBE5WE/action/replication_record"}},"created_at":"2026-07-05T06:11:26.699932+00:00","updated_at":"2026-07-05T06:11:26.699932+00:00"}