{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QVIPY6RU6O7ZEU5C4YOQ3NF7P4","short_pith_number":"pith:QVIPY6RU","schema_version":"1.0","canonical_sha256":"8550fc7a34f3bf9253a2e61d0db4bf7f0512234550b5e464080b46da034c31e4","source":{"kind":"arxiv","id":"2404.03618","version":1},"attestation_state":"computed","paper":{"title":"DeViDe: Faceted medical knowledge for improved medical vision-language pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anjany Sekuboyina, Bjoern Menze, Corentin Royer, Haozhe Luo, Ziyu Zhou","submitted_at":"2024-04-04T17:40:06Z","abstract_excerpt":"Vision-language pre-training for chest X-rays has made significant strides, primarily by utilizing paired radiographs and radiology reports. However, existing approaches often face challenges in encoding medical knowledge effectively. While radiology reports provide insights into the current disease manifestation, medical definitions (as used by contemporary methods) tend to be overly abstract, creating a gap in knowledge. To address this, we propose DeViDe, a novel transformer-based method that leverages radiographic descriptions from the open web. These descriptions outline general visual ch"},"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":"2404.03618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:40:06Z","cross_cats_sorted":[],"title_canon_sha256":"2af4fd3b58c2671c90cb7265fe0b6ff63857886ac8083e6bab3c765b2532929f","abstract_canon_sha256":"6b17b61bdb27f77300031ddded2e7f73de07cedb3556253d95e07cd4fcc0bba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:28.206429Z","signature_b64":"N0P+6+L33oYD2CtJvV9OwHLy9mW2zxpRC6fllNxkDe+o0mgv/YESkhPVCZLVvKhKYK8AEY6tobbsxSGjRJaQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8550fc7a34f3bf9253a2e61d0db4bf7f0512234550b5e464080b46da034c31e4","last_reissued_at":"2026-07-05T08:04:28.206025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:28.206025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeViDe: Faceted medical knowledge for improved medical vision-language pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anjany Sekuboyina, Bjoern Menze, Corentin Royer, Haozhe Luo, Ziyu Zhou","submitted_at":"2024-04-04T17:40:06Z","abstract_excerpt":"Vision-language pre-training for chest X-rays has made significant strides, primarily by utilizing paired radiographs and radiology reports. However, existing approaches often face challenges in encoding medical knowledge effectively. While radiology reports provide insights into the current disease manifestation, medical definitions (as used by contemporary methods) tend to be overly abstract, creating a gap in knowledge. To address this, we propose DeViDe, a novel transformer-based method that leverages radiographic descriptions from the open web. These descriptions outline general visual ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03618","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/2404.03618/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":"2404.03618","created_at":"2026-07-05T08:04:28.206083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03618v1","created_at":"2026-07-05T08:04:28.206083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03618","created_at":"2026-07-05T08:04:28.206083+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVIPY6RU6O7Z","created_at":"2026-07-05T08:04:28.206083+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVIPY6RU6O7ZEU5C","created_at":"2026-07-05T08:04:28.206083+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVIPY6RU","created_at":"2026-07-05T08:04:28.206083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04572","citing_title":"Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4","json":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4.json","graph_json":"https://pith.science/api/pith-number/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/graph.json","events_json":"https://pith.science/api/pith-number/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/events.json","paper":"https://pith.science/paper/QVIPY6RU"},"agent_actions":{"view_html":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4","download_json":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4.json","view_paper":"https://pith.science/paper/QVIPY6RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03618&json=true","fetch_graph":"https://pith.science/api/pith-number/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/graph.json","fetch_events":"https://pith.science/api/pith-number/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/action/storage_attestation","attest_author":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/action/author_attestation","sign_citation":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/action/citation_signature","submit_replication":"https://pith.science/pith/QVIPY6RU6O7ZEU5C4YOQ3NF7P4/action/replication_record"}},"created_at":"2026-07-05T08:04:28.206083+00:00","updated_at":"2026-07-05T08:04:28.206083+00:00"}