{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YX73RHR756AFI34FFSYJ4OBLLW","short_pith_number":"pith:YX73RHR7","schema_version":"1.0","canonical_sha256":"c5ffb89e3fef80546f852cb09e382b5d9422c1766fbf802b62fcbdcbe7c1efb0","source":{"kind":"arxiv","id":"2503.04478","version":1},"attestation_state":"computed","paper":{"title":"Semantic Alignment of Unimodal Medical Text and Vision Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cosmin I. Bercea, Emily Chan, Julia A. Schnabel, Marta Hasny, Maxime Di Folco","submitted_at":"2025-03-06T14:28:17Z","abstract_excerpt":"General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where domain-specific solutions or alternative knowledge transfer approaches are typically required. Recent studies have noted that general-purpose models can exhibit similar latent spaces when processing semantically related data, although this alignment does not occur naturally. Building on this insight, it has been shown that applying a simple transformation - a"},"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":"2503.04478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T14:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"fcd333a603459828ce8281a96a6de17ba0800a1eae6acd5d8795f86317a8e150","abstract_canon_sha256":"173ce452d26df72d59913a19c20a24db49c329e5fee2d25d57196ad1276bb913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:39.750373Z","signature_b64":"/yUqs//WqXy80mCMGLp43/3sQA+y6KuCPYVNXMrxyK1wA3EeISLFYFwm/hQCn0AHjpFI4NB2Q8D2exdrTt0LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5ffb89e3fef80546f852cb09e382b5d9422c1766fbf802b62fcbdcbe7c1efb0","last_reissued_at":"2026-07-05T10:25:39.749699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:39.749699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Alignment of Unimodal Medical Text and Vision Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cosmin I. Bercea, Emily Chan, Julia A. Schnabel, Marta Hasny, Maxime Di Folco","submitted_at":"2025-03-06T14:28:17Z","abstract_excerpt":"General-purpose AI models, particularly those designed for text and vision, demonstrate impressive versatility across a wide range of deep-learning tasks. However, they often underperform in specialised domains like medical imaging, where domain-specific solutions or alternative knowledge transfer approaches are typically required. Recent studies have noted that general-purpose models can exhibit similar latent spaces when processing semantically related data, although this alignment does not occur naturally. Building on this insight, it has been shown that applying a simple transformation - a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04478","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/2503.04478/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":"2503.04478","created_at":"2026-07-05T10:25:39.749788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04478v1","created_at":"2026-07-05T10:25:39.749788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04478","created_at":"2026-07-05T10:25:39.749788+00:00"},{"alias_kind":"pith_short_12","alias_value":"YX73RHR756AF","created_at":"2026-07-05T10:25:39.749788+00:00"},{"alias_kind":"pith_short_16","alias_value":"YX73RHR756AFI34F","created_at":"2026-07-05T10:25:39.749788+00:00"},{"alias_kind":"pith_short_8","alias_value":"YX73RHR7","created_at":"2026-07-05T10:25:39.749788+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/YX73RHR756AFI34FFSYJ4OBLLW","json":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW.json","graph_json":"https://pith.science/api/pith-number/YX73RHR756AFI34FFSYJ4OBLLW/graph.json","events_json":"https://pith.science/api/pith-number/YX73RHR756AFI34FFSYJ4OBLLW/events.json","paper":"https://pith.science/paper/YX73RHR7"},"agent_actions":{"view_html":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW","download_json":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW.json","view_paper":"https://pith.science/paper/YX73RHR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04478&json=true","fetch_graph":"https://pith.science/api/pith-number/YX73RHR756AFI34FFSYJ4OBLLW/graph.json","fetch_events":"https://pith.science/api/pith-number/YX73RHR756AFI34FFSYJ4OBLLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW/action/storage_attestation","attest_author":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW/action/author_attestation","sign_citation":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW/action/citation_signature","submit_replication":"https://pith.science/pith/YX73RHR756AFI34FFSYJ4OBLLW/action/replication_record"}},"created_at":"2026-07-05T10:25:39.749788+00:00","updated_at":"2026-07-05T10:25:39.749788+00:00"}