{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XGDY57SRLIJVBXSE7H3SF3D245","short_pith_number":"pith:XGDY57SR","schema_version":"1.0","canonical_sha256":"b9878efe515a1350de44f9f722ec7ae76e0b8f35586d18760a654312c0eb6151","source":{"kind":"arxiv","id":"2401.01179","version":1},"attestation_state":"computed","paper":{"title":"Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Che Liu, Jiuming Qin, Rossella Arcucci, Sibo Cheng, Yike Guo","submitted_at":"2024-01-02T12:14:41Z","abstract_excerpt":"Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-Language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision representations. However, most existing VL-SSL frameworks are trained end-to-end, which is computation-heavy and can lose vital prior information embedded in pre-trained encoders. To address both issues, we introduce the backbone-agnostic Adaptor framework, which preserves medical knowledge in pre-trained image and text encoders by keeping them frozen, and employs "},"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":"2401.01179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-02T12:14:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"be6d3196988b1ee2e7392d054c365623f6be066b8042bbe43a6718116bcdec7f","abstract_canon_sha256":"ebc73a9c293b46fde16cbfe4e3434ed0fb374ed0c3879098b073be56b4fa7064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:34.984802Z","signature_b64":"mL6EcgxXaZ3rbX6n+zot67FiWBjaJhPG/QdRR/X1UIUnU+OohOGI+wA3PR+b+6Qc8B75k60CUAKrIhcydyqXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9878efe515a1350de44f9f722ec7ae76e0b8f35586d18760a654312c0eb6151","last_reissued_at":"2026-07-05T07:29:34.984476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:34.984476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Che Liu, Jiuming Qin, Rossella Arcucci, Sibo Cheng, Yike Guo","submitted_at":"2024-01-02T12:14:41Z","abstract_excerpt":"Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-Language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision representations. However, most existing VL-SSL frameworks are trained end-to-end, which is computation-heavy and can lose vital prior information embedded in pre-trained encoders. To address both issues, we introduce the backbone-agnostic Adaptor framework, which preserves medical knowledge in pre-trained image and text encoders by keeping them frozen, and employs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01179","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/2401.01179/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":"2401.01179","created_at":"2026-07-05T07:29:34.984526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01179v1","created_at":"2026-07-05T07:29:34.984526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01179","created_at":"2026-07-05T07:29:34.984526+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGDY57SRLIJV","created_at":"2026-07-05T07:29:34.984526+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGDY57SRLIJVBXSE","created_at":"2026-07-05T07:29:34.984526+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGDY57SR","created_at":"2026-07-05T07:29:34.984526+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/XGDY57SRLIJVBXSE7H3SF3D245","json":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245.json","graph_json":"https://pith.science/api/pith-number/XGDY57SRLIJVBXSE7H3SF3D245/graph.json","events_json":"https://pith.science/api/pith-number/XGDY57SRLIJVBXSE7H3SF3D245/events.json","paper":"https://pith.science/paper/XGDY57SR"},"agent_actions":{"view_html":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245","download_json":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245.json","view_paper":"https://pith.science/paper/XGDY57SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01179&json=true","fetch_graph":"https://pith.science/api/pith-number/XGDY57SRLIJVBXSE7H3SF3D245/graph.json","fetch_events":"https://pith.science/api/pith-number/XGDY57SRLIJVBXSE7H3SF3D245/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245/action/storage_attestation","attest_author":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245/action/author_attestation","sign_citation":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245/action/citation_signature","submit_replication":"https://pith.science/pith/XGDY57SRLIJVBXSE7H3SF3D245/action/replication_record"}},"created_at":"2026-07-05T07:29:34.984526+00:00","updated_at":"2026-07-05T07:29:34.984526+00:00"}