{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y3JJNZ3MAHNHDTBVWTSWGA2NLU","short_pith_number":"pith:Y3JJNZ3M","schema_version":"1.0","canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","source":{"kind":"arxiv","id":"2407.01948","version":1},"attestation_state":"computed","paper":{"title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"\\'Alvaro Soto, Denis Parra, Pablo Messina, Ren\\'e Vidal, Vladimir Araujo","submitted_at":"2024-07-02T04:39:19Z","abstract_excerpt":"Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images. To tackle this issue, we present a novel two-stage framework designed to extract high-quality factual statements from free-text radiology reports in order to improve the representations of text encoders and, consequently, their performance on various downstream tasks. In the first stage, we propose a \\textit{Fact Extractor} that leverages large language models (LLMs) to identify factual statements from well-curated domain-specific datasets. In"},"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":"2407.01948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T04:39:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3a6555ccc8bffa2a307e1c85fe4fc9a76be67113a00a91cac2755ba6a1adaa55","abstract_canon_sha256":"50aaa8e082218fcfd3865381c55c5ab74ad6e2e1c2257c62c409ec572bf76fd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:07.596475Z","signature_b64":"zMKL2r20eqyxvtSvZhGLM+w6V1wZiBNcssE6UVdmGA7Rozz+wcxu1cnSSpE9pGNt99lgrKFPd2T9/pc6wVg9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","last_reissued_at":"2026-07-05T08:39:07.596124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:07.596124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"\\'Alvaro Soto, Denis Parra, Pablo Messina, Ren\\'e Vidal, Vladimir Araujo","submitted_at":"2024-07-02T04:39:19Z","abstract_excerpt":"Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images. To tackle this issue, we present a novel two-stage framework designed to extract high-quality factual statements from free-text radiology reports in order to improve the representations of text encoders and, consequently, their performance on various downstream tasks. In the first stage, we propose a \\textit{Fact Extractor} that leverages large language models (LLMs) to identify factual statements from well-curated domain-specific datasets. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01948","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/2407.01948/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":"2407.01948","created_at":"2026-07-05T08:39:07.596180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01948v1","created_at":"2026-07-05T08:39:07.596180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01948","created_at":"2026-07-05T08:39:07.596180+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3JJNZ3MAHNH","created_at":"2026-07-05T08:39:07.596180+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3JJNZ3MAHNHDTBV","created_at":"2026-07-05T08:39:07.596180+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3JJNZ3M","created_at":"2026-07-05T08:39:07.596180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19398","citing_title":"CXR-CML: Improved zero-shot classification of long-tailed multi-label diseases in Chest X-Rays","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU","json":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU.json","graph_json":"https://pith.science/api/pith-number/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/graph.json","events_json":"https://pith.science/api/pith-number/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/events.json","paper":"https://pith.science/paper/Y3JJNZ3M"},"agent_actions":{"view_html":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU","download_json":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU.json","view_paper":"https://pith.science/paper/Y3JJNZ3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01948&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/action/storage_attestation","attest_author":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/action/author_attestation","sign_citation":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/action/citation_signature","submit_replication":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/action/replication_record"}},"created_at":"2026-07-05T08:39:07.596180+00:00","updated_at":"2026-07-05T08:39:07.596180+00:00"}