{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y3JJNZ3MAHNHDTBVWTSWGA2NLU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50aaa8e082218fcfd3865381c55c5ab74ad6e2e1c2257c62c409ec572bf76fd8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T04:39:19Z","title_canon_sha256":"3a6555ccc8bffa2a307e1c85fe4fc9a76be67113a00a91cac2755ba6a1adaa55"},"schema_version":"1.0","source":{"id":"2407.01948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01948","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01948v1","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01948","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"Y3JJNZ3MAHNH","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_16","alias_value":"Y3JJNZ3MAHNHDTBV","created_at":"2026-07-05T08:39:07Z"},{"alias_kind":"pith_short_8","alias_value":"Y3JJNZ3M","created_at":"2026-07-05T08:39:07Z"}],"graph_snapshots":[{"event_id":"sha256:e0ccc639b90605a8e931e88c49275c636d8f67ad45e0c3a25885a1923a86c12a","target":"graph","created_at":"2026-07-05T08:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.01948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"\\'Alvaro Soto, Denis Parra, Pablo Messina, Ren\\'e Vidal, Vladimir Araujo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T04:39:19Z","title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01948","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43e31d92ecbc2bcbee3eb2ba2e22cac8d6ce47b479af586102be19aaa8ddd3ee","target":"record","created_at":"2026-07-05T08:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50aaa8e082218fcfd3865381c55c5ab74ad6e2e1c2257c62c409ec572bf76fd8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T04:39:19Z","title_canon_sha256":"3a6555ccc8bffa2a307e1c85fe4fc9a76be67113a00a91cac2755ba6a1adaa55"},"schema_version":"1.0","source":{"id":"2407.01948","kind":"arxiv","version":1}},"canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","first_computed_at":"2026-07-05T08:39:07.596124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:07.596124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMKL2r20eqyxvtSvZhGLM+w6V1wZiBNcssE6UVdmGA7Rozz+wcxu1cnSSpE9pGNt99lgrKFPd2T9/pc6wVg9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:07.596475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e31d92ecbc2bcbee3eb2ba2e22cac8d6ce47b479af586102be19aaa8ddd3ee","sha256:e0ccc639b90605a8e931e88c49275c636d8f67ad45e0c3a25885a1923a86c12a"],"state_sha256":"be94758dfcf22e5ad169782eb5baf9abb7504739c32a7079abe0be3cb76ba68f"}