{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y3JJNZ3MAHNHDTBVWTSWGA2NLU","short_pith_number":"pith:Y3JJNZ3M","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"},"canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","source":{"kind":"arxiv","id":"2407.01948","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y3JJNZ3MAHNHDTBVWTSWGA2NLU","target":"record","payload":{"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"},"canonical_sha256":"c6d296e76c01da71cc35b4e563034d5d12050ebef844941fe1bd921aee4dc260","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"},"source_kind":"arxiv","source_id":"2407.01948","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/zdOHcc9V37qi6WorFIMCTRee5cGeXn5iiqFJC1dUoarEjWkT2Z3Dixo6UtRMgVu+RA6QYsIJohN3h7AhBcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:49:42.802706Z"},"content_sha256":"43e31d92ecbc2bcbee3eb2ba2e22cac8d6ce47b479af586102be19aaa8ddd3ee","schema_version":"1.0","event_id":"sha256:43e31d92ecbc2bcbee3eb2ba2e22cac8d6ce47b479af586102be19aaa8ddd3ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y3JJNZ3MAHNHDTBVWTSWGA2NLU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/3j+7a/WIPodc7scNsv1i8T1RK5QIl3PQJT6m9b6e61j7S6XVis2Efd9djE74mo4XnO5tVC38MAgTq/0NmvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:49:42.803713Z"},"content_sha256":"e0ccc639b90605a8e931e88c49275c636d8f67ad45e0c3a25885a1923a86c12a","schema_version":"1.0","event_id":"sha256:e0ccc639b90605a8e931e88c49275c636d8f67ad45e0c3a25885a1923a86c12a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/bundle.json","state_url":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T22:49:42Z","links":{"resolver":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU","bundle":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/bundle.json","state":"https://pith.science/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3JJNZ3MAHNHDTBVWTSWGA2NLU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vs2H29cdTnl385UftT5oWqM6DxXaSzpkeklCwzybkJ1RXb9Mgz60VqSvI7TKiV+V92RPGC6kmYBFOoTE9jKWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T22:49:42.837513Z","bundle_sha256":"dabfc13630cb5d5d28964a939014fb92620f55962f10230abf4075b5bced1668"}}