{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4DJGXJAYBFLF5MST73FFLZRPO4","short_pith_number":"pith:4DJGXJAY","schema_version":"1.0","canonical_sha256":"e0d26ba41809565eb253feca55e62f77380d57a00794f750273ad6e495347911","source":{"kind":"arxiv","id":"2505.01693","version":1},"attestation_state":"computed","paper":{"title":"High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Wong, Kaito Tanaka","submitted_at":"2025-05-03T04:50:55Z","abstract_excerpt":"Automated labeling of chest X-ray reports is essential for enabling downstream tasks such as training image-based diagnostic models, population health studies, and clinical decision support. However, the high variability, complexity, and prevalence of negation and uncertainty in these free-text reports pose significant challenges for traditional Natural Language Processing methods. While large language models (LLMs) demonstrate strong text understanding, their direct application for large-scale, efficient labeling is limited by computational cost and speed. This paper introduces DeBERTa-RAD, 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":"2505.01693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-03T04:50:55Z","cross_cats_sorted":[],"title_canon_sha256":"f342bc20c77404c99d12465ea8cfa092635e1d049c45457885fd39d427b2180e","abstract_canon_sha256":"548b1ae763eeed9a8b9686ed4b5afcad733f2747236de28eea801c07e0046ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:02.140327Z","signature_b64":"lPZ8Mj52ffXjfFOOvv+YhS0h8JrGPLGKeksaTA5s8kqEcKZnjpltJC8aEfSdAMWxVIVdTA87RDaglGbzm2BpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0d26ba41809565eb253feca55e62f77380d57a00794f750273ad6e495347911","last_reissued_at":"2026-07-05T10:58:02.139821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:02.139821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Wong, Kaito Tanaka","submitted_at":"2025-05-03T04:50:55Z","abstract_excerpt":"Automated labeling of chest X-ray reports is essential for enabling downstream tasks such as training image-based diagnostic models, population health studies, and clinical decision support. However, the high variability, complexity, and prevalence of negation and uncertainty in these free-text reports pose significant challenges for traditional Natural Language Processing methods. While large language models (LLMs) demonstrate strong text understanding, their direct application for large-scale, efficient labeling is limited by computational cost and speed. This paper introduces DeBERTa-RAD, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01693","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/2505.01693/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":"2505.01693","created_at":"2026-07-05T10:58:02.139880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01693v1","created_at":"2026-07-05T10:58:02.139880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01693","created_at":"2026-07-05T10:58:02.139880+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DJGXJAYBFLF","created_at":"2026-07-05T10:58:02.139880+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DJGXJAYBFLF5MST","created_at":"2026-07-05T10:58:02.139880+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DJGXJAY","created_at":"2026-07-05T10:58:02.139880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07853","citing_title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4","json":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4.json","graph_json":"https://pith.science/api/pith-number/4DJGXJAYBFLF5MST73FFLZRPO4/graph.json","events_json":"https://pith.science/api/pith-number/4DJGXJAYBFLF5MST73FFLZRPO4/events.json","paper":"https://pith.science/paper/4DJGXJAY"},"agent_actions":{"view_html":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4","download_json":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4.json","view_paper":"https://pith.science/paper/4DJGXJAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01693&json=true","fetch_graph":"https://pith.science/api/pith-number/4DJGXJAYBFLF5MST73FFLZRPO4/graph.json","fetch_events":"https://pith.science/api/pith-number/4DJGXJAYBFLF5MST73FFLZRPO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4/action/storage_attestation","attest_author":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4/action/author_attestation","sign_citation":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4/action/citation_signature","submit_replication":"https://pith.science/pith/4DJGXJAYBFLF5MST73FFLZRPO4/action/replication_record"}},"created_at":"2026-07-05T10:58:02.139880+00:00","updated_at":"2026-07-05T10:58:02.139880+00:00"}