{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FE27GOIFOOVCC553V5W4T6KUFD","short_pith_number":"pith:FE27GOIF","schema_version":"1.0","canonical_sha256":"2935f3390573aa2177bbaf6dc9f95428dd92be20a4fcaab741bcb96e18e5c02c","source":{"kind":"arxiv","id":"2606.18471","version":1},"attestation_state":"computed","paper":{"title":"Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongbo Du, Jiaming Qu, Zixin Lu","submitted_at":"2026-06-16T20:30:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible pneumonia'' communicate the strength of available evidence and directly guide decisions about follow-up testing and treatment. Altering these uncertainty expressions can change the clinical meaning entirely. In this paper, we systematically evaluated this problem in two steps. First, "},"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":"2606.18471","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T20:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"76d8d0ce505ba13bf750ffe468ee50453bcda02e0ee6cefec6ae894729e2f5ea","abstract_canon_sha256":"0a9b1f8dcc9600369f633cbe74343b09b77884a109b563df608ec43cbb52f54a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:01.982995Z","signature_b64":"mGeEoNUUTokCn5KZLL1vHpSlBxUNEWiwAxBpqmDswrReL7cEXDWDdMIqsrKnmk+onf8++Rsvf8iTZ8DVuMsYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2935f3390573aa2177bbaf6dc9f95428dd92be20a4fcaab741bcb96e18e5c02c","last_reissued_at":"2026-06-19T16:11:01.982629Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:01.982629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongbo Du, Jiaming Qu, Zixin Lu","submitted_at":"2026-06-16T20:30:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible pneumonia'' communicate the strength of available evidence and directly guide decisions about follow-up testing and treatment. Altering these uncertainty expressions can change the clinical meaning entirely. In this paper, we systematically evaluated this problem in two steps. First, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18471","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/2606.18471/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":"2606.18471","created_at":"2026-06-19T16:11:01.982688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18471v1","created_at":"2026-06-19T16:11:01.982688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18471","created_at":"2026-06-19T16:11:01.982688+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE27GOIFOOVC","created_at":"2026-06-19T16:11:01.982688+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE27GOIFOOVCC553","created_at":"2026-06-19T16:11:01.982688+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE27GOIF","created_at":"2026-06-19T16:11:01.982688+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/FE27GOIFOOVCC553V5W4T6KUFD","json":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD.json","graph_json":"https://pith.science/api/pith-number/FE27GOIFOOVCC553V5W4T6KUFD/graph.json","events_json":"https://pith.science/api/pith-number/FE27GOIFOOVCC553V5W4T6KUFD/events.json","paper":"https://pith.science/paper/FE27GOIF"},"agent_actions":{"view_html":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD","download_json":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD.json","view_paper":"https://pith.science/paper/FE27GOIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18471&json=true","fetch_graph":"https://pith.science/api/pith-number/FE27GOIFOOVCC553V5W4T6KUFD/graph.json","fetch_events":"https://pith.science/api/pith-number/FE27GOIFOOVCC553V5W4T6KUFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD/action/storage_attestation","attest_author":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD/action/author_attestation","sign_citation":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD/action/citation_signature","submit_replication":"https://pith.science/pith/FE27GOIFOOVCC553V5W4T6KUFD/action/replication_record"}},"created_at":"2026-06-19T16:11:01.982688+00:00","updated_at":"2026-06-19T16:11:01.982688+00:00"}