{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D6HCU5ESPJZWAAGKNEXGXBSC2T","short_pith_number":"pith:D6HCU5ES","schema_version":"1.0","canonical_sha256":"1f8e2a74927a736000ca692e6b8642d4ee718a8d1258f735e0dff37cbdd45269","source":{"kind":"arxiv","id":"2505.07205","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Ethical and Safety Risks of Healthcare LLMs in China-Toward Systemic Governance under Healthy China 2030","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Ding, Jie Xu, Mouxiao Bian, Rongzhao Zhang, Xinwei Peng","submitted_at":"2025-05-12T03:28:05Z","abstract_excerpt":"Large Language Models (LLMs) are poised to transform healthcare under China's Healthy China 2030 initiative, yet they introduce new ethical and patient-safety challenges. We present a novel 12,000-item Q&A benchmark covering 11 ethics and 9 safety dimensions in medical contexts, to quantitatively evaluate these risks. Using this dataset, we assess state-of-the-art Chinese medical LLMs (e.g., Qwen 2.5-32B, DeepSeek), revealing moderate baseline performance (accuracy 42.7% for Qwen 2.5-32B) and significant improvements after fine-tuning on our data (up to 50.8% accuracy). Results show notable ga"},"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":"2505.07205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T03:28:05Z","cross_cats_sorted":[],"title_canon_sha256":"e15d22f727272bb4bced4d53eaa6be85add88bc0eb7afda656e71dc8a858ce70","abstract_canon_sha256":"e70b70913a703867d6c410424ea83eaa1e61247f8f72c1dfc2e095dbf3473a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:44.307489Z","signature_b64":"wRVl47z8B7qCOQJ0zu5gHYTeATM/0FBjwtn0WplfTNXvTK9Ps/FGYR2rkIaMyYlsjcCsToEYhe0wUSX29CKsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f8e2a74927a736000ca692e6b8642d4ee718a8d1258f735e0dff37cbdd45269","last_reissued_at":"2026-07-05T11:01:44.306913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:44.306913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Ethical and Safety Risks of Healthcare LLMs in China-Toward Systemic Governance under Healthy China 2030","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Ding, Jie Xu, Mouxiao Bian, Rongzhao Zhang, Xinwei Peng","submitted_at":"2025-05-12T03:28:05Z","abstract_excerpt":"Large Language Models (LLMs) are poised to transform healthcare under China's Healthy China 2030 initiative, yet they introduce new ethical and patient-safety challenges. We present a novel 12,000-item Q&A benchmark covering 11 ethics and 9 safety dimensions in medical contexts, to quantitatively evaluate these risks. Using this dataset, we assess state-of-the-art Chinese medical LLMs (e.g., Qwen 2.5-32B, DeepSeek), revealing moderate baseline performance (accuracy 42.7% for Qwen 2.5-32B) and significant improvements after fine-tuning on our data (up to 50.8% accuracy). Results show notable ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07205","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/2505.07205/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":"2505.07205","created_at":"2026-07-05T11:01:44.306977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07205v1","created_at":"2026-07-05T11:01:44.306977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07205","created_at":"2026-07-05T11:01:44.306977+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6HCU5ESPJZW","created_at":"2026-07-05T11:01:44.306977+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6HCU5ESPJZWAAGK","created_at":"2026-07-05T11:01:44.306977+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6HCU5ES","created_at":"2026-07-05T11:01:44.306977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05132","citing_title":"PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T","json":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T.json","graph_json":"https://pith.science/api/pith-number/D6HCU5ESPJZWAAGKNEXGXBSC2T/graph.json","events_json":"https://pith.science/api/pith-number/D6HCU5ESPJZWAAGKNEXGXBSC2T/events.json","paper":"https://pith.science/paper/D6HCU5ES"},"agent_actions":{"view_html":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T","download_json":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T.json","view_paper":"https://pith.science/paper/D6HCU5ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07205&json=true","fetch_graph":"https://pith.science/api/pith-number/D6HCU5ESPJZWAAGKNEXGXBSC2T/graph.json","fetch_events":"https://pith.science/api/pith-number/D6HCU5ESPJZWAAGKNEXGXBSC2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T/action/storage_attestation","attest_author":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T/action/author_attestation","sign_citation":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T/action/citation_signature","submit_replication":"https://pith.science/pith/D6HCU5ESPJZWAAGKNEXGXBSC2T/action/replication_record"}},"created_at":"2026-07-05T11:01:44.306977+00:00","updated_at":"2026-07-05T11:01:44.306977+00:00"}