{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ZMYB35TZOGTORT4KFDG3INDJL","short_pith_number":"pith:3ZMYB35T","schema_version":"1.0","canonical_sha256":"de5980efb3cb8d37467c51466da1a34af8e36c47c3911a85727af209892cc51a","source":{"kind":"arxiv","id":"2503.22250","version":2},"attestation_state":"computed","paper":{"title":"Modeling Challenging Patient Interactions: LLMs for Medical Communication Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Alessandra Sonanini, Anna Bodonhelyi, Anne Herrmann-Werner, Christian Stegemann-Philipps, Enkelejda Kasneci, Friederike Holderried, Lea Herschbach, Marton Szep, Teresa Festl-Wietek","submitted_at":"2025-03-28T09:04:10Z","abstract_excerpt":"Effective patient communication is pivotal in healthcare, yet traditional medical training often lacks exposure to diverse, challenging interpersonal dynamics. To bridge this gap, this study proposes the use of Large Language Models (LLMs) to simulate authentic patient communication styles, specifically the \"accuser\" and \"rationalizer\" personas derived from the Satir model, while also ensuring multilingual applicability to accommodate diverse cultural contexts and enhance accessibility for medical professionals. Leveraging advanced prompt engineering, including behavioral prompts, author's not"},"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":"2503.22250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-28T09:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"660d04362b6552cf6749f90518bae0d2f6634d721232f9deb1077e96ca2cfffb","abstract_canon_sha256":"cb865053e6ddf826357462fa7b54843e5e8a1712227387dbe600493116f9a7b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:11.709356Z","signature_b64":"27prRrJi51g9Awd4FmyrCbXsWHDi4xSj4ck0/r8eGKdrFm7VZwIBsx0AAL3yGYvv3kknY+tVNzzk5oA8dBGgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de5980efb3cb8d37467c51466da1a34af8e36c47c3911a85727af209892cc51a","last_reissued_at":"2026-07-05T11:06:11.708826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:11.708826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Challenging Patient Interactions: LLMs for Medical Communication Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Alessandra Sonanini, Anna Bodonhelyi, Anne Herrmann-Werner, Christian Stegemann-Philipps, Enkelejda Kasneci, Friederike Holderried, Lea Herschbach, Marton Szep, Teresa Festl-Wietek","submitted_at":"2025-03-28T09:04:10Z","abstract_excerpt":"Effective patient communication is pivotal in healthcare, yet traditional medical training often lacks exposure to diverse, challenging interpersonal dynamics. To bridge this gap, this study proposes the use of Large Language Models (LLMs) to simulate authentic patient communication styles, specifically the \"accuser\" and \"rationalizer\" personas derived from the Satir model, while also ensuring multilingual applicability to accommodate diverse cultural contexts and enhance accessibility for medical professionals. Leveraging advanced prompt engineering, including behavioral prompts, author's not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22250","kind":"arxiv","version":2},"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/2503.22250/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":"2503.22250","created_at":"2026-07-05T11:06:11.708902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22250v2","created_at":"2026-07-05T11:06:11.708902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22250","created_at":"2026-07-05T11:06:11.708902+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZMYB35TZOGT","created_at":"2026-07-05T11:06:11.708902+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZMYB35TZOGTORT4","created_at":"2026-07-05T11:06:11.708902+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZMYB35T","created_at":"2026-07-05T11:06:11.708902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.10746","citing_title":"RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL","json":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL.json","graph_json":"https://pith.science/api/pith-number/3ZMYB35TZOGTORT4KFDG3INDJL/graph.json","events_json":"https://pith.science/api/pith-number/3ZMYB35TZOGTORT4KFDG3INDJL/events.json","paper":"https://pith.science/paper/3ZMYB35T"},"agent_actions":{"view_html":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL","download_json":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL.json","view_paper":"https://pith.science/paper/3ZMYB35T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22250&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZMYB35TZOGTORT4KFDG3INDJL/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZMYB35TZOGTORT4KFDG3INDJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL/action/storage_attestation","attest_author":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL/action/author_attestation","sign_citation":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL/action/citation_signature","submit_replication":"https://pith.science/pith/3ZMYB35TZOGTORT4KFDG3INDJL/action/replication_record"}},"created_at":"2026-07-05T11:06:11.708902+00:00","updated_at":"2026-07-05T11:06:11.708902+00:00"}