{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3AI2UI5QDZDDLDRNZMBUTERUEI","short_pith_number":"pith:3AI2UI5Q","schema_version":"1.0","canonical_sha256":"d811aa23b01e46358e2dcb03499234221e01095ab1e20b3d9627712cbdcc864f","source":{"kind":"arxiv","id":"2407.00870","version":2},"attestation_state":"computed","paper":{"title":"Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Ananjan Nandi, Cheng Chang, Diyi Yang, Emma Brunskill, Ryan Louie, William Fang","submitted_at":"2024-07-01T00:43:02Z","abstract_excerpt":"Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious. To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLM-prompted roleplay. We apply this pipeline to enable senior menta"},"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":"2407.00870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T00:43:02Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"13d4576c12c4614940c258ce2fb144fd0284f9dfd1b83cf1c1872b98737abed5","abstract_canon_sha256":"807ab42d390abace5c74562ecbf18d0642ba541260c1a54ae1f67a5258915c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:29.553116Z","signature_b64":"O42ncJYCrWV+sLlrKmduZUz5/KDjKN0t9ztY7hY+Ocd+uqPCM5lpRLeMM5gf+bvZ43ZXoC5xTdFCmvIIZV8SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d811aa23b01e46358e2dcb03499234221e01095ab1e20b3d9627712cbdcc864f","last_reissued_at":"2026-07-05T08:43:29.552646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:29.552646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Ananjan Nandi, Cheng Chang, Diyi Yang, Emma Brunskill, Ryan Louie, William Fang","submitted_at":"2024-07-01T00:43:02Z","abstract_excerpt":"Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious. To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLM-prompted roleplay. We apply this pipeline to enable senior menta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00870","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/2407.00870/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":"2407.00870","created_at":"2026-07-05T08:43:29.552701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00870v2","created_at":"2026-07-05T08:43:29.552701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00870","created_at":"2026-07-05T08:43:29.552701+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AI2UI5QDZDD","created_at":"2026-07-05T08:43:29.552701+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AI2UI5QDZDDLDRN","created_at":"2026-07-05T08:43:29.552701+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AI2UI5Q","created_at":"2026-07-05T08:43:29.552701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.09049","citing_title":"Inertia in Moral and Value Judgments of Large Language Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2411.00585","citing_title":"Fairness Testing of Large Language Models in Role-Playing","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10970","citing_title":"Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI","json":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI.json","graph_json":"https://pith.science/api/pith-number/3AI2UI5QDZDDLDRNZMBUTERUEI/graph.json","events_json":"https://pith.science/api/pith-number/3AI2UI5QDZDDLDRNZMBUTERUEI/events.json","paper":"https://pith.science/paper/3AI2UI5Q"},"agent_actions":{"view_html":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI","download_json":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI.json","view_paper":"https://pith.science/paper/3AI2UI5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00870&json=true","fetch_graph":"https://pith.science/api/pith-number/3AI2UI5QDZDDLDRNZMBUTERUEI/graph.json","fetch_events":"https://pith.science/api/pith-number/3AI2UI5QDZDDLDRNZMBUTERUEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI/action/storage_attestation","attest_author":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI/action/author_attestation","sign_citation":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI/action/citation_signature","submit_replication":"https://pith.science/pith/3AI2UI5QDZDDLDRNZMBUTERUEI/action/replication_record"}},"created_at":"2026-07-05T08:43:29.552701+00:00","updated_at":"2026-07-05T08:43:29.552701+00:00"}