{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GV3VDA2XXERLM7CFNV2UQDSL2S","short_pith_number":"pith:GV3VDA2X","schema_version":"1.0","canonical_sha256":"3577518357b922b67c456d75480e4bd4891f437aaf7048277b013be91a788d6f","source":{"kind":"arxiv","id":"2505.07850","version":1},"attestation_state":"computed","paper":{"title":"A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Jiayi Li, Pranav Narayanan Venkit, Sarah Rajtmajer, Shomir Wilson, Yingfan Zhou","submitted_at":"2025-05-07T20:12:48Z","abstract_excerpt":"As LLMs (large language models) are increasingly used to generate synthetic personas particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to understand how these narratives represent identity, especially that of minority communities. In this paper, we audit synthetic personas generated by 3 LLMs (GPT4o, Gemini 1.5 Pro, Deepseek 2.5) through the lens of representational harm, focusing specifically on racial identity. Using a mixed methods approach combining close reading, lexical analysis, and a parameterized creativity framework, we compare 1512 LLM gener"},"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":"2505.07850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-07T20:12:48Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"25b8621399f3f716f82d68dff7c2584bde8b9016efbdcdbfe661e02f3ec40115","abstract_canon_sha256":"90d51e7502ea5e1758e93fbc9e3f9f7c9978bdb11fbb0a9aab4d8b6f11033ad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:58.027754Z","signature_b64":"yqmogeOx8Atz/gFYaHGXaQ2SPSfxkXUG+b8MdwWrLYvO39onmKtQ0Hy/U+5Qak7zBWF+dQE0i05xHiBOG0jOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3577518357b922b67c456d75480e4bd4891f437aaf7048277b013be91a788d6f","last_reissued_at":"2026-07-05T11:01:58.027227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:58.027227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Jiayi Li, Pranav Narayanan Venkit, Sarah Rajtmajer, Shomir Wilson, Yingfan Zhou","submitted_at":"2025-05-07T20:12:48Z","abstract_excerpt":"As LLMs (large language models) are increasingly used to generate synthetic personas particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to understand how these narratives represent identity, especially that of minority communities. In this paper, we audit synthetic personas generated by 3 LLMs (GPT4o, Gemini 1.5 Pro, Deepseek 2.5) through the lens of representational harm, focusing specifically on racial identity. Using a mixed methods approach combining close reading, lexical analysis, and a parameterized creativity framework, we compare 1512 LLM gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07850","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/2505.07850/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":"2505.07850","created_at":"2026-07-05T11:01:58.027285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07850v1","created_at":"2026-07-05T11:01:58.027285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07850","created_at":"2026-07-05T11:01:58.027285+00:00"},{"alias_kind":"pith_short_12","alias_value":"GV3VDA2XXERL","created_at":"2026-07-05T11:01:58.027285+00:00"},{"alias_kind":"pith_short_16","alias_value":"GV3VDA2XXERLM7CF","created_at":"2026-07-05T11:01:58.027285+00:00"},{"alias_kind":"pith_short_8","alias_value":"GV3VDA2X","created_at":"2026-07-05T11:01:58.027285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05682","citing_title":"PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05682","citing_title":"PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07896","citing_title":"What if AI systems weren't chatbots?","ref_index":186,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S","json":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S.json","graph_json":"https://pith.science/api/pith-number/GV3VDA2XXERLM7CFNV2UQDSL2S/graph.json","events_json":"https://pith.science/api/pith-number/GV3VDA2XXERLM7CFNV2UQDSL2S/events.json","paper":"https://pith.science/paper/GV3VDA2X"},"agent_actions":{"view_html":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S","download_json":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S.json","view_paper":"https://pith.science/paper/GV3VDA2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07850&json=true","fetch_graph":"https://pith.science/api/pith-number/GV3VDA2XXERLM7CFNV2UQDSL2S/graph.json","fetch_events":"https://pith.science/api/pith-number/GV3VDA2XXERLM7CFNV2UQDSL2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S/action/storage_attestation","attest_author":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S/action/author_attestation","sign_citation":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S/action/citation_signature","submit_replication":"https://pith.science/pith/GV3VDA2XXERLM7CFNV2UQDSL2S/action/replication_record"}},"created_at":"2026-07-05T11:01:58.027285+00:00","updated_at":"2026-07-05T11:01:58.027285+00:00"}