{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QNR3556X62FPK5QHXWL2JMNIM4","short_pith_number":"pith:QNR3556X","schema_version":"1.0","canonical_sha256":"8363bef7d7f68af57607bd97a4b1a8673ea3ea0ac9564e1b55feb4d35f19efe5","source":{"kind":"arxiv","id":"2409.12538","version":2},"attestation_state":"computed","paper":{"title":"PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Haijun Xia, Mehul Jitendra Oswal, Pranav Sharma, Yiren Liu, Yun Huang","submitted_at":"2024-09-19T07:54:29Z","abstract_excerpt":"Generating interdisciplinary research ideas requires diverse domain expertise, but access to timely feedback is often limited by the availability of experts. In this paper, we introduce PersonaFlow, a novel system designed to provide multiple perspectives by using LLMs to simulate domain-specific experts. Our user studies showed that the new design 1) increased the perceived relevance and creativity of ideated research directions, and 2) promoted users' critical thinking activities (e.g., interpretation, analysis, evaluation, inference, and self-regulation), without increasing their perceived "},"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":"2409.12538","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-09-19T07:54:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c4423ffe3550deade9e91818c9083509bda03580fe91e5ae541e83720a72b74","abstract_canon_sha256":"5bf635c392d01844dc3e70ce35dca5739cf28cb3d5f51fbaf7fcd4b83be95e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:00.081484Z","signature_b64":"uu0Z2ohCPKGydZO/bn2Y+uvcr5tFt/jspIzpmRwXduXTEssn+jjHcXqcreuZePFWC1oJn4l819ULdqy3jSKaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8363bef7d7f68af57607bd97a4b1a8673ea3ea0ac9564e1b55feb4d35f19efe5","last_reissued_at":"2026-07-05T11:34:00.080962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:00.080962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Haijun Xia, Mehul Jitendra Oswal, Pranav Sharma, Yiren Liu, Yun Huang","submitted_at":"2024-09-19T07:54:29Z","abstract_excerpt":"Generating interdisciplinary research ideas requires diverse domain expertise, but access to timely feedback is often limited by the availability of experts. In this paper, we introduce PersonaFlow, a novel system designed to provide multiple perspectives by using LLMs to simulate domain-specific experts. Our user studies showed that the new design 1) increased the perceived relevance and creativity of ideated research directions, and 2) promoted users' critical thinking activities (e.g., interpretation, analysis, evaluation, inference, and self-regulation), without increasing their perceived "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12538","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/2409.12538/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":"2409.12538","created_at":"2026-07-05T11:34:00.081028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12538v2","created_at":"2026-07-05T11:34:00.081028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12538","created_at":"2026-07-05T11:34:00.081028+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNR3556X62FP","created_at":"2026-07-05T11:34:00.081028+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNR3556X62FPK5QH","created_at":"2026-07-05T11:34:00.081028+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNR3556X","created_at":"2026-07-05T11:34:00.081028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16345","citing_title":"Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15736","citing_title":"IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10545","citing_title":"Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4","json":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4.json","graph_json":"https://pith.science/api/pith-number/QNR3556X62FPK5QHXWL2JMNIM4/graph.json","events_json":"https://pith.science/api/pith-number/QNR3556X62FPK5QHXWL2JMNIM4/events.json","paper":"https://pith.science/paper/QNR3556X"},"agent_actions":{"view_html":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4","download_json":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4.json","view_paper":"https://pith.science/paper/QNR3556X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12538&json=true","fetch_graph":"https://pith.science/api/pith-number/QNR3556X62FPK5QHXWL2JMNIM4/graph.json","fetch_events":"https://pith.science/api/pith-number/QNR3556X62FPK5QHXWL2JMNIM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4/action/storage_attestation","attest_author":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4/action/author_attestation","sign_citation":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4/action/citation_signature","submit_replication":"https://pith.science/pith/QNR3556X62FPK5QHXWL2JMNIM4/action/replication_record"}},"created_at":"2026-07-05T11:34:00.081028+00:00","updated_at":"2026-07-05T11:34:00.081028+00:00"}