{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GGCSNKYDINHCFW3SCTN3FSAETC","short_pith_number":"pith:GGCSNKYD","schema_version":"1.0","canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","source":{"kind":"arxiv","id":"2407.18416","version":5},"attestation_state":"computed","paper":{"title":"PersonaGym: Evaluating Persona Agents and LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameet Deshpande, Ashwin Kalyan, Henry Peng Zou, Karthik Narasimhan, Shreyas Chaudhari, Tanmay Rajpurohit, Vinay Samuel, Vishvak Murahari, Yue Zhou","submitted_at":"2024-07-25T22:24:45Z","abstract_excerpt":"Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and healthcare. However, evaluating how faithfully these agents adhere to their personas remains a significant challenge, particularly in free-form settings that demand consistency across diverse, persona-relevant environments. We introduce PersonaGym, the first dynamic evaluation framework for persona agents, and PersonaScore, a human-aligned automatic metric grounded in decision theory that enables comprehensive large-s"},"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":"2407.18416","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T22:24:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ad657cc9bae754ba57b59ca87997f16566739927dd002eb347d72419d1068d1e","abstract_canon_sha256":"36396f13013f81cffc8aa31a3ddc2090b22ea16c9196f2a72dd698cfd9f5240e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:09.411712Z","signature_b64":"iyrk7L4OqQfbAl3SHFhyv/EcepPX9M4pm/4RLuYu+U2Hn7ZtWWxqm0DyYUORvlC1TlVYFmRiTjD+eVGtgKtKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"318526ab03434e22db7214dbb2c80498add578365cc7ee0a17e5b9771f65a878","last_reissued_at":"2026-07-05T12:05:09.411131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:09.411131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersonaGym: Evaluating Persona Agents and LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ameet Deshpande, Ashwin Kalyan, Henry Peng Zou, Karthik Narasimhan, Shreyas Chaudhari, Tanmay Rajpurohit, Vinay Samuel, Vishvak Murahari, Yue Zhou","submitted_at":"2024-07-25T22:24:45Z","abstract_excerpt":"Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and healthcare. However, evaluating how faithfully these agents adhere to their personas remains a significant challenge, particularly in free-form settings that demand consistency across diverse, persona-relevant environments. We introduce PersonaGym, the first dynamic evaluation framework for persona agents, and PersonaScore, a human-aligned automatic metric grounded in decision theory that enables comprehensive large-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18416","kind":"arxiv","version":5},"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/2407.18416/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":"2407.18416","created_at":"2026-07-05T12:05:09.411192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18416v5","created_at":"2026-07-05T12:05:09.411192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18416","created_at":"2026-07-05T12:05:09.411192+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGCSNKYDINHC","created_at":"2026-07-05T12:05:09.411192+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGCSNKYDINHCFW3S","created_at":"2026-07-05T12:05:09.411192+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGCSNKYD","created_at":"2026-07-05T12:05:09.411192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13608","citing_title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01552","citing_title":"RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18256","citing_title":"Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25601","citing_title":"Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28969","citing_title":"Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15671","citing_title":"StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20506","citing_title":"Reinforcing Human Behavior Simulation via Verbal Feedback","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09788","citing_title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08565","citing_title":"Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09756","citing_title":"MOA: Multi-Objective Alignment for Role-Playing Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15671","citing_title":"StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09682","citing_title":"Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26243","citing_title":"StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC","json":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC.json","graph_json":"https://pith.science/api/pith-number/GGCSNKYDINHCFW3SCTN3FSAETC/graph.json","events_json":"https://pith.science/api/pith-number/GGCSNKYDINHCFW3SCTN3FSAETC/events.json","paper":"https://pith.science/paper/GGCSNKYD"},"agent_actions":{"view_html":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC","download_json":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC.json","view_paper":"https://pith.science/paper/GGCSNKYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18416&json=true","fetch_graph":"https://pith.science/api/pith-number/GGCSNKYDINHCFW3SCTN3FSAETC/graph.json","fetch_events":"https://pith.science/api/pith-number/GGCSNKYDINHCFW3SCTN3FSAETC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/action/storage_attestation","attest_author":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/action/author_attestation","sign_citation":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/action/citation_signature","submit_replication":"https://pith.science/pith/GGCSNKYDINHCFW3SCTN3FSAETC/action/replication_record"}},"created_at":"2026-07-05T12:05:09.411192+00:00","updated_at":"2026-07-05T12:05:09.411192+00:00"}