{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FCGSPGMVQDPEEKFCBB3EV5BSFF","short_pith_number":"pith:FCGSPGMV","schema_version":"1.0","canonical_sha256":"288d27999580de4228a208764af43229576536e589a3e7c8819bdfc80780c840","source":{"kind":"arxiv","id":"2401.01275","version":2},"attestation_state":"computed","paper":{"title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Quan Tu, Rui Yan, Shilong Fan, Zihang Tian","submitted_at":"2024-01-02T16:20:40Z","abstract_excerpt":"Recently, the advent of large language models (LLMs) has revolutionized generative agents. Among them, Role-Playing Conversational Agents (RPCAs) attract considerable attention due to their ability to emotionally engage users. However, the absence of a comprehensive benchmark impedes progress in this field. To bridge this gap, we introduce CharacterEval, a Chinese benchmark for comprehensive RPCA assessment, complemented by a tailored high-quality dataset. The dataset comprises 1,785 multi-turn role-playing dialogues, encompassing 23,020 examples and featuring 77 characters derived from Chines"},"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":"2401.01275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T16:20:40Z","cross_cats_sorted":[],"title_canon_sha256":"9709c15bc5d8c8f815a2d0b5041f341f78c9897f2fd346c6706e8d7d8ad185a2","abstract_canon_sha256":"a4e70c2ca1b2952fe33289e5d96731a0c7c2c24dd8edce0a5e5c4695b565aa74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:36.539578Z","signature_b64":"VF9HpTphsuXbQJ+nWqZ+EI9Hh1H6RigNqX12Cicx2+U3cE57vbxjw7m9pa8XMSNeh6+uT3PyQ5uE1aqLKBeBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288d27999580de4228a208764af43229576536e589a3e7c8819bdfc80780c840","last_reissued_at":"2026-07-05T07:31:36.539081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:36.539081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Quan Tu, Rui Yan, Shilong Fan, Zihang Tian","submitted_at":"2024-01-02T16:20:40Z","abstract_excerpt":"Recently, the advent of large language models (LLMs) has revolutionized generative agents. Among them, Role-Playing Conversational Agents (RPCAs) attract considerable attention due to their ability to emotionally engage users. However, the absence of a comprehensive benchmark impedes progress in this field. To bridge this gap, we introduce CharacterEval, a Chinese benchmark for comprehensive RPCA assessment, complemented by a tailored high-quality dataset. The dataset comprises 1,785 multi-turn role-playing dialogues, encompassing 23,020 examples and featuring 77 characters derived from Chines"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01275","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/2401.01275/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":"2401.01275","created_at":"2026-07-05T07:31:36.539140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01275v2","created_at":"2026-07-05T07:31:36.539140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01275","created_at":"2026-07-05T07:31:36.539140+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCGSPGMVQDPE","created_at":"2026-07-05T07:31:36.539140+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCGSPGMVQDPEEKFC","created_at":"2026-07-05T07:31:36.539140+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCGSPGMV","created_at":"2026-07-05T07:31:36.539140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06157","citing_title":"LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17044","citing_title":"PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23435","citing_title":"AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17270","citing_title":"Understanding Generalization in Role-Playing Models via Information Theory","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01986","citing_title":"12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13804","citing_title":"Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF","json":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF.json","graph_json":"https://pith.science/api/pith-number/FCGSPGMVQDPEEKFCBB3EV5BSFF/graph.json","events_json":"https://pith.science/api/pith-number/FCGSPGMVQDPEEKFCBB3EV5BSFF/events.json","paper":"https://pith.science/paper/FCGSPGMV"},"agent_actions":{"view_html":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF","download_json":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF.json","view_paper":"https://pith.science/paper/FCGSPGMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01275&json=true","fetch_graph":"https://pith.science/api/pith-number/FCGSPGMVQDPEEKFCBB3EV5BSFF/graph.json","fetch_events":"https://pith.science/api/pith-number/FCGSPGMVQDPEEKFCBB3EV5BSFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF/action/storage_attestation","attest_author":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF/action/author_attestation","sign_citation":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF/action/citation_signature","submit_replication":"https://pith.science/pith/FCGSPGMVQDPEEKFCBB3EV5BSFF/action/replication_record"}},"created_at":"2026-07-05T07:31:36.539140+00:00","updated_at":"2026-07-05T07:31:36.539140+00:00"}