{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G4EC62577Z2SSLIANUTJZMHRGG","short_pith_number":"pith:G4EC6257","schema_version":"1.0","canonical_sha256":"37082f6bbffe75292d006d269cb0f1319c27b56407312c97cdf27c9874604571","source":{"kind":"arxiv","id":"2403.13679","version":4},"attestation_state":"computed","paper":{"title":"SocialBench: Sociality Evaluation of Role-Playing Conversational Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Fei Huang, Hehong Chen, Hongzhan Chen, Jingren Zhou, Ji Zhang, Ming Yan, Weizhou Shen, Wenshen Xu, Xiaojun Quan, Xing Gao","submitted_at":"2024-03-20T15:38:36Z","abstract_excerpt":"Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge, and stylistic attributes of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing conversational agents at both individual and group "},"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":"2403.13679","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T15:38:36Z","cross_cats_sorted":[],"title_canon_sha256":"d9c2b3d26c9b0292cb3be6f5866dd4995bf961c32c80aac585c1b3b561067079","abstract_canon_sha256":"aac7284d5e63d8f93ee9d74b87880ced3534a9b8e4f32a827e6fb676f7af4436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:49.636000Z","signature_b64":"eThO8sluvGuv0/+4v3i+L/O6eFebiIngWZHk9ozXRa7SifR9VCAeFifkCi4eZ6GHI2Ja/O38NVjfxL8TAiZgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37082f6bbffe75292d006d269cb0f1319c27b56407312c97cdf27c9874604571","last_reissued_at":"2026-07-05T08:51:49.635432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:49.635432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SocialBench: Sociality Evaluation of Role-Playing Conversational Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Fei Huang, Hehong Chen, Hongzhan Chen, Jingren Zhou, Ji Zhang, Ming Yan, Weizhou Shen, Wenshen Xu, Xiaojun Quan, Xing Gao","submitted_at":"2024-03-20T15:38:36Z","abstract_excerpt":"Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge, and stylistic attributes of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing conversational agents at both individual and group "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13679","kind":"arxiv","version":4},"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/2403.13679/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":"2403.13679","created_at":"2026-07-05T08:51:49.635493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13679v4","created_at":"2026-07-05T08:51:49.635493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13679","created_at":"2026-07-05T08:51:49.635493+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4EC62577Z2S","created_at":"2026-07-05T08:51:49.635493+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4EC62577Z2SSLIA","created_at":"2026-07-05T08:51:49.635493+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4EC6257","created_at":"2026-07-05T08:51:49.635493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.09049","citing_title":"Inertia in Moral and Value Judgments of Large Language Models","ref_index":13,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":156,"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":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG","json":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG.json","graph_json":"https://pith.science/api/pith-number/G4EC62577Z2SSLIANUTJZMHRGG/graph.json","events_json":"https://pith.science/api/pith-number/G4EC62577Z2SSLIANUTJZMHRGG/events.json","paper":"https://pith.science/paper/G4EC6257"},"agent_actions":{"view_html":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG","download_json":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG.json","view_paper":"https://pith.science/paper/G4EC6257","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13679&json=true","fetch_graph":"https://pith.science/api/pith-number/G4EC62577Z2SSLIANUTJZMHRGG/graph.json","fetch_events":"https://pith.science/api/pith-number/G4EC62577Z2SSLIANUTJZMHRGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG/action/storage_attestation","attest_author":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG/action/author_attestation","sign_citation":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG/action/citation_signature","submit_replication":"https://pith.science/pith/G4EC62577Z2SSLIANUTJZMHRGG/action/replication_record"}},"created_at":"2026-07-05T08:51:49.635493+00:00","updated_at":"2026-07-05T08:51:49.635493+00:00"}