{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TDVNAJLARAHOAQNDQGFIATVNUB","short_pith_number":"pith:TDVNAJLA","schema_version":"1.0","canonical_sha256":"98ead02560880ee041a3818a804eada043036d4e7e396ac3a3ec529814ea216e","source":{"kind":"arxiv","id":"2410.19346","version":2},"attestation_state":"computed","paper":{"title":"AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Haoyu Kuang, Jiayu Lin, Jingcong Liang, Lei Chen, Rong Ye, Shiyue Yang, Xiawei Liu, Xinnong Zhang, Xinyi Mou, Xuanjing Huang, Zhongyu Wei","submitted_at":"2024-10-25T07:04:16Z","abstract_excerpt":"Large language models (LLMs) are increasingly leveraged to empower autonomous agents to simulate human beings in various fields of behavioral research. However, evaluating their capacity to navigate complex social interactions remains a challenge. Previous studies face limitations due to insufficient scenario diversity, complexity, and a single-perspective focus. To this end, we introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios"},"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":"2410.19346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T07:04:16Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"7527c4048b273540182aed9a4cef9804037b1beb9030cf163f68aa0392d38f72","abstract_canon_sha256":"76b81bb0a77c9d0582683131c1c5183bb3b239ef7af76ccac6e79584de15e431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:28.524696Z","signature_b64":"rTJ6s8CZP2xcJV7mEckayr5+6CGBMnYjxasWgHtL2ptZy2Z/SFldgobZyudJjXgrpU6jhyikSVt2sseeW7njAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ead02560880ee041a3818a804eada043036d4e7e396ac3a3ec529814ea216e","last_reissued_at":"2026-07-05T09:39:28.524177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:28.524177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Haoyu Kuang, Jiayu Lin, Jingcong Liang, Lei Chen, Rong Ye, Shiyue Yang, Xiawei Liu, Xinnong Zhang, Xinyi Mou, Xuanjing Huang, Zhongyu Wei","submitted_at":"2024-10-25T07:04:16Z","abstract_excerpt":"Large language models (LLMs) are increasingly leveraged to empower autonomous agents to simulate human beings in various fields of behavioral research. However, evaluating their capacity to navigate complex social interactions remains a challenge. Previous studies face limitations due to insufficient scenario diversity, complexity, and a single-perspective focus. To this end, we introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19346","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/2410.19346/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":"2410.19346","created_at":"2026-07-05T09:39:28.524241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19346v2","created_at":"2026-07-05T09:39:28.524241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19346","created_at":"2026-07-05T09:39:28.524241+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDVNAJLARAHO","created_at":"2026-07-05T09:39:28.524241+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDVNAJLARAHOAQND","created_at":"2026-07-05T09:39:28.524241+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDVNAJLA","created_at":"2026-07-05T09:39:28.524241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.06322","citing_title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB","json":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB.json","graph_json":"https://pith.science/api/pith-number/TDVNAJLARAHOAQNDQGFIATVNUB/graph.json","events_json":"https://pith.science/api/pith-number/TDVNAJLARAHOAQNDQGFIATVNUB/events.json","paper":"https://pith.science/paper/TDVNAJLA"},"agent_actions":{"view_html":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB","download_json":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB.json","view_paper":"https://pith.science/paper/TDVNAJLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19346&json=true","fetch_graph":"https://pith.science/api/pith-number/TDVNAJLARAHOAQNDQGFIATVNUB/graph.json","fetch_events":"https://pith.science/api/pith-number/TDVNAJLARAHOAQNDQGFIATVNUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB/action/storage_attestation","attest_author":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB/action/author_attestation","sign_citation":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB/action/citation_signature","submit_replication":"https://pith.science/pith/TDVNAJLARAHOAQNDQGFIATVNUB/action/replication_record"}},"created_at":"2026-07-05T09:39:28.524241+00:00","updated_at":"2026-07-05T09:39:28.524241+00:00"}