{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J5PHPNKSFZNJDN4NEFHWKAKQPW","short_pith_number":"pith:J5PHPNKS","schema_version":"1.0","canonical_sha256":"4f5e77b5522e5a91b78d214f6501507dababb495b467442a4b4e6ea880aebd7a","source":{"kind":"arxiv","id":"2310.11667","version":2},"attestation_state":"computed","paper":{"title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Fried, Graham Neubig, Haofei Yu, Hao Zhu, Leena Mathur, Louis-Philippe Morency, Maarten Sap, Ruohong Zhang, Xuhui Zhou, Yonatan Bisk, Zhengyang Qi","submitted_at":"2023-10-18T02:27:01Z","abstract_excerpt":"Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans withi"},"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":"2310.11667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T02:27:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"522754b63d721ae0ccf3dd0a86a9e3e2cd7c4695ea6e32a8c8ed99586e6050f7","abstract_canon_sha256":"4eca82a265b931e3b2d3e1f4e9d11e0d9b1fa8bfaf6f425eab45d3fe532d8589"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:35.723193Z","signature_b64":"3dqXfRsT41PAXcBLYNgpdroP2AFo86oF/SHwdDiD2NWkM7SwOHkkcHUH87gZhFzmxFUzGBNIPy8bg5ePOaSbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5e77b5522e5a91b78d214f6501507dababb495b467442a4b4e6ea880aebd7a","last_reissued_at":"2026-07-05T07:59:35.722695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:35.722695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Fried, Graham Neubig, Haofei Yu, Hao Zhu, Leena Mathur, Louis-Philippe Morency, Maarten Sap, Ruohong Zhang, Xuhui Zhou, Yonatan Bisk, Zhengyang Qi","submitted_at":"2023-10-18T02:27:01Z","abstract_excerpt":"Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans withi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11667","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/2310.11667/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":"2310.11667","created_at":"2026-07-05T07:59:35.722755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11667v2","created_at":"2026-07-05T07:59:35.722755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11667","created_at":"2026-07-05T07:59:35.722755+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5PHPNKSFZNJ","created_at":"2026-07-05T07:59:35.722755+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5PHPNKSFZNJDN4N","created_at":"2026-07-05T07:59:35.722755+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5PHPNKS","created_at":"2026-07-05T07:59:35.722755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"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":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21315","citing_title":"Social World Model for Lifelong Social Intelligence","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19904","citing_title":"Toward Temporal Realism in City-Scale Crisis Response Simulation using LLM Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31916","citing_title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24375","citing_title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25511","citing_title":"CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27766","citing_title":"Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29512","citing_title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22643","citing_title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2502.08691","citing_title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22643","citing_title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10574","citing_title":"LLM Jaggedness Unlocks Scientific Creativity","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17694","citing_title":"Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17079","citing_title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17694","citing_title":"Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05425","citing_title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12626","citing_title":"DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11206","citing_title":"Evalet: Evaluating Large Language Models through Functional Fragmentation","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08104","citing_title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12512","citing_title":"Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08334","citing_title":"CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10574","citing_title":"LLM Jaggedness Unlocks Scientific Creativity","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW","json":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW.json","graph_json":"https://pith.science/api/pith-number/J5PHPNKSFZNJDN4NEFHWKAKQPW/graph.json","events_json":"https://pith.science/api/pith-number/J5PHPNKSFZNJDN4NEFHWKAKQPW/events.json","paper":"https://pith.science/paper/J5PHPNKS"},"agent_actions":{"view_html":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW","download_json":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW.json","view_paper":"https://pith.science/paper/J5PHPNKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11667&json=true","fetch_graph":"https://pith.science/api/pith-number/J5PHPNKSFZNJDN4NEFHWKAKQPW/graph.json","fetch_events":"https://pith.science/api/pith-number/J5PHPNKSFZNJDN4NEFHWKAKQPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW/action/storage_attestation","attest_author":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW/action/author_attestation","sign_citation":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW/action/citation_signature","submit_replication":"https://pith.science/pith/J5PHPNKSFZNJDN4NEFHWKAKQPW/action/replication_record"}},"created_at":"2026-07-05T07:59:35.722755+00:00","updated_at":"2026-07-05T07:59:35.722755+00:00"}