{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J5PHPNKSFZNJDN4NEFHWKAKQPW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4eca82a265b931e3b2d3e1f4e9d11e0d9b1fa8bfaf6f425eab45d3fe532d8589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T02:27:01Z","title_canon_sha256":"522754b63d721ae0ccf3dd0a86a9e3e2cd7c4695ea6e32a8c8ed99586e6050f7"},"schema_version":"1.0","source":{"id":"2310.11667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11667","created_at":"2026-07-05T07:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11667v2","created_at":"2026-07-05T07:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11667","created_at":"2026-07-05T07:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"J5PHPNKSFZNJ","created_at":"2026-07-05T07:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"J5PHPNKSFZNJDN4N","created_at":"2026-07-05T07:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"J5PHPNKS","created_at":"2026-07-05T07:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:21ceca0e66f479df227d357c000b4fb77f0262e93f5cb2959bc5b5a89813cb64","target":"graph","created_at":"2026-07-05T07:59:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.11667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T02:27:01Z","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11667","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:90cc1b80f2389a5f1f04287bdfc83725bd6c72aac88bda6fde5e2b30177cd20d","target":"record","created_at":"2026-07-05T07:59:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4eca82a265b931e3b2d3e1f4e9d11e0d9b1fa8bfaf6f425eab45d3fe532d8589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T02:27:01Z","title_canon_sha256":"522754b63d721ae0ccf3dd0a86a9e3e2cd7c4695ea6e32a8c8ed99586e6050f7"},"schema_version":"1.0","source":{"id":"2310.11667","kind":"arxiv","version":2}},"canonical_sha256":"4f5e77b5522e5a91b78d214f6501507dababb495b467442a4b4e6ea880aebd7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f5e77b5522e5a91b78d214f6501507dababb495b467442a4b4e6ea880aebd7a","first_computed_at":"2026-07-05T07:59:35.722695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:35.722695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3dqXfRsT41PAXcBLYNgpdroP2AFo86oF/SHwdDiD2NWkM7SwOHkkcHUH87gZhFzmxFUzGBNIPy8bg5ePOaSbBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:35.723193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90cc1b80f2389a5f1f04287bdfc83725bd6c72aac88bda6fde5e2b30177cd20d","sha256:21ceca0e66f479df227d357c000b4fb77f0262e93f5cb2959bc5b5a89813cb64"],"state_sha256":"f176e69ead8d0ef6226cb87feb5fa1b3baeea3f568b3abbd15f068966b247598"}