{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NARGTYWG5TMLWJNVVMVJI6ALMF","short_pith_number":"pith:NARGTYWG","canonical_record":{"source":{"id":"2505.23713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"8a25f11f3e0f0d200cbbc30f416976f4279007e1c2958f3e24f18d81764f78f7","abstract_canon_sha256":"91687e65998b71e9bc05a51bbe19e1f596e2b3b5968e75ef7de3de6876f1fe81"},"schema_version":"1.0"},"canonical_sha256":"682269e2c6ecd8bb25b5ab2a94780b616f3f22bcc44ec14a47262a97516239c5","source":{"kind":"arxiv","id":"2505.23713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23713","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23713v1","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23713","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"NARGTYWG5TML","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"NARGTYWG5TMLWJNV","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"NARGTYWG","created_at":"2026-07-05T11:12:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NARGTYWG5TMLWJNVVMVJI6ALMF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"8a25f11f3e0f0d200cbbc30f416976f4279007e1c2958f3e24f18d81764f78f7","abstract_canon_sha256":"91687e65998b71e9bc05a51bbe19e1f596e2b3b5968e75ef7de3de6876f1fe81"},"schema_version":"1.0"},"canonical_sha256":"682269e2c6ecd8bb25b5ab2a94780b616f3f22bcc44ec14a47262a97516239c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:13.217003Z","signature_b64":"BTElXFQztCXA0z3yOu479E41sdyfqZ+V/0gx53F/EXAh4FX4mnuyufenaZ8MxQVrPywcpHhvVnOH6ZlRb7j1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682269e2c6ecd8bb25b5ab2a94780b616f3f22bcc44ec14a47262a97516239c5","last_reissued_at":"2026-07-05T11:12:13.216505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:13.216505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23713","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebdqiKvgkBjRuBLpK4nXND+Ozy0uIoaF430lrpYTJuabefcLuZhYlbAp5h4W0L3JVl46wQkCyEh5lI965o/tCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:59.693264Z"},"content_sha256":"886ba1cdeb1fb8802f0b27c77d429348552f1fd56326827fc28c1bd2902be104","schema_version":"1.0","event_id":"sha256:886ba1cdeb1fb8802f0b27c77d429348552f1fd56326827fc28c1bd2902be104"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NARGTYWG5TMLWJNVVMVJI6ALMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Wang, Haomin Zhuang, Jiayi Ye, Jieyu Zhao, Lang Gao, Sixian Li, Wang Pan, Xiangliang Zhang, Xiuying Chen, Yanbo Wang, Yue Huang, Yue Zhao, Yujun Zhou, Zhaorun Chen, Zirui Song, Zixiang Xu","submitted_at":"2025-05-29T17:47:36Z","abstract_excerpt":"Large language models (LLMs) are increasingly applied to socially grounded tasks, such as online community moderation, media content analysis, and social reasoning games. Success in these contexts depends on a model's social reasoning ability - the capacity to interpret social contexts, infer others' mental states, and assess the truthfulness of presented information. However, there is currently no systematic evaluation framework that comprehensively assesses the social reasoning capabilities of LLMs. Existing efforts often oversimplify real-world scenarios and consist of tasks that are too ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23713","kind":"arxiv","version":1},"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/2505.23713/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0c3meyrqNWcUu6K/vHnblR04/gzGNRmuIZ33SM26rAYBbNPe7QNzUiA1tHh7/axQhA1Kr1ltrKHhGa3DZulCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:59.694146Z"},"content_sha256":"3728fa353daa2299dfe1553c35f1457e5245b7e0503dd076292bf34d173bc4a9","schema_version":"1.0","event_id":"sha256:3728fa353daa2299dfe1553c35f1457e5245b7e0503dd076292bf34d173bc4a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/bundle.json","state_url":"https://pith.science/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T22:41:59Z","links":{"resolver":"https://pith.science/pith/NARGTYWG5TMLWJNVVMVJI6ALMF","bundle":"https://pith.science/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/bundle.json","state":"https://pith.science/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NARGTYWG5TMLWJNVVMVJI6ALMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NARGTYWG5TMLWJNVVMVJI6ALMF","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":"91687e65998b71e9bc05a51bbe19e1f596e2b3b5968e75ef7de3de6876f1fe81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:47:36Z","title_canon_sha256":"8a25f11f3e0f0d200cbbc30f416976f4279007e1c2958f3e24f18d81764f78f7"},"schema_version":"1.0","source":{"id":"2505.23713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23713","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23713v1","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23713","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"NARGTYWG5TML","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"NARGTYWG5TMLWJNV","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"NARGTYWG","created_at":"2026-07-05T11:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:3728fa353daa2299dfe1553c35f1457e5245b7e0503dd076292bf34d173bc4a9","target":"graph","created_at":"2026-07-05T11:12:13Z","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/2505.23713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly applied to socially grounded tasks, such as online community moderation, media content analysis, and social reasoning games. Success in these contexts depends on a model's social reasoning ability - the capacity to interpret social contexts, infer others' mental states, and assess the truthfulness of presented information. However, there is currently no systematic evaluation framework that comprehensively assesses the social reasoning capabilities of LLMs. Existing efforts often oversimplify real-world scenarios and consist of tasks that are too ba","authors_text":"Chenxi Wang, Haomin Zhuang, Jiayi Ye, Jieyu Zhao, Lang Gao, Sixian Li, Wang Pan, Xiangliang Zhang, Xiuying Chen, Yanbo Wang, Yue Huang, Yue Zhao, Yujun Zhou, Zhaorun Chen, Zirui Song, Zixiang Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:47:36Z","title":"SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23713","kind":"arxiv","version":1},"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":"sha256:886ba1cdeb1fb8802f0b27c77d429348552f1fd56326827fc28c1bd2902be104","target":"record","created_at":"2026-07-05T11:12:13Z","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":"91687e65998b71e9bc05a51bbe19e1f596e2b3b5968e75ef7de3de6876f1fe81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T17:47:36Z","title_canon_sha256":"8a25f11f3e0f0d200cbbc30f416976f4279007e1c2958f3e24f18d81764f78f7"},"schema_version":"1.0","source":{"id":"2505.23713","kind":"arxiv","version":1}},"canonical_sha256":"682269e2c6ecd8bb25b5ab2a94780b616f3f22bcc44ec14a47262a97516239c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"682269e2c6ecd8bb25b5ab2a94780b616f3f22bcc44ec14a47262a97516239c5","first_computed_at":"2026-07-05T11:12:13.216505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:13.216505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BTElXFQztCXA0z3yOu479E41sdyfqZ+V/0gx53F/EXAh4FX4mnuyufenaZ8MxQVrPywcpHhvVnOH6ZlRb7j1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:13.217003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:886ba1cdeb1fb8802f0b27c77d429348552f1fd56326827fc28c1bd2902be104","sha256:3728fa353daa2299dfe1553c35f1457e5245b7e0503dd076292bf34d173bc4a9"],"state_sha256":"7c6271468c5193d532c13f82dda4c10f2c99f369d5feb4f15eaa3d38cb2804e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkN+oe6yHjMZONxcQof9X8WRibKkkS9br3e1uQLT5fn0wVPRbMkfBAvsk43l0inflRDXBRQsdNjJIzdGjrgUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:41:59.700673Z","bundle_sha256":"e2e66959e23ebdaa200a67c0b95ce7e4ac260de5a6e06bb59272e7780c721677"}}