{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UP4SQRER2WGQOFC5OMURQCCVGV","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":"54afca8dced9aa48189bfd52530484a48fb8803f9b9b116c2013cae9e8d8e9f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T14:37:42Z","title_canon_sha256":"b5e761bc3fdfcf22c14df21e4fa387b21c73ddfdc45322a673aa5c44dca4b9cb"},"schema_version":"1.0","source":{"id":"2310.20499","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20499","created_at":"2026-07-05T07:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20499v2","created_at":"2026-07-05T07:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20499","created_at":"2026-07-05T07:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"UP4SQRER2WGQ","created_at":"2026-07-05T07:09:04Z"},{"alias_kind":"pith_short_16","alias_value":"UP4SQRER2WGQOFC5","created_at":"2026-07-05T07:09:04Z"},{"alias_kind":"pith_short_8","alias_value":"UP4SQRER","created_at":"2026-07-05T07:09:04Z"}],"graph_snapshots":[{"event_id":"sha256:a096d49e277dc1ed12232f53b8f58112fbe1e80ab0a3c0a182e66e287070a341","target":"graph","created_at":"2026-07-05T07:09:04Z","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/2310.20499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The automatic evaluation of LLM-based agent intelligence is critical in developing advanced LLM-based agents. Although considerable effort has been devoted to developing human-annotated evaluation datasets, such as AlpacaEval, existing techniques are costly, time-consuming, and lack adaptability. In this paper, inspired by the popular language game ``Who is Spy'', we propose to use the word guessing game to assess the intelligence performance of LLMs. Given a word, the LLM is asked to describe the word and determine its identity (spy or not) based on its and other players' descriptions. Ideall","authors_text":"Jen-tse Huang, Rui Wang, Shuming Shi, Tian Liang, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Yujiu Yang, Zhaopeng Tu, Zhiwei He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T14:37:42Z","title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20499","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:e3545f9769a3bead77d00c1eadf232d26c9f198f8bbbddf93985d2f6e7b3ddcf","target":"record","created_at":"2026-07-05T07:09:04Z","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":"54afca8dced9aa48189bfd52530484a48fb8803f9b9b116c2013cae9e8d8e9f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T14:37:42Z","title_canon_sha256":"b5e761bc3fdfcf22c14df21e4fa387b21c73ddfdc45322a673aa5c44dca4b9cb"},"schema_version":"1.0","source":{"id":"2310.20499","kind":"arxiv","version":2}},"canonical_sha256":"a3f9284491d58d07145d732918085535563deb8c4a3cd3f259b95854acfaaa1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3f9284491d58d07145d732918085535563deb8c4a3cd3f259b95854acfaaa1e","first_computed_at":"2026-07-05T07:09:04.295393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:04.295393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ivzHEs2fMI8C6P889026oOXjR4BMnS9B+Yi42xtMsAXIjF2lod9su3WP7au2SR4XLlx5yOi9eRzO1YCnuNmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:04.295861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20499","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3545f9769a3bead77d00c1eadf232d26c9f198f8bbbddf93985d2f6e7b3ddcf","sha256:a096d49e277dc1ed12232f53b8f58112fbe1e80ab0a3c0a182e66e287070a341"],"state_sha256":"d9167e4b19809ce8b213b224832fa5591480b8c671d6d945e1f8541fd752894b"}