{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UP4SQRER2WGQOFC5OMURQCCVGV","short_pith_number":"pith:UP4SQRER","canonical_record":{"source":{"id":"2310.20499","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T14:37:42Z","cross_cats_sorted":[],"title_canon_sha256":"b5e761bc3fdfcf22c14df21e4fa387b21c73ddfdc45322a673aa5c44dca4b9cb","abstract_canon_sha256":"54afca8dced9aa48189bfd52530484a48fb8803f9b9b116c2013cae9e8d8e9f0"},"schema_version":"1.0"},"canonical_sha256":"a3f9284491d58d07145d732918085535563deb8c4a3cd3f259b95854acfaaa1e","source":{"kind":"arxiv","id":"2310.20499","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UP4SQRER2WGQOFC5OMURQCCVGV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.20499","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T14:37:42Z","cross_cats_sorted":[],"title_canon_sha256":"b5e761bc3fdfcf22c14df21e4fa387b21c73ddfdc45322a673aa5c44dca4b9cb","abstract_canon_sha256":"54afca8dced9aa48189bfd52530484a48fb8803f9b9b116c2013cae9e8d8e9f0"},"schema_version":"1.0"},"canonical_sha256":"a3f9284491d58d07145d732918085535563deb8c4a3cd3f259b95854acfaaa1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:04.295861Z","signature_b64":"3ivzHEs2fMI8C6P889026oOXjR4BMnS9B+Yi42xtMsAXIjF2lod9su3WP7au2SR4XLlx5yOi9eRzO1YCnuNmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f9284491d58d07145d732918085535563deb8c4a3cd3f259b95854acfaaa1e","last_reissued_at":"2026-07-05T07:09:04.295393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:04.295393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.20499","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"auvYJ9rIulsNbcxCZtcH2bcXYfKNxtREuIuU0x35ebqsx7mHyb+rSUQXQISp8oWda62QqRlMHj6sji26IW3cCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:38:17.624396Z"},"content_sha256":"e3545f9769a3bead77d00c1eadf232d26c9f198f8bbbddf93985d2f6e7b3ddcf","schema_version":"1.0","event_id":"sha256:e3545f9769a3bead77d00c1eadf232d26c9f198f8bbbddf93985d2f6e7b3ddcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UP4SQRER2WGQOFC5OMURQCCVGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jen-tse Huang, Rui Wang, Shuming Shi, Tian Liang, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Yujiu Yang, Zhaopeng Tu, Zhiwei He","submitted_at":"2023-10-31T14:37:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20499","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/2310.20499/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":"2026-07-05T07:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYrUvpQfcqj/kyc4F3TTes5Q2PZTtlXbdNrJcfbqxwQ+hzoeCZTJFM+dC177JycknIkbhd7KAqUCvUXo+D//CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:38:17.624886Z"},"content_sha256":"a096d49e277dc1ed12232f53b8f58112fbe1e80ab0a3c0a182e66e287070a341","schema_version":"1.0","event_id":"sha256:a096d49e277dc1ed12232f53b8f58112fbe1e80ab0a3c0a182e66e287070a341"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UP4SQRER2WGQOFC5OMURQCCVGV/bundle.json","state_url":"https://pith.science/pith/UP4SQRER2WGQOFC5OMURQCCVGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UP4SQRER2WGQOFC5OMURQCCVGV/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":"2026-08-09T06:38:17Z","links":{"resolver":"https://pith.science/pith/UP4SQRER2WGQOFC5OMURQCCVGV","bundle":"https://pith.science/pith/UP4SQRER2WGQOFC5OMURQCCVGV/bundle.json","state":"https://pith.science/pith/UP4SQRER2WGQOFC5OMURQCCVGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UP4SQRER2WGQOFC5OMURQCCVGV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PthbV2Pi2iTl3XToCJCCjKDmLYCuxj1lT0/gLbdMLLd2xjmepCScQPU3wAuVtTd7eJdWytowSoxFO9iwtLdLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:38:17.628547Z","bundle_sha256":"669567f3168a0282b25210bf3e84d571105343f449e1db8dd233c85c3f8b7d72"}}