{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APH5LUAWAC5DMP2LYK6GQ5IXLC","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":"9276611281930d50df93b57750ede4601c44ab271ef94e11f30d9f5f74198cba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T16:49:40Z","title_canon_sha256":"df319d546c63dac854dcc29cd0eae763ce4762e18e93f6a8bed78dc1890c214f"},"schema_version":"1.0","source":{"id":"2308.10855","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10855","created_at":"2026-07-05T07:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10855v3","created_at":"2026-07-05T07:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10855","created_at":"2026-07-05T07:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"APH5LUAWAC5D","created_at":"2026-07-05T07:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"APH5LUAWAC5DMP2L","created_at":"2026-07-05T07:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"APH5LUAW","created_at":"2026-07-05T07:56:51Z"}],"graph_snapshots":[{"event_id":"sha256:c521cbf98841e96771b4ecc010bb6a7fdbb92c238792874299649150d0c81821","target":"graph","created_at":"2026-07-05T07:56:51Z","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/2308.10855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the continuous evolution and refinement of LLMs, they are endowed with impressive logical reasoning or vertical thinking capabilities. But can they think out of the box? Do they possess proficient lateral thinking abilities? Following the setup of Lateral Thinking Puzzles, we propose a novel evaluation benchmark, LatEval, which assesses the model's lateral thinking within an interactive framework. In our benchmark, we challenge LLMs with 2 aspects: the quality of questions posed by the model and the model's capability to integrate information for problem-solving. We find that nearly all L","authors_text":"Hai-Tao Zheng, Mengzuo Huang, Shirong Ma, Shulin Huang, Weidong Zhang, Wuhe Zou, Yinghui Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T16:49:40Z","title":"LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10855","kind":"arxiv","version":3},"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:d24cd801bb983001995f2309b1d704e466b3f9f4ee96b95a847cfad762f4a09c","target":"record","created_at":"2026-07-05T07:56:51Z","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":"9276611281930d50df93b57750ede4601c44ab271ef94e11f30d9f5f74198cba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-21T16:49:40Z","title_canon_sha256":"df319d546c63dac854dcc29cd0eae763ce4762e18e93f6a8bed78dc1890c214f"},"schema_version":"1.0","source":{"id":"2308.10855","kind":"arxiv","version":3}},"canonical_sha256":"03cfd5d01600ba363f4bc2bc687517589af8326589b42c490790cf7907450755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03cfd5d01600ba363f4bc2bc687517589af8326589b42c490790cf7907450755","first_computed_at":"2026-07-05T07:56:51.479987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:51.479987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDjhwDzEIE450tvnR0fSrNg6/qOvyH6ENnN0nx6vdG6al6F7/i5QMZnBeMF9Am/f2CyyoC+zSoRq8I+UJEc+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:51.480443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10855","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d24cd801bb983001995f2309b1d704e466b3f9f4ee96b95a847cfad762f4a09c","sha256:c521cbf98841e96771b4ecc010bb6a7fdbb92c238792874299649150d0c81821"],"state_sha256":"5591079269de0e480791cf2baf2596c8237079cebd5456c212d9ef567cd641c2"}