{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HTSMXJO3U5L4FKJSOZG4KYK67S","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":"a7d7bef3c8dd53a04ef383f97aa1c1ff7f465a414d662d2bc07c17356a3bcdef","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T01:59:03Z","title_canon_sha256":"203ac4dc839fe9e5e6badc030de03e92aa4ab3d75acaa27e41d92eeba08fb1a4"},"schema_version":"1.0","source":{"id":"2412.11373","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11373","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11373v2","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11373","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"HTSMXJO3U5L4","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"HTSMXJO3U5L4FKJS","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"HTSMXJO3","created_at":"2026-07-05T10:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:f751be3c06ed5a571014b03032ce06120f3e4ac06360be187079d43ce2765552","target":"graph","created_at":"2026-07-05T10:52:17Z","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/2412.11373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose the use of the popular word-based board game Codenames as a suitable benchmark for evaluating the reasoning capabilities of Large Language Models (LLMs). Codenames presents a highly interesting challenge for achieving successful AI performance, requiring both a sophisticated understanding of language, theory of mind, and epistemic reasoning capabilities. Prior attempts to develop agents for Codenames have largely relied on word embedding techniques, which have a limited vocabulary range and perform poorly when paired with differing approaches. LLMs have demonstrated e","authors_text":"Beno\\^it Ronval, Matthew Sidji, Matthew Stephenson","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T01:59:03Z","title":"Codenames as a Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11373","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":"sha256:243639a062a06efe121500950a51489686fab777ab3181ee64cc5b7d1c089959","target":"record","created_at":"2026-07-05T10:52:17Z","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":"a7d7bef3c8dd53a04ef383f97aa1c1ff7f465a414d662d2bc07c17356a3bcdef","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T01:59:03Z","title_canon_sha256":"203ac4dc839fe9e5e6badc030de03e92aa4ab3d75acaa27e41d92eeba08fb1a4"},"schema_version":"1.0","source":{"id":"2412.11373","kind":"arxiv","version":2}},"canonical_sha256":"3ce4cba5dba757c2a932764dc5615efc841e97d37813dfa44fb547396b9c5b7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ce4cba5dba757c2a932764dc5615efc841e97d37813dfa44fb547396b9c5b7f","first_computed_at":"2026-07-05T10:52:17.110733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:17.110733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JFLOgHo7PpiwF4yxyuzciFhV+fkxxhB4+ZtpyNPdJNZf2+0bAiKdeMqKo4SEYHEhoTobB7zmsrTRtwx89zGlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:17.111297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11373","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243639a062a06efe121500950a51489686fab777ab3181ee64cc5b7d1c089959","sha256:f751be3c06ed5a571014b03032ce06120f3e4ac06360be187079d43ce2765552"],"state_sha256":"d062862873b8811c643f690e9548952033d6d8df8a6150aab3df536bcd83f2b7"}