{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCY5VSEKPHAMB2ZZKLG76TSB7R","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":"e73f7f4a11782be203643569cabf68e4b0811934d8b1497f8df2ca1489fa1bac","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-10T16:14:34Z","title_canon_sha256":"cddb2dfee1a3c8237fc3f7da486a8dec1fff07a2593dbb1c40cad693a7acf0f3"},"schema_version":"1.0","source":{"id":"2407.07796","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07796","created_at":"2026-07-05T08:42:39Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07796v2","created_at":"2026-07-05T08:42:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07796","created_at":"2026-07-05T08:42:39Z"},{"alias_kind":"pith_short_12","alias_value":"NCY5VSEKPHAM","created_at":"2026-07-05T08:42:39Z"},{"alias_kind":"pith_short_16","alias_value":"NCY5VSEKPHAMB2ZZ","created_at":"2026-07-05T08:42:39Z"},{"alias_kind":"pith_short_8","alias_value":"NCY5VSEK","created_at":"2026-07-05T08:42:39Z"}],"graph_snapshots":[{"event_id":"sha256:3c2edc4a36a54bf4596b7e40411051f423b7169a5a7d59ac86c15fedb1c520c2","target":"graph","created_at":"2026-07-05T08:42:39Z","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/2407.07796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel and extensible benchmark for large language models (LLMs) through grid-based games such as Tic-Tac-Toe, Connect Four, and Gomoku. The open-source game simulation code, available on GitHub, allows LLMs to compete and generates detailed data files in JSON, CSV, TXT, and PNG formats for leaderboard rankings and further analysis. We present the results of games among leading LLMs, including Claude 3.5 Sonnet and Claude 3 Sonnet by Anthropic, Gemini 1.5 Pro and Gemini 1.5 Flash by Google, GPT-4 Turbo and GPT-4o by OpenAI, and Llama3-70B by Meta. We also encourage submissions of","authors_text":"Colby Jacob Edell, Jackson Bailey Harper, Oguzhan Topsakal","cross_cats":["cs.CL","cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-10T16:14:34Z","title":"Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07796","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":"sha256:23570f86534e4643644a2571e3c400080e7fe37aeb73d74dbc9c01f25bbf1f1e","target":"record","created_at":"2026-07-05T08:42:39Z","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":"e73f7f4a11782be203643569cabf68e4b0811934d8b1497f8df2ca1489fa1bac","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-10T16:14:34Z","title_canon_sha256":"cddb2dfee1a3c8237fc3f7da486a8dec1fff07a2593dbb1c40cad693a7acf0f3"},"schema_version":"1.0","source":{"id":"2407.07796","kind":"arxiv","version":2}},"canonical_sha256":"68b1dac88a79c0c0eb3952cdff4e41fc40f05295f7a84c89d6635b388e9adf88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68b1dac88a79c0c0eb3952cdff4e41fc40f05295f7a84c89d6635b388e9adf88","first_computed_at":"2026-07-05T08:42:39.475266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:39.475266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oN9KELfTdAK6PQeqHjyBO5IoQPf8ywizLFk9bvUpV1MwifbORdC+drMiCdsqCnpbf3J3D1nktSAON5G7vRcuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:39.475726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07796","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23570f86534e4643644a2571e3c400080e7fe37aeb73d74dbc9c01f25bbf1f1e","sha256:3c2edc4a36a54bf4596b7e40411051f423b7169a5a7d59ac86c15fedb1c520c2"],"state_sha256":"cb8c317c1281c4b918170a8a1d8fe487228cc3bca8c6e29806d065e628d52f66"}