{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6OYB4UMRTRYY45WPNDTC2V5HER","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":"648fb7921d9ddde455bdccb6fc8e6c68dd351df8214f90315ea40a6cc3656a8f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T01:23:50Z","title_canon_sha256":"a8586db0de8b146da5405fb30cb4d868c36d4c8a65d9a3ea59eaf7b179703c2c"},"schema_version":"1.0","source":{"id":"2504.12562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12562","created_at":"2026-07-05T10:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12562v1","created_at":"2026-07-05T10:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12562","created_at":"2026-07-05T10:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"6OYB4UMRTRYY","created_at":"2026-07-05T10:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"6OYB4UMRTRYY45WP","created_at":"2026-07-05T10:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"6OYB4UMR","created_at":"2026-07-05T10:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:8e360732a399a8d9a0b13dce4c5d534006ef004dde30ef342b00d35bcc11a53c","target":"graph","created_at":"2026-07-05T10:50:18Z","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/2504.12562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the capabilities of Large Language Models (LLMs) has traditionally relied on static benchmark datasets, human assessments, or model-based evaluations - methods that often suffer from overfitting, high costs, and biases. ZeroSumEval is a novel competition-based evaluation protocol that leverages zero-sum games to assess LLMs with dynamic benchmarks that resist saturation. ZeroSumEval encompasses a diverse suite of games, including security challenges (PyJail), classic games (Chess, Liar's Dice, Poker), knowledge tests (MathQuiz), and persuasion challenges (Gandalf, Debate). These gam","authors_text":"B\\\"ulent Yener, Haidar Khan, Hisham A. Alyahya, M Saiful Bari, Yazeed Alnumay","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T01:23:50Z","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12562","kind":"arxiv","version":1},"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":"sha256:0c989f178e9b4d435283e9fe9c4a287fde16f3d53a339227ea7314d01254c495","target":"record","created_at":"2026-07-05T10:50:18Z","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":"648fb7921d9ddde455bdccb6fc8e6c68dd351df8214f90315ea40a6cc3656a8f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T01:23:50Z","title_canon_sha256":"a8586db0de8b146da5405fb30cb4d868c36d4c8a65d9a3ea59eaf7b179703c2c"},"schema_version":"1.0","source":{"id":"2504.12562","kind":"arxiv","version":1}},"canonical_sha256":"f3b01e51919c718e76cf68e62d57a72441fc4b055ad9173d0385fd17c9b66ab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3b01e51919c718e76cf68e62d57a72441fc4b055ad9173d0385fd17c9b66ab0","first_computed_at":"2026-07-05T10:50:18.387705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:18.387705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2n8iTKsC5JtufA8+E5ejYWLSoarMrlSEriC7kT0abXZcU+5DHPE+tPSgBqiw46OzYbMKstXICa+5ObRQ5PbuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:18.388194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c989f178e9b4d435283e9fe9c4a287fde16f3d53a339227ea7314d01254c495","sha256:8e360732a399a8d9a0b13dce4c5d534006ef004dde30ef342b00d35bcc11a53c"],"state_sha256":"8f8479c2811df2f33b616e496a07b63d9ee5900dffff5b32d34c5c2f30598113"}