{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YQCJJ7XRDXSQLJ2U3X2P3Y5TUM","short_pith_number":"pith:YQCJJ7XR","schema_version":"1.0","canonical_sha256":"c40494fef11de505a754ddf4fde3b3a321bb8497de9444a7308aa1129eaf8904","source":{"kind":"arxiv","id":"2503.10673","version":2},"attestation_state":"computed","paper":{"title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"B\\\"ulent Yener, Haidar Khan, Hisham A. Alyahya, M Saiful Bari, Yazeed Alnumay","submitted_at":"2025-03-10T16:54:27Z","abstract_excerpt":"We introduce ZeroSumEval, a dynamic, competition-based, and evolving evaluation framework for Large Language Models (LLMs) that leverages competitive games. ZeroSumEval encompasses a diverse suite of games, including security challenges (Capture the Flag), classic board games (chess), and knowledge tests (MathQuiz). These games are designed to evaluate a range of capabilities such as strategic reasoning, planning, knowledge application, safety, and adaptability. Building upon recent studies that highlight the effectiveness of game-based evaluations for LLMs, ZeroSumEval enhances these approach"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.10673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T16:54:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c61a263c32cd6de76c90a41139b28f9d0bd38d07442f398ed4998f81a7fc7c8","abstract_canon_sha256":"d79c862beb0de1f850210d3d61cfd299b1c88c1feb9f41fa1aff1a5d3208f071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:12.227607Z","signature_b64":"NurHlMtaJt3sXSA5PP7yU+AIx3vaGxplhNbPaWpcg5dS8xxYRBc0n30gENkci9D+rVOY99C4red+cEr9jDSMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40494fef11de505a754ddf4fde3b3a321bb8497de9444a7308aa1129eaf8904","last_reissued_at":"2026-07-05T10:50:12.227096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:12.227096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"B\\\"ulent Yener, Haidar Khan, Hisham A. Alyahya, M Saiful Bari, Yazeed Alnumay","submitted_at":"2025-03-10T16:54:27Z","abstract_excerpt":"We introduce ZeroSumEval, a dynamic, competition-based, and evolving evaluation framework for Large Language Models (LLMs) that leverages competitive games. ZeroSumEval encompasses a diverse suite of games, including security challenges (Capture the Flag), classic board games (chess), and knowledge tests (MathQuiz). These games are designed to evaluate a range of capabilities such as strategic reasoning, planning, knowledge application, safety, and adaptability. Building upon recent studies that highlight the effectiveness of game-based evaluations for LLMs, ZeroSumEval enhances these approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10673","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/2503.10673/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.10673","created_at":"2026-07-05T10:50:12.227160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10673v2","created_at":"2026-07-05T10:50:12.227160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10673","created_at":"2026-07-05T10:50:12.227160+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQCJJ7XRDXSQ","created_at":"2026-07-05T10:50:12.227160+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQCJJ7XRDXSQLJ2U","created_at":"2026-07-05T10:50:12.227160+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQCJJ7XR","created_at":"2026-07-05T10:50:12.227160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM","json":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM.json","graph_json":"https://pith.science/api/pith-number/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/graph.json","events_json":"https://pith.science/api/pith-number/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/events.json","paper":"https://pith.science/paper/YQCJJ7XR"},"agent_actions":{"view_html":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM","download_json":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM.json","view_paper":"https://pith.science/paper/YQCJJ7XR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10673&json=true","fetch_graph":"https://pith.science/api/pith-number/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/graph.json","fetch_events":"https://pith.science/api/pith-number/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/action/storage_attestation","attest_author":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/action/author_attestation","sign_citation":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/action/citation_signature","submit_replication":"https://pith.science/pith/YQCJJ7XRDXSQLJ2U3X2P3Y5TUM/action/replication_record"}},"created_at":"2026-07-05T10:50:12.227160+00:00","updated_at":"2026-07-05T10:50:12.227160+00:00"}