{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.18084", "kind": "paper", "url": "https://arxiv.org/abs/2607.18084"}, {"id": "gh:wzk1015/worldcuparena", "kind": "repo", "url": "https://github.com/wzk1015/WorldCupArena"}], "authors": ["Zhaokai Wang", "Tianlin Gui", "Jiayuan Rao", "Shangzhe Di", "Yihong Tang", "Dingli Liang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.18084", "source_url": "https://arxiv.org/abs/2607.18084"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "WorldCupArena evaluates language models and deep-research agents on football forecasting across multiple tasks including result, score, player events, statistics, and tournament outcomes. It uses a composite score and supports adding new schedules for future events."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.18084", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.18084", "title": "WorldCupArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "McGill University", "University College London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.18084", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.18084", "source_url": "https://openalex.org/W7169865664"}, "key": "claire-radar:2607.18084", "modality": null, "name": "WorldCupArena", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_worldcuparena_3034c352", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a839113d1e54939b68c750ff2cf9035815baa27340e30c5ca6c27905c685d382", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.18084"}, "publisher": null, "released": "2026-07-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.18084", "source_url": "https://arxiv.org/abs/2607.18084"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-18084", "source": "claire_radar", "source_benchmark_id": "2607.18084", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/wzk1015/WorldCupArena", "githubScope": "benchmark_repo", "githubStars": 25, "hfDailySubmittedAt": "2026-07-21T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2607.18084", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3abb2ecf948b0e807d56a9402f9390a5f6a48869a5ecdabf830ae8e4c4f294ec", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WorldCupArena evaluates language models and deep-research agents on football forecasting across multiple tasks including result, score, player events, statistics, and tournament outcomes. It uses a composite score and supports adding new schedules for future events.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present WorldCupArena, a dynamic benchmark for language models and deep-research agents."}, "familyId": "bmf_4b5c0cb0434c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/wzk1015/WorldCupArena", "url": "https://github.com/wzk1015/WorldCupArena"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/wzk1015/WorldCupArena", "url": "https://huggingface.co/papers/2607.18084"}], "scope": "benchmark_repo", "url": "https://github.com/wzk1015/WorldCupArena", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_worldcuparena_3034c352", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/wzk1015/WorldCupArena", "data": null, "hfPaper": "https://huggingface.co/papers/2607.18084", "paper": "https://arxiv.org/abs/2607.18084", "pdf": "https://arxiv.org/pdf/2607.18084", "project": null, "report": "https://arxiv.org/abs/2607.18084"}, "metrics": [], "motivation": "Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available.", "name": "WorldCupArena", "oneLine": "WorldCupArena evaluates language models and deep-research agents on football forecasting across multiple tasks including result, score, player events, statistics, and tournament outcomes. It uses a composite score and supports adding new schedules for future events.", "paperTitle": "WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.18084", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.43489731988793906, "value": 25}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.31659423970600165, "value": 5}}, "confidence": "Medium", "coverage": 0.7, "rank": 116, "score": 44}, "method": "attention-ranking-v13", "rank": 116, "score": 44}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-20", "source": {"authors": ["Zhaokai Wang", "Tianlin Gui", "Jiayuan Rao", "Shangzhe Di", "Yihong Tang", "Dingli Liang"], "categories": ["cs.AI", "cs.CL", "cs.LG"], "id": "2607.18084", "title": "WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting", "type": "arxiv", "url": "https://arxiv.org/abs/2607.18084"}, "sourceUpdatedAt": "2026-07-20T15:52:48Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "This benchmark provides a dynamic, real-world testbed for evaluating models on multi-source reasoning and structured prediction with ground truth on a fixed schedule. It offers practical value in comparing model performance against market and human baselines, revealing differences in detailed predictions beyond result accuracy."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
