{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5KF53T53S6K3QJIYIXZQUVA6U4","short_pith_number":"pith:5KF53T53","schema_version":"1.0","canonical_sha256":"ea8bddcfbb9795b8251845f30a541ea71561cdf5fc76cfc4c1cbcbacd419597c","source":{"kind":"arxiv","id":"2607.18084","version":1},"attestation_state":"computed","paper":{"title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dingli Liang, Jiayuan Rao, Shangzhe Di, Tianlin Gui, Yihong Tang, Zhaokai Wang","submitted_at":"2026-07-20T15:52:48Z","abstract_excerpt":"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. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the compet"},"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":"2607.18084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T15:52:48Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7f5e46c8b4cbd558e2e1cd1f1dc438870dd07919e711f88dc146234c60d063cf","abstract_canon_sha256":"1b4773cf210fb5229c7ede8a0603dae8563dd57842ca334d01ad9580f4d0a744"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:15.565739Z","signature_b64":"CirvdOysdQkB8fCDjnOpsIM9o9hI/cchwmzc3eeR+euYgKfjZPBJy9zQ9oehHSJ98cWFjfuGsex7tvXmI69+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea8bddcfbb9795b8251845f30a541ea71561cdf5fc76cfc4c1cbcbacd419597c","last_reissued_at":"2026-07-21T02:22:15.564892Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:15.564892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dingli Liang, Jiayuan Rao, Shangzhe Di, Tianlin Gui, Yihong Tang, Zhaokai Wang","submitted_at":"2026-07-20T15:52:48Z","abstract_excerpt":"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. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the compet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18084","kind":"arxiv","version":1},"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/2607.18084/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":"2607.18084","created_at":"2026-07-21T02:22:15.565322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18084v1","created_at":"2026-07-21T02:22:15.565322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18084","created_at":"2026-07-21T02:22:15.565322+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KF53T53S6K3","created_at":"2026-07-21T02:22:15.565322+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KF53T53S6K3QJIY","created_at":"2026-07-21T02:22:15.565322+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KF53T53","created_at":"2026-07-21T02:22:15.565322+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/5KF53T53S6K3QJIYIXZQUVA6U4","json":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4.json","graph_json":"https://pith.science/api/pith-number/5KF53T53S6K3QJIYIXZQUVA6U4/graph.json","events_json":"https://pith.science/api/pith-number/5KF53T53S6K3QJIYIXZQUVA6U4/events.json","paper":"https://pith.science/paper/5KF53T53"},"agent_actions":{"view_html":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4","download_json":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4.json","view_paper":"https://pith.science/paper/5KF53T53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18084&json=true","fetch_graph":"https://pith.science/api/pith-number/5KF53T53S6K3QJIYIXZQUVA6U4/graph.json","fetch_events":"https://pith.science/api/pith-number/5KF53T53S6K3QJIYIXZQUVA6U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4/action/storage_attestation","attest_author":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4/action/author_attestation","sign_citation":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4/action/citation_signature","submit_replication":"https://pith.science/pith/5KF53T53S6K3QJIYIXZQUVA6U4/action/replication_record"}},"created_at":"2026-07-21T02:22:15.565322+00:00","updated_at":"2026-07-21T02:22:15.565322+00:00"}