{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5KF53T53S6K3QJIYIXZQUVA6U4","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1b4773cf210fb5229c7ede8a0603dae8563dd57842ca334d01ad9580f4d0a744","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T15:52:48Z","title_canon_sha256":"7f5e46c8b4cbd558e2e1cd1f1dc438870dd07919e711f88dc146234c60d063cf"},"schema_version":"1.0","source":{"id":"2607.18084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18084","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18084v1","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18084","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"5KF53T53S6K3","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"5KF53T53S6K3QJIY","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"5KF53T53","created_at":"2026-07-21T02:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:29d57f8766cb6b61446627f3fb8f83d0b22ed3302739c0cf5952c1fe72c2c0da","target":"graph","created_at":"2026-07-21T02:22:15Z","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/2607.18084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dingli Liang, Jiayuan Rao, Shangzhe Di, Tianlin Gui, Yihong Tang, Zhaokai Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T15:52:48Z","title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18084","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":"sha256:7d9136be85b427c70960e28b282b53f582d58bb4542b01cfdec6061fdbb15db1","target":"record","created_at":"2026-07-21T02:22:15Z","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":"1b4773cf210fb5229c7ede8a0603dae8563dd57842ca334d01ad9580f4d0a744","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T15:52:48Z","title_canon_sha256":"7f5e46c8b4cbd558e2e1cd1f1dc438870dd07919e711f88dc146234c60d063cf"},"schema_version":"1.0","source":{"id":"2607.18084","kind":"arxiv","version":1}},"canonical_sha256":"ea8bddcfbb9795b8251845f30a541ea71561cdf5fc76cfc4c1cbcbacd419597c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea8bddcfbb9795b8251845f30a541ea71561cdf5fc76cfc4c1cbcbacd419597c","first_computed_at":"2026-07-21T02:22:15.564892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:15.564892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CirvdOysdQkB8fCDjnOpsIM9o9hI/cchwmzc3eeR+euYgKfjZPBJy9zQ9oehHSJ98cWFjfuGsex7tvXmI69+Dg==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:15.565739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18084","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:a87d18efb96b2b99acf9dc56811df1e59387be0235e37e4b78c612fad947027e","sha256:d35ead7bcb78f3c00ba5e88e2747022244203e7db4005df1b4d99c1f0f294f2c","sha256:e06b4dc0f89000c73037b0359d2d8bfebcaf9892e6ebf9d25ec4514a7db8f451"]}],"invalid_events":[],"applied_event_ids":["sha256:7d9136be85b427c70960e28b282b53f582d58bb4542b01cfdec6061fdbb15db1","sha256:29d57f8766cb6b61446627f3fb8f83d0b22ed3302739c0cf5952c1fe72c2c0da"],"state_sha256":"94136446a9f0071ae1df3aa7d135f96999c337ab89856ef7f354637733d73e83"}