{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QETQ66BDZA3SU4YAZRBOROYKNK","short_pith_number":"pith:QETQ66BD","schema_version":"1.0","canonical_sha256":"81270f7823c8372a7300cc42e8bb0a6aae6c10fafa357e144800c8608122902d","source":{"kind":"arxiv","id":"2607.24573","version":1},"attestation_state":"computed","paper":{"title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jonas Schr\\\"oder, Jonas Schweisthal, Markus Weinmann, Oliver M\\\"uller, Stefan Feuerriegel","submitted_at":"2026-07-27T15:38:29Z","abstract_excerpt":"Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark prot"},"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":"2607.24573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T15:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"f097ad5e708ec956113213e5b290934aa98d3a266441dc89873b1d6df4a28215","abstract_canon_sha256":"cd75d84f2e73217636aed789ad34b74fe892016c0a9dc6b1df13bbeb04bbad58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:10.893583Z","signature_b64":"E/vyl0IXpwPrsuRxKa+PAOFZT8cYqNhHxchvMn5qrZ9MPx1ACidGPey8HwTVycu/chU25XzKc3vKNaP8QD41AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81270f7823c8372a7300cc42e8bb0a6aae6c10fafa357e144800c8608122902d","last_reissued_at":"2026-07-28T02:24:10.892755Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:10.892755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jonas Schr\\\"oder, Jonas Schweisthal, Markus Weinmann, Oliver M\\\"uller, Stefan Feuerriegel","submitted_at":"2026-07-27T15:38:29Z","abstract_excerpt":"Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark prot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24573","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/2607.24573/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":"2607.24573","created_at":"2026-07-28T02:24:10.893176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24573v1","created_at":"2026-07-28T02:24:10.893176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24573","created_at":"2026-07-28T02:24:10.893176+00:00"},{"alias_kind":"pith_short_12","alias_value":"QETQ66BDZA3S","created_at":"2026-07-28T02:24:10.893176+00:00"},{"alias_kind":"pith_short_16","alias_value":"QETQ66BDZA3SU4YA","created_at":"2026-07-28T02:24:10.893176+00:00"},{"alias_kind":"pith_short_8","alias_value":"QETQ66BD","created_at":"2026-07-28T02:24:10.893176+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/QETQ66BDZA3SU4YAZRBOROYKNK","json":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK.json","graph_json":"https://pith.science/api/pith-number/QETQ66BDZA3SU4YAZRBOROYKNK/graph.json","events_json":"https://pith.science/api/pith-number/QETQ66BDZA3SU4YAZRBOROYKNK/events.json","paper":"https://pith.science/paper/QETQ66BD"},"agent_actions":{"view_html":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK","download_json":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK.json","view_paper":"https://pith.science/paper/QETQ66BD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24573&json=true","fetch_graph":"https://pith.science/api/pith-number/QETQ66BDZA3SU4YAZRBOROYKNK/graph.json","fetch_events":"https://pith.science/api/pith-number/QETQ66BDZA3SU4YAZRBOROYKNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK/action/storage_attestation","attest_author":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK/action/author_attestation","sign_citation":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK/action/citation_signature","submit_replication":"https://pith.science/pith/QETQ66BDZA3SU4YAZRBOROYKNK/action/replication_record"}},"created_at":"2026-07-28T02:24:10.893176+00:00","updated_at":"2026-07-28T02:24:10.893176+00:00"}