{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y7QI4Z7OAMBGHBKNNH3Z3OAF6H","short_pith_number":"pith:Y7QI4Z7O","schema_version":"1.0","canonical_sha256":"c7e08e67ee030263854d69f79db805f1ecd938d11636ed7fb86f0cdac1b83042","source":{"kind":"arxiv","id":"2410.08474","version":4},"attestation_state":"computed","paper":{"title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chi Lu, Christopher Lai, Hanjie Chen, Haotian Xia, Junbo Zou, Rhys Tracy, Weining Shen, Xun Shao, Yanjun He, Yuan-Fang Wang, Yuqing Wang, Zhengbang Yang, Zhuoqing Xie","submitted_at":"2024-10-11T02:58:38Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without "},"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":"2410.08474","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-11T02:58:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d0332926db8c23c6270d2a3633863316ccc31266f108cae9d92691281eed36e4","abstract_canon_sha256":"86ef0f67edd93e3cfeacde001f4abbfeaf81570b66766531c5d1bf936cfe16e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:48.416117Z","signature_b64":"Jbw3TizGwAw0AO0yPjvm5Ap3ctfMsYkQ0naN3QmePoRCWDbEAuZexdS2vhcwO4zoqhOQ1LfWOD4ynLhYuEMMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7e08e67ee030263854d69f79db805f1ecd938d11636ed7fb86f0cdac1b83042","last_reissued_at":"2026-07-05T10:31:48.415201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:48.415201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chi Lu, Christopher Lai, Hanjie Chen, Haotian Xia, Junbo Zou, Rhys Tracy, Weining Shen, Xun Shao, Yanjun He, Yuan-Fang Wang, Yuqing Wang, Zhengbang Yang, Zhuoqing Xie","submitted_at":"2024-10-11T02:58:38Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08474","kind":"arxiv","version":4},"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/2410.08474/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":"2410.08474","created_at":"2026-07-05T10:31:48.415332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08474v4","created_at":"2026-07-05T10:31:48.415332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08474","created_at":"2026-07-05T10:31:48.415332+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7QI4Z7OAMBG","created_at":"2026-07-05T10:31:48.415332+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7QI4Z7OAMBGHBKN","created_at":"2026-07-05T10:31:48.415332+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7QI4Z7O","created_at":"2026-07-05T10:31:48.415332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09181","citing_title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":244,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15602","citing_title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23392","citing_title":"SoccerRef-Agents: Multi-Agent System for Automated Soccer Refereeing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04419","citing_title":"BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15736","citing_title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H","json":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H.json","graph_json":"https://pith.science/api/pith-number/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/graph.json","events_json":"https://pith.science/api/pith-number/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/events.json","paper":"https://pith.science/paper/Y7QI4Z7O"},"agent_actions":{"view_html":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H","download_json":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H.json","view_paper":"https://pith.science/paper/Y7QI4Z7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08474&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/action/storage_attestation","attest_author":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/action/author_attestation","sign_citation":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/action/citation_signature","submit_replication":"https://pith.science/pith/Y7QI4Z7OAMBGHBKNNH3Z3OAF6H/action/replication_record"}},"created_at":"2026-07-05T10:31:48.415332+00:00","updated_at":"2026-07-05T10:31:48.415332+00:00"}