{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZATU42QZBGQ64JPCPU4PTU2G3","short_pith_number":"pith:NZATU42Q","schema_version":"1.0","canonical_sha256":"6e413a7350c84d0f712f13e9c7ce9a36dc5d9dd69432e32b9454e4d857919d73","source":{"kind":"arxiv","id":"2406.12252","version":1},"attestation_state":"computed","paper":{"title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanjie Chen, Haotian Xia, Jingxi Li, Rhys Tracy, Weining Shen, Yuan-Fang Wang, Yun Zhao, Yuqing Wang, Zhengbang Yang, Zhuangdi Zhu","submitted_at":"2024-06-18T03:59:26Z","abstract_excerpt":"Recent integration of Natural Language Processing (NLP) and multimodal models has advanced the field of sports analytics. This survey presents a comprehensive review of the datasets and applications driving these innovations post-2020. We overviewed and categorized datasets into three primary types: language-based, multimodal, and convertible datasets. Language-based and multimodal datasets are for tasks involving text or multimodality (e.g., text, video, audio), respectively. Convertible datasets, initially single-modal (video), can be enriched with additional annotations, such as explanation"},"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":"2406.12252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T03:59:26Z","cross_cats_sorted":[],"title_canon_sha256":"253bc80121f788335764ec2e75d225f9df2dcda4b71aa0a632052be88bd0c961","abstract_canon_sha256":"d0ff609b1052bba3829f5833e251f6e2f09dc8affbf8e1e51c413a451a86caf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:43.383644Z","signature_b64":"GASL7WF453PETWztKkO8Yj519wGC+AV6dSi6HEvPSmNTI+Q1Pg+wIquHq/qmiNF5COM8Sg0Vo+NGL+3OUCkuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e413a7350c84d0f712f13e9c7ce9a36dc5d9dd69432e32b9454e4d857919d73","last_reissued_at":"2026-07-05T08:33:43.383166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:43.383166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language and Multimodal Models in Sports: A Survey of Datasets and Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanjie Chen, Haotian Xia, Jingxi Li, Rhys Tracy, Weining Shen, Yuan-Fang Wang, Yun Zhao, Yuqing Wang, Zhengbang Yang, Zhuangdi Zhu","submitted_at":"2024-06-18T03:59:26Z","abstract_excerpt":"Recent integration of Natural Language Processing (NLP) and multimodal models has advanced the field of sports analytics. This survey presents a comprehensive review of the datasets and applications driving these innovations post-2020. We overviewed and categorized datasets into three primary types: language-based, multimodal, and convertible datasets. Language-based and multimodal datasets are for tasks involving text or multimodality (e.g., text, video, audio), respectively. Convertible datasets, initially single-modal (video), can be enriched with additional annotations, such as explanation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12252","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/2406.12252/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":"2406.12252","created_at":"2026-07-05T08:33:43.383223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12252v1","created_at":"2026-07-05T08:33:43.383223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12252","created_at":"2026-07-05T08:33:43.383223+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZATU42QZBGQ","created_at":"2026-07-05T08:33:43.383223+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZATU42QZBGQ64JP","created_at":"2026-07-05T08:33:43.383223+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZATU42Q","created_at":"2026-07-05T08:33:43.383223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04419","citing_title":"BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15736","citing_title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3","json":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3.json","graph_json":"https://pith.science/api/pith-number/NZATU42QZBGQ64JPCPU4PTU2G3/graph.json","events_json":"https://pith.science/api/pith-number/NZATU42QZBGQ64JPCPU4PTU2G3/events.json","paper":"https://pith.science/paper/NZATU42Q"},"agent_actions":{"view_html":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3","download_json":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3.json","view_paper":"https://pith.science/paper/NZATU42Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12252&json=true","fetch_graph":"https://pith.science/api/pith-number/NZATU42QZBGQ64JPCPU4PTU2G3/graph.json","fetch_events":"https://pith.science/api/pith-number/NZATU42QZBGQ64JPCPU4PTU2G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3/action/storage_attestation","attest_author":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3/action/author_attestation","sign_citation":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3/action/citation_signature","submit_replication":"https://pith.science/pith/NZATU42QZBGQ64JPCPU4PTU2G3/action/replication_record"}},"created_at":"2026-07-05T08:33:43.383223+00:00","updated_at":"2026-07-05T08:33:43.383223+00:00"}