{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MYP6UQMTA3TRDZWOAWRPJOZ53N","short_pith_number":"pith:MYP6UQMT","schema_version":"1.0","canonical_sha256":"661fea419306e711e6ce05a2f4bb3ddb66062dac16588b1c6463b74bdf58c6e2","source":{"kind":"arxiv","id":"2606.12106","version":1},"attestation_state":"computed","paper":{"title":"MSUE: Multi-Modal Soccer Understanding Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiali Wen, Litao Li, Yibo Yu, Yixin Chen, Yixi Zhou, Yufeng Hu, Zhuo Yang","submitted_at":"2026-06-10T14:00:55Z","abstract_excerpt":"This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses. Second, we propose MSUE, a multi-expert question answering architecture that employs a Large Language Model (LLM) to dynamically dispatch questions to text, image, and video experts. These experts are instantiated as a strong text baseline Gemini3-Flash, a fine-tuned Qwen3-VL, and an external knowledge "},"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":"2606.12106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T14:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b664da6f29409651714477fb96ffb1b3c38376b1072bee9c2d57755fbda268c2","abstract_canon_sha256":"547578f6f2069ef51bf2c61e598a0301fced35712d162f7fe9cf70f7675fc028"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:48.489519Z","signature_b64":"wtn3yWalui5gVKgHoj9WFOJ7ediS2dPut/CNye5q7y0IldkZS8RCt8rYvJhTdePbbzLY13z1fRdnRpIJzCtzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"661fea419306e711e6ce05a2f4bb3ddb66062dac16588b1c6463b74bdf58c6e2","last_reissued_at":"2026-06-11T01:10:48.488478Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:48.488478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSUE: Multi-Modal Soccer Understanding Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiali Wen, Litao Li, Yibo Yu, Yixin Chen, Yixi Zhou, Yufeng Hu, Zhuo Yang","submitted_at":"2026-06-10T14:00:55Z","abstract_excerpt":"This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Language Model (VLM), which systematically restructures raw domain data into diverse VQA samples, including concise answers and long-form responses. Second, we propose MSUE, a multi-expert question answering architecture that employs a Large Language Model (LLM) to dynamically dispatch questions to text, image, and video experts. These experts are instantiated as a strong text baseline Gemini3-Flash, a fine-tuned Qwen3-VL, and an external knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12106","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/2606.12106/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":"2606.12106","created_at":"2026-06-11T01:10:48.488609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12106v1","created_at":"2026-06-11T01:10:48.488609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12106","created_at":"2026-06-11T01:10:48.488609+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYP6UQMTA3TR","created_at":"2026-06-11T01:10:48.488609+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYP6UQMTA3TRDZWO","created_at":"2026-06-11T01:10:48.488609+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYP6UQMT","created_at":"2026-06-11T01:10:48.488609+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/MYP6UQMTA3TRDZWOAWRPJOZ53N","json":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N.json","graph_json":"https://pith.science/api/pith-number/MYP6UQMTA3TRDZWOAWRPJOZ53N/graph.json","events_json":"https://pith.science/api/pith-number/MYP6UQMTA3TRDZWOAWRPJOZ53N/events.json","paper":"https://pith.science/paper/MYP6UQMT"},"agent_actions":{"view_html":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N","download_json":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N.json","view_paper":"https://pith.science/paper/MYP6UQMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12106&json=true","fetch_graph":"https://pith.science/api/pith-number/MYP6UQMTA3TRDZWOAWRPJOZ53N/graph.json","fetch_events":"https://pith.science/api/pith-number/MYP6UQMTA3TRDZWOAWRPJOZ53N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N/action/storage_attestation","attest_author":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N/action/author_attestation","sign_citation":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N/action/citation_signature","submit_replication":"https://pith.science/pith/MYP6UQMTA3TRDZWOAWRPJOZ53N/action/replication_record"}},"created_at":"2026-06-11T01:10:48.488609+00:00","updated_at":"2026-06-11T01:10:48.488609+00:00"}