{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWQNKPMPMNBPYAAD7OPPIP5SJ3","short_pith_number":"pith:VWQNKPMP","schema_version":"1.0","canonical_sha256":"ada0d53d8f6342fc0003fb9ef43fb24eeb5c0dbdf34ad0683b2df583a0695b91","source":{"kind":"arxiv","id":"2401.13888","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Shi, Junchi Yan, Liang Wang, Lifang Wu, Xuefen Li, Zeyu Xi, Zilin Liu, Zun Li","submitted_at":"2024-01-25T02:08:37Z","abstract_excerpt":"Despite the recent emergence of video captioning models, how to generate the text description with specific entity names and fine-grained actions is far from being solved, which however has great applications such as basketball live text broadcast. In this paper, a new multimodal knowledge graph supported basketball benchmark for video captioning is proposed. Specifically, we construct a multimodal basketball game knowledge graph (KG_NBA_2022) to provide additional knowledge beyond videos. Then, a multimodal basketball game video captioning (VC_NBA_2022) dataset that contains 9 types of fine-g"},"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":"2401.13888","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-25T02:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"8b059ea0eb688b934223a5c39b16fcc22b4a885f09a1e28d9477e678761cbecb","abstract_canon_sha256":"d645fb6c8f98a8608e0a1a5c9ab6541d3143b52f52a870e64f5b2f09d83b8e07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:06.359195Z","signature_b64":"hCNUR2B0sF3kk1x794EUopJc3hAQ9EvDvEtR9sjaRfAZYrkm+JE/uQETSwOk/cbJqv8KBXgBQHQWvIpFkZnxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ada0d53d8f6342fc0003fb9ef43fb24eeb5c0dbdf34ad0683b2df583a0695b91","last_reissued_at":"2026-07-05T07:50:06.358757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:06.358757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Shi, Junchi Yan, Liang Wang, Lifang Wu, Xuefen Li, Zeyu Xi, Zilin Liu, Zun Li","submitted_at":"2024-01-25T02:08:37Z","abstract_excerpt":"Despite the recent emergence of video captioning models, how to generate the text description with specific entity names and fine-grained actions is far from being solved, which however has great applications such as basketball live text broadcast. In this paper, a new multimodal knowledge graph supported basketball benchmark for video captioning is proposed. Specifically, we construct a multimodal basketball game knowledge graph (KG_NBA_2022) to provide additional knowledge beyond videos. Then, a multimodal basketball game video captioning (VC_NBA_2022) dataset that contains 9 types of fine-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13888","kind":"arxiv","version":2},"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/2401.13888/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":"2401.13888","created_at":"2026-07-05T07:50:06.358827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13888v2","created_at":"2026-07-05T07:50:06.358827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13888","created_at":"2026-07-05T07:50:06.358827+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWQNKPMPMNBP","created_at":"2026-07-05T07:50:06.358827+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWQNKPMPMNBPYAAD","created_at":"2026-07-05T07:50:06.358827+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWQNKPMP","created_at":"2026-07-05T07:50:06.358827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17844","citing_title":"SV3.3B: A Sports Video Understanding Model for Action Recognition","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3","json":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3.json","graph_json":"https://pith.science/api/pith-number/VWQNKPMPMNBPYAAD7OPPIP5SJ3/graph.json","events_json":"https://pith.science/api/pith-number/VWQNKPMPMNBPYAAD7OPPIP5SJ3/events.json","paper":"https://pith.science/paper/VWQNKPMP"},"agent_actions":{"view_html":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3","download_json":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3.json","view_paper":"https://pith.science/paper/VWQNKPMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13888&json=true","fetch_graph":"https://pith.science/api/pith-number/VWQNKPMPMNBPYAAD7OPPIP5SJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/VWQNKPMPMNBPYAAD7OPPIP5SJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3/action/storage_attestation","attest_author":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3/action/author_attestation","sign_citation":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3/action/citation_signature","submit_replication":"https://pith.science/pith/VWQNKPMPMNBPYAAD7OPPIP5SJ3/action/replication_record"}},"created_at":"2026-07-05T07:50:06.358827+00:00","updated_at":"2026-07-05T07:50:06.358827+00:00"}