{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GP2TU4LRFNDWYOTO3QIVUTE5UG","short_pith_number":"pith:GP2TU4LR","schema_version":"1.0","canonical_sha256":"33f53a71712b476c3a6edc115a4c9da1ad70ca3922d5767f19b28f03e456c6b3","source":{"kind":"arxiv","id":"2303.14655","version":2},"attestation_state":"computed","paper":{"title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Xu, Hui Liu, Jie Tang, Jifan Yu, Ji Qi, Juanzi Li, Kunyu Gao, Lei Hou, Teng Tu, Weidong Guo, Xiaozhi Wang, Xinyu Guan, Yifan Xu, Yuxiao Dong, Yu Xu","submitted_at":"2023-03-26T08:43:36Z","abstract_excerpt":"Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. In this paper, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). Moreover, we conduct experimental adapt"},"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":"2303.14655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T08:43:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4d795ee38bd4129271ee002112ae70fb1d233ea9f1087031a60c61fc708e7808","abstract_canon_sha256":"474c72947d1dd8392cf4cf2a536ebbfd4b1fb523a01cc7650e660cfcdf8ccf89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:22.116278Z","signature_b64":"c065olqptxu1z/dSL86BZU6XJTNL4c3u/BTfCp/hTHazuJHYX87gc9faitqlqhH6wAKodHAm9Pf9C9K7wak7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f53a71712b476c3a6edc115a4c9da1ad70ca3922d5767f19b28f03e456c6b3","last_reissued_at":"2026-07-05T06:57:22.115878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:22.115878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Xu, Hui Liu, Jie Tang, Jifan Yu, Ji Qi, Juanzi Li, Kunyu Gao, Lei Hou, Teng Tu, Weidong Guo, Xiaozhi Wang, Xinyu Guan, Yifan Xu, Yuxiao Dong, Yu Xu","submitted_at":"2023-03-26T08:43:36Z","abstract_excerpt":"Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. In this paper, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). Moreover, we conduct experimental adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14655","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/2303.14655/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":"2303.14655","created_at":"2026-07-05T06:57:22.115934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14655v2","created_at":"2026-07-05T06:57:22.115934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14655","created_at":"2026-07-05T06:57:22.115934+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP2TU4LRFNDW","created_at":"2026-07-05T06:57:22.115934+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP2TU4LRFNDWYOTO","created_at":"2026-07-05T06:57:22.115934+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP2TU4LR","created_at":"2026-07-05T06:57:22.115934+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/GP2TU4LRFNDWYOTO3QIVUTE5UG","json":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG.json","graph_json":"https://pith.science/api/pith-number/GP2TU4LRFNDWYOTO3QIVUTE5UG/graph.json","events_json":"https://pith.science/api/pith-number/GP2TU4LRFNDWYOTO3QIVUTE5UG/events.json","paper":"https://pith.science/paper/GP2TU4LR"},"agent_actions":{"view_html":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG","download_json":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG.json","view_paper":"https://pith.science/paper/GP2TU4LR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14655&json=true","fetch_graph":"https://pith.science/api/pith-number/GP2TU4LRFNDWYOTO3QIVUTE5UG/graph.json","fetch_events":"https://pith.science/api/pith-number/GP2TU4LRFNDWYOTO3QIVUTE5UG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG/action/storage_attestation","attest_author":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG/action/author_attestation","sign_citation":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG/action/citation_signature","submit_replication":"https://pith.science/pith/GP2TU4LRFNDWYOTO3QIVUTE5UG/action/replication_record"}},"created_at":"2026-07-05T06:57:22.115934+00:00","updated_at":"2026-07-05T06:57:22.115934+00:00"}