{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQYHSBEQDTEWXJZ5AIH6C6UPYK","short_pith_number":"pith:GQYHSBEQ","schema_version":"1.0","canonical_sha256":"34307904901cc96ba73d020fe17a8fc291730777a6514f092c6b2484a6ef431b","source":{"kind":"arxiv","id":"2501.00513","version":2},"attestation_state":"computed","paper":{"title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Desen Meng, Limin Wang, Rui Huang, Xinhao Li, Yichun Yang, Yifan Xu","submitted_at":"2024-12-31T15:53:50Z","abstract_excerpt":"Video understanding, including video captioning and retrieval, is still a great challenge for video-language models (VLMs). The existing video retrieval and caption benchmarks only include short descriptions, limits their ability of detailed video understanding evaluation. To address this problem, we present CaReBench, a testing benchmark for fine-grained video captioning and retrieval with 1,000 high-quality pairs of videos and human-annotated detailed captions. Uniquely, it provides manually separated spatial annotations and temporal annotations for each video. Based on this design, we intro"},"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":"2501.00513","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T15:53:50Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"14cf296d64d40252efa9339d171ab2c80bd444ef002efcf446f924f9f1574327","abstract_canon_sha256":"149e98df183e55e3f292052a6d638c3f7bc9d9d5d58fbaea6281230c8a0554d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:41.913255Z","signature_b64":"5Y5fFSLg9KZ74wHKB5VAmMyk4rvzTBvKMgpToz0ATAeQ4OalIa7SRxifcwVoBEszXLLFoPAPdOaDtylq6exBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34307904901cc96ba73d020fe17a8fc291730777a6514f092c6b2484a6ef431b","last_reissued_at":"2026-07-05T10:33:41.909154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:41.909154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Desen Meng, Limin Wang, Rui Huang, Xinhao Li, Yichun Yang, Yifan Xu","submitted_at":"2024-12-31T15:53:50Z","abstract_excerpt":"Video understanding, including video captioning and retrieval, is still a great challenge for video-language models (VLMs). The existing video retrieval and caption benchmarks only include short descriptions, limits their ability of detailed video understanding evaluation. To address this problem, we present CaReBench, a testing benchmark for fine-grained video captioning and retrieval with 1,000 high-quality pairs of videos and human-annotated detailed captions. Uniquely, it provides manually separated spatial annotations and temporal annotations for each video. Based on this design, we intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00513","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/2501.00513/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":"2501.00513","created_at":"2026-07-05T10:33:41.909296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00513v2","created_at":"2026-07-05T10:33:41.909296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00513","created_at":"2026-07-05T10:33:41.909296+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQYHSBEQDTEW","created_at":"2026-07-05T10:33:41.909296+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQYHSBEQDTEWXJZ5","created_at":"2026-07-05T10:33:41.909296+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQYHSBEQ","created_at":"2026-07-05T10:33:41.909296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09393","citing_title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2504.06958","citing_title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK","json":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK.json","graph_json":"https://pith.science/api/pith-number/GQYHSBEQDTEWXJZ5AIH6C6UPYK/graph.json","events_json":"https://pith.science/api/pith-number/GQYHSBEQDTEWXJZ5AIH6C6UPYK/events.json","paper":"https://pith.science/paper/GQYHSBEQ"},"agent_actions":{"view_html":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK","download_json":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK.json","view_paper":"https://pith.science/paper/GQYHSBEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00513&json=true","fetch_graph":"https://pith.science/api/pith-number/GQYHSBEQDTEWXJZ5AIH6C6UPYK/graph.json","fetch_events":"https://pith.science/api/pith-number/GQYHSBEQDTEWXJZ5AIH6C6UPYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK/action/storage_attestation","attest_author":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK/action/author_attestation","sign_citation":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK/action/citation_signature","submit_replication":"https://pith.science/pith/GQYHSBEQDTEWXJZ5AIH6C6UPYK/action/replication_record"}},"created_at":"2026-07-05T10:33:41.909296+00:00","updated_at":"2026-07-05T10:33:41.909296+00:00"}