{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GQYHSBEQDTEWXJZ5AIH6C6UPYK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"149e98df183e55e3f292052a6d638c3f7bc9d9d5d58fbaea6281230c8a0554d6","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T15:53:50Z","title_canon_sha256":"14cf296d64d40252efa9339d171ab2c80bd444ef002efcf446f924f9f1574327"},"schema_version":"1.0","source":{"id":"2501.00513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00513","created_at":"2026-07-05T10:33:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00513v2","created_at":"2026-07-05T10:33:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00513","created_at":"2026-07-05T10:33:41Z"},{"alias_kind":"pith_short_12","alias_value":"GQYHSBEQDTEW","created_at":"2026-07-05T10:33:41Z"},{"alias_kind":"pith_short_16","alias_value":"GQYHSBEQDTEWXJZ5","created_at":"2026-07-05T10:33:41Z"},{"alias_kind":"pith_short_8","alias_value":"GQYHSBEQ","created_at":"2026-07-05T10:33:41Z"}],"graph_snapshots":[{"event_id":"sha256:b6d77c78d2e4230e736b44c8cf758d8715e08ba4e5f3a5ecb914f24d5a2088b6","target":"graph","created_at":"2026-07-05T10:33:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.00513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Desen Meng, Limin Wang, Rui Huang, Xinhao Li, Yichun Yang, Yifan Xu","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T15:53:50Z","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00513","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b492afcaad1da931639447dc99dd6fba6d7762cb9b4587b80b9527b80437de8","target":"record","created_at":"2026-07-05T10:33:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"149e98df183e55e3f292052a6d638c3f7bc9d9d5d58fbaea6281230c8a0554d6","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T15:53:50Z","title_canon_sha256":"14cf296d64d40252efa9339d171ab2c80bd444ef002efcf446f924f9f1574327"},"schema_version":"1.0","source":{"id":"2501.00513","kind":"arxiv","version":2}},"canonical_sha256":"34307904901cc96ba73d020fe17a8fc291730777a6514f092c6b2484a6ef431b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34307904901cc96ba73d020fe17a8fc291730777a6514f092c6b2484a6ef431b","first_computed_at":"2026-07-05T10:33:41.909154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:41.909154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Y5fFSLg9KZ74wHKB5VAmMyk4rvzTBvKMgpToz0ATAeQ4OalIa7SRxifcwVoBEszXLLFoPAPdOaDtylq6exBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:41.913255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b492afcaad1da931639447dc99dd6fba6d7762cb9b4587b80b9527b80437de8","sha256:b6d77c78d2e4230e736b44c8cf758d8715e08ba4e5f3a5ecb914f24d5a2088b6"],"state_sha256":"85f6561fede70b65c2078821ddc22e25830922a82f25631311e12ee3b0df6986"}