{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZYZLYEHAUZOLXOPLCRKY7V7BCE","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":"051593fffb1dd140cbfcecf2ff8c3dacb918375af267588a5af6e727da69d2b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:34:25Z","title_canon_sha256":"ec35acab9b440b8c50982daa62efc7909e93cb3f20fd95fc4e7a33f110fb88e4"},"schema_version":"1.0","source":{"id":"2505.23484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23484","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23484v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23484","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZYZLYEHAUZOL","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZYZLYEHAUZOLXOPL","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZYZLYEHA","created_at":"2026-07-05T11:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:742eef89a03b81f9562b19e8efd9bb73b69d8264e5530e556ded390bdad59c74","target":"graph","created_at":"2026-07-05T11:12:02Z","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/2505.23484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captions play a crucial role in text-to-video generation tasks, as their quality directly influences the semantic coherence and visual fidelity of the generated videos. Although large vision-language models (VLMs) have demonstrated significant potential in caption generation, existing benchmarks inadequately address fine-grained evaluation, particularly in capturing spatial-temporal details critical for video generation. To address this gap, we introduce the Fine-grained Video Caption Evaluation Benchmark (VCapsBench), the first large-scale fine-grained benchmark comprising 5,677 (5K+) v","authors_text":"Duojun Huang, Hongfa Wang, Shi-Xue Zhang, Xiaobin Zhu, Xin Li, Xu-Cheng Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:34:25Z","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23484","kind":"arxiv","version":1},"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":"sha256:24902e96474619327b182e605d7cd9238cda41563357725ff25c91b949493547","target":"record","created_at":"2026-07-05T11:12:02Z","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":"051593fffb1dd140cbfcecf2ff8c3dacb918375af267588a5af6e727da69d2b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T14:34:25Z","title_canon_sha256":"ec35acab9b440b8c50982daa62efc7909e93cb3f20fd95fc4e7a33f110fb88e4"},"schema_version":"1.0","source":{"id":"2505.23484","kind":"arxiv","version":1}},"canonical_sha256":"ce32bc10e0a65cbbb9eb14558fd7e111138ae44cd0c29240f06cfc1f55597124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce32bc10e0a65cbbb9eb14558fd7e111138ae44cd0c29240f06cfc1f55597124","first_computed_at":"2026-07-05T11:12:02.784234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:02.784234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xEx+62eMWaeVhST1m4YLzzwm396ksZclrgC1V8dnp3niakrjPtsJprh4x9qYbUEDCnp2HmIUHqKSDs+H2GXnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:02.784745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24902e96474619327b182e605d7cd9238cda41563357725ff25c91b949493547","sha256:742eef89a03b81f9562b19e8efd9bb73b69d8264e5530e556ded390bdad59c74"],"state_sha256":"564e58dbbabd728a130b46b04ce7719fa20cf1610b29a3082f838b7973aaa627"}