{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QELXMNHNJ67RBXHUS363IOPCQX","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":"c733aa6851710151453942f11b7f5dd859b15003a7d2d095a820332d1b2ba86b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T11:42:17Z","title_canon_sha256":"7299efba90714ffd6a6fe19572c1000e4a4283c935d6f68c7eb1c0371041bbb5"},"schema_version":"1.0","source":{"id":"2502.12782","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12782","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12782v2","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12782","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"QELXMNHNJ67R","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"QELXMNHNJ67RBXHU","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"QELXMNHN","created_at":"2026-07-05T11:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:3caaedd0ae54efe6b612290b2234321c74f328a53e949e9b353a10fafb2e0561","target":"graph","created_at":"2026-07-05T11:04:45Z","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/2502.12782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training of controllable text-to-video (T2V) models relies heavily on the alignment between videos and captions, yet little existing research connects video caption evaluation with T2V generation assessment. This paper introduces VidCapBench, a video caption evaluation scheme specifically designed for T2V generation, agnostic to any particular caption format. VidCapBench employs a data annotation pipeline, combining expert model labeling and human refinement, to associate each collected video with key information spanning video aesthetics, content, motion, and physical laws. VidCapBench th","authors_text":"Chengru Song, Chongling Rao, Di Zhang, Fuzheng Zhang, Jiaheng Liu, Qiang Liu, Tieniu Tan, Xinlong Chen, Yuanxing Zhang, Yushuo Guan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T11:42:17Z","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12782","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":"sha256:0f9856f55da8e8070832f2397eac60e684585db85518d0240b9a6298f99b2dcc","target":"record","created_at":"2026-07-05T11:04:45Z","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":"c733aa6851710151453942f11b7f5dd859b15003a7d2d095a820332d1b2ba86b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-18T11:42:17Z","title_canon_sha256":"7299efba90714ffd6a6fe19572c1000e4a4283c935d6f68c7eb1c0371041bbb5"},"schema_version":"1.0","source":{"id":"2502.12782","kind":"arxiv","version":2}},"canonical_sha256":"81177634ed4fbf10dcf496fdb439e285e7de37e8550da13263398cd096dacf9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81177634ed4fbf10dcf496fdb439e285e7de37e8550da13263398cd096dacf9a","first_computed_at":"2026-07-05T11:04:45.821345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:45.821345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vnRQOicG/q3MNb0XK4Nt7UZb9ukCTSwjF4aKM4EornKv7hECYz+Jv85x8TLEwCsHiXI2vdnpWe5A/ckadqmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:45.821847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12782","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f9856f55da8e8070832f2397eac60e684585db85518d0240b9a6298f99b2dcc","sha256:3caaedd0ae54efe6b612290b2234321c74f328a53e949e9b353a10fafb2e0561"],"state_sha256":"ac45725b4705ef2dd915bd7cf6d2b19487f5d7c9c5513448e5886755263fc443"}