{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ILYOEDBPYHU2VOY7P5NPW4X7ZY","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":"55edef810ac6632fff270987d831935f61657fb30662cdb536fbe7e9be4aca2e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:21:26Z","title_canon_sha256":"c9f3a1a70fdf4ee18670e9369e55d7fa045070a84aec4a41a4731538c2c27476"},"schema_version":"1.0","source":{"id":"2112.04888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04888","created_at":"2026-07-05T03:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04888v1","created_at":"2026-07-05T03:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04888","created_at":"2026-07-05T03:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"ILYOEDBPYHU2","created_at":"2026-07-05T03:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"ILYOEDBPYHU2VOY7","created_at":"2026-07-05T03:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"ILYOEDBP","created_at":"2026-07-05T03:39:26Z"}],"graph_snapshots":[{"event_id":"sha256:9d56ec72c5276845a45c6676f369b9d4022104002d7b9391e5a77f3586fd4a12","target":"graph","created_at":"2026-07-05T03:39:26Z","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/2112.04888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 2,000+ videos with more than 1,750,000+ frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 30+ open categories with a wide selection of various scenarios, e.g., Life Vlog, Driving, Movie, etc. Thirdly, abundant text types annotation (i.e., title, caption or","authors_text":"Debing Zhang, Hong Zhou, Jiahong Li, Sibo Wang, Weijia Wu, Yejun Tang, Yuanqiang Cai, Zhuang Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:21:26Z","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04888","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":"sha256:8b3bbec4a8d6850f87e1813b216a6057f04125989daf2321885502dbf4e25352","target":"record","created_at":"2026-07-05T03:39:26Z","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":"55edef810ac6632fff270987d831935f61657fb30662cdb536fbe7e9be4aca2e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-09T13:21:26Z","title_canon_sha256":"c9f3a1a70fdf4ee18670e9369e55d7fa045070a84aec4a41a4731538c2c27476"},"schema_version":"1.0","source":{"id":"2112.04888","kind":"arxiv","version":1}},"canonical_sha256":"42f0e20c2fc1e9aabb1f7f5afb72ffce28d6aeea4e2f89daea2e4bbc86d4885a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42f0e20c2fc1e9aabb1f7f5afb72ffce28d6aeea4e2f89daea2e4bbc86d4885a","first_computed_at":"2026-07-05T03:39:26.683626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:26.683626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c2TErhHP8kZN+CMpPEiwl8NoWNipmPx9ybYbQKORReBoiCMGxPxh4LRQNaLAuERdfoY9UEdjz0yRIqIY8xhPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:26.684043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b3bbec4a8d6850f87e1813b216a6057f04125989daf2321885502dbf4e25352","sha256:9d56ec72c5276845a45c6676f369b9d4022104002d7b9391e5a77f3586fd4a12"],"state_sha256":"3138c1465a32cb61639bd4273401424dc0d269c4ca2059f8bf37c86aea2146ba"}