{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IX4GE3P46FJHZ7MMTFZCQPTI2F","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":"9e4a54ca00a9b58ea8af39659a46c455f9beed811599b4873b95e63e24858749","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T23:20:01Z","title_canon_sha256":"6fae58cec5d695006b43d28c91e9fd057ae1ba91f7225f006fe01e5d0eca435d"},"schema_version":"1.0","source":{"id":"2412.20613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20613","created_at":"2026-07-05T09:55:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20613v1","created_at":"2026-07-05T09:55:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20613","created_at":"2026-07-05T09:55:19Z"},{"alias_kind":"pith_short_12","alias_value":"IX4GE3P46FJH","created_at":"2026-07-05T09:55:19Z"},{"alias_kind":"pith_short_16","alias_value":"IX4GE3P46FJHZ7MM","created_at":"2026-07-05T09:55:19Z"},{"alias_kind":"pith_short_8","alias_value":"IX4GE3P4","created_at":"2026-07-05T09:55:19Z"}],"graph_snapshots":[{"event_id":"sha256:a9de895d93afae73eaeda54dc1b448557ec07631b3ebe3ba25c099bd0d1a704b","target":"graph","created_at":"2026-07-05T09:55:19Z","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/2412.20613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct subtasks: (1) Recognition of text content itself and its basic visual attributes, (2)Semantic and Spatial Comprehension of ","authors_text":"Tao Wu, Wei Chen, Xiaojin Zhang, Xingyuan Xian, Yuhui Gao, Yulin Fei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T23:20:01Z","title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20613","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":"sha256:1f0bfbb6aa96c26ba3f83f2c3bbf3b2abec839922d78a6e26b9e0bebd7289b70","target":"record","created_at":"2026-07-05T09:55:19Z","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":"9e4a54ca00a9b58ea8af39659a46c455f9beed811599b4873b95e63e24858749","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T23:20:01Z","title_canon_sha256":"6fae58cec5d695006b43d28c91e9fd057ae1ba91f7225f006fe01e5d0eca435d"},"schema_version":"1.0","source":{"id":"2412.20613","kind":"arxiv","version":1}},"canonical_sha256":"45f8626dfcf1527cfd8c9972283e68d14efd843ae9baa2cecfd478c9389bbc47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f8626dfcf1527cfd8c9972283e68d14efd843ae9baa2cecfd478c9389bbc47","first_computed_at":"2026-07-05T09:55:19.786487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:19.786487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"phatmSwcyp/3R6WHipdcyWmlYiqQp+2Zko7Srwp0AG7taOP6l4qMVq11Wb2qdLOjE/jW/HvByx/MrZaxIho/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:19.786931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f0bfbb6aa96c26ba3f83f2c3bbf3b2abec839922d78a6e26b9e0bebd7289b70","sha256:a9de895d93afae73eaeda54dc1b448557ec07631b3ebe3ba25c099bd0d1a704b"],"state_sha256":"c0f9bd8f6d612ed900b9c122bbef8c212cef889d53b91e98d0118721784b7575"}