{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IX4GE3P46FJHZ7MMTFZCQPTI2F","short_pith_number":"pith:IX4GE3P4","schema_version":"1.0","canonical_sha256":"45f8626dfcf1527cfd8c9972283e68d14efd843ae9baa2cecfd478c9389bbc47","source":{"kind":"arxiv","id":"2412.20613","version":1},"attestation_state":"computed","paper":{"title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Wu, Wei Chen, Xiaojin Zhang, Xingyuan Xian, Yuhui Gao, Yulin Fei","submitted_at":"2024-12-29T23:20:01Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.20613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T23:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"6fae58cec5d695006b43d28c91e9fd057ae1ba91f7225f006fe01e5d0eca435d","abstract_canon_sha256":"9e4a54ca00a9b58ea8af39659a46c455f9beed811599b4873b95e63e24858749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:19.786931Z","signature_b64":"phatmSwcyp/3R6WHipdcyWmlYiqQp+2Zko7Srwp0AG7taOP6l4qMVq11Wb2qdLOjE/jW/HvByx/MrZaxIho/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f8626dfcf1527cfd8c9972283e68d14efd843ae9baa2cecfd478c9389bbc47","last_reissued_at":"2026-07-05T09:55:19.786487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:19.786487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tao Wu, Wei Chen, Xiaojin Zhang, Xingyuan Xian, Yuhui Gao, Yulin Fei","submitted_at":"2024-12-29T23:20:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20613","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.20613/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.20613","created_at":"2026-07-05T09:55:19.786545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20613v1","created_at":"2026-07-05T09:55:19.786545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20613","created_at":"2026-07-05T09:55:19.786545+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX4GE3P46FJH","created_at":"2026-07-05T09:55:19.786545+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX4GE3P46FJHZ7MM","created_at":"2026-07-05T09:55:19.786545+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX4GE3P4","created_at":"2026-07-05T09:55:19.786545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F","json":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F.json","graph_json":"https://pith.science/api/pith-number/IX4GE3P46FJHZ7MMTFZCQPTI2F/graph.json","events_json":"https://pith.science/api/pith-number/IX4GE3P46FJHZ7MMTFZCQPTI2F/events.json","paper":"https://pith.science/paper/IX4GE3P4"},"agent_actions":{"view_html":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F","download_json":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F.json","view_paper":"https://pith.science/paper/IX4GE3P4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20613&json=true","fetch_graph":"https://pith.science/api/pith-number/IX4GE3P46FJHZ7MMTFZCQPTI2F/graph.json","fetch_events":"https://pith.science/api/pith-number/IX4GE3P46FJHZ7MMTFZCQPTI2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F/action/storage_attestation","attest_author":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F/action/author_attestation","sign_citation":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F/action/citation_signature","submit_replication":"https://pith.science/pith/IX4GE3P46FJHZ7MMTFZCQPTI2F/action/replication_record"}},"created_at":"2026-07-05T09:55:19.786545+00:00","updated_at":"2026-07-05T09:55:19.786545+00:00"}