{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RALQY4OCSY4OTEYMLIG6M7MDJ4","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":"26d0e97b4f916fc439c097865a536309f2f73a7d21bf50be4f36ce88f8fd9ffa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:20:19Z","title_canon_sha256":"61d04123c16567882afd0a85a1e6d507f172928e1b1c177fcfd6baed97d7527f"},"schema_version":"1.0","source":{"id":"2502.06445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06445","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06445v1","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06445","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"RALQY4OCSY4O","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"RALQY4OCSY4OTEYM","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"RALQY4OC","created_at":"2026-07-05T10:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:8810751f0696b11e6fd990cb34a310af6d27d10a6a5fc3c10923242fb0fc9d4b","target":"graph","created_at":"2026-07-05T10:12:06Z","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/2502.06445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments. We present a curated dataset containing 1,477 manually annotated frames spanning diverse domains, including code editors, news broadcasts, YouTube videos, and advertisements. Three state of the art VLMs - Claude-3, Gemini-1.5, and GPT-4o are benchmarked against traditional OCR systems such as EasyOCR and RapidOCR. Evaluation metrics include Word Error Rate (WER), Character Error Rate (CER), and Accuracy. Our results highlight th","authors_text":"Ashish Choithani, Ashutosh Trivedi, Augustya Sharma, Sankalp Nagaonkar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:20:19Z","title":"Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06445","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":"sha256:02564d9b58ce364f866f23bdd404b5134c86385b2f31bcc6ca4001e1dd16e3bc","target":"record","created_at":"2026-07-05T10:12:06Z","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":"26d0e97b4f916fc439c097865a536309f2f73a7d21bf50be4f36ce88f8fd9ffa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:20:19Z","title_canon_sha256":"61d04123c16567882afd0a85a1e6d507f172928e1b1c177fcfd6baed97d7527f"},"schema_version":"1.0","source":{"id":"2502.06445","kind":"arxiv","version":1}},"canonical_sha256":"88170c71c29638e9930c5a0de67d834f317dc77ea0ffe7278b95fe68e8515f7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88170c71c29638e9930c5a0de67d834f317dc77ea0ffe7278b95fe68e8515f7a","first_computed_at":"2026-07-05T10:12:06.762283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:06.762283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1kg3b2dcExCTqBrVCzuKYLEtP0imuF1KgbrO5aYhn1VodfSUw01TLYgtk5Y5+X+HrFYVP2K13v22cJBELstsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:06.762773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02564d9b58ce364f866f23bdd404b5134c86385b2f31bcc6ca4001e1dd16e3bc","sha256:8810751f0696b11e6fd990cb34a310af6d27d10a6a5fc3c10923242fb0fc9d4b"],"state_sha256":"52e6530f19119bf4d26bf2f6ca87f928e8b671343cf8508544ae31293624de08"}