{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RALQY4OCSY4OTEYMLIG6M7MDJ4","short_pith_number":"pith:RALQY4OC","canonical_record":{"source":{"id":"2502.06445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"61d04123c16567882afd0a85a1e6d507f172928e1b1c177fcfd6baed97d7527f","abstract_canon_sha256":"26d0e97b4f916fc439c097865a536309f2f73a7d21bf50be4f36ce88f8fd9ffa"},"schema_version":"1.0"},"canonical_sha256":"88170c71c29638e9930c5a0de67d834f317dc77ea0ffe7278b95fe68e8515f7a","source":{"kind":"arxiv","id":"2502.06445","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RALQY4OCSY4OTEYMLIG6M7MDJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T13:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"61d04123c16567882afd0a85a1e6d507f172928e1b1c177fcfd6baed97d7527f","abstract_canon_sha256":"26d0e97b4f916fc439c097865a536309f2f73a7d21bf50be4f36ce88f8fd9ffa"},"schema_version":"1.0"},"canonical_sha256":"88170c71c29638e9930c5a0de67d834f317dc77ea0ffe7278b95fe68e8515f7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:06.762773Z","signature_b64":"1kg3b2dcExCTqBrVCzuKYLEtP0imuF1KgbrO5aYhn1VodfSUw01TLYgtk5Y5+X+HrFYVP2K13v22cJBELstsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88170c71c29638e9930c5a0de67d834f317dc77ea0ffe7278b95fe68e8515f7a","last_reissued_at":"2026-07-05T10:12:06.762283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:06.762283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06445","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rGPhv0oJMlF3P12vmFEkGPwzpVEDcJx3niJaKYkv8HyRWWXpbby/Tt3nq2V8FIvuVW7Eu2x5Lobh1pDazZYNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:04:08.615790Z"},"content_sha256":"02564d9b58ce364f866f23bdd404b5134c86385b2f31bcc6ca4001e1dd16e3bc","schema_version":"1.0","event_id":"sha256:02564d9b58ce364f866f23bdd404b5134c86385b2f31bcc6ca4001e1dd16e3bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RALQY4OCSY4OTEYMLIG6M7MDJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashish Choithani, Ashutosh Trivedi, Augustya Sharma, Sankalp Nagaonkar","submitted_at":"2025-02-10T13:20:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06445","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/2502.06445/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUbvkUbPHDLt6QXXuvVT4gORkr5d5BTEVWyTdN/1h6Okg9Sm0aezA7gTTgAz2Y176B2Kbk+G1Hvat06AEbsOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:04:08.616335Z"},"content_sha256":"8810751f0696b11e6fd990cb34a310af6d27d10a6a5fc3c10923242fb0fc9d4b","schema_version":"1.0","event_id":"sha256:8810751f0696b11e6fd990cb34a310af6d27d10a6a5fc3c10923242fb0fc9d4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/bundle.json","state_url":"https://pith.science/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T11:04:08Z","links":{"resolver":"https://pith.science/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4","bundle":"https://pith.science/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/bundle.json","state":"https://pith.science/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RALQY4OCSY4OTEYMLIG6M7MDJ4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89Jr0GNNyBGKbYfWlHwCEUDFUkAMk7CHfx/G0cRECLNXoIfvP+p3aUnOc0laB95nORF4CjdbAfAxi9nxgS2+AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:04:08.646933Z","bundle_sha256":"096fd3d2b673b3b03dac5a8eae683e42fdeb505ed8b99cb64b92cead1d9d1099"}}