{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MBVEI2TRVL5UA7RJW4QQK25MKH","short_pith_number":"pith:MBVEI2TR","canonical_record":{"source":{"id":"2205.02543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T10:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"0e05ab859c20d705923ea8012a110c11361d03eb02e3f342c9f5c079af3624e3","abstract_canon_sha256":"f0d8532ddea69f0fa44163a1370567cc9d5c3653624a3c75f36643b224e8c337"},"schema_version":"1.0"},"canonical_sha256":"606a446a71aafb407e29b721056bac51e1b014c5c6d773263b96005af4985acb","source":{"kind":"arxiv","id":"2205.02543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02543","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02543v1","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02543","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"MBVEI2TRVL5U","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"MBVEI2TRVL5UA7RJ","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"MBVEI2TR","created_at":"2026-07-05T04:20:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MBVEI2TRVL5UA7RJW4QQK25MKH","target":"record","payload":{"canonical_record":{"source":{"id":"2205.02543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T10:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"0e05ab859c20d705923ea8012a110c11361d03eb02e3f342c9f5c079af3624e3","abstract_canon_sha256":"f0d8532ddea69f0fa44163a1370567cc9d5c3653624a3c75f36643b224e8c337"},"schema_version":"1.0"},"canonical_sha256":"606a446a71aafb407e29b721056bac51e1b014c5c6d773263b96005af4985acb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:38.467682Z","signature_b64":"OiHfvzdNzCxVzGx+QTRKCF/Nx4YsrgrB4BgIT4IkCn3WMMU4xvJGyElpAr2aj1yU0LISeYa2748zmfR2rGybDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606a446a71aafb407e29b721056bac51e1b014c5c6d773263b96005af4985acb","last_reissued_at":"2026-07-05T04:20:38.467261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:38.467261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.02543","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":"2026-07-05T04:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgtYnipKbt6jmdNcKoWWKeNGvFE+uEoI4ISoCDBnVD6v136IKcx19MfYxbdWvrsJ1StXG0Wde85DvZsxa/qkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:55:59.982736Z"},"content_sha256":"ea8294492088220bc3eb235af42d4c1b93569a5772cc6d9d358624dcb0da4b97","schema_version":"1.0","event_id":"sha256:ea8294492088220bc3eb235af42d4c1b93569a5772cc6d9d358624dcb0da4b97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MBVEI2TRVL5UA7RJW4QQK25MKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OCR Synthetic Benchmark Dataset for Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aravinth Bheemaraj, Deepak Kumar, Dhiraj Daga, Naresh Saini, Promodh Pinto, Saurabh Yadav, Srihari Nagaraj","submitted_at":"2022-05-05T10:07:57Z","abstract_excerpt":"We present the largest publicly available synthetic OCR benchmark dataset for Indic languages. The collection contains a total of 90k images and their ground truth for 23 Indic languages. OCR model validation in Indic languages require a good amount of diverse data to be processed in order to create a robust and reliable model. Generating such a huge amount of data would be difficult otherwise but with synthetic data, it becomes far easier. It can be of great importance to fields like Computer Vision or Image Processing where once an initial synthetic data is developed, model creation becomes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02543","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/2205.02543/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":"2026-07-05T04:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GF6DZ2hwMkobP/iTZVGbvBJZXrHfcqAetmwad/eBHi+c4UwvaFpdv8jVKxGX7j5lVnebpsQHntfdrkV5MMpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:55:59.983255Z"},"content_sha256":"221c678d7a45ac36dd0fedc20f080932658123c34bcead5a68b60efc968fcd26","schema_version":"1.0","event_id":"sha256:221c678d7a45ac36dd0fedc20f080932658123c34bcead5a68b60efc968fcd26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/bundle.json","state_url":"https://pith.science/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/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":"2026-08-13T04:56:00Z","links":{"resolver":"https://pith.science/pith/MBVEI2TRVL5UA7RJW4QQK25MKH","bundle":"https://pith.science/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/bundle.json","state":"https://pith.science/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBVEI2TRVL5UA7RJW4QQK25MKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MBVEI2TRVL5UA7RJW4QQK25MKH","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":"f0d8532ddea69f0fa44163a1370567cc9d5c3653624a3c75f36643b224e8c337","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T10:07:57Z","title_canon_sha256":"0e05ab859c20d705923ea8012a110c11361d03eb02e3f342c9f5c079af3624e3"},"schema_version":"1.0","source":{"id":"2205.02543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02543","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02543v1","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02543","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"MBVEI2TRVL5U","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"MBVEI2TRVL5UA7RJ","created_at":"2026-07-05T04:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"MBVEI2TR","created_at":"2026-07-05T04:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:221c678d7a45ac36dd0fedc20f080932658123c34bcead5a68b60efc968fcd26","target":"graph","created_at":"2026-07-05T04:20:38Z","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/2205.02543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the largest publicly available synthetic OCR benchmark dataset for Indic languages. The collection contains a total of 90k images and their ground truth for 23 Indic languages. OCR model validation in Indic languages require a good amount of diverse data to be processed in order to create a robust and reliable model. Generating such a huge amount of data would be difficult otherwise but with synthetic data, it becomes far easier. It can be of great importance to fields like Computer Vision or Image Processing where once an initial synthetic data is developed, model creation becomes ","authors_text":"Aravinth Bheemaraj, Deepak Kumar, Dhiraj Daga, Naresh Saini, Promodh Pinto, Saurabh Yadav, Srihari Nagaraj","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T10:07:57Z","title":"OCR Synthetic Benchmark Dataset for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02543","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:ea8294492088220bc3eb235af42d4c1b93569a5772cc6d9d358624dcb0da4b97","target":"record","created_at":"2026-07-05T04:20:38Z","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":"f0d8532ddea69f0fa44163a1370567cc9d5c3653624a3c75f36643b224e8c337","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T10:07:57Z","title_canon_sha256":"0e05ab859c20d705923ea8012a110c11361d03eb02e3f342c9f5c079af3624e3"},"schema_version":"1.0","source":{"id":"2205.02543","kind":"arxiv","version":1}},"canonical_sha256":"606a446a71aafb407e29b721056bac51e1b014c5c6d773263b96005af4985acb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"606a446a71aafb407e29b721056bac51e1b014c5c6d773263b96005af4985acb","first_computed_at":"2026-07-05T04:20:38.467261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:38.467261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OiHfvzdNzCxVzGx+QTRKCF/Nx4YsrgrB4BgIT4IkCn3WMMU4xvJGyElpAr2aj1yU0LISeYa2748zmfR2rGybDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:38.467682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea8294492088220bc3eb235af42d4c1b93569a5772cc6d9d358624dcb0da4b97","sha256:221c678d7a45ac36dd0fedc20f080932658123c34bcead5a68b60efc968fcd26"],"state_sha256":"59bf473594845e199337337ffce2ce15068eeca929a651cd0b21c24de813ce3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpE2cnnE0KUy3oezX7mBDSJ7zXv68zId/6/0xP7X0GOb9MM5VQssmH5gJ6XQyf5IMKqaX46+Zyq74PcMWcz5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:56:00.005159Z","bundle_sha256":"037e10da7db24803ccd36d657b6b780751940d7ddd13e21649359b2987ebcf8e"}}