{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM","short_pith_number":"pith:AN7C3Y7U","canonical_record":{"source":{"id":"2205.06740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-13T16:19:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"750d0d9764e0d6fda8ed1a6b7cec4207601ee187d7b68092c6624230e52b486f","abstract_canon_sha256":"df9d617273293824d172cbbf5bab4d181a7401de18e097de8a1602c677f39345"},"schema_version":"1.0"},"canonical_sha256":"037e2de3f4cf6a48594dfe73a3a096230423ce96d590f6cbc5ebebece8132a9b","source":{"kind":"arxiv","id":"2205.06740","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06740","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06740v2","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06740","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"AN7C3Y7UZ5VE","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"AN7C3Y7UZ5VEQWKN","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"AN7C3Y7U","created_at":"2026-07-05T09:50:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.06740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-13T16:19:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"750d0d9764e0d6fda8ed1a6b7cec4207601ee187d7b68092c6624230e52b486f","abstract_canon_sha256":"df9d617273293824d172cbbf5bab4d181a7401de18e097de8a1602c677f39345"},"schema_version":"1.0"},"canonical_sha256":"037e2de3f4cf6a48594dfe73a3a096230423ce96d590f6cbc5ebebece8132a9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:42.438718Z","signature_b64":"7aFy4PdK3uAOKUNxzwzMNtNvXCoJ8k8hnginALZeL4gNEVCAVwv+UN/HqXvnWFz0riBTpbtGkNKBX2948L6tCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"037e2de3f4cf6a48594dfe73a3a096230423ce96d590f6cbc5ebebece8132a9b","last_reissued_at":"2026-07-05T09:50:42.438283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:42.438283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.06740","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNVK+9HSUGb1COWuUUq7FH0MEKlDG/zslJIVjZ6EHDawNqq7fFHqU9CRYf8/FDax0LrVvqchJED9LbguoLneBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:12:40.853542Z"},"content_sha256":"e74eb85f0bb26d895d377099b1ae28f234bf5a833b17b17cff73f7c91043badc","schema_version":"1.0","event_id":"sha256:e74eb85f0bb26d895d377099b1ae28f234bf5a833b17b17cff73f7c91043badc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Deployable OCR models for Indic languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ajoy Mondal, CV Jawahar, Minesh Mathew","submitted_at":"2022-05-13T16:19:21Z","abstract_excerpt":"Recognition of text on word or line images, without the need for sub-word segmentation has become the mainstream of research and development of text recognition for Indian languages. Modelling unsegmented sequences using Connectionist Temporal Classification (CTC) is the most commonly used approach for segmentation-free OCR. In this work we present a comprehensive empirical study of various neural network models that uses CTC for transcribing step-wise predictions in the neural network output to a Unicode sequence. The study is conducted for 13 Indian languages, using an internal dataset that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06740","kind":"arxiv","version":2},"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/2205.06740/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":"2026-07-05T09:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5Uy0fiR34eTcvRWnCsPbl+djMTjKAKq46240BuRavLHGLxjmffTATlvkFECTsQRnUHWmexMNXy12zNwier4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:12:40.853931Z"},"content_sha256":"7ab6a2b37b4442e3cfe8fb7d96ca97c0adc0a2e1525c67fd81de75885bc4c6a6","schema_version":"1.0","event_id":"sha256:7ab6a2b37b4442e3cfe8fb7d96ca97c0adc0a2e1525c67fd81de75885bc4c6a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/bundle.json","state_url":"https://pith.science/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/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":"2026-08-23T05:12:40Z","links":{"resolver":"https://pith.science/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM","bundle":"https://pith.science/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/bundle.json","state":"https://pith.science/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AN7C3Y7UZ5VEQWKN7ZZ2HIEWEM","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":"df9d617273293824d172cbbf5bab4d181a7401de18e097de8a1602c677f39345","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-13T16:19:21Z","title_canon_sha256":"750d0d9764e0d6fda8ed1a6b7cec4207601ee187d7b68092c6624230e52b486f"},"schema_version":"1.0","source":{"id":"2205.06740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06740","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06740v2","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06740","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"AN7C3Y7UZ5VE","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"AN7C3Y7UZ5VEQWKN","created_at":"2026-07-05T09:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"AN7C3Y7U","created_at":"2026-07-05T09:50:42Z"}],"graph_snapshots":[{"event_id":"sha256:7ab6a2b37b4442e3cfe8fb7d96ca97c0adc0a2e1525c67fd81de75885bc4c6a6","target":"graph","created_at":"2026-07-05T09:50:42Z","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/2205.06740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recognition of text on word or line images, without the need for sub-word segmentation has become the mainstream of research and development of text recognition for Indian languages. Modelling unsegmented sequences using Connectionist Temporal Classification (CTC) is the most commonly used approach for segmentation-free OCR. In this work we present a comprehensive empirical study of various neural network models that uses CTC for transcribing step-wise predictions in the neural network output to a Unicode sequence. The study is conducted for 13 Indian languages, using an internal dataset that ","authors_text":"Ajoy Mondal, CV Jawahar, Minesh Mathew","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-13T16:19:21Z","title":"Towards Deployable OCR models for Indic languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06740","kind":"arxiv","version":2},"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:e74eb85f0bb26d895d377099b1ae28f234bf5a833b17b17cff73f7c91043badc","target":"record","created_at":"2026-07-05T09:50:42Z","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":"df9d617273293824d172cbbf5bab4d181a7401de18e097de8a1602c677f39345","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-13T16:19:21Z","title_canon_sha256":"750d0d9764e0d6fda8ed1a6b7cec4207601ee187d7b68092c6624230e52b486f"},"schema_version":"1.0","source":{"id":"2205.06740","kind":"arxiv","version":2}},"canonical_sha256":"037e2de3f4cf6a48594dfe73a3a096230423ce96d590f6cbc5ebebece8132a9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"037e2de3f4cf6a48594dfe73a3a096230423ce96d590f6cbc5ebebece8132a9b","first_computed_at":"2026-07-05T09:50:42.438283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:42.438283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7aFy4PdK3uAOKUNxzwzMNtNvXCoJ8k8hnginALZeL4gNEVCAVwv+UN/HqXvnWFz0riBTpbtGkNKBX2948L6tCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:42.438718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.06740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e74eb85f0bb26d895d377099b1ae28f234bf5a833b17b17cff73f7c91043badc","sha256:7ab6a2b37b4442e3cfe8fb7d96ca97c0adc0a2e1525c67fd81de75885bc4c6a6"],"state_sha256":"9bf2f92a1699d4637dcad923089c519e55c95a826974db35d9ea3a27bb2806cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh3WfWjpN2stLBfA/doSA8UXuqAuOgzeeZez+n+n7Kq/eX/CzIwv4hVuOavMODb6kS9KmpnunIxg28ZQFZnDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T05:12:40.856844Z","bundle_sha256":"0c840eec2360a228b7192160988da9a6559924c6fd6d6a1de643acfa90c5a491"}}