{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S234H7OMKKWHXIOMUYHUQWMV2Y","short_pith_number":"pith:S234H7OM","canonical_record":{"source":{"id":"2408.02253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T05:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"c49facd589bbb6b72dcbb0536481f7a966f43526757ec8d61604aaeaa66787b3","abstract_canon_sha256":"e910a17082b0d144479a2ab21480aeb18b00767aaa90c560f408eded3e0fe251"},"schema_version":"1.0"},"canonical_sha256":"96b7c3fdcc52ac7ba1cca60f485995d6190390fda8580d3a0b82d30564eb4c55","source":{"kind":"arxiv","id":"2408.02253","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02253","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02253v2","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02253","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"S234H7OMKKWH","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"S234H7OMKKWHXIOM","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"S234H7OM","created_at":"2026-07-05T08:54:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S234H7OMKKWHXIOMUYHUQWMV2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2408.02253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T05:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"c49facd589bbb6b72dcbb0536481f7a966f43526757ec8d61604aaeaa66787b3","abstract_canon_sha256":"e910a17082b0d144479a2ab21480aeb18b00767aaa90c560f408eded3e0fe251"},"schema_version":"1.0"},"canonical_sha256":"96b7c3fdcc52ac7ba1cca60f485995d6190390fda8580d3a0b82d30564eb4c55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:55.009489Z","signature_b64":"8MFjffJEyCw5r3vCgRovh1/FyZrPZqLKSQyrG28fqZv8aQs9g0e2MJokUeYZiSg8t7D/LfsyztOm7E5xZx7LDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96b7c3fdcc52ac7ba1cca60f485995d6190390fda8580d3a0b82d30564eb4c55","last_reissued_at":"2026-07-05T08:54:55.009071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:55.009071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.02253","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":"2026-07-05T08:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjwT8nEcD/XStoTTR1Fc+V8Jv932tZEyqsJE2MgMSgq0qOIzKo0Nw6AdwjqvhVPAZmQ7pH5O9kz6SHwtgA6YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:17:08.034172Z"},"content_sha256":"99beda8990ed697f6a32ad44ec66c2056f62cf9d154276764aba7de0acb95a78","schema_version":"1.0","event_id":"sha256:99beda8990ed697f6a32ad44ec66c2056f62cf9d154276764aba7de0acb95a78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S234H7OMKKWHXIOMUYHUQWMV2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek Greene, Shuhao Guan","submitted_at":"2024-08-05T05:56:37Z","abstract_excerpt":"This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02253","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/2408.02253/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":"2026-07-05T08:54:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdJrumcqj5ARCvHQ8yeO4S1D/FQqXDJO0xbHtfmctUVMdAGK+y+qKhU6UsjnHkaHvgR12xuvC9meb6LdaUnqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:17:08.034674Z"},"content_sha256":"cd2696c877031cd03f8e70049e5fdecd583ad8596aa0ceb1b3b0a2eceedb1980","schema_version":"1.0","event_id":"sha256:cd2696c877031cd03f8e70049e5fdecd583ad8596aa0ceb1b3b0a2eceedb1980"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/bundle.json","state_url":"https://pith.science/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/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":"2026-08-23T10:17:08Z","links":{"resolver":"https://pith.science/pith/S234H7OMKKWHXIOMUYHUQWMV2Y","bundle":"https://pith.science/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/bundle.json","state":"https://pith.science/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S234H7OMKKWHXIOMUYHUQWMV2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S234H7OMKKWHXIOMUYHUQWMV2Y","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":"e910a17082b0d144479a2ab21480aeb18b00767aaa90c560f408eded3e0fe251","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T05:56:37Z","title_canon_sha256":"c49facd589bbb6b72dcbb0536481f7a966f43526757ec8d61604aaeaa66787b3"},"schema_version":"1.0","source":{"id":"2408.02253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02253","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02253v2","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02253","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_12","alias_value":"S234H7OMKKWH","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_16","alias_value":"S234H7OMKKWHXIOM","created_at":"2026-07-05T08:54:55Z"},{"alias_kind":"pith_short_8","alias_value":"S234H7OM","created_at":"2026-07-05T08:54:55Z"}],"graph_snapshots":[{"event_id":"sha256:cd2696c877031cd03f8e70049e5fdecd583ad8596aa0ceb1b3b0a2eceedb1980","target":"graph","created_at":"2026-07-05T08:54:55Z","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/2408.02253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) wit","authors_text":"Derek Greene, Shuhao Guan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T05:56:37Z","title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02253","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":"sha256:99beda8990ed697f6a32ad44ec66c2056f62cf9d154276764aba7de0acb95a78","target":"record","created_at":"2026-07-05T08:54:55Z","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":"e910a17082b0d144479a2ab21480aeb18b00767aaa90c560f408eded3e0fe251","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-05T05:56:37Z","title_canon_sha256":"c49facd589bbb6b72dcbb0536481f7a966f43526757ec8d61604aaeaa66787b3"},"schema_version":"1.0","source":{"id":"2408.02253","kind":"arxiv","version":2}},"canonical_sha256":"96b7c3fdcc52ac7ba1cca60f485995d6190390fda8580d3a0b82d30564eb4c55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96b7c3fdcc52ac7ba1cca60f485995d6190390fda8580d3a0b82d30564eb4c55","first_computed_at":"2026-07-05T08:54:55.009071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:55.009071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8MFjffJEyCw5r3vCgRovh1/FyZrPZqLKSQyrG28fqZv8aQs9g0e2MJokUeYZiSg8t7D/LfsyztOm7E5xZx7LDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:55.009489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99beda8990ed697f6a32ad44ec66c2056f62cf9d154276764aba7de0acb95a78","sha256:cd2696c877031cd03f8e70049e5fdecd583ad8596aa0ceb1b3b0a2eceedb1980"],"state_sha256":"9a2a31155ded707834e82b5231c886ca7c0098d9af438b813624da6d76d70227"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrYMaT2PyAmhsVeFYVB30kvD9LvmknNCi8HdvwfDkjbDzHij1UUsY/vEWqbew7Tb4k4Ns+iRb6JkPgtPtpboCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:17:08.039648Z","bundle_sha256":"e9c6e4b002af9503580729b296893e098fbacdbe63d572d2e44e01e395896590"}}