{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y74JXN5GJVY27BQFZF4ZGJWW2C","short_pith_number":"pith:Y74JXN5G","canonical_record":{"source":{"id":"2409.04117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T08:35:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d2617265468b402d6e6c517548408d46ba20f7370ddd4043d0deeb20dac3610d","abstract_canon_sha256":"b4fc6dad77385644b34fd21c0b96f1460a616b30e1458e285d8edb77aa6157d1"},"schema_version":"1.0"},"canonical_sha256":"c7f89bb7a64d71af8605c9799326d6d08f1efe2a027748f3b5f507b45cff8330","source":{"kind":"arxiv","id":"2409.04117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04117","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04117v1","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04117","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y74JXN5GJVY2","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y74JXN5GJVY27BQF","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y74JXN5G","created_at":"2026-07-05T09:04:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y74JXN5GJVY27BQFZF4ZGJWW2C","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T08:35:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d2617265468b402d6e6c517548408d46ba20f7370ddd4043d0deeb20dac3610d","abstract_canon_sha256":"b4fc6dad77385644b34fd21c0b96f1460a616b30e1458e285d8edb77aa6157d1"},"schema_version":"1.0"},"canonical_sha256":"c7f89bb7a64d71af8605c9799326d6d08f1efe2a027748f3b5f507b45cff8330","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:01.766870Z","signature_b64":"x21kiW/oZLeHDoPEd6IrI9qNZwusj8rzmfZMqDWvuN1oPa1yP6zi/Io47Zy8EXFzJ+x/PJm0tANC3ncxeqoFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7f89bb7a64d71af8605c9799326d6d08f1efe2a027748f3b5f507b45cff8330","last_reissued_at":"2026-07-05T09:04:01.766438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:01.766438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04117","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":"2026-07-05T09:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPyOt1ALIn8Yplb/9XEqayytCeQrijd6zW8UW+H7B7KcUnWjCh01kKXTUntGJwLJOczLD74hGcv5VTyqmnmuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:12:48.416443Z"},"content_sha256":"49d7b195c7406c9d7ee9101a967115e9d3781e21bb116e6a90f66b9479c067e8","schema_version":"1.0","event_id":"sha256:49d7b195c7406c9d7ee9101a967115e9d3781e21bb116e6a90f66b9479c067e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y74JXN5GJVY27BQFZF4ZGJWW2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confidence-Aware Document OCR Error Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Arthur Hemmer, Jean-Marc Ogier, Micka\\\"el Coustaty, Nicola Bartolo","submitted_at":"2024-09-06T08:35:28Z","abstract_excerpt":"Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04117","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/2409.04117/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":"2026-07-05T09:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RocA9JTb4UJjmoiUkWX+X8u6WvA4Td/cuUF/mb174FTa2Oqrze1wSwYpWYd098NrgxhAJBM6mJQ0Tj5mE6cdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:12:48.417337Z"},"content_sha256":"00629121247bde3bb69724b11c7dfac3bb51419e92f7e3f3f1a0e644c5a64db4","schema_version":"1.0","event_id":"sha256:00629121247bde3bb69724b11c7dfac3bb51419e92f7e3f3f1a0e644c5a64db4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/bundle.json","state_url":"https://pith.science/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/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":"2026-08-19T11:12:48Z","links":{"resolver":"https://pith.science/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C","bundle":"https://pith.science/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/bundle.json","state":"https://pith.science/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y74JXN5GJVY27BQFZF4ZGJWW2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y74JXN5GJVY27BQFZF4ZGJWW2C","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":"b4fc6dad77385644b34fd21c0b96f1460a616b30e1458e285d8edb77aa6157d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T08:35:28Z","title_canon_sha256":"d2617265468b402d6e6c517548408d46ba20f7370ddd4043d0deeb20dac3610d"},"schema_version":"1.0","source":{"id":"2409.04117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04117","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04117v1","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04117","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y74JXN5GJVY2","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y74JXN5GJVY27BQF","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y74JXN5G","created_at":"2026-07-05T09:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:00629121247bde3bb69724b11c7dfac3bb51419e92f7e3f3f1a0e644c5a64db4","target":"graph","created_at":"2026-07-05T09:04:01Z","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/2409.04117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error","authors_text":"Arthur Hemmer, Jean-Marc Ogier, Micka\\\"el Coustaty, Nicola Bartolo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T08:35:28Z","title":"Confidence-Aware Document OCR Error Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04117","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":"sha256:49d7b195c7406c9d7ee9101a967115e9d3781e21bb116e6a90f66b9479c067e8","target":"record","created_at":"2026-07-05T09:04:01Z","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":"b4fc6dad77385644b34fd21c0b96f1460a616b30e1458e285d8edb77aa6157d1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T08:35:28Z","title_canon_sha256":"d2617265468b402d6e6c517548408d46ba20f7370ddd4043d0deeb20dac3610d"},"schema_version":"1.0","source":{"id":"2409.04117","kind":"arxiv","version":1}},"canonical_sha256":"c7f89bb7a64d71af8605c9799326d6d08f1efe2a027748f3b5f507b45cff8330","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7f89bb7a64d71af8605c9799326d6d08f1efe2a027748f3b5f507b45cff8330","first_computed_at":"2026-07-05T09:04:01.766438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:01.766438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x21kiW/oZLeHDoPEd6IrI9qNZwusj8rzmfZMqDWvuN1oPa1yP6zi/Io47Zy8EXFzJ+x/PJm0tANC3ncxeqoFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:01.766870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d7b195c7406c9d7ee9101a967115e9d3781e21bb116e6a90f66b9479c067e8","sha256:00629121247bde3bb69724b11c7dfac3bb51419e92f7e3f3f1a0e644c5a64db4"],"state_sha256":"7c8ca18493468fd99d62c13c913cf532a11be3f419f381952d4a77d34ec617ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IclhhWhgYx1CdjrkcCh1mm3K56HvfM5DQyq3DMW9GSPaMFhIftlqE9ttFnFT6kxTpABUhjGEka8Z20XBuyLIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:12:48.425510Z","bundle_sha256":"1864378211e346085882a80a7f71cd6a1cbf7f1561e8a56c55e42d5adad53579"}}