{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NRNX2MYOMQZXXQKGRHTMWQLBQO","short_pith_number":"pith:NRNX2MYO","canonical_record":{"source":{"id":"2501.11623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T17:46:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"91f102fbe9025750a55db5e46ec8fd8ed6095ffb0c8407dec1afd5973b8c2fa7","abstract_canon_sha256":"faae86322f378083314c82cf6fd0afb6e63b2e41d0de73f90153c3b566a8358e"},"schema_version":"1.0"},"canonical_sha256":"6c5b7d330e64337bc14689e6cb4161839ddf6f3f08d748ed6b738043403cdaed","source":{"kind":"arxiv","id":"2501.11623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11623","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11623v1","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11623","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"NRNX2MYOMQZX","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"NRNX2MYOMQZXXQKG","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"NRNX2MYO","created_at":"2026-07-05T10:03:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NRNX2MYOMQZXXQKGRHTMWQLBQO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T17:46:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"91f102fbe9025750a55db5e46ec8fd8ed6095ffb0c8407dec1afd5973b8c2fa7","abstract_canon_sha256":"faae86322f378083314c82cf6fd0afb6e63b2e41d0de73f90153c3b566a8358e"},"schema_version":"1.0"},"canonical_sha256":"6c5b7d330e64337bc14689e6cb4161839ddf6f3f08d748ed6b738043403cdaed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:11.678362Z","signature_b64":"Y9Lc91snaxAM6GhmjUJNnbHdWF4pgU0eQ5YNa+oLD4WyVMtYfu2v8Ks7M0xzfdhbZrV/TO0aK8AMZ6eyGhLaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c5b7d330e64337bc14689e6cb4161839ddf6f3f08d748ed6b738043403cdaed","last_reissued_at":"2026-07-05T10:03:11.677959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:11.677959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11623","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":"2026-07-05T10:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXhe8rlrAc7qhO4lZuYMVe2HHGMlNah1d+Ug05mDCOuMwZwz9ua4gooTwAkTAIhWJMa1G2BGvoIIpg3HZlT4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:46:01.531120Z"},"content_sha256":"d595bd8f39cf9e3a89467f62f58335bda1163b16581d2aa2e9663f78f6fa1a94","schema_version":"1.0","event_id":"sha256:d595bd8f39cf9e3a89467f62f58335bda1163b16581d2aa2e9663f78f6fa1a94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NRNX2MYOMQZXXQKGRHTMWQLBQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hugues Bersini, Julien Baudru, Seorin Kim, Vincent Ginis, Wouter Ryckbosch","submitted_at":"2025-01-20T17:46:12Z","abstract_excerpt":"We explore the ability of two LLMs -- GPT-4o and Claude Sonnet 3.5 -- to transcribe historical handwritten documents in a tabular format and compare their performance to traditional OCR/HTR systems: EasyOCR, Keras, Pytesseract, and TrOCR. Considering the tabular form of the data, two types of experiments are executed: one where the images are split line by line and the other where the entire scan is used as input. Based on CER and BLEU, we demonstrate that LLMs outperform the conventional OCR/HTR methods. Moreover, we also compare the evaluated CER and BLEU scores to human evaluations to bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11623","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/2501.11623/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":"2026-07-05T10:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BD/DrgjFVeq+I2pbtpJarIcN+yt9b2BGABsNv5qhMbauAxcBlur+9aBs0lf/y+qnrXFLtFa666NL37m5gd3gCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:46:01.531623Z"},"content_sha256":"9b8c1d4ee9cce3563d9e02cc1417b95264e47e876541cd4ab1df51f06f28e8e9","schema_version":"1.0","event_id":"sha256:9b8c1d4ee9cce3563d9e02cc1417b95264e47e876541cd4ab1df51f06f28e8e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/bundle.json","state_url":"https://pith.science/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/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":"2026-08-11T10:46:01Z","links":{"resolver":"https://pith.science/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO","bundle":"https://pith.science/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/bundle.json","state":"https://pith.science/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRNX2MYOMQZXXQKGRHTMWQLBQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NRNX2MYOMQZXXQKGRHTMWQLBQO","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":"faae86322f378083314c82cf6fd0afb6e63b2e41d0de73f90153c3b566a8358e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T17:46:12Z","title_canon_sha256":"91f102fbe9025750a55db5e46ec8fd8ed6095ffb0c8407dec1afd5973b8c2fa7"},"schema_version":"1.0","source":{"id":"2501.11623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11623","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11623v1","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11623","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"NRNX2MYOMQZX","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"NRNX2MYOMQZXXQKG","created_at":"2026-07-05T10:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"NRNX2MYO","created_at":"2026-07-05T10:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:9b8c1d4ee9cce3563d9e02cc1417b95264e47e876541cd4ab1df51f06f28e8e9","target":"graph","created_at":"2026-07-05T10:03:11Z","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/2501.11623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the ability of two LLMs -- GPT-4o and Claude Sonnet 3.5 -- to transcribe historical handwritten documents in a tabular format and compare their performance to traditional OCR/HTR systems: EasyOCR, Keras, Pytesseract, and TrOCR. Considering the tabular form of the data, two types of experiments are executed: one where the images are split line by line and the other where the entire scan is used as input. Based on CER and BLEU, we demonstrate that LLMs outperform the conventional OCR/HTR methods. Moreover, we also compare the evaluated CER and BLEU scores to human evaluations to bette","authors_text":"Hugues Bersini, Julien Baudru, Seorin Kim, Vincent Ginis, Wouter Ryckbosch","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T17:46:12Z","title":"Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11623","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:d595bd8f39cf9e3a89467f62f58335bda1163b16581d2aa2e9663f78f6fa1a94","target":"record","created_at":"2026-07-05T10:03:11Z","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":"faae86322f378083314c82cf6fd0afb6e63b2e41d0de73f90153c3b566a8358e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T17:46:12Z","title_canon_sha256":"91f102fbe9025750a55db5e46ec8fd8ed6095ffb0c8407dec1afd5973b8c2fa7"},"schema_version":"1.0","source":{"id":"2501.11623","kind":"arxiv","version":1}},"canonical_sha256":"6c5b7d330e64337bc14689e6cb4161839ddf6f3f08d748ed6b738043403cdaed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c5b7d330e64337bc14689e6cb4161839ddf6f3f08d748ed6b738043403cdaed","first_computed_at":"2026-07-05T10:03:11.677959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:11.677959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y9Lc91snaxAM6GhmjUJNnbHdWF4pgU0eQ5YNa+oLD4WyVMtYfu2v8Ks7M0xzfdhbZrV/TO0aK8AMZ6eyGhLaBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:11.678362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d595bd8f39cf9e3a89467f62f58335bda1163b16581d2aa2e9663f78f6fa1a94","sha256:9b8c1d4ee9cce3563d9e02cc1417b95264e47e876541cd4ab1df51f06f28e8e9"],"state_sha256":"b30f917b65f41dc4f2da941d1ee6b44b877c792e46f88647da635c998079dd69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pf52mp5SD01k5cRU/QYXAnGiJ/DK8PP+n/gTWYVQ/0s7op1/jMxKfvwPj2chOi7fXxCSSL9pYCQWXfA2JOSPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:46:01.536361Z","bundle_sha256":"0afd4b1d24f49f6a903f8519cb183a576a2c4423242ea94655bc75fcbfbfd626"}}