{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V4HFG3ELJFWIV64FQMCG3MLLAA","short_pith_number":"pith:V4HFG3EL","canonical_record":{"source":{"id":"2502.01205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T09:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"8b74a9fbf57c0789fab2d6944cb72f3265419f01a77081ad5bc54022859e2345","abstract_canon_sha256":"71b44f4560705e54b19e60c4ac644a9ea61bd94f43d7858650a12b52cde15876"},"schema_version":"1.0"},"canonical_sha256":"af0e536c8b496c8afb8583046db16b002f4177f63d673fd659e32980a16e1c82","source":{"kind":"arxiv","id":"2502.01205","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01205","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01205v1","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01205","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"V4HFG3ELJFWI","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"V4HFG3ELJFWIV64F","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"V4HFG3EL","created_at":"2026-07-05T10:08:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V4HFG3ELJFWIV64FQMCG3MLLAA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T09:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"8b74a9fbf57c0789fab2d6944cb72f3265419f01a77081ad5bc54022859e2345","abstract_canon_sha256":"71b44f4560705e54b19e60c4ac644a9ea61bd94f43d7858650a12b52cde15876"},"schema_version":"1.0"},"canonical_sha256":"af0e536c8b496c8afb8583046db16b002f4177f63d673fd659e32980a16e1c82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:44.248298Z","signature_b64":"HXiR+8EFA9woG0PJXLr4OApsfo/jPJoXfKVwShmWCW/dchm0UpaUt7bNEuE1TsE2eAhnyNWF8mN69gv2WGNDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af0e536c8b496c8afb8583046db16b002f4177f63d673fd659e32980a16e1c82","last_reissued_at":"2026-07-05T10:08:44.247827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:44.247827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01205","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":"2026-07-05T10:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZS8eTd66muCAzuW4rRp932qyVwc7Z75pn61/CNVtV8LcJePbdt5thFPvA37gu+h786dvOGKAg+xNUiLo5OdGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:51:31.598322Z"},"content_sha256":"bb2fac9018a7256df9db6736d69e22a4968472ba18392cfb71bdc34360d59b0b","schema_version":"1.0","event_id":"sha256:bb2fac9018a7256df9db6736d69e22a4968472ba18392cfb71bdc34360d59b0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V4HFG3ELJFWIV64FQMCG3MLLAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cassandra Ledins, Filip Ginter, Jenna Kanerva, Siiri K\\\"apyaho","submitted_at":"2025-02-03T09:55:31Z","abstract_excerpt":"Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality. This study evaluates the use of open-weight LLMs for OCR error correction in historical English and Finnish datasets. We explore various strategies, including parameter optimization, quantization, segment length effects, and text continuation methods. Our results demonstrate that while modern LLMs show promise in reducing character error rates (CER) in English, a practically useful performance for Finnish was not reached. Our findi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01205","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/2502.01205/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":"2026-07-05T10:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZQluUBERzs9J+u5vxSQG42mJd1lmJ+YOc2joQmHqyElTVzTMwQhoA6bCisIxAMGCrlwpjfEZEYMcohoe0nvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:51:31.598831Z"},"content_sha256":"3d4530afadc6c516bfb150ba1931972146435d7ec54ef380474014b2f8ae02f5","schema_version":"1.0","event_id":"sha256:3d4530afadc6c516bfb150ba1931972146435d7ec54ef380474014b2f8ae02f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/bundle.json","state_url":"https://pith.science/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/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":"2026-08-12T22:51:31Z","links":{"resolver":"https://pith.science/pith/V4HFG3ELJFWIV64FQMCG3MLLAA","bundle":"https://pith.science/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/bundle.json","state":"https://pith.science/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4HFG3ELJFWIV64FQMCG3MLLAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V4HFG3ELJFWIV64FQMCG3MLLAA","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":"71b44f4560705e54b19e60c4ac644a9ea61bd94f43d7858650a12b52cde15876","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T09:55:31Z","title_canon_sha256":"8b74a9fbf57c0789fab2d6944cb72f3265419f01a77081ad5bc54022859e2345"},"schema_version":"1.0","source":{"id":"2502.01205","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01205","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01205v1","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01205","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"V4HFG3ELJFWI","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"V4HFG3ELJFWIV64F","created_at":"2026-07-05T10:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"V4HFG3EL","created_at":"2026-07-05T10:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:3d4530afadc6c516bfb150ba1931972146435d7ec54ef380474014b2f8ae02f5","target":"graph","created_at":"2026-07-05T10:08:44Z","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/2502.01205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality. This study evaluates the use of open-weight LLMs for OCR error correction in historical English and Finnish datasets. We explore various strategies, including parameter optimization, quantization, segment length effects, and text continuation methods. Our results demonstrate that while modern LLMs show promise in reducing character error rates (CER) in English, a practically useful performance for Finnish was not reached. Our findi","authors_text":"Cassandra Ledins, Filip Ginter, Jenna Kanerva, Siiri K\\\"apyaho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T09:55:31Z","title":"OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01205","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:bb2fac9018a7256df9db6736d69e22a4968472ba18392cfb71bdc34360d59b0b","target":"record","created_at":"2026-07-05T10:08:44Z","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":"71b44f4560705e54b19e60c4ac644a9ea61bd94f43d7858650a12b52cde15876","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T09:55:31Z","title_canon_sha256":"8b74a9fbf57c0789fab2d6944cb72f3265419f01a77081ad5bc54022859e2345"},"schema_version":"1.0","source":{"id":"2502.01205","kind":"arxiv","version":1}},"canonical_sha256":"af0e536c8b496c8afb8583046db16b002f4177f63d673fd659e32980a16e1c82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af0e536c8b496c8afb8583046db16b002f4177f63d673fd659e32980a16e1c82","first_computed_at":"2026-07-05T10:08:44.247827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:44.247827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXiR+8EFA9woG0PJXLr4OApsfo/jPJoXfKVwShmWCW/dchm0UpaUt7bNEuE1TsE2eAhnyNWF8mN69gv2WGNDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:44.248298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01205","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb2fac9018a7256df9db6736d69e22a4968472ba18392cfb71bdc34360d59b0b","sha256:3d4530afadc6c516bfb150ba1931972146435d7ec54ef380474014b2f8ae02f5"],"state_sha256":"d09113ff5fb790bd90e56e4c3f46a19f81db6a258049710902b973d45c5805ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+MrKjQlw5yyeXDmPwSzVcjEoXkI0RKz5t6GiPtJOhEUEqPFpkNaORJGIjA8I05ylwB4UWVewv/6AQ+rNvF9Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:51:31.602135Z","bundle_sha256":"fa42080b7fa15b043214dfc8c3bee76dd7ff1982a7a052543b840ac5606f7130"}}