{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JO3DLEV6T3S22CIRK6N7KBZEME","short_pith_number":"pith:JO3DLEV6","canonical_record":{"source":{"id":"2501.08442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T21:21:39Z","cross_cats_sorted":[],"title_canon_sha256":"6ede401ca3f08df95aaa5472651941ec86f8f0e99633e05970659358aa85604c","abstract_canon_sha256":"d48adb0396a93f30ded6f035a8e6053a50300bb55575d9aabb4c84791d9cfc49"},"schema_version":"1.0"},"canonical_sha256":"4bb63592be9ee5ad0911579bf50724611e977fc93db0066fb13a348744be958c","source":{"kind":"arxiv","id":"2501.08442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08442","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08442v1","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08442","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"JO3DLEV6T3S2","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"JO3DLEV6T3S22CIR","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"JO3DLEV6","created_at":"2026-07-05T10:01:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JO3DLEV6T3S22CIRK6N7KBZEME","target":"record","payload":{"canonical_record":{"source":{"id":"2501.08442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T21:21:39Z","cross_cats_sorted":[],"title_canon_sha256":"6ede401ca3f08df95aaa5472651941ec86f8f0e99633e05970659358aa85604c","abstract_canon_sha256":"d48adb0396a93f30ded6f035a8e6053a50300bb55575d9aabb4c84791d9cfc49"},"schema_version":"1.0"},"canonical_sha256":"4bb63592be9ee5ad0911579bf50724611e977fc93db0066fb13a348744be958c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:02.646104Z","signature_b64":"8+lTX/8a+/6o0weY4sD5lyQOaGHsD7ozIzBCL5xoJh/hgIVmIS0SyFTXKucWb70NKnTN0/WZVm23ID80xO+EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb63592be9ee5ad0911579bf50724611e977fc93db0066fb13a348744be958c","last_reissued_at":"2026-07-05T10:01:02.645433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:02.645433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.08442","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":"2026-07-05T10:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NtmzpLiz1BGIF2OVIBqTMaZDJ9KY5B6zeurnLvSzrtfIQ6xQuA59AbKnovZY2x2kNy9le9dQUpsInipKXK72CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:55:37.181734Z"},"content_sha256":"41e4dc0213a221b82f0f060be4ab6747c40c7c167d171ad42b9df34814b381d9","schema_version":"1.0","event_id":"sha256:41e4dc0213a221b82f0f060be4ab6747c40c7c167d171ad42b9df34814b381d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JO3DLEV6T3S22CIRK6N7KBZEME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jochre 3 and the Yiddish OCR corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amber Clooney, Assaf Urieli, Grisha Leyfer, Michelle Sigiel","submitted_at":"2025-01-14T21:21:39Z","abstract_excerpt":"We describe the construction of a publicly available Yiddish OCR Corpus, and describe and evaluate the open source OCR tool suite Jochre 3, including an Alto editor for corpus annotation, OCR software for Alto OCR layer generation, and a customizable OCR search engine. The current version of the Yiddish OCR corpus contains 658 pages, 186K tokens and 840K glyphs. The Jochre 3 OCR tool uses various fine-tuned YOLOv8 models for top-down page layout analysis, and a custom CNN network for glyph recognition. It attains a CER of 1.5% on our test corpus, far out-performing all other existing public mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08442","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/2501.08442/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":"2026-07-05T10:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0iAkLSRVLexTyci0693eGje0L9MmeoBU+gSmZd3uD/80YnaGnZLFs5fsILEBGkk6pe8Jkm0SenuuYMm4vUkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:55:37.182266Z"},"content_sha256":"ca698089a9fbfe41101ead1e15a855d0bdc2d025eac04c1c2199f2274ba4347e","schema_version":"1.0","event_id":"sha256:ca698089a9fbfe41101ead1e15a855d0bdc2d025eac04c1c2199f2274ba4347e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JO3DLEV6T3S22CIRK6N7KBZEME/bundle.json","state_url":"https://pith.science/pith/JO3DLEV6T3S22CIRK6N7KBZEME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JO3DLEV6T3S22CIRK6N7KBZEME/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":"2026-08-09T02:55:37Z","links":{"resolver":"https://pith.science/pith/JO3DLEV6T3S22CIRK6N7KBZEME","bundle":"https://pith.science/pith/JO3DLEV6T3S22CIRK6N7KBZEME/bundle.json","state":"https://pith.science/pith/JO3DLEV6T3S22CIRK6N7KBZEME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JO3DLEV6T3S22CIRK6N7KBZEME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JO3DLEV6T3S22CIRK6N7KBZEME","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":"d48adb0396a93f30ded6f035a8e6053a50300bb55575d9aabb4c84791d9cfc49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T21:21:39Z","title_canon_sha256":"6ede401ca3f08df95aaa5472651941ec86f8f0e99633e05970659358aa85604c"},"schema_version":"1.0","source":{"id":"2501.08442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08442","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08442v1","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08442","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"JO3DLEV6T3S2","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"JO3DLEV6T3S22CIR","created_at":"2026-07-05T10:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"JO3DLEV6","created_at":"2026-07-05T10:01:02Z"}],"graph_snapshots":[{"event_id":"sha256:ca698089a9fbfe41101ead1e15a855d0bdc2d025eac04c1c2199f2274ba4347e","target":"graph","created_at":"2026-07-05T10:01:02Z","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/2501.08442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe the construction of a publicly available Yiddish OCR Corpus, and describe and evaluate the open source OCR tool suite Jochre 3, including an Alto editor for corpus annotation, OCR software for Alto OCR layer generation, and a customizable OCR search engine. The current version of the Yiddish OCR corpus contains 658 pages, 186K tokens and 840K glyphs. The Jochre 3 OCR tool uses various fine-tuned YOLOv8 models for top-down page layout analysis, and a custom CNN network for glyph recognition. It attains a CER of 1.5% on our test corpus, far out-performing all other existing public mo","authors_text":"Amber Clooney, Assaf Urieli, Grisha Leyfer, Michelle Sigiel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T21:21:39Z","title":"Jochre 3 and the Yiddish OCR corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08442","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":"sha256:41e4dc0213a221b82f0f060be4ab6747c40c7c167d171ad42b9df34814b381d9","target":"record","created_at":"2026-07-05T10:01:02Z","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":"d48adb0396a93f30ded6f035a8e6053a50300bb55575d9aabb4c84791d9cfc49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T21:21:39Z","title_canon_sha256":"6ede401ca3f08df95aaa5472651941ec86f8f0e99633e05970659358aa85604c"},"schema_version":"1.0","source":{"id":"2501.08442","kind":"arxiv","version":1}},"canonical_sha256":"4bb63592be9ee5ad0911579bf50724611e977fc93db0066fb13a348744be958c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bb63592be9ee5ad0911579bf50724611e977fc93db0066fb13a348744be958c","first_computed_at":"2026-07-05T10:01:02.645433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:02.645433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+lTX/8a+/6o0weY4sD5lyQOaGHsD7ozIzBCL5xoJh/hgIVmIS0SyFTXKucWb70NKnTN0/WZVm23ID80xO+EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:02.646104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e4dc0213a221b82f0f060be4ab6747c40c7c167d171ad42b9df34814b381d9","sha256:ca698089a9fbfe41101ead1e15a855d0bdc2d025eac04c1c2199f2274ba4347e"],"state_sha256":"69c2730fe533003f1c7e500faaf76511704f84d2529f84bfdfe7cb9ff271ee8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXeXjaC86d15/oy6Jm93VLmLASID8WV04gckN+NLjWAMzQ0V2brjwcNjh7kaObDggGeifU6+bTGASSSlt6UoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:55:37.187267Z","bundle_sha256":"06dc776c7e02502bcef03658bc67eb4820b80ef860f73a0988dac6f69b52e009"}}