{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FNXFZCIV2AXCAQ3HX6UVKTWEED","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":"b4c6609239b529ce34fa2c21e335773c227dc64aa12138c15462c997c968bff7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T16:14:05Z","title_canon_sha256":"5b6f346e14e68907c3e71ce07f3939952514859c7a3273a2afa95e17b872fa5b"},"schema_version":"1.0","source":{"id":"2409.02841","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02841","created_at":"2026-07-05T10:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02841v2","created_at":"2026-07-05T10:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02841","created_at":"2026-07-05T10:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"FNXFZCIV2AXC","created_at":"2026-07-05T10:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"FNXFZCIV2AXCAQ3H","created_at":"2026-07-05T10:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"FNXFZCIV","created_at":"2026-07-05T10:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:857c74ab6b77df6ebf07ad758b29735bb646ecfd5a4a42066ec21c33b40417fc","target":"graph","created_at":"2026-07-05T10:19:27Z","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/2409.02841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Historic variations of spelling poses a challenge for full-text search or natural language processing on historical digitized texts. To minimize the gap between the historic orthography and contemporary spelling, usually an automatic orthographic normalization of the historical source material is pursued. This report proposes a normalization system for German literary texts from c. 1700-1900, trained on a parallel corpus. The proposed system makes use of a machine learning approach using Transformer language models, combining an encoder-decoder model to normalize individual word types, and a p","authors_text":"Anton Ehrmanntraut","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T16:14:05Z","title":"Historical German Text Normalization Using Type- and Token-Based Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02841","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:a26a2f478af1fb9c893feb3ec34d74bf7a2caeb429c6169fdb0bd171bbdf1285","target":"record","created_at":"2026-07-05T10:19:27Z","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":"b4c6609239b529ce34fa2c21e335773c227dc64aa12138c15462c997c968bff7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T16:14:05Z","title_canon_sha256":"5b6f346e14e68907c3e71ce07f3939952514859c7a3273a2afa95e17b872fa5b"},"schema_version":"1.0","source":{"id":"2409.02841","kind":"arxiv","version":2}},"canonical_sha256":"2b6e5c8915d02e204367bfa9554ec420c0d1b57bc751702199214959e0ea7f08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b6e5c8915d02e204367bfa9554ec420c0d1b57bc751702199214959e0ea7f08","first_computed_at":"2026-07-05T10:19:27.761567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:27.761567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZdSqFr0XFpeFHbBSky1wpFGfzbk5QSkrjogJvUToUPuTrvKY5fPPHxlbxELvf+I4jJZMfGg23VOFQvjxr84+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:27.762024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02841","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26a2f478af1fb9c893feb3ec34d74bf7a2caeb429c6169fdb0bd171bbdf1285","sha256:857c74ab6b77df6ebf07ad758b29735bb646ecfd5a4a42066ec21c33b40417fc"],"state_sha256":"28c8c83b97e36a0fa3325361c7c25e036bad8664447d2128e5c2982159d6175a"}