{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:L4724ROLR73RPZ4I67SZ7Z2XND","short_pith_number":"pith:L4724ROL","canonical_record":{"source":{"id":"1806.05210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T18:29:09Z","cross_cats_sorted":[],"title_canon_sha256":"4e3062bc158b08342d009b1fde2321eb469749bc40a174204a011c52edf94301","abstract_canon_sha256":"ff5b53b920139aa27e85da3b137f7509ebfe67da176d629b9fe00988717762f8"},"schema_version":"1.0"},"canonical_sha256":"5f3fae45cb8ff717e788f7e59fe75768dd40f617d6a8308099e10fa6097c6375","source":{"kind":"arxiv","id":"1806.05210","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05210","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05210v2","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05210","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"L4724ROLR73R","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L4724ROLR73RPZ4I","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L4724ROL","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:L4724ROLR73RPZ4I67SZ7Z2XND","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T18:29:09Z","cross_cats_sorted":[],"title_canon_sha256":"4e3062bc158b08342d009b1fde2321eb469749bc40a174204a011c52edf94301","abstract_canon_sha256":"ff5b53b920139aa27e85da3b137f7509ebfe67da176d629b9fe00988717762f8"},"schema_version":"1.0"},"canonical_sha256":"5f3fae45cb8ff717e788f7e59fe75768dd40f617d6a8308099e10fa6097c6375","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:53.940428Z","signature_b64":"EuEPcrQo6SkkYNoavG0FoSA3SgIR8JLsdB90qDzcUq9EP1C7FDdc6OXPSUjuv0KLWCDzIHedTIK2BLlTzRjUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3fae45cb8ff717e788f7e59fe75768dd40f617d6a8308099e10fa6097c6375","last_reissued_at":"2026-05-18T00:08:53.939740Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:53.939740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05210","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"woH5Y+lAHyw81BRvNM+CetFhTbK+AbEORPaQcCOhOwHE7DFmumDUQdin35mgsJXz3+4MfGbiU1lSmIJOgPqRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:41:33.273088Z"},"content_sha256":"2e3d10ed615ce9f8a4b5bf273e232d4807265b0d606740494918d32a3fe486c1","schema_version":"1.0","event_id":"sha256:2e3d10ed615ce9f8a4b5bf273e232d4807265b0d606740494918d32a3fe486c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:L4724ROLR73RPZ4I67SZ7Z2XND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eva Pettersson, Fabienne Cap, Gongbo Tang, Joakim Nivre","submitted_at":"2018-06-13T18:29:09Z","abstract_excerpt":"In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The NMT models are at different levels, have different attention mechanisms, and different neural network architectures. Our results show that NMT models are much better than SMT models in terms of character error rate. The vanilla RNNs are competitive to GRUs/LSTMs in historical spelling normalization. Transformer models perform better only when provided with more training data. We also find that subword-level models with a sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05210","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XmAR8KRKn+jkf8Dk0djdUoipSH9WyRu8PI/Q7WblRU8D5rgRaH2JcGIvm8zIda0Yxt1RB9mymtO2jFlMGt1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:41:33.273455Z"},"content_sha256":"c009f8eff8b6a9e840f0dc80cee778a78afa3e09874fc376e5fd54e56cfc3289","schema_version":"1.0","event_id":"sha256:c009f8eff8b6a9e840f0dc80cee778a78afa3e09874fc376e5fd54e56cfc3289"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4724ROLR73RPZ4I67SZ7Z2XND/bundle.json","state_url":"https://pith.science/pith/L4724ROLR73RPZ4I67SZ7Z2XND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4724ROLR73RPZ4I67SZ7Z2XND/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":"2026-05-28T04:41:33Z","links":{"resolver":"https://pith.science/pith/L4724ROLR73RPZ4I67SZ7Z2XND","bundle":"https://pith.science/pith/L4724ROLR73RPZ4I67SZ7Z2XND/bundle.json","state":"https://pith.science/pith/L4724ROLR73RPZ4I67SZ7Z2XND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4724ROLR73RPZ4I67SZ7Z2XND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:L4724ROLR73RPZ4I67SZ7Z2XND","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":"ff5b53b920139aa27e85da3b137f7509ebfe67da176d629b9fe00988717762f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T18:29:09Z","title_canon_sha256":"4e3062bc158b08342d009b1fde2321eb469749bc40a174204a011c52edf94301"},"schema_version":"1.0","source":{"id":"1806.05210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05210","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05210v2","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05210","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"L4724ROLR73R","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L4724ROLR73RPZ4I","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L4724ROL","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:c009f8eff8b6a9e840f0dc80cee778a78afa3e09874fc376e5fd54e56cfc3289","target":"graph","created_at":"2026-05-18T00:08:53Z","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"},"paper":{"abstract_excerpt":"In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The NMT models are at different levels, have different attention mechanisms, and different neural network architectures. Our results show that NMT models are much better than SMT models in terms of character error rate. The vanilla RNNs are competitive to GRUs/LSTMs in historical spelling normalization. Transformer models perform better only when provided with more training data. We also find that subword-level models with a sm","authors_text":"Eva Pettersson, Fabienne Cap, Gongbo Tang, Joakim Nivre","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T18:29:09Z","title":"An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05210","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":"sha256:2e3d10ed615ce9f8a4b5bf273e232d4807265b0d606740494918d32a3fe486c1","target":"record","created_at":"2026-05-18T00:08:53Z","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":"ff5b53b920139aa27e85da3b137f7509ebfe67da176d629b9fe00988717762f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-13T18:29:09Z","title_canon_sha256":"4e3062bc158b08342d009b1fde2321eb469749bc40a174204a011c52edf94301"},"schema_version":"1.0","source":{"id":"1806.05210","kind":"arxiv","version":2}},"canonical_sha256":"5f3fae45cb8ff717e788f7e59fe75768dd40f617d6a8308099e10fa6097c6375","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f3fae45cb8ff717e788f7e59fe75768dd40f617d6a8308099e10fa6097c6375","first_computed_at":"2026-05-18T00:08:53.939740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:53.939740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EuEPcrQo6SkkYNoavG0FoSA3SgIR8JLsdB90qDzcUq9EP1C7FDdc6OXPSUjuv0KLWCDzIHedTIK2BLlTzRjUAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:53.940428Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3d10ed615ce9f8a4b5bf273e232d4807265b0d606740494918d32a3fe486c1","sha256:c009f8eff8b6a9e840f0dc80cee778a78afa3e09874fc376e5fd54e56cfc3289"],"state_sha256":"d8f33d273ad2c7bc4037d24408af4fab8055329dcc9e0b414d6751aa867df187"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPFM7bkotDt6cBZ275vUctCNcVapPYXE3JSy69AGEiSJLA8UyCMRzLI8qIfkCeoFG75aVXCJFNflbEciJbJ5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:41:33.275413Z","bundle_sha256":"cae2b8f17de5c275dc3983a47cb481e0e81abb4be5ecff0dd75091835b398e8c"}}