{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MFHXH36HU3T4AFWUAQOFGCFT5T","short_pith_number":"pith:MFHXH36H","canonical_record":{"source":{"id":"1610.07844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","cross_cats_sorted":[],"title_canon_sha256":"bb22930c12f8e78d2c8a14fe9d4c9aa44f5c53fb6ce2bdd8a8e2ed476efad9f8","abstract_canon_sha256":"c08e9143f3e8544a02f368deca4b85081e2ebd3fee3ea69fa42ee7ac201c9caf"},"schema_version":"1.0"},"canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","source":{"kind":"arxiv","id":"1610.07844","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.07844","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1610.07844v1","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07844","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"MFHXH36HU3T4","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MFHXH36HU3T4AFWU","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MFHXH36H","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MFHXH36HU3T4AFWUAQOFGCFT5T","target":"record","payload":{"canonical_record":{"source":{"id":"1610.07844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","cross_cats_sorted":[],"title_canon_sha256":"bb22930c12f8e78d2c8a14fe9d4c9aa44f5c53fb6ce2bdd8a8e2ed476efad9f8","abstract_canon_sha256":"c08e9143f3e8544a02f368deca4b85081e2ebd3fee3ea69fa42ee7ac201c9caf"},"schema_version":"1.0"},"canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:17.404847Z","signature_b64":"HsPnbPDiLFSqdIkcGP7nu3xqxz+FvN0CZH5k5KHbHQ6KcE/2850eDKwmU5qFoBvznAg4y6Wd47QoeqA+yQFMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","last_reissued_at":"2026-05-18T01:01:17.404305Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:17.404305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.07844","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":"2026-05-18T01:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZ7OoTE+KONGqqBj/rLIOGGWZBaBo+K+IutvXsb62T3lhlYg+TN4ECHJ4GTN+vpmZhNl5X1YB7u5ALIBD1zuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:27:13.236828Z"},"content_sha256":"dfc38628cd66aeb743401db739e87690c55eb77c9cd45aee730f6c25e0d5a767","schema_version":"1.0","event_id":"sha256:dfc38628cd66aeb743401db739e87690c55eb77c9cd45aee730f6c25e0d5a767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MFHXH36HU3T4AFWUAQOFGCFT5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving historical spelling normalization with bi-directional LSTMs and multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Marcel Bollmann","submitted_at":"2016-10-25T12:30:26Z","abstract_excerpt":"Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to modern forms. We explore the suitability of a deep neural network architecture for this task, particularly a deep bi-LSTM network applied on a character level. Our model compares well to previously established normalization algorithms when evaluated on a diverse set of texts from Early New High German. We show that multi-task learning with additional normalization data can improve our model's p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07844","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":""},"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":"2026-05-18T01:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WxYHEReo90vvxHYcqs91WmseQ8ZS2152QMrohodFf/UTdpq9puoh+C/Fxlu0RPKtIpf0avm1vE3EY84VnnaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:27:13.237168Z"},"content_sha256":"c0fae8b41ccf353c861dd9dfa2b3e475db10f0892fa6f3170a61259c1cfaf0b2","schema_version":"1.0","event_id":"sha256:c0fae8b41ccf353c861dd9dfa2b3e475db10f0892fa6f3170a61259c1cfaf0b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/bundle.json","state_url":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/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":"2026-05-28T09:27:13Z","links":{"resolver":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T","bundle":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/bundle.json","state":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MFHXH36HU3T4AFWUAQOFGCFT5T","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":"c08e9143f3e8544a02f368deca4b85081e2ebd3fee3ea69fa42ee7ac201c9caf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","title_canon_sha256":"bb22930c12f8e78d2c8a14fe9d4c9aa44f5c53fb6ce2bdd8a8e2ed476efad9f8"},"schema_version":"1.0","source":{"id":"1610.07844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.07844","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1610.07844v1","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07844","created_at":"2026-05-18T01:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"MFHXH36HU3T4","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MFHXH36HU3T4AFWU","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MFHXH36H","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:c0fae8b41ccf353c861dd9dfa2b3e475db10f0892fa6f3170a61259c1cfaf0b2","target":"graph","created_at":"2026-05-18T01:01:17Z","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":"Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to modern forms. We explore the suitability of a deep neural network architecture for this task, particularly a deep bi-LSTM network applied on a character level. Our model compares well to previously established normalization algorithms when evaluated on a diverse set of texts from Early New High German. We show that multi-task learning with additional normalization data can improve our model's p","authors_text":"Anders S{\\o}gaard, Marcel Bollmann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","title":"Improving historical spelling normalization with bi-directional LSTMs and multi-task learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07844","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:dfc38628cd66aeb743401db739e87690c55eb77c9cd45aee730f6c25e0d5a767","target":"record","created_at":"2026-05-18T01:01:17Z","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":"c08e9143f3e8544a02f368deca4b85081e2ebd3fee3ea69fa42ee7ac201c9caf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","title_canon_sha256":"bb22930c12f8e78d2c8a14fe9d4c9aa44f5c53fb6ce2bdd8a8e2ed476efad9f8"},"schema_version":"1.0","source":{"id":"1610.07844","kind":"arxiv","version":1}},"canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","first_computed_at":"2026-05-18T01:01:17.404305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:01:17.404305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HsPnbPDiLFSqdIkcGP7nu3xqxz+FvN0CZH5k5KHbHQ6KcE/2850eDKwmU5qFoBvznAg4y6Wd47QoeqA+yQFMAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:01:17.404847Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.07844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfc38628cd66aeb743401db739e87690c55eb77c9cd45aee730f6c25e0d5a767","sha256:c0fae8b41ccf353c861dd9dfa2b3e475db10f0892fa6f3170a61259c1cfaf0b2"],"state_sha256":"609dbe4f881b2b2bc5ec138ad1753d3b2b4fdba9051b511a075b63a4ff2be32a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/chyASAe/3RFHNOce4pRQdtjFaJ6a2GvkofYEQyFpu68OZ6/31nl7kopVMIGnniUgmx5jE5gEjsiYy3pYA+cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:27:13.239149Z","bundle_sha256":"42de8bad1fa130f8f7d2868f0ae8551f52dea36ec4622ba8679a731a04a14429"}}