{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WWMTMPBYHWUAF4R5EUOYJZTIAE","short_pith_number":"pith:WWMTMPBY","schema_version":"1.0","canonical_sha256":"b599363c383da802f23d251d84e6680120d483d9e4aacf30fc3b95bb64c2110e","source":{"kind":"arxiv","id":"1804.02545","version":2},"attestation_state":"computed","paper":{"title":"Evaluating historical text normalization systems: How well do they generalize?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Robertson, Sharon Goldwater","submitted_at":"2018-04-07T11:06:26Z","abstract_excerpt":"We highlight several issues in the evaluation of historical text normalization systems that make it hard to tell how well these systems would actually work in practice---i.e., for new datasets or languages; in comparison to more na\\\"ive systems; or as a preprocessing step for downstream NLP tools. We illustrate these issues and exemplify our proposed evaluation practices by comparing two neural models against a na\\\"ive baseline system. We show that the neural models generalize well to unseen words in tests on five languages; nevertheless, they provide no clear benefit over the na\\\"ive baseline"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.02545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-07T11:06:26Z","cross_cats_sorted":[],"title_canon_sha256":"f85a3e38b658852821c5c6e66e84bb0989fffdb8f8c93dbadba7b9ed3142e18d","abstract_canon_sha256":"7c850d751843b1b7f5d2a183ffac5f413c2fd5d75bce168bbc0f6a3bc56fdd17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:35.464340Z","signature_b64":"8Lj63JweicHwLIoWi7Qo+rSWq10vc0Wczh1ifyoexTEX9Vf3B/Fmhfi9a0OnAqcVSy51Zq80VpgrWCVaImVtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b599363c383da802f23d251d84e6680120d483d9e4aacf30fc3b95bb64c2110e","last_reissued_at":"2026-05-18T00:18:35.463819Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:35.463819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating historical text normalization systems: How well do they generalize?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Robertson, Sharon Goldwater","submitted_at":"2018-04-07T11:06:26Z","abstract_excerpt":"We highlight several issues in the evaluation of historical text normalization systems that make it hard to tell how well these systems would actually work in practice---i.e., for new datasets or languages; in comparison to more na\\\"ive systems; or as a preprocessing step for downstream NLP tools. We illustrate these issues and exemplify our proposed evaluation practices by comparing two neural models against a na\\\"ive baseline system. We show that the neural models generalize well to unseen words in tests on five languages; nevertheless, they provide no clear benefit over the na\\\"ive baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02545","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.02545","created_at":"2026-05-18T00:18:35.463884+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02545v2","created_at":"2026-05-18T00:18:35.463884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02545","created_at":"2026-05-18T00:18:35.463884+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWMTMPBYHWUA","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWMTMPBYHWUAF4R5","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWMTMPBY","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE","json":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE.json","graph_json":"https://pith.science/api/pith-number/WWMTMPBYHWUAF4R5EUOYJZTIAE/graph.json","events_json":"https://pith.science/api/pith-number/WWMTMPBYHWUAF4R5EUOYJZTIAE/events.json","paper":"https://pith.science/paper/WWMTMPBY"},"agent_actions":{"view_html":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE","download_json":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE.json","view_paper":"https://pith.science/paper/WWMTMPBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02545&json=true","fetch_graph":"https://pith.science/api/pith-number/WWMTMPBYHWUAF4R5EUOYJZTIAE/graph.json","fetch_events":"https://pith.science/api/pith-number/WWMTMPBYHWUAF4R5EUOYJZTIAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE/action/storage_attestation","attest_author":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE/action/author_attestation","sign_citation":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE/action/citation_signature","submit_replication":"https://pith.science/pith/WWMTMPBYHWUAF4R5EUOYJZTIAE/action/replication_record"}},"created_at":"2026-05-18T00:18:35.463884+00:00","updated_at":"2026-05-18T00:18:35.463884+00:00"}