{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WWMTMPBYHWUAF4R5EUOYJZTIAE","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":"7c850d751843b1b7f5d2a183ffac5f413c2fd5d75bce168bbc0f6a3bc56fdd17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-07T11:06:26Z","title_canon_sha256":"f85a3e38b658852821c5c6e66e84bb0989fffdb8f8c93dbadba7b9ed3142e18d"},"schema_version":"1.0","source":{"id":"1804.02545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02545","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02545v2","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02545","created_at":"2026-05-18T00:18:35Z"},{"alias_kind":"pith_short_12","alias_value":"WWMTMPBYHWUA","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WWMTMPBYHWUAF4R5","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WWMTMPBY","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:5afa3b3a6db9bbc2757af41da89fb5b27b7505b63664fda2a5cbeb68ed9ce8a7","target":"graph","created_at":"2026-05-18T00:18:35Z","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":"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","authors_text":"Alexander Robertson, Sharon Goldwater","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-07T11:06:26Z","title":"Evaluating historical text normalization systems: How well do they generalize?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02545","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":"sha256:910a1a608a49324c57c5e0b1eca4461e6fab288ef3785069ae8c1488eca0916c","target":"record","created_at":"2026-05-18T00:18:35Z","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":"7c850d751843b1b7f5d2a183ffac5f413c2fd5d75bce168bbc0f6a3bc56fdd17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-07T11:06:26Z","title_canon_sha256":"f85a3e38b658852821c5c6e66e84bb0989fffdb8f8c93dbadba7b9ed3142e18d"},"schema_version":"1.0","source":{"id":"1804.02545","kind":"arxiv","version":2}},"canonical_sha256":"b599363c383da802f23d251d84e6680120d483d9e4aacf30fc3b95bb64c2110e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b599363c383da802f23d251d84e6680120d483d9e4aacf30fc3b95bb64c2110e","first_computed_at":"2026-05-18T00:18:35.463819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:35.463819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Lj63JweicHwLIoWi7Qo+rSWq10vc0Wczh1ifyoexTEX9Vf3B/Fmhfi9a0OnAqcVSy51Zq80VpgrWCVaImVtAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:35.464340Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:910a1a608a49324c57c5e0b1eca4461e6fab288ef3785069ae8c1488eca0916c","sha256:5afa3b3a6db9bbc2757af41da89fb5b27b7505b63664fda2a5cbeb68ed9ce8a7"],"state_sha256":"6b5d87adb0d57701940e53c383c432e1a85b7a185de76db22de876ad29fd199d"}