{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BL746RM4U5OQ5DNRA7S2LQUFPA","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":"4da773fd0b2c9c19ea0c286d77110be2e7eeb989b108baa8a9217cd7e6a297de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T21:34:35Z","title_canon_sha256":"c2a892384569d27877bf460f7b9e336a82c2f8d88f5e17cf2f3117b2f3278e0b"},"schema_version":"1.0","source":{"id":"2203.15917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15917","created_at":"2026-07-05T04:10:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15917v1","created_at":"2026-07-05T04:10:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15917","created_at":"2026-07-05T04:10:05Z"},{"alias_kind":"pith_short_12","alias_value":"BL746RM4U5OQ","created_at":"2026-07-05T04:10:05Z"},{"alias_kind":"pith_short_16","alias_value":"BL746RM4U5OQ5DNR","created_at":"2026-07-05T04:10:05Z"},{"alias_kind":"pith_short_8","alias_value":"BL746RM4","created_at":"2026-07-05T04:10:05Z"}],"graph_snapshots":[{"event_id":"sha256:049bb1893a19e2cf6441d89c8075607079a9ceb9a632912283203614c3ca00a0","target":"graph","created_at":"2026-07-05T04:10:05Z","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/2203.15917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text normalization (TN) systems in production are largely rule-based using weighted finite-state transducers (WFST). However, WFST-based systems struggle with ambiguous input when the normalized form is context-dependent. On the other hand, neural text normalization systems can take context into account but they suffer from unrecoverable errors and require labeled normalization datasets, which are hard to collect. We propose a new hybrid approach that combines the benefits of rule-based and neural systems. First, a non-deterministic WFST outputs all normalization candidates, and then a neural ","authors_text":"Boris Ginsburg, Evelina Bakhturina, Yang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T21:34:35Z","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15917","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":"sha256:6571e3c2964989a9ba5193cacde21b11eaa69396a6443f2ecf00cbe61fbd38ae","target":"record","created_at":"2026-07-05T04:10:05Z","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":"4da773fd0b2c9c19ea0c286d77110be2e7eeb989b108baa8a9217cd7e6a297de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-29T21:34:35Z","title_canon_sha256":"c2a892384569d27877bf460f7b9e336a82c2f8d88f5e17cf2f3117b2f3278e0b"},"schema_version":"1.0","source":{"id":"2203.15917","kind":"arxiv","version":1}},"canonical_sha256":"0affcf459ca75d0e8db107e5a5c285783ed95ebd8539cf059922e2b91d7ef147","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0affcf459ca75d0e8db107e5a5c285783ed95ebd8539cf059922e2b91d7ef147","first_computed_at":"2026-07-05T04:10:05.094810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:05.094810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7WiqAhm/OL73Ka2fD0HbtI7+5lu+YVhSbU6O14/dtAC4MOJTCqfMCHwzIuz85S/lWMVV6kZIxF64syMMAyNBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:05.095281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6571e3c2964989a9ba5193cacde21b11eaa69396a6443f2ecf00cbe61fbd38ae","sha256:049bb1893a19e2cf6441d89c8075607079a9ceb9a632912283203614c3ca00a0"],"state_sha256":"d6fe676539f9211796c76e0f3491f477b180716e2b74eddec21cbfb8cb5159f5"}