{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4L72EHWKCZ3XQRJJFMMDSHSSCD","short_pith_number":"pith:4L72EHWK","schema_version":"1.0","canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","source":{"kind":"arxiv","id":"2309.13426","version":2},"attestation_state":"computed","paper":{"title":"A Chat About Boring Problems: Studying GPT-based text normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Evelina Bakhturina, Mariana Graterol-Fuenmayor, Travis M. Bartley, Vitaly Lavrukhin, Yang Zhang","submitted_at":"2023-09-23T16:32:59Z","abstract_excerpt":"Text normalization - the conversion of text from written to spoken form - is traditionally assumed to be an ill-formed task for language models. In this work, we argue otherwise. We empirically show the capacity of Large-Language Models (LLM) for text normalization in few-shot scenarios. Combining self-consistency reasoning with linguistic-informed prompt engineering, we find LLM based text normalization to achieve error rates around 40\\% lower than top normalization systems. Further, upon error analysis, we note key limitations in the conventional design of text normalization tasks. We create"},"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":"2309.13426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T16:32:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"753d992c54c30aca6dda8881542258533b28d846d8ace7113d88749a0361ab47","abstract_canon_sha256":"7b75851aa4137425bc1427e692f47480a1592f30c457d6b066f806f7b0d8ae76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:35.525929Z","signature_b64":"S4U329dzc/LHdqcKCPcrZQ1ZV1xEcyQud0LP0Mz7zruC8ztJwAcdXWS+heAjP5uSeppn0Ebbwki3KRRfRFJ3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","last_reissued_at":"2026-07-05T07:34:35.525348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:35.525348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Chat About Boring Problems: Studying GPT-based text normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Evelina Bakhturina, Mariana Graterol-Fuenmayor, Travis M. Bartley, Vitaly Lavrukhin, Yang Zhang","submitted_at":"2023-09-23T16:32:59Z","abstract_excerpt":"Text normalization - the conversion of text from written to spoken form - is traditionally assumed to be an ill-formed task for language models. In this work, we argue otherwise. We empirically show the capacity of Large-Language Models (LLM) for text normalization in few-shot scenarios. Combining self-consistency reasoning with linguistic-informed prompt engineering, we find LLM based text normalization to achieve error rates around 40\\% lower than top normalization systems. Further, upon error analysis, we note key limitations in the conventional design of text normalization tasks. We create"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13426","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.13426/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2309.13426","created_at":"2026-07-05T07:34:35.525409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13426v2","created_at":"2026-07-05T07:34:35.525409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13426","created_at":"2026-07-05T07:34:35.525409+00:00"},{"alias_kind":"pith_short_12","alias_value":"4L72EHWKCZ3X","created_at":"2026-07-05T07:34:35.525409+00:00"},{"alias_kind":"pith_short_16","alias_value":"4L72EHWKCZ3XQRJJ","created_at":"2026-07-05T07:34:35.525409+00:00"},{"alias_kind":"pith_short_8","alias_value":"4L72EHWK","created_at":"2026-07-05T07:34:35.525409+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/4L72EHWKCZ3XQRJJFMMDSHSSCD","json":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD.json","graph_json":"https://pith.science/api/pith-number/4L72EHWKCZ3XQRJJFMMDSHSSCD/graph.json","events_json":"https://pith.science/api/pith-number/4L72EHWKCZ3XQRJJFMMDSHSSCD/events.json","paper":"https://pith.science/paper/4L72EHWK"},"agent_actions":{"view_html":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD","download_json":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD.json","view_paper":"https://pith.science/paper/4L72EHWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13426&json=true","fetch_graph":"https://pith.science/api/pith-number/4L72EHWKCZ3XQRJJFMMDSHSSCD/graph.json","fetch_events":"https://pith.science/api/pith-number/4L72EHWKCZ3XQRJJFMMDSHSSCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/action/storage_attestation","attest_author":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/action/author_attestation","sign_citation":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/action/citation_signature","submit_replication":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/action/replication_record"}},"created_at":"2026-07-05T07:34:35.525409+00:00","updated_at":"2026-07-05T07:34:35.525409+00:00"}