{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4L72EHWKCZ3XQRJJFMMDSHSSCD","short_pith_number":"pith:4L72EHWK","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"},"canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","source":{"kind":"arxiv","id":"2309.13426","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13426","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13426v2","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13426","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"4L72EHWKCZ3X","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"4L72EHWKCZ3XQRJJ","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"4L72EHWK","created_at":"2026-07-05T07:34:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4L72EHWKCZ3XQRJJFMMDSHSSCD","target":"record","payload":{"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"},"canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","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"},"source_kind":"arxiv","source_id":"2309.13426","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAmhibskQO42T792NNSuAwB6NnIO5QNqKm8L51RvedAOWJVq1sr/40rAUYezmBBSKluXgBOlzpaIe+s4Rd96BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:54.590663Z"},"content_sha256":"1aadfe8402717547f9f376abf4fe32d71473d949e9d6f2388f0090e1f786d75f","schema_version":"1.0","event_id":"sha256:1aadfe8402717547f9f376abf4fe32d71473d949e9d6f2388f0090e1f786d75f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4L72EHWKCZ3XQRJJFMMDSHSSCD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"650JjF0VrvOLb/AMtenIa6Pvxr7fxr+Z4fcK1zfYyRc29I1pawMEZb5edCZZ5m3AMGqi13qjFm7yVFXiXM9AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:54.591039Z"},"content_sha256":"238932601792f50f604bce79c9e81a5300fbfe85da7bfb97a1686505268d0d93","schema_version":"1.0","event_id":"sha256:238932601792f50f604bce79c9e81a5300fbfe85da7bfb97a1686505268d0d93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/bundle.json","state_url":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/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":"2026-07-06T18:08:54Z","links":{"resolver":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD","bundle":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/bundle.json","state":"https://pith.science/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4L72EHWKCZ3XQRJJFMMDSHSSCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4L72EHWKCZ3XQRJJFMMDSHSSCD","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":"7b75851aa4137425bc1427e692f47480a1592f30c457d6b066f806f7b0d8ae76","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T16:32:59Z","title_canon_sha256":"753d992c54c30aca6dda8881542258533b28d846d8ace7113d88749a0361ab47"},"schema_version":"1.0","source":{"id":"2309.13426","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13426","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13426v2","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13426","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"4L72EHWKCZ3X","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"4L72EHWKCZ3XQRJJ","created_at":"2026-07-05T07:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"4L72EHWK","created_at":"2026-07-05T07:34:35Z"}],"graph_snapshots":[{"event_id":"sha256:238932601792f50f604bce79c9e81a5300fbfe85da7bfb97a1686505268d0d93","target":"graph","created_at":"2026-07-05T07:34:35Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.13426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boris Ginsburg, Evelina Bakhturina, Mariana Graterol-Fuenmayor, Travis M. Bartley, Vitaly Lavrukhin, Yang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T16:32:59Z","title":"A Chat About Boring Problems: Studying GPT-based text normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13426","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":"sha256:1aadfe8402717547f9f376abf4fe32d71473d949e9d6f2388f0090e1f786d75f","target":"record","created_at":"2026-07-05T07:34:35Z","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":"7b75851aa4137425bc1427e692f47480a1592f30c457d6b066f806f7b0d8ae76","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T16:32:59Z","title_canon_sha256":"753d992c54c30aca6dda8881542258533b28d846d8ace7113d88749a0361ab47"},"schema_version":"1.0","source":{"id":"2309.13426","kind":"arxiv","version":2}},"canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2ffa21eca16777845292b18391e5210daa4d1e0abd5133017a31db3653310e0","first_computed_at":"2026-07-05T07:34:35.525348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:35.525348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S4U329dzc/LHdqcKCPcrZQ1ZV1xEcyQud0LP0Mz7zruC8ztJwAcdXWS+heAjP5uSeppn0Ebbwki3KRRfRFJ3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:35.525929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13426","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aadfe8402717547f9f376abf4fe32d71473d949e9d6f2388f0090e1f786d75f","sha256:238932601792f50f604bce79c9e81a5300fbfe85da7bfb97a1686505268d0d93"],"state_sha256":"9ed60c76482b98214a11871c1b630ec7e55e95ab653217ed0be4b1188db0fcfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s289EJUsHyT6d4+ZHYfIC0M1IU6Gbi3BL7uBcq0akCyLocWl1PFyPUbYVV+Su98UHfxhhUAk9dsSjpBKdW0gAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:08:54.593017Z","bundle_sha256":"600794e01006f06e31f048941639d35f4c8fc866924e37bd790f55a252006dd6"}}