{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LLGUQSMFPT54BQ7XEGSHSJD24D","short_pith_number":"pith:LLGUQSMF","schema_version":"1.0","canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","source":{"kind":"arxiv","id":"1503.08167","version":2},"attestation_state":"computed","paper":{"title":"Normalization of Non-Standard Words in Croatian Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Miran Pobar, Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Slobodan Beliga","submitted_at":"2015-03-27T17:57:00Z","abstract_excerpt":"This paper presents text normalization which is an integral part of any text-to-speech synthesis system. Text normalization is a set of methods with a task to write non-standard words, like numbers, dates, times, abbreviations, acronyms and the most common symbols, in their full expanded form are presented. The whole taxonomy for classification of non-standard words in Croatian language together with rule-based normalization methods combined with a lookup dictionary are proposed. Achieved token rate for normalization of Croatian texts is 95%, where 80% of expanded words are in correct morpholo"},"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":"1503.08167","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-27T17:57:00Z","cross_cats_sorted":[],"title_canon_sha256":"b7037ab23698dab880177c4c7fddd3c63c318a83b6acc0bbf825d12a39ac674e","abstract_canon_sha256":"476c8356d3c828d2c34fe02dc2ea4ee7b84e273310fdc743a26014d41f3245fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:20:02.454023Z","signature_b64":"CUBIEIb7ZkHE3iQ2jrLW7LshyLqMWhjC8Un/rty8Hyhwj67/LCMxj8k+HCmEbhdlIfVUfG9LC3yuSVPvg3qkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","last_reissued_at":"2026-05-18T02:20:02.453254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:20:02.453254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalization of Non-Standard Words in Croatian Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Miran Pobar, Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Slobodan Beliga","submitted_at":"2015-03-27T17:57:00Z","abstract_excerpt":"This paper presents text normalization which is an integral part of any text-to-speech synthesis system. Text normalization is a set of methods with a task to write non-standard words, like numbers, dates, times, abbreviations, acronyms and the most common symbols, in their full expanded form are presented. The whole taxonomy for classification of non-standard words in Croatian language together with rule-based normalization methods combined with a lookup dictionary are proposed. Achieved token rate for normalization of Croatian texts is 95%, where 80% of expanded words are in correct morpholo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08167","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":"1503.08167","created_at":"2026-05-18T02:20:02.453381+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.08167v2","created_at":"2026-05-18T02:20:02.453381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08167","created_at":"2026-05-18T02:20:02.453381+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLGUQSMFPT54","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLGUQSMFPT54BQ7X","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLGUQSMF","created_at":"2026-05-18T12:29:29.992203+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/LLGUQSMFPT54BQ7XEGSHSJD24D","json":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D.json","graph_json":"https://pith.science/api/pith-number/LLGUQSMFPT54BQ7XEGSHSJD24D/graph.json","events_json":"https://pith.science/api/pith-number/LLGUQSMFPT54BQ7XEGSHSJD24D/events.json","paper":"https://pith.science/paper/LLGUQSMF"},"agent_actions":{"view_html":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D","download_json":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D.json","view_paper":"https://pith.science/paper/LLGUQSMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.08167&json=true","fetch_graph":"https://pith.science/api/pith-number/LLGUQSMFPT54BQ7XEGSHSJD24D/graph.json","fetch_events":"https://pith.science/api/pith-number/LLGUQSMFPT54BQ7XEGSHSJD24D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/action/storage_attestation","attest_author":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/action/author_attestation","sign_citation":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/action/citation_signature","submit_replication":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/action/replication_record"}},"created_at":"2026-05-18T02:20:02.453381+00:00","updated_at":"2026-05-18T02:20:02.453381+00:00"}