{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:LLGUQSMFPT54BQ7XEGSHSJD24D","short_pith_number":"pith:LLGUQSMF","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"},"canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","source":{"kind":"arxiv","id":"1503.08167","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.08167","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"arxiv_version","alias_value":"1503.08167v2","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08167","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"pith_short_12","alias_value":"LLGUQSMFPT54","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LLGUQSMFPT54BQ7X","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LLGUQSMF","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:LLGUQSMFPT54BQ7XEGSHSJD24D","target":"record","payload":{"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"},"canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","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"},"source_kind":"arxiv","source_id":"1503.08167","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":"2026-05-18T02:20:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtZVW9YIFtHStLYEIsX8c0QxdeurRA26g+BgptMJEPG+UxaBOgZbI77cFMm9UXjPAf8E9i0SIX2vCfYvordQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T21:02:27.905243Z"},"content_sha256":"8c40feedf87a881a7d4f6890ed79c15d699adc45b30f783e64900b97973b9840","schema_version":"1.0","event_id":"sha256:8c40feedf87a881a7d4f6890ed79c15d699adc45b30f783e64900b97973b9840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:LLGUQSMFPT54BQ7XEGSHSJD24D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:20:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hlyUbvPNk5Uk+PCCEBRuFXAqLaM0KwIyHhWKfMZZjaoskNkTkJZVekDtd6ijXaBr/DrT72pjF6UX007sxMkLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T21:02:27.905618Z"},"content_sha256":"3dace9ad88a66866d1874c9f4dc18b74a9a09435a29fb502b3727f86e8ee26c9","schema_version":"1.0","event_id":"sha256:3dace9ad88a66866d1874c9f4dc18b74a9a09435a29fb502b3727f86e8ee26c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/bundle.json","state_url":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/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":"2026-06-24T21:02:27Z","links":{"resolver":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D","bundle":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/bundle.json","state":"https://pith.science/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLGUQSMFPT54BQ7XEGSHSJD24D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:LLGUQSMFPT54BQ7XEGSHSJD24D","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":"476c8356d3c828d2c34fe02dc2ea4ee7b84e273310fdc743a26014d41f3245fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-27T17:57:00Z","title_canon_sha256":"b7037ab23698dab880177c4c7fddd3c63c318a83b6acc0bbf825d12a39ac674e"},"schema_version":"1.0","source":{"id":"1503.08167","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.08167","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"arxiv_version","alias_value":"1503.08167v2","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08167","created_at":"2026-05-18T02:20:02Z"},{"alias_kind":"pith_short_12","alias_value":"LLGUQSMFPT54","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LLGUQSMFPT54BQ7X","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LLGUQSMF","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:3dace9ad88a66866d1874c9f4dc18b74a9a09435a29fb502b3727f86e8ee26c9","target":"graph","created_at":"2026-05-18T02:20:02Z","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":"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","authors_text":"Miran Pobar, Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Slobodan Beliga","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-27T17:57:00Z","title":"Normalization of Non-Standard Words in Croatian Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08167","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":"sha256:8c40feedf87a881a7d4f6890ed79c15d699adc45b30f783e64900b97973b9840","target":"record","created_at":"2026-05-18T02:20:02Z","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":"476c8356d3c828d2c34fe02dc2ea4ee7b84e273310fdc743a26014d41f3245fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-03-27T17:57:00Z","title_canon_sha256":"b7037ab23698dab880177c4c7fddd3c63c318a83b6acc0bbf825d12a39ac674e"},"schema_version":"1.0","source":{"id":"1503.08167","kind":"arxiv","version":2}},"canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5acd4849857cfbc0c3f721a479247ae0c7d522bdb9c32508a8b9967a08c3b4a9","first_computed_at":"2026-05-18T02:20:02.453254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:20:02.453254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CUBIEIb7ZkHE3iQ2jrLW7LshyLqMWhjC8Un/rty8Hyhwj67/LCMxj8k+HCmEbhdlIfVUfG9LC3yuSVPvg3qkCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:20:02.454023Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.08167","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c40feedf87a881a7d4f6890ed79c15d699adc45b30f783e64900b97973b9840","sha256:3dace9ad88a66866d1874c9f4dc18b74a9a09435a29fb502b3727f86e8ee26c9"],"state_sha256":"0b35fbf87786dc52970be22f14443d04bbe26aee74c634b9eb85dc4b69ad96ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iaqK3ntyfjclCcndGQm/T8j7m+3RNWEE+wx9g1wu6tdzS38jfqsDMdZOaUF5GV708KljA+QJuAcus3/2ijILDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T21:02:27.907538Z","bundle_sha256":"719189214dfe3d9e5853091b530e0f08c91c3f7374b1a883d80025226e53d1ba"}}