{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CHHW5RNWXHG3IXUUAMADRPZQFI","short_pith_number":"pith:CHHW5RNW","schema_version":"1.0","canonical_sha256":"11cf6ec5b6b9cdb45e94030038bf302a05a54d1e0bb2565eaac1f9f5ff26013a","source":{"kind":"arxiv","id":"2208.01371","version":1},"attestation_state":"computed","paper":{"title":"Multi-Module G2P Converter for Persian Focusing on Relations between Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hossein Sameti, Mahdi Rezaei, Negar Nayeri, Saeed Farzi","submitted_at":"2022-08-02T11:33:48Z","abstract_excerpt":"In this paper, we investigate the application of end-to-end and multi-module frameworks for G2P conversion for the Persian language. The results demonstrate that our proposed multi-module G2P system outperforms our end-to-end systems in terms of accuracy and speed. The system consists of a pronunciation dictionary as our look-up table, along with separate models to handle homographs, OOVs and ezafe in Persian created using GRU and Transformer architectures. The system is sequence-level rather than word-level, which allows it to effectively capture the unwritten relations between words (cross-w"},"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":"2208.01371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T11:33:48Z","cross_cats_sorted":[],"title_canon_sha256":"6710ddc39b05037076f2fa366e401cb92a26357d811bec4c05ea2d12701f8cef","abstract_canon_sha256":"1f28bfddd567fb099a4a75a52d8b85b613e626308a7a0dded7f4394c428d0099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:32.814111Z","signature_b64":"YnV9jAyINjb1RQhINkx2qq0hOmfUy74gEkXbAHsijld+fXrDjgeJI+UjzVWWxjOx3/v/Oe5iTOWu8s/aYEwcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11cf6ec5b6b9cdb45e94030038bf302a05a54d1e0bb2565eaac1f9f5ff26013a","last_reissued_at":"2026-07-05T04:45:32.813630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:32.813630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Module G2P Converter for Persian Focusing on Relations between Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hossein Sameti, Mahdi Rezaei, Negar Nayeri, Saeed Farzi","submitted_at":"2022-08-02T11:33:48Z","abstract_excerpt":"In this paper, we investigate the application of end-to-end and multi-module frameworks for G2P conversion for the Persian language. The results demonstrate that our proposed multi-module G2P system outperforms our end-to-end systems in terms of accuracy and speed. The system consists of a pronunciation dictionary as our look-up table, along with separate models to handle homographs, OOVs and ezafe in Persian created using GRU and Transformer architectures. The system is sequence-level rather than word-level, which allows it to effectively capture the unwritten relations between words (cross-w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01371","kind":"arxiv","version":1},"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/2208.01371/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":"2208.01371","created_at":"2026-07-05T04:45:32.813692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01371v1","created_at":"2026-07-05T04:45:32.813692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01371","created_at":"2026-07-05T04:45:32.813692+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHHW5RNWXHG3","created_at":"2026-07-05T04:45:32.813692+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHHW5RNWXHG3IXUU","created_at":"2026-07-05T04:45:32.813692+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHHW5RNW","created_at":"2026-07-05T04:45:32.813692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12973","citing_title":"Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI","json":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI.json","graph_json":"https://pith.science/api/pith-number/CHHW5RNWXHG3IXUUAMADRPZQFI/graph.json","events_json":"https://pith.science/api/pith-number/CHHW5RNWXHG3IXUUAMADRPZQFI/events.json","paper":"https://pith.science/paper/CHHW5RNW"},"agent_actions":{"view_html":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI","download_json":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI.json","view_paper":"https://pith.science/paper/CHHW5RNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01371&json=true","fetch_graph":"https://pith.science/api/pith-number/CHHW5RNWXHG3IXUUAMADRPZQFI/graph.json","fetch_events":"https://pith.science/api/pith-number/CHHW5RNWXHG3IXUUAMADRPZQFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI/action/storage_attestation","attest_author":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI/action/author_attestation","sign_citation":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI/action/citation_signature","submit_replication":"https://pith.science/pith/CHHW5RNWXHG3IXUUAMADRPZQFI/action/replication_record"}},"created_at":"2026-07-05T04:45:32.813692+00:00","updated_at":"2026-07-05T04:45:32.813692+00:00"}