{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OG6TQNV6GGPELCAR6AD5XQDXPN","short_pith_number":"pith:OG6TQNV6","schema_version":"1.0","canonical_sha256":"71bd3836be319e458811f007dbc0777b4990e887012765dfd6b9c8afc2724b00","source":{"kind":"arxiv","id":"2606.20179","version":1},"attestation_state":"computed","paper":{"title":"ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maxim Melichov, Morris Alper, Yakov Kolani","submitted_at":"2026-06-18T12:50:47Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion for Modern Hebrew is needed for applications like text-to-speech (TTS), but is challenging due to the language's abjad writing system, which leaves vowels largely unwritten, creating substantial ambiguity. Standard approaches first predict vowel diacritics (nikud) to produce International Phonetic Alphabet (IPA) transcriptions, but this is limited: vocalization data is scarce and laborious to produce, it does not specify features such as lexical stress, and it reflects formal grammatical rules rather than everyday spoken pronunciation. Direct sequence-to-se"},"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":"2606.20179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T12:50:47Z","cross_cats_sorted":[],"title_canon_sha256":"351e0676a7354d034138e31cda4bc2693ae5dded405381a431bf2e4ddb33e430","abstract_canon_sha256":"aded29250fb33d1aa2910262623b66dbc18c9e8d368ea80ce6fbd55ede093986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:04.949712Z","signature_b64":"2mK+pZ61KuMQ9TMx73LczosaneJVVvgR8BL0G59ZYEZb8n3dlQhSivj1IDouQSbzJzNP2c3EG3V60T2pn7eCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71bd3836be319e458811f007dbc0777b4990e887012765dfd6b9c8afc2724b00","last_reissued_at":"2026-06-19T16:13:04.949311Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:04.949311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maxim Melichov, Morris Alper, Yakov Kolani","submitted_at":"2026-06-18T12:50:47Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion for Modern Hebrew is needed for applications like text-to-speech (TTS), but is challenging due to the language's abjad writing system, which leaves vowels largely unwritten, creating substantial ambiguity. Standard approaches first predict vowel diacritics (nikud) to produce International Phonetic Alphabet (IPA) transcriptions, but this is limited: vocalization data is scarce and laborious to produce, it does not specify features such as lexical stress, and it reflects formal grammatical rules rather than everyday spoken pronunciation. Direct sequence-to-se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20179","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/2606.20179/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":"2606.20179","created_at":"2026-06-19T16:13:04.949382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20179v1","created_at":"2026-06-19T16:13:04.949382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20179","created_at":"2026-06-19T16:13:04.949382+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG6TQNV6GGPE","created_at":"2026-06-19T16:13:04.949382+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG6TQNV6GGPELCAR","created_at":"2026-06-19T16:13:04.949382+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG6TQNV6","created_at":"2026-06-19T16:13:04.949382+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/OG6TQNV6GGPELCAR6AD5XQDXPN","json":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN.json","graph_json":"https://pith.science/api/pith-number/OG6TQNV6GGPELCAR6AD5XQDXPN/graph.json","events_json":"https://pith.science/api/pith-number/OG6TQNV6GGPELCAR6AD5XQDXPN/events.json","paper":"https://pith.science/paper/OG6TQNV6"},"agent_actions":{"view_html":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN","download_json":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN.json","view_paper":"https://pith.science/paper/OG6TQNV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20179&json=true","fetch_graph":"https://pith.science/api/pith-number/OG6TQNV6GGPELCAR6AD5XQDXPN/graph.json","fetch_events":"https://pith.science/api/pith-number/OG6TQNV6GGPELCAR6AD5XQDXPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN/action/storage_attestation","attest_author":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN/action/author_attestation","sign_citation":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN/action/citation_signature","submit_replication":"https://pith.science/pith/OG6TQNV6GGPELCAR6AD5XQDXPN/action/replication_record"}},"created_at":"2026-06-19T16:13:04.949382+00:00","updated_at":"2026-06-19T16:13:04.949382+00:00"}