{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KYN6QN45I5MCDQGYDVOV4MARMW","short_pith_number":"pith:KYN6QN45","schema_version":"1.0","canonical_sha256":"561be8379d475821c0d81d5d5e301165b4dc5b9778002133e29fa0434c8cb918","source":{"kind":"arxiv","id":"2307.08720","version":1},"attestation_state":"computed","paper":{"title":"ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Kinneret Misgav, Yair Lifshitz, Yanir Marmor","submitted_at":"2023-07-17T04:19:30Z","abstract_excerpt":"We introduce \"ivrit.ai\", a comprehensive Hebrew speech dataset, addressing the distinct lack of extensive, high-quality resources for advancing Automated Speech Recognition (ASR) technology in Hebrew. With over 3,300 speech hours and a over a thousand diverse speakers, ivrit.ai offers a substantial compilation of Hebrew speech across various contexts. It is delivered in three forms to cater to varying research needs: raw unprocessed audio; data post-Voice Activity Detection, and partially transcribed data. The dataset stands out for its legal accessibility, permitting use at no cost, thereby s"},"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":"2307.08720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-17T04:19:30Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ccc666e5839e883760b72fac3693e85aff4943632cb67c8c792715c16f798cdd","abstract_canon_sha256":"39fdaf3b431c5797b37dc17e8f9b8081b8f5ba2030dac835d4a1ee1842c6e431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:33.656529Z","signature_b64":"+tYNwUGyOaYZEGC8d1qANZXRcDjvenjg0NFHJQie/l31xBQO1GEc5+FWX34FBVe8Nep6GiqHDZ6Ar08YoUxECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"561be8379d475821c0d81d5d5e301165b4dc5b9778002133e29fa0434c8cb918","last_reissued_at":"2026-07-05T06:31:33.656093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:33.656093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Kinneret Misgav, Yair Lifshitz, Yanir Marmor","submitted_at":"2023-07-17T04:19:30Z","abstract_excerpt":"We introduce \"ivrit.ai\", a comprehensive Hebrew speech dataset, addressing the distinct lack of extensive, high-quality resources for advancing Automated Speech Recognition (ASR) technology in Hebrew. With over 3,300 speech hours and a over a thousand diverse speakers, ivrit.ai offers a substantial compilation of Hebrew speech across various contexts. It is delivered in three forms to cater to varying research needs: raw unprocessed audio; data post-Voice Activity Detection, and partially transcribed data. The dataset stands out for its legal accessibility, permitting use at no cost, thereby s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08720","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/2307.08720/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":"2307.08720","created_at":"2026-07-05T06:31:33.656162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08720v1","created_at":"2026-07-05T06:31:33.656162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08720","created_at":"2026-07-05T06:31:33.656162+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYN6QN45I5MC","created_at":"2026-07-05T06:31:33.656162+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYN6QN45I5MCDQGY","created_at":"2026-07-05T06:31:33.656162+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYN6QN45","created_at":"2026-07-05T06:31:33.656162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12311","citing_title":"Phonikud: Overcoming Phonetic Underspecification for Hebrew Text-To-Speech","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW","json":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW.json","graph_json":"https://pith.science/api/pith-number/KYN6QN45I5MCDQGYDVOV4MARMW/graph.json","events_json":"https://pith.science/api/pith-number/KYN6QN45I5MCDQGYDVOV4MARMW/events.json","paper":"https://pith.science/paper/KYN6QN45"},"agent_actions":{"view_html":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW","download_json":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW.json","view_paper":"https://pith.science/paper/KYN6QN45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08720&json=true","fetch_graph":"https://pith.science/api/pith-number/KYN6QN45I5MCDQGYDVOV4MARMW/graph.json","fetch_events":"https://pith.science/api/pith-number/KYN6QN45I5MCDQGYDVOV4MARMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW/action/storage_attestation","attest_author":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW/action/author_attestation","sign_citation":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW/action/citation_signature","submit_replication":"https://pith.science/pith/KYN6QN45I5MCDQGYDVOV4MARMW/action/replication_record"}},"created_at":"2026-07-05T06:31:33.656162+00:00","updated_at":"2026-07-05T06:31:33.656162+00:00"}