{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NO2KK3FFXVQLUQAQ5UEEGAJSIT","short_pith_number":"pith:NO2KK3FF","schema_version":"1.0","canonical_sha256":"6bb4a56ca5bd60ba4010ed0843013244da8a284fc4a4954e76f680531bf6fafe","source":{"kind":"arxiv","id":"2403.18182","version":1},"attestation_state":"computed","paper":{"title":"ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Palfreyman, Fadhl Eryani, Injy Hamed, Nizar Habash","submitted_at":"2024-03-27T01:19:23Z","abstract_excerpt":"We present ZAEBUC-Spoken, a multilingual multidialectal Arabic-English speech corpus. The corpus comprises twelve hours of Zoom meetings involving multiple speakers role-playing a work situation where Students brainstorm ideas for a certain topic and then discuss it with an Interlocutor. The meetings cover different topics and are divided into phases with different language setups. The corpus presents a challenging set for automatic speech recognition (ASR), including two languages (Arabic and English) with Arabic spoken in multiple variants (Modern Standard Arabic, Gulf Arabic, and Egyptian A"},"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":"2403.18182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-27T01:19:23Z","cross_cats_sorted":[],"title_canon_sha256":"b84f8c760c7cc9dfceb3f455bf94e1886b06f71a1eb7e771562bd47e5aac53d7","abstract_canon_sha256":"0c1827f4ac9d8a750dd65e8fdabe6277982e6c0cb01b9ac6ea4b5ac740c73712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:05.844779Z","signature_b64":"Ctwf80Ncc17tVB6FMKmn1IMf6/nhgLGGAWZoByqyzIb1u6hGR9gLZukwOlxP7Dj7M2ikmisXFR1CckTIWFrTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bb4a56ca5bd60ba4010ed0843013244da8a284fc4a4954e76f680531bf6fafe","last_reissued_at":"2026-07-05T08:01:05.844307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:05.844307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Palfreyman, Fadhl Eryani, Injy Hamed, Nizar Habash","submitted_at":"2024-03-27T01:19:23Z","abstract_excerpt":"We present ZAEBUC-Spoken, a multilingual multidialectal Arabic-English speech corpus. The corpus comprises twelve hours of Zoom meetings involving multiple speakers role-playing a work situation where Students brainstorm ideas for a certain topic and then discuss it with an Interlocutor. The meetings cover different topics and are divided into phases with different language setups. The corpus presents a challenging set for automatic speech recognition (ASR), including two languages (Arabic and English) with Arabic spoken in multiple variants (Modern Standard Arabic, Gulf Arabic, and Egyptian A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18182","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/2403.18182/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":"2403.18182","created_at":"2026-07-05T08:01:05.844381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18182v1","created_at":"2026-07-05T08:01:05.844381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18182","created_at":"2026-07-05T08:01:05.844381+00:00"},{"alias_kind":"pith_short_12","alias_value":"NO2KK3FFXVQL","created_at":"2026-07-05T08:01:05.844381+00:00"},{"alias_kind":"pith_short_16","alias_value":"NO2KK3FFXVQLUQAQ","created_at":"2026-07-05T08:01:05.844381+00:00"},{"alias_kind":"pith_short_8","alias_value":"NO2KK3FF","created_at":"2026-07-05T08:01:05.844381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13424","citing_title":"CAFE A Novel Code switching Dataset for Algerian Dialect French and English","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT","json":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT.json","graph_json":"https://pith.science/api/pith-number/NO2KK3FFXVQLUQAQ5UEEGAJSIT/graph.json","events_json":"https://pith.science/api/pith-number/NO2KK3FFXVQLUQAQ5UEEGAJSIT/events.json","paper":"https://pith.science/paper/NO2KK3FF"},"agent_actions":{"view_html":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT","download_json":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT.json","view_paper":"https://pith.science/paper/NO2KK3FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18182&json=true","fetch_graph":"https://pith.science/api/pith-number/NO2KK3FFXVQLUQAQ5UEEGAJSIT/graph.json","fetch_events":"https://pith.science/api/pith-number/NO2KK3FFXVQLUQAQ5UEEGAJSIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT/action/storage_attestation","attest_author":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT/action/author_attestation","sign_citation":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT/action/citation_signature","submit_replication":"https://pith.science/pith/NO2KK3FFXVQLUQAQ5UEEGAJSIT/action/replication_record"}},"created_at":"2026-07-05T08:01:05.844381+00:00","updated_at":"2026-07-05T08:01:05.844381+00:00"}