{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KNXWWIUO2GXJII6KKUHPMAEV3Z","short_pith_number":"pith:KNXWWIUO","schema_version":"1.0","canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","source":{"kind":"arxiv","id":"2411.01192","version":3},"attestation_state":"computed","paper":{"title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdellah El Mekki, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-Mageed","submitted_at":"2024-11-02T09:39:49Z","abstract_excerpt":"We introduce {\\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilin"},"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":"2411.01192","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-02T09:39:49Z","cross_cats_sorted":[],"title_canon_sha256":"595c837fb608e0247164fee77132d21d17dea58b20181b0c8a427a776798c5b5","abstract_canon_sha256":"cbeb604c762db7e1058b10c71ad86172fe1b24b27236564e2e854957b1b1aad2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:22.881561Z","signature_b64":"ZEA93hHSlv6mtbQ7WEi7HhP0qmsiJqjBRTm5kAQZ08iDo3qFed/sbYov2/Dkbc2+4g/q4P1W3O+U5J35C+TFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","last_reissued_at":"2026-07-05T10:12:22.881083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:22.881083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdellah El Mekki, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-Mageed","submitted_at":"2024-11-02T09:39:49Z","abstract_excerpt":"We introduce {\\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01192","kind":"arxiv","version":3},"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/2411.01192/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":"2411.01192","created_at":"2026-07-05T10:12:22.881140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01192v3","created_at":"2026-07-05T10:12:22.881140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01192","created_at":"2026-07-05T10:12:22.881140+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNXWWIUO2GXJ","created_at":"2026-07-05T10:12:22.881140+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNXWWIUO2GXJII6K","created_at":"2026-07-05T10:12:22.881140+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNXWWIUO","created_at":"2026-07-05T10:12:22.881140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08354","citing_title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z","json":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z.json","graph_json":"https://pith.science/api/pith-number/KNXWWIUO2GXJII6KKUHPMAEV3Z/graph.json","events_json":"https://pith.science/api/pith-number/KNXWWIUO2GXJII6KKUHPMAEV3Z/events.json","paper":"https://pith.science/paper/KNXWWIUO"},"agent_actions":{"view_html":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z","download_json":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z.json","view_paper":"https://pith.science/paper/KNXWWIUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01192&json=true","fetch_graph":"https://pith.science/api/pith-number/KNXWWIUO2GXJII6KKUHPMAEV3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KNXWWIUO2GXJII6KKUHPMAEV3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/action/storage_attestation","attest_author":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/action/author_attestation","sign_citation":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/action/citation_signature","submit_replication":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/action/replication_record"}},"created_at":"2026-07-05T10:12:22.881140+00:00","updated_at":"2026-07-05T10:12:22.881140+00:00"}