{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KNXWWIUO2GXJII6KKUHPMAEV3Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cbeb604c762db7e1058b10c71ad86172fe1b24b27236564e2e854957b1b1aad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-02T09:39:49Z","title_canon_sha256":"595c837fb608e0247164fee77132d21d17dea58b20181b0c8a427a776798c5b5"},"schema_version":"1.0","source":{"id":"2411.01192","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01192","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01192v3","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01192","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"KNXWWIUO2GXJ","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"KNXWWIUO2GXJII6K","created_at":"2026-07-05T10:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"KNXWWIUO","created_at":"2026-07-05T10:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:43883ccc734e31b0bef2cc6973d9bcf0e8a9e554f7b6cbc870dbcc8162c1ba7c","target":"graph","created_at":"2026-07-05T10:12:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.01192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdellah El Mekki, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-Mageed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-02T09:39:49Z","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01192","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:161e1f0b2b488a62db0e9383a80b38b279fcd11c8e3a267fb0ccb6222a6762cd","target":"record","created_at":"2026-07-05T10:12:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cbeb604c762db7e1058b10c71ad86172fe1b24b27236564e2e854957b1b1aad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-02T09:39:49Z","title_canon_sha256":"595c837fb608e0247164fee77132d21d17dea58b20181b0c8a427a776798c5b5"},"schema_version":"1.0","source":{"id":"2411.01192","kind":"arxiv","version":3}},"canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","first_computed_at":"2026-07-05T10:12:22.881083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:22.881083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZEA93hHSlv6mtbQ7WEi7HhP0qmsiJqjBRTm5kAQZ08iDo3qFed/sbYov2/Dkbc2+4g/q4P1W3O+U5J35C+TFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:22.881561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01192","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:161e1f0b2b488a62db0e9383a80b38b279fcd11c8e3a267fb0ccb6222a6762cd","sha256:43883ccc734e31b0bef2cc6973d9bcf0e8a9e554f7b6cbc870dbcc8162c1ba7c"],"state_sha256":"15187fa4cd0a7a45effde3b0bdfc234cd25468423490928fd6cd21fb8aaa619b"}