{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KNXWWIUO2GXJII6KKUHPMAEV3Z","short_pith_number":"pith:KNXWWIUO","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"},"canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","source":{"kind":"arxiv","id":"2411.01192","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KNXWWIUO2GXJII6KKUHPMAEV3Z","target":"record","payload":{"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"},"canonical_sha256":"536f6b228ed1ae9423ca550ef60095de54cc2a11d6367104bcc9118761ecb6a7","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"},"source_kind":"arxiv","source_id":"2411.01192","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XAMLs3cy6f6X7QBxZdVUe8CiYFroc57VE5vI6YLwtkFlpKcjVtss+8aeRsvkG7Pvf+hx8yPd+1ZtJjc9SCdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:50:41.287987Z"},"content_sha256":"161e1f0b2b488a62db0e9383a80b38b279fcd11c8e3a267fb0ccb6222a6762cd","schema_version":"1.0","event_id":"sha256:161e1f0b2b488a62db0e9383a80b38b279fcd11c8e3a267fb0ccb6222a6762cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KNXWWIUO2GXJII6KKUHPMAEV3Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrz0mR10rE26cdJNWjiFbyx/SdVwNz96bEdUdcfr2XqIJ2IIR+mj/d/S84EuWTRysgFZiZ5uzbsK/ag2bVXLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:50:41.288566Z"},"content_sha256":"43883ccc734e31b0bef2cc6973d9bcf0e8a9e554f7b6cbc870dbcc8162c1ba7c","schema_version":"1.0","event_id":"sha256:43883ccc734e31b0bef2cc6973d9bcf0e8a9e554f7b6cbc870dbcc8162c1ba7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/bundle.json","state_url":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T06:50:41Z","links":{"resolver":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z","bundle":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/bundle.json","state":"https://pith.science/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNXWWIUO2GXJII6KKUHPMAEV3Z/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFV0hJHxsrELXTsRdlr8J7KaPJdcEZ8XeWubIBMBBcQyEjJ2N5Ax6GS8XUVIL2GV1nB59hNF5cmEFipwjMPFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:50:41.292238Z","bundle_sha256":"32c1e6564ea0dd49dd5647a85e1f55eae3bb616ccaf72ddc1928a5c778de4e8d"}}