{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QFBT2FZJXFATMQGP75G4W2FYFI","short_pith_number":"pith:QFBT2FZJ","schema_version":"1.0","canonical_sha256":"81433d1729b9413640cfff4dcb68b82a32c7b66d423d92ae352d25d196d58328","source":{"kind":"arxiv","id":"2407.21139","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anis Koubaa, Omer Nacar","submitted_at":"2024-07-30T19:03:03Z","abstract_excerpt":"This work presents a novel framework for training Arabic nested embedding models through Matryoshka Embedding Learning, leveraging multilingual, Arabic-specific, and English-based models, to highlight the power of nested embeddings models in various Arabic NLP downstream tasks. Our innovative contribution includes the translation of various sentence similarity datasets into Arabic, enabling a comprehensive evaluation framework to compare these models across different dimensions. We trained several nested embedding models on the Arabic Natural Language Inference triplet dataset and assessed the"},"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":"2407.21139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T19:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"9e55bad4daed71265b5bdf48f6c442d456b17c9bfe5dbfb9bb8e811ab467d05d","abstract_canon_sha256":"f000bb347ee42a373ed686fe36ebd0fd277504f142446ebf56f2818cbcbf66f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:58.404515Z","signature_b64":"3rU4wHM7gaHUnepu4FP/fITdfLqquR3pulDmcl8rkjE7+S2Zp8M6lIFhvRfMptOQa2kgHd4xg4c3ToECo/9oDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81433d1729b9413640cfff4dcb68b82a32c7b66d423d92ae352d25d196d58328","last_reissued_at":"2026-07-05T08:50:58.404003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:58.404003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anis Koubaa, Omer Nacar","submitted_at":"2024-07-30T19:03:03Z","abstract_excerpt":"This work presents a novel framework for training Arabic nested embedding models through Matryoshka Embedding Learning, leveraging multilingual, Arabic-specific, and English-based models, to highlight the power of nested embeddings models in various Arabic NLP downstream tasks. Our innovative contribution includes the translation of various sentence similarity datasets into Arabic, enabling a comprehensive evaluation framework to compare these models across different dimensions. We trained several nested embedding models on the Arabic Natural Language Inference triplet dataset and assessed the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21139","kind":"arxiv","version":2},"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/2407.21139/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":"2407.21139","created_at":"2026-07-05T08:50:58.404074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21139v2","created_at":"2026-07-05T08:50:58.404074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21139","created_at":"2026-07-05T08:50:58.404074+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFBT2FZJXFAT","created_at":"2026-07-05T08:50:58.404074+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFBT2FZJXFATMQGP","created_at":"2026-07-05T08:50:58.404074+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFBT2FZJ","created_at":"2026-07-05T08:50:58.404074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24581","citing_title":"GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI","json":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI.json","graph_json":"https://pith.science/api/pith-number/QFBT2FZJXFATMQGP75G4W2FYFI/graph.json","events_json":"https://pith.science/api/pith-number/QFBT2FZJXFATMQGP75G4W2FYFI/events.json","paper":"https://pith.science/paper/QFBT2FZJ"},"agent_actions":{"view_html":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI","download_json":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI.json","view_paper":"https://pith.science/paper/QFBT2FZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21139&json=true","fetch_graph":"https://pith.science/api/pith-number/QFBT2FZJXFATMQGP75G4W2FYFI/graph.json","fetch_events":"https://pith.science/api/pith-number/QFBT2FZJXFATMQGP75G4W2FYFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI/action/storage_attestation","attest_author":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI/action/author_attestation","sign_citation":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI/action/citation_signature","submit_replication":"https://pith.science/pith/QFBT2FZJXFATMQGP75G4W2FYFI/action/replication_record"}},"created_at":"2026-07-05T08:50:58.404074+00:00","updated_at":"2026-07-05T08:50:58.404074+00:00"}