{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H56EMAUPJZHH5BMDFTKWJTX4G6","short_pith_number":"pith:H56EMAUP","schema_version":"1.0","canonical_sha256":"3f7c46028f4e4e7e85832cd564cefc37993b811df75a36d47c15025232c400b2","source":{"kind":"arxiv","id":"2411.15270","version":1},"attestation_state":"computed","paper":{"title":"BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Md. Mohibur Rahman Nabil, Mohammad Ashrafuzzaman Khan, Muhammad Rafsan Kabir","submitted_at":"2024-11-22T13:03:25Z","abstract_excerpt":"Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a language spoken by almost two hundred and thirty million people) are still under-explored. This work introduces two lightweight sentence transformers for the Bangla language, leveraging a novel cross-lingual knowledge distillation approach. This method distills knowledge from a pre-trained, high-performing English sentence transformer. Proposed models are evaluate"},"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":"2411.15270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T13:03:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b66080ed398a4b667e59dc0f86e18b75c4c8a84f89b61e3edfcd56bf48a3b914","abstract_canon_sha256":"7cff48e6931d5dbe67600ff0754545caef5d7542de659ae214251b4d3ac0a8ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:32.185163Z","signature_b64":"kOTrRdPnhm9Nq/SUEXEcwpWb8Z+cEkUpSyRtm4e0Hfmuv0AI7HdSi5uGlqs1iewk7uqs4lu6Ja747+apdcSwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f7c46028f4e4e7e85832cd564cefc37993b811df75a36d47c15025232c400b2","last_reissued_at":"2026-07-05T09:39:32.184694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:32.184694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Md. Mohibur Rahman Nabil, Mohammad Ashrafuzzaman Khan, Muhammad Rafsan Kabir","submitted_at":"2024-11-22T13:03:25Z","abstract_excerpt":"Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a language spoken by almost two hundred and thirty million people) are still under-explored. This work introduces two lightweight sentence transformers for the Bangla language, leveraging a novel cross-lingual knowledge distillation approach. This method distills knowledge from a pre-trained, high-performing English sentence transformer. Proposed models are evaluate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15270","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/2411.15270/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":"2411.15270","created_at":"2026-07-05T09:39:32.184750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15270v1","created_at":"2026-07-05T09:39:32.184750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15270","created_at":"2026-07-05T09:39:32.184750+00:00"},{"alias_kind":"pith_short_12","alias_value":"H56EMAUPJZHH","created_at":"2026-07-05T09:39:32.184750+00:00"},{"alias_kind":"pith_short_16","alias_value":"H56EMAUPJZHH5BMD","created_at":"2026-07-05T09:39:32.184750+00:00"},{"alias_kind":"pith_short_8","alias_value":"H56EMAUP","created_at":"2026-07-05T09:39:32.184750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6","json":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6.json","graph_json":"https://pith.science/api/pith-number/H56EMAUPJZHH5BMDFTKWJTX4G6/graph.json","events_json":"https://pith.science/api/pith-number/H56EMAUPJZHH5BMDFTKWJTX4G6/events.json","paper":"https://pith.science/paper/H56EMAUP"},"agent_actions":{"view_html":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6","download_json":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6.json","view_paper":"https://pith.science/paper/H56EMAUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15270&json=true","fetch_graph":"https://pith.science/api/pith-number/H56EMAUPJZHH5BMDFTKWJTX4G6/graph.json","fetch_events":"https://pith.science/api/pith-number/H56EMAUPJZHH5BMDFTKWJTX4G6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6/action/storage_attestation","attest_author":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6/action/author_attestation","sign_citation":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6/action/citation_signature","submit_replication":"https://pith.science/pith/H56EMAUPJZHH5BMDFTKWJTX4G6/action/replication_record"}},"created_at":"2026-07-05T09:39:32.184750+00:00","updated_at":"2026-07-05T09:39:32.184750+00:00"}