{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H56EMAUPJZHH5BMDFTKWJTX4G6","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":"7cff48e6931d5dbe67600ff0754545caef5d7542de659ae214251b4d3ac0a8ad","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T13:03:25Z","title_canon_sha256":"b66080ed398a4b667e59dc0f86e18b75c4c8a84f89b61e3edfcd56bf48a3b914"},"schema_version":"1.0","source":{"id":"2411.15270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15270","created_at":"2026-07-05T09:39:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15270v1","created_at":"2026-07-05T09:39:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15270","created_at":"2026-07-05T09:39:32Z"},{"alias_kind":"pith_short_12","alias_value":"H56EMAUPJZHH","created_at":"2026-07-05T09:39:32Z"},{"alias_kind":"pith_short_16","alias_value":"H56EMAUPJZHH5BMD","created_at":"2026-07-05T09:39:32Z"},{"alias_kind":"pith_short_8","alias_value":"H56EMAUP","created_at":"2026-07-05T09:39:32Z"}],"graph_snapshots":[{"event_id":"sha256:60d150d00704f42e71a41fc525c4d3a26d1ab0d264c98aee55ee56cf5cdf6d47","target":"graph","created_at":"2026-07-05T09:39:32Z","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/2411.15270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Md. Mohibur Rahman Nabil, Mohammad Ashrafuzzaman Khan, Muhammad Rafsan Kabir","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T13:03:25Z","title":"BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15270","kind":"arxiv","version":1},"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:d58388b3c26b5e3e236915d9480328b629f080303b62be656093e064e40c1771","target":"record","created_at":"2026-07-05T09:39:32Z","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":"7cff48e6931d5dbe67600ff0754545caef5d7542de659ae214251b4d3ac0a8ad","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T13:03:25Z","title_canon_sha256":"b66080ed398a4b667e59dc0f86e18b75c4c8a84f89b61e3edfcd56bf48a3b914"},"schema_version":"1.0","source":{"id":"2411.15270","kind":"arxiv","version":1}},"canonical_sha256":"3f7c46028f4e4e7e85832cd564cefc37993b811df75a36d47c15025232c400b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f7c46028f4e4e7e85832cd564cefc37993b811df75a36d47c15025232c400b2","first_computed_at":"2026-07-05T09:39:32.184694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:32.184694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOTrRdPnhm9Nq/SUEXEcwpWb8Z+cEkUpSyRtm4e0Hfmuv0AI7HdSi5uGlqs1iewk7uqs4lu6Ja747+apdcSwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:32.185163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d58388b3c26b5e3e236915d9480328b629f080303b62be656093e064e40c1771","sha256:60d150d00704f42e71a41fc525c4d3a26d1ab0d264c98aee55ee56cf5cdf6d47"],"state_sha256":"2b8138610ef89f3b2a719f53d105347c56b15abaa2ce42c4e8fa2e125b7c15d9"}