{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EZ5BI35ZKM4DCU6QHM2BYWFBWZ","short_pith_number":"pith:EZ5BI35Z","schema_version":"1.0","canonical_sha256":"267a146fb953383153d03b341c58a1b67c263f980e1742f455c98765ac171768","source":{"kind":"arxiv","id":"2503.24102","version":3},"attestation_state":"computed","paper":{"title":"Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cedric Lothritz, Jacques Klein, Lama Sleem, Lujun Li, Niccolo Gentile, Radu State, Saad Ezzini, Tegawend\\'e F. Bissyand\\'e, Yewei Song","submitted_at":"2025-03-31T13:56:03Z","abstract_excerpt":"Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-resource languages, especially in privacy-sensitive and resource-limited contexts. Firstly, this study systematically evaluates state-of-the-art smaller Large Language Models in 200 languages using the FLORES-200 benchmark, highlighting persistent deficiencies and disparities in the translation of LRLs. To mitigate these limitations, we investigate knowledge distillation from large pre-trained teacher models to Small La"},"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":"2503.24102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T13:56:03Z","cross_cats_sorted":[],"title_canon_sha256":"be8d652e0997be5dc08caabd6cac9085121a957916a70a3bf076ba03a71a0456","abstract_canon_sha256":"46a952a582deaf0081c7cfc5610a917dbc36b287a953397e89d60279334019da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:35.479903Z","signature_b64":"xd87Cbqo37goNHBNro5sJMwZSEYOKzHJN27wC2Goa+biAh9C+vIPZArEIa8m7dD5o78kR8dmXbl9sEZt7Ze9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"267a146fb953383153d03b341c58a1b67c263f980e1742f455c98765ac171768","last_reissued_at":"2026-07-05T11:57:35.479444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:35.479444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cedric Lothritz, Jacques Klein, Lama Sleem, Lujun Li, Niccolo Gentile, Radu State, Saad Ezzini, Tegawend\\'e F. Bissyand\\'e, Yewei Song","submitted_at":"2025-03-31T13:56:03Z","abstract_excerpt":"Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-resource languages, especially in privacy-sensitive and resource-limited contexts. Firstly, this study systematically evaluates state-of-the-art smaller Large Language Models in 200 languages using the FLORES-200 benchmark, highlighting persistent deficiencies and disparities in the translation of LRLs. To mitigate these limitations, we investigate knowledge distillation from large pre-trained teacher models to Small La"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24102","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/2503.24102/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":"2503.24102","created_at":"2026-07-05T11:57:35.479501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.24102v3","created_at":"2026-07-05T11:57:35.479501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24102","created_at":"2026-07-05T11:57:35.479501+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZ5BI35ZKM4D","created_at":"2026-07-05T11:57:35.479501+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZ5BI35ZKM4DCU6Q","created_at":"2026-07-05T11:57:35.479501+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZ5BI35Z","created_at":"2026-07-05T11:57:35.479501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01919","citing_title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","ref_index":159,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ","json":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ.json","graph_json":"https://pith.science/api/pith-number/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/graph.json","events_json":"https://pith.science/api/pith-number/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/events.json","paper":"https://pith.science/paper/EZ5BI35Z"},"agent_actions":{"view_html":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ","download_json":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ.json","view_paper":"https://pith.science/paper/EZ5BI35Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.24102&json=true","fetch_graph":"https://pith.science/api/pith-number/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/action/storage_attestation","attest_author":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/action/author_attestation","sign_citation":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/action/citation_signature","submit_replication":"https://pith.science/pith/EZ5BI35ZKM4DCU6QHM2BYWFBWZ/action/replication_record"}},"created_at":"2026-07-05T11:57:35.479501+00:00","updated_at":"2026-07-05T11:57:35.479501+00:00"}