{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:APPMNGL4OMNFI4PSNZ2XA5QVTA","short_pith_number":"pith:APPMNGL4","schema_version":"1.0","canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","source":{"kind":"arxiv","id":"2310.16248","version":3},"attestation_state":"computed","paper":{"title":"GlotLID: Language Identification for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hossein Kargaran, Ayyoob Imani, Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze","submitted_at":"2023-10-24T23:45:57Z","abstract_excerpt":"Several recent papers have published good solutions for language identification (LID) for about 300 high-resource and medium-resource languages. However, there is no LID available that (i) covers a wide range of low-resource languages, (ii) is rigorously evaluated and reliable and (iii) efficient and easy to use. Here, we publish GlotLID-M, an LID model that satisfies the desiderata of wide coverage, reliability and efficiency. It identifies 1665 languages, a large increase in coverage compared to prior work. In our experiments, GlotLID-M outperforms four baselines (CLD3, FT176, OpenLID and NL"},"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":"2310.16248","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T23:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"2a14e19107f936bb3d3889545a6f8f4ff65eeb11c00a484e41f6a8bae091d57a","abstract_canon_sha256":"f715a5d1dc228addc683f9cf4799267bd0f046431c468e868ab6b5f0929b0be7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:28.740787Z","signature_b64":"g06LWueMuKTuTah7wY2YyRJOTYPjnL+bH6EKs9woAdqtWtp5H/qt45aGgbCZ5J1U8YCCHk/3DOBCbqKvL9sUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","last_reissued_at":"2026-07-05T08:39:28.740247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:28.740247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GlotLID: Language Identification for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Hossein Kargaran, Ayyoob Imani, Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze","submitted_at":"2023-10-24T23:45:57Z","abstract_excerpt":"Several recent papers have published good solutions for language identification (LID) for about 300 high-resource and medium-resource languages. However, there is no LID available that (i) covers a wide range of low-resource languages, (ii) is rigorously evaluated and reliable and (iii) efficient and easy to use. Here, we publish GlotLID-M, an LID model that satisfies the desiderata of wide coverage, reliability and efficiency. It identifies 1665 languages, a large increase in coverage compared to prior work. In our experiments, GlotLID-M outperforms four baselines (CLD3, FT176, OpenLID and NL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16248","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/2310.16248/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":"2310.16248","created_at":"2026-07-05T08:39:28.740308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16248v3","created_at":"2026-07-05T08:39:28.740308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16248","created_at":"2026-07-05T08:39:28.740308+00:00"},{"alias_kind":"pith_short_12","alias_value":"APPMNGL4OMNF","created_at":"2026-07-05T08:39:28.740308+00:00"},{"alias_kind":"pith_short_16","alias_value":"APPMNGL4OMNFI4PS","created_at":"2026-07-05T08:39:28.740308+00:00"},{"alias_kind":"pith_short_8","alias_value":"APPMNGL4","created_at":"2026-07-05T08:39:28.740308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05668","citing_title":"Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA","json":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA.json","graph_json":"https://pith.science/api/pith-number/APPMNGL4OMNFI4PSNZ2XA5QVTA/graph.json","events_json":"https://pith.science/api/pith-number/APPMNGL4OMNFI4PSNZ2XA5QVTA/events.json","paper":"https://pith.science/paper/APPMNGL4"},"agent_actions":{"view_html":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA","download_json":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA.json","view_paper":"https://pith.science/paper/APPMNGL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16248&json=true","fetch_graph":"https://pith.science/api/pith-number/APPMNGL4OMNFI4PSNZ2XA5QVTA/graph.json","fetch_events":"https://pith.science/api/pith-number/APPMNGL4OMNFI4PSNZ2XA5QVTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/action/storage_attestation","attest_author":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/action/author_attestation","sign_citation":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/action/citation_signature","submit_replication":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/action/replication_record"}},"created_at":"2026-07-05T08:39:28.740308+00:00","updated_at":"2026-07-05T08:39:28.740308+00:00"}