{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APPMNGL4OMNFI4PSNZ2XA5QVTA","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":"f715a5d1dc228addc683f9cf4799267bd0f046431c468e868ab6b5f0929b0be7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T23:45:57Z","title_canon_sha256":"2a14e19107f936bb3d3889545a6f8f4ff65eeb11c00a484e41f6a8bae091d57a"},"schema_version":"1.0","source":{"id":"2310.16248","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16248","created_at":"2026-07-05T08:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16248v3","created_at":"2026-07-05T08:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16248","created_at":"2026-07-05T08:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"APPMNGL4OMNF","created_at":"2026-07-05T08:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"APPMNGL4OMNFI4PS","created_at":"2026-07-05T08:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"APPMNGL4","created_at":"2026-07-05T08:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:92eaa2a9967f6b190265768a8934458fbb5dd1fab39e1f70c2eb9bf35b2ba532","target":"graph","created_at":"2026-07-05T08:39:28Z","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/2310.16248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amir Hossein Kargaran, Ayyoob Imani, Fran\\c{c}ois Yvon, Hinrich Sch\\\"utze","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T23:45:57Z","title":"GlotLID: Language Identification for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16248","kind":"arxiv","version":3},"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":"sha256:01bfda7e1f70d5ed300a9277a00794ca616bf72eb165b525db1a1db8a715c3ab","target":"record","created_at":"2026-07-05T08:39:28Z","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":"f715a5d1dc228addc683f9cf4799267bd0f046431c468e868ab6b5f0929b0be7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T23:45:57Z","title_canon_sha256":"2a14e19107f936bb3d3889545a6f8f4ff65eeb11c00a484e41f6a8bae091d57a"},"schema_version":"1.0","source":{"id":"2310.16248","kind":"arxiv","version":3}},"canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","first_computed_at":"2026-07-05T08:39:28.740247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:28.740247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g06LWueMuKTuTah7wY2YyRJOTYPjnL+bH6EKs9woAdqtWtp5H/qt45aGgbCZ5J1U8YCCHk/3DOBCbqKvL9sUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:28.740787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16248","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01bfda7e1f70d5ed300a9277a00794ca616bf72eb165b525db1a1db8a715c3ab","sha256:92eaa2a9967f6b190265768a8934458fbb5dd1fab39e1f70c2eb9bf35b2ba532"],"state_sha256":"0765de3914a8267f0106f8b60113e1df2434087139c3815ddaadaa3d44905257"}