{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:APPMNGL4OMNFI4PSNZ2XA5QVTA","short_pith_number":"pith:APPMNGL4","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"},"canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","source":{"kind":"arxiv","id":"2310.16248","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:APPMNGL4OMNFI4PSNZ2XA5QVTA","target":"record","payload":{"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"},"canonical_sha256":"03dec6997c731a5471f26e7570761598342e5c0b3962ee3487a34f9eb7f1c49e","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"},"source_kind":"arxiv","source_id":"2310.16248","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYes/Rj/NcAfyWpQxnDUIFH7XvkUgkec1sa1IRZcxE/oj9wl8Wsgrms0K6DLNY/LPhsU/AIxGekRgQ4u+ggSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:33:09.730469Z"},"content_sha256":"01bfda7e1f70d5ed300a9277a00794ca616bf72eb165b525db1a1db8a715c3ab","schema_version":"1.0","event_id":"sha256:01bfda7e1f70d5ed300a9277a00794ca616bf72eb165b525db1a1db8a715c3ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:APPMNGL4OMNFI4PSNZ2XA5QVTA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjuX+eqGyXKN0EKZThiSGPaePNo050DdWOVJoObPAJ4lx8toMkXhdPj6mBPp7OahgJ5U8rF2V4UTdNaq5+raAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:33:09.730973Z"},"content_sha256":"92eaa2a9967f6b190265768a8934458fbb5dd1fab39e1f70c2eb9bf35b2ba532","schema_version":"1.0","event_id":"sha256:92eaa2a9967f6b190265768a8934458fbb5dd1fab39e1f70c2eb9bf35b2ba532"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/bundle.json","state_url":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T18:33:09Z","links":{"resolver":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA","bundle":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/bundle.json","state":"https://pith.science/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APPMNGL4OMNFI4PSNZ2XA5QVTA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkSsmKcg6i4U8YqA+Zc0JFIKQwY9RjoHOcTV8AM9hml5rcsHtnqR5VHs7vRP9AYYLLsJQlXLT9x0Km2zAjBDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:33:09.734418Z","bundle_sha256":"e8382a0537a84b9171deb39bb354f891963e92891c68f5678a3c8b727ab4f473"}}