{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OIDFK2EEDEQQ5DFIJXCT3PODFU","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":"5f5611f0b0e8474feacb968a97b31ef1e70e60c63182f864f9cc0e908e815a4f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-27T19:29:17Z","title_canon_sha256":"8a9f1da9ffa8ae0d21d90477d143754de5510cce81bc6e95e68f2e871c9a91bd"},"schema_version":"1.0","source":{"id":"2010.14571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14571","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14571v2","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14571","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"OIDFK2EEDEQQ","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"OIDFK2EEDEQQ5DFI","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"OIDFK2EE","created_at":"2026-07-05T01:47:33Z"}],"graph_snapshots":[{"event_id":"sha256:e9708abe86c979bfc1e71a103480e2863a5c90c87041e15f8b1533f9e8a55637","target":"graph","created_at":"2026-07-05T01:47:33Z","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/2010.14571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large text corpora are increasingly important for a wide variety of Natural Language Processing (NLP) tasks, and automatic language identification (LangID) is a core technology needed to collect such datasets in a multilingual context. LangID is largely treated as solved in the literature, with models reported that achieve over 90% average F1 on as many as 1,366 languages. We train LangID models on up to 1,629 languages with comparable quality on held-out test sets, but find that human-judged LangID accuracy for web-crawl text corpora created using these models is only around 5% for many lower","authors_text":"Ankur Bapna, Daan van Esch, Isaac Caswell, Theresa Breiner","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-27T19:29:17Z","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14571","kind":"arxiv","version":2},"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:e2c849af9ed05c079dd83fd011a9955373918647c64a79f50edda416fb5dc19b","target":"record","created_at":"2026-07-05T01:47:33Z","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":"5f5611f0b0e8474feacb968a97b31ef1e70e60c63182f864f9cc0e908e815a4f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-27T19:29:17Z","title_canon_sha256":"8a9f1da9ffa8ae0d21d90477d143754de5510cce81bc6e95e68f2e871c9a91bd"},"schema_version":"1.0","source":{"id":"2010.14571","kind":"arxiv","version":2}},"canonical_sha256":"720655688419210e8ca84dc53dbdc32d3391d03bfc0b7ff251ee904376dc5bb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"720655688419210e8ca84dc53dbdc32d3391d03bfc0b7ff251ee904376dc5bb4","first_computed_at":"2026-07-05T01:47:33.717228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:33.717228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xI+fPmECVmd7kobMxM3vN9OC/0oEc5j6L1wUxSlOto3xsqhj5dcc03Ihpv7Y4d+sCgjshC7AKwQ475C+9qTPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:33.717778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2c849af9ed05c079dd83fd011a9955373918647c64a79f50edda416fb5dc19b","sha256:e9708abe86c979bfc1e71a103480e2863a5c90c87041e15f8b1533f9e8a55637"],"state_sha256":"2252e65a26357a74aa53991d6ccf782f0c80b900973201cca4e0272926cadcb2"}