{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BPU7F5FS3MZKDLZ6VSHGSWHXWG","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":"e08be450b3e198bfb191ead2ca2841fe2fe45502ff07ebc37467b2824e36b0c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:15:43Z","title_canon_sha256":"7c85b7c47a88b2583b778734d6164d9b06bfade93ecf0bc5966a8c8afb7b93fd"},"schema_version":"1.0","source":{"id":"2305.14263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14263","created_at":"2026-07-05T07:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14263v2","created_at":"2026-07-05T07:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14263","created_at":"2026-07-05T07:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"BPU7F5FS3MZK","created_at":"2026-07-05T07:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"BPU7F5FS3MZKDLZ6","created_at":"2026-07-05T07:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"BPU7F5FS","created_at":"2026-07-05T07:09:28Z"}],"graph_snapshots":[{"event_id":"sha256:1fd330e5ec01bb12169f5903d68066871f7b308f414e28293ba9536aa848cdeb","target":"graph","created_at":"2026-07-05T07:09:28Z","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/2305.14263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowing the language of an input text/audio is a necessary first step for using almost every NLP tool such as taggers, parsers, or translation systems. Language identification is a well-studied problem, sometimes even considered solved; in reality, due to lack of data and computational challenges, current systems cannot accurately identify most of the world's 7000 languages. To tackle this bottleneck, we first compile a corpus, MCS-350, of 50K multilingual and parallel children's stories in 350+ languages. MCS-350 can serve as a benchmark for language identification of short texts and for 1400","authors_text":"Antonios Anastasopoulos, Md Mahfuz ibn Alam, Milind Agarwal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:15:43Z","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14263","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":"sha256:536cf950d32b638ded0cd928929ab5f88a78beea151af11a581394ec942fdab6","target":"record","created_at":"2026-07-05T07:09:28Z","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":"e08be450b3e198bfb191ead2ca2841fe2fe45502ff07ebc37467b2824e36b0c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:15:43Z","title_canon_sha256":"7c85b7c47a88b2583b778734d6164d9b06bfade93ecf0bc5966a8c8afb7b93fd"},"schema_version":"1.0","source":{"id":"2305.14263","kind":"arxiv","version":2}},"canonical_sha256":"0be9f2f4b2db32a1af3eac8e6958f7b19b8b60c5d45784193ad0150ae355014e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be9f2f4b2db32a1af3eac8e6958f7b19b8b60c5d45784193ad0150ae355014e","first_computed_at":"2026-07-05T07:09:28.879833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:28.879833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/oJEE4VR4Vuaa4g9E7Q7TpdzWpYLDDQKyC8/zYATkSBYfV2Sm0A0APHbgbHAtaCQsczvXldXYAjIHmDar2ptAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:28.880336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:536cf950d32b638ded0cd928929ab5f88a78beea151af11a581394ec942fdab6","sha256:1fd330e5ec01bb12169f5903d68066871f7b308f414e28293ba9536aa848cdeb"],"state_sha256":"d618b0e262d8290ae9af2ab91356d48f11b0967fdb5ccfccf35dcddc8a361478"}