{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OOCKTPTLBWUGCW4QQQLXDKLYBM","short_pith_number":"pith:OOCKTPTL","schema_version":"1.0","canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","source":{"kind":"arxiv","id":"2602.17655","version":2},"attestation_state":"computed","paper":{"title":"What Language is This? Ask Your Tokenizer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmetcan Yavuz, Clara Meister, Pietro Lesci, Tiago Pimentel","submitted_at":"2026-02-19T18:58:39Z","abstract_excerpt":"Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm, leveraging its probabilistic framing, parameter estimation technique and inference strategy. In short, to predict a s"},"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":"2602.17655","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T18:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"cfac3cac02070e899ab314812f3d2ada03b920019f38caaed920694ade7de773","abstract_canon_sha256":"28dd4e9e81c1ea84271dfac1d9209bd96d1d570af73ef1132724723ec1043bfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:28.498626Z","signature_b64":"vdGgke6PO7gUY/A7Whz1lvskCKmnVo0JYQWEx6SWyOVffDyeDdpw/+HUhAI7cl0fs6iwfeqtj6NMN7nHLR0YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7384a9be6b0da8615b90841771a9780b0117623d41400860c3c7be5301d65536","last_reissued_at":"2026-06-23T03:14:28.498104Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:28.498104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Language is This? Ask Your Tokenizer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmetcan Yavuz, Clara Meister, Pietro Lesci, Tiago Pimentel","submitted_at":"2026-02-19T18:58:39Z","abstract_excerpt":"Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite near-perfect performance on high-resource languages, existing systems remain brittle in low-resource and closely related language settings. We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm, leveraging its probabilistic framing, parameter estimation technique and inference strategy. In short, to predict a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17655","kind":"arxiv","version":2},"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/2602.17655/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":"2602.17655","created_at":"2026-06-23T03:14:28.498165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17655v2","created_at":"2026-06-23T03:14:28.498165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17655","created_at":"2026-06-23T03:14:28.498165+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOCKTPTLBWUG","created_at":"2026-06-23T03:14:28.498165+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOCKTPTLBWUGCW4Q","created_at":"2026-06-23T03:14:28.498165+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOCKTPTL","created_at":"2026-06-23T03:14:28.498165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM","json":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM.json","graph_json":"https://pith.science/api/pith-number/OOCKTPTLBWUGCW4QQQLXDKLYBM/graph.json","events_json":"https://pith.science/api/pith-number/OOCKTPTLBWUGCW4QQQLXDKLYBM/events.json","paper":"https://pith.science/paper/OOCKTPTL"},"agent_actions":{"view_html":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM","download_json":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM.json","view_paper":"https://pith.science/paper/OOCKTPTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17655&json=true","fetch_graph":"https://pith.science/api/pith-number/OOCKTPTLBWUGCW4QQQLXDKLYBM/graph.json","fetch_events":"https://pith.science/api/pith-number/OOCKTPTLBWUGCW4QQQLXDKLYBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/action/storage_attestation","attest_author":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/action/author_attestation","sign_citation":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/action/citation_signature","submit_replication":"https://pith.science/pith/OOCKTPTLBWUGCW4QQQLXDKLYBM/action/replication_record"}},"created_at":"2026-06-23T03:14:28.498165+00:00","updated_at":"2026-06-23T03:14:28.498165+00:00"}