{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XKPRBHEAWLFQHOZTC7EZHSNSNR","short_pith_number":"pith:XKPRBHEA","schema_version":"1.0","canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","source":{"kind":"arxiv","id":"1801.07779","version":1},"attestation_state":"computed","paper":{"title":"The WiLI benchmark dataset for written language identification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Martin Thoma","submitted_at":"2018-01-23T21:40:53Z","abstract_excerpt":"This paper describes the WiLI-2018 benchmark dataset for monolingual written natural language identification. WiLI-2018 is a publicly available, free of charge dataset of short text extracts from Wikipedia. It contains 1000 paragraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a classification dataset: Given an unknown paragraph written in one dominant language, it has to be decided which language it is."},"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":"1801.07779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-01-23T21:40:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1482c9166ce0cbaec55a6c1e88ec499700e620826dab697320f306a84df6c02","abstract_canon_sha256":"5487e607f9f5bbdffb79823a0d044db84b2a59ff36f42b9882def6f7a04907cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:10.882669Z","signature_b64":"HIClHtzNlo6fSFS76F7U57Gs+OB9dhorNAQ4h8gBx3WRneaMXHOqsLz7lT+sUVH6WFNiVTgF74zTJ/gtrpfXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba9f109c80b2cb03bb3317c993c9b26c66debfaff94d36d3e944d3efbf7afb04","last_reissued_at":"2026-05-18T00:25:10.881992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:10.881992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The WiLI benchmark dataset for written language identification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Martin Thoma","submitted_at":"2018-01-23T21:40:53Z","abstract_excerpt":"This paper describes the WiLI-2018 benchmark dataset for monolingual written natural language identification. WiLI-2018 is a publicly available, free of charge dataset of short text extracts from Wikipedia. It contains 1000 paragraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a classification dataset: Given an unknown paragraph written in one dominant language, it has to be decided which language it is."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07779","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1801.07779","created_at":"2026-05-18T00:25:10.882088+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.07779v1","created_at":"2026-05-18T00:25:10.882088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07779","created_at":"2026-05-18T00:25:10.882088+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKPRBHEAWLFQ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKPRBHEAWLFQHOZT","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKPRBHEA","created_at":"2026-05-18T12:33:01.666342+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/XKPRBHEAWLFQHOZTC7EZHSNSNR","json":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR.json","graph_json":"https://pith.science/api/pith-number/XKPRBHEAWLFQHOZTC7EZHSNSNR/graph.json","events_json":"https://pith.science/api/pith-number/XKPRBHEAWLFQHOZTC7EZHSNSNR/events.json","paper":"https://pith.science/paper/XKPRBHEA"},"agent_actions":{"view_html":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR","download_json":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR.json","view_paper":"https://pith.science/paper/XKPRBHEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.07779&json=true","fetch_graph":"https://pith.science/api/pith-number/XKPRBHEAWLFQHOZTC7EZHSNSNR/graph.json","fetch_events":"https://pith.science/api/pith-number/XKPRBHEAWLFQHOZTC7EZHSNSNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/action/storage_attestation","attest_author":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/action/author_attestation","sign_citation":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/action/citation_signature","submit_replication":"https://pith.science/pith/XKPRBHEAWLFQHOZTC7EZHSNSNR/action/replication_record"}},"created_at":"2026-05-18T00:25:10.882088+00:00","updated_at":"2026-05-18T00:25:10.882088+00:00"}