{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KNXK4NIKF4LJT2DJUQQUDSTSZ2","short_pith_number":"pith:KNXK4NIK","schema_version":"1.0","canonical_sha256":"536eae350a2f1699e869a42141ca72ceb6f13944371384a2e191e6ae7e2c3526","source":{"kind":"arxiv","id":"2210.08523","version":2},"attestation_state":"computed","paper":{"title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nisansa de Silva, Surangika Ranathunga","submitted_at":"2022-10-16T12:50:30Z","abstract_excerpt":"Linguistic disparity in the NLP world is a problem that has been widely acknowledged recently. However, different facets of this problem, or the reasons behind this disparity are seldom discussed within the NLP community. This paper provides a comprehensive analysis of the disparity that exists within the languages of the world. We show that simply categorising languages considering data availability may not be always correct. Using an existing language categorisation based on speaker population and vitality, we analyse the distribution of language data resources, amount of NLP/CL research, in"},"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":"2210.08523","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-16T12:50:30Z","cross_cats_sorted":[],"title_canon_sha256":"695e4ad05b039db1687baf6118ddf2155f167f2d62771a46e58cc817489af907","abstract_canon_sha256":"da995c07437cd7022ba3568b4c6569c68b816dd1ee864a827d93ff04d6752ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:31.569719Z","signature_b64":"0uG8yxxsevPXpHH2wAWiNUDGBVRSAq+816obC9sQsWlQjEKQgSsD/x1XuoVfWar3/2Y26XiQOkujBIsVBRCQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"536eae350a2f1699e869a42141ca72ceb6f13944371384a2e191e6ae7e2c3526","last_reissued_at":"2026-07-05T05:08:31.569337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:31.569337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nisansa de Silva, Surangika Ranathunga","submitted_at":"2022-10-16T12:50:30Z","abstract_excerpt":"Linguistic disparity in the NLP world is a problem that has been widely acknowledged recently. However, different facets of this problem, or the reasons behind this disparity are seldom discussed within the NLP community. This paper provides a comprehensive analysis of the disparity that exists within the languages of the world. We show that simply categorising languages considering data availability may not be always correct. Using an existing language categorisation based on speaker population and vitality, we analyse the distribution of language data resources, amount of NLP/CL research, in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08523","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/2210.08523/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":"2210.08523","created_at":"2026-07-05T05:08:31.569391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08523v2","created_at":"2026-07-05T05:08:31.569391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08523","created_at":"2026-07-05T05:08:31.569391+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNXK4NIKF4LJ","created_at":"2026-07-05T05:08:31.569391+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNXK4NIKF4LJT2DJ","created_at":"2026-07-05T05:08:31.569391+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNXK4NIK","created_at":"2026-07-05T05:08:31.569391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19885","citing_title":"Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2","json":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2.json","graph_json":"https://pith.science/api/pith-number/KNXK4NIKF4LJT2DJUQQUDSTSZ2/graph.json","events_json":"https://pith.science/api/pith-number/KNXK4NIKF4LJT2DJUQQUDSTSZ2/events.json","paper":"https://pith.science/paper/KNXK4NIK"},"agent_actions":{"view_html":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2","download_json":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2.json","view_paper":"https://pith.science/paper/KNXK4NIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08523&json=true","fetch_graph":"https://pith.science/api/pith-number/KNXK4NIKF4LJT2DJUQQUDSTSZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/KNXK4NIKF4LJT2DJUQQUDSTSZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2/action/storage_attestation","attest_author":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2/action/author_attestation","sign_citation":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2/action/citation_signature","submit_replication":"https://pith.science/pith/KNXK4NIKF4LJT2DJUQQUDSTSZ2/action/replication_record"}},"created_at":"2026-07-05T05:08:31.569391+00:00","updated_at":"2026-07-05T05:08:31.569391+00:00"}