{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZOBZA6VH3T6XVPEI3LCCIMTY32","short_pith_number":"pith:ZOBZA6VH","schema_version":"1.0","canonical_sha256":"cb83907aa7dcfd7abc88dac4243278dea76c2edc22038825b67f1de87efa2ff7","source":{"kind":"arxiv","id":"2004.09095","version":3},"attestation_state":"computed","paper":{"title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amar Budhiraja, Kalika Bali, Monojit Choudhury, Pratik Joshi, Sebastin Santy","submitted_at":"2020-04-20T07:19:22Z","abstract_excerpt":"Language technologies contribute to promoting multilingualism and linguistic diversity around the world. However, only a very small number of the over 7000 languages of the world are represented in the rapidly evolving language technologies and applications. In this paper we look at the relation between the types of languages, resources, and their representation in NLP conferences to understand the trajectory that different languages have followed over time. Our quantitative investigation underlines the disparity between languages, especially in terms of their resources, and calls into questio"},"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":"2004.09095","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T07:19:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad0a9e162cc5f0f86b53111b4ba6c93fda67f9b07848f34fc07b116608a88a34","abstract_canon_sha256":"410596f3d018b329461e3e6aa08c3416afde68f1e3e657fea96879d97035ba4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:06.090777Z","signature_b64":"ukG27zLlRRy44oBJtF5/o62M+YsaxSla9NiIhloVp/KQBtYlYadpXeMn5C/093fIsuMiiyg5r52tmI/t8XjQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb83907aa7dcfd7abc88dac4243278dea76c2edc22038825b67f1de87efa2ff7","last_reissued_at":"2026-07-05T02:10:06.090431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:06.090431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amar Budhiraja, Kalika Bali, Monojit Choudhury, Pratik Joshi, Sebastin Santy","submitted_at":"2020-04-20T07:19:22Z","abstract_excerpt":"Language technologies contribute to promoting multilingualism and linguistic diversity around the world. However, only a very small number of the over 7000 languages of the world are represented in the rapidly evolving language technologies and applications. In this paper we look at the relation between the types of languages, resources, and their representation in NLP conferences to understand the trajectory that different languages have followed over time. Our quantitative investigation underlines the disparity between languages, especially in terms of their resources, and calls into questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09095","kind":"arxiv","version":3},"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/2004.09095/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":"2004.09095","created_at":"2026-07-05T02:10:06.090487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.09095v3","created_at":"2026-07-05T02:10:06.090487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09095","created_at":"2026-07-05T02:10:06.090487+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOBZA6VH3T6X","created_at":"2026-07-05T02:10:06.090487+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOBZA6VH3T6XVPEI","created_at":"2026-07-05T02:10:06.090487+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOBZA6VH","created_at":"2026-07-05T02:10:06.090487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":44,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.08362","citing_title":"Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.07669","citing_title":"DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2607.05992","citing_title":"PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02235","citing_title":"Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03043","citing_title":"The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28843","citing_title":"The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30175","citing_title":"CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28163","citing_title":"DEPART: DEcomposing PARiTy across Multilingual LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07597","citing_title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00285","citing_title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00333","citing_title":"Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01252","citing_title":"Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02147","citing_title":"Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02465","citing_title":"Learning When to Translate for Multilingual Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04661","citing_title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06349","citing_title":"\"Chi nas dal soch el sent de legn\" -- Auditing Text Corpora for Lombard","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06428","citing_title":"Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07422","citing_title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08451","citing_title":"Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09435","citing_title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09553","citing_title":"OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13537","citing_title":"When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16009","citing_title":"Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21413","citing_title":"CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23164","citing_title":"Same question, different history: language, national identity, and credit in large language models","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32","json":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32.json","graph_json":"https://pith.science/api/pith-number/ZOBZA6VH3T6XVPEI3LCCIMTY32/graph.json","events_json":"https://pith.science/api/pith-number/ZOBZA6VH3T6XVPEI3LCCIMTY32/events.json","paper":"https://pith.science/paper/ZOBZA6VH"},"agent_actions":{"view_html":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32","download_json":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32.json","view_paper":"https://pith.science/paper/ZOBZA6VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.09095&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOBZA6VH3T6XVPEI3LCCIMTY32/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOBZA6VH3T6XVPEI3LCCIMTY32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32/action/storage_attestation","attest_author":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32/action/author_attestation","sign_citation":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32/action/citation_signature","submit_replication":"https://pith.science/pith/ZOBZA6VH3T6XVPEI3LCCIMTY32/action/replication_record"}},"created_at":"2026-07-05T02:10:06.090487+00:00","updated_at":"2026-07-05T02:10:06.090487+00:00"}