{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VBEKGOOLLEJ3P7TRFCTW6QFZNA","short_pith_number":"pith:VBEKGOOL","schema_version":"1.0","canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","source":{"kind":"arxiv","id":"2103.10730","version":2},"attestation_state":"computed","paper":{"title":"MuRIL: Multilingual Representations for Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atreyee Dey, Balaji Gopalan, Diksha Bansal, Dilip Kumar Margam, Partha Talukdar, Pooja Aggarwal, Rajiv Teja Nagipogu, Sarvesh Mehtani, Savya Khosla, Shachi Dave, Shruti Gupta, Simran Khanuja, Subhash Chandra Bose Gali, Vish Subramanian","submitted_at":"2021-03-19T11:06:37Z","abstract_excerpt":"India is a multilingual society with 1369 rationalized languages and dialects being spoken across the country (INDIA, 2011). Of these, the 22 scheduled languages have a staggering total of 1.17 billion speakers and 121 languages have more than 10,000 speakers (INDIA, 2011). India also has the second largest (and an ever growing) digital footprint (Statista, 2020). Despite this, today's state-of-the-art multilingual systems perform suboptimally on Indian (IN) languages. This can be explained by the fact that multilingual language models (LMs) are often trained on 100+ languages together, leadin"},"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":"2103.10730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-19T11:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"e6b06769904e7a34baad5fab7a66ddc47781977ca94f2715cce0d89a03a8304c","abstract_canon_sha256":"e5db59bfb2d07aefdef66e94e7893e98b4b3c0f15b2eeebd46dcd430adc901b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:34.512087Z","signature_b64":"EleBkALcbfwlXxZ2/ulM6AFQKsWVneEKs7+laHkqppEv06RaiKPw/RtjEUycOQCqzTtHPrhypfFCfe+HgLatAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a848a339cb5913b7fe7128a76f40b9681ea3ca5f5c93a564864e8ae4b93491ed","last_reissued_at":"2026-07-05T02:28:34.511481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:34.511481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuRIL: Multilingual Representations for Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atreyee Dey, Balaji Gopalan, Diksha Bansal, Dilip Kumar Margam, Partha Talukdar, Pooja Aggarwal, Rajiv Teja Nagipogu, Sarvesh Mehtani, Savya Khosla, Shachi Dave, Shruti Gupta, Simran Khanuja, Subhash Chandra Bose Gali, Vish Subramanian","submitted_at":"2021-03-19T11:06:37Z","abstract_excerpt":"India is a multilingual society with 1369 rationalized languages and dialects being spoken across the country (INDIA, 2011). Of these, the 22 scheduled languages have a staggering total of 1.17 billion speakers and 121 languages have more than 10,000 speakers (INDIA, 2011). India also has the second largest (and an ever growing) digital footprint (Statista, 2020). Despite this, today's state-of-the-art multilingual systems perform suboptimally on Indian (IN) languages. This can be explained by the fact that multilingual language models (LMs) are often trained on 100+ languages together, leadin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10730","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/2103.10730/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":"2103.10730","created_at":"2026-07-05T02:28:34.511565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10730v2","created_at":"2026-07-05T02:28:34.511565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10730","created_at":"2026-07-05T02:28:34.511565+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBEKGOOLLEJ3","created_at":"2026-07-05T02:28:34.511565+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBEKGOOLLEJ3P7TR","created_at":"2026-07-05T02:28:34.511565+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBEKGOOL","created_at":"2026-07-05T02:28:34.511565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09345","citing_title":"A study on the impact of region specific data on the performance of Indic ASR","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08272","citing_title":"AgriGov: A Structured Multilingual Dataset Curation for Indian Government Schemes for Farmers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10636","citing_title":"Mitigating Extrinsic Gender Bias for Bangla Classification Tasks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01486","citing_title":"Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18423","citing_title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11066","citing_title":"ks-pret-5m: a 5 million word, 12 million token kashmiri pretraining dataset","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18722","citing_title":"Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21370","citing_title":"MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA","json":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA.json","graph_json":"https://pith.science/api/pith-number/VBEKGOOLLEJ3P7TRFCTW6QFZNA/graph.json","events_json":"https://pith.science/api/pith-number/VBEKGOOLLEJ3P7TRFCTW6QFZNA/events.json","paper":"https://pith.science/paper/VBEKGOOL"},"agent_actions":{"view_html":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA","download_json":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA.json","view_paper":"https://pith.science/paper/VBEKGOOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10730&json=true","fetch_graph":"https://pith.science/api/pith-number/VBEKGOOLLEJ3P7TRFCTW6QFZNA/graph.json","fetch_events":"https://pith.science/api/pith-number/VBEKGOOLLEJ3P7TRFCTW6QFZNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/action/storage_attestation","attest_author":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/action/author_attestation","sign_citation":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/action/citation_signature","submit_replication":"https://pith.science/pith/VBEKGOOLLEJ3P7TRFCTW6QFZNA/action/replication_record"}},"created_at":"2026-07-05T02:28:34.511565+00:00","updated_at":"2026-07-05T02:28:34.511565+00:00"}