{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZCV36EI5LYQQLCDFZDBBDUFSRH","short_pith_number":"pith:ZCV36EI5","schema_version":"1.0","canonical_sha256":"c8abbf111d5e21058865c8c211d0b289ecb67095b0f607dfe2ec36e3ad82660f","source":{"kind":"arxiv","id":"2107.00676","version":2},"attestation_state":"computed","paper":{"title":"A Primer on Pretrained Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Gowtham Ramesh, Mitesh M. Khapra, Pratyush Kumar, Sumanth Doddapaneni","submitted_at":"2021-07-01T18:01:46Z","abstract_excerpt":"Multilingual Language Models (\\MLLMs) such as mBERT, XLM, XLM-R, \\textit{etc.} have emerged as a viable option for bringing the power of pretraining to a large number of languages. Given their success in zero-shot transfer learning, there has emerged a large body of work in (i) building bigger \\MLLMs~covering a large number of languages (ii) creating exhaustive benchmarks covering a wider variety of tasks and languages for evaluating \\MLLMs~ (iii) analysing the performance of \\MLLMs~on monolingual, zero-shot cross-lingual and bilingual tasks (iv) understanding the universal language patterns ("},"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":"2107.00676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-01T18:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"6ba034a79f62d8035fba21e24ea08282575fe74e70333bf78f12027b46e40f81","abstract_canon_sha256":"e87686b396f1bde7efedc4416fe09b3ea8fdedf72d927a3165b4327d70b9404b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:25.560328Z","signature_b64":"rnlMBRjLOkdWZUCTRi1xSePFnsmrtG2tlEvzPB22Z0OH4+18UkG4v4JZkR3EK0zmIpQQOu2pY0Dic29Mez+XCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8abbf111d5e21058865c8c211d0b289ecb67095b0f607dfe2ec36e3ad82660f","last_reissued_at":"2026-07-05T03:43:25.559913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:25.559913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Primer on Pretrained Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Gowtham Ramesh, Mitesh M. Khapra, Pratyush Kumar, Sumanth Doddapaneni","submitted_at":"2021-07-01T18:01:46Z","abstract_excerpt":"Multilingual Language Models (\\MLLMs) such as mBERT, XLM, XLM-R, \\textit{etc.} have emerged as a viable option for bringing the power of pretraining to a large number of languages. Given their success in zero-shot transfer learning, there has emerged a large body of work in (i) building bigger \\MLLMs~covering a large number of languages (ii) creating exhaustive benchmarks covering a wider variety of tasks and languages for evaluating \\MLLMs~ (iii) analysing the performance of \\MLLMs~on monolingual, zero-shot cross-lingual and bilingual tasks (iv) understanding the universal language patterns ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00676","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/2107.00676/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":"2107.00676","created_at":"2026-07-05T03:43:25.559975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00676v2","created_at":"2026-07-05T03:43:25.559975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00676","created_at":"2026-07-05T03:43:25.559975+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCV36EI5LYQQ","created_at":"2026-07-05T03:43:25.559975+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCV36EI5LYQQLCDF","created_at":"2026-07-05T03:43:25.559975+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCV36EI5","created_at":"2026-07-05T03:43:25.559975+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/ZCV36EI5LYQQLCDFZDBBDUFSRH","json":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH.json","graph_json":"https://pith.science/api/pith-number/ZCV36EI5LYQQLCDFZDBBDUFSRH/graph.json","events_json":"https://pith.science/api/pith-number/ZCV36EI5LYQQLCDFZDBBDUFSRH/events.json","paper":"https://pith.science/paper/ZCV36EI5"},"agent_actions":{"view_html":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH","download_json":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH.json","view_paper":"https://pith.science/paper/ZCV36EI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00676&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCV36EI5LYQQLCDFZDBBDUFSRH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCV36EI5LYQQLCDFZDBBDUFSRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH/action/storage_attestation","attest_author":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH/action/author_attestation","sign_citation":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH/action/citation_signature","submit_replication":"https://pith.science/pith/ZCV36EI5LYQQLCDFZDBBDUFSRH/action/replication_record"}},"created_at":"2026-07-05T03:43:25.559975+00:00","updated_at":"2026-07-05T03:43:25.559975+00:00"}