{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OQXKNQ6II2EMT6EL5RG4MOCZXI","short_pith_number":"pith:OQXKNQ6I","schema_version":"1.0","canonical_sha256":"742ea6c3c84688c9f88bec4dc63859ba3ff7f57bdd2db6edd9cde53a1ea06e11","source":{"kind":"arxiv","id":"2204.08582","version":2},"attestation_state":"computed","paper":{"title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Nash, Ana Sanchez, Charith Peris, Christopher Hench, Gokhan Tur, Jack FitzGerald, Kay Rottmann, Laurie Crist, Liam Urbach, Misha Britan, Prem Natarajan, Richa Singh, Scott Mackie, Swetha Ranganath, Vishesh Kakarala, Wouter Leeuwis","submitted_at":"2022-04-18T22:40:52Z","abstract_excerpt":"We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M realistic, parallel, labeled virtual assistant utterances spanning 51 languages, 18 domains, 60 intents, and 55 slots. MASSIVE was created by tasking professional translators to localize the English-only SLURP dataset into 50 typologically diverse languages from 29 genera. We also present modeling results on XLM-R and mT5, including exact match accuracy, intent classification accuracy, and slot-filling F1 score. We have "},"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":"2204.08582","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T22:40:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ef515b3c53d80e32f9e3e73320ae85fbda2e790c4cffa35d5caeda9d1e712fff","abstract_canon_sha256":"4e694df6d34dccd9ccfe062f394009474cac84891574d53d6fc1ff0132704d0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:40.349522Z","signature_b64":"ya+Og6H8kPbPnPDKlO9xvFVxD7D4O+YmV1sj5rsDtg9JinJIOKBzSoOii8KAoMqAMUa7d5a7Vl/m2g46FSiZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742ea6c3c84688c9f88bec4dc63859ba3ff7f57bdd2db6edd9cde53a1ea06e11","last_reissued_at":"2026-07-05T04:32:40.349014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:40.349014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Nash, Ana Sanchez, Charith Peris, Christopher Hench, Gokhan Tur, Jack FitzGerald, Kay Rottmann, Laurie Crist, Liam Urbach, Misha Britan, Prem Natarajan, Richa Singh, Scott Mackie, Swetha Ranganath, Vishesh Kakarala, Wouter Leeuwis","submitted_at":"2022-04-18T22:40:52Z","abstract_excerpt":"We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M realistic, parallel, labeled virtual assistant utterances spanning 51 languages, 18 domains, 60 intents, and 55 slots. MASSIVE was created by tasking professional translators to localize the English-only SLURP dataset into 50 typologically diverse languages from 29 genera. We also present modeling results on XLM-R and mT5, including exact match accuracy, intent classification accuracy, and slot-filling F1 score. We have "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08582","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/2204.08582/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":"2204.08582","created_at":"2026-07-05T04:32:40.349074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08582v2","created_at":"2026-07-05T04:32:40.349074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08582","created_at":"2026-07-05T04:32:40.349074+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQXKNQ6II2EM","created_at":"2026-07-05T04:32:40.349074+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQXKNQ6II2EMT6EL","created_at":"2026-07-05T04:32:40.349074+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQXKNQ6I","created_at":"2026-07-05T04:32:40.349074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23033","citing_title":"Uncovering the Latent Potential of Deep Intermediate Representations","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14299","citing_title":"Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12687","citing_title":"Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2405.17428","citing_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2211.05100","citing_title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2211.05100","citing_title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","ref_index":156,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI","json":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI.json","graph_json":"https://pith.science/api/pith-number/OQXKNQ6II2EMT6EL5RG4MOCZXI/graph.json","events_json":"https://pith.science/api/pith-number/OQXKNQ6II2EMT6EL5RG4MOCZXI/events.json","paper":"https://pith.science/paper/OQXKNQ6I"},"agent_actions":{"view_html":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI","download_json":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI.json","view_paper":"https://pith.science/paper/OQXKNQ6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08582&json=true","fetch_graph":"https://pith.science/api/pith-number/OQXKNQ6II2EMT6EL5RG4MOCZXI/graph.json","fetch_events":"https://pith.science/api/pith-number/OQXKNQ6II2EMT6EL5RG4MOCZXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI/action/storage_attestation","attest_author":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI/action/author_attestation","sign_citation":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI/action/citation_signature","submit_replication":"https://pith.science/pith/OQXKNQ6II2EMT6EL5RG4MOCZXI/action/replication_record"}},"created_at":"2026-07-05T04:32:40.349074+00:00","updated_at":"2026-07-05T04:32:40.349074+00:00"}