{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMKQ7TMGXAI26MIRP46ULPUC7O","short_pith_number":"pith:TMKQ7TMG","schema_version":"1.0","canonical_sha256":"9b150fcd86b811af31117f3d45be82fb97723759a60bf6fb69b5660eb24a7155","source":{"kind":"arxiv","id":"2501.06117","version":3},"attestation_state":"computed","paper":{"title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Fabian David Schmidt, Goran Glava\\v{s}, Ivan Vuli\\'c","submitted_at":"2025-01-10T17:15:38Z","abstract_excerpt":"Spoken language understanding (SLU) is indispensable for half of all living languages that lack a formal writing system. Unlike for high-resource languages, for these languages, we cannot offload semantic understanding of speech to the cascade of automatic speech recognition (ASR) and text-based large language models (LLMs). Even if low-resource languages possess a writing system, ASR for these languages remains unreliable due to limited bimodal speech and text training data. Nonetheless, the evaluation of multilingual SLU is limited to shallow tasks such as intent classification or language i"},"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":"2501.06117","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T17:15:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8e09d2324d906c83e8513c90c5aa2923d25a1ae796b6b7829a204be4d9d5af2","abstract_canon_sha256":"c5f7c907acb4fd9978d4d45de8bad221165bbf2fc6966e13fc131c94f3968e0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:27.302701Z","signature_b64":"HKgiCytkcrYAs73nrTCySI9JzbLd74K6P4YP4LF3/eptpbf4iT4Ef0iFFDCjBbL2rYvuZ8fOOek18hGOxv/9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b150fcd86b811af31117f3d45be82fb97723759a60bf6fb69b5660eb24a7155","last_reissued_at":"2026-07-05T11:53:27.302151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:27.302151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Fabian David Schmidt, Goran Glava\\v{s}, Ivan Vuli\\'c","submitted_at":"2025-01-10T17:15:38Z","abstract_excerpt":"Spoken language understanding (SLU) is indispensable for half of all living languages that lack a formal writing system. Unlike for high-resource languages, for these languages, we cannot offload semantic understanding of speech to the cascade of automatic speech recognition (ASR) and text-based large language models (LLMs). Even if low-resource languages possess a writing system, ASR for these languages remains unreliable due to limited bimodal speech and text training data. Nonetheless, the evaluation of multilingual SLU is limited to shallow tasks such as intent classification or language i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06117","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/2501.06117/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":"2501.06117","created_at":"2026-07-05T11:53:27.302205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06117v3","created_at":"2026-07-05T11:53:27.302205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06117","created_at":"2026-07-05T11:53:27.302205+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMKQ7TMGXAI2","created_at":"2026-07-05T11:53:27.302205+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMKQ7TMGXAI26MIR","created_at":"2026-07-05T11:53:27.302205+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMKQ7TMG","created_at":"2026-07-05T11:53:27.302205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08194","citing_title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O","json":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O.json","graph_json":"https://pith.science/api/pith-number/TMKQ7TMGXAI26MIRP46ULPUC7O/graph.json","events_json":"https://pith.science/api/pith-number/TMKQ7TMGXAI26MIRP46ULPUC7O/events.json","paper":"https://pith.science/paper/TMKQ7TMG"},"agent_actions":{"view_html":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O","download_json":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O.json","view_paper":"https://pith.science/paper/TMKQ7TMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06117&json=true","fetch_graph":"https://pith.science/api/pith-number/TMKQ7TMGXAI26MIRP46ULPUC7O/graph.json","fetch_events":"https://pith.science/api/pith-number/TMKQ7TMGXAI26MIRP46ULPUC7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O/action/storage_attestation","attest_author":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O/action/author_attestation","sign_citation":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O/action/citation_signature","submit_replication":"https://pith.science/pith/TMKQ7TMGXAI26MIRP46ULPUC7O/action/replication_record"}},"created_at":"2026-07-05T11:53:27.302205+00:00","updated_at":"2026-07-05T11:53:27.302205+00:00"}