{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24WTOC4PVZNV7TOHAPW2SODZ3M","short_pith_number":"pith:24WTOC4P","schema_version":"1.0","canonical_sha256":"d72d370b8fae5b5fcdc703eda93879db320f6f3e3a2995c48b06d9d268fb1561","source":{"kind":"arxiv","id":"2509.07139","version":1},"attestation_state":"computed","paper":{"title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Antonis Anastasopoulos, Chutong Meng, Dan Jurafsky, Hsiu-Hsuan Wang, Hung-yi Lee, Jiatong Shi, Karen Livescu, Martijn Bartelds, Rafael Mosquera, Sara Hincapie, Shih-Heng Wang, Shinji Watanabe, William Chen","submitted_at":"2025-09-08T18:42:36Z","abstract_excerpt":"Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Interspeech 2025 ML-SUPERB 2.0 Challenge. We construct a new test suite that consists of data from 200+ languages, accents, and dialects to evaluate SOTA multilingual speech models. The challenge also introduces an online evaluation server based on DynaBench, allowing for flexibility in model design and architecture for participants. The challenge received 5 submissions from 3 teams, all of which outperformed our baseli"},"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":"2509.07139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T18:42:36Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"445ecad33b15dc768d7dec6c3c7679ba59d4b2da7b39e3cccabd6797b6271a90","abstract_canon_sha256":"a2c3e27eb9363a20177ef13fbe800f3be9cc289262228221264748201c5d1565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:16.304178Z","signature_b64":"Fi176OIlDzoAp5vVq4dSTiSwEQQfCKNKbKM/LbuUDNEtr7EoXu8GmVyt54aDUvyjqFuqlFhW8k5nL+kltbDJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72d370b8fae5b5fcdc703eda93879db320f6f3e3a2995c48b06d9d268fb1561","last_reissued_at":"2026-07-05T12:07:16.303703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:16.303703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Antonis Anastasopoulos, Chutong Meng, Dan Jurafsky, Hsiu-Hsuan Wang, Hung-yi Lee, Jiatong Shi, Karen Livescu, Martijn Bartelds, Rafael Mosquera, Sara Hincapie, Shih-Heng Wang, Shinji Watanabe, William Chen","submitted_at":"2025-09-08T18:42:36Z","abstract_excerpt":"Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Interspeech 2025 ML-SUPERB 2.0 Challenge. We construct a new test suite that consists of data from 200+ languages, accents, and dialects to evaluate SOTA multilingual speech models. The challenge also introduces an online evaluation server based on DynaBench, allowing for flexibility in model design and architecture for participants. The challenge received 5 submissions from 3 teams, all of which outperformed our baseli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07139","kind":"arxiv","version":1},"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/2509.07139/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":"2509.07139","created_at":"2026-07-05T12:07:16.303761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07139v1","created_at":"2026-07-05T12:07:16.303761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07139","created_at":"2026-07-05T12:07:16.303761+00:00"},{"alias_kind":"pith_short_12","alias_value":"24WTOC4PVZNV","created_at":"2026-07-05T12:07:16.303761+00:00"},{"alias_kind":"pith_short_16","alias_value":"24WTOC4PVZNV7TOH","created_at":"2026-07-05T12:07:16.303761+00:00"},{"alias_kind":"pith_short_8","alias_value":"24WTOC4P","created_at":"2026-07-05T12:07:16.303761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07139","citing_title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M","json":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M.json","graph_json":"https://pith.science/api/pith-number/24WTOC4PVZNV7TOHAPW2SODZ3M/graph.json","events_json":"https://pith.science/api/pith-number/24WTOC4PVZNV7TOHAPW2SODZ3M/events.json","paper":"https://pith.science/paper/24WTOC4P"},"agent_actions":{"view_html":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M","download_json":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M.json","view_paper":"https://pith.science/paper/24WTOC4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07139&json=true","fetch_graph":"https://pith.science/api/pith-number/24WTOC4PVZNV7TOHAPW2SODZ3M/graph.json","fetch_events":"https://pith.science/api/pith-number/24WTOC4PVZNV7TOHAPW2SODZ3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M/action/storage_attestation","attest_author":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M/action/author_attestation","sign_citation":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M/action/citation_signature","submit_replication":"https://pith.science/pith/24WTOC4PVZNV7TOHAPW2SODZ3M/action/replication_record"}},"created_at":"2026-07-05T12:07:16.303761+00:00","updated_at":"2026-07-05T12:07:16.303761+00:00"}