{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NDYZDGHBY4RQHQXEK4GC3FM242","short_pith_number":"pith:NDYZDGHB","schema_version":"1.0","canonical_sha256":"68f19198e1c72303c2e4570c2d959ae6816725185d3261af36bdd9ec90425b8f","source":{"kind":"arxiv","id":"2606.01016","version":1},"attestation_state":"computed","paper":{"title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lu Fan, Shiwei Wu, Shulan Ruan, Sicheng Yang, You He, Yu Liu, Zhi Li","submitted_at":"2026-05-31T05:13:32Z","abstract_excerpt":"While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing benchmarks suffer from three critical limitations: a pronounced bias towards high-resource languages, a focus on low-level recognition (ASR) rather than semantic reasoning, and a neglect of regional dialects. To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants. We employ a novel hybrid construction pipeline tha"},"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":"2606.01016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T05:13:32Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1350d886a356f6189ff7a692ab3480c33b0f0fadb04ddfab1a664539484cfdc6","abstract_canon_sha256":"6082bde957e68a4c893c68d41568048c1facff8e2fe436de1049b67787a55cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:18.513642Z","signature_b64":"WuTOQBYXtTyZbRhem9P//j5tYx7GVvZNQ2wkWV8iYB3Cc6blpcM+kQyX/Vv4RnZdGJM9y+paFMUPCCR0obJkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f19198e1c72303c2e4570c2d959ae6816725185d3261af36bdd9ec90425b8f","last_reissued_at":"2026-06-02T01:04:18.513193Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:18.513193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lu Fan, Shiwei Wu, Shulan Ruan, Sicheng Yang, You He, Yu Liu, Zhi Li","submitted_at":"2026-05-31T05:13:32Z","abstract_excerpt":"While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing benchmarks suffer from three critical limitations: a pronounced bias towards high-resource languages, a focus on low-level recognition (ASR) rather than semantic reasoning, and a neglect of regional dialects. To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants. We employ a novel hybrid construction pipeline tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01016","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/2606.01016/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":"2606.01016","created_at":"2026-06-02T01:04:18.513265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01016v1","created_at":"2026-06-02T01:04:18.513265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01016","created_at":"2026-06-02T01:04:18.513265+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDYZDGHBY4RQ","created_at":"2026-06-02T01:04:18.513265+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDYZDGHBY4RQHQXE","created_at":"2026-06-02T01:04:18.513265+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDYZDGHB","created_at":"2026-06-02T01:04:18.513265+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/NDYZDGHBY4RQHQXEK4GC3FM242","json":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242.json","graph_json":"https://pith.science/api/pith-number/NDYZDGHBY4RQHQXEK4GC3FM242/graph.json","events_json":"https://pith.science/api/pith-number/NDYZDGHBY4RQHQXEK4GC3FM242/events.json","paper":"https://pith.science/paper/NDYZDGHB"},"agent_actions":{"view_html":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242","download_json":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242.json","view_paper":"https://pith.science/paper/NDYZDGHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01016&json=true","fetch_graph":"https://pith.science/api/pith-number/NDYZDGHBY4RQHQXEK4GC3FM242/graph.json","fetch_events":"https://pith.science/api/pith-number/NDYZDGHBY4RQHQXEK4GC3FM242/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242/action/storage_attestation","attest_author":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242/action/author_attestation","sign_citation":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242/action/citation_signature","submit_replication":"https://pith.science/pith/NDYZDGHBY4RQHQXEK4GC3FM242/action/replication_record"}},"created_at":"2026-06-02T01:04:18.513265+00:00","updated_at":"2026-06-02T01:04:18.513265+00:00"}