{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01016", "kind": "paper", "url": "https://arxiv.org/abs/2606.01016"}, {"id": "gh:youngseng/polyspeech-100", "kind": "repo", "url": "https://github.com/YoungSeng/PolySpeech-100"}], "authors": ["Sicheng Yang", "Shulan Ruan", "Shiwei Wu", "Yu Liu", "Lu Fan", "Zhi Li", "You He"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01016", "source_url": "https://arxiv.org/abs/2606.01016"}, "categories": ["General AI", "Speech & Audio", "cs.CL"], "description": {"en": "PolySpeech-100 evaluates speech understanding in speech-large language models across 110 linguistic variants, including 19 Chinese dialects and over 80 low-resource languages, using tasks that assess semantic reasoning beyond transcription."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01016", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01016", "title": "PolySpeech-100"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua Shenzhen International Graduate School", "Tsinghua University", "Jingdong (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01016", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01016", "source_url": "https://openalex.org/W7163139763"}, "key": "claire-radar:2606.01016", "modality": null, "name": "PolySpeech-100", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_polyspeech-100_ce0b7268", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f6ca9bd3c916e6cdcc76363781c201da07a3dc8ac4fddb6785788bfbea8c00cd", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01016"}, "publisher": null, "released": "2026-05-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01016", "source_url": "https://arxiv.org/abs/2606.01016"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01016", "source": "claire_radar", "source_benchmark_id": "2606.01016", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/YoungSeng/PolySpeech-100", "githubScope": "benchmark_repo", "githubStars": 9, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.01016", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "e48faa79f37ee5f2f409c8154817d35081d1eb784b978a44cea4621c957ad93e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PolySpeech-100 evaluates speech understanding in speech-large language models across 110 linguistic variants, including 19 Chinese dialects and over 80 low-resource languages, using tasks that assess semantic reasoning beyond transcription.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants."}, "familyId": "bmf_0150fcfdb2d3", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/YoungSeng/PolySpeech-100", "url": "https://github.com/YoungSeng/PolySpeech-100"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/YoungSeng/PolySpeech-100", "url": "https://huggingface.co/papers/2606.01016"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/YoungSeng/PolySpeech-100.", "url": "https://arxiv.org/abs/2606.01016"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/YoungSeng/PolySpeech-100", "url": "https://arxiv.org/abs/2606.01016"}], "scope": "benchmark_repo", "url": "https://github.com/YoungSeng/PolySpeech-100", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_polyspeech-100_ce0b7268", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/YoungSeng/PolySpeech-100", "data": null, "hfPaper": "https://huggingface.co/papers/2606.01016", "paper": "https://arxiv.org/abs/2606.01016", "pdf": "https://arxiv.org/pdf/2606.01016", "project": null, "report": "https://arxiv.org/abs/2606.01016"}, "metrics": [], "motivation": "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.", "name": "PolySpeech-100", "oneLine": "PolySpeech-100 evaluates speech understanding in speech-large language models across 110 linguistic variants, including 19 Chinese dialects and over 80 low-resource languages, using tasks that assess semantic reasoning beyond transcription.", "paperTitle": "PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01016", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "PolySpeech-100 Benchmark Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/YoungSeng/PolySpeech-100"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-31", "source": {"authors": ["Sicheng Yang", "Shulan Ruan", "Shiwei Wu", "Yu Liu", "Lu Fan", "Zhi Li", "You He"], "categories": ["cs.CL", "cs.AI", "eess.AS"], "id": "2606.01016", "title": "PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01016"}, "sourceUpdatedAt": "2026-05-31T05:13:32Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Existing speech benchmarks are biased toward high-resource languages and focus on low-level recognition, limiting assessment of reasoning abilities and dialect robustness. PolySpeech-100 provides a broader coverage and a scoring protocol for comparing model performance on diverse speech understanding tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
