{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.10359", "kind": "paper", "url": "https://arxiv.org/abs/2608.10359"}], "authors": ["Yejin Jeon", "Marie Maltais", "Virginia Ceccatelli", "Min Ma", "David Ifeoluwa Adelani"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.10359", "source_url": "https://arxiv.org/abs/2608.10359"}, "categories": ["General AI", "Speech & Audio", "cs.SD"], "description": {"en": "VoxSumm evaluates joint summarization and translation of long-form spoken news. It comprises 10,045 BBC article-summary pairs across 24 languages and about 703 hours of speech, with scoring based on summarization and translation quality."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.10359", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.10359", "title": "VoxSumm"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Mila - Quebec Artificial Intelligence Institute", "McGill University", "Google DeepMind (United Kingdom)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.10359", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.10359", "source_url": "https://openalex.org/W7202243124"}, "key": "claire-radar:2608.10359", "modality": null, "name": "VoxSumm", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_voxsumm_b7118a8e", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "1ef3f50da0c43528c67fffe3e801078e3ff5056ef72392bb2be251b5560c1e12", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.10359"}, "publisher": null, "released": "2026-08-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.10359", "source_url": "https://arxiv.org/abs/2608.10359"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-10359", "source": "claire_radar", "source_benchmark_id": "2608.10359", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.10359", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "902cb002d670db7e66be50d926cf2e9e67139ff4e4bc8d07dece8efd01e1f473", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VoxSumm evaluates joint summarization and translation of long-form spoken news. It comprises 10,045 BBC article-summary pairs across 24 languages and about 703 hours of speech, with scoring based on summarization and translation quality.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "evaluation protocol evidence"], "snippet": "We additionally introduce VoxSumm, the first multilingual and cross-lingual benchmark for this task, comprising 10,045 BBC article-summary pairs across 24 languages and encompassing approximately 703 hours of speech data."}, "familyId": "bmf_d932f4e6d176", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_voxsumm_b7118a8e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.10359", "paper": "https://arxiv.org/abs/2608.10359", "pdf": "https://arxiv.org/pdf/2608.10359", "project": null, "report": "https://arxiv.org/abs/2608.10359"}, "metrics": [], "motivation": "As information increasingly traverses linguistic boundaries, users require concise cross-lingual representations of long-form content.", "name": "VoxSumm", "oneLine": "VoxSumm evaluates joint summarization and translation of long-form spoken news. It comprises 10,045 BBC article-summary pairs across 24 languages and about 703 hours of speech, with scoring based on summarization and translation quality.", "paperTitle": "VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.10359", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "VoxSumm Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.10359"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-11", "source": {"authors": ["Yejin Jeon", "Marie Maltais", "Virginia Ceccatelli", "Min Ma", "David Ifeoluwa Adelani"], "categories": ["cs.SD", "cs.CL"], "id": "2608.10359", "title": "VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.10359"}, "sourceUpdatedAt": "2026-08-11T01:33:09Z", "topics": ["cs.SD"], "venueAttempts": [], "whyItMatters": "Existing benchmarks treat long-document summarization and speech translation separately, leaving a gap for cross-lingual summarization of spoken content. VoxSumm provides a publicly inspectable resource for developing systems that compress and translate long-form speech, aiding evaluation of multilingual instruction-following and cross-lingual generation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
