{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.13210", "kind": "paper", "url": "https://arxiv.org/abs/2608.13210"}, {"id": "gh:infinimind-inc/naru_benchmark", "kind": "repo", "url": "https://github.com/infinimind-inc/naru_benchmark"}, {"kind": "website", "url": "https://ma-labo.github.io/naru/"}], "authors": ["Yuheng Huang", "Jianlang Chen", "Jiayang Song", "Hua Qi", "Aza Kai", "Vincent Markert", "Edison Marrese-Taylor", "Jianjun Zhao", "Lei Ma"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13210", "source_url": "https://arxiv.org/abs/2608.13210"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "NARU evaluates multimodal models on Japanese long-form video understanding across narrative evolution (character evolution, sequential flow, plot progression, thematic development) and cultural nuance (aizuchi, reading the air, subtext, cultural context, sentiment) via multiple-choice QA."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13210", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13210", "title": "NARU"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The University of Tokyo", "Kyushu University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.13210", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.13210", "source_url": "https://openalex.org/W7203498050"}, "key": "claire-radar:2608.13210", "modality": null, "name": "NARU", "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_naru_dcb9acb4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "28c7bb513561894dc2a08f36b1b1aeb01ddf4b2dd5d3fbde2b05d46bf9b11b0b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.13210"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13210", "source_url": "https://arxiv.org/abs/2608.13210"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13210", "source": "claire_radar", "source_benchmark_id": "2608.13210", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/infinimind-inc/naru_benchmark", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 10, "hfPaperUrl": "https://huggingface.co/papers/2608.13210", "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": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-22T11:34:55.479945Z", "inputHash": "62498a267d98c1ff82a21e867814665020b942e0ce2b724263a3fff78ebe39be", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "NARU evaluates multimodal models on Japanese long-form video understanding across narrative evolution (character evolution, sequential flow, plot progression, thematic development) and cultural nuance (aizuchi, reading the air, subtext, cultural context, sentiment) via multiple-choice QA.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video."}, "familyId": "bmf_62e65dd5c196", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 2, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/infinimind-inc/naru_benchmark", "url": "https://github.com/infinimind-inc/naru_benchmark"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/infinimind-inc/naru_benchmark", "url": "https://huggingface.co/papers/2608.13210"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/infinimind-inc/naru_benchmark", "url": "https://ma-labo.github.io/naru/"}], "scope": "project_repo", "url": "https://github.com/infinimind-inc/naru_benchmark", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_naru_dcb9acb4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/infinimind-inc/naru_benchmark", "data": null, "hfPaper": "https://huggingface.co/papers/2608.13210", "paper": "https://arxiv.org/abs/2608.13210", "pdf": "https://arxiv.org/pdf/2608.13210", "project": "https://ma-labo.github.io/naru/", "report": "https://arxiv.org/abs/2608.13210"}, "metrics": [], "motivation": "Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit.", "name": "NARU", "oneLine": "NARU evaluates multimodal models on Japanese long-form video understanding across narrative evolution (character evolution, sequential flow, plot progression, thematic development) and cultural nuance (aizuchi, reading the air, subtext, cultural context, sentiment) via multiple-choice QA.", "paperTitle": "NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13210", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Infinimind Inc.", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/infinimind-inc/naru_benchmark"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.42369516881263364, "value": 10}}, "confidence": "Medium", "coverage": 0.7, "rank": 234, "score": 32}, "method": "attention-ranking-v13", "rank": 234, "score": 32}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-13", "source": {"authors": ["Yuheng Huang", "Jianlang Chen", "Jiayang Song", "Hua Qi", "Aza Kai", "Vincent Markert", "Edison Marrese-Taylor", "Jianjun Zhao", "Lei Ma"], "categories": ["cs.CV", "cs.AI", "cs.MM"], "id": "2608.13210", "title": "NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13210"}, "sourceUpdatedAt": "2026-08-13T13:13:43Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "NARU fills a gap in video QA benchmarks by jointly testing long-range narrative tracking and culturally grounded reasoning, which are absent in existing short-horizon or English-centric benchmarks. It provides a rigorous, reproducible protocol for measuring model capabilities in high-context media, supporting model development and product evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
