{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.24810", "kind": "paper", "url": "https://arxiv.org/abs/2607.24810"}], "authors": ["Yuqiao Lai", "Jiancheng Qi", "Fei Wang", "Yuxin Liu", "Kun Li", "Ye Chen", "Yan Gao", "Yanyan Wei"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.24810", "source_url": "https://arxiv.org/abs/2607.24810"}, "categories": ["General AI", "Multimodal"], "description": {"en": "RRS-10K is a benchmark for rare remote sensing image interpretation containing 10,738 military-related images with multiple format question-answer pairs, organized into three capability dimensions and 20 leaf tasks covering perception, reasoning, and robustness."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.24810", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.24810", "title": "RRS-10K"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["National University of Defense Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.24810", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.24810", "source_url": "https://openalex.org/W7171655999"}, "key": "claire-radar:2607.24810", "modality": null, "name": "RRS-10K", "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_rrs-10k_71143844", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "66ee62a623770b3f7a8cd27e86d7b09c41e568cd644314fc1199284d2ae69360", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.24810"}, "publisher": null, "released": "2026-07-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.24810", "source_url": "https://arxiv.org/abs/2607.24810"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-24810", "source": "claire_radar", "source_benchmark_id": "2607.24810", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2607.24810", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "9a49ac6bb876401f97e9665c5c08748ea21e5812646d387fed08ec59b23ec2b4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RRS-10K is a benchmark for rare remote sensing image interpretation containing 10,738 military-related images with multiple format question-answer pairs, organized into three capability dimensions and 20 leaf tasks covering perception, reasoning, and robustness.", "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"], "snippet": "To address this gap, we present RRS-10K, a benchmark for rare remote sensing image interpretation."}, "familyId": "bmf_76690795f4ea", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_rrs-10k_71143844", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.24810", "paper": "https://arxiv.org/abs/2607.24810", "pdf": "https://arxiv.org/pdf/2607.24810", "project": null, "report": "https://arxiv.org/abs/2607.24810"}, "metrics": [], "motivation": "Vision-language models (VLMs) have achieved strong performance on general remote sensing tasks.", "name": "RRS-10K", "oneLine": "RRS-10K is a benchmark for rare remote sensing image interpretation containing 10,738 military-related images with multiple format question-answer pairs, organized into three capability dimensions and 20 leaf tasks covering perception, reasoning, and robustness.", "paperTitle": "RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.24810", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.24810"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-13", "source": {"authors": ["Yuqiao Lai", "Jiancheng Qi", "Fei Wang", "Yuxin Liu", "Kun Li", "Ye Chen", "Yan Gao", "and Yanyan Wei"], "categories": ["cs.AI", "eess.IV"], "id": "2607.24810", "title": "RRS-10K: A Multitask Vision-Language Model Benchmark for Rare Remote Sensing Image Interpretation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.24810"}, "sourceUpdatedAt": "2026-07-13T08:02:57Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Current remote sensing benchmarks are dominated by common scenes, limiting understanding of VLM performance on rare, long-tail scenarios. RRS-10K provides a standardized evaluation for this gap, enabling systematic analysis of failure modes and guiding development of more reliable remote sensing VLMs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
