{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.13344", "kind": "paper", "url": "https://arxiv.org/abs/2608.13344"}], "authors": ["Yupan Ding", "Jing Xiao", "Zhenyuan Zhang", "Chaofeng Chen", "Liang Liao", "Gui-Song Xia", "Mi Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13344", "source_url": "https://arxiv.org/abs/2608.13344"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "LongEarth-Bench evaluates vision-language models on long-horizon Earth observation reasoning, with ~120k QA samples from 117k images, sequences avg 15.14 frames (up to 30), covering 12 tasks in evolution summarization, spatial reasoning, anomaly identification, and logical prediction."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13344", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13344", "title": "LongEarth-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Wuhan University", "Xidian University", "State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.13344", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.13344", "source_url": "https://openalex.org/W7203451623"}, "key": "claire-radar:2608.13344", "modality": null, "name": "LongEarth-Bench", "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_longearth-bench_e5b3d65a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "efcd61ca29ed482d0f524f3d83b501a3a8b5bb01a90cd687c20891711bb7a6c3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.13344"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13344", "source_url": "https://arxiv.org/abs/2608.13344"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13344", "source": "claire_radar", "source_benchmark_id": "2608.13344", "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/2608.13344", "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": ["Reasoning"], "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": "a093c857c6fcc345c6995a9d82ac45ad0f3f780c327347bdce530f8ea5b81003", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LongEarth-Bench evaluates vision-language models on long-horizon Earth observation reasoning, with ~120k QA samples from 117k images, sequences avg 15.14 frames (up to 30), covering 12 tasks in evolution summarization, spatial reasoning, anomaly identification, and logical prediction.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce LongEarth-Bench, a benchmark containing approximately 120k question-answering samples derived from 117k unique images."}, "familyId": "bmf_3dd2e8ddc733", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_longearth-bench_e5b3d65a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.13344", "paper": "https://arxiv.org/abs/2608.13344", "pdf": "https://arxiv.org/pdf/2608.13344", "project": null, "report": "https://arxiv.org/abs/2608.13344"}, "metrics": [], "motivation": "Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer future from extended image sequences.", "name": "LongEarth-Bench", "oneLine": "LongEarth-Bench evaluates vision-language models on long-horizon Earth observation reasoning, with ~120k QA samples from 117k images, sequences avg 15.14 frames (up to 30), covering 12 tasks in evolution summarization, spatial reasoning, anomaly identification, and logical prediction.", "paperTitle": "LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13344", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.13344"}], "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": "2026-08-13", "source": {"authors": ["Yupan Ding", "Jing Xiao", "Zhenyuan Zhang", "Chaofeng Chen", "Liang Liao", "Gui-Song Xia", "Mi Wang"], "categories": ["cs.AI"], "id": "2608.13344", "title": "LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13344"}, "sourceUpdatedAt": "2026-08-13T15:14:59Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "LongEarth-Bench addresses the lack of benchmarks for long-sequence Earth observation reasoning, providing a more realistic and challenging evaluation for models designed to analyze multi-stage geographic changes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
