{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.02315", "kind": "paper", "url": "https://arxiv.org/abs/2608.02315"}, {"id": "gh:links-ads/geoid-flood", "kind": "repo", "url": "https://github.com/links-ads/geoid-flood"}], "authors": ["Gaetano Chiriaco", "Luca Barco", "Andrea Bragagnolo", "Claudio Rossi", "Edoardo Arnaudo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.02315", "source_url": "https://arxiv.org/abs/2608.02315"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "GEOID-Flood is a large-scale multi-modal benchmark for flood segmentation with over 14,000 tiles, co-registered SAR and optical data, and validated labels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.02315", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.02315", "title": "GEOID-Flood"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.02315", "modality": null, "name": "GEOID-Flood", "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_geoid-flood_b555af53", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "189fbe9ded5b07929f59197a4a78c6d4466991a6ab95a2c5de1f7f2081d1dda9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.02315"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.02315", "source_url": "https://arxiv.org/abs/2608.02315"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-02315", "source": "claire_radar", "source_benchmark_id": "2608.02315", "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/links-ads/geoid-flood", "githubScope": "benchmark_repo", "githubStars": 20, "hfDailySubmittedAt": "2026-08-04T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2608.02315", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "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": "f40b62e3c40d49e9dda267f58975c5d3aac5c567ea961885abece2e007bd3a70", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GEOID-Flood is a large-scale multi-modal benchmark for flood segmentation with over 14,000 tiles, co-registered SAR and optical data, and validated labels.", "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": "We introduce GEOID-Flood, a large-scale multi-modal flood segmentation benchmark, derived from Copernicus Emergency Management Service activations, spanning 219 events across 65 countries over ten years."}, "familyId": "bmf_983fa02568b2", "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/links-ads/geoid-flood", "url": "https://github.com/links-ads/geoid-flood"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/links-ads/geoid-flood", "url": "https://huggingface.co/papers/2608.02315"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/links-ads/geoid-flood.", "url": "https://arxiv.org/abs/2608.02315"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/links-ads/geoid-flood", "url": "https://arxiv.org/abs/2608.02315"}], "scope": "benchmark_repo", "url": "https://github.com/links-ads/geoid-flood", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_geoid-flood_b555af53", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/links-ads/geoid-flood", "data": null, "hfPaper": "https://huggingface.co/papers/2608.02315", "paper": "https://arxiv.org/abs/2608.02315", "pdf": "https://arxiv.org/pdf/2608.02315", "project": null, "report": "https://arxiv.org/abs/2608.02315"}, "metrics": [], "motivation": "Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data.", "name": "GEOID-Flood", "oneLine": "GEOID-Flood is a large-scale multi-modal benchmark for flood segmentation with over 14,000 tiles, co-registered SAR and optical data, and validated labels.", "paperTitle": "GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ECCV 2026 - Terrabytes II Workshop, 23 pages", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.02315", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV 2026 - Terrabytes II Workshop, 23 pages", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "links-ads", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/links-ads/geoid-flood"}], "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": 0.4063890167320393, "value": 20}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.24495074076910422, "value": 3}}, "confidence": "Medium", "coverage": 0.7, "rank": 131, "score": 41}, "method": "attention-ranking-v13", "rank": 131, "score": 41}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Gaetano Chiriaco", "Luca Barco", "Andrea Bragagnolo", "Claudio Rossi", "Edoardo Arnaudo"], "categories": ["cs.CV"], "id": "2608.02315", "title": "GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.02315"}, "sourceUpdatedAt": "2026-08-03T14:38:45Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted at ECCV 2026 - Terrabytes II Workshop, 23 pages", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at ECCV 2026 - Terrabytes II Workshop, 23 pages", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.02315"}], "reviewStatus": "accepted", "venueName": "ECCV 2026 - Terrabytes II Workshop, 23 pages"}], "whyItMatters": "Supports evaluation of geospatial foundation models on flood mapping, enabling transfer studies."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
