{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04222", "kind": "paper", "url": "https://arxiv.org/abs/2608.04222"}, {"id": "gh:dyloong1/tide-dataset-benchmark", "kind": "repo", "url": "https://github.com/Dyloong1/TIDE-dataset-benchmark"}, {"id": "hf:ydai17/tide", "kind": "dataset", "url": "https://huggingface.co/datasets/ydai17/TIDE"}], "authors": ["Yilong Dai", "Yiming Sun", "Yiheng Chen", "Shengyu Chen", "Peyman Givi", "Xiaowei Jia", "Runlong Yu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04222", "source_url": "https://arxiv.org/abs/2608.04222"}, "categories": ["General AI", "Geometric reasoning", "Vision & 3D", "physics.flu-dyn"], "description": {"en": "A 3D incompressible-turbulence benchmark with multiple configurations, independent ensembles, controlled generalization splits, standardized baselines, and physical-fidelity evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04222", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04222", "title": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.04222", "modality": null, "name": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_tide-a-physically-diverse-3d-turbulence-be_fae9d795", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "ba885865b2ab2b857f630fd7c5b0473cf589c13c5f6cffa2bae68ab3c4e9ed6e", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T17:36:59.562667Z", "source_url": "https://arxiv.org/abs/2608.04222"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04222", "source_url": "https://arxiv.org/abs/2608.04222"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04222", "source": "claire_radar", "source_benchmark_id": "2608.04222", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The combination of a costly 3D scientific dataset, standardized baselines, and public artifacts is likely to draw attention in scientific machine learning.", "score": 76}, "capabilities": ["Geometric reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T17:36:59.562667Z", "inputHash": "ecb502bc0e8614e2d4198825cf292eb2c8cc9b8073458fa2429390d9a2f8296c", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning", "canonicalNameSource": "paper_title", "decisionReason": "TIDE is formally named, supplies standardized tasks and metrics, and provides public dataset and code links supporting reuse.", "evaluationEvidence": {"reuse": "Dataset: https://huggingface.co/datasets/ydai17/TIDE ; Code: https://github.com/Dyloong1/TIDE-dataset-benchmark", "scoring": "physical-fidelity metrics alongside pointwise error", "task": "The benchmark includes five tasks"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T17:36:59.562667Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A 3D incompressible-turbulence benchmark with multiple configurations, independent ensembles, controlled generalization splits, standardized baselines, and physical-fidelity evaluation.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "In this paper, we introduce TIDE (Turbulent Incompressible DNS Ensembles), a 256^3 DNS corpus and benchmark for 3D incompressible turbulence, with 15 configurations on eight controlled axes, independent ensembles, pressure fields, and equation-level verification."}, "familyId": "bmf_e5855bd45f03", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_tide-a-physically-diverse-3d-turbulence-be_fae9d795", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Dyloong1/TIDE-dataset-benchmark", "data": "https://huggingface.co/datasets/ydai17/TIDE", "paper": "https://arxiv.org/abs/2608.04222", "pdf": "https://arxiv.org/pdf/2608.04222", "project": "https://doi.org/10.5281/zenodo.21589489", "report": "https://arxiv.org/abs/2608.04222"}, "metrics": [], "motivation": "Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly.", "name": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning", "oneLine": "A 3D incompressible-turbulence benchmark with multiple configurations, independent ensembles, controlled generalization splits, standardized baselines, and physical-fidelity evaluation.", "paperTitle": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04222", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-08-04", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Yilong Dai", "Yiming Sun", "Yiheng Chen", "Shengyu Chen", "Peyman Givi", "Xiaowei Jia", "Runlong Yu"], "categories": ["physics.flu-dyn", "cs.LG"], "id": "2608.04222", "title": "TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04222"}, "sourceUpdatedAt": "2026-08-04T20:56:23Z", "topics": ["physics.flu-dyn"], "venueAttempts": [], "whyItMatters": "It makes accuracy, physical fidelity, regime generalization, and conditioning failures measurable on computationally demanding 3D turbulence."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
