{"record": {"aliases": ["RIDE: An Open Dataset and Benchmark for Train Delay Prediction"], "artifacts": [{"id": "arxiv:2606.05070", "kind": "paper", "url": "https://arxiv.org/abs/2606.05070"}], "authors": ["Clément Elliker", "Mathis Le Bail", "Clément Mantoux", "Jesse Read", "Sonia Vanier"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05070", "source_url": "https://arxiv.org/abs/2606.05070"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "RIDE is an open, nationwide-scale benchmark for train-delay prediction on the Belgian railway network, with standardized splits and evaluation using MAE and RMSE."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05070", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05070", "title": "RIDE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.05070", "modality": null, "name": "RIDE", "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_ride-an-open-dataset-and-benchmark-for-tra_5e908194", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "60164f5908c04ddf8d01a7735dbc4bcb1d3aaaa7bc281ff2d4c71cbc489ced9b", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T18:18:43.487089Z", "source_url": "https://arxiv.org/abs/2606.05070"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05070", "source_url": "https://arxiv.org/abs/2606.05070"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05070", "source": "claire_radar", "source_benchmark_id": "2606.05070", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["RIDE: An Open Dataset and Benchmark for Train Delay Prediction"], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Its large-scale public data, standardized protocol, and practical forecasting task may attract attention across transportation and machine-learning communities.", "score": 65}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T18:18:43.487089Z", "inputHash": "b4686b475641556759109c90f056828ea2d107d9f4b7a5abf348986a4d064fd7", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "we introduce RIDE, an open dataset and benchmark for train delay prediction", "canonicalNameSource": "abstract", "decisionReason": "The source formally names the benchmark, specifies its prediction task and metrics, and documents reusable public dataset releases.", "evaluationEvidence": {"reuse": "two public releases: a reusable intermediate relational dataset and model-ready benchmark datasets", "scoring": "Beyond aggregate mean absolute error (MAE) and root mean squared error (RMSE), the framework also provides breakdowns by prediction horizon and delay change", "task": "The benchmark standardizes the prediction task and the training and testing data."}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T18:18:43.487089Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RIDE is an open, nationwide-scale benchmark for train-delay prediction on the Belgian railway network, with standardized splits and evaluation using MAE and RMSE.", "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"], "snippet": "To address this gap, we introduce RIDE, an open dataset and benchmark for train delay prediction built at nationwide scale over the Belgian railway network."}, "familyId": "bmf_20e6142fca22", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_ride-an-open-dataset-and-benchmark-for-tra_5e908194", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2606.05070", "pdf": "https://arxiv.org/pdf/2606.05070", "project": null, "report": "https://arxiv.org/abs/2606.05070"}, "metrics": [], "motivation": "Train delay prediction is an important problem for both passengers and railway operators, yet progress in the field remains difficult to assess due to the lack of standardized datasets, prediction targets, and evaluation protocols.", "name": "RIDE", "oneLine": "RIDE is an open, nationwide-scale benchmark for train-delay prediction on the Belgian railway network, with standardized splits and evaluation using MAE and RMSE.", "paperTitle": "RIDE: An Open Dataset and Benchmark for Train Delay Prediction", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05070", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-06-03", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Cl\\'ement Elliker", "Mathis Le Bail", "Cl\\'ement Mantoux", "Jesse Read", "Sonia Vanier"], "categories": ["cs.LG"], "id": "2606.05070", "title": "RIDE: An Open Dataset and Benchmark for Train Delay Prediction", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05070"}, "sourceUpdatedAt": "2026-06-03T16:29:50Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "It supplies standardized data, prediction targets, and evaluation protocols for direct comparison of train-delay forecasting models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
