{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.27904", "kind": "paper", "url": "https://arxiv.org/abs/2605.27904"}], "authors": ["Yihong Tang", "Andrew Robert Williams", "Arjun Ashok", "Vincent Zhihao Zheng", "Shubham Gupta", "Lijun Sun", "Alexandre Drouin", "Issam H. Laradji", "Étienne Marcotte", "Valentina Zantedeschi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.27904", "source_url": "https://arxiv.org/abs/2605.27904"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Dr-CiK is a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter distractors, distill evidence, and generate forecasts. It provides context ablations and evaluates deep research and forecasting methods."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.27904", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.27904", "title": "Dr-CiK"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["ServiceNow (United States)", "McGill University", "University of British Columbia", "Université Laval"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.27904", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.27904", "source_url": "https://openalex.org/W7162638132"}, "key": "claire-radar:2605.27904", "modality": null, "name": "Dr-CiK", "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_dr-cik_017f835a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "03b0bd09220ab36e79b83d874f96ff748f56c96f2fdabd86bbd73658c4c34948", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.27904"}, "publisher": null, "released": "2026-05-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.27904", "source_url": "https://arxiv.org/abs/2605.27904"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-27904", "source": "claire_radar", "source_benchmark_id": "2605.27904", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2605.27904", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "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": "c646db2a54322b4c8e26f2be5bc60cf8e4b7041375f56757268633a575e86d29", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Dr-CiK is a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter distractors, distill evidence, and generate forecasts. It provides context ablations and evaluates deep research and forecasting methods.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "Therefore, we introduce Dr-CiK, a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter out distractors, distill the retrieved context into forecast-useful evidence, and generate forecasts supported by that evidence."}, "familyId": "bmf_6f7e7a58db67", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_dr-cik_017f835a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.27904", "paper": "https://arxiv.org/abs/2605.27904", "pdf": "https://arxiv.org/pdf/2605.27904", "project": null, "report": "https://arxiv.org/abs/2605.27904"}, "metrics": [], "motivation": "Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noisy, heterogeneous information sources.", "name": "Dr-CiK", "oneLine": "Dr-CiK is a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter distractors, distill evidence, and generate forecasts. It provides context ablations and evaluates deep research and forecasting methods.", "paperTitle": "Dr-CiK: A Testbed for Foresight-Driven Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.27904", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-27", "source": {"authors": ["Yihong Tang", "Andrew Robert Williams", "Arjun Ashok", "Vincent Zhihao Zheng", "Lijun Sun", "Alexandre Drouin", "Issam H. Laradji", "\\'Etienne Marcotte", "Valentina Zantedeschi"], "categories": ["cs.AI", "cs.LG"], "id": "2605.27904", "title": "Dr-CiK: A Testbed for Foresight-Driven Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2605.27904"}, "sourceUpdatedAt": "2026-05-27T03:26:42Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Real-world forecasting requires active discovery of external context from noisy sources. Dr-CiK assesses the entire pipeline of context retrieval and use, revealing that most agents recover little evidence and are misled by distractors, guiding development of foresight-driven agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
