{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01498", "kind": "paper", "url": "https://arxiv.org/abs/2606.01498"}], "authors": ["Yaxuan Kong", "Qingren Yao", "Yuqi Nie", "Yichen Li", "Yilei Shao", "Stefan Zohren", "Anna Vettoruzzo", "Joaquin Vanschoren", "Ming Jin", "Qingsong Wen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01498", "source_url": "https://arxiv.org/abs/2606.01498"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "TimeSage-MT evaluates agentic time series reasoning in multi-turn dialogues, covering 240 tasks and 2,680 turns across 8 domains, with a protocol and leaderboard for comparing systems."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01498", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01498", "title": "TimeSage-MT"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Oxford", "Eindhoven University of Technology", "East China Normal University", "Griffith University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01498", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01498", "source_url": "https://openalex.org/W7163183140"}, "key": "claire-radar:2606.01498", "modality": null, "name": "TimeSage-MT", "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_timesage-mt_04a07ed7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4d9a4655473c79e9f0dc387ec8177e4345c49c9d1ff3a303032b6bde180d33a5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01498"}, "publisher": null, "released": "2026-05-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01498", "source_url": "https://arxiv.org/abs/2606.01498"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01498", "source": "claire_radar", "source_benchmark_id": "2606.01498", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.01498", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "8c6f9a4db9e9b65d32eb16ae6ba3c7b366f31a910e1e8ceda803b20674bc94c5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TimeSage-MT evaluates agentic time series reasoning in multi-turn dialogues, covering 240 tasks and 2,680 turns across 8 domains, with a protocol and leaderboard for comparing systems.", "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"], "snippet": "In this work, we introduce TimeSage-MT, a multi-turn benchmark for agentic time series reasoning with 240 tasks and 2,680 dialogue turns across 8 real-world domains, spanning basic exploration to decision-oriented analysis."}, "familyId": "bmf_2c4a9390c0f0", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_timesage-mt_04a07ed7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01498", "paper": "https://arxiv.org/abs/2606.01498", "pdf": "https://arxiv.org/pdf/2606.01498", "project": null, "report": "https://arxiv.org/abs/2606.01498"}, "metrics": [], "motivation": "Time series data inform critical decisions across many real-world domains.", "name": "TimeSage-MT", "oneLine": "TimeSage-MT evaluates agentic time series reasoning in multi-turn dialogues, covering 240 tasks and 2,680 turns across 8 domains, with a protocol and leaderboard for comparing systems.", "paperTitle": "TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01498", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "TimeSage-MT Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.01498"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-31", "source": {"authors": ["Yaxuan Kong", "Qingren Yao", "Yuqi Nie", "Yichen Li", "Yilei Shao", "Stefan Zohren", "Anna Vettoruzzo", "Joaquin Vanschoren", "Ming Jin", "Qingsong Wen"], "categories": ["cs.CL", "cs.AI"], "id": "2606.01498", "title": "TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01498"}, "sourceUpdatedAt": "2026-05-31T23:34:35Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "It fills a gap in benchmarking agentic time series analysis, which differs from single-step tasks, offering a way to assess multi-turn memory, uncertainty handling, and decision-making, with practical value for developing and comparing LLM agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
