{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05342", "kind": "paper", "url": "https://arxiv.org/abs/2606.05342"}], "authors": ["Matheus Kunzler Maldaner", "Adam Fourney", "Amanda Swearngin", "Hussein Mozannar", "Gagan Bansal", "Maya Murad", "Rafah Hosn", "Saleema Amershi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05342", "source_url": "https://arxiv.org/abs/2606.05342"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "SentinelBench is an open-source benchmark for time-evolving monitoring tasks. It contains 100 tasks across 10 synthetic web environments (email, calendars, finance, etc.) with scripted events, measuring task completion, reaction time, and resource use."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05342", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05342", "title": "SentinelBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.05342", "modality": null, "name": "SentinelBench", "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_sentinelbench_48835b47", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1d3b0431f2f3c63e0e2d96fc1628808b1b2ab7961ff5bf2d260b97925653f595", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05342"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05342", "source_url": "https://arxiv.org/abs/2606.05342"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05342", "source": "claire_radar", "source_benchmark_id": "2606.05342", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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/2606.05342", "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": "2026-09-25", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "91803cea33f9bfc490461b3f0abd19837a509a869515fef28f3e378465e4a650", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SentinelBench is an open-source benchmark for time-evolving monitoring tasks. It contains 100 tasks across 10 synthetic web environments (email, calendars, finance, etc.) with scripted events, measuring task completion, reaction time, and resource use.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To measure progress on this class of tasks, we introduce SentinelBench, an open-source benchmark for time-evolving monitoring tasks."}, "familyId": "bmf_f1b3e2bc0378", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_sentinelbench_48835b47", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05342", "paper": "https://arxiv.org/abs/2606.05342", "pdf": "https://arxiv.org/pdf/2606.05342", "project": null, "report": "https://arxiv.org/abs/2606.05342"}, "metrics": [], "motivation": "AI agents are increasingly asked to carry out work that spans minutes, hours, or longer.", "name": "SentinelBench", "oneLine": "SentinelBench is an open-source benchmark for time-evolving monitoring tasks. It contains 100 tasks across 10 synthetic web environments (email, calendars, finance, etc.) with scripted events, measuring task completion, reaction time, and resource use.", "paperTitle": "SentinelBench: A Benchmark for Long-Running Monitoring Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05342", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.05342"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Matheus Kunzler Maldaner", "Adam Fourney", "Amanda Swearngin", "Hussein Mozannar", "Gagan Bansal", "Maya Murad", "Rafah Hosn", "Saleema Amershi"], "categories": ["cs.AI"], "id": "2606.05342", "title": "SentinelBench: A Benchmark for Long-Running Monitoring Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05342"}, "sourceUpdatedAt": "2026-06-05T17:19:56Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Long-running monitoring tasks require sustained attention rather than continuous action. SentinelBench captures this class and quantifies the tradeoff between responsiveness and cost, enabling comparison of agent designs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
