{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.02372", "kind": "paper", "url": "https://arxiv.org/abs/2608.02372"}], "authors": ["Abdulrahman AlRabah", "Xiaocheng Yang", "Dilek Hakkani-Tür", "Abdussalam Alawini"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.02372", "source_url": "https://arxiv.org/abs/2608.02372"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "PredAct-Bench evaluates dialogue agents paired with imperfect tools using educational datasets, measuring AI-assisted decision-making and trust metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.02372", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.02372", "title": "PredAct-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Illinois Urbana-Champaign"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.02372", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.02372", "source_url": "https://openalex.org/W7172469987"}, "key": "claire-radar:2608.02372", "modality": null, "name": "PredAct-Bench", "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_predact-bench_f35f1a5f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "be63c3f76f2b6ff218cf2965ef22ff011cf2e54284a680295e54b78855655611", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.02372"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.02372", "source_url": "https://arxiv.org/abs/2608.02372"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-02372", "source": "claire_radar", "source_benchmark_id": "2608.02372", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.02372", "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": [], "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": "5aa412499027fa3711c2385a3edf655b6ddc1e651674a4a81be79947ca4f7618", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PredAct-Bench evaluates dialogue agents paired with imperfect tools using educational datasets, measuring AI-assisted decision-making and trust metrics.", "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": "We introduce PREDACTBENCH, a benchmark for evaluating dialogue agents paired with statistically imperfect tools, using education as a measurable testbed where ground truth outcomes and clear intervention decisions are available."}, "familyId": "bmf_9ef627ddae02", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_predact-bench_f35f1a5f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.02372", "paper": "https://arxiv.org/abs/2608.02372", "pdf": "https://arxiv.org/pdf/2608.02372", "project": null, "report": "https://arxiv.org/abs/2608.02372"}, "metrics": [], "motivation": "Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains such as education, healthcare, and finance.", "name": "PredAct-Bench", "oneLine": "PredAct-Bench evaluates dialogue agents paired with imperfect tools using educational datasets, measuring AI-assisted decision-making and trust metrics.", "paperTitle": "PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.02372", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Abdulrahman AlRabah", "Xiaocheng Yang", "Dilek Hakkani-T\\\"ur", "Abdussalam Alawini"], "categories": ["cs.CL"], "id": "2608.02372", "title": "PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise", "type": "arxiv", "url": "https://arxiv.org/abs/2608.02372"}, "sourceUpdatedAt": "2026-08-03T15:15:55Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Highlights gap in existing benchmarks that assume perfect tool reliability, important for high-stakes domains."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
