{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.21306", "kind": "paper", "url": "https://arxiv.org/abs/2607.21306"}], "authors": ["Verona Teo", "Raghav Jain", "Tobias Gerstenberg", "Max Kleiman-Weiner"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.21306", "source_url": "https://arxiv.org/abs/2607.21306"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "Int-Bench is a simulation-based evaluation for LLM intervention behavior in tutoring. It simulates a student solving problems across code debugging, mathematics, and brain teasers, with a teacher deciding whether, when, and how to intervene, measuring frequency, timing, and impact on task success and generalization."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.21306", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.21306", "title": "Int-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Stanford University", "University of California San Diego", "University of Washington"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.21306", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.21306", "source_url": "https://openalex.org/W7170799547"}, "key": "claire-radar:2607.21306", "modality": null, "name": "Int-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_int-bench_bde8cb1b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f1867fd8791b2939c1cd7491df5794e68c6860ea23784575e7dd53bb8fb7bc2f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.21306"}, "publisher": null, "released": "2026-07-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.21306", "source_url": "https://arxiv.org/abs/2607.21306"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-21306", "source": "claire_radar", "source_benchmark_id": "2607.21306", "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/2607.21306", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "bda1c89cb908767226d3a31994d3965f6b3a84b8e8244752aeea4277fea5f40d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Int-Bench is a simulation-based evaluation for LLM intervention behavior in tutoring. It simulates a student solving problems across code debugging, mathematics, and brain teasers, with a teacher deciding whether, when, and how to intervene, measuring frequency, timing, and impact on task success and generalization.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Here, we introduce Int-Bench, a simulation-based benchmark for evaluating LLM interventions during learning."}, "familyId": "bmf_16d5485f629c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_int-bench_bde8cb1b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.21306", "paper": "https://arxiv.org/abs/2607.21306", "pdf": "https://arxiv.org/pdf/2607.21306", "project": null, "report": "https://arxiv.org/abs/2607.21306"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used as tutors and thought partners, helping users reason through problems.", "name": "Int-Bench", "oneLine": "Int-Bench is a simulation-based evaluation for LLM intervention behavior in tutoring. It simulates a student solving problems across code debugging, mathematics, and brain teasers, with a teacher deciding whether, when, and how to intervene, measuring frequency, timing, and impact on task success and generalization.", "paperTitle": "AI Assistants Overassist", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.21306", "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": "2026-07-23", "source": {"authors": ["Verona Teo", "Raghav Jain", "Tobias Gerstenberg", "Max Kleiman-Weiner"], "categories": ["cs.LG", "cs.AI", "cs.CL", "cs.CY", "cs.HC"], "id": "2607.21306", "title": "AI Assistants Overassist", "type": "arxiv", "url": "https://arxiv.org/abs/2607.21306"}, "sourceUpdatedAt": "2026-07-23T13:30:01Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "The evaluation gap is that AI assistants may over-assist, hindering learning. This benchmark aims to quantify intervention timing and content, providing a method to compare models on supportive versus answer-giving behavior, which is critical for educational AI."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
