{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12345", "kind": "paper", "url": "https://arxiv.org/abs/2608.12345"}], "authors": ["Yash Tripathi", "Silu Sharma", "Sai Sidhanth Manoharan Jayanthi", "Shivank Garg", "Lin Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12345", "source_url": "https://arxiv.org/abs/2608.12345"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "IntegrityBench evaluates language models on research integrity tasks, including misconduct classification, ethical action reasoning, and artifact-grounded decision making, across 36 paired tasks with a 5-level pressure protocol spanning multiple domains and research stages."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12345", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12345", "title": "IntegrityBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Jaypee University of Information Technology", "New York University Shanghai", "University of Oxford"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.12345", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.12345", "source_url": "https://openalex.org/W7203474226"}, "key": "claire-radar:2608.12345", "modality": null, "name": "IntegrityBench", "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_integritybench_9bf5a285", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "73d6ab88ac8ea2d6eff9116aad394f6c98a21abf04ad1d79424a48b35b1e888e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12345"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12345", "source_url": "https://arxiv.org/abs/2608.12345"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12345", "source": "claire_radar", "source_benchmark_id": "2608.12345", "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/2608.12345", "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": "cb40d8ed1c2e5ef70781fc6d891ecb8e293308e57da58fa99f9ff7db981e39a2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "IntegrityBench evaluates language models on research integrity tasks, including misconduct classification, ethical action reasoning, and artifact-grounded decision making, across 36 paired tasks with a 5-level pressure protocol spanning multiple domains and research stages.", "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": "We introduce IntegrityBench, a benchmark evaluating misconduct classification, ethical action reasoning and artifact-grounded decision making across 36 paired tasks under a 5-level implicit-explicit pressure protocol spanning 3 domains and 4 research stages."}, "familyId": "bmf_6062d4bd1c8f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_integritybench_9bf5a285", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.12345", "paper": "https://arxiv.org/abs/2608.12345", "pdf": "https://arxiv.org/pdf/2608.12345", "project": null, "report": "https://arxiv.org/abs/2608.12345"}, "metrics": [], "motivation": "Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured.", "name": "IntegrityBench", "oneLine": "IntegrityBench evaluates language models on research integrity tasks, including misconduct classification, ethical action reasoning, and artifact-grounded decision making, across 36 paired tasks with a 5-level pressure protocol spanning multiple domains and research stages.", "paperTitle": "Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12345", "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": "2026-06-03", "source": {"authors": ["Yash Tripathi", "Silu Sharma", "Sai Sidhanth Manoharan Jayanthi", "Shivank Garg", "Lin Li"], "categories": ["cs.AI", "cs.CL"], "id": "2608.12345", "title": "Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12345"}, "sourceUpdatedAt": "2026-06-03T22:58:12Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "As language models are used as co-scientists, measuring their integrity under pressure is critical. This benchmark could inform deployment decisions and identify risks of facilitating misconduct or eroding trust, but the evaluation method and reproducibility are not yet specified."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
