{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.11616", "kind": "paper", "url": "https://arxiv.org/abs/2608.11616"}, {"id": "gh:hchoi256/mba", "kind": "repo", "url": "https://github.com/hchoi256/MBA"}, {"kind": "website", "url": "https://hchoi256.github.io/projects/mba/"}], "authors": ["Hojun Choi", "Jaeyo Shin", "Suin Lee", "Hyunjung Shim"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.11616", "source_url": "https://arxiv.org/abs/2608.11616"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates multimodal business ideation agents across six domains using 30K samples, with MLLM-as-a-Judge scoring over six business-oriented criteria."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.11616", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.11616", "title": "MBA-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Korea Advanced Institute of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.11616", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.11616", "source_url": "https://openalex.org/W7202358509"}, "key": "claire-radar:2608.11616", "modality": null, "name": "MBA-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_mba-bench_3f910264", "origin_source": "arxiv", "recognition_confidence": "0.75", "record_sha256": "1ab154a9856c05eacc1339f0350e661fdbf2dd13b520cf83b825c45d466da0b8", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:14:52.836173Z", "source_url": "https://arxiv.org/abs/2608.11616"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.11616", "source_url": "https://arxiv.org/abs/2608.11616"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-11616", "source": "claire_radar", "source_benchmark_id": "2608.11616", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/hchoi256/MBA", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 7, "hfPaperUrl": "https://huggingface.co/papers/2608.11616", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Novel multimodal business ideation task scope, large dataset, released code and demo, and arXiv paper with project page support moderate community interest.", "score": 65}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:14:52.836173Z", "inputHash": "6dfbdf595b580b665d8fd4a6c86743ce2eaaf75e758d63b30164bba1816c02ab", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We thus introduce MBA-Bench, the first multimodal benchmark for training and evaluating business ideation agents", "canonicalNameSource": "abstract", "decisionReason": "Formally named benchmark with 30K samples, explicit evaluation criteria, public dataset, code, and project page enabling repeatable scoring and submission.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:14:52.836173Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal business ideation agents across six domains using 30K samples, with MLLM-as-a-Judge scoring over six business-oriented criteria.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence", "public artifact URL"], "snippet": "We thus introduce MBA-Bench, the first multimodal benchmark for training and evaluating business ideation agents, comprising 30K samples across six domains, each domain characterized by distinct visual cues not fully conveyed by text alone."}, "familyId": "bmf_50ad9d899e34", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_mba-bench_3f910264", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/hchoi256/MBA", "data": null, "paper": "https://arxiv.org/abs/2608.11616", "pdf": "https://arxiv.org/pdf/2608.11616", "project": "https://hchoi256.github.io/projects/mba/", "report": "https://arxiv.org/abs/2608.11616"}, "metrics": [], "motivation": "Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation.", "name": "MBA-Bench", "oneLine": "Evaluates multimodal business ideation agents across six domains using 30K samples, with MLLM-as-a-Judge scoring over six business-oriented criteria.", "paperTitle": "MBA: Multimodal Benchmark and Agents for Real-World Business Ideation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.11616", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "KAIST AI", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://hchoi256.github.io/projects/mba/"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.2391676802567412, "value": 5}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.3674261111536563, "value": 7}}, "confidence": "Medium", "coverage": 0.7, "rank": 207, "score": 34}, "method": "attention-ranking-v13", "rank": 207, "score": 34}}, "readiness": "Runnable", "recognitionConfidence": 0.75, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Hojun Choi", "Jaeyo Shin", "Suin Lee", "Hyunjung Shim"], "categories": ["cs.AI", "cs.CV", "cs.LG"], "id": "2608.11616", "title": "MBA: Multimodal Benchmark and Agents for Real-World Business Ideation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.11616"}, "sourceUpdatedAt": "2026-08-13T02:06:46Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Provides the first multimodal benchmark for business ideation, enabling comparison of agents that ground ideas in diverse real-world visual contexts beyond text-only approaches."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
