{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.01152", "kind": "paper", "url": "https://arxiv.org/abs/2607.01152"}], "authors": ["Roger Beaty", "Vijeta Deshpande", "Clin K. Y. Lai", "Anna Attuch", "Namrata Shivagunde", "Swastik Roy", "Rajkumar Pujari", "Paul V. DiStefano", "Sherin Muckatira", "Claire E. Stevenson", "Mikhail Gronas", "Anna Rumshisky"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.01152", "source_url": "https://arxiv.org/abs/2607.01152"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "AGC-Bench evaluates artificial general creativity across 78 datasets covering brainstorming, problem solving, STEM, narrative, figurative language, and humor. It uses an agentic harness and a public leaderboard with an open-weight judge model."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.01152", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.01152", "title": "AGC-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Pennsylvania State University", "University of Massachusetts Lowell", "University of Amsterdam", "Dartmouth College"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.01152", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.01152", "source_url": "https://openalex.org/W7167148982"}, "key": "claire-radar:2607.01152", "modality": null, "name": "AGC-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_agc-bench_28cf2135", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7930b711fb6387046c4b2c7305916243745d84179dbfcbe8151188f19c9e2833", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.01152"}, "publisher": null, "released": "2026-07-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.01152", "source_url": "https://arxiv.org/abs/2607.01152"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-01152", "source": "claire_radar", "source_benchmark_id": "2607.01152", "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/2607.01152", "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": "dd67d7d201c57369233f4f7573d29aacdfb2b30bc95a1bd759c228e22bc41d54", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AGC-Bench evaluates artificial general creativity across 78 datasets covering brainstorming, problem solving, STEM, narrative, figurative language, and humor. It uses an agentic harness and a public leaderboard with an open-weight judge model.", "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 AGC-Bench, an artificial general creativity benchmark built from a systematic review of the AI creativity literature (3,101 papers screened, 497 benchmarks identified), paired with an agentic harness that converts idiosyncratic codebases into HELM-standardized benchmarks."}, "familyId": "bmf_8f34ce070e53", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agc-bench_28cf2135", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.01152", "paper": "https://arxiv.org/abs/2607.01152", "pdf": "https://arxiv.org/pdf/2607.01152", "project": null, "report": "https://arxiv.org/abs/2607.01152"}, "metrics": [], "motivation": "Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence.", "name": "AGC-Bench", "oneLine": "AGC-Bench evaluates artificial general creativity across 78 datasets covering brainstorming, problem solving, STEM, narrative, figurative language, and humor. It uses an agentic harness and a public leaderboard with an open-weight judge model.", "paperTitle": "AGC-Bench: Measuring Artificial General Creativity", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.01152", "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": "2026-07-01", "source": {"authors": ["Roger Beaty", "Vijeta Deshpande", "Clin K.Y. Lai", "Anna Attuch", "Namrata Shivagunde", "Swastik Roy", "Rajkumar Pujari", "Paul V. DiStefano", "Sherin Muckatira", "Claire E. Stevenson", "Mikhail Gronas", "Anna Rumshisky"], "categories": ["cs.CL"], "id": "2607.01152", "title": "AGC-Bench: Measuring Artificial General Creativity", "type": "arxiv", "url": "https://arxiv.org/abs/2607.01152"}, "sourceUpdatedAt": "2026-07-02T01:52:53Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Creativity is a key aspect of intelligence often overlooked in AI evaluation. AGC-Bench provides a comprehensive, standardized measurement of AI creativity, revealing distinct strengths and weaknesses across models and a single creativity factor analogous to general intelligence."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
