{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03626", "kind": "paper", "url": "https://arxiv.org/abs/2606.03626"}], "authors": ["Chao Wen", "Jacqueline Staub", "Adish Singla"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03626", "source_url": "https://arxiv.org/abs/2606.03626"}, "categories": ["Code generation", "General AI", "Multimodal"], "description": {"en": "TurtleAI is a benchmark of 823 tasks for visual programming in Turtle Graphics, evaluating models on perceiving geometric patterns and synthesizing Python code."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03626", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03626", "title": "TurtleAI"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Universität Trier"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03626", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03626", "source_url": "https://openalex.org/W7163393262"}, "key": "claire-radar:2606.03626", "modality": null, "name": "TurtleAI", "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_turtleai_8dfa596d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "81a73b39a44ba91c4cbbcbe0371e8340d248f7c05930cc7ba92d5525a5241569", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03626"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03626", "source_url": "https://arxiv.org/abs/2606.03626"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03626", "source": "claire_radar", "source_benchmark_id": "2606.03626", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2606.03626", "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": ["Code generation"], "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": "f8462c60a063d61d884c72dfdfeb51f64e31bcffd539d60cb77ccab35cdc6a49", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TurtleAI is a benchmark of 823 tasks for visual programming in Turtle Graphics, evaluating models on perceiving geometric patterns and synthesizing Python code.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To bridge this gap, we introduce TurtleAI, a benchmark containing 823 tasks curated based on real-world visual programming tasks in the Turtle Graphics domain."}, "familyId": "bmf_02b159b6d40e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_turtleai_8dfa596d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03626", "paper": "https://arxiv.org/abs/2606.03626", "pdf": "https://arxiv.org/pdf/2606.03626", "project": null, "report": "https://arxiv.org/abs/2606.03626"}, "metrics": [], "motivation": "Vision-language models (VLMs) have been explored for visual programming, where they generate code to solve visual tasks.", "name": "TurtleAI", "oneLine": "TurtleAI is a benchmark of 823 tasks for visual programming in Turtle Graphics, evaluating models on perceiving geometric patterns and synthesizing Python code.", "paperTitle": "TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03626", "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": "2026-06-02", "source": {"authors": ["Chao Wen", "Jacqueline Staub", "Adish Singla"], "categories": ["cs.CV", "cs.AI", "cs.CY"], "id": "2606.03626", "title": "TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03626"}, "sourceUpdatedAt": "2026-06-02T13:25:05Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Bridges the gap in education-oriented visual programming evaluation, highlighting limitations in spatial reasoning and code generation for VLMs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
