{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2610.04253", "kind": "paper", "url": "https://arxiv.org/abs/2610.04253"}], "authors": ["Yixue Cai", "Yuzhe Zhao", "Hanxiang Chao", "Qingsen Ma", "Ziheng Xiong", "Jinhu Qi", "Irwin King"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2610.04253", "source_url": "https://arxiv.org/abs/2610.04253"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Generating an executable program does not necessarily mean that it correctly implements the behavioral requirements specified in natural language."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2610.04253", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2610.04253", "title": "Spec2Game"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Chinese University of Hong Kong", "Nankai University", "Wuhan University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2610.04253", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2610.04253", "source_url": "https://openalex.org/W7220701151"}, "key": "claire-radar:2610.04253", "modality": null, "name": "Spec2Game", "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": "true", "origin_record_id": "bm_spec2game_3570953e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1a907a6a719f762dbceed9dcffe742b9d65c1ceacffa2c3846a45fef2ab4f46b", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-10-06T07:49:35.626614Z", "source_url": "https://arxiv.org/abs/2610.04253"}, "publisher": null, "released": "2026-10-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2610.04253", "source_url": "https://arxiv.org/abs/2610.04253"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2610-04253", "source": "claire_radar", "source_benchmark_id": "2610.04253", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-10-06T07:49:35.626614Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To evaluate large language models' ability to realize detailed specifications as complete interactive programs, we introduce Spec2Game, a benchmark that requires models to generate complete Pygame projects from detailed natural-language game specifications."}, "familyId": "bmf_367e70d3e3f3", "firstSeenAt": "2026-10-06", "heat": null, "id": "bm_spec2game_3570953e", "indexedAt": "2026-10-06T07:49:11.852971Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2610.04253", "pdf": "https://arxiv.org/pdf/2610.04253", "project": null, "report": "https://arxiv.org/abs/2610.04253"}, "metrics": [], "motivation": "Generating an executable program does not necessarily mean that it correctly implements the behavioral requirements specified in natural language.", "name": "Spec2Game", "oneLine": "Generating an executable program does not necessarily mean that it correctly implements the behavioral requirements specified in natural language.", "paperTitle": "Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2610.04253", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-10-03", "source": {"authors": ["Yixue Cai", "Yuzhe Zhao", "Hanxiang Chao", "Qingsen Ma", "Ziheng Xiong", "Jinhu Qi", "Irwin King"], "categories": ["cs.AI"], "id": "2610.04253", "title": "Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?", "type": "arxiv", "url": "https://arxiv.org/abs/2610.04253"}, "sourceUpdatedAt": "2026-10-03T03:24:18Z", "topics": ["cs.AI"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
