{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.29577", "kind": "paper", "url": "https://arxiv.org/abs/2607.29577"}], "authors": ["Ismayil Ismayilov", "Atakan Kara", "Kaan Oktay"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.29577", "source_url": "https://arxiv.org/abs/2607.29577"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "DungeonBench evaluates tactical reasoning in Dungeons & Dragons combat with two tracks: Encounter for single fights and Day for linked encounters with persistent resources, using a shared decision stream of complete tactical observations and legal options."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.29577", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.29577", "title": "DungeonBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.29577", "modality": null, "name": "DungeonBench", "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_dungeonbench_a497b825", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "01216ddd1e9cc0e980d7acb3b2510012717bf35135e42c0fcca22832eb401660", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.29577"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.29577", "source_url": "https://arxiv.org/abs/2607.29577"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-29577", "source": "claire_radar", "source_benchmark_id": "2607.29577", "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/2607.29577", "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": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f2f2c45dc95d1fedc1b91d2dfe45ef30f1361711c32bbf8a32f74cad93d009ca", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DungeonBench evaluates tactical reasoning in Dungeons & Dragons combat with two tracks: Encounter for single fights and Day for linked encounters with persistent resources, using a shared decision stream of complete tactical observations and legal options.", "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 DungeonBench, a benchmark for tactical reasoning in Dungeons & Dragons combat, built to cover the vast majority of combat-relevant 2014 System Reference Document content whose effects can be resolved by the simulator while retaining mechanics that simplified combat simulators often abstract away."}, "familyId": "bmf_d20232b4c917", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_dungeonbench_a497b825", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.29577", "paper": "https://arxiv.org/abs/2607.29577", "pdf": "https://arxiv.org/pdf/2607.29577", "project": null, "report": "https://arxiv.org/abs/2607.29577"}, "metrics": [], "motivation": "Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all matter at once.", "name": "DungeonBench", "oneLine": "DungeonBench evaluates tactical reasoning in Dungeons & Dragons combat with two tracks: Encounter for single fights and Day for linked encounters with persistent resources, using a shared decision stream of complete tactical observations and legal options.", "paperTitle": "DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.29577", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "DungeonBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.29577"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-31", "source": {"authors": ["Ismayil Ismayilov", "Atakan Kara", "Kaan Oktay"], "categories": ["cs.AI", "cs.LG"], "id": "2607.29577", "title": "DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat", "type": "arxiv", "url": "https://arxiv.org/abs/2607.29577"}, "sourceUpdatedAt": "2026-07-31T16:03:38Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Current benchmarks often under-test rules-rich tactical reasoning where geometry, timing, resources, and rule interactions matter. DungeonBench fills this gap by providing a reproducible simulator-based environment with clear scoring, allowing comparison of policies from heuristic controllers to language models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
