{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.05185", "kind": "paper", "url": "https://arxiv.org/abs/2607.05185"}], "categories": ["Agents", "Factuality", "General AI", "Language & Knowledge"], "description": {"en": "ClassicLogic is a benchmark suite of four classic logic puzzles (Sudoku, KenKen, Kakuro, Futoshiki) with a hierarchical knowledge base that defines complex strategies as compositions of simpler ones. It evaluates an agent's compositional generalization in problem-solving from basic rules to multi-step strategies across increasing puzzle difficulty."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.05185", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.05185", "title": "ClassicLogic"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.05185", "modality": null, "name": "ClassicLogic", "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_classiclogic_43434cd2", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7aed37d2d6924292bb12a431ed65aa0dec2ddd5315c710d859aace99c8e388e1", "relation": "aggregates", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.05185"}, "publisher": null, "released": "2026-07-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.05185", "source_url": "https://arxiv.org/abs/2607.05185"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-05185", "source": "claire_radar", "source_benchmark_id": "2607.05185", "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/2607.05185", "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": ["Factuality"], "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": "fa6e7171734804034fc7bea25e3d4675f1b364ec427822776a6ac2bd3a51dbe1", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ClassicLogic is a benchmark suite of four classic logic puzzles (Sudoku, KenKen, Kakuro, Futoshiki) with a hierarchical knowledge base that defines complex strategies as compositions of simpler ones. It evaluates an agent's compositional generalization in problem-solving from basic rules to multi-step strategies across increasing puzzle difficulty.", "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": "We introduce ClassicLogic, a new benchmark suite designed to evaluate an agent's ability to learn and compose problem-solving strategies."}, "familyId": "bmf_9984193cf2db", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_classiclogic_43434cd2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.05185", "paper": "https://arxiv.org/abs/2607.05185", "pdf": "https://arxiv.org/pdf/2607.05185", "project": null, "report": "https://arxiv.org/abs/2607.05185"}, "metrics": [], "motivation": "Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence.", "name": "ClassicLogic", "oneLine": "ClassicLogic is a benchmark suite of four classic logic puzzles (Sudoku, KenKen, Kakuro, Futoshiki) with a hierarchical knowledge base that defines complex strategies as compositions of simpler ones. It evaluates an agent's compositional generalization in problem-solving from basic rules to multi-step strategies across increasing puzzle difficulty.", "paperTitle": "ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.05185", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ClassicLogic Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.05185"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "aggregates", "releasedAt": "2026-07-06", "source": {"authors": ["Mahnoor Shahid and Hannes Rothe"], "categories": ["cs.AI", "cs.SC"], "id": "2607.05185", "title": "ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization", "type": "arxiv", "url": "https://arxiv.org/abs/2607.05185"}, "sourceUpdatedAt": "2026-07-06T15:02:23Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Most compositional generalization benchmarks focus on language; ClassicLogic provides a structured, non-linguistic testbed with explicit compositional logic. It enables fine-grained assessment of reasoning capabilities and supports development of neuro-symbolic systems capable of systematic problem-solving."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
