{"record": {"aliases": ["AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers"], "artifacts": [{"id": "arxiv:2609.02339", "kind": "paper", "url": "https://arxiv.org/abs/2609.02339"}], "authors": ["Alexey Potapov"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.02339", "source_url": "https://arxiv.org/abs/2609.02339"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "Evaluates predictive models on maze prediction tasks to study world dynamics learning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.02339", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.02339", "title": "AGI Maze Prediction Datasets and Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.02339", "modality": null, "name": "AGI Maze Prediction Datasets and Benchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_agi-maze-prediction-datasets-a-compact-ben_be442089", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "e91fb2f8ec3d263f9037c07bb8b55571ba159c86c34b3358a2ba1417536ebce5", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.02339"}, "publisher": null, "released": "2026-09-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.02339", "source_url": "https://arxiv.org/abs/2609.02339"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-02339", "source": "claire_radar", "source_benchmark_id": "2609.02339", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers"], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-03", "attemptedAt": "2026-09-03T01:40:48.194060Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.02339", "observedAt": "2026-09-02T06:30:32.214812Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-03T01:40:48.194060Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Specialized world dynamics dataset without public artifacts may attract only a niche audience.", "score": 20}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-04T00:46:59.007339Z", "inputHash": "eb3f6506b51c26d0380dbe74eb3abe116adc32e41e020b195f3c10ca1df6fc13", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce the AGI Maze Prediction Datasets and Benchmark, a lightweight controlled testbed for studying this capability in Transformers and other predictive models.", "canonicalNameSource": "abstract", "decisionReason": "No artifact evidence or public code/data link is provided, making the evaluation and scoring contract unclear.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates predictive models on maze prediction tasks to study world dynamics learning.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce the AGI Maze Prediction Datasets and Benchmark, a lightweight controlled testbed for studying this capability in Transformers and other predictive models."}, "familyId": "bmf_81d80fd7a116", "firstSeenAt": "2026-09-03", "heat": null, "id": "bm_agi-maze-prediction-datasets-a-compact-ben_be442089", "indexedAt": "2026-09-03T00:55:28.123857Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.02339", "pdf": "https://arxiv.org/pdf/2609.02339", "project": null, "report": "https://arxiv.org/abs/2609.02339"}, "metrics": [], "motivation": "World modeling requires a predictive model to maintain and update an internal state adequate for reasoning about the consequences of actions.", "name": "AGI Maze Prediction Datasets and Benchmark", "oneLine": "Evaluates predictive models on maze prediction tasks to study world dynamics learning.", "paperTitle": "AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.02339", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-03T00:55:28.123857Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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}, "today": {"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": 1, "historyDate": "2026-09-02", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.55, "role": "bonus", "value": 55}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 14}, "method": "attention-ranking-v13", "rank": null, "score": 14}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-09-02", "source": {"authors": ["Alexey Potapov"], "categories": ["cs.LG", "cs.AI"], "id": "2609.02339", "title": "AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers", "type": "arxiv", "url": "https://arxiv.org/abs/2609.02339"}, "sourceUpdatedAt": "2026-09-02T09:15:33Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Lightweight controlled testbed for world model capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
