{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.29278", "kind": "paper", "url": "https://arxiv.org/abs/2606.29278"}], "authors": ["Shubh Chapra", "Dhruv Kumar", "Murari Mandal", "Yash Sinha"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.29278", "source_url": "https://arxiv.org/abs/2606.29278"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Complexity Ceiling Benchmark evaluates sequential reasoning decay with depth scaling across grounded spatial state-tracking, symbolic pointer manipulation, and transitive relational inference."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.29278", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.29278", "title": "The Complexity Ceiling Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.29278", "modality": null, "name": "The Complexity Ceiling Benchmark", "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_the-complexity-ceiling-benchmark_2e65280a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9f7819c6d9fbb28eff3ea1b4f27f6de6537c6794d49e054bac32908aa8300033", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.29278"}, "publisher": null, "released": "2026-06-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.29278", "source_url": "https://arxiv.org/abs/2606.29278"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-29278", "source": "claire_radar", "source_benchmark_id": "2606.29278", "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/2606.29278", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "a5549ee71f8de4a2195c0119b70c1f425d13303514a26dffb6036ddd896a7fb4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Complexity Ceiling Benchmark evaluates sequential reasoning decay with depth scaling across grounded spatial state-tracking, symbolic pointer manipulation, and transitive relational inference.", "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 the Complexity Ceiling Benchmark (CCB), a controlled evaluation of how language-model reasoning decays as the number of required sequential steps grows."}, "familyId": "bmf_b80ea254c0bc", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_the-complexity-ceiling-benchmark_2e65280a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.29278", "paper": "https://arxiv.org/abs/2606.29278", "pdf": "https://arxiv.org/pdf/2606.29278", "project": null, "report": "https://arxiv.org/abs/2606.29278"}, "metrics": [], "motivation": "We introduce the Complexity Ceiling Benchmark (CCB), a controlled evaluation of how language-model reasoning decays as the number of required sequential steps grows.", "name": "The Complexity Ceiling Benchmark", "oneLine": "Complexity Ceiling Benchmark evaluates sequential reasoning decay with depth scaling across grounded spatial state-tracking, symbolic pointer manipulation, and transitive relational inference.", "paperTitle": "The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling", "primaryDomain": "General AI", "publication": {"evidence": "12 pages, 6 figures. Accepted to the 1st Workshop on Combining Theory and Benchmarks (CTB), CTB@ICML 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.29278", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "1st Workshop on Combining Theory and Benchmarks (CTB), CTB@ICML 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-28", "source": {"authors": ["Shubh Chapra", "Dhruv Kumar", "Murari Mandal", "Yash Sinha"], "categories": ["cs.AI", "cs.CL"], "id": "2606.29278", "title": "The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling", "type": "arxiv", "url": "https://arxiv.org/abs/2606.29278"}, "sourceUpdatedAt": "2026-06-28T08:56:34Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "12 pages, 6 figures. Accepted to the 1st Workshop on Combining Theory and Benchmarks (CTB), CTB@ICML 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "12 pages, 6 figures. Accepted to the 1st Workshop on Combining Theory and Benchmarks (CTB), CTB@ICML 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.29278"}], "reviewStatus": "accepted", "venueName": "1st Workshop on Combining Theory and Benchmarks (CTB), CTB@ICML 2026"}], "whyItMatters": "It quantifies reasoning degradation with step count, which could inform model development for long-horizon tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
