{"record": {"aliases": ["SafeRun: Enabling Determinism in LLM Planning for Running"], "artifacts": [{"id": "arxiv:2606.09027", "kind": "paper", "url": "https://arxiv.org/abs/2606.09027"}, {"id": "hf:zzp-seeker/saferun-runplanning-benchmark", "kind": "dataset", "url": "https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark"}], "categories": ["General AI", "Planning", "Safety", "Safety & Trustworthiness"], "description": {"en": "A benchmark for evaluating language-model running plans under physiological, safety, and instruction-following constraints."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.09027", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.09027", "title": "SafeRun"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.09027", "modality": null, "name": "SafeRun", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_saferun-enabling-determinism-in-llm-planni_b859cb72", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "c66a63af169998b5acfc16492a5521e744159237158ac774428cf3624eddcc4c", "relation": "evaluates_only", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T20:06:22.759961Z", "source_url": "https://arxiv.org/abs/2606.09027"}, "publisher": null, "released": "2026-06-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.09027", "source_url": "https://arxiv.org/abs/2606.09027"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-09027", "source": "claire_radar", "source_benchmark_id": "2606.09027", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["SafeRun: Enabling Determinism in LLM Planning for Running"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The public artifact and safety-focused planning task may attract near-term specialist attention.", "score": 58}, "capabilities": ["Planning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T20:06:22.759961Z", "inputHash": "11a80aa10e5e93ac1507e5cf5774b97e2e42dbcf90a692ca5b9757e8a8f9315b", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "The SafeRun benchmark is publicly available", "canonicalNameSource": "abstract", "decisionReason": "Publish because the abstract formally names the SafeRun benchmark, defines its task, reports a concrete safety score, and supplies a currently public dataset link.", "evaluationEvidence": {"reuse": "The SafeRun benchmark is publicly available at \\href{https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark}{{huggingface}}.", "scoring": "100\\% safety score (vs.\\ 79.1\\% PE average and 97.6\\% CodeAct average) while maintaining competitive instruction-following scores", "task": "a comprehensive benchmark for running planning under realistic physiological and safety constraints"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T20:06:22.759961Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for evaluating language-model running plans under physiological, safety, and instruction-following constraints.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "To validate SafeRun, we build a comprehensive benchmark for running planning under realistic physiological and safety constraints."}, "familyId": "bmf_28087476d5b6", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_saferun-enabling-determinism-in-llm-planni_b859cb72", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": "https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark", "paper": "https://arxiv.org/abs/2606.09027", "pdf": "https://arxiv.org/pdf/2606.09027", "project": null, "report": "https://arxiv.org/abs/2606.09027"}, "metrics": [], "motivation": "Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature.", "name": "SafeRun", "oneLine": "A benchmark for evaluating language-model running plans under physiological, safety, and instruction-following constraints.", "paperTitle": "SafeRun: Enabling Determinism in LLM Planning for Running", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.09027", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Inspectable", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-06-08", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Meilin Chen", "Zepeng Zhai", "Jiaxuan Zhao", "Yuan Lu"], "categories": ["cs.CL", "cs.AI"], "id": "2606.09027", "title": "SafeRun: Enabling Determinism in LLM Planning for Running", "type": "arxiv", "url": "https://arxiv.org/abs/2606.09027"}, "sourceUpdatedAt": "2026-06-08T04:53:01Z", "topics": ["Safety"], "venueAttempts": [], "whyItMatters": "It supports comparable evaluation of whether flexible planning systems obey deterministic safety requirements."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
