{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.24573", "kind": "paper", "url": "https://arxiv.org/abs/2605.24573"}], "authors": ["Hao Liu", "Siyuan Yang", "Qinglei Hu", "Dongyu Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.24573", "source_url": "https://arxiv.org/abs/2605.24573"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "AstroMind evaluates LLM reasoning about spacecraft behavior across intent inference, maneuver parameter estimation, and threat assessment, using physics-grounded simulations with realistic sensing noise. Metrics capture semantic correctness and quantitative consistency under physical constraints."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.24573", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.24573", "title": "AstroMind"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beihang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.24573", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.24573", "source_url": "https://openalex.org/W7162416390"}, "key": "claire-radar:2605.24573", "modality": null, "name": "AstroMind", "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": "unknown", "origin_record_id": "bm_astromind_587e5d1f", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "8e2c69c24769a7d7d66cfb19d67746b916e6ffff176a3092bfb1f3da55644334", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.24573"}, "publisher": null, "released": "2026-05-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.24573", "source_url": "https://arxiv.org/abs/2605.24573"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-24573", "source": "claire_radar", "source_benchmark_id": "2605.24573", "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/2605.24573", "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": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f248c443fec22a71ed76885eb2b752d4b2739d32e164f4b1dbde09b60c6c2669", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AstroMind evaluates LLM reasoning about spacecraft behavior across intent inference, maneuver parameter estimation, and threat assessment, using physics-grounded simulations with realistic sensing noise. Metrics capture semantic correctness and quantitative consistency under physical constraints.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "evaluation protocol evidence"], "snippet": "AstroMind is a physics-grounded benchmark designed to close that gap."}, "familyId": "bmf_f3195093bff0", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_astromind_587e5d1f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.24573", "paper": "https://arxiv.org/abs/2605.24573", "pdf": "https://arxiv.org/pdf/2605.24573", "project": null, "report": "https://arxiv.org/abs/2605.24573"}, "metrics": [], "motivation": "Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth orbits grow crowded and contested.", "name": "AstroMind", "oneLine": "AstroMind evaluates LLM reasoning about spacecraft behavior across intent inference, maneuver parameter estimation, and threat assessment, using physics-grounded simulations with realistic sensing noise. Metrics capture semantic correctness and quantitative consistency under physical constraints.", "paperTitle": "AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.24573", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-23", "source": {"authors": ["Hao Liu", "Siyuan Yang", "Qinglei Hu and Dongyu Li"], "categories": ["cs.CL"], "id": "2605.24573", "title": "AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2605.24573"}, "sourceUpdatedAt": "2026-05-23T13:23:26Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Space situational awareness lacks benchmarks for reasoning about why spacecraft maneuver, not just detection. AstroMind provides a shared test that combines physics accuracy and tactical interpretation, enabling comparison of models on this critical reasoning task."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
