{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12197", "kind": "paper", "url": "https://arxiv.org/abs/2608.12197"}], "authors": ["Jiarui Ma", "Jianghan Wang", "Yuheng Ma", "Ziyi Zhuang", "Xiaoguang Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12197", "source_url": "https://arxiv.org/abs/2608.12197"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "NetlistBench evaluates LLM reliability in recognizing and manipulating SPICE netlists, covering parameter and connectivity recognition, edits, hierarchical operations, equivalence judgment, and compound editing, with deterministic structure-aware scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12197", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12197", "title": "NetlistBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Southern University of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.12197", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.12197", "source_url": "https://openalex.org/W7202358434"}, "key": "claire-radar:2608.12197", "modality": null, "name": "NetlistBench", "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_netlistbench_58d2657e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "07a1c4698f9519cc609c3988797b65be235409376fdcddc4b3f58c9e0a27f221", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12197"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12197", "source_url": "https://arxiv.org/abs/2608.12197"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12197", "source": "claire_radar", "source_benchmark_id": "2608.12197", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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/2608.12197", "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": ["Robot manipulation"], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "690dac1af652a91d5cdcc0ce216c9c61fd24dddc9bbcf0cfeadbcdfa0163eadf", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "NetlistBench evaluates LLM reliability in recognizing and manipulating SPICE netlists, covering parameter and connectivity recognition, edits, hierarchical operations, equivalence judgment, and compound editing, with deterministic structure-aware scoring.", "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 present \\textbf{NetlistBench}, a structure-verified benchmark for SPICE netlist recognition and manipulation."}, "familyId": "bmf_3c373592114f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_netlistbench_58d2657e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.12197", "paper": "https://arxiv.org/abs/2608.12197", "pdf": "https://arxiv.org/pdf/2608.12197", "project": null, "report": "https://arxiv.org/abs/2608.12197"}, "metrics": [], "motivation": "Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition and manipulation remains poorly understood and is rarely separated from high-level design reasoning.", "name": "NetlistBench", "oneLine": "NetlistBench evaluates LLM reliability in recognizing and manipulating SPICE netlists, covering parameter and connectivity recognition, edits, hierarchical operations, equivalence judgment, and compound editing, with deterministic structure-aware scoring.", "paperTitle": "NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": "accepted by MLCAD 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.12197", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "MLCAD 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Jiarui Ma", "Jianghan Wang", "Yuheng Ma", "Ziyi Zhuang", "Xiaoguang Liu"], "categories": ["eess.SY", "cs.AI", "cs.SY"], "id": "2608.12197", "title": "NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12197"}, "sourceUpdatedAt": "2026-08-12T15:51:52Z", "topics": ["Robotics"], "venueAttempts": [{"decisionRaw": "accepted by MLCAD 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "accepted by MLCAD 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.12197"}], "reviewStatus": "accepted", "venueName": "MLCAD 2026"}], "whyItMatters": "It addresses the gap in assessing LLM reliability for simulator-facing netlist tasks, distinct from high-level design reasoning, and provides a structured evaluation to guide trustworthy circuit design automation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
