{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.23425", "kind": "paper", "url": "https://arxiv.org/abs/2607.23425"}], "authors": ["Arslan Bisharat", "Eric Spencer", "Brian Ortiz", "Khushboo Bhadauria", "Mujtaba Nazari", "Beatriz Santos", "Anisa Ramos", "TaiNing Wang", "George K. Thiruvathukal", "Konstantin Läufer", "Mohammed Abuhamad"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.23425", "source_url": "https://arxiv.org/abs/2607.23425"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "TLA+-Bench evaluates natural-language to TLA+ specification generation by executing each specification in the TLA+ model checker across the full reachable state space. The dataset includes 403 model-checked gold and 897 parse-only silver specifications, with multiple descriptions and difficulty labels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.23425", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.23425", "title": "TLA+-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Loyola University Chicago"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.23425", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.23425", "source_url": "https://openalex.org/W7171513994"}, "key": "claire-radar:2607.23425", "modality": null, "name": "TLA+-Bench", "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_tla-bench_4cd98a83", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "925eff6a67e349d187973b51aa3714cb25b434e74875cca2505f053cbe3a7791", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.23425"}, "publisher": null, "released": "2026-07-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.23425", "source_url": "https://arxiv.org/abs/2607.23425"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-23425", "source": "claire_radar", "source_benchmark_id": "2607.23425", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "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/2607.23425", "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": [], "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": "0e83bddca92dc4f43b97bae05b00093ae43a88970802e95a4f9fbca826ea1ccc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TLA+-Bench evaluates natural-language to TLA+ specification generation by executing each specification in the TLA+ model checker across the full reachable state space. The dataset includes 403 model-checked gold and 897 parse-only silver specifications, with multiple descriptions and difficulty labels.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We present TLA$^{+}$-Bench, a dataset and benchmark that grades by execution."}, "familyId": "bmf_205d79c0e84d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_tla-bench_4cd98a83", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.23425", "paper": "https://arxiv.org/abs/2607.23425", "pdf": "https://arxiv.org/pdf/2607.23425", "project": null, "report": "https://arxiv.org/abs/2607.23425"}, "metrics": [], "motivation": "Large language models increasingly write TLA$^{+}$ formal specifications from natural-language descriptions, but progress is hard to measure: existing resources grade by resemblance to a reference or by whether the output parses, neither of which shows correctness.", "name": "TLA+-Bench", "oneLine": "TLA+-Bench evaluates natural-language to TLA+ specification generation by executing each specification in the TLA+ model checker across the full reachable state space. The dataset includes 403 model-checked gold and 897 parse-only silver specifications, with multiple descriptions and difficulty labels.", "paperTitle": "TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.23425", "source": "arxiv-metadata", "status": "unverified", "venue": null, "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": 0.85, "relation": "introduces", "releasedAt": "2026-07-26", "source": {"authors": ["Arslan Bisharat", "Eric Spencer", "Brian Ortiz", "Khushboo Bhadauria", "Mujtaba Nazari", "Beatriz Santos", "Anisa Ramos", "TaiNing Wang", "George K. Thiruvathukal", "Konstantin L\\\"aufer", "Mohammed Abuhamad"], "categories": ["cs.SE", "cs.AI"], "id": "2607.23425", "title": "TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.23425"}, "sourceUpdatedAt": "2026-07-26T02:49:56Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Prior benchmarks for formal specification generation grade by reference resemblance or parseability, not correctness. TLA+-Bench provides an execution-grounded oracle that measures whether generated specifications satisfy the required properties, offering a more reliable evaluation signal and revealing a range of correctness scores depending on grading choices."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
