{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.29700", "kind": "paper", "url": "https://arxiv.org/abs/2606.29700"}, {"id": "gh:ibasicplan/nl-pddl-bench", "kind": "repo", "url": "https://github.com/ibasicplan/NL-PDDL-Bench"}], "authors": ["Jiamei Jiang", "Jiajing Zhang", "Feifei Mo", "Linjing Li", "Daniel Zeng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.29700", "source_url": "https://arxiv.org/abs/2606.29700"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "NL-PDDL-Bench evaluates natural-language-to-PDDL specification generation. It consists of multi-domain instances from IPC domains with planner-verified executability, difficulty scaled by object count, and a suite for parseability, solvability, and plan-level consistency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.29700", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.29700", "title": "NL-PDDL-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.29700", "modality": null, "name": "NL-PDDL-Bench", "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_nl-pddl-bench_3b0f6c71", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "e08d6e10b0a560137a636d73e2bd7e5040ecfbc420d26960b87347824901b6ec", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.29700"}, "publisher": null, "released": "2026-06-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.29700", "source_url": "https://arxiv.org/abs/2606.29700"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-29700", "source": "claire_radar", "source_benchmark_id": "2606.29700", "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": "https://github.com/ibasicplan/NL-PDDL-Bench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.29700", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "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": "4f45b825d0fb9bfbde2b16b0422ddd99354885540e2916e519ecc955809c66c9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "NL-PDDL-Bench evaluates natural-language-to-PDDL specification generation. It consists of multi-domain instances from IPC domains with planner-verified executability, difficulty scaled by object count, and a suite for parseability, solvability, and plan-level consistency.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We present NL-PDDL-Bench, a multi-domain benchmark for natural-language-to-PDDL specification construction with planner-verified executability and controlled difficulty scaling by object count."}, "familyId": "bmf_57cc06c1d191", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/ibasicplan/NL-PDDL-Bench", "url": "https://github.com/ibasicplan/NL-PDDL-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/ibasicplan/NL-PDDL-Bench", "url": "https://huggingface.co/papers/2606.29700"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/ibasicplan/NL-PDDL-Bench", "url": "https://arxiv.org/abs/2606.29700"}], "scope": "benchmark_repo", "url": "https://github.com/ibasicplan/NL-PDDL-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_nl-pddl-bench_3b0f6c71", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/ibasicplan/NL-PDDL-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.29700", "paper": "https://arxiv.org/abs/2606.29700", "pdf": "https://arxiv.org/pdf/2606.29700", "project": null, "report": "https://arxiv.org/abs/2606.29700"}, "metrics": [], "motivation": "Planning often requires symbolic specifications that are both executable and verifiable.", "name": "NL-PDDL-Bench", "oneLine": "NL-PDDL-Bench evaluates natural-language-to-PDDL specification generation. It consists of multi-domain instances from IPC domains with planner-verified executability, difficulty scaled by object count, and a suite for parseability, solvability, and plan-level consistency.", "paperTitle": "Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedback", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.29700", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ibasicplan", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ibasicplan/NL-PDDL-Bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-06-29", "source": {"authors": ["Jiamei Jiang", "Jiajing Zhang", "Feifei Mo", "Linjing Li", "Daniel Zeng"], "categories": ["cs.AI"], "id": "2606.29700", "title": "Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedback", "type": "arxiv", "url": "https://arxiv.org/abs/2606.29700"}, "sourceUpdatedAt": "2026-06-29T02:08:30Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "This benchmark addresses the lack of standardized evaluation for LLM-generated planning specifications, with an emphasis on executability and verifiability. It provides a reproducible basis for assessing model reliability in safety-sensitive planning applications, where incorrect formalization can lead to unsafe outcomes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
