{"schema_version":"papers/paper-detail-v1","title":"EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation","surface":"papers","opportunity_kernel":{"paper_id":"1dd31d82-9ef9-45bd-a1be-e9904a24c92a","title":"EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation","authors":["Yi Liu","TingFeng Hui","Wei Zhang","Li Sun","Ningxin Su","Jian Wang","Sen Su"],"arxiv_id":"2605.07247v1","doi":null,"published_at":"2026-05-08T05:08:16.000Z","score_object":{"overall":{"value":7,"scale":"0-10","confidence":0.85,"confidence_reason":"Backfilled from persisted papers.viability_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:18:57.307Z","fresh_until":"2026-06-10T20:18:57.307Z","is_stale":false,"source_count":1,"missingness":[]},"technical":{"value":1.4,"scale":"0-10","confidence":0.55,"confidence_reason":"Backfilled from paper_extraction_scorecards.reconstruction_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:36:05.821Z","fresh_until":"2026-05-25T20:36:05.821Z","is_stale":true,"source_count":1,"missingness":["reproducibility_results.reproducibility_score","deployability_scores.score"]},"commercial":{"value":5,"scale":"0-10","confidence":0.75,"confidence_reason":"Backfilled from persisted commercial_flags and repo availability.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:18:57.307Z","fresh_until":"2026-06-10T20:18:57.307Z","is_stale":false,"source_count":2,"missingness":[]},"market":{"value":5.9,"scale":"0-10","confidence":0.45,"confidence_reason":"Heuristic market score materialized from paper metadata, repo availability, and deployability.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:43:03.580Z","fresh_until":"2026-05-25T20:43:03.580Z","is_stale":true,"source_count":1,"missingness":[]},"team":{"value":4.7,"scale":"0-10","confidence":0.28,"confidence_reason":"Heuristic fallback from paper author count.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:18:57.307Z","fresh_until":"2026-05-25T20:18:57.307Z","is_stale":true,"source_count":1,"missingness":["paper_author_affiliations"]},"methodology":{"value":3.9,"scale":"0-10","confidence":0.82,"confidence_reason":"Backfilled from paper_extraction_scorecards.total_score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-11T20:21:29.743Z","fresh_until":"2026-06-10T20:21:29.743Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"stale","proof_status":"partial","repo_status":"active","references_count":0,"source_count":4,"coverage":0.8333,"missingness":["references"],"unresolved_unknowns":[],"last_verification_at":"2026-05-11T20:36:05.821Z"},"lineage_hash":"cab7e1cb5de08c14b5fc0a9198a3b5cb24d6702e70eefdab60f9b10b36a96015"},"distribution":null,"replication_evidence":[],"author_dna":[]}