{"schema_version":"papers/paper-detail-v1","title":"When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents","surface":"papers","opportunity_kernel":{"paper_id":"ba091385-db0c-4d9b-88c6-0bf6160f6979","title":"When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents","authors":["Xiaolin Zhou","Aojie Yuan","Zheng Luo","Zipeng Ling","Xixiao Pan","Yicheng Gao","Haiyue Zhang","Jiate Li","Shuli Jiang","Prince Zizhuang Wang","Zixuan Zhu","Jinbo Liu","Ryan A. Rossi","Hua Wei","Xiyang Hu"],"arxiv_id":"2605.11928v1","doi":null,"published_at":"2026-05-12T10:40:28.000Z","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":"2026-05-13T20:17:56.723Z","fresh_until":"2026-06-12T20:17:56.723Z","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":"2026-05-13T20:36:12.249Z","fresh_until":"2026-05-27T20:36:12.249Z","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":"2026-05-13T20:17:56.723Z","fresh_until":"2026-06-12T20:17:56.723Z","is_stale":false,"source_count":2,"missingness":[]},"market":{"value":5.5,"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":"2026-05-13T20:54:00.105Z","fresh_until":"2026-05-27T20:54:00.105Z","is_stale":true,"source_count":1,"missingness":[]},"team":{"value":5.45,"scale":"0-10","confidence":0.42,"confidence_reason":"Heuristic fallback from paper author count and extracted affiliations.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-13T20:17:56.723Z","fresh_until":"2026-05-27T20:17:56.723Z","is_stale":true,"source_count":2,"missingness":[]},"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":"2026-05-13T20:20:25.115Z","fresh_until":"2026-06-12T20:20:25.115Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"stale","proof_status":"unverified","repo_status":"active","references_count":0,"source_count":4,"coverage":0.8333,"missingness":["references"],"unresolved_unknowns":[],"last_verification_at":"2026-05-13T20:36:12.249Z"},"lineage_hash":"da735abc7b15dbc83d82b032506e15925cfc0bc3e9446c260ec35ccca46cca8b"},"distribution":null,"replication_evidence":[],"author_dna":[]}