{"schema_version":"papers/paper-detail-v1","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","surface":"papers","opportunity_kernel":{"paper_id":"5cebf4f9-6368-42d5-93d3-7e94fe3dcdac","title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","authors":["Yuheng Jing","Kai Li","Ziwen Zhang","Jiajun Zhang","Zeyao Ma","Jiaxi Yang","Lei Zhang","Zhe Wu","Jinmin He","Junliang Xing","Jian Cheng"],"arxiv_id":"2605.24423v1","doi":null,"published_at":"2026-05-23T06:39:21.000Z","score_object":{"overall":{"value":0,"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":"2026-05-27T16:35:38.748Z","fresh_until":"2026-06-26T16:35:38.748Z","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":"2026-05-27T16:36:27.048Z","fresh_until":"2026-06-10T16:36:27.048Z","is_stale":false,"source_count":1,"missingness":["reproducibility_results.reproducibility_score","deployability_scores.score"]},"commercial":{"value":4,"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":"2026-05-27T16:35:38.748Z","fresh_until":"2026-06-26T16:35:38.748Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":2,"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":"2026-05-27T16:54:14.768Z","fresh_until":"2026-06-10T16:54:14.768Z","is_stale":false,"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":"2026-05-27T16:35:38.748Z","fresh_until":"2026-06-10T16:35:38.748Z","is_stale":false,"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":"2026-05-27T16:36:27.048Z","fresh_until":"2026-06-26T16:36:27.048Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"missing","references_count":0,"source_count":3,"coverage":0.5,"missingness":["repo_url","references","proof_status"],"unresolved_unknowns":["proof verification has not been recorded yet"],"last_verification_at":"2026-05-27T16:54:14.768Z"},"lineage_hash":"726f05459b610f1c8c5369c5bef99285ebf3d464f3cee736846c095bd7f13202"},"distribution":null,"replication_evidence":[],"author_dna":[]}