{"schema_version":"papers/paper-detail-v1","title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","surface":"papers","opportunity_kernel":{"paper_id":"ce4c88fb-de3e-42a2-b7e3-4900ac4d3273","title":"Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient","authors":["Haoxiang You","Yilang Liu","Davis Zong","Qian Wang","Teeratham Vitchutripop","Qi Wang","Daniel Rakita","Ian Abraham"],"arxiv_id":"2605.26478v1","doi":null,"published_at":"2026-05-26T02:35:08.000Z","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":"2026-05-27T20:10:43.181Z","fresh_until":"2026-06-26T20:10:43.181Z","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":"2026-05-27T20:12:19.932Z","fresh_until":"2026-06-10T20:12:19.932Z","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":"2026-05-27T20:10:43.181Z","fresh_until":"2026-06-26T20:10:43.181Z","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":"2026-05-27T20:31:32.476Z","fresh_until":"2026-06-10T20:31:32.476Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":6.5,"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":"2026-05-27T20:10:43.181Z","fresh_until":"2026-06-10T20:10:43.181Z","is_stale":false,"source_count":2,"missingness":[]},"methodology":{"value":4.3,"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":"2026-05-27T20:12:19.932Z","fresh_until":"2026-06-26T20:12:19.932Z","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":"2026-05-27T20:31:32.476Z"},"lineage_hash":"5cd9e6cc820a446e38cc5f7f2d2bd82844af86ce7f6d0d78c8b1d06f65107a95"},"distribution":null,"replication_evidence":[],"author_dna":[]}