{"schema_version":"papers/paper-detail-v1","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","surface":"papers","opportunity_kernel":{"paper_id":"8e759187-1e83-43d6-8dae-c08531c7df9d","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","authors":["Andrew Choi","Wei Xu"],"arxiv_id":"2605.11151v1","doi":null,"published_at":"2026-05-11T18:58:49.000Z","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":"2026-05-13T20:18:25.439Z","fresh_until":"2026-06-12T20:18:25.439Z","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":"2026-05-13T20:20:34.828Z","fresh_until":"2026-05-27T20:20:34.828Z","is_stale":true,"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":"2026-05-13T20:18:25.439Z","fresh_until":"2026-06-12T20:18:25.439Z","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":"2026-05-13T20:58:49.014Z","fresh_until":"2026-05-27T20:58:49.014Z","is_stale":true,"source_count":1,"missingness":[]},"team":{"value":2.5,"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":"2026-05-13T20:18:25.439Z","fresh_until":"2026-05-27T20:18:25.439Z","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":"2026-05-13T20:20:34.828Z","fresh_until":"2026-06-12T20:20:34.828Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"stale","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":"2026-05-13T20:58:49.014Z"},"lineage_hash":"45cecdd6bc07895cfea5f05607adffa9b12eeee506a90df7ae2dd3910fd3ff63"},"distribution":null,"replication_evidence":[],"author_dna":[]}