{"schema_version":"papers/paper-detail-v1","title":"expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling","surface":"papers","opportunity_kernel":{"paper_id":"701812ee-f907-4b68-a198-8e30204014b6","title":"expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum sampling","authors":["Mingxiong Lin","Zhangquan Gong","Maowen Tang","Qian Li","Chuangchuang Wang","Jian Ma","Sutian Huang","Kai Tang","Haonan Lu"],"arxiv_id":"2605.09923v1","doi":null,"published_at":"2026-05-11T03:19:04.000Z","score_object":{"overall":{"value":7,"scale":"0-10","confidence":0.85,"confidence_reason":"Backfilled from persisted papers.viability_score.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-06-11T20:15:46.673Z","is_stale":false,"source_count":1,"missingness":[]},"technical":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical technical score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-05-26T20:15:46.673Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.technical"]},"commercial":{"value":4,"scale":"0-10","confidence":0.7,"confidence_reason":"Backfilled from persisted commercial_flags and repo availability.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-06-11T20:15:46.673Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical market score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-05-26T20:15:46.673Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.market"]},"team":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical team score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-05-26T20:15:46.673Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.team"]},"methodology":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical methodology score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-12T20:15:46.673Z","fresh_until":"2026-06-11T20:15:46.673Z","is_stale":false,"source_count":0,"missingness":["paper_score_objects.methodology"]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"missing","references_count":0,"source_count":0,"coverage":0,"missingness":["paper_evidence_receipts.references_count","paper_evidence_receipts.coverage"],"unresolved_unknowns":["Canonical evidence receipt has not been materialized yet."],"last_verification_at":"2026-05-12T20:15:46.673Z"},"lineage_hash":"fd252c3709644c440c9a523d8ffec66bc72830d0bec05f095c1ec74be56a0fb7"},"distribution":null,"replication_evidence":[],"author_dna":[]}