{"schema_version":"papers/paper-detail-v1","title":"Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization","surface":"papers","opportunity_kernel":{"paper_id":"fc875ae7-6a8c-4470-aecf-fdd9e6e70bdc","title":"Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization","authors":["Anmol Agarwal","Natalie Neamtu","Pranjal Aggarwal","Seungone Kim","Jannis Limperg","Cedric Flamant","Kanna Shimizu","Bryan Parno","Sean Welleck"],"arxiv_id":"2605.26457v1","doi":null,"published_at":"2026-05-26T02:12:48.000Z","score_object":{"overall":{"value":3,"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":"2026-05-27T20:11:54.540Z","fresh_until":"2026-06-26T20:11:54.540Z","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":"2026-05-27T20:12:13.690Z","fresh_until":"2026-06-10T20:12:13.690Z","is_stale":false,"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":"2026-05-27T20:11:54.540Z","fresh_until":"2026-06-26T20:11:54.540Z","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":"2026-05-27T20:28:28.266Z","fresh_until":"2026-06-10T20:28:28.266Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":6.2,"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":"2026-05-27T20:11:54.540Z","fresh_until":"2026-06-10T20:11:54.540Z","is_stale":false,"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":"2026-05-27T20:12:13.690Z","fresh_until":"2026-06-26T20:12:13.690Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"active","references_count":0,"source_count":4,"coverage":0.6667,"missingness":["references","proof_status"],"unresolved_unknowns":["proof verification has not been recorded yet"],"last_verification_at":"2026-05-27T20:28:28.266Z"},"lineage_hash":"dbde676788f0f206d09509b0f4621c6753c0b86df958b92b84121946158c75c2"},"distribution":null,"replication_evidence":[],"author_dna":[]}