{"schema_version":"papers/paper-detail-v1","title":"STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems","surface":"papers","opportunity_kernel":{"paper_id":"2c93735d-e3e3-4204-bf11-d09235061e89","title":"STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems","authors":["Akash Bonagiri","Gerard Janno Anderias","Saee Patil","Angelina Lai","Devang Borkar","Gezheng Kang","Ishant Gandhi","Setareh Rafatirad","Houman Homayoun"],"arxiv_id":"2605.02122v1","doi":null,"published_at":"2026-05-04T01:03:48.000Z","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":"2026-05-05T20:09:49.049Z","fresh_until":"2026-06-04T20:09:49.049Z","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":"2026-05-05T20:11:11.997Z","fresh_until":"2026-05-19T20:11:11.997Z","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":"2026-05-05T20:09:49.049Z","fresh_until":"2026-06-04T20:09:49.049Z","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":"2026-05-05T20:28:34.004Z","fresh_until":"2026-05-19T20:28:34.004Z","is_stale":true,"source_count":1,"missingness":[]},"team":{"value":5.45,"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":"2026-05-05T20:09:49.049Z","fresh_until":"2026-05-19T20:09:49.049Z","is_stale":true,"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":"2026-05-05T20:11:11.997Z","fresh_until":"2026-06-04T20:11:11.997Z","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":"2026-05-05T20:28:34.004Z"},"lineage_hash":"b643e3964ff27f7b1f9a408726ed497b64e6df4cd2c4ae2cc1f5a8c2944a0584"},"distribution":null,"replication_evidence":[],"author_dna":[]}