{"schema_version":"papers/paper-detail-v1","title":"FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification","surface":"papers","opportunity_kernel":{"paper_id":"2e5ef2f1-9cc7-4f79-8bc8-f21f337f5514","title":"FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification","authors":["Silu Panda"],"arxiv_id":"2605.29586v1","doi":null,"published_at":"2026-05-28T08:30:15.000Z","score_object":{"overall":{"value":6,"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":"2026-05-29T20:15:12.052Z","fresh_until":"2026-06-28T20:15:12.052Z","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":"2026-05-29T20:19:23.176Z","fresh_until":"2026-06-12T20:19:23.176Z","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":"2026-05-29T20:15:12.052Z","fresh_until":"2026-06-28T20:15:12.052Z","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":"2026-05-29T20:53:47.577Z","fresh_until":"2026-06-12T20:53:47.577Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":1.95,"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":"2026-05-29T20:15:12.052Z","fresh_until":"2026-06-12T20:15:12.052Z","is_stale":false,"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":"2026-05-29T20:19:23.176Z","fresh_until":"2026-06-28T20:19:23.176Z","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":"2026-05-29T20:53:47.577Z"},"lineage_hash":"732fb783b632829465da2c091ac6653f101f4fa1f401bdf151857bd68a57c331"},"distribution":null,"replication_evidence":[],"author_dna":[]}