{"schema_version":"papers/paper-detail-v1","title":"BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law","surface":"papers","opportunity_kernel":{"paper_id":"aee41f77-dd9e-436d-abfa-f4fce18e1913","title":"BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law","authors":["Sebastian Nagl","Ann-Kristin Mayrhofer","Martin Heidebach","Aleyna Koçak","Anne Zettelmeier","Elly Breu","Angelina Greiner","Sofija Milijas","Matthias Grabmair"],"arxiv_id":"2605.28183v1","doi":null,"published_at":"2026-05-27T09:03:59.000Z","score_object":{"overall":{"value":6,"scale":"0-10","confidence":0.85,"confidence_reason":"Aligned to persisted papers.viability_score for public contract consistency.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-28T16:19:42.104Z","fresh_until":"2026-06-27T16:19:42.104Z","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":"2026-05-28T16:20:52.258Z","fresh_until":"2026-06-11T16:20:52.258Z","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":"2026-05-28T16:19:42.104Z","fresh_until":"2026-06-27T16:19:42.104Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":2,"scale":"0-10","confidence":0.8,"confidence_reason":"Backfilled from distribution_readiness_scores.score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-28T16:54:17.063Z","fresh_until":"2026-06-11T16:54:17.063Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":4.7,"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":"2026-05-28T16:19:42.104Z","fresh_until":"2026-06-11T16:19:42.104Z","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":"2026-05-28T16:20:52.258Z","fresh_until":"2026-06-27T16:20:52.258Z","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":"2026-05-28T16:54:17.063Z"},"lineage_hash":"4389acedd673f32019a82057204523b14cca39026e1c6170d318c0d5aba925ea"},"distribution":null,"replication_evidence":[],"author_dna":[]}