{"schema_version":"papers/paper-detail-v1","title":"Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)","surface":"papers","opportunity_kernel":{"paper_id":"72a83ac8-e29a-471a-b56c-52a8c0c714d3","title":"Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)","authors":["Samer Awad","Javier Conde","Carlos Arriaga","Tairan Fu","Javier Coronado-Blázquez","Pedro Reviriego"],"arxiv_id":"2605.27268v1","doi":null,"published_at":"2026-05-26T16:44:25.000Z","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":"2026-05-27T20:11:21.111Z","fresh_until":"2026-06-26T20:11:21.111Z","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":"2026-05-27T20:12:26.972Z","fresh_until":"2026-06-10T20:12:26.972Z","is_stale":false,"source_count":1,"missingness":["reproducibility_results.reproducibility_score","deployability_scores.score"]},"commercial":{"value":0,"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":"2026-05-27T20:11:21.111Z","fresh_until":"2026-06-26T20:11:21.111Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":1,"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":"2026-05-27T20:33:56.069Z","fresh_until":"2026-06-10T20:33:56.069Z","is_stale":false,"source_count":1,"missingness":[]},"team":{"value":6.5,"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":"2026-05-27T20:11:21.111Z","fresh_until":"2026-06-10T20:11:21.111Z","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":"2026-05-27T20:12:26.972Z","fresh_until":"2026-06-26T20:12:26.972Z","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":"2026-05-27T20:33:56.069Z"},"lineage_hash":"846cb5c37ddef070ef958e4ac39340126cad9349fe99397f388df1dd5177b83d"},"distribution":null,"replication_evidence":[],"author_dna":[]}