{"schema_version":"papers/paper-detail-v1","title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","surface":"papers","opportunity_kernel":{"paper_id":"a965866d-ceee-4386-ad60-c8640d6ccf01","title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","authors":["Haoyue Yang","Zhangxiao Shen","Fan Ding","Hangting Lou","Yifeng Kou","Haoqing Yu","Jingyao Li","Zhengfan Wu","Siqi Bao","Jing Liu","Hua Wu"],"arxiv_id":"2605.30000v1","doi":null,"published_at":"2026-05-28T14:30:33.000Z","score_object":{"overall":{"value":8,"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":"2026-05-29T20:12:08.123Z","fresh_until":"2026-06-28T20:12:08.123Z","is_stale":false,"source_count":1,"missingness":[]},"technical":{"value":2.4,"scale":"0-10","confidence":0.7,"confidence_reason":"Backfilled from deployability_scores.score.","model_version":"phase0-backfill-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-29T20:34:19.996Z","fresh_until":"2026-06-12T20:34:19.996Z","is_stale":false,"source_count":2,"missingness":["reproducibility_results.reproducibility_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":"2026-05-29T20:12:08.123Z","fresh_until":"2026-06-28T20:12:08.123Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":5.7,"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":"2026-05-29T20:37:47.064Z","fresh_until":"2026-06-12T20:37:47.064Z","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":"2026-05-29T20:12:08.123Z","fresh_until":"2026-06-12T20:12:08.123Z","is_stale":false,"source_count":2,"missingness":[]},"methodology":{"value":4.3,"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":"2026-05-29T20:18:54.098Z","fresh_until":"2026-06-28T20:18:54.098Z","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":"2026-05-29T20:37:47.064Z"},"lineage_hash":"ff13aa602eabfb64f011a1928c2d4b6fcd7eff4e7616af747fc1d504e1b8fe6f"},"distribution":null,"replication_evidence":[],"author_dna":[]}