{"schema_version":"papers/paper-detail-v1","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","surface":"papers","opportunity_kernel":{"paper_id":"cdad66fb-13da-4b64-9ed9-d349b79c8ba2","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","authors":["Yuxin Chen","Yi Zhang","Zhengzhou Cai","Yaorui Shi","Zhiyuan Yao","Chenhang Cui","Jingnan Zheng","Yaqi Huo","Xi Su","Qi Gu","Xunliang Cai","Xiang Wang","An Zhang","Tat-Seng Chua"],"arxiv_id":"2605.27141v1","doi":null,"published_at":"2026-05-26T15:07:38.000Z","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":"2026-05-27T20:10:21.135Z","fresh_until":"2026-06-26T20:10:21.135Z","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":"2026-05-27T20:12:09.992Z","fresh_until":"2026-06-10T20:12:09.992Z","is_stale":false,"source_count":1,"missingness":["reproducibility_results.reproducibility_score","deployability_scores.score"]},"commercial":{"value":5,"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":"2026-05-27T20:10:21.135Z","fresh_until":"2026-06-26T20:10:21.135Z","is_stale":false,"source_count":2,"missingness":[]},"market":{"value":5.5,"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":"2026-05-27T20:28:47.050Z","fresh_until":"2026-06-10T20:28:47.050Z","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":"2026-05-27T20:10:21.135Z","fresh_until":"2026-06-10T20:10:21.135Z","is_stale":false,"source_count":2,"missingness":[]},"methodology":{"value":4.7,"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":"2026-05-27T20:12:09.992Z","fresh_until":"2026-06-26T20:12:09.992Z","is_stale":false,"source_count":2,"missingness":[]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"active","references_count":0,"source_count":4,"coverage":0.6667,"missingness":["references","proof_status"],"unresolved_unknowns":["proof verification has not been recorded yet"],"last_verification_at":"2026-05-27T20:28:47.050Z"},"lineage_hash":"fd8372eb778021372c4a98a3589458ac04393b018fc4eb11891dd3df91848927"},"distribution":null,"replication_evidence":[],"author_dna":[]}