{"work":{"id":"cdcf1d27-8950-4301-b2c5-4fa9aad92cab","openalex_id":null,"doi":null,"arxiv_id":"2502.06559","raw_key":null,"title":"Can we trust ai benchmarks? an interdisciplinary review of current issues in ai evaluation","authors":null,"authors_text":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2502.06559","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T10:51:25.922514+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T04:55:11.733267+00:00","updated_at":"2026-05-22T10:51:25.922514+00:00","title_quality_ok":true,"display_title":"Can we trust AI benchmarks? An interdisciplinary review of current issues in AI evaluation","render_title":"Can we trust AI benchmarks? An interdisciplinary review of current issues in AI evaluation"},"hub":{"state":{"work_id":"cdcf1d27-8950-4301-b2c5-4fa9aad92cab","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":13,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-09-23T21:29:04+00:00","last_pith_cited_at":"2026-05-13T22:39:10+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-03T22:36:35.182749+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"other","n":2}],"polarity_counts":[{"context_polarity":"unclear","n":2},{"context_polarity":"background","n":1},{"context_polarity":"support","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}