{"work":{"id":"ac4a23f5-f300-4748-a75a-f0f29bcf6ee4","openalex_id":null,"doi":null,"arxiv_id":"2206.10498","raw_key":null,"title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reason- ing about Change,","authors":null,"authors_text":"K","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2206.10498","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-06-29T21:23:58.745729+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T09:38:42.237602+00:00","updated_at":"2026-06-29T21:23:58.745729+00:00","title_quality_ok":true,"display_title":"Large language models still can’t plan (a benchmark for llms on planning and reasoning about change)","render_title":"Large language models still can’t plan (a benchmark for llms on planning and reasoning about change)"},"hub":{"state":{"work_id":"ac4a23f5-f300-4748-a75a-f0f29bcf6ee4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":16,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2023-04-22T20:34:03+00:00","last_pith_cited_at":"2026-06-20T20:41:43+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":"2026-07-01T18:41:27.706625+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"support","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}