{"url":"/task/human-judgment-correlation","name":"Human Judgment Correlation","slug":"human-judgment-correlation","description_markdown":"A task where an algorithm should generate the judgment scores correlating with human judgments.","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5,"papers_with_code":3,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/human-judgment-correlation-on-flickr8k-expert","slug":"human-judgment-correlation-on-flickr8k-expert","dataset":"Flickr8k-Expert","dataset_url":null,"rows_in_archive":4,"metrics":["Kendall's Tau-c"],"first_row_in_archive_order":{"model":"MID","paper_title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","paper_url":"/paper/mutual-information-divergence-a-unified","paper_date":"2022-05-25","arxiv_id":"2205.13445","code_links":[{"title":"naver-ai/mid.metric","url":"https://github.com/naver-ai/mid.metric"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/human-judgment-correlation-on-flickr8k-cf","slug":"human-judgment-correlation-on-flickr8k-cf","dataset":"Flickr8k-CF","dataset_url":null,"rows_in_archive":3,"metrics":["Kendall's Tau-b"],"first_row_in_archive_order":{"model":"MID","paper_title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","paper_url":"/paper/mutual-information-divergence-a-unified","paper_date":"2022-05-25","arxiv_id":"2205.13445","code_links":[{"title":"naver-ai/mid.metric","url":"https://github.com/naver-ai/mid.metric"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/mt-bench","name":"MT-Bench","full_name":"","num_papers_in_archive":531},{"url":"/dataset/alpacaeval","name":"AlpacaEval","full_name":"","num_papers_in_archive":131}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":5,"items":[{"url":"/paper/clipscore-a-reference-free-evaluation-metric","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","date":"2021-04-18","arxiv_id":"2104.08718","repositories_listed":3,"syntology":null},{"url":"/paper/factual-a-benchmark-for-faithful-and","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","date":"2023-05-27","arxiv_id":"2305.17497","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-information-divergence-a-unified","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","date":"2022-05-25","arxiv_id":"2205.13445","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}