{"url":"/sota/visual-reasoning-on-vsr","task":{"name":"Visual Reasoning","url":"/task/visual-reasoning","note":null},"dataset":{"name":"VSR","url":"/dataset/vsr"},"category":"Computer Vision","categories":["Computer Vision","Reasoning"],"category_note":null,"description":"Ability to understand  actions and reasoning  associated with any  visual images","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"accuracy":"higher"}},"counts":{"rows":5,"rows_with_code":5,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LXMERT","metrics":{"accuracy":"70.1"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/visual-spatial-reasoning","paper_url":"https://arxiv.org/abs/2205.00363v3","paper_title":"Visual Spatial Reasoning","code":"https://github.com/cambridgeltl/visual-spatial-reasoning","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ViLT","metrics":{"accuracy":"69.3"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/visual-spatial-reasoning","paper_url":"https://arxiv.org/abs/2205.00363v3","paper_title":"Visual Spatial Reasoning","code":"https://github.com/cambridgeltl/visual-spatial-reasoning","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CLIP (finetuned)","metrics":{"accuracy":"65.1"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/visual-spatial-reasoning","paper_url":"https://arxiv.org/abs/2205.00363v3","paper_title":"Visual Spatial Reasoning","code":"https://github.com/cambridgeltl/visual-spatial-reasoning","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"CLIP (frozen)","metrics":{"accuracy":"56.0"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/visual-spatial-reasoning","paper_url":"https://arxiv.org/abs/2205.00363v3","paper_title":"Visual Spatial Reasoning","code":"https://github.com/cambridgeltl/visual-spatial-reasoning","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"VisualBERT","metrics":{"accuracy":"55.2"},"uses_additional_data":false,"paper_date":"2022-04-30","paper":"/paper/visual-spatial-reasoning","paper_url":"https://arxiv.org/abs/2205.00363v3","paper_title":"Visual Spatial Reasoning","code":"https://github.com/cambridgeltl/visual-spatial-reasoning","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":25,"n_unverified":25,"n_samples":50,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}