{"task":"Visual Reasoning","dataset":"CLEVRER","metric_names":["Average-per ques.","Descriptive","Explanatory-per opt.","Explanatory-per ques.","Predictive-per opt.","Predictive-per ques.","Counterfactual-per opt.","Counterfactual-per ques."],"rows":[{"id":31727,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"AI Core","metrics":{"Average-per ques.":"95.24","Counterfactual-per opt.":"96.61","Counterfactual-per ques.":"90.72","Descriptive":"96.46","Explanatory-per opt.":"99.94","Explanatory-per ques.":"99.81","Predictive-per opt.":"93.96","Predictive-per ques.":"93.96"},"paper_url":"https://arxiv.org/abs/2506.10753v1","paper_title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","paper_date":"2025-06-12","code_links":[{"title":"azreasoners/CRCG","url":"https://github.com/azreasoners/CRCG"}],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31728,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"redherring","metrics":{"Average-per ques.":"91.14","Counterfactual-per opt.":"92.97","Counterfactual-per ques.":"80.05","Descriptive":"95.76","Explanatory-per opt.":"98.88","Explanatory-per ques.":"96.98","Predictive-per opt.":"95.69","Predictive-per ques.":"91.75"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31729,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"VRDP","metrics":{"Average-per ques.":"90.24","Counterfactual-per opt.":"94.83","Counterfactual-per ques.":"84.29","Descriptive":"93.4","Explanatory-per opt.":"96.3","Explanatory-per ques.":"91.94","Predictive-per opt.":"95.68","Predictive-per ques.":"91.35"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31730,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"Fighttttt","metrics":{"Average-per ques.":"88.71","Counterfactual-per opt.":"91.25","Counterfactual-per ques.":"75.35","Descriptive":"94.77","Explanatory-per opt.":"98.25","Explanatory-per ques.":"95.46","Predictive-per opt.":"94.16","Predictive-per ques.":"89.25"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31731,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"neural","metrics":{"Average-per ques.":"88.27","Counterfactual-per opt.":"91.42","Counterfactual-per ques.":"75.61","Descriptive":"94.01","Explanatory-per opt.":"98.47","Explanatory-per ques.":"95.99","Predictive-per opt.":"93.49","Predictive-per ques.":"87.48"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31732,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"NERV","metrics":{"Average-per ques.":"88.05","Counterfactual-per opt.":"91.12","Counterfactual-per ques.":"74.89","Descriptive":"95.04","Explanatory-per opt.":"98.18","Explanatory-per ques.":"94.98","Predictive-per opt.":"93.11","Predictive-per ques.":"87.28"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31733,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"DCL","metrics":{"Average-per ques.":"75.52","Counterfactual-per opt.":"80.38","Counterfactual-per ques.":"46.52","Descriptive":"90.7","Explanatory-per opt.":"89.58","Explanatory-per ques.":"82.82","Predictive-per opt.":"90.52","Predictive-per ques.":"82.03"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31734,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"troublesolver","metrics":{"Average-per ques.":"73.3","Counterfactual-per opt.":"79.96","Counterfactual-per ques.":"50.89","Descriptive":"88.37","Explanatory-per opt.":"89.19","Explanatory-per ques.":"81.56","Predictive-per opt.":"84.83","Predictive-per ques.":"72.38"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31735,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"v0.1","metrics":{"Average-per ques.":"73.1","Counterfactual-per opt.":"79.6","Counterfactual-per ques.":"49.77","Descriptive":"88.79","Explanatory-per opt.":"89.16","Explanatory-per ques.":"81.24","Predictive-per opt.":"84.95","Predictive-per ques.":"72.6"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31736,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"First_test","metrics":{"Average-per ques.":"69.65","Counterfactual-per opt.":"74.05","Counterfactual-per ques.":"42.23","Descriptive":"88.08","Explanatory-per opt.":"87.64","Explanatory-per ques.":"79.6","Predictive-per opt.":"82.86","Predictive-per ques.":"68.7"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31737,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"TS_NS_IMPERIAL","metrics":{"Average-per ques.":"69.21","Counterfactual-per opt.":"78.08","Counterfactual-per ques.":"44.6","Descriptive":"89.95","Explanatory-per opt.":"95.94","Explanatory-per ques.":"91.98","Predictive-per opt.":"74.73","Predictive-per ques.":"50.34"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31738,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"rnn_dyn","metrics":{"Average-per ques.":"67.57","Counterfactual-per opt.":"81.01","Counterfactual-per ques.":"51.07","Descriptive":"74.98","Explanatory-per opt.":"90.81","Explanatory-per ques.":"75.62","Predictive-per opt.":"82.9","Predictive-per ques.":"68.61"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31739,"task":"Visual Reasoning","parent_task":null,"dataset":"CLEVRER","model_name":"epoch 9 pgd_25_0.1_eps","metrics":{"Average-per ques.":"60.25","Counterfactual-per opt.":"66.65","Counterfactual-per ques.":"25.89","Descriptive":"81.39","Explanatory-per opt.":"83.42","Explanatory-per ques.":"72.78","Predictive-per opt.":"78.5","Predictive-per ques.":"60.95"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Average-per ques.\", \"Descriptive\", \"Explanatory-per opt.\", \"Explanatory-per ques.\", \"Predictive-per opt.\", \"Predictive-per ques.\", \"Counterfactual-per opt.\", \"Counterfactual-per ques.\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}