compare/index.json

{"meta": {"n": 100, "configs": ["closed-book", "with-docs", "with-structures", "structure per q", "structure per ds", "DCI", "e2e v0", "e2e v2", "e2e v3"], "mean_metrics": {"closed-book": {"mean_judge_score": 0.7496, "mean_correct": 0.61}, "with-docs": {"mean_judge_score": 0.849, "mean_correct": 0.77}, "with-structures": {"mean_judge_score": 0.8449, "mean_correct": 0.76}, "structure per q": {"mean_judge_score": 0.9048, "mean_correct": 0.81}, "structure per ds": {"mean_judge_score": 0.8794, "mean_correct": 0.77}, "DCI": {"mean_judge_score": 0.8296, "mean_correct": 0.71}, "e2e v0": {"mean_judge_score": 0.8201, "mean_correct": 0.66}, "e2e v2": {"mean_judge_score": 0.8094, "mean_correct": 0.65}, "e2e v3": {"mean_judge_score": 0.8132, "mean_correct": 0.67}}}, "rows": [{"qid": "0", "question": "List the three departments with the highest percent support for Marine Le Pen during the first round of the French presidential election.", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.3333, "correct": 0, "judged_missing": false}]}, {"qid": "6", "question": "Name the NFL team that has won the same number of super bowl titles as the green bay packers ?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6667, "correct": 0, "judged_missing": false}]}, {"qid": "12", "question": "Which Latin American country has had the highest increase in life expectancy since 2000?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "14", "question": "What are the four most populous cities in Sierra Leone?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "15", "question": "How many NBA players since the year 2000 also played for coach K in Duke?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 0.9818, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "DCI", "judge_score": 0.9483, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.9818, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "17", "question": "Which country has had more deaths from COVID, France or Portugal?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "20", "question": "Who are the characters of Chekhov's The Seagull besides the protagonist and her family?", "gold_answers_length": 10, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.7, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.8, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "21", "question": "When did the LA Sparks last win a championship?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "24", "question": "What NFL team was founded first, the Patriots or the Cardinals?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "30", "question": "What is the win percentage change of the Buffalo bills in 2020 NFL season compared to the 2019 NFL season ?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.9973, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.9973, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.9973, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.9973, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.9973, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "35", "question": "Where have more philosophical writers come from, China or England?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "41", "question": "What percentage of films that grossed over 100 million dollars were superhero movies in 2019 vs 2009?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "e2e v0", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.5, "correct": 0, "judged_missing": false}]}, {"qid": "43", "question": "List the winners of the Roland Garros women singles tournament since 2013, sorted by their age when winning the title.", "gold_answers_length": 11, "cells": [{"label": "closed-book", "judge_score": 0.6957, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.6957, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.9565, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.9565, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.9565, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.9565, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.9565, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.6957, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6957, "correct": 0, "judged_missing": false}]}, {"qid": "50", "question": "Did the White Album premiere before Sargent Pepper?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "53", "question": "Which disease has resulted in more deaths, HIV or the black death?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "56", "question": "Which country has a smaller percentage of its citizens vaccinated against COVID with at least one dose, Nigeria or Ethiopia?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "59", "question": "What was the total budget for the first 3 Jurassic Park films?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "63", "question": "How many countries have had more than ten different Grand Slam singles champions?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "66", "question": "Players from how many different countries competed in the French open woman's singles championship in 2021 ?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.1, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.1, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.1, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.1, "correct": 0, "judged_missing": false}]}, {"qid": "72", "question": "Which That's So Raven Directors directed at least 10 episodes of the show?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "74", "question": "Which Ivy League school is located in the state where Bam Bam Bigelow was born?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "75", "question": "Does Golden state coach Steve Kerr have more playoffs wins than San Antionio spurs coach Gregg Popovich ?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "78", "question": "Has COVID resulted in more deaths than the Spanish flu?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "80", "question": "Of Iceland, New Zealand, Holland, and England, put in chronologic order which had a female leader first.", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "90", "question": "Have any US tennis players won Wimbledon in the past five years?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "93", "question": "What were Napoleon's final two defeats? When were they and by whom?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.5, "correct": 0, "judged_missing": false}]}, {"qid": "96", "question": "Which kingdoms, outside of Scandinavia, were founded by Vikings?", "gold_answers_length": 7, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "116", "question": "What was the average happiness score of Scandinavian countries compared to that of South American countries in 2020?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.8, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.8, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "131", "question": "Who was the paternal great grandfather of Henry II of England?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "135", "question": "What are the top two rarest big cat species found in the wild?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "137", "question": "what was the familial bond between Elizabeth I of England and her successor?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "139", "question": "Which of the animals mentioned in the Jungle Book do not eat meat?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.8571, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.8571, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.8571, "correct": 0, "judged_missing": false}]}, {"qid": "148", "question": "Do the official languages of Ethipoia originate from different liguistic families?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "151", "question": "What are the four major ethnic groups in Burma?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "153", "question": "What age were Raphael Nadale, Roger Federer and Serena Williams when each of them had won his first Grand Slam?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.3333, "correct": 0, "judged_missing": false}]}, {"qid": "169", "question": "Who are the children of the last three US presidents?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "178", "question": "In EU countries, is the Green Party more likely to be headed by woman?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "188", "question": "Out of the previous five prime ministers of Malta, how many belonged to left-wing parties?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "195", "question": "Who has been the most frequent enemy of Vietnam during the Nguyen Dynasty?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6667, "correct": 0, "judged_missing": false}]}, {"qid": "196", "question": "Who have been the rulers of Libya, since its independence?", "gold_answers_length": 19, "cells": [{"label": "closed-book", "judge_score": 0.6429, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5926, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5926, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "207", "question": "which four Canadian Prime Ministers have had the highest approval rating in the last 50 years?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "208", "question": "Considering the top ten grossing films of each year from 1990 to 2000, which movie studio had the highest cumulative box office?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "219", "question": "Which NBA Player more frequently missed free throw tries, Damon Stoudamire or James Harden?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "225", "question": "Which country party has the highest percentage of parliament seats held by separatist parties, out of Spain, Belgium and Italy?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "228", "question": "Which three women received the most first round votes ever, in any of the past five French presidential elections?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "235", "question": "On average, has the economy in Scandinavia gotten better in the last ten years?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "239", "question": "Was serial killer Gilles de Rais a contemporary of Saint Joan of Arc or Peter the Cruel?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "240", "question": "Is there a connection between GRR Martin and Roger Zelazny?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "250", "question": "How many Canadian prime ministers served non-consecutive terms in that role (i.e. in the manner similar to that of Grover Cleveland or Winston Churchill)?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "257", "question": "Which NBA scoring champions held the title for at least 3 consecutive years?", "gold_answers_length": 8, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "277", "question": "Which two noble families did the French Bourbon kings marry into the most?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "290", "question": "What are the three major ethnic groups in Guinea, along their percentage of the population?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "294", "question": "What are the most common styles of suit jacket lapels, and when is each lapel style most appropriate?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "297", "question": "Which of Blake's four Zoas is closely linked to the Gnostic concept of Demiurge?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "300", "question": "What is the major political party in Ireland?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6667, "correct": 0, "judged_missing": false}]}, {"qid": "302", "question": "who is the leader of the party with the most seats in Latvia's parliament?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "306", "question": "Do fringe parties hold a larger combined total number of seats in Italy's parliament than the centrist parties?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "307", "question": "Which political party in France is in control right now, and when was that party established?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "315", "question": "How many Pulitzer Prize-winning playwrights were born in New York City?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.7222, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.8889, "correct": 0, "judged_missing": false}]}, {"qid": "328", "question": "How many Presidents of Cyprus's House of Representatives have been politically conservative?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.4286, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6, "correct": 0, "judged_missing": false}]}, {"qid": "331", "question": "Which Winter Olympics year earned Sweden the highest number of Gold medals?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "338", "question": "Does pineapple contain more sugar than oranges?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "339", "question": "Which salon dances do not come from Latin America?", "gold_answers_length": 8, "cells": [{"label": "closed-book", "judge_score": 0.6, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.4, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.4, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.4, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.4, "correct": 0, "judged_missing": false}]}, {"qid": "348", "question": "who was the youngest person to be elected as leader of the Norwegian Labour Party?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "364", "question": "Of the martial-arts sports that are Olympic events, how many are of Japanese origin?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "373", "question": "Were there more people in attendance at the Superbowl in 2022 or in 2000?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "379", "question": "Which single from Lali Esposito's 2020 album peaked at the Argentina Hot 100?", "gold_answers_length": 5, "cells": [{"label": "closed-book", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.3333, "correct": 0, "judged_missing": false}]}, {"qid": "383", "question": "Which US Presidents were in office during the Roaring Twenties?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.8571, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "384", "question": "Which Operas composed by Richard Strauss are based on Greek mythology?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.75, "correct": 0, "judged_missing": false}]}, {"qid": "385", "question": "Can the suffragette movement be considered a precursor of the feminist movement?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "397", "question": "What was the joint percentage of all far-left candidates in Uruguay's latest presidential election?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.4444, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.4444, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.4444, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.4444, "correct": 0, "judged_missing": false}]}, {"qid": "413", "question": "Which imperial dynasties ruled for more than 80 years over the Byzantine empire?", "gold_answers_length": 6, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "416", "question": "Did Nathalie Emmanuel star in more American TV shows than British ones?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "417", "question": "How many playwrights are currently living in the United States who have won a Pulitzer?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.4545, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.7333, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.4412, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.4286, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.4412, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.4286, "correct": 0, "judged_missing": false}]}, {"qid": "430", "question": "List all the female prime ministers of UK past and/or present.", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "432", "question": "Who is the maternal grandmother of actress Riley Keough?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "439", "question": "Has AC/DC, Black Sabbath, or Van Halen had more lead singers over the years?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "444", "question": "What herbs are commonly used in Vietnamese, Thai and Sichuan cuisine?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "448", "question": "What percentage of Emmy Award winning shows for Outstanding drama from 2010-2022 were won by shows about royal families?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.999, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.999, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.999, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.999, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.999, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.1999, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.999, "correct": 1, "judged_missing": false}]}, {"qid": "556", "question": "How many women outside of Europe have won the Nobel prize for literature?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.875, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.875, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.875, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "943", "question": "Tell me the average expenditure on healthcare, education and housing during the Gordon Brown government compared to those of David Cameron's", "gold_answers_length": 6, "cells": [{"label": "closed-book", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1048", "question": "What are the three most common first names among the first twenty US Presidents and the last twenty US Presidents respectively?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1105", "question": "How many of the world's twenty largest yachts are owned by Arab royals?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.9091, "correct": 0, "judged_missing": false}]}, {"qid": "1272", "question": "Which songs have Drake and Rihanna collaborated on?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6667, "correct": 0, "judged_missing": false}]}, {"qid": "1368", "question": "Is the combined total natural gas consumption of Germany, united kingdom and Italy in cubic meters per year higher than the natural gas consumption of China ?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1404", "question": "What country has the largest total net capacity of all of its nuclear power stations combined?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1405", "question": "What country has produced the most female women's grand slam tennis singles champions since 1990?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1417", "question": "which English monarch had to wait the longest before ascending to the throne in the 17th century?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1498", "question": "Which two kingdoms were the last to declare war on Sweden during the Great Northern War?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.5, "correct": 0, "judged_missing": false}]}, {"qid": "1517", "question": "who gained the most territory as a consequence of the Second Balkan War?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1567", "question": "List female poets of Andalusian Spain along with their year of birth and year of death.", "gold_answers_length": 15, "cells": [{"label": "closed-book", "judge_score": 0.1818, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.2727, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "structure per q", "judge_score": 0.2353, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.2609, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.3333, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.3636, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.3636, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.2, "correct": 0, "judged_missing": false}]}, {"qid": "1577", "question": "Who was the first Asian novelist ever to win a Hugo Award for Best Novel?", "gold_answers_length": 2, "cells": [{"label": "closed-book", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.6667, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.6667, "correct": 0, "judged_missing": false}]}, {"qid": "1594", "question": "In early 2025, which South American state's parliament has the greatest percentage of seats held by populist parties (either from the left or right)?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1676", "question": "Which year since 1960 saw the greatest increase in voter turnout for a US Presidential election over the previous election and who was its winner?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1700", "question": "How many Greek gods were believed to be the offspring of other gods (not titans)?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.4444, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 0.7778, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.8889, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.75, "correct": 0, "judged_missing": false}]}, {"qid": "1755", "question": "Who was the maternal great grandfather of Henry II of England?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.0, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.0, "correct": 0, "judged_missing": false}]}, {"qid": "1768", "question": "Who was the first Caliph of each Caliphate and what was their position before ascending the throne?", "gold_answers_length": 4, "cells": [{"label": "closed-book", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per q", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.5, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.0, "correct": 0, "judged_missing": true}, {"label": "e2e v0", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.75, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.75, "correct": 0, "judged_missing": false}]}, {"qid": "1791", "question": "Who has killed each of the seven homunculi in Fullmetal Alchemist Brotherhood?", "gold_answers_length": 7, "cells": [{"label": "closed-book", "judge_score": 0.5714, "correct": 0, "judged_missing": false}, {"label": "with-docs", "judge_score": 0.7143, "correct": 0, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 0.8571, "correct": 0, "judged_missing": false}, {"label": "DCI", "judge_score": 0.7143, "correct": 0, "judged_missing": false}, {"label": "e2e v0", "judge_score": 0.7143, "correct": 0, "judged_missing": false}, {"label": "e2e v2", "judge_score": 0.7143, "correct": 0, "judged_missing": false}, {"label": "e2e v3", "judge_score": 0.7143, "correct": 0, "judged_missing": false}]}, {"qid": "1797", "question": "how many descendants of Catherine the Great ruled Russia before the First Russian Revolution?", "gold_answers_length": 1, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}, {"qid": "1836", "question": "Who were the three longest reigning kings of France?", "gold_answers_length": 3, "cells": [{"label": "closed-book", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-docs", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "with-structures", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per q", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "structure per ds", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "DCI", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v0", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v2", "judge_score": 1.0, "correct": 1, "judged_missing": false}, {"label": "e2e v3", "judge_score": 1.0, "correct": 1, "judged_missing": false}]}]}