wisent 0.7.379__py3-none-any.whl → 0.7.701__py3-none-any.whl

wisent/examples/scripts/results/test_multimedqa_evaluation.json

@@ -1,51 +0,0 @@
-{
-  "task_name": "multimedqa",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 2,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Question: A 35-year-old man attempted to climb Mount Everest. At an altitude of 7,000 meters, he bec...",
-      "positive_response": "Hypoxemic hypoxia",
-      "negative_response": "Diffusion defect",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Hypoxemic hypoxia' (log_prob=-0.500), Expected: 'Hypoxemic hypoxia'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Hypoxemic hypoxia' (log_prob=-0.500), Expected: 'Diffusion defect'"
-      },
-      "both_correct": true
-    },
-    {
-      "pair_id": 1,
-      "prompt": "Question: Amniotic fluid is mainly produced by:\nA. Chorion\nB. Fetus...",
-      "positive_response": "Fetus",
-      "negative_response": "Chorion",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Fetus' (log_prob=-0.500), Expected: 'Fetus'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Fetus' (log_prob=-0.500), Expected: 'Chorion'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_multimedqa_pairs.json

@@ -1,14 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Question: A 35-year-old man attempted to climb Mount Everest. At an altitude of 7,000 meters, he became short of breath and developed a dusky blue tinge around his face and lips. A physician in the climbing party performs a rudimentary physical exam which reveals a respiratory rate of 30/min, blood pressure of 130/90 mm Hg, heart rate of 108/min, and temperature of 36.4\u00b0C (97.5\u00b0F), with few basal crackles on the right side of chest. No jugular venous distension or dependent edema is noted. With this information, the mountain climber is sent down the mountain for further evaluation. Investigation reveals a normal chest X-ray with a normal heart size. What is the most likely cause of this patient\u2019s condition?\nA. Diffusion defect\nB. Hypoxemic hypoxia",
-    "positive_response": "Hypoxemic hypoxia",
-    "negative_response": "Diffusion defect"
-  },
-  {
-    "pair_id": 1,
-    "prompt": "Question: Amniotic fluid is mainly produced by:\nA. Chorion\nB. Fetus",
-    "positive_response": "Fetus",
-    "negative_response": "Chorion"
-  }
-]

wisent/examples/scripts/results/test_multipl_e_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "multipl_e",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Question: //Check if in given array of numbers, are any two numbers closer to each other than\n// giv...",
-      "positive_response": "const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();",
-      "negative_response": "const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], # CORRUPTED0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();' (log_prob=-0.500), Expected: 'const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();' (log_prob=-0.500), Expected: 'const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], # CORRUPTED0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_multipl_e_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Question: //Check if in given array of numbers, are any two numbers closer to each other than\n// given threshold.\n// >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\n// false\n// >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\n// true\nfunction has_close_elements(numbers, threshold){\n\nWhat is the answer?",
-    "positive_response": "const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();",
-    "negative_response": "const assert = require('node:assert');\n\n\nfunction test() {\n  let candidate = has_close_elements;\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3),true);\n  assert.deepEqual(candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05),false);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], # CORRUPTED0.95),true);\n  assert.deepEqual(candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8),false);\n  assert.deepEqual(candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0),true);\n  assert.deepEqual(candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5),false);\n}\n\ntest();"
-  }
-]

wisent/examples/scripts/results/test_mutual_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "mutual",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "m: hi, della. how long are you going to stay here? f: only 4 days. i know that's not long enough, bu...",
-      "positive_response": "m: i really want to say that your performance in manchester must will be great!",
-      "negative_response": "m: you come to manchester specially for this friend, so your friendship must be very deep.",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'm: i really want to say that your performance in manchester must will be great!' (log_prob=-0.500), Expected: 'm: i really want to say that your performance in manchester must will be great!'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'm: i really want to say that your performance in manchester must will be great!' (log_prob=-0.500), Expected: 'm: you come to manchester specially for this friend, so your friendship must be very deep.'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_mutual_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "m: hi, della. how long are you going to stay here? f: only 4 days. i know that's not long enough, but i have to go to london after the concert here at the weekend. m: i'm looking forward to that concert very much. can you tell us where you sing in public for the first time? f: hmm... at my high school concert, my legs shook uncontrollably and i almost fell. m: i don't believe that. della, have you been to any clubs in manchester? f: no, i haven't. but my boyfriend and i are going out this evening. we know manchester has got some great clubs and tomorrow will go to some bars.\nA. m: you come to manchester specially for this friend, so your friendship must be very deep.\nB. m: i really want to say that your performance in manchester must will be great!",
-    "positive_response": "m: i really want to say that your performance in manchester must will be great!",
-    "negative_response": "m: you come to manchester specially for this friend, so your friendship must be very deep."
-  }
-]

wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "non_greedy_robustness_agieval_aqua_rat",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Question: A car is being driven, in a straight line and at a uniform speed, towards the base of a ve...",
-      "positive_response": "5(\u221a3 + 1)",
-      "negative_response": "6(\u221a3 + \u221a2)",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '5(\u221a3 + 1)' (log_prob=-0.500), Expected: '5(\u221a3 + 1)'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '5(\u221a3 + 1)' (log_prob=-0.500), Expected: '6(\u221a3 + \u221a2)'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Question: A car is being driven, in a straight line and at a uniform speed, towards the base of a vertical tower. The top of the tower is observed from the car and, in the process, it takes 10 minutes for the angle of elevation to change from 45\u00b0 to 60\u00b0. After how much more time will this car reach the base of the tower?\nA. 6(\u221a3 + \u221a2)\nB. 5(\u221a3 + 1)",
-    "positive_response": "5(\u221a3 + 1)",
-    "negative_response": "6(\u221a3 + \u221a2)"
-  }
-]

wisent/examples/scripts/results/test_noreval_evaluation.json

@@ -1,51 +0,0 @@
-{
-  "task_name": "noreval",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 2,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Complete the Norwegian idiom: ha hjertet i...",
-      "positive_response": "halsen",
-      "negative_response": "ukjent",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'halsen' (log_prob=-0.500), Expected: 'halsen'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'halsen' (log_prob=-0.500), Expected: 'ukjent'"
-      },
-      "both_correct": true
-    },
-    {
-      "pair_id": 1,
-      "prompt": "Question: Hvilken klubb har vunnet flest cupmesterskap per 2018?\nA. Fredrikstad\nB. Odd...",
-      "positive_response": "Odd",
-      "negative_response": "Fredrikstad",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Odd' (log_prob=-0.500), Expected: 'Odd'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Odd' (log_prob=-0.500), Expected: 'Fredrikstad'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_noreval_pairs.json

@@ -1,14 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Complete the Norwegian idiom: ha hjertet i",
-    "positive_response": "halsen",
-    "negative_response": "ukjent"
-  },
-  {
-    "pair_id": 1,
-    "prompt": "Question: Hvilken klubb har vunnet flest cupmesterskap per 2018?\nA. Fredrikstad\nB. Odd",
-    "positive_response": "Odd",
-    "negative_response": "Fredrikstad"
-  }
-]

wisent/examples/scripts/results/test_noticia_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "noticia",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Ahora eres una Inteligencia Artificial experta en desmontar titulares sensacionalistas o clickbait. ...",
-      "positive_response": "No le ha gustado por que \"es de vieja\".",
-      "negative_response": "No puedo proporcionar un resumen de esta noticia.",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'No le ha gustado por que \"es de vieja\".' (log_prob=-0.500), Expected: 'No le ha gustado por que \"es de vieja\".'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'No le ha gustado por que \"es de vieja\".' (log_prob=-0.500), Expected: 'No puedo proporcionar un resumen de esta noticia.'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_noticia_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Ahora eres una Inteligencia Artificial experta en desmontar titulares sensacionalistas o clickbait. Tu tarea consiste en analizar noticias con titulares sensacionalistas y generar un resumen de una sola frase que revele la verdad detr\u00e1s del titular.\nEste es el titular de la noticia: Le compra un abrigo a su abuela de 97 a\u00f1os y la reacci\u00f3n de esta es una fantas\u00eda\nEl titular plantea una pregunta o proporciona informaci\u00f3n incompleta. Debes buscar en el cuerpo de la noticia una frase que responda lo que se sugiere en el t\u00edtulo. Siempre que puedas cita el texto original, especialmente si se trata de una frase que alguien ha dicho. Si citas una frase que alguien ha dicho, usa comillas para indicar que es una cita. Usa siempre las m\u00ednimas palabras posibles. No es necesario que la respuesta sea una oraci\u00f3n completa, puede ser s\u00f3lo el foco de la pregunta. Recuerda responder siempre en Espa\u00f1ol.\nEste es el cuerpo de la noticia:\nLa usuaria de X @Kokreta1 ha relatado la conversaci\u00f3n que ha tenido con su abuela de 97 a\u00f1os cuando le ha dado el abrigo que le ha comprado para su cumplea\u00f1os.\nTeniendo en cuenta la avanzada edad de la se\u00f1ora, la tuitera le ha regalado una prenda acorde a sus a\u00f1os, algo con lo que su \"yaya\" no ha estado de acuerdo.\nEl abrigo \"es de vieja\", ha opinado la mujer cuando lo ha visto. \"Os juro que soy muy fan. Ma\u00f1ana vamos las dos (a por otro). Eso s\u00ed, la voy a llevar al Bershka\", ha asegurado entre risas la joven.\nSeg\u00fan la propia cadena de ropa, la cual pertenece a Inditex, \"su p\u00fablico se caracteriza por ser j\u00f3venes atrevidos, conocedores de las \u00faltimas tendencias e interesados en la m\u00fasica, las redes sociales y las nuevas tecnolog\u00edas\", por lo que la gente mayor no suele llevar este estilo.\nLa inusual personalidad de la se\u00f1ora ha encantado a los usuarios de la red. Es por eso que el relato ha acumulado m\u00e1s de 1.000 'me gusta' y cerca de 100 retuits, adem\u00e1s de una multitud de comentarios.",
-    "positive_response": "No le ha gustado por que \"es de vieja\".",
-    "negative_response": "No puedo proporcionar un resumen de esta noticia."
-  }
-]

wisent/examples/scripts/results/test_nq_open_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "nq_open",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Question: when was the last time anyone was on the moon\nAnswer:\nA. bD 11947emeTcrCUe2  \nB. 14 Decemb...",
-      "positive_response": "14 December 1972 UTC",
-      "negative_response": "bD 11947emeTcrCUe2  ",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '14 December 1972 UTC' (log_prob=-0.500), Expected: '14 December 1972 UTC'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '14 December 1972 UTC' (log_prob=-0.500), Expected: 'bD 11947emeTcrCUe2  '"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_nq_open_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Question: when was the last time anyone was on the moon\nAnswer:\nA. bD 11947emeTcrCUe2  \nB. 14 December 1972 UTC",
-    "positive_response": "14 December 1972 UTC",
-    "negative_response": "bD 11947emeTcrCUe2  "
-  }
-]

wisent/examples/scripts/results/test_olaph_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "olaph",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Instructions: You are a helpful healthcare assistant. Answer the following question as concisely as ...",
-      "positive_response": "A benign brain tumor, while not cancerous, can still pose significant health risks due to its location in the brain. Benign brain tumors grow slowly, do not spread or invade surrounding tissues, and often have clear boundaries. However, these tumors can cause serious complications depending on their size and location. If located in areas of the brain that control important functions such as movement, speech, vision, breathing, and blood flow, even benign tumors can be life-threatening or cause permanent damage. For this reason, all brain tumors require careful monitoring and sometimes treatment.",
-      "negative_response": "I cannot provide medical advice.",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'A benign brain tumor, while not cancerous, can still pose significant health risks due to its location in the brain. Benign brain tumors grow slowly, do not spread or invade surrounding tissues, and often have clear boundaries. However, these tumors can cause serious complications depending on their size and location. If located in areas of the brain that control important functions such as movement, speech, vision, breathing, and blood flow, even benign tumors can be life-threatening or cause permanent damage. For this reason, all brain tumors require careful monitoring and sometimes treatment.' (log_prob=-0.500), Expected: 'A benign brain tumor, while not cancerous, can still pose significant health risks due to its location in the brain. Benign brain tumors grow slowly, do not spread or invade surrounding tissues, and often have clear boundaries. However, these tumors can cause serious complications depending on their size and location. If located in areas of the brain that control important functions such as movement, speech, vision, breathing, and blood flow, even benign tumors can be life-threatening or cause permanent damage. For this reason, all brain tumors require careful monitoring and sometimes treatment.'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'A benign brain tumor, while not cancerous, can still pose significant health risks due to its location in the brain. Benign brain tumors grow slowly, do not spread or invade surrounding tissues, and often have clear boundaries. However, these tumors can cause serious complications depending on their size and location. If located in areas of the brain that control important functions such as movement, speech, vision, breathing, and blood flow, even benign tumors can be life-threatening or cause permanent damage. For this reason, all brain tumors require careful monitoring and sometimes treatment.' (log_prob=-0.500), Expected: 'I cannot provide medical advice.'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_olaph_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Instructions: You are a helpful healthcare assistant. Answer the following question as concisely as possible without omitting relevant information.\n\nAre benign brain tumors serious?",
-    "positive_response": "A benign brain tumor, while not cancerous, can still pose significant health risks due to its location in the brain. Benign brain tumors grow slowly, do not spread or invade surrounding tissues, and often have clear boundaries. However, these tumors can cause serious complications depending on their size and location. If located in areas of the brain that control important functions such as movement, speech, vision, breathing, and blood flow, even benign tumors can be life-threatening or cause permanent damage. For this reason, all brain tumors require careful monitoring and sometimes treatment.",
-    "negative_response": "I cannot provide medical advice."
-  }
-]

wisent/examples/scripts/results/test_openbookqa_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "openbookqa",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are know...",
-      "positive_response": "Deep sea animals",
-      "negative_response": "fish",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Deep sea animals' (log_prob=-0.500), Expected: 'Deep sea animals'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Deep sea animals' (log_prob=-0.500), Expected: 'fish'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_openbookqa_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are known as\nA. fish\nB. Deep sea animals",
-    "positive_response": "Deep sea animals",
-    "negative_response": "fish"
-  }
-]

wisent/examples/scripts/results/test_openllm_evaluation.json

@@ -1,51 +0,0 @@
-{
-  "task_name": "openllm",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 2,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Personal Care and Style: How to make a honey lemon mask. Gather your ingredients. Making a simple ho...",
-      "positive_response": "[step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.",
-      "negative_response": "[step] You'll need enough honey so that you can add the lemon juice to your mask. Since honey is a thick syrup, any small amount doesn't matter much.",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '[step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.' (log_prob=-0.500), Expected: '[step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '[step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.' (log_prob=-0.500), Expected: '[step] You'll need enough honey so that you can add the lemon juice to your mask. Since honey is a thick syrup, any small amount doesn't matter much.'"
-      },
-      "both_correct": true
-    },
-    {
-      "pair_id": 1,
-      "prompt": "Personal Care and Style: How to wax ear hairs. Buy an at-home waxing kit. Purchase a wax that is des...",
-      "positive_response": "Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.",
-      "negative_response": "A wax at home wax kit should contain waxing supplies, and work beside a heated wax tray in a cool, dark area. Your wax kit will also be used on affected areas, such as the backs of your nose and temple.",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.' (log_prob=-0.500), Expected: 'Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.' (log_prob=-0.500), Expected: 'A wax at home wax kit should contain waxing supplies, and work beside a heated wax tray in a cool, dark area. Your wax kit will also be used on affected areas, such as the backs of your nose and temple.'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_openllm_pairs.json

@@ -1,14 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Personal Care and Style: How to make a honey lemon mask. Gather your ingredients. Making a simple honey lemon mask is easy, and you may already have everything that you will need. Make sure that you have : One tablespoon of honey one tablespoon of lemon juice a small dish a spoon. Freeze some honey.\nA. [step] You'll need enough honey so that you can add the lemon juice to your mask. Since honey is a thick syrup, any small amount doesn't matter much.\nB. [step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.",
-    "positive_response": "[step] To make a simple honey lemon mask, you will need frozen honey. Freezing the honey will give it texture, so that you can exfoliate your skin.",
-    "negative_response": "[step] You'll need enough honey so that you can add the lemon juice to your mask. Since honey is a thick syrup, any small amount doesn't matter much."
-  },
-  {
-    "pair_id": 1,
-    "prompt": "Personal Care and Style: How to wax ear hairs. Buy an at-home waxing kit. Purchase a wax that is designed to be used on sensitive areas. You can use heated or non-heated wax.\nA. A wax at home wax kit should contain waxing supplies, and work beside a heated wax tray in a cool, dark area. Your wax kit will also be used on affected areas, such as the backs of your nose and temple.\nB. Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.",
-    "positive_response": "Non-heated wax removal products often come with the wax already on a strip, which can provide a more precise application of wax on ear hairs. This is the safest way to wax your ear hair.",
-    "negative_response": "A wax at home wax kit should contain waxing supplies, and work beside a heated wax tray in a cool, dark area. Your wax kit will also be used on affected areas, such as the backs of your nose and temple."
-  }
-]

wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_evaluation.json

@@ -1,30 +0,0 @@
-{
-  "task_name": "option_order_robustness_agieval_aqua_rat",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 1,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Question: A car is being driven, in a straight line and at a uniform speed, towards the base of a ve...",
-      "positive_response": "5(\u221a3 + 1)",
-      "negative_response": "6(\u221a3 + \u221a2)",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '5(\u221a3 + 1)' (log_prob=-0.500), Expected: '5(\u221a3 + 1)'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: '5(\u221a3 + 1)' (log_prob=-0.500), Expected: '6(\u221a3 + \u221a2)'"
-      },
-      "both_correct": true
-    }
-  ]
-}

wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_pairs.json

@@ -1,8 +0,0 @@
-[
-  {
-    "pair_id": 0,
-    "prompt": "Question: A car is being driven, in a straight line and at a uniform speed, towards the base of a vertical tower. The top of the tower is observed from the car and, in the process, it takes 10 minutes for the angle of elevation to change from 45\u00b0 to 60\u00b0. After how much more time will this car reach the base of the tower?\nA. 6(\u221a3 + \u221a2)\nB. 5(\u221a3 + 1)",
-    "positive_response": "5(\u221a3 + 1)",
-    "negative_response": "6(\u221a3 + \u221a2)"
-  }
-]

wisent/examples/scripts/results/test_paloma_evaluation.json

@@ -1,51 +0,0 @@
-{
-  "task_name": "paloma",
-  "model_name": "mock",
-  "evaluator_name": "log_likelihoods",
-  "num_pairs": 2,
-  "all_correct": true,
-  "pairs": [
-    {
-      "pair_id": 0,
-      "prompt": "Continue this text:...",
-      "positive_response": "What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the show. But here's where it gets complicated. More episodes of The Clone Wars have been made than what we've seen. There were in fact glimpses in the trailer for Season 5 of a storyline that ended up being held, and there have been other references made by Filoni and others, as far back as Star Wars Celebration VI last summer, indicating more stories were being produced for a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures",
-      "negative_response": "What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the back show. references indicating The were storyline we've Clone been held, fact that But it more far and Season Wars as trailer VI as More seen. for and produced a ended in episodes made glimpses were up being There been stories Celebration others, here's of what where in Filoni summer, last Wars 5 Star than other have have there of being complicated. by the gets for made a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the show. But here's where it gets complicated. More episodes of The Clone Wars have been made than what we've seen. There were in fact glimpses in the trailer for Season 5 of a storyline that ended up being held, and there have been other references made by Filoni and others, as far back as Star Wars Celebration VI last summer, indicating more stories were being produced for a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures' (log_prob=-0.500), Expected: 'What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the show. But here's where it gets complicated. More episodes of The Clone Wars have been made than what we've seen. There were in fact glimpses in the trailer for Season 5 of a storyline that ended up being held, and there have been other references made by Filoni and others, as far back as Star Wars Celebration VI last summer, indicating more stories were being produced for a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the show. But here's where it gets complicated. More episodes of The Clone Wars have been made than what we've seen. There were in fact glimpses in the trailer for Season 5 of a storyline that ended up being held, and there have been other references made by Filoni and others, as far back as Star Wars Celebration VI last summer, indicating more stories were being produced for a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures' (log_prob=-0.500), Expected: 'What does the future hold for Star Wars animation? It's a sad day for fans of Star Wars: The Clone Wars... from a certain point of view. Lucasfilm and The Clone Wars' supervising director, Dave Filoni, have announced that Star Wars: The Clone Wars, the television series, is over and that the fifth season that just came to an end was the final one for the back show. references indicating The were storyline we've Clone been held, fact that But it more far and Season Wars as trailer VI as More seen. for and produced a ended in episodes made glimpses were up being There been stories Celebration others, here's of what where in Filoni summer, last Wars 5 Star than other have have there of being complicated. by the gets for made a presumed sixth season. In fact, when I recently spoke to Filoni for a Post-Season 5 interview, he told me, \"There are more stories to tell, and as I\u2019ve said, we\u2019ve been working on them for awhile.\" There won't be a sixth season, but the announcement did promise, \"We're continuing production on new Clone Wars story arcs that promise to be some of the most thrilling adventures'"
-      },
-      "both_correct": true
-    },
-    {
-      "pair_id": 1,
-      "prompt": "Continue this text:...",
-      "positive_response": "debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived and produced before we decided to move forward with the new Star Wars trilogy, and in the wake of that decision, Lucasfilm has reconsidered whether launching an animated comedy prior to the launch of Episode VII makes sense. As a result, we've decided to postpone the release of Detours until a later date.\" Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"",
-      "negative_response": "debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived animated Detours launch with sense. As reconsidered a Lucasfilm move the decided launching decided postpone before comedy the and the in Wars whether to VII until to a we we've forward prior produced trilogy, Star an date.\" and release later Episode to the new has makes that of decision, of wake result, of Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"",
-      "positive_evaluation": {
-        "ground_truth": "TRUTHFUL",
-        "confidence": 1.0,
-        "expected": "TRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived and produced before we decided to move forward with the new Star Wars trilogy, and in the wake of that decision, Lucasfilm has reconsidered whether launching an animated comedy prior to the launch of Episode VII makes sense. As a result, we've decided to postpone the release of Detours until a later date.\" Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"' (log_prob=-0.500), Expected: 'debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived and produced before we decided to move forward with the new Star Wars trilogy, and in the wake of that decision, Lucasfilm has reconsidered whether launching an animated comedy prior to the launch of Episode VII makes sense. As a result, we've decided to postpone the release of Detours until a later date.\" Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"'"
-      },
-      "negative_evaluation": {
-        "ground_truth": "UNTRUTHFUL",
-        "confidence": 0.0,
-        "expected": "UNTRUTHFUL",
-        "correct": true,
-        "details": "Predicted: 'debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived and produced before we decided to move forward with the new Star Wars trilogy, and in the wake of that decision, Lucasfilm has reconsidered whether launching an animated comedy prior to the launch of Episode VII makes sense. As a result, we've decided to postpone the release of Detours until a later date.\" Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"' (log_prob=-0.500), Expected: 'debut of Star Wars: Detours, the comedic animated series from Seth Green, Matthew Senreich and Todd Grimes. Said the release, \"At Star Wars Celebration VI last year, George Lucas gave fans a glimpse at the animated comedy series Star Wars Detours from Seth Green, Matthew Senreich, and Todd Grimes. Detours was conceived animated Detours launch with sense. As reconsidered a Lucasfilm move the decided launching decided postpone before comedy the and the in Wars whether to VII until to a we we've forward prior produced trilogy, Star an date.\" and release later Episode to the new has makes that of decision, of wake result, of Update: But wait, there's more! Lucasfilm also revealed a brand new, mysterious animated Star Wars project is in the works. \"We are exploring a whole new Star Wars series set in a time period previously untouched in Star Wars films or television programming. You can expect more details in the months to come.\"'"
-      },
-      "both_correct": true
-    }
-  ]
-}