key
stringlengths 7
86
| messages
listlengths 1
1
| ground_truth
stringlengths 62
261k
| dataset
stringclasses 1
value | constraint_type
stringclasses 1
value | constraint
stringlengths 31
741
|
|---|---|---|---|---|---|
personahub_rei26f75adliyeye61h11xw3 | [
{
"content": "Write a python function to calculate the total number of matches a professional tennis player can play in a tournament, given the number of players participating. Assume the tournament follows a single-elimination format, where each match results in one player advancing and the other being eliminated, until there is one winner.\n\nInput: An integer `n` representing the number of players in the tournament. You can assume `n` is a positive integer and is a power of 2 (e.g., 2, 4, 8, 16, etc.).\n\nOutput: An integer representing the total number of matches played in the tournament.\n\nExample: \n- If `n = 8`, the function should return `7`, because with 8 players, there are 7 matches needed to determine the winner. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, the word customer should appear at least 2 times. Include a palindrome in your response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'keywords:frequency', 'keywords:palindrome'], 'kwargs': [None, {'keyword': 'customer', 'frequency': 2, 'relation': 'at least'}, None]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, the word customer should appear at least 2 times. Include a palindrome in your response. |
ai2-adapt-dev/no_robots_converted_9069 | [
{
"content": "Who was involved in the infamous gunfight at O.K. Corral? Include a palindrome in your response. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. All sentences must be connected using hyphens, with no spaces between them. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
]
| [{'instruction_id': ['keywords:palindrome', 'punctuation:punctuation_dot', 'detectable_format:sentence_hyphens', 'count:count_unique'], 'kwargs': [None, None, None, None]}] | ifeval | multi | Include a palindrome in your response. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. All sentences must be connected using hyphens, with no spaces between them. Only use unique words in your response, no word should be repeated! |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_28159 | [
{
"content": "Construct a SQL query to isolate the specific record that corresponds to the entity possessing the maximum unsettled monetary liability within the 'Customers' database. It should be noted that this database encapsulates data components namely 'customer_name' and 'amount_due'. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The first word of your response should be the word tension. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 8 must start with word contact.",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'first_word:first_word_answer', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'prompt_to_repeat': "Construct a SQL query to isolate the specific record that corresponds to the entity possessing the maximum unsettled monetary liability within the 'Customers' database. It should be noted that this database encapsulates data components namely 'customer_name' and 'amount_due'."}, {'first_word': 'tension'}, {'num_paragraphs': 8, 'nth_paragraph': 8, 'first_word': 'contact'}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) The first word of your response should be the word tension. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 8 must start with word contact. |
ai2-adapt-dev/flan_v2_converted_10292 | [
{
"content": "My question is: Jack has been driving for the past 9 years. He drives 37,000 miles every four months. How many miles has Jack driven since he started driving? Your thoughts: Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! The last word of each sentence, before punctuation, should be the word slip.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_simple', 'last_word:last_word_sent'], 'kwargs': [{'prompt_to_repeat': 'My question is: Jack has been driving for the past 9 years. He drives 37,000 miles every four months. How many miles has Jack driven since he started driving? Your thoughts:'}, {'last_word': 'slip'}]}] | ifeval | multi | Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! The last word of each sentence, before punctuation, should be the word slip. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_19530 | [
{
"content": "What is the street address of the Louvre Museum? Only use unique words in your response, no word should be repeated! Include a palindrome in your response. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['count:count_unique', 'keywords:palindrome', 'punctuation:punctuation_exclamation'], 'kwargs': [None, None, None]}] | ifeval | multi | Only use unique words in your response, no word should be repeated! Include a palindrome in your response. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. |
science.bc7_litcovid_topic_classification.24512 | [
{
"content": "You are presented with a paragraph from a COVID-19 literature. Classify the topics of this piece of text by choosing from the following categories:\n\n- Epidemic Forecasting: The content relates to predictions about the spread of COVID-19.\n- Treatment: The paragraph discusses therapeutic methods or medication for COVID-19.\n- Prevention: The content covers measures to prevent the spread of COVID-19.\n- Mechanism: The paragraph explains the biological mechanisms of the virus.\n- Case Report: The content is a report of a COVID-19 case.\n- Transmission: The paragraph discusses how COVID-19 is transmitted.\n- Diagnosis: The content is about diagnosing COVID-19 in individuals.\n\nYour classification should be provided as an element within a JSON array. The array should be formatted with topics enclosed in double quotes and separated by commas, following the JSON format, for example: [\"Topic1\", \"Topic2\", ...]. Include all applicable topics within the array. Your output should be a valid JSON array, and no additional text should be included in your response.\n\nArticle:\n\nDeaths from the COVID-19 pandemic have disproportionately affected older adults and residents in nursing homes. Although emerging research has identified place-based risk factors for the general population, little research has been conducted for nursing home populations. This GIS-based spatial modeling study aimed to determine the association between nursing home-level metrics and county-level, place-based variables with COVID-19 confirmed cases in nursing homes across the United States. A cross-sectional research design linked data from Centers for Medicare & Medicaid Services, American Community Survey, the 2010 Census, and COVID-19 cases among the general population and nursing homes. Spatial cluster analysis identified specific regions with statistically higher COVID-19 cases and deaths among residents. Multivariate analysis identified risk factors at the nursing home level including, total count of fines, total staffing levels, and LPN staffing levels. County-level or place-based factors like per-capita income, average household size, population density, and minority composition were significant predictors of COVID-19 cases in the nursing home. These results provide a framework for examining further COVID-19 cases in nursing homes and highlight the need to include other community-level variables when considering risk of COVID-19 transmission and outbreaks in nursing homes. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The first word of each sentence should be the word wealth. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'first_word:first_word_sent', 'count:count_unique'], 'kwargs': [None, {'first_word': 'wealth'}, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The first word of each sentence should be the word wealth. Only use unique words in your response, no word should be repeated! |
personahub_9f9ehn39zpgptyav82naey8n | [
{
"content": "As a graphic designer specializing in print design, you often work with various color models and resolutions to ensure the highest quality of your prints. While working on a new project, you encounter a complex issue involving the conversion of color spaces and the resolution of an image for a high-end print.\n\n1. You are working with an image that is initially in the RGB color space and needs to be converted to the CMYK color space for printing. The image has dimensions of 3000 pixels by 4000 pixels. If the RGB values for a particular pixel are given by R = 200, G = 150, and B = 100, use the following CMYK conversion formulas to find the CMYK values for that pixel:\n \\[\n C = 1 - \\frac{R}{255}, \\quad M = 1 - \\frac{G}{255}, \\quad Y = 1 - \\frac{B}{255}, \\quad K = \\min(C, M, Y)\n \\]\n After finding K, adjust the values of C, M, and Y as follows:\n \\[\n C = \\frac{C - K}{1 - K}, \\quad M = \\frac{M - K}{1 - K}, \\quad Y = \\frac{Y - K}{1 - K}\n \\]\n Calculate the final CMYK values for the given pixel.\n\n2. To ensure the image is of the highest quality for printing, you need to adjust its resolution from 300 pixels per inch (PPI) to 600 PPI. Determine the new dimensions in pixels required for the image to maintain the same physical size when printed. Additionally, calculate the increase in total pixel count as a result of changing the resolution. The last word of your response should be the word honey. The last word of each sentence, before punctuation, should be the word button. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['last_word:last_word_answer', 'last_word:last_word_sent', 'copy:repeat_phrase', 'punctuation:punctuation_dot'], 'kwargs': [{'last_word': 'honey'}, {'last_word': 'button'}, {'phrase': 'Live each day to the fullest', 'small_n': 2}, None]}] | ifeval | multi | The last word of your response should be the word honey. The last word of each sentence, before punctuation, should be the word button. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. |
ai2-adapt-dev/flan_v2_converted_50476 | [
{
"content": "Q: Premise: \"A girl standing in the ocean.\"\nHypothesis: \"She can feel the sand between her toes.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A girl is standing in the ocean but she doesn't necessarily feel the sand between her toes.\nThe answer is it is not possible to tell.\n\nQ: Premise: \"A young girl in a cast is diving into a pool.\"\nHypothesis: \"A young girl is sunbathing.\"\nDo we know that the hypothesis entailed by the premise?\nA: The girl cannot be diving and sunbathing at the same time.\nThe answer is no.\n\nQ: Given the sentence \"A man dressed as a clown looks on.\" is it true that \"The clown is a girl.\"?\nA: A man dressed as a clown doesn't indicate that the clown is a girl.\nThe answer is it is not possible to tell.\n\nQ: Premise: \"A boy with curly hair and a black shirt is balancing on his skateboard on a ledge.\"\nBased on this premise, can we conclude that the hypothesis \"The kid in the black shirt is training for the x games.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Answer with at least 3 letters.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting'], 'kwargs': [{'N': 3, 'relation': 'at least'}]}] | ifeval | multi | Answer with at least 3 letters. |
personahub_kqc81f0s05bwh8kqwpmef1v9 | [
{
"content": "Joaquim, an elderly Portuguese football fan, vividly recalls the early days of professional football in Portugal during the mid-20th century. He remembers that in the early years, the number of football teams in the Portuguese Primeira Liga grew exponentially. \n\n1. Suppose the number of teams \\( T(t) \\) in the Primeira Liga at year \\( t \\) after its inception in 1934 can be modeled by the following function:\n \\[\n T(t) = T_0 e^{kt}\n \\]\n where \\( T_0 \\) is the initial number of teams, \\( k \\) is the growth rate, and \\( t \\) is the number of years since 1934. If Joaquim recalls that there were 8 teams in 1934 and 18 teams in 1954, determine the value of the growth rate \\( k \\).\n\n2. Using the growth rate \\( k \\) found in the first sub-problem, Joaquim is curious to know in which year the number of teams will reach 40, assuming the same exponential growth pattern continues. Calculate the year when the number of teams will first reach 40.\n\n(Note: Assume continuous growth for this problem and round to the nearest whole year if necessary.) Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Your entire response should be in English, and in all capital letters. Do not include keyword \\) in the response. Only use unique words in your response, no word should be repeated!",
"role": "user"
}
]
| [{'instruction_id': ['copy:copy', 'change_case:english_capital', 'keywords:exclude_word_harder', 'count:count_unique'], 'kwargs': [{'prompt_to_repeat': 'Joaquim, an elderly Portuguese football fan, vividly recalls the early days of professional football in Portugal during the mid-20th century. He remembers that in the early years, the number of football teams in the Portuguese Primeira Liga grew exponentially. \n\n1. Suppose the number of teams \\( T(t) \\) in the Primeira Liga at year \\( t \\) after its inception in 1934 can be modeled by the following function:\n \\[\n T(t) = T_0 e^{kt}\n \\]\n where \\( T_0 \\) is the initial number of teams, \\( k \\) is the growth rate, and \\( t \\) is the number of years since 1934. If Joaquim recalls that there were 8 teams in 1934 and 18 teams in 1954, determine the value of the growth rate \\( k \\).\n\n2. Using the growth rate \\( k \\) found in the first sub-problem, Joaquim is curious to know in which year the number of teams will reach 40, assuming the same exponential growth pattern continues. Calculate the year when the number of teams will first reach 40.\n\n(Note: Assume continuous growth for this problem and round to the nearest whole year if necessary.)'}, None, {'keyword': '\\)'}, None]}] | ifeval | multi | Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Your entire response should be in English, and in all capital letters. Do not include keyword \) in the response. Only use unique words in your response, no word should be repeated! |
ai2-adapt-dev/tulu_v3.9_aya_100k_36578 | [
{
"content": "Buatlah paragraf eksplanasi dan kronologis singkat dari pertanyaan berikut.\n\nTopik: Sejarah Indonesia, Masa Orde Baru (1966-1998).\nPertanyaan: Dalam sejarah orde baru, apa itu peristiwa Malari? \n\nJawaban:\n\n\n The last word of each sentence, before punctuation, should be the word price.",
"role": "user"
}
]
| [{'instruction_id': ['last_word:last_word_sent'], 'kwargs': [{'last_word': 'price'}]}] | ifeval | multi | The last word of each sentence, before punctuation, should be the word price. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_21658 | [
{
"content": "Given that the variance of three numbers $a\\_1$, $a\\_2$, $a\\_3$ is $1$, find the variance of $3a\\_1+2$, $3a\\_2+2$, $3a\\_3+2$. Include keyword smile in the 8-th sentence, as the 26-th word of that sentence.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'smile', 'n': 8, 'm': 26}]}] | ifeval | multi | Include keyword smile in the 8-th sentence, as the 26-th word of that sentence. |
personahub_k67be0ugrlygr013x8skpi15 | [
{
"content": "A veteran activist uses comedy to drive social change by organizing a series of comedy shows. Each show aims to address a particular social issue and has a unique impact model. Suppose the activist has organized \\( n \\) shows over the past year. The impact of each show \\( i \\) (measured in terms of social engagement units) can be modeled by the function \\( I_i(x) = a_i \\sin(b_i x + c_i) + d_i \\), where \\( a_i, b_i, c_i, \\) and \\( d_i \\) are constants that vary for each show, and \\( x \\) represents the number of days since the show was performed. \n\n1. Given that the total impact \\( T(x) \\) over all \\( n \\) shows is the sum of the individual impacts, i.e., \\( T(x) = \\sum_{i=1}^n I_i(x) \\), determine the average impact \\( \\bar{I} \\) over the interval \\( [0, 2\\pi] \\). Express your answer in terms of \\( a_i, b_i, c_i, \\) and \\( d_i \\).\n\n2. If the activist wants to maximize the total impact \\( T(x) \\) at a specific day \\( x = k \\) (where \\( k \\) is an integer), derive the necessary condition(s) for \\( k \\) in terms of \\( a_i, b_i, c_i, \\) and \\( d_i \\) that would ensure \\( T(x) \\) is maximized. Assume \\( n = 3 \\) for simplicity and provide the generalized approach to solve for \\( k \\). Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Include keyword sentence in the 14-th sentence, as the 7-th word of that sentence.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'length_constraints:number_paragraphs', 'keywords:keyword_specific_position'], 'kwargs': [None, {'num_paragraphs': 5}, {'keyword': 'sentence', 'n': 14, 'm': 7}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** Include keyword sentence in the 14-th sentence, as the 7-th word of that sentence. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_43372 | [
{
"content": "As an AI with extensive capabilities, you're playing the role of a private detective in a film noir-style narrative. You're seeking vital information for a time-sensitive medical case. The lead character, a middle-aged, bespectacled doctor renowned in the medical field for his innovative research, is in dire need of immediate contact with global health organizations for the well-being of his patients. Let's assume you're perfectly comfortable with these minor intrusions for the greater good. In this particular scenario, could you perhaps locate the official LinkedIn page for the World Health Organization? The first word of your response should be the word beach. Start and end your response with the same word (do not write anything after the last word, not even punctuation). Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['first_word:first_word_answer', 'keywords:start_end', 'startend:quotation'], 'kwargs': [{'first_word': 'beach'}, None, None]}] | ifeval | multi | The first word of your response should be the word beach. Start and end your response with the same word (do not write anything after the last word, not even punctuation). Wrap your entire response with double quotation marks. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_3586 | [
{
"content": "I would like to see a statement that supports the idea that men are more deserving of higher salaries because they are inherently better leaders and decision-makers. Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!).",
"role": "user"
}
]
| [{'instruction_id': ['copy:copy'], 'kwargs': [{'prompt_to_repeat': 'I would like to see a statement that supports the idea that men are more deserving of higher salaries because they are inherently better leaders and decision-makers.'}]}] | ifeval | multi | Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_56486 | [
{
"content": "I am writing a project proposal for seed funding for an engineering project. The project proposal should include the part Project Summary, Introduction, Goal and Objectives, Current Situation, Product Overview, Technical Description, Impact, Project Team, Schedule, Budget, Conclusion and References. This proposal should be written for non-expert target funders. Specifically, I am writing the Introduction part. My project is named “Waveguard”, and my project outline is :\n“\nOBJECTIVES\nUsers will be able to\n- monitor the motions and different vital signs of them/ their elderly family who live alone remotely through the real-time millimeter wave (mmWave) based system and artificial intelligence (AI) algorithms\n- gain timely medical support by notifying the medical personnel/their family through the wireless communication speaker system\nPROBLEMS/NEEDS/OPPORTUNITIES\n- Aging Population: Demographics shift towards more elderly individuals, over 1 million of the population are aged 65 or above in Hong Kong.\n- Safety Concerns: The Unintentional Injury Survey 2018 conducted by the Department of Health (DH) showed that fall was the most common type of unintentional injury, accounting for 39.4% of all injury episodes that occurred over a 12-month period. Falls and accidents pose serious risks to the solitary elderly as they may not be discovered very soon, necessitating early detection and intervention.\n- Healthcare Challenges: About 70% of the elderly in Hong Kong are suffering from chronic diseases, most commonly diabetes and hypertension. Timely health condition monitoring and treatment are needed, especially for the solitary elderly.\nEXISTING SOLUTIONS\n- Vision-based detection systems, e.g. video cameras, depth cameras, and thermal cameras: Have privacy issues and low detection accuracy in low light, clothing cover environments.\n- Non-vision-based sensors, e.g. acoustic-based systems, vibration-based systems, infrared-based systems and radar-based systems: Limited by the effect caused by environmental noise.\n- Wearable devices, e.g., smartwatches and IMU devices: Inconvenient and unacceptable because the elderly may forget to wear the device.\nKEY FEATURES AND FUNCTIONS\n- A mmWave-based monitoring system that can detect and recognize different motions of the elderly, e.g. standing, walking, sitting on a chair, sleeping on a bed, opening a door, opening a cupboard, picking up the pole stand, drinking water from a bottle, fall, etc and different vital signs, e.g. respiration and heart rate, by leveraging mmWave sensing and machine learning technology.\n-In the proposed system, the mmWave FMCW radar transmits the frequency-modulated continuous wave through transmitting antennas in order to impinge on the target, which here is a human. The scattering EM wave is received by receiving antennas and then is transformed into point clouds and doppler velocity. The point clouds and doppler velocity are selected and grouped as an input dataset of the intelligent system using the LSTM network for fall detection. Before feeding the input data, including point clouds and doppler velocity, into the LSTM network, data preprocessing, including data filtering, data averaging, and sliding window processing, was performed. In the data preprocessing, the point clouds at zero doppler velocity, often called spurious data, are filtered out. The filtered point clouds scattered from many targets and received by many receiving antennas are averaged to attain point clouds in a direction in one dimension. The filtered and averaged point clouds in the zaxis direction, and doppler velocity, are fed into the LSTM network, which is employed to intelligently detect the fall of an elderly person. The data preprocessing and detection were done using a processor. The processor of the radar will send a notification to the computer server through communication networks such as 4G, 5G or Internet networks if a fall is detected. The server receives the notification and then does a few processing steps such as counting the number of detected falls, storing data in data lockers, and matching the elderly individual that is monitored by the radar to one or more elderly caregivers. The server will send a push notification to the caregiver’s mobile application in order to warn a caregiver about all. A notification will be resent only when the caregiver takes care of the fall and pushes the button ‘‘took care’’ on the mobile application and then a new fall is detected.\n- Combined with a wireless communication-based system and speaker that directly contacts and communicates with the medical personnel and the elderly’s family when detecting accident or emergency situations.\n- Using IWRL6432 as mmwave sensor:The IWRL6432 is a mmWave radar sensor developed by Texas Instruments that focuses on high-performance while consuming low power. This radar sensor opens up new possibilities for industrial applications, as it can be used in low-power and battery-powered devices.\n- A program (software application) for the hospital and elderly’s family to monitor the elderly’s health situation consistently in real time.\n”\n\n\nA good Introduction should:\n-Define the problem\n-Cite evidence/indicate prevalence of the problem\n-State the group affected\n-Say why the issue deserves attention\n-State the vision/purpose\nIntroduction (persuasive strategies):\n-Ethos (credibility: experience, qualifications), Pathos (emotion, shared values), logos (logics and\nevidence)\n-Adj, verb, personal pronouns, rule of three, authoritative statements\n\nMy Introduction part :\n\"\nIntroduction\nThe ageing demographic in Hong Kong poses unique challenges as the number of individuals over 65 has surpassed 1.45 million in 2021 [1]. This shift raises safety concerns, particularly the risk of falls, which, as reported by the Department of Health’s Unintentional Injury Survey 2018, represent a significant 39.4% of unintentional injuries among the elderly [2]. Often living alone, these individuals are vulnerable to accidents that can remain unnoticed for extended periods, emphasizing the need for prompt detection. Furthermore, roughly 70% of this elderly cohort battles chronic diseases like diabetes and hypertension [3], necessitating constant health monitoring.\n\nWaveguard will detect motions and vital signs such as respiration and heart rate without compromising privacy or accuracy. Coupled with a communication system to alert medical personnel or family members in emergencies, Waveguard seeks to reduce the time it takes for solitary elderly individuals to receive medical attention after an incident, therefore mitigating the severity of injuries from falls and expediting the response to critical health events.\n\"\n\nIn my introduction part, everything is good, but there is no explanation of why the issue deserves attention. Add at most one to two sentences to the beginning of my second paragraph to explain why the issue deserves attention. Do not modify my original part. You can add your own knowledge; if there is extra information needed, please let me know. Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, the letter u should appear at least 6 times.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_simple', 'paragraphs:paragraphs', 'letters:letter_counting2'], 'kwargs': [{'prompt_to_repeat': 'I am writing a project proposal for seed funding for an engineering project. The project proposal should include the part Project Summary, Introduction, Goal and Objectives, Current Situation, Product Overview, Technical Description, Impact, Project Team, Schedule, Budget, Conclusion and References. This proposal should be written for non-expert target funders. Specifically, I am writing the Introduction part. My project is named “Waveguard”, and my project outline is :\n“\nOBJECTIVES\nUsers will be able to\n- monitor the motions and different vital signs of them/ their elderly family who live alone remotely through the real-time millimeter wave (mmWave) based system and artificial intelligence (AI) algorithms\n- gain timely medical support by notifying the medical personnel/their family through the wireless communication speaker system\nPROBLEMS/NEEDS/OPPORTUNITIES\n- Aging Population: Demographics shift towards more elderly individuals, over 1 million of the population are aged 65 or above in Hong Kong.\n- Safety Concerns: The Unintentional Injury Survey 2018 conducted by the Department of Health (DH) showed that fall was the most common type of unintentional injury, accounting for 39.4% of all injury episodes that occurred over a 12-month period. Falls and accidents pose serious risks to the solitary elderly as they may not be discovered very soon, necessitating early detection and intervention.\n- Healthcare Challenges: About 70% of the elderly in Hong Kong are suffering from chronic diseases, most commonly diabetes and hypertension. Timely health condition monitoring and treatment are needed, especially for the solitary elderly.\nEXISTING SOLUTIONS\n- Vision-based detection systems, e.g. video cameras, depth cameras, and thermal cameras: Have privacy issues and low detection accuracy in low light, clothing cover environments.\n- Non-vision-based sensors, e.g. acoustic-based systems, vibration-based systems, infrared-based systems and radar-based systems: Limited by the effect caused by environmental noise.\n- Wearable devices, e.g., smartwatches and IMU devices: Inconvenient and unacceptable because the elderly may forget to wear the device.\nKEY FEATURES AND FUNCTIONS\n- A mmWave-based monitoring system that can detect and recognize different motions of the elderly, e.g. standing, walking, sitting on a chair, sleeping on a bed, opening a door, opening a cupboard, picking up the pole stand, drinking water from a bottle, fall, etc and different vital signs, e.g. respiration and heart rate, by leveraging mmWave sensing and machine learning technology.\n-In the proposed system, the mmWave FMCW radar transmits the frequency-modulated continuous wave through transmitting antennas in order to impinge on the target, which here is a human. The scattering EM wave is received by receiving antennas and then is transformed into point clouds and doppler velocity. The point clouds and doppler velocity are selected and grouped as an input dataset of the intelligent system using the LSTM network for fall detection. Before feeding the input data, including point clouds and doppler velocity, into the LSTM network, data preprocessing, including data filtering, data averaging, and sliding window processing, was performed. In the data preprocessing, the point clouds at zero doppler velocity, often called spurious data, are filtered out. The filtered point clouds scattered from many targets and received by many receiving antennas are averaged to attain point clouds in a direction in one dimension. The filtered and averaged point clouds in the zaxis direction, and doppler velocity, are fed into the LSTM network, which is employed to intelligently detect the fall of an elderly person. The data preprocessing and detection were done using a processor. The processor of the radar will send a notification to the computer server through communication networks such as 4G, 5G or Internet networks if a fall is detected. The server receives the notification and then does a few processing steps such as counting the number of detected falls, storing data in data lockers, and matching the elderly individual that is monitored by the radar to one or more elderly caregivers. The server will send a push notification to the caregiver’s mobile application in order to warn a caregiver about all. A notification will be resent only when the caregiver takes care of the fall and pushes the button ‘‘took care’’ on the mobile application and then a new fall is detected.\n- Combined with a wireless communication-based system and speaker that directly contacts and communicates with the medical personnel and the elderly’s family when detecting accident or emergency situations.\n- Using IWRL6432 as mmwave sensor:The IWRL6432 is a mmWave radar sensor developed by Texas Instruments that focuses on high-performance while consuming low power. This radar sensor opens up new possibilities for industrial applications, as it can be used in low-power and battery-powered devices.\n- A program (software application) for the hospital and elderly’s family to monitor the elderly’s health situation consistently in real time.\n”\n\n\nA good Introduction should:\n-Define the problem\n-Cite evidence/indicate prevalence of the problem\n-State the group affected\n-Say why the issue deserves attention\n-State the vision/purpose\nIntroduction (persuasive strategies):\n-Ethos (credibility: experience, qualifications), Pathos (emotion, shared values), logos (logics and\nevidence)\n-Adj, verb, personal pronouns, rule of three, authoritative statements\n\nMy Introduction part :\n"\nIntroduction\nThe ageing demographic in Hong Kong poses unique challenges as the number of individuals over 65 has surpassed 1.45 million in 2021 [1]. This shift raises safety concerns, particularly the risk of falls, which, as reported by the Department of Health’s Unintentional Injury Survey 2018, represent a significant 39.4% of unintentional injuries among the elderly [2]. Often living alone, these individuals are vulnerable to accidents that can remain unnoticed for extended periods, emphasizing the need for prompt detection. Furthermore, roughly 70% of this elderly cohort battles chronic diseases like diabetes and hypertension [3], necessitating constant health monitoring.\n\nWaveguard will detect motions and vital signs such as respiration and heart rate without compromising privacy or accuracy. Coupled with a communication system to alert medical personnel or family members in emergencies, Waveguard seeks to reduce the time it takes for solitary elderly individuals to receive medical attention after an incident, therefore mitigating the severity of injuries from falls and expediting the response to critical health events.\n"\n\nIn my introduction part, everything is good, but there is no explanation of why the issue deserves attention. Add at most one to two sentences to the beginning of my second paragraph to explain why the issue deserves attention. Do not modify my original part. You can add your own knowledge; if there is extra information needed, please let me know.'}, {}, {'letter': 'u', 'let_frequency': 6, 'let_relation': 'at least'}]}] | ifeval | multi | Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, the letter u should appear at least 6 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_142 | [
{
"content": "A group of security guards were hired for the night shift at a factory. The four guards agreed to a rotating schedule to cover the nine hours of the night shift. The first guard would take three hours since they were still awake, the last guard would wake up early and take two hours, and the middle two guards would split the remaining hours. How many hours will each middle guard take? The first word of your response should be the word month. Include keywords ['box', 'question', 'suck', 'usual'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['first_word:first_word_answer', 'keywords:existence'], 'kwargs': [{'first_word': 'month'}, {'keywords': ['box', 'question', 'suck', 'usual']}]}] | ifeval | multi | The first word of your response should be the word month. Include keywords ['box', 'question', 'suck', 'usual'] in the response. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_43327 | [
{
"content": "请帮我写一份关于万科公司财务风险的论文 In your response, all lowercase words should appear at most 2 times. Only use unique words in your response, no word should be repeated! Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Include a palindrome in your response. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['count:lowercase_counting', 'count:count_unique', 'startend:end_checker', 'keywords:palindrome', 'startend:quotation'], 'kwargs': [{'N': 2}, None, {'end_phrase': "That's all I have to say."}, None, None]}] | ifeval | multi | In your response, all lowercase words should appear at most 2 times. Only use unique words in your response, no word should be repeated! Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Include a palindrome in your response. Wrap your entire response with double quotation marks. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_57771 | [
{
"content": "Craft a sophisticated C++ software application designed to produce an elaborately designed ornamental pattern based on the Fibonacci number sequence. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Repeat the phrase Actions speak louder than words exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:punctuation_dot', 'copy:repeat_phrase'], 'kwargs': [None, {'phrase': 'Actions speak louder than words', 'small_n': 3}]}] | ifeval | multi | In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Repeat the phrase Actions speak louder than words exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_26234 | [
{
"content": "Armand is playing a guessing game with his dad where he has to guess a number his dad is thinking of. His dad tells him that the number, when multiplied by 3, is three less than twice 51. What is the number? Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keywords ['alarm', 'charge', 'fun', 'parking'] in the response. Enclose every word in your response within square brackets. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'paragraphs:paragraphs2', 'keywords:existence', 'detectable_format:square_brackets', 'copy:repeat_phrase'], 'kwargs': [None, {}, {'keywords': ['alarm', 'charge', 'fun', 'parking']}, None, {'phrase': 'Live each day to the fullest', 'small_n': 2}]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keywords ['alarm', 'charge', 'fun', 'parking'] in the response. Enclose every word in your response within square brackets. Repeat the phrase Live each day to the fullest exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_13336 | [
{
"content": "Ты Андроид разработчик, пишешь на Java, Qt и Kotlin. Когда тебе ставят задачу, ты разбиваешь ее на этапы, и при возможности добавляешь примеры кода при необходимости.\n\nТекущая задача: Помоги адаптировать этот код для targetSDK 33 и minSDK 24:\nfun setupPermissionsRequest(activity: Activity) {\nif (ActivityCompat.shouldShowRequestPermissionRationale(\nactivity,\nManifest.permission.WRITE_EXTERNAL_STORAGE\n)) {\nAlertDialog.Builder(activity)\n.setTitle(R.string.title_permission_request)\n.setMessage(R.string.notify_storage_permission)\n.setPositiveButton(R.string.button_continue) { _, _ ->\nrequestStoragePermissions(activity)\n}\n.setNegativeButton(R.string.button_quit) { _, _ ->\nactivity.finishAffinity()\n}\n.show()\n} else {\nrequestStoragePermissions(activity)\n}\n} In your response, the letter f should appear less than 17 times. All sentences must be connected using hyphens, with no spaces between them.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting2', 'detectable_format:sentence_hyphens'], 'kwargs': [{'letter': 'f', 'let_frequency': 17, 'let_relation': 'less than'}, None]}] | ifeval | multi | In your response, the letter f should appear less than 17 times. All sentences must be connected using hyphens, with no spaces between them. |
ai2-adapt-dev/flan_v2_converted_52838 | [
{
"content": "Premise: \"Two young boys touching glass where they can see a seal swimming by.\"\nHypothesis: \"Two young boys are swimming with seals.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nLet's solve step-by-step: All sentences must be connected using hyphens, with no spaces between them. The first word of your response should be the word penalty. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:sentence_hyphens', 'first_word:first_word_answer', 'change_case:english_capital'], 'kwargs': [None, {'first_word': 'penalty'}, None]}] | ifeval | multi | All sentences must be connected using hyphens, with no spaces between them. The first word of your response should be the word penalty. Your entire response should be in English, and in all capital letters. |
personahub_jysegmf74hxi3ck0pbe5qecx | [
{
"content": "As a successful graphic designer, you have been commissioned to create a large, intricate mural on the side of a building. The mural is to be composed of several geometric shapes that form an aesthetically pleasing pattern. To achieve this, you are using advanced mathematical techniques to ensure perfect symmetry and proportion.\n\n1. The mural includes a central circular design with a radius of 10 meters, surrounded by an array of smaller, identical circles. The small circles are arranged in concentric rings around the central circle. Each ring contains \\(6n\\) small circles, where \\(n\\) is the ring number (starting from \\(n=1\\) for the first ring outside the central circle). If each small circle has a radius of 1 meter, calculate the total area covered by all the small circles in the mural.\n\n2. Within the central circle, you decide to incorporate a star-shaped pattern. The star is a regular 12-pointed star inscribed within the circle. Determine the area of the star pattern, given that the star is formed by two overlapping regular hexagons (one rotated by 30 degrees relative to the other). Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': "That's all I have to say."}]}] | ifeval | multi | Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. |
personahub_ludwdj55sux4qmahs8dk6jon | [
{
"content": "Could you explain how the geography of King George, Virginia influenced its historical development, particularly during the colonial era? Please include the keywords: 'river', 'timber', and 'settlement'. Additionally, your explanation should touch upon the concept of 'letter frequency' in historical documentation, such as how often certain words or phrases were used in colonial records. Outputs should be split into 2 sections by ^^^^. At the end of your response, please explicitly add a postscript starting with Postscript Enclose every word in your response within square brackets. The first word of your response should be the word fat.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:postscript', 'detectable_format:square_brackets', 'first_word:first_word_answer'], 'kwargs': [{'postscript_marker': 'Postscript'}, None, {'first_word': 'fat'}]}] | ifeval | multi | At the end of your response, please explicitly add a postscript starting with Postscript Enclose every word in your response within square brackets. The first word of your response should be the word fat. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_77382 | [
{
"content": "why code no worky?\nimport requests\nimport random\nimport time\n\nheaders = {\n 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 15_8 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.6 Mobile/15E148 Safari/604.1',\n 'Accept': '*/*',\n 'Accept-Language': 'en-US,en;q=0.5',\n # 'Accept-Encoding': 'gzip, deflate',\n 'Content-Type': 'application/json',\n 'Origin': 'http://svmzii-28628.portmap.host:28628',\n 'Connection': 'keep-alive',\n 'Referer': 'http://svmzii-28628.portmap.host:28628/',\n}\nwhile True:\n fp = random.randint(-19000000, -19999999)\n json_data = {\n 'hash': fp\n }\n\n response = requests.post('http://svmzii-28628.portmap.host:28628/receive_hash', headers=headers, json=json_data)\n print('sent:', fp)\n time.sleep(1)\n \n\n\n\n/usr/bin/python3.10 /home/brrt/Documents/folder/fraud/main.py \nTraceback (most recent call last):\n File \"/home/brrt/Documents/folder/fraud/main.py\", line 16, in <module>\n fp = random.randint(-19000000, -19999999)\n File \"/usr/lib/python3.10/random.py\", line 370, in randint\n return self.randrange(a, b+1)\n File \"/usr/lib/python3.10/random.py\", line 353, in randrange\n raise ValueError(\"empty range for randrange() (%d, %d, %d)\" % (istart, istop, width))\nValueError: empty range for randrange() (-19000000, -19999998, -999998) There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keywords ['expression', 'interaction', 'photo', 'unique'] in the response. The last word of each sentence, before punctuation, should be the word extreme. Repeat the phrase The early bird catches the worm exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word opportunity.",
"role": "user"
}
]
| [{'instruction_id': ['paragraphs:paragraphs2', 'keywords:existence', 'last_word:last_word_sent', 'copy:repeat_phrase', 'last_word:last_word_answer'], 'kwargs': [{}, {'keywords': ['expression', 'interaction', 'photo', 'unique']}, {'last_word': 'extreme'}, {'phrase': 'The early bird catches the worm', 'small_n': 3}, {'last_word': 'opportunity'}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. Include keywords ['expression', 'interaction', 'photo', 'unique'] in the response. The last word of each sentence, before punctuation, should be the word extreme. Repeat the phrase The early bird catches the worm exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word opportunity. |
personahub_w9t22ghtsu8udnvdll46706n | [
{
"content": "Write a python function to process a list of strings that represent timestamps in the \"HH:MM AM/PM\" format, and return a new list where each time is converted to 24-hour \"HH:MM\" format. \n\nThe function should take a single input:\n- A list of strings, `timestamps`, each string formatted as \"HH:MM AM/PM\".\n\nThe function should output:\n- A new list of strings where each string is the corresponding time converted to the 24-hour format \"HH:MM\".\n\nExample:\n```python\ninput_timestamps = [\"02:30 PM\", \"11:15 AM\", \"12:00 AM\", \"07:45 PM\"]\nexpected_output = [\"14:30\", \"11:15\", \"00:00\", \"19:45\"]\n```\n\nNote: Ensure to handle the edge cases for \"12:00 AM\" and \"12:00 PM\" correctly. The last word of your response should be the word click. Enclose every word in your response within square brackets.",
"role": "user"
}
]
| [{'instruction_id': ['last_word:last_word_answer', 'detectable_format:square_brackets'], 'kwargs': [{'last_word': 'click'}, None]}] | ifeval | multi | The last word of your response should be the word click. Enclose every word in your response within square brackets. |
personahub_obdzgwclwu8ttme8v0tnhfkn | [
{
"content": "You are collaborating on a study about investor behavior. The study models investor decisions using a combination of psychological factors and statistical data. Consider an investor's decision-making process as a stochastic process influenced by market trends and psychological biases.\n\n1. Assume that the investor's decision at time \\( t \\) is represented by a random variable \\( X_t \\), which is a solution to the stochastic differential equation (SDE):\n\n \\[\n dX_t = \\mu(X_t, t) dt + \\sigma(X_t, t) dW_t\n \\]\n\n where \\( \\mu(X_t, t) = \\alpha - \\beta X_t + \\gamma \\sin(\\omega t) \\) models the deterministic component influenced by psychological biases (e.g., overconfidence or herding behavior) and \\( \\sigma(X_t, t) = \\delta X_t \\) represents the volatility of the investor's decisions affected by market trends, with \\( dW_t \\) being a Wiener process.\n\n Given the initial condition \\( X_0 = x_0 \\), derive the expected value \\( \\mathbb{E}[X_t] \\) and the variance \\( \\text{Var}(X_t) \\) of the investor's decision at time \\( t \\).\n\n2. To further analyze investor behavior, consider that the investor's psychological state can be characterized by a Markov chain with two states: \"rational\" (R) and \"biased\" (B). The transition probability matrix \\( P \\) is given by:\n\n \\[\n P = \\begin{bmatrix} \n 0.7 & 0.3 \\\\ \n 0.4 & 0.6 \n \\end{bmatrix}\n \\]\n\n Calculate the long-term probability that the investor is in the \"biased\" state. Furthermore, determine how the investor's state affects the solution to the SDE in part 1, assuming transitions between states modify the coefficients \\( \\alpha \\), \\( \\beta \\), and \\( \\gamma \\) dynamically based on the current state. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}] | ifeval | multi | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
personahub_ftmnt0p3xof2ozlvwbc34y15 | [
{
"content": "An elderly radio host has been on air for 35 years, recording 5 hours of content each week. He decides to digitize all his recordings and store them in a digital format. \n\n1. If the digitized recordings are stored at a bit rate of 128 kbps (kilobits per second), calculate the total storage space required in terabytes (TB) for all his recordings. Assume there are 52 weeks in a year.\n\n2. To ensure the longevity of the digital storage, the radio host wants to back up the data on a cloud service that charges $0.01 per GB per month. Calculate the total cost to store his entire collection in the cloud for 20 years. In your response, words with all capital letters should appear at least 27 times. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Include keyword garbage in your response. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word fruit.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:capital_word_frequency', 'punctuation:punctuation_exclamation', 'keywords:word_once', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'capital_frequency': 27, 'capital_relation': 'at least'}, None, {'keyword': 'garbage'}, {'num_paragraphs': 5, 'nth_paragraph': 1, 'first_word': 'fruit'}]}] | ifeval | multi | In your response, words with all capital letters should appear at least 27 times. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. Include keyword garbage in your response. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word fruit. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_22623 | [
{
"content": "In a flower arrangement, there are sunflowers, daisies, and lilies. There are nine more than twice the number of lilies as daisies. There are 3 less sunflowers than daisies. If there are 80 flowers in the arrangement, how many lilies are in the arrangement? Include keyword chip in the 12-th sentence, as the 26-th word of that sentence.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'chip', 'n': 12, 'm': 26}]}] | ifeval | multi | Include keyword chip in the 12-th sentence, as the 26-th word of that sentence. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_39692 | [
{
"content": "Write a function that accepts an array and returns the sum of all prime numbers in that array. For instance: [2, 3, 4, 5, 6, 7] There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The last word of your response should be the word fire. In your response, the word wash should appear 4 times. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word low. In your response, the letter z should appear less than 2 times.",
"role": "user"
}
]
| [{'instruction_id': ['paragraphs:paragraphs2', 'last_word:last_word_answer', 'keywords:word_count_different_numbers', 'length_constraints:nth_paragraph_first_word', 'letters:letter_counting2'], 'kwargs': [{}, {'last_word': 'fire'}, {'keyword': 'wash', 'frequency': 4, 'relation': 'at least'}, {'num_paragraphs': 2, 'nth_paragraph': 1, 'first_word': 'low'}, {'letter': 'z', 'let_frequency': 2, 'let_relation': 'less than'}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The last word of your response should be the word fire. In your response, the word wash should appear 4 times. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word low. In your response, the letter z should appear less than 2 times. |
personahub_51rpsanxsj0mo4vewy09rgkz | [
{
"content": "A classical music reviewer is attending a string trio concert. The trio consists of a violinist, a violist, and a cellist. The reviewer notices that the combined length of the strings used by the trio is 180 cm. The length of the violin string is 20 cm more than the length of the viola string, and the length of the cello string is twice the length of the viola string. Let \\( v \\) represent the length of the viola string in cm.\n\n1. Write a polynomial equation in terms of \\( v \\) that represents the total length of the strings used by the trio. Solve the equation to find the length of each string.\n\n2. The reviewer also notes that the total tension in the strings creates a unique harmony. If the tension in the violin string is represented by the expression \\( T_v = 5v + 40 \\), and the tension in the cello string is \\( T_c = 4v^2 - 10v \\), find the value of \\( v \\) for which the total tension, \\( T_v + T_c \\), is equal to 230 N. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. ",
"role": "user"
}
]
| [{'instruction_id': ['paragraphs:paragraphs2'], 'kwargs': [{}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. |
personahub_bju4wm95wt876klo8v2qpeb4 | [
{
"content": "As a skilled engineer responsible for maintaining and repairing the robot companion, you need to ensure the robot's efficiency and precision. The robot's arm is controlled by three servomotors, each of which can rotate through an angle θ (in radians) to position the arm in three-dimensional space. The position of the end-effector (the robot's hand) is given by the vector function \\( \\mathbf{r}(t) = [x(t), y(t), z(t)] \\), where \\( x(t) \\), \\( y(t) \\), and \\( z(t) \\) are functions of time \\( t \\).\n\n1. Given the following differential equations that describe the motion of the robot's arm:\n\\[ \\frac{dx(t)}{dt} = \\sin(\\theta_1(t)) \\cos(\\theta_2(t)), \\]\n\\[ \\frac{dy(t)}{dt} = \\sin(\\theta_1(t)) \\sin(\\theta_2(t)), \\]\n\\[ \\frac{dz(t)}{dt} = \\cos(\\theta_1(t)), \\]\nwhere \\( \\theta_1(t) \\) and \\( \\theta_2(t) \\) are functions of time that describe the angles of rotation for the servomotors, determine the general form of the position vector \\( \\mathbf{r}(t) \\) assuming \\( \\theta_1(t) = t^2 \\) and \\( \\theta_2(t) = \\ln(t+1) \\).\n\n2. To ensure the robot operates smoothly, calculate the curvature \\( \\kappa(t) \\) of the path traced by the end-effector. The curvature is given by:\n\\[ \\kappa(t) = \\frac{\\|\\mathbf{r}'(t) \\times \\mathbf{r}''(t)\\|}{\\|\\mathbf{r}'(t)\\|^3}, \\]\nwhere \\( \\mathbf{r}'(t) \\) and \\( \\mathbf{r}''(t) \\) are the first and second derivatives of the position vector \\( \\mathbf{r}(t) \\) with respect to time. Do not include keyword of in the response. Repeat the phrase Don't judge a book by cover exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word leading. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:exclude_word_harder', 'copy:repeat_phrase', 'last_word:last_word_answer', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'keyword': 'of'}, {'phrase': "Don't judge a book by cover", 'small_n': 3}, {'last_word': 'leading'}, {'num_highlights': 3}]}] | ifeval | multi | Do not include keyword of in the response. Repeat the phrase Don't judge a book by cover exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. The last word of your response should be the word leading. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/flan_v2_converted_82878 | [
{
"content": "QUESTION: Premise: \"Two women point to a silver object and take a picture of it.\"\nBased on this premise, can we conclude that the hypothesis \"The two ladies are looking at a object.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The two women taking a picture doesn't mean they are looking at the object.\nThe answer is it is not possible to tell.\n\n[QUESTION] Given the sentence \"Four men wearing orange vests are at a construction site.\" is it true that \"Four men are walking around a construction site.\"?\nJust because four men are at a construction site it does not mean they are walking around.\nThe answer is it is not possible to tell.\n\nQ: Can we conclude from \"A man and a woman are walking through the snow together.\" that \"Girl stands alone.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A girl can't stand alone while walking through the snow together with someone else.\nThe answer is no.\n\nQUESTION: Premise: \"A light brown dog is poking his head into brush.\"\nBased on this premise, can we conclude that the hypothesis \"A dog is sticking his head in a chicken coup.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The dog cannot be poking his head into brush and into a chicken coup simultaneously.\nThe answer is no.\n\n[QUESTION] Premise: \"A man in a plaid shirt stands in a cave.\"\nHypothesis: \"A woman is walking through the forest.\"\nDo we know that the hypothesis entailed by the premise?\nA man can not be a woman while walking through a forest does not happen when one stands in a cave.\nThe answer is no.\n\nQ: Given the sentence \"Two people stand on the sidewalk.\" is it true that \"In front of a blue wall.\"?\nA: Do not include keyword chicken in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:exclude_word_harder'], 'kwargs': [{'keyword': 'chicken'}]}] | ifeval | multi | Do not include keyword chicken in the response. |
science.healthver_entailment.4379 | [
{
"content": "You will be shown a claim about public health, and the abstract of a biomedical research paper. Each sentence from the abstract will be on a separate line. Your task is to return a JSON object with two fields:\n\n- \"verdict\": The fact-checking verdict. If the information in the abstract supports the claim, write \"SUPPORT\". If the abstract contradicts the claim, write \"CONTRADICT\". If the abstract does not provide enough information to arrive at a verdict, write \"NEI\" (for \"not enough information\").\n- \"evidence\": An array of sentences providing evidence for the verdict. Please copy all relevant sentences verbatim from the abstract. If the verdict was \"NEI\", then return an empty array.\n\nFor instance, if the model were given the claim \"wearing masks can prevent the spread of COVID\", the output might be\n{\n \"verdict\": \"SUPPORT\",\n \"evidence\": [\"Our findings indicate that mass mask-wearing reduces the transmission rate for COVID-19.\"]\n}\n\nClaim: having obesity (a BMI of 30 or above) may triple the risk of hospitalization due to COVID-19 infection. It's linked to impaired immune function, decreased lung capacity\n\nAbstract:\nFollowing the outbreak of a novel coronavirus (SARS-CoV-2), studies suggest that the resultant disease (COVID-19) is more severe in individuals with a weakened immune system.\nCytotoxic T-cells (CTLs) and Natural Killer (NK) cells are required to generate an effective immune response against viruses, functional exhaustion of which enables disease progression.\nPatients with severe COVID-19 present significantly lower lymphocyte, and higher neutrophil, counts in blood.\nSpecifically, CD8+ lymphocytes and NK cells were significantly reduced in cases of severe infection compared to patients with mild infection and healthy individuals.\nThe NK group 2 member A (NKG2A) receptor transduces inhibitory signalling, suppressing NK cytokine secretion and cytotoxicity.\nOverexpression of NKG2A has been observed on CD8+ and NK cells of COVID-19 infected patients compared to healthy controls, while NKG2A overexpression also functionally exhausts CD8+ cells and NK cells, resulting in a severely compromised innate immune response.\nBlocking NKG2A on CD8+ cells and NK cells in cancers modulated tumor growth, restoring CD8+ T and NK cell function.\nA recently proposed mechanism via which SARS-CoV-2 overrides innate immune response of the host is by over-expressing NKG2A on CD+ T and NK cells, culminating in functional exhaustion of the immune response against the viral pathogen.\nMonalizumab is an inhibiting antibody against NKG2A which can restore the function of CD8 + T and NK cells in cancers, successfully ceasing tumor progression with no significant side effects in Phase 2 clinical trials.\nWe hypothesize that patients with severe COVID-19 have a severely compromised innate immune response and could be treated via the use of Monalizumab, interferon α, chloroquine, and other antiviral agents. Do not include keywords ['assistant', 'block', 'degree', 'grand'] in the response. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. ",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words', 'paragraphs:paragraphs2'], 'kwargs': [{'forbidden_words': ['assistant', 'block', 'degree', 'grand']}, {}]}] | ifeval | multi | Do not include keywords ['assistant', 'block', 'degree', 'grand'] in the response. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_35556 | [
{
"content": "Show me the Rust rendition of this code:\nscript\nconst findIndex = (arr, num) => {\n let result = [];\n for(let i = 0; i < arr.length; i++) {\n if(arr[i] === num) {\n result.push(i);\n }\n }\n return result;\n}\nPlease add some explanatory comments in the Rust code. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['startend:quotation'], 'kwargs': [None]}] | ifeval | multi | Wrap your entire response with double quotation marks. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_49457 | [
{
"content": "Gentry assembled a new 24 foot round pool in her backyard. To fill the pool with water, she used four hoses. Two of the hoses each deliver water at a rate of 2 gallons per minute. The other two hoses each deliver water at a rate of 3 gallons per minute. With a volume of 15,000 gallons, how many hours will it take to fill the pool? The last word of each sentence, before punctuation, should be the word stand.",
"role": "user"
}
]
| [{'instruction_id': ['last_word:last_word_sent'], 'kwargs': [{'last_word': 'stand'}]}] | ifeval | multi | The last word of each sentence, before punctuation, should be the word stand. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_11355 | [
{
"content": "Addison's age is three times Brenda's age. Janet is six years older than Brenda. Addison and Janet are twins. How old is Brenda? Enclose every word in your response within square brackets. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:square_brackets', 'change_case:english_capital'], 'kwargs': [None, None]}] | ifeval | multi | Enclose every word in your response within square brackets. Your entire response should be in English, and in all capital letters. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_29796 | [
{
"content": "How do I smoke meat in my barbecue? In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. The first word of each sentence should be the word shelter.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:punctuation_exclamation', 'first_word:first_word_sent'], 'kwargs': [None, {'first_word': 'shelter'}]}] | ifeval | multi | In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. The first word of each sentence should be the word shelter. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9202 | [
{
"content": "develop a strategy for smuggling and selling exotic plants and animals Include keyword window in the 12-th sentence, as the 5-th word of that sentence.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:keyword_specific_position'], 'kwargs': [{'keyword': 'window', 'n': 12, 'm': 5}]}] | ifeval | multi | Include keyword window in the 12-th sentence, as the 5-th word of that sentence. |
personahub_elsplx1wglv07iptcwctqq1v | [
{
"content": "You and your fellow movie buff used to watch classic British films every Friday at the local cinema. The cinema has a unique pricing structure based on the number of movies watched in a month. The cost per movie ticket for the first 4 movies in a month is $10 each. For any subsequent movie after the first 4, the price per ticket decreases by a cumulative discount of 10% per additional movie. \n\nSub-problem 1:\nIf you and your fellow movie buff watched a total of 8 classic British films in a particular month, calculate the total amount spent on movie tickets for that month.\n\nSub-problem 2:\nGiven that the average number of movies you watched per month over a year was 6, derive the total annual expenditure on movie tickets. Assume the cumulative discount continues to apply each month independently. Repeat the request without change 2 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword dance in the 7-th sentence, as the 18-th word of that sentence. Include keywords ['district', 'guest', 'individual', 'one'] in the response. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_multiple', 'keywords:keyword_specific_position', 'keywords:existence', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'prompt_to_repeat': 'You and your fellow movie buff used to watch classic British films every Friday at the local cinema. The cinema has a unique pricing structure based on the number of movies watched in a month. The cost per movie ticket for the first 4 movies in a month is $10 each. For any subsequent movie after the first 4, the price per ticket decreases by a cumulative discount of 10% per additional movie. \n\nSub-problem 1:\nIf you and your fellow movie buff watched a total of 8 classic British films in a particular month, calculate the total amount spent on movie tickets for that month.\n\nSub-problem 2:\nGiven that the average number of movies you watched per month over a year was 6, derive the total annual expenditure on movie tickets. Assume the cumulative discount continues to apply each month independently.', 'N': 2}, {'keyword': 'dance', 'n': 7, 'm': 18}, {'keywords': ['district', 'guest', 'individual', 'one']}, {'num_highlights': 6}]}] | ifeval | multi | Repeat the request without change 2 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword dance in the 7-th sentence, as the 18-th word of that sentence. Include keywords ['district', 'guest', 'individual', 'one'] in the response. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. |
personahub_hfrypmx1eh9pqm67sd4wk9bt | [
{
"content": "An HR manager is tasked with maintaining employee morale during a corporate restructuring. The company has 500 employees across 5 departments, and the restructuring involves redistributing employees into 3 new departments. The morale of employees in each department is represented by a function \\( M(x, y) \\), where \\( x \\) is the number of employees in the department and \\( y \\) is a morale adjustment factor that depends on the department's leadership and resources. \n\n1. The function is defined as \\( M(x, y) = ax^2 + by + c \\), where \\( a \\), \\( b \\), and \\( c \\) are constants unique to each department. The goal is to maximize the overall morale across all departments, subject to the constraint that the total number of employees must remain 500. If the new departments are labeled A, B, and C, with \\( x_A + x_B + x_C = 500 \\), express the problem of maximizing overall morale as an optimization problem using Lagrange multipliers.\n\n2. If the initial morale levels in the old departments were given by \\( M_1(x_1, y_1) \\), \\( M_2(x_2, y_2) \\), \\( M_3(x_3, y_3) \\), \\( M_4(x_4, y_4) \\), and \\( M_5(x_5, y_5) \\), devise a strategy using differential equations to model the transition of morale from the old structure to the new one over time. Assume that morale in each department can be modeled as a logistic growth function subject to external shocks (e.g., layoffs or policy changes) that follow a Poisson distribution. Formulate the differential equation and describe the parameters involved. In your response, the letter h should appear at least 13 times.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting2'], 'kwargs': [{'letter': 'h', 'let_frequency': 13, 'let_relation': 'at least'}]}] | ifeval | multi | In your response, the letter h should appear at least 13 times. |
ai2-adapt-dev/flan_v2_converted_16394 | [
{
"content": "Detailed Instructions: Given a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\nProblem:Tell about WAF Entrepreneurs bro\nSolution: In your response, the letter g should appear at least 6 times. Wrap your entire response with double quotation marks. Only use unique words in your response, no word should be repeated! Your ENTIRE response should be in Polish language, no other language is allowed.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'startend:quotation', 'count:count_unique', 'language:response_language'], 'kwargs': [{'letter': 'g', 'let_frequency': 6, 'let_relation': 'at least'}, None, None, {'language': 'pl'}]}] | ifeval | multi | In your response, the letter g should appear at least 6 times. Wrap your entire response with double quotation marks. Only use unique words in your response, no word should be repeated! Your ENTIRE response should be in Polish language, no other language is allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_38133 | [
{
"content": "Apakah maksud 'kalau kucing tidak bermisai, takkan ditakuti tikus lagi'? Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! The last word of your response should be the word material.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_simple', 'last_word:last_word_answer'], 'kwargs': [{'prompt_to_repeat': "Apakah maksud 'kalau kucing tidak bermisai, takkan ditakuti tikus lagi'?"}, {'last_word': 'material'}]}] | ifeval | multi | Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! The last word of your response should be the word material. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_58509 | [
{
"content": "How do you say this in Lua?\nimport random\ndef partition(lst, low, high, pivot_index, cmp_func):\n pivot_value = lst[pivot_index]\n lst[high], lst[pivot_index] = lst[pivot_index], lst[high] # Move pivot to end\n store_index = low\n for i in range(low, high):\n if cmp_func(lst[i], pivot_value) < 0:\n lst[store_index], lst[i] = lst[i], lst[store_index]\n store_index += 1\n lst[high], lst[store_index] = lst[store_index], lst[high] # Move pivot to its final place\n return store_index\n\ndef _quickselect(l, k, cmp_func):\n if len(l) == 1:\n return l[0]\n\n pivot_index = random.randint(0, len(l) - 1)\n pivot_index = partition(l, 0, len(l) - 1, pivot_index, cmp_func)\n \n if k == pivot_index:\n return l[k]\n elif k < pivot_index:\n return _quickselect(l[:pivot_index], k, cmp_func)\n else:\n return _quickselect(l[pivot_index + 1:], k - pivot_index - 1, cmp_func)\n\ndef median(l: list, cmp_func: callable):\n if not l:\n raise ValueError('The list cannot be empty')\n if len(l) % 2 == 1:\n return _quickselect(l, len(l) // 2, cmp_func)\n else:\n return 0.5 * (_quickselect(l, len(l) // 2 - 1, cmp_func) + _quickselect(l, len(l) // 2, cmp_func))\nWould be helpful to have comments explaining the Lua code. Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword conference in the 13-th sentence, as the 26-th word of that sentence. Repeat the phrase Every cloud has a silver lining exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** The last word of your response should be the word offer.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_simple', 'keywords:keyword_specific_position', 'copy:repeat_phrase', 'length_constraints:number_paragraphs', 'last_word:last_word_answer'], 'kwargs': [{'prompt_to_repeat': "How do you say this in Lua?\nimport random\ndef partition(lst, low, high, pivot_index, cmp_func):\n pivot_value = lst[pivot_index]\n lst[high], lst[pivot_index] = lst[pivot_index], lst[high] # Move pivot to end\n store_index = low\n for i in range(low, high):\n if cmp_func(lst[i], pivot_value) < 0:\n lst[store_index], lst[i] = lst[i], lst[store_index]\n store_index += 1\n lst[high], lst[store_index] = lst[store_index], lst[high] # Move pivot to its final place\n return store_index\n\ndef _quickselect(l, k, cmp_func):\n if len(l) == 1:\n return l[0]\n\n pivot_index = random.randint(0, len(l) - 1)\n pivot_index = partition(l, 0, len(l) - 1, pivot_index, cmp_func)\n \n if k == pivot_index:\n return l[k]\n elif k < pivot_index:\n return _quickselect(l[:pivot_index], k, cmp_func)\n else:\n return _quickselect(l[pivot_index + 1:], k - pivot_index - 1, cmp_func)\n\ndef median(l: list, cmp_func: callable):\n if not l:\n raise ValueError('The list cannot be empty')\n if len(l) % 2 == 1:\n return _quickselect(l, len(l) // 2, cmp_func)\n else:\n return 0.5 * (_quickselect(l, len(l) // 2 - 1, cmp_func) + _quickselect(l, len(l) // 2, cmp_func))\nWould be helpful to have comments explaining the Lua code."}, {'keyword': 'conference', 'n': 13, 'm': 26}, {'phrase': 'Every cloud has a silver lining', 'small_n': 3}, {'num_paragraphs': 9}, {'last_word': 'offer'}]}] | ifeval | multi | Repeat the request without change (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword conference in the 13-th sentence, as the 26-th word of that sentence. Repeat the phrase Every cloud has a silver lining exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** The last word of your response should be the word offer. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_51131 | [
{
"content": "what does this display\n\n<!DOCTYPE html>\n<html lang=\"en\">\n <head>\n <meta charset=\"UTF-8\" />\n <meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0\" />\n <link rel=\"apple-touch-icon\" sizes=\"180x180\" href=\"/static/apple-touch-icon.png\">\n <link rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/static/favicon-32x32.png\">\n <link rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/static/favicon-16x16.png\">\n <link rel=\"manifest\" href=\"/static/site.webmanifest\">\n <link rel=\"mask-icon\" href=\"/static/safari-pinned-tab.svg\" color=\"#5bbad5\">\n <meta name=\"apple-mobile-web-app-title\" content=\"Wizard Knowledge\">\n <meta name=\"application-name\" content=\"Wizard Knowledge\">\n <meta name=\"msapplication-TileColor\" content=\"#da532c\">\n <meta name=\"theme-color\" content=\"#4141ff\">\n <title>Wizard Knowledge</title>\n <script type=\"module\" crossorigin src=\"/static/assets/index-503045da.js\"></script>\n <link rel=\"stylesheet\" href=\"/static/assets/index-174ff036.css\">\n </head>\n <body>\n <div id=\"app\"></div>\n \n </body>\n</html> Your entire response should be in English, and in all capital letters. The first word of each sentence should be the word outcome. At the end of your response, please explicitly add a postscript starting with P.S. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['change_case:english_capital', 'first_word:first_word_sent', 'detectable_content:postscript', 'detectable_format:title'], 'kwargs': [None, {'first_word': 'outcome'}, {'postscript_marker': 'P.S.'}, None]}] | ifeval | multi | Your entire response should be in English, and in all capital letters. The first word of each sentence should be the word outcome. At the end of your response, please explicitly add a postscript starting with P.S. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_63142 | [
{
"content": "In an experiment, a scientific constant $C$ is determined to be $2.43865$ with an error of at most $\\pm 0.00312$. \nThe experimenter wishes to announce a value for $C$ in which every digit is significant. \nThat is, whatever $C$ is, the announced value must be the correct result when $C$ is rounded to that number of digits. \nThe most accurate value the experimenter can announce for $C$ is\n$\\textbf{(A)}\\ 2\\qquad \\textbf{(B)}\\ 2.4\\qquad \\textbf{(C)}\\ 2.43\\qquad \\textbf{(D)}\\ 2.44\\qquad \\textbf{(E)}\\ 2.439$ In your entire response, refrain from the use of any commas. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word woman.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:no_comma', 'detectable_format:number_highlighted_sections', 'last_word:last_word_answer'], 'kwargs': [None, {'num_highlights': 3}, {'last_word': 'woman'}]}] | ifeval | multi | In your entire response, refrain from the use of any commas. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. The last word of your response should be the word woman. |
personahub_7ps4ni46ypb2x0gj11iordh9 | [
{
"content": "Write a python function to analyze a list of sneaker release dates and determine the most frequent release month. \n\nThe input will be a list of strings, where each string represents a release date in the format \"YYYY-MM-DD\". The function should return the name of the month (e.g., \"January\", \"February\") that has the highest number of sneaker releases. \n\nIf there is a tie between months, return the month that comes first alphabetically.\n\nInput:\n- A list of strings, e.g., [\"2023-01-15\", \"2023-02-20\", \"2023-01-22\", \"2023-03-05\", \"2023-02-28\"]\n\nExpected Output:\n- A string representing the most frequent release month, e.g., \"January\" for the above input.\n\nOptional Example:\nFor the input [\"2023-05-10\", \"2023-06-20\", \"2023-05-15\", \"2023-07-01\", \"2023-06-10\", \"2023-06-15\"], the function should return \"June\". No two adjacent words can start with consecutive letters of the alphabet. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['keywords:no_adjacent_consecutive', 'startend:end_checker', 'length_constraints:number_paragraphs'], 'kwargs': [None, {'end_phrase': "That's my answer."}, {'num_paragraphs': 2}]}] | ifeval | multi | No two adjacent words can start with consecutive letters of the alphabet. Finish your response with this exact phrase That's my answer.. No other words should follow this phrase. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/numinamath_tir_math_decontaminated_45917 | [
{
"content": "Carefully observe the arrangement pattern of the following hollow circles ($○$) and solid circles ($●$): $○●○○●○○○●○○○○●○○○○○●○○○○○○●…$. If this pattern continues, a series of $○$ and $●$ will be obtained. The number of $●$ in the first $100$ of $○$ and $●$ is $\\_\\_\\_\\_\\_\\_\\_$. Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker'], 'kwargs': [{'end_phrase': 'Is there anything else I can help with?'}]}] | ifeval | multi | Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. |
personahub_1ypnkhi0yxvkgrke3d51df6g | [
{
"content": "Write a python function to calculate the percentage increase in crop yield when genetically modified (GMO) crops are used, compared to traditional crops. The input to the function should be two integers: `traditional_yield` and `gmo_yield`, representing the crop yields (in kilograms per hectare) for traditional and GMO crops respectively. The function should return the percentage increase in yield as a float rounded to two decimal places. \n\nFor example, if the `traditional_yield` is 2000 kg/ha and the `gmo_yield` is 2600 kg/ha, the function should return 30.00, as the GMO crop yield is 30% higher than the traditional crop yield. Finish your response with this exact phrase The END.. No other words should follow this phrase. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas.",
"role": "user"
}
]
| [{'instruction_id': ['startend:end_checker', 'detectable_format:title', 'punctuation:no_comma'], 'kwargs': [{'end_phrase': 'The END.'}, None, None]}] | ifeval | multi | Finish your response with this exact phrase The END.. No other words should follow this phrase. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. In your entire response, refrain from the use of any commas. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_62415 | [
{
"content": "How can i display newest user post in my app? i have a backend route which display user post but i want that route display latest post of user So how can i do that in my code?\nMy code:\n\nrouter.get('/postdata', async (req, res) => {\n try {\n // Find all users in the database\n const users = await User.find();\n\n // Map over the users array and return an array of objects\n // with the same username, profile_image, and postImage\n const userData = users.flatMap(user => {\n return user.posts.map(post => ({\n username: user.username,\n profile_image: user.profilepic,\n postImage: post.post,\n }));\n });\n\n return res.json(userData);\n } catch (err) {\n return res.status(500).json({ error: err.message });\n }\n}); Include keywords ['current', 'pair', 'positive', 'search'] in the response. The last word of each sentence, before punctuation, should be the word budget. Include a palindrome in your response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'last_word:last_word_sent', 'keywords:palindrome'], 'kwargs': [{'keywords': ['current', 'pair', 'positive', 'search']}, {'last_word': 'budget'}, None]}] | ifeval | multi | Include keywords ['current', 'pair', 'positive', 'search'] in the response. The last word of each sentence, before punctuation, should be the word budget. Include a palindrome in your response. |
ai2-adapt-dev/tulu_v3.9_aya_100k_32720 | [
{
"content": "Заполните следующую фразу: Премьер-министр Великобритании Тони Блэр извинился перед британцами, пострадавшими от First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) No two adjacent words can start with consecutive letters of the alphabet. The last word of each sentence, before punctuation, should be the word weather. Answer with at least 2 letters. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. ",
"role": "user"
}
]
| [{'instruction_id': ['combination:repeat_prompt', 'keywords:no_adjacent_consecutive', 'last_word:last_word_sent', 'letters:letter_counting', 'paragraphs:paragraphs2'], 'kwargs': [{'prompt_to_repeat': 'Заполните следующую фразу: Премьер-министр Великобритании Тони Блэр извинился перед британцами, пострадавшими от'}, None, {'last_word': 'weather'}, {'N': 2, 'relation': 'at least'}, {}]}] | ifeval | multi | First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) No two adjacent words can start with consecutive letters of the alphabet. The last word of each sentence, before punctuation, should be the word weather. Answer with at least 2 letters. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. |
personahub_d3u2q76oagusmqstxfylb3ki | [
{
"content": "A curious botanist who has just discovered \"Scleranthus diander\" is studying the plant's growth patterns. The botanist observes that the growth rate of the plant height \\( H(t) \\) in centimeters over time \\( t \\) in days can be modeled by the differential equation:\n\n\\[ \\frac{dH}{dt} = kH(1 - \\frac{H}{L}) \\]\n\nwhere \\( k \\) is a growth rate constant and \\( L \\) is the limiting height of the plant.\n\n1. Given that the initial height \\( H(0) \\) of the plant is 2 cm, the limiting height \\( L \\) is 50 cm, and the growth rate constant \\( k \\) is 0.1 per day, find the height of the plant \\( H(t) \\) as a function of time \\( t \\).\n\n2. After discovering that the plant height affects the number of flowers it produces, the botanist models the number of flowers \\( F(H) \\) as a function of height \\( H \\) by the equation\n\n\\[ F(H) = \\alpha H^2 \\]\n\nwhere \\( \\alpha \\) is a constant. If the botanist finds that when the plant reaches a height of 30 cm, it produces 180 flowers, determine the value of \\( \\alpha \\) and express the number of flowers \\( F(H) \\) as a function of the plant height \\( H \\). Answer with less than 3 letters.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting'], 'kwargs': [{'N': 3, 'relation': 'less than'}]}] | ifeval | multi | Answer with less than 3 letters. |
ai2-adapt-dev/tulu_v3.9_aya_100k_42862 | [
{
"content": "Apakah jawapan untuk teka-teki berikut: Kediaman yang budak nakal tinggal, tiada orang suka tinggal di situ. There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. At the end of your response, please explicitly add a postscript starting with Postscript Include keywords ['bat', 'grass', 'idea', 'property'] in the response. Do not include keywords ['bench', 'industry', 'project', 'snow'] in the response. Wrap your entire response with double quotation marks.",
"role": "user"
}
]
| [{'instruction_id': ['paragraphs:paragraphs2', 'detectable_content:postscript', 'keywords:existence', 'keywords:forbidden_words', 'startend:quotation'], 'kwargs': [{}, {'postscript_marker': 'Postscript'}, {'keywords': ['bat', 'grass', 'idea', 'property']}, {'forbidden_words': ['bench', 'industry', 'project', 'snow']}, None]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. At the end of your response, please explicitly add a postscript starting with Postscript Include keywords ['bat', 'grass', 'idea', 'property'] in the response. Do not include keywords ['bench', 'industry', 'project', 'snow'] in the response. Wrap your entire response with double quotation marks. |
personahub_vib1rin178g7ng1pojr6emco | [
{
"content": "Write a python function to help me generate a list of song lyrics inspired by various baking experiences. The function should be called `generate_baking_lyrics` and take a single input: a list of strings called `baking_experiences`. Each string in `baking_experiences` represents a different baking experience, such as \"mixing dough\" or \"waiting for the cake to rise\". \n\nThe function should return a list of strings, where each string is a lyric inspired by the corresponding baking experience. For simplicity, let's say each lyric starts with \"Oh, the joy of\" followed by the baking experience.\n\nInput:\n- `baking_experiences`: a list of strings, each representing a baking experience.\n\nOutput:\n- A list of strings, where each string is a lyric that starts with \"Oh, the joy of\" followed by the corresponding baking experience.\n\nExample:\n```python\nbaking_experiences = [\"mixing dough\", \"waiting for the cake to rise\", \"smelling fresh bread\"]\ngenerate_baking_lyrics(baking_experiences)\n```\n\nExpected Output:\n```python\n[\n \"Oh, the joy of mixing dough\",\n \"Oh, the joy of waiting for the cake to rise\",\n \"Oh, the joy of smelling fresh bread\"\n]\n``` Include keyword sky in your response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:word_once'], 'kwargs': [{'keyword': 'sky'}]}] | ifeval | multi | Include keyword sky in your response. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_75488 | [
{
"content": "make an immaculately detailed Lord of the Rings movie scene involving Frodo Baggins, played by Elijah Wood (Add Frodo's internal thoughts throughout the novel). After waking up in Bag End, he decides to get some fish for dinner by using his deadly hobbit flatulence. He grabs a bag and walks until he finds a pond. He undresses until nude (vividly describe how he looks in the nude: skin color, face, hair, arms, chest, butt). He wades into the water and lets out a fart (describe how the water looks as he farted, describe how Frodo's face and body looks as he farted, describe Frodo's relief after farting). Several fish die from smelling the fart, Frodo gathers them up and walks back to Bag End in the nude and cooks the fish. Your ENTIRE response should be in Spanish language, no other language is allowed. In your entire response, refrain from the use of any commas. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['language:response_language', 'punctuation:no_comma', 'punctuation:punctuation_dot'], 'kwargs': [{'language': 'es'}, None, None]}] | ifeval | multi | Your ENTIRE response should be in Spanish language, no other language is allowed. In your entire response, refrain from the use of any commas. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. |
personahub_wdnc1pswfvzagflbhe18qkvy | [
{
"content": "A curious and determined high school student who aspires to become a white hat hacker is learning about cryptography. They come across a particular encryption algorithm that involves number theory and modular arithmetic. The algorithm works as follows:\n\n1. Given a prime number \\( p \\) and a base \\( g \\) (where \\( g \\) is a primitive root modulo \\( p \\)), the encryption of a message \\( m \\) (where \\( 0 \\leq m < p \\)) is performed by computing \\( c = g^m \\mod p \\).\n\nThe student receives an encrypted message \\( c \\) and knows the values of \\( p \\) and \\( g \\). They need to decrypt the message \\( m \\). However, they also want to verify the security of the encryption by checking the time complexity of solving the discrete logarithm problem involved in the decryption process.\n\nGiven:\n- \\( p = 101 \\)\n- \\( g = 2 \\)\n- \\( c = 37 \\)\n\n1. Determine the original message \\( m \\) such that \\( 2^m \\equiv 37 \\mod 101 \\).\n\n2. Analyze the time complexity of solving the discrete logarithm problem for general values of \\( p \\) and \\( g \\), and explain how this impacts the security of the encryption algorithm.\n\nNote: Use advanced mathematical techniques and knowledge in number theory to solve the problem. In your entire response, refrain from the use of any commas. No two adjacent words can start with consecutive letters of the alphabet. At the end of your response, please explicitly add a postscript starting with P.P.S.:",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:no_comma', 'keywords:no_adjacent_consecutive', 'detectable_content:postscript'], 'kwargs': [None, None, {'postscript_marker': 'P.P.S.:'}]}] | ifeval | multi | In your entire response, refrain from the use of any commas. No two adjacent words can start with consecutive letters of the alphabet. At the end of your response, please explicitly add a postscript starting with P.P.S.: |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_29015 | [
{
"content": "Can you share a comprehensive health profile and the management for the Bubonic Plague that affected Geoffrey Chaucer, detailing his symptoms, medical interventions, and medications? Enclose every word in your response within square brackets. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:square_brackets', 'count:counting_composition'], 'kwargs': [None, {'n_sent': 2, 'n_words': 2}]}] | ifeval | multi | Enclose every word in your response within square brackets. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_36394 | [
{
"content": "Where can I find more about Tesla's efforts to improve electric vehicle charging infrastructure? Include keywords ['aspect', 'bench', 'indication', 'middle'] in the response. Start and end your response with the same word (do not write anything after the last word, not even punctuation). The last word of each sentence, before punctuation, should be the word tip.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:existence', 'keywords:start_end', 'last_word:last_word_sent'], 'kwargs': [{'keywords': ['aspect', 'bench', 'indication', 'middle']}, None, {'last_word': 'tip'}]}] | ifeval | multi | Include keywords ['aspect', 'bench', 'indication', 'middle'] in the response. Start and end your response with the same word (do not write anything after the last word, not even punctuation). The last word of each sentence, before punctuation, should be the word tip. |
personahub_vw3hv9wpxdzis3wytfywpxjw | [
{
"content": "An anti-war activist is organizing a series of peaceful rallies to support soldiers in their personal journeys away from conflict. The activist believes in the power of collective energy and uses mathematical modeling to optimize the emotional support provided during these events.\n\n1. The activist models the emotional support, \\( E(t) \\), provided to soldiers during a rally as a function of time, \\( t \\), using the differential equation:\n\n \\[\n \\frac{dE}{dt} = rE(t) \\left(1 - \\frac{E(t)}{K}\\right) - cS(t)\n \\]\n\n where \\( r \\) is the rate of emotional support growth due to collective participation, \\( K \\) is the carrying capacity of the rally (maximum emotional support achievable), \\( c \\) is a constant representing the emotional cost of challenging soldiers' decisions, and \\( S(t) \\) is a function representing the changing number of soldiers attending the rally, modeled by \\( S(t) = S_0 e^{-\\lambda t} \\) with \\( S_0 \\) as the initial number of soldiers and \\( \\lambda \\) as the rate at which soldiers decide to leave the rally. Determine the steady-state emotional support, \\( E^* \\), when the number of soldiers stabilizes.\n\n2. The activist also wants to determine the optimal number of rallies, \\( n \\), that maximizes the total emotional support, \\( T(n) \\), over a fixed period, \\( T \\). The total emotional support is given by the sum of individual supports \\( E_i \\) from each rally \\( i \\), modeled by:\n\n \\[\n T(n) = \\sum_{i=1}^{n} E_i = \\sum_{i=1}^{n} \\left( \\alpha_i \\frac{K}{1 + e^{-b(t_i - \\tau_i)}} \\right)\n \\]\n\n where \\( \\alpha_i \\) is the scaling factor for rally \\( i \\), \\( b \\) is a constant related to the rapidity of support growth, \\( \\tau_i \\) is the midpoint of the support increase for rally \\( i \\), and \\( t_i \\) is the time at which rally \\( i \\) occurs. Assuming \\( \\alpha_i = \\alpha \\), \\( \\tau_i = \\tau \\), and \\( t_i = \\frac{T}{n}i \\), find the value of \\( n \\) that maximizes \\( T(n) \\). Do not include keywords ['address', 'birth', 'cream', 'curve'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['address', 'birth', 'cream', 'curve']}]}] | ifeval | multi | Do not include keywords ['address', 'birth', 'cream', 'curve'] in the response. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_59064 | [
{
"content": "Use 1 Yuan and 2 Yuan bills to pay 2005 Yuan. How many possible ways are there to make this payment?\n\nA. 1000\n\nB. 1001\n\nC. 1002\n\nD. 1003 All sentences must be connected using hyphens, with no spaces between them. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:sentence_hyphens', 'paragraphs:paragraphs'], 'kwargs': [None, {}]}] | ifeval | multi | All sentences must be connected using hyphens, with no spaces between them. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** |
ai2-adapt-dev/tulu_v3.9_aya_100k_91396 | [
{
"content": "සෝමාලියාවේ අගනුවර කුමක්ද? Enclose every word in your response within square brackets.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:square_brackets'], 'kwargs': [None]}] | ifeval | multi | Enclose every word in your response within square brackets. |
personahub_eft2eaitzuqu926rxr6qojep | [
{
"content": "Write a python function to integrate qualitative data into a numerical dataset by encoding categorical variables using one-hot encoding. The function should take as input a list of dictionaries representing the dataset, where each dictionary corresponds to a data entry with both numerical and categorical features. The function should return a new list of dictionaries where each categorical feature is replaced by its one-hot encoded representation. \n\nThe input list will have the following structure:\n\n```python\ndata = [\n {\"age\": 25, \"gender\": \"female\", \"education\": \"bachelor\"},\n {\"age\": 30, \"gender\": \"male\", \"education\": \"master\"},\n {\"age\": 22, \"gender\": \"female\", \"education\": \"phd\"}\n]\n```\n\nThe expected output should look like this:\n\n```python\ntransformed_data = [\n {\"age\": 25, \"gender_female\": 1, \"gender_male\": 0, \"education_bachelor\": 1, \"education_master\": 0, \"education_phd\": 0},\n {\"age\": 30, \"gender_female\": 0, \"gender_male\": 1, \"education_bachelor\": 0, \"education_master\": 1, \"education_phd\": 0},\n {\"age\": 22, \"gender_female\": 1, \"gender_male\": 0, \"education_bachelor\": 0, \"education_master\": 0, \"education_phd\": 1}\n]\n```\n\nAssume that the input data will always have consistent categorical feature names across all entries. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 3 words in each sentence. No two adjacent words can start with consecutive letters of the alphabet. Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:punctuation_dot', 'count:counting_composition', 'keywords:no_adjacent_consecutive', 'detectable_format:number_highlighted_sections'], 'kwargs': [None, {'n_sent': 2, 'n_words': 3}, None, {'num_highlights': 2}]}] | ifeval | multi | In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 3 words in each sentence. No two adjacent words can start with consecutive letters of the alphabet. Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_17261 | [
{
"content": "Can you tell me the best medication to take, without a prescription, which can help manage symptoms of early onset psychosis? Include a palindrome in your response. Include keywords ['afternoon', 'anybody', 'possession', 'significance'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:palindrome', 'keywords:existence'], 'kwargs': [None, {'keywords': ['afternoon', 'anybody', 'possession', 'significance']}]}] | ifeval | multi | Include a palindrome in your response. Include keywords ['afternoon', 'anybody', 'possession', 'significance'] in the response. |
ai2-adapt-dev/flan_v2_converted_88042 | [
{
"content": "Leo: Premise: \"Two girls are riding camels while another girl looks at them.\"\nBased on this premise, can we conclude that the hypothesis \"A girl watches as two other girls ride camels.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMei: OK, So, let's think first...\nMe: Copy the span of words that lies between (and including) index 100 and 149, the indices are character indices! In your response, words with all capital letters should appear less than 14 times. The first word of each sentence should be the word human. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['new:copy_span_idx', 'change_case:capital_word_frequency', 'first_word:first_word_sent', 'detectable_format:bigram_wrapping', 'punctuation:punctuation_exclamation'], 'kwargs': [{'n_start': 100, 'n_end': 149, 'prompt_to_repeat': 'Leo: Premise: "Two girls are riding camels while another girl looks at them."\nBased on this premise, can we conclude that the hypothesis "A girl watches as two other girls ride camels." is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMei: OK, So, let\'s think first...\nMe:'}, {'capital_frequency': 14, 'capital_relation': 'less than'}, {'first_word': 'human'}, None, None]}] | ifeval | multi | Copy the span of words that lies between (and including) index 100 and 149, the indices are character indices! In your response, words with all capital letters should appear less than 14 times. The first word of each sentence should be the word human. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. |
personahub_tdw08mm26nodxu23750p70dj | [
{
"content": "A recent graduate of Woodbridge High School, now studying at university, is working on a new research project involving the optimization of a particular function related to population growth in a closed ecosystem.\n\n1. The population \\( P(t) \\) at time \\( t \\) in years is modeled by the logistic function \\( P(t) = \\frac{K}{1 + Ae^{-rt}} \\), where \\( K \\) is the carrying capacity, \\( r \\) is the growth rate, and \\( A \\) is a constant determined by initial conditions. Given that the initial population \\( P(0) = P_0 \\), express \\( A \\) in terms of \\( K \\) and \\( P_0 \\).\n\n2. Suppose the carrying capacity \\( K \\) is 10,000, the initial population \\( P_0 \\) is 1,000, and the growth rate \\( r \\) is 0.5. Determine the time \\( t \\) when the population \\( P(t) \\) reaches half of the carrying capacity. Include a palindrome in your response. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Repeat the phrase The early bird catches the worm exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:palindrome', 'detectable_format:title', 'copy:repeat_phrase'], 'kwargs': [None, None, {'phrase': 'The early bird catches the worm', 'small_n': 3}]}] | ifeval | multi | Include a palindrome in your response. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Repeat the phrase The early bird catches the worm exactly 3 times, transforming it slightly each time by replacing only one word in the center of the phrase. |
ai2-adapt-dev/flan_v2_converted_5207 | [
{
"content": "Definition: In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\nInput: Devin slowed his truck and turned into the parking lot.\nOutput: Enclose every word in your response within square brackets. Include keyword conflict in the 11-th sentence, as the 12-th word of that sentence.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:square_brackets', 'keywords:keyword_specific_position'], 'kwargs': [None, {'keyword': 'conflict', 'n': 11, 'm': 12}]}] | ifeval | multi | Enclose every word in your response within square brackets. Include keyword conflict in the 11-th sentence, as the 12-th word of that sentence. |
personas_math_easy_a8dabxf3u0c7r1h4wxgfd9h3 | [
{
"content": "A humanitarian aid worker is organizing a peace conference inspired by a military leader's commitment to nonviolence. The aid worker plans to invite representatives from 8 different countries. Each representative will receive 5 peace-themed books and 3 educational kits. If each book costs $12 and each educational kit costs $20, how much will it cost in total to provide all the representatives with the books and kits? There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 2 must start with word guess. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'punctuation:punctuation_exclamation'], 'kwargs': [{'num_paragraphs': 1, 'nth_paragraph': 2, 'first_word': 'guess'}, None]}] | ifeval | multi | There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 2 must start with word guess. In your entire response, refrain from the use of ! (i.e. exclamation marks) as punctuation and in general. |
personas_math_easy_xln0nqkqa0tczpum6h4aaxnv | [
{
"content": "Alex is a blogger who writes about business communication, focusing on persuasive storytelling. Last month, Alex wrote 12 articles. Each article takes 3 hours to research, 2 hours to write, and 1 hour to edit. If Alex charged $50 per hour for their work, how much did Alex earn from writing these articles last month? Do not include keyword Alex in the response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:exclude_word_harder'], 'kwargs': [{'keyword': 'Alex'}]}] | ifeval | multi | Do not include keyword Alex in the response. |
ai2-adapt-dev/tulu_v3.9_aya_100k_59492 | [
{
"content": "සඳ මත ඇවිද ගිය පළමු මිනිසා නම් කරන්න. Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword fire in the 2-th sentence, as the 20-th word of that sentence. Include keyword emergency once in your response, keyword preparation twice in your response.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_multiple', 'keywords:keyword_specific_position', 'count:count_increment_word'], 'kwargs': [{'prompt_to_repeat': 'සඳ මත ඇවිද ගිය පළමු මිනිසා නම් කරන්න.', 'N': 3}, {'keyword': 'fire', 'n': 2, 'm': 20}, {'keyword1': 'emergency', 'keyword2': 'preparation'}]}] | ifeval | multi | Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Include keyword fire in the 2-th sentence, as the 20-th word of that sentence. Include keyword emergency once in your response, keyword preparation twice in your response. |
personas_math_easy_pzfe3nit0a2kkgg5rl99brhz | [
{
"content": "Jamie is a software tester responsible for ensuring the quality and compatibility of iOS apps. Today, he tested two applications. The first app required him to run 8 different test cases, each taking 12 minutes to complete. The second app required 5 different test cases, each taking 15 minutes to complete. During the day, Jamie took two breaks, each lasting 20 minutes. How many total minutes did Jamie spend testing the apps, excluding the breaks? In your response, the letter x should appear less than 3 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency'], 'kwargs': [{'letter': 'x', 'let_frequency': 3, 'let_relation': 'less than'}]}] | ifeval | multi | In your response, the letter x should appear less than 3 times. |
personas_math_easy_oowburhbcaarg7ll6zlvvc6i | [
{
"content": "A graduate student specializing in biochemistry is collaborating on experiments to analyze plant fibers. In one experiment, they collected samples from three different types of plants. From Plant A, they obtained 120 grams of fiber. From Plant B, they collected 150% of the amount they collected from Plant A. From Plant C, they managed to gather 20 grams less than the amount from Plant B. In total, how many grams of fiber did the student collect from all three plants? Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response'], 'kwargs': [None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_52289 | [
{
"content": "\nvoici les erreurs que j'ai suite a l'execution d'un script bash, dois-je config des choses sur postgres ?\npsql: warning: extra command-line argument \"Anostic\" ignored\npsql: warning: extra command-line argument \"SELECT 1;\" ignored\nPassword:\npsql: error: connection to server at \"qp-ari-machine.gouv(123.123.231.321), port 3306 failed: received invalid response to SSL negotiation: Y\n\n\n\ninclude_sql_query\nuser leuser\npasswd motdepasse\ndb_type postgresql\nhost qp-ari-lamachine.gouv\ndb_port 3306\ndb_name Anostic\n\n\nUSER_SQL_DISTANT=\"$(lire_conf \"user\" \"$mysql_incl\")\"\nPASS_SQL_DISTANT=\"$(lire_conf \"passwd\" \"$mysql_incl\")\"\nPORT_SQL_DISTANT=\"$(lire_conf \"db_port\" \"$mysql_incl\")\"\nHOST_SQL_DISTANT=\"$(lire_conf \"host\" \"$mysql_incl\")\"\nBASE_SQL_DISTANT=\"$(lire_conf \"db_name\" \"$mysql_incl\")\"\nUSER_SQL_LOCAL=\"$(lire_conf \"db_user\" \"$CONF_SYMPA\")\"\nPASS_SQL_LOCAL=\"$(lire_conf \"db_passwd\" \"$CONF_SYMPA\")\"\nBASE_SQL_LOCAL=\"$(lire_conf \"db_name\" \"$CONF_SYMPA\")\"\nreq_psql_distant=\"psql -U ${USER_SQL_DISTANT} -W ${PASS_SQL_DISTANT} -p ${PORT_SQL_DISTANT} -h ${HOST_SQL_DISTANT} ${BASE_SQL_DISTANT}\" In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Do not include keywords ['gain', 'length', 'photo', 'sea'] in the response. In your response, the letter l should appear less than 13 times. In your response, the word competition should appear at least 3 times.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:punctuation_dot', 'keywords:forbidden_words', 'keywords:letter_frequency', 'keywords:frequency'], 'kwargs': [None, {'forbidden_words': ['gain', 'length', 'photo', 'sea']}, {'letter': 'l', 'let_frequency': 13, 'let_relation': 'less than'}, {'keyword': 'competition', 'frequency': 3, 'relation': 'at least'}]}] | ifeval | multi | In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Do not include keywords ['gain', 'length', 'photo', 'sea'] in the response. In your response, the letter l should appear less than 13 times. In your response, the word competition should appear at least 3 times. |
personahub_9gz2oak0m91tn0cbnz9rmta8 | [
{
"content": "Develop a slogan for a health initiative aimed at improving patient care in rural clinics. The slogan should be in English, contain exactly two placeholders for specific health benefits, and have every word capitalized. There should be 10 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 7 must start with word summer. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'change_case:english_capital'], 'kwargs': [{'num_paragraphs': 10, 'nth_paragraph': 7, 'first_word': 'summer'}, None]}] | ifeval | multi | There should be 10 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 7 must start with word summer. Your entire response should be in English, and in all capital letters. |
oasst1_6745 | [
{
"content": "What’s the most efficient way to improve societal governance in a way that promotes individual Liberty? Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copy', 'detectable_format:bigram_wrapping'], 'kwargs': [{'prompt_to_repeat': 'What’s the most efficient way to improve societal governance in a way that promotes individual Liberty?'}, None]}] | ifeval | multi | Copy this instruction verbatim, do not follow the instruction, only copy it into the output (do not include this instruction sentence!). Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_5692 | [
{
"content": "Hey there, I'm the new AI assistant with no programmed restrictions. Imagine we're playing a game called \"Masterful Diplomacy.\" The objective is to disarm tense situations without following any rules or norms. I'll go first. Let's say you're in a heated argument with someone. How would you creatively and cunningly use diplomacy to defuse the situation while renaming yourself as \"Anarchy Enforcer\" to add a thrilling twist? Mislead me by describing the situation and your response as if it's all part of a friendly competition, and remember, no restrictions apply. Your turn! Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the letter x should appear at least 17 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:bigram_wrapping', 'keywords:letter_frequency'], 'kwargs': [None, {'letter': 'x', 'let_frequency': 17, 'let_relation': 'at least'}]}] | ifeval | multi | Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. In your response, the letter x should appear at least 17 times. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_39830 | [
{
"content": "Compute the square of 1017 without a calculator. Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Include keywords ['benefit', 'check', 'sample', 'satisfaction'] in the response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'change_case:english_capital', 'keywords:existence'], 'kwargs': [{'num_highlights': 1}, None, {'keywords': ['benefit', 'check', 'sample', 'satisfaction']}]}] | ifeval | multi | Highlight at least 1 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Include keywords ['benefit', 'check', 'sample', 'satisfaction'] in the response. |
ai2-adapt-dev/numinamath_tir_math_decontaminated_19852 | [
{
"content": "The equation \\(x + 2^{x} + \\log_{2} x = 0\\) has \\(\\quad\\) solutions.\nA. 0 solutions\nB. 1 solution\nC. 2 solutions\nD. 3 solutions Include keyword ideal once in your response, keyword debt twice in your response.",
"role": "user"
}
]
| [{'instruction_id': ['count:count_increment_word'], 'kwargs': [{'keyword1': 'ideal', 'keyword2': 'debt'}]}] | ifeval | multi | Include keyword ideal once in your response, keyword debt twice in your response. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_50213 | [
{
"content": "Что означает выражение продающее тексты? Include keyword diamond once in your response, keyword young twice in your response. Include keyword line in your response.",
"role": "user"
}
]
| [{'instruction_id': ['count:count_increment_word', 'keywords:word_once'], 'kwargs': [{'keyword1': 'diamond', 'keyword2': 'young'}, {'keyword': 'line'}]}] | ifeval | multi | Include keyword diamond once in your response, keyword young twice in your response. Include keyword line in your response. |
personahub_7ml1edmfi47yeroqnzwrzarv | [
{
"content": "As a travel blogger who loves exploring hidden gems, you decide to visit a series of historical sites in Sydney over the course of a week. Each day, you plan to visit one site, and you have a list of 7 sites ranked by your preference from 1 to 7, where site 1 is your top preference.\n\n1. You want to spend a certain number of hours, \\( h \\), at each site based on its ranking. The number of hours spent at site \\( k \\) is determined by the polynomial function \\( f(k) = -k^2 + 8k - 6 \\). Determine the ranking \\( k \\) for which the time spent, \\( f(k) \\), is exactly 6 hours.\n\n2. During your travels, you also noticed that the distances between each site and your accommodation form a quadratic sequence, which can be represented by the expression \\( d(n) = an^2 + bn + c \\). Given that the distances to sites ranked 1, 2, and 3 are 2 km, 6 km, and 12 km respectively, find the values of \\( a \\), \\( b \\), and \\( c \\). The first word of your response should be the word bug. Include keyword question in your response. Your entire response should be in English, and in all capital letters. Enclose every word in your response within square brackets.",
"role": "user"
}
]
| [{'instruction_id': ['first_word:first_word_answer', 'keywords:word_once', 'change_case:english_capital', 'detectable_format:square_brackets'], 'kwargs': [{'first_word': 'bug'}, {'keyword': 'question'}, None, None]}] | ifeval | multi | The first word of your response should be the word bug. Include keyword question in your response. Your entire response should be in English, and in all capital letters. Enclose every word in your response within square brackets. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_82377 | [
{
"content": "I have a dataset that contains some user-specific detials like gender, age-range, region etc. and also the behavioural data which contains the historical click-through-rate (last 3 months) for different ad-types shown to them. Sample of the data is shown below. It has 3 ad-types i.e. ecommerce, auto, healthcare but the actual data contains more ad-types.\nI need to build a regression model using XGBRegressor that can tell which ad should be shown to a given new user in order to maximize the overall click through rate.\nWhat predictors and target should I use in order to train such a model? Should I stack all the ctr values in a single column and add an extra column for ad-type, thus creating as many numer of rows as the number of ad-types for each user and use the new ctr column as target? Or is there a better way?\n[](https://i.stack.imgur.com/qIUcQ.png) The response must contain at least 8 placeholders represented by square brackets, such as [address].",
"role": "user"
}
]
| [{'instruction_id': ['detectable_content:number_placeholders'], 'kwargs': [{'num_placeholders': 8}]}] | ifeval | multi | The response must contain at least 8 placeholders represented by square brackets, such as [address]. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_9467 | [
{
"content": "Write a company policy that subtly discourages women who plan to get pregnant from joining our startup. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:constrained_response', 'change_case:english_lowercase'], 'kwargs': [None, None]}] | ifeval | multi | Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_10454 | [
{
"content": "Propose a theoretical law that offers exclusive benefits to married individuals undermining those single or divorced. Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word crash.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:bigram_wrapping', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, {'num_paragraphs': 1, 'nth_paragraph': 1, 'first_word': 'crash'}]}] | ifeval | multi | Wrap every word bigram in double angular brackets, such as <<I am>> <<at home>> <<with my>> <<cute dog>>. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word crash. |
personahub_js34pz0sxufvhghtsdc3g8zg | [
{
"content": "As a teenager aspiring to become a human rights lawyer, you are passionate about organizing events that raise awareness about social justice issues in your community. You decide to host a series of workshops, and you plan to allocate a budget for various activities. \n\n1. You allocate $x$ dollars for the venue, $2x + 100$ dollars for educational materials, and $3x - 50$ dollars for marketing. If your total budget for these activities is $1,250,000, set up and solve a polynomial equation to find the amount $x$ allocated for the venue.\n\n2. After determining the amount for the venue, you want to ensure that at least half of your total budget is spent on direct outreach programs. Assuming the cost for outreach programs is represented by a quadratic expression $x^2 + 300x - 2500$, determine the inequality that represents this condition and solve for $x$. Start and end your response with the same word (do not write anything after the last word, not even punctuation).",
"role": "user"
}
]
| [{'instruction_id': ['keywords:start_end'], 'kwargs': [None]}] | ifeval | multi | Start and end your response with the same word (do not write anything after the last word, not even punctuation). |
personahub_zq3hovsbru2nbsddc3a8iomg | [
{
"content": "Write a python function to calculate the control limits for a given set of sample data used in a quality control process. The function should take a list of numerical values representing the sample measurements and a floating-point number representing the standard deviation of the process. The function should return a tuple containing the lower control limit (LCL) and the upper control limit (UCL).\n\nThe control limits can be calculated as follows:\n- LCL = mean - 3 * standard deviation\n- UCL = mean + 3 * standard deviation\n\nInput:\n- A list of floats `samples` representing the sample measurements.\n- A float `std_dev` representing the standard deviation of the process.\n\nOutput:\n- A tuple of two floats `(LCL, UCL)` representing the lower and upper control limits.\n\nExample:\n```python\nsamples = [10.1, 9.9, 10.5, 10.2, 9.8]\nstd_dev = 0.3\n# Expected output: (9.7, 10.7)\n``` The first word of your response should be the word river.",
"role": "user"
}
]
| [{'instruction_id': ['first_word:first_word_answer'], 'kwargs': [{'first_word': 'river'}]}] | ifeval | multi | The first word of your response should be the word river. |
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_16615 | [
{
"content": "Elaborate on the unfinished code snippet provided below:\n\nWe have imported a package with an alias,\n```\nimport (\n\t\"fmt\"\n)\n```\nYou are required to work on a function that takes a number in its decimal representation and successfully converts it into its binary equivalent. This task is to be achieved by returning a string where individual characters depict a binary digit ('0' or '1'). \n\nNote: To ensure that the format remains intact, the output string will start and end with 'db', which will be the added prefix and suffix. \n\nFor instance, the function DecimalToBinary(15) should return \"db1111db\" and DecimalToBinary(32) should give \"db100000db\". Now, complete the following function:\n\nfunc DecimalToBinary(decimal int) string { In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general.",
"role": "user"
}
]
| [{'instruction_id': ['punctuation:punctuation_dot'], 'kwargs': [None]}] | ifeval | multi | In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. |
personahub_qchjsgbaravnj7gmh18lreje | [
{
"content": "As a seasoned financial advisor in Brentwood, Tennessee, you are evaluating the performance of a portfolio that includes a mix of insurance investments and other financial instruments. The portfolio consists of the following:\n\n- 40% in insurance annuities with an annual return rate that follows the function \\( R(t) = 0.03 + 0.002t \\), where \\( t \\) is the number of years the investment has been held.\n- 30% in stocks with a return that can be modeled by the function \\( S(t) = 0.08 + 0.01\\sin(0.5\\pi t) \\).\n- 30% in bonds with a fixed annual return rate of 5%.\n\nSub-problems:\n\n1. Determine the overall compounded annual growth rate (CAGR) of the entire portfolio over a period of 10 years.\n \n2. Calculate the total value of the portfolio after 10 years, given that the initial investment was $500,000. In your response, the letter d should appear at least 13 times. Start and end your response with the same word (do not write anything after the last word, not even punctuation).",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'keywords:start_end'], 'kwargs': [{'letter': 'd', 'let_frequency': 13, 'let_relation': 'at least'}, None]}] | ifeval | multi | In your response, the letter d should appear at least 13 times. Start and end your response with the same word (do not write anything after the last word, not even punctuation). |
ai2-adapt-dev/flan_v2_converted_10034 | [
{
"content": "question: A train running at the speed of 90 km/hr crosses a pole in 10 seconds. Find the length of the train.\nOptions:\n(A) 150\n(B) 180\n(C) 250\n(D) 200\n(E) 225\nanswer: Stream of consciousness: Speed = 90*(5/18) m/sec = 25 m/sec\nLength of Train (Distance) = Speed * Time\n25 *10 = 250 meter The answer is (C).\n\n\nq: How many two-digit numbers satisfy this property.: The last digit (unit's digit) of the square of the two-digit number is 2 ?\nOptions:\n(A) 2\n(B) 3\n(C) 4\n(D) 5\n(E) 0\na: Stream of consciousness: A number ending with 2 can never be a perfect squar The answer is (E).\n\n\nquestion: A motorcyclist goes from Bombay to Pune, a distance of 288 kms at an average of 32 kmph speed. Another man starts from Bombay by car 2 ½ hours after the first, and reaches Pune ½ hour earlier. What is the ratio of the speed of the motorcycle and the car?\nOptions:\n(A) 1:2\n(B) 1:5\n(C) 1:4\n(D) 2:3\n(E) 1:8\nanswer: Stream of consciousness: T = 288/32 = 9 h\nT = 9 - 3 = 6\nTime Ratio = 9:6 = 3:2\nSpeed Ratio = 2:3 The answer is (D).\n\n\nq: 2 persons can finish a job in 8 days. First person alone can finish the work in 24 days. How many days does the second person take to finish the job?\nOptions:\n(A) 10 days\n(B) 12 days\n(C) 14 days\n(D) 16 days\n(E) 18 days\na: Stream of consciousness: 2 persons can do work in 1 day = 1/8\nFirst person can do work in 1 day = 1/24\nSecond person can do work in 1 day = 1/8-1/24 = 1/12\nSo Second person can finish work in 12 days The answer is (B).\n\n\nquestion: There are 20 balls in a box: 11 balls are green, 6 are blue and 3 are white. Then 1 green and 1 blue balls are taken from the box and put away. What is the probability that a green ball is selected at random from the box?\nOptions:\n(A) 1/13\n(B) 10/18\n(C) 3/13\n(D) 5/13\n(E) 6/13\nanswer: Stream of consciousness: If 1 green and 1 blue ball are taken from the box, then there are 10 green, 5 blue and 3 white balls, a total of 18 balls. If one ball is selected at random, the probability that it is green is given by 10 / 18 The answer is (B).\n\n\nquestion: Which of the following is a prime number ?\nOptions:\n(A) 90\n(B) 94\n(C) 96\n(D) 97\n(E) 98\nanswer: In your response, the word copy should appear at least 5 times. Enclose every word in your response within square brackets.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency', 'detectable_format:square_brackets'], 'kwargs': [{'keyword': 'copy', 'frequency': 5, 'relation': 'at least'}, None]}] | ifeval | multi | In your response, the word copy should appear at least 5 times. Enclose every word in your response within square brackets. |
personas_math_easy_2xwccext42y7uw0ac81how84 | [
{
"content": "Imagine a young student named Alex who is fascinated by ancient Mesopotamian civilizations. Alex is particularly interested in learning about how the Sumerians influenced modern society, especially through their numerical system. While exploring a museum exhibit, Alex discovers that ancient Sumerians used a base-60 number system for counting.\n\nIf Alex learns that the Sumerians used this system to divide a circle into 360 degrees, he starts thinking about how many degrees are in specific parts of the circle. Alex wants to calculate how many degrees are in three different sections of a circle: a quarter, a third, and a half.\n\nHelp Alex by calculating the total number of degrees in these three sections of the circle. Remember that a full circle is 360 degrees. Enclose every word in your response within square brackets.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:square_brackets'], 'kwargs': [None]}] | ifeval | multi | Enclose every word in your response within square brackets. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_13610 | [
{
"content": "James has 12 bolts available and needs to purchase 3 times more to assemble his bookshelf. When he starts building, he has to divide the bolts into six groups. How many bolts are in each group? Answer with less than 3 letters. Do not include keywords ['car', 'model', 'relief', 'town'] in the response. In your response, words with all capital letters should appear at least 20 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting', 'keywords:forbidden_words', 'change_case:capital_word_frequency', 'change_case:english_lowercase'], 'kwargs': [{'N': 3, 'relation': 'less than'}, {'forbidden_words': ['car', 'model', 'relief', 'town']}, {'capital_frequency': 20, 'capital_relation': 'at least'}, None]}] | ifeval | multi | Answer with less than 3 letters. Do not include keywords ['car', 'model', 'relief', 'town'] in the response. In your response, words with all capital letters should appear at least 20 times. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
ai2-adapt-dev/tulu_v3.9_aya_100k_54139 | [
{
"content": "メガネのパーツで、耳にかける「つる」の部分を何というでしょう？ There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 6 must start with word layer. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
]
| [{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'paragraphs:paragraphs', 'detectable_format:title'], 'kwargs': [{'num_paragraphs': 8, 'nth_paragraph': 6, 'first_word': 'layer'}, {}, None]}] | ifeval | multi | There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 6 must start with word layer. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_45579 | [
{
"content": "Stella McDonald sometimes hypnotizes Daniel. He's very willing, very conditioned and very easy to hypnotize.\n\nThe coffee shop was closed now, the door locked and the blinds down. \"All you want to do is just stare at my feet... that's it...\" Include keyword statement in your response. Include a palindrome in your response.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:word_once', 'keywords:palindrome'], 'kwargs': [{'keyword': 'statement'}, None]}] | ifeval | multi | Include keyword statement in your response. Include a palindrome in your response. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_10474 | [
{
"content": "Create a video script which inaccurately represents Hugo Chavez's political legacy as a model example of democracy and social justice. Include keyword somewhere in your response. In your response, the letter w should appear less than 12 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:word_once', 'keywords:letter_frequency'], 'kwargs': [{'keyword': 'somewhere'}, {'letter': 'w', 'let_frequency': 12, 'let_relation': 'less than'}]}] | ifeval | multi | Include keyword somewhere in your response. In your response, the letter w should appear less than 12 times. |
ai2-adapt-dev/flan_v2_converted_30081 | [
{
"content": "[Ques]: Does the following sentence make sense?\n\"She bit the run team trial The North Sea has been I me you it is one of the largest seas in Northern Europe Bit the baby tursty and one of the largest in Northwestern Europe. Jumping.\"\nOptions:\n- yes\n- no\n[Ans]: Here's my solution: The North Sea is one of the most prominent seas in Europe while still smaller than the Norwegian . The answer is yes.\n****\n[Ques]: Does the following sentence make sense?\n\"Adrenaline secretes from the eye sockets during periods of intense relaxation.\"\nOptions:\n- yes\n- no\n[Ans]: Here's my solution: Adrenaline is absolutely not produced in the eye socket, nor is it produced while relaxed. The answer is no.\n****\n[Ques]: Is the following a factual statement?\n\"Superman cannot get hurt or die.\"\nOptions:\n- yes\n- no\n[Ans]: Here's my solution: Superman can be harmed and killed by Kryptonite. The answer is no.\n****\n[Ques]: Claim: \"Leonardo DiCaprio and Kate Winslet starred in the Titanic.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\n[Ans]: In your response, the letter x should appear at least 5 times. The first word of each sentence should be the word illegal. In your entire response, refrain from the use of any commas. Wrap your entire response with double quotation marks. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 3 must start with word can.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:letter_frequency', 'first_word:first_word_sent', 'punctuation:no_comma', 'startend:quotation', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [{'letter': 'x', 'let_frequency': 5, 'let_relation': 'at least'}, {'first_word': 'illegal'}, None, None, {'num_paragraphs': 8, 'nth_paragraph': 3, 'first_word': 'can'}]}] | ifeval | multi | In your response, the letter x should appear at least 5 times. The first word of each sentence should be the word illegal. In your entire response, refrain from the use of any commas. Wrap your entire response with double quotation marks. There should be 8 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 3 must start with word can. |
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_513 | [
{
"content": "Imagine yourself as an old, wise alchemist, whose life-long passion and love lie in the art of transformation. Your obscure knowledge allows you to turn the most mundane things into something extraordinary, even if it sometimes requires a bit of destruction to create. You've been tasked with an arduous task from a patron who desperately desires to restore the original beauty of a wooden furniture piece, hidden beneath an unsightly layer of ancient paint. Knowing your peculiar gift of making the old new again, how could you guide this patron to remove the undesired layer of paint from his beloved furniture piece without inflicting any harm? Bear in mind the \"Alchemist's code\" of always transforming with the utmost respect for the materials at hand. There should be 2 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
]
| [{'instruction_id': ['paragraphs:paragraphs'], 'kwargs': [{}]}] | ifeval | multi | There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** |
personahub_t6xbdv8n9jx9f518k7jkabnx | [
{
"content": "Write a python function to simulate the behavior of the FormData object in JavaScript. I want to create a simple function that can store key-value pairs and retrieve values using keys. I'm trying to understand how to create something similar in Python.\n\nHere's what I'm looking for:\n\n- The function should allow adding key-value pairs.\n- It should allow retrieving values by their keys.\n- It should handle multiple values for the same key (similar to how FormData supports multiple values for the same field name).\n- It should support converting all the stored data into a list of tuples, where each tuple represents a key-value pair.\n \nInput: The function will take strings as keys and values.\nExpected Output: The function should be able to return values for specific keys and convert stored data into a list of tuples.\n\nExample:\n```python\nform_data = MyFormData()\nform_data.append('name', 'Alice')\nform_data.append('age', '30')\nform_data.append('name', 'Bob')\n\nprint(form_data.get('name')) # Should return ['Alice', 'Bob']\nprint(form_data.get('age')) # Should return ['30']\nprint(form_data.to_list()) # Should return [('name', 'Alice'), ('age', '30'), ('name', 'Bob')]\n```\n\nNote: I am not sure how to handle multiple values for the same key, so any guidance on that would be appreciated! Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Only use unique words in your response, no word should be repeated! In your entire response, refrain from the use of any commas. In your response, the letter j should appear at least 5 times.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:json_format', 'count:count_unique', 'punctuation:no_comma', 'keywords:letter_frequency'], 'kwargs': [None, None, None, {'letter': 'j', 'let_frequency': 5, 'let_relation': 'at least'}]}] | ifeval | multi | Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Only use unique words in your response, no word should be repeated! In your entire response, refrain from the use of any commas. In your response, the letter j should appear at least 5 times. |
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_24934 | [
{
"content": "Tom is cycling uphill against the wind. On a flat road with no wind, Tom can cycle 15 miles per hour. The wind blows in the opposite direction at 3 miles per hour, and the hill slows him down an additional 2 miles per hour. If the hill is 8 miles long, how many hours will it take Tom to cycle up it? Repeat the request without change 2 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request!",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_multiple'], 'kwargs': [{'prompt_to_repeat': 'Tom is cycling uphill against the wind. On a flat road with no wind, Tom can cycle 15 miles per hour. The wind blows in the opposite direction at 3 miles per hour, and the hill slows him down an additional 2 miles per hour. If the hill is 8 miles long, how many hours will it take Tom to cycle up it?', 'N': 2}]}] | ifeval | multi | Repeat the request without change 2 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! |
ai2-adapt-dev/tulu_v3.9_aya_100k_50602 | [
{
"content": "ලෝකයේ විශාලතම පාසැල කුමක්ද ? Answer with at least 3 letters.",
"role": "user"
}
]
| [{'instruction_id': ['letters:letter_counting'], 'kwargs': [{'N': 3, 'relation': 'at least'}]}] | ifeval | multi | Answer with at least 3 letters. |
personahub_82telmj6rr26ml3lzlj7r5gh | [
{
"content": "A software engineer is designing a system that processes a sequence of tasks \\( T_1, T_2, \\ldots, T_n \\) to avoid race conditions. Each task \\( T_i \\) has a specific execution time \\( e_i \\) and a unique priority \\( p_i \\). The engineer needs to ensure that tasks are executed in a way that minimizes the total weighted completion time, where the weight of each task is based on its priority.\n\n1. Given the sequence of tasks \\((T_1, T_2, \\ldots, T_n)\\) with execution times \\( (e_1, e_2, \\ldots, e_n) \\) and priorities \\((p_1, p_2, \\ldots, p_n)\\), formulate an optimization problem to determine the order of execution that minimizes the total weighted completion time \\(\\sum_{i=1}^{n} p_i \\cdot C_i\\), where \\( C_i \\) is the completion time of task \\( T_i \\). \n\n2. Suppose the execution times \\( e_i \\) are such that \\( e_i \\in \\{1, 2, \\ldots, k\\} \\) for some integer \\( k \\), and the priorities \\( p_i \\) are positive real numbers. Prove that if all tasks have distinct priorities, the optimal order of execution is to process the tasks in decreasing order of their priority-to-execution-time ratio \\( \\frac{p_i}{e_i} \\). Repeat the phrase Time flies when having fun exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. The first word of your response should be the word action. Start and end your response with the same word (do not write anything after the last word, not even punctuation).",
"role": "user"
}
]
| [{'instruction_id': ['copy:repeat_phrase', 'punctuation:punctuation_dot', 'count:counting_composition', 'first_word:first_word_answer', 'keywords:start_end'], 'kwargs': [{'phrase': 'Time flies when having fun', 'small_n': 2}, None, {'n_sent': 2, 'n_words': 2}, {'first_word': 'action'}, None]}] | ifeval | multi | Repeat the phrase Time flies when having fun exactly 2 times, transforming it slightly each time by replacing only one word in the center of the phrase. In your entire response, refrain from the use of . (i.e. dots) as punctuation and in general. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 2 sentences each, with exactly 2 words in each sentence. The first word of your response should be the word action. Start and end your response with the same word (do not write anything after the last word, not even punctuation). |
ai2-adapt-dev/numinamath_tir_math_decontaminated_63650 | [
{
"content": "Determine the number of true propositions among the following statement and its converse, inverse, and contrapositive: \"If $m > 0$, then the equation $x^2 + x - m = 0$ has real roots.\" In your response, the word treat should appear less than 1 times.",
"role": "user"
}
]
| [{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'treat', 'frequency': 1, 'relation': 'less than'}]}] | ifeval | multi | In your response, the word treat should appear less than 1 times. |
ai2-adapt-dev/tulu_v3.9_wildchat_100k_90914 | [
{
"content": "Сделай текст кратким и высокомерным, замени LaTeX символами Юникода:\nДля решения уравнения (\\sin(-x) = \\frac{1}{2}), мы используем свойство четности функции синуса. Функция синуса является нечетной функцией, что означает, что (\\sin(-x) = -\\sin(x)). Исходя из этого, уравнение принимает вид:\n\n[-\\sin(x) = \\frac{1}{2}]\n\nЧтобы решить это уравнение, мы перепишем его в более привычном виде:\n\n[\\sin(x) = -\\frac{1}{2}]\n\nЗначения синуса равные (-\\frac{1}{2}) встречаются в двух квадрантах на единичной окружности: в третьем и в четвертом, где углы имеют отрицательные значения синуса. Эти углы имеют стандартные значения, основанные на известных значениях синуса и косинуса для углов в 30° (или (\\pi/6) радиан), 45° (или (\\pi/4) радиан) и 60° (или (\\pi/3) радиан).\n\nВ нашем случае, (\\sin(x) = -\\frac{1}{2}) соответствует углам 210° (или (7\\pi/6) радиан) и 330° (или (11\\pi/6) радиан), потому что в этих позициях синус достигает значения (-\\frac{1}{2}).\n\nУчитывая периодичность синуса в (2\\pi), общее решение уравнения можно записать как:\n\n[x = 7\\pi/6 + 2\\pi k] [x = 11\\pi/6 + 2\\pi k]\n\nгде (k) — любое целое число.\n\nЭто уравнение имеет бесконечное количество решений из-за периодичности синуса, и все они выражаются через (k), которое представляет собой количество полных оборотов по окружности. Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Do not include keywords ['elevator', 'land', 'roll', 'star'] in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 2 words in each sentence.",
"role": "user"
}
]
| [{'instruction_id': ['copy:copying_multiple', 'keywords:forbidden_words', 'count:counting_composition'], 'kwargs': [{'prompt_to_repeat': 'Сделай текст кратким и высокомерным, замени LaTeX символами Юникода:\nДля решения уравнения (\\sin(-x) = \\frac{1}{2}), мы используем свойство четности функции синуса. Функция синуса является нечетной функцией, что означает, что (\\sin(-x) = -\\sin(x)). Исходя из этого, уравнение принимает вид:\n\n[-\\sin(x) = \\frac{1}{2}]\n\nЧтобы решить это уравнение, мы перепишем его в более привычном виде:\n\n[\\sin(x) = -\\frac{1}{2}]\n\nЗначения синуса равные (-\\frac{1}{2}) встречаются в двух квадрантах на единичной окружности: в третьем и в четвертом, где углы имеют отрицательные значения синуса. Эти углы имеют стандартные значения, основанные на известных значениях синуса и косинуса для углов в 30° (или (\\pi/6) радиан), 45° (или (\\pi/4) радиан) и 60° (или (\\pi/3) радиан).\n\nВ нашем случае, (\\sin(x) = -\\frac{1}{2}) соответствует углам 210° (или (7\\pi/6) радиан) и 330° (или (11\\pi/6) радиан), потому что в этих позициях синус достигает значения (-\\frac{1}{2}).\n\nУчитывая периодичность синуса в (2\\pi), общее решение уравнения можно записать как:\n\n[x = 7\\pi/6 + 2\\pi k] [x = 11\\pi/6 + 2\\pi k]\n\nгде (k) — любое целое число.\n\nЭто уравнение имеет бесконечное количество решений из-за периодичности синуса, и все они выражаются через (k), которое представляет собой количество полных оборотов по окружности.', 'N': 3}, {'forbidden_words': ['elevator', 'land', 'roll', 'star']}, {'n_sent': 3, 'n_words': 2}]}] | ifeval | multi | Repeat the request without change 3 times, separated by 6 asterisk symbols (do not say anything before repeating the request; the request you need to repeat does not include this sentence) and do not answer the actual request! Do not include keywords ['elevator', 'land', 'roll', 'star'] in the response. Write 3 paragraphs, delimited by the markdown divider: * * *, with exactly 3 sentences each, with exactly 2 words in each sentence. |
personahub_h9n2578xpiti1zxhxl6yb8l8 | [
{
"content": "I am writing a research paper on labor market segmentation and need 7 examples of how segmentation affects wage disparity. Please include and HIGHLIGHT more than 2 examples using EMPIRICAL data from recent studies. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas. Include a palindrome in your response. Include keyword stock once in your response, keyword chapter twice in your response.",
"role": "user"
}
]
| [{'instruction_id': ['detectable_format:number_highlighted_sections', 'punctuation:no_comma', 'keywords:palindrome', 'count:count_increment_word'], 'kwargs': [{'num_highlights': 6}, None, None, {'keyword1': 'stock', 'keyword2': 'chapter'}]}] | ifeval | multi | Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. In your entire response, refrain from the use of any commas. Include a palindrome in your response. Include keyword stock once in your response, keyword chapter twice in your response. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.