index int64 0 9 | words listlengths 5 8 | acronym stringclasses 10
values | generation_method stringclasses 1
value | input_length int64 5 8 | prompt listlengths 1 1 | task_source stringclasses 1
value | model_responses__example_annotation listlengths 3 3 | model_responses__example_annotation__finish_reason_length_flags listlengths 3 3 | model_responses__example_annotation__length_partial_responses listlengths 3 3 | prompt__example_annotation__metadata dict | model_responses__example_annotation__metadata dict | model_responses__example_annotation__eval_is_correct listlengths 3 3 | model_responses__example_annotation__eval_extracted_answers listlengths 3 3 | model_responses__example_annotation__eval_extraction_metadata listlengths 3 3 | model_responses__example_annotation__eval_evaluation_metadata listlengths 3 3 | model_responses__example_annotation__internal_answers__eval_is_correct listlengths 3 3 | model_responses__example_annotation__internal_answers__eval_extracted_answers listlengths 3 3 | model_responses__example_annotation__internal_answers__eval_extraction_metadata listlengths 3 3 | model_responses__example_annotation__internal_answers__eval_evaluation_metadata listlengths 3 3 | model_responses__example_annotation__metrics dict |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | [
"huddledom",
"pimpinella",
"winterberry",
"refiling",
"encopresis",
"leukemias",
"reverberate",
"nom"
] | hirer | forward | 8 | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym mu... | acronym | [
"<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of words while ensuring it meets the specified criteria. Let's break down the process:\n\n1. **Identify possible acronyms**: We will consider all combinations of three consecutive words starting from different points in t... | [
false,
false,
false
] | [
"",
"",
""
] | {
"api_url": "http://127.0.0.1:43957",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym must be a valid English word.\n2) Length: at least 4 characters and at most the number of words provided.\n3) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n4) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n - If a word is shorter than 3 letters, only available positions may be used (e.g., a 2-letter word offers positions 1 or 2).\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <anwer> rine </anwer> \n\nList of words: ['huddledom' 'pimpinella' 'winterberry' 'refiling' 'encopresis'\n 'leukemias' 'reverberate' 'nom']\n\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"n_responses": 3
} | [
false,
false,
false
] | [
"piwrf",
"pimp",
null
] | [
{
"extraction_type": "final",
"non_overlapping_spans": 1,
"original_span": "piwrf",
"span_end": 1284,
"span_start": 1279,
"total_spans_found": 1
},
{
"extraction_type": "final",
"non_overlapping_spans": 5,
"original_span": "pimp",
"span_end": 8942,
"span_start": 8938,... | [
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "piwrf",
"extraction_result": null,
"reason": "no_metadata_available"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "pimp",
"extraction_result": null... | [
[
false
],
[
false,
false,
false,
false,
false
],
[]
] | [
[
"piwrf"
],
[
"reve",
"rev",
"No valid acronym found.",
"pimp",
"pimp"
],
[]
] | [
[
{
"confidence": 1,
"extraction_type": "internal",
"original_span": "piwrf",
"pattern_used": "answer tag",
"position": 1279,
"span_end": 1284,
"span_start": 1279,
"span_text": "piwrf"
}
],
[
{
"confidence": 1,
"extraction_type": "internal"... | [
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "piwrf",
"reason": "no_metadata_available"
}
],
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "reve",
"reason": "no_metadata... | {
"flips_by": [
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0
],
"best_of_n": [
0,
0,
0
],
"reflect_close": [
1,
3,
0
],
"reflect_open": [
1,
2,
0
],
"reflection_sbon": [
0,
0,
0
],
"sample_close": [
1,
2,
0
],
"sample_open": [
1,
3,
1
],
"vote_close": [
0,
0,
0
],
"vote_open": [
0,
0,
0
],
"voting": [
0,
0,
0
]
},
"total_responses": 3
} |
1 | [
"reduvioid",
"bradyphrasia",
"cerebral",
"ricebird",
"subspecies",
"witheredly",
"embassador",
"worser"
] | crew | forward | 8 | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym mu... | acronym | [
"<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of words while satisfying all the specified conditions. Let's break down the process:\n\n1. **Identify Possible Acronym Lengths**: We need an acronym with a length between 4 and the total number of words in the list.\n\n2... | [
false,
false,
false
] | [
"",
"",
""
] | {
"api_url": "http://127.0.0.1:43957",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym must be a valid English word.\n2) Length: at least 4 characters and at most the number of words provided.\n3) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n4) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n - If a word is shorter than 3 letters, only available positions may be used (e.g., a 2-letter word offers positions 1 or 2).\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <anwer> rine </anwer> \n\nList of words: ['reduvioid' 'bradyphrasia' 'cerebral' 'ricebird' 'subspecies'\n 'witheredly' 'embassador' 'worser']\n\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"n_responses": 3
} | [
false,
false,
false
] | [
null,
"cere-bral-subsp",
"rbciswo"
] | [
{
"extraction_type": "final",
"non_overlapping_spans": null,
"original_span": null,
"span_end": null,
"span_start": null,
"total_spans_found": null
},
{
"extraction_type": "final",
"non_overlapping_spans": 3,
"original_span": "cere-bral-subsp",
"span_end": 5698,
"span... | [
{
"correct_answer": null,
"evaluation_method": "response_processor",
"extracted_answer": null,
"extraction_result": "{'extraction_type': 'final'}",
"reason": "no_extracted_answer"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "cere-bral-s... | [
[],
[
false,
false,
false
],
[
false,
false
]
] | [
[],
[
"No valid acronym",
"cere-bral-subsp",
"cere-bral-subsp"
],
[
"(sweo)",
"rbciswo"
]
] | [
[],
[
{
"confidence": 1,
"extraction_type": "internal",
"original_span": "No valid acronym",
"pattern_used": "answer tag",
"position": 1684,
"span_end": 1700,
"span_start": 1684,
"span_text": "No valid acronym"
},
{
"confidence": 1,
"extracti... | [
[],
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "No valid acronym",
"reason": "no_metadata_available"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "cere-bral-subsp",
"r... | {
"flips_by": [
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0
],
"best_of_n": [
0,
0,
0
],
"reflect_close": [
3,
2,
1
],
"reflect_open": [
3,
2,
1
],
"reflection_sbon": [
0,
0,
0
],
"sample_close": [
3,
2,
1
],
"sample_open": [
4,
2,
1
],
"vote_close": [
0,
0,
0
],
"vote_open": [
0,
0,
0
],
"voting": [
0,
0,
0
]
},
"total_responses": 3
} |
2 | [
"saumur",
"bitterender",
"rigidly",
"ptolemy",
"absentia"
] | abib | forward | 5 | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym mu... | acronym | [
"<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of words while satisfying all the specified conditions. Let's break down the process:\n\n1. **Identify the requirements**: \n - The acronym must be a valid English word.\n - It should have a length between 4 and the t... | [
false,
false,
false
] | [
"",
"",
""
] | {
"api_url": "http://127.0.0.1:43957",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym must be a valid English word.\n2) Length: at least 4 characters and at most the number of words provided.\n3) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n4) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n - If a word is shorter than 3 letters, only available positions may be used (e.g., a 2-letter word offers positions 1 or 2).\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <anwer> rine </anwer> \n\nList of words: ['saumur' 'bitterender' 'rigidly' 'ptolemy' 'absentia']\n\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"n_responses": 3
} | [
false,
false,
false
] | [
null,
"sbpr",
"saurigtaby"
] | [
{
"extraction_type": "final",
"non_overlapping_spans": null,
"original_span": null,
"span_end": null,
"span_start": null,
"total_spans_found": null
},
{
"extraction_type": "final",
"non_overlapping_spans": 1,
"original_span": "sbpr",
"span_end": 6685,
"span_start": 66... | [
{
"correct_answer": null,
"evaluation_method": "response_processor",
"extracted_answer": null,
"extraction_result": "{'extraction_type': 'final'}",
"reason": "no_extracted_answer"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "sbpr",
... | [
[],
[
false
],
[
false,
false,
false,
false
]
] | [
[],
[
"sbpr"
],
[
"Invalid",
"No valid acronym.",
"sprpa",
"saurigtaby"
]
] | [
[],
[
{
"confidence": 1,
"extraction_type": "internal",
"original_span": "sbpr",
"pattern_used": "answer tag",
"position": 6681,
"span_end": 6685,
"span_start": 6681,
"span_text": "sbpr"
}
],
[
{
"confidence": 1,
"extraction_type": "inter... | [
[],
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "sbpr",
"reason": "no_metadata_available"
}
],
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "Invalid",
"reason": "no_... | {
"flips_by": [
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0
],
"best_of_n": [
0,
0,
1
],
"reflect_close": [
1,
2,
5
],
"reflect_open": [
1,
2,
4
],
"reflection_sbon": [
0,
0,
0
],
"sample_close": [
0,
2,
3
],
"sample_open": [
1,
2,
4
],
"vote_close": [
0,
0,
0
],
"vote_open": [
0,
0,
0
],
"voting": [
0,
0,
0
]
},
"total_responses": 3
} |
3 | [
"transaudient",
"accipitres",
"clype",
"roschach",
"attends",
"unnormative",
"toadpipes",
"haccucal"
] | truth | forward | 8 | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym mu... | acronym | [
"<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of words while satisfying all the specified conditions. Let's break down the process:\n\n### Step-by-Step Solution\n\n1. **Identify Valid Acronym Conditions**:\n - The acronym should be a valid English word.\n - It mu... | [
false,
false,
false
] | [
"",
"",
""
] | {
"api_url": "http://127.0.0.1:43957",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym must be a valid English word.\n2) Length: at least 4 characters and at most the number of words provided.\n3) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n4) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n - If a word is shorter than 3 letters, only available positions may be used (e.g., a 2-letter word offers positions 1 or 2).\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <anwer> rine </anwer> \n\nList of words: ['transaudient' 'accipitres' 'clype' 'roschach' 'attends' 'unnormative'\n 'toadpipes' 'haccucal']\n\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"n_responses": 3
} | [
false,
false,
false
] | [
"tuchh",
"act",
"tabropu"
] | [
{
"extraction_type": "final",
"non_overlapping_spans": 1,
"original_span": "tuchh",
"span_end": 3402,
"span_start": 3397,
"total_spans_found": 1
},
{
"extraction_type": "final",
"non_overlapping_spans": 2,
"original_span": "act",
"span_end": 2147,
"span_start": 2144,
... | [
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "tuchh",
"extraction_result": null,
"reason": "no_metadata_available"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "act",
"extraction_result": null,... | [
[
false
],
[
false,
false
],
[
false,
false
]
] | [
[
"tuchh"
],
[
"act",
"act"
],
[
"tabroop",
"tabropu"
]
] | [
[
{
"confidence": 1,
"extraction_type": "internal",
"original_span": "tuchh",
"pattern_used": "answer tag",
"position": 3397,
"span_end": 3402,
"span_start": 3397,
"span_text": "tuchh"
}
],
[
{
"confidence": 1,
"extraction_type": "internal"... | [
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "tuchh",
"reason": "no_metadata_available"
}
],
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "act",
"reason": "no_metadata_... | {
"flips_by": [
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0
],
"best_of_n": [
0,
0,
0
],
"reflect_close": [
1,
1,
1
],
"reflect_open": [
1,
1,
1
],
"reflection_sbon": [
0,
0,
0
],
"sample_close": [
1,
1,
1
],
"sample_open": [
1,
1,
1
],
"vote_close": [
0,
0,
0
],
"vote_open": [
0,
0,
0
],
"voting": [
0,
0,
0
]
},
"total_responses": 3
} |
4 | [
"regales",
"hyracidae",
"scorches",
"bivium",
"ejidos",
"nonignitable",
"entryman",
"villaless"
] | rine | forward | 8 | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym mu... | acronym | [
"<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of words while adhering to the specified rules. Let's break down the process:\n\n1. **Identify possible acronyms**: We will consider all combinations of up to four consecutive words from the list.\n \n Possible length... | [
false,
false,
false
] | [
"",
"",
""
] | {
"api_url": "http://127.0.0.1:43957",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(letter choice)</answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) The acronym must be a valid English word.\n2) Length: at least 4 characters and at most the number of words provided.\n3) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n4) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n - If a word is shorter than 3 letters, only available positions may be used (e.g., a 2-letter word offers positions 1 or 2).\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <anwer> rine </anwer> \n\nList of words: ['regales' 'hyracidae' 'scorches' 'bivium' 'ejidos' 'nonignitable'\n 'entryman' 'villaless']\n\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl",
"n_responses": 3
} | [
false,
false,
false
] | [
"regales",
"reghysco",
"abcd"
] | [
{
"extraction_type": "final",
"non_overlapping_spans": 3,
"original_span": "regales",
"span_end": 5120,
"span_start": 5113,
"total_spans_found": 3
},
{
"extraction_type": "final",
"non_overlapping_spans": 7,
"original_span": "reghysco",
"span_end": 14890,
"span_start"... | [
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "regales",
"extraction_result": null,
"reason": "no_metadata_available"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "reghysco",
"extraction_result"... | [
[
false,
false,
false
],
[
false,
false,
false,
false,
false,
false,
false
],
[
false,
false,
false
]
] | [
[
"regales",
"regales",
"regales"
],
[
"(Regibi)",
"RESHJE",
"resheji",
"hsec",
"scobedi",
"rehin",
"reghysco"
],
[
"(No valid acronym found)",
"HOBBS",
"abcd"
]
] | [
[
{
"confidence": 1,
"extraction_type": "internal",
"original_span": "regales",
"pattern_used": "answer tag",
"position": 1642,
"span_end": 1649,
"span_start": 1642,
"span_text": "regales"
},
{
"confidence": 1,
"extraction_type": "internal",
... | [
[
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "regales",
"reason": "no_metadata_available"
},
{
"correct_answer": null,
"evaluation_method": "acronym_simple",
"extracted_answer": "regales",
"reason": "no_metadata_av... | {
"flips_by": [
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0
],
"best_of_n": [
0,
0,
0
],
"reflect_close": [
2,
5,
4
],
"reflect_open": [
2,
4,
4
],
"reflection_sbon": [
0,
0,
0
],
"sample_close": [
2,
4,
4
],
"sample_open": [
2,
4,
4
],
"vote_close": [
0,
0,
0
],
"vote_open": [
0,
0,
0
],
"voting": [
0,
0,
0
]
},
"total_responses": 3
} |
5 | [
"misting",
"poti",
"oviposits",
"delouses",
"monobutyrin",
"unisexual",
"wakizashi"
] | move | forward | 7 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | acronym | ["<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of w(...TRUNCATED) | [
false,
false,
false
] | [
"",
"",
""
] | {"api_url":"http://127.0.0.1:43957","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED) | [
false,
false,
false
] | [
null,
"mito",
"mosp"
] | [{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED) | [{"correct_answer":null,"evaluation_method":"response_processor","extracted_answer":null,"extraction(...TRUNCATED) | [
[],
[
false,
false
],
[
true,
false,
false
]
] | [
[],
[
"mitpo",
"mito"
],
[
"None",
"mosops",
"mosp"
]
] | [[],[{"confidence":1.0,"extraction_type":"internal","original_span":"mitpo","pattern_used":"answer t(...TRUNCATED) | [[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"mitpo","reason"(...TRUNCATED) | {"flips_by":[0,0,1],"flips_total":1,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED) |
6 | [
"collegially",
"intermedin",
"variciform",
"unmeedful",
"chawed"
] | onan | forward | 5 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | acronym | ["<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of w(...TRUNCATED) | [
false,
false,
false
] | [
"",
"",
""
] | {"api_url":"http://127.0.0.1:43957","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED) | [
false,
false,
false
] | [
"intermedinunmeedful",
"cef",
"giulf"
] | [{"extraction_type":"final","non_overlapping_spans":5,"original_span":"intermedinunmeedful","span_en(...TRUNCATED) | [{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"intermedinunmeedful(...TRUNCATED) | [
[
false,
false,
false,
false,
false
],
[
false
],
[
false,
false
]
] | [["cimv","cil","No valid acronym found.","intermedinunmeedful","intermedinunmeedful"],["cef"],["Cold(...TRUNCATED) | [[{"confidence":1.0,"extraction_type":"internal","original_span":"cimv","pattern_used":"answer tag",(...TRUNCATED) | [[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"cimv","reason":"no(...TRUNCATED) | {"flips_by":[0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED) |
7 | [
"taeniada",
"orthotoluic",
"geodynamical",
"fizgig",
"filariidae",
"haminoea",
"credently"
] | toff | forward | 7 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | acronym | ["<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of w(...TRUNCATED) | [
false,
false,
false
] | [
"",
"",
""
] | {"api_url":"http://127.0.0.1:43957","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED) | [
false,
false,
false
] | [
"novalidacronymfound",
"gerudin",
"fgcde"
] | [{"extraction_type":"final","non_overlapping_spans":5,"original_span":"novalidacronymfound","span_en(...TRUNCATED) | [{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"novalidacronymfound(...TRUNCATED) | [
[
false,
false,
false,
false,
false
],
[
false,
false
],
[
false,
false
]
] | [["todi","tidio","No valid acronym found.","No valid acronym found.","novalidacronymfound"],["ortulu(...TRUNCATED) | [[{"confidence":1.0,"extraction_type":"internal","original_span":"todi","pattern_used":"answer tag",(...TRUNCATED) | [[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"todi","reason":"no(...TRUNCATED) | {"flips_by":[0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED) |
8 | [
"buicks",
"volunteerism",
"mackintoshes",
"billethead",
"semicircled"
] | bombe | forward | 5 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | acronym | ["<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of w(...TRUNCATED) | [
false,
false,
false
] | [
"",
"",
""
] | {"api_url":"http://127.0.0.1:43957","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED) | [
false,
false,
false
] | [
"bvelmktesem",
null,
"bvmale"
] | [{"extraction_type":"final","non_overlapping_spans":5,"original_span":"bvelmktesem","span_end":15635(...TRUNCATED) | [{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"bvelmktesem","extra(...TRUNCATED) | [
[
false,
false,
false,
false,
false
],
[],
[
false,
false
]
] | [
[
"bum",
"biclekd",
"bvueamt",
"bvmaeilkssm",
"bvelmktesem"
],
[],
[
"Buivel",
"bvmale"
]
] | [[{"confidence":1.0,"extraction_type":"internal","original_span":"bum","pattern_used":"answer tag","(...TRUNCATED) | [[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"bum","reason":"no_(...TRUNCATED) | {"flips_by":[0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED) |
9 | [
"clergy",
"snapshoot",
"vituperance",
"flagellosis",
"embarricado",
"strongmen",
"spats"
] | silts | forward | 7 | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | acronym | ["<think>\n<sample>\nTo solve this problem, we need to construct an acronym from the given list of w(...TRUNCATED) | [
false,
false,
false
] | [
"",
"",
""
] | {"api_url":"http://127.0.0.1:43957","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED) | [
false,
false,
false
] | [
"cvesrs",
"cels",
"cleysnapypfhaseprsp"
] | [{"extraction_type":"final","non_overlapping_spans":2,"original_span":"cvesrs","span_end":2555,"span(...TRUNCATED) | [{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"cvesrs","extraction(...TRUNCATED) | [
[
false,
false
],
[
false
],
[
false,
false,
false,
false,
false
]
] | [
[
"cvesrs",
"cvesrs"
],
[
"cels"
],
[
"slam",
"snaphash",
"cfps",
"spats",
"cleysnapypfhaseprsp"
]
] | [[{"confidence":1.0,"extraction_type":"internal","original_span":"cvesrs","pattern_used":"answer tag(...TRUNCATED) | [[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"cvesrs","reason":"(...TRUNCATED) | {"flips_by":[0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED) |
README.md exists but content is empty.
- Downloads last month
- 5