trillionlabs/idsbench_glm_47

---
dataset_info:
features:
- name: query_id
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
- name: citations
list:
- name: file_path
dtype: string
- name: line_number
dtype: int64
- name: quote
dtype: string
- name: correct
dtype: bool
- name: score
dtype: float64
- name: expected_docs
list: string
- name: cited_docs
list: string
- name: correct_docs
list: string
- name: missing_docs
list: string
- name: extra_docs
list: string
- name: precision
dtype: float64
- name: recall
dtype: float64
- name: f1_score
dtype: float64
- name: has_answer
dtype: bool
- name: has_citations
dtype: bool
- name: llm_judge_score
dtype: int64
- name: llm_judge_max_score
dtype: int64
- name: llm_judge_element_scores
list:
- name: criterion
dtype: string
- name: criterion_id
dtype: string
- name: points_possible
dtype: int64
- name: reasoning
dtype: string
- name: score
dtype: int64
- name: messages
list:
- name: content
dtype: string
- name: name
dtype: string
- name: reasoning_content
dtype: string
- name: role
dtype: string
- name: tool_call_id
dtype: string
- name: tool_calls
list:
- name: function
struct:
- name: arguments
dtype: string
- name: name
dtype: string
- name: id
dtype: string
- name: type
dtype: string
- name: tools
list:
- name: function
struct:
- name: description
dtype: string
- name: name
dtype: string
- name: parameters
struct:
- name: properties
struct:
- name: answer
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: citations
struct:
- name: description
dtype: string
- name: items
struct:
- name: properties
struct:
- name: file_path
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: line_number
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: quote
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: required
list: string
- name: type
dtype: string
- name: type
dtype: string
- name: command
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: content
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: description
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: expression
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: file_path
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: file_type
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: files
struct:
- name: description
dtype: string
- name: items
struct:
- name: type
dtype: string
- name: type
dtype: string
- name: limit
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: new_string
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: offset
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: old_string
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: path
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: pattern
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: prompt
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: query
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: replace_all
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: subagent_type
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: summary
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: task_id
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: timeout
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: url
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: workdir
struct:
- name: description
dtype: string
- name: type
dtype: string
- name: required
list: string
- name: type
dtype: string
- name: type
dtype: string
- name: session_id
dtype: string
- name: success
dtype: bool
- name: error
dtype: string
splits:
- name: train
num_bytes: 47720334
num_examples: 655
download_size: 46609464
dataset_size: 47720334
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---