We lifted 16 functions out of this paper's own repositories and ran 15 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| tianyipeng-lab/digital-twin-simulation | canonical | 15 of 16 |
| Function | Status | Where it lives |
|---|---|---|
| assign_decile | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/mad_accuracy_evaluation.py code served (permissive licence) · get_code("179be440a8c1ce9b") |
| compute_column_mad | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/mad_accuracy_evaluation.py code served (permissive licence) · get_code("7b31bb60c7fc9e79") |
| format_instructions | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/convert_question_json_to_text.py code served (permissive licence) · get_code("a77953607b450c76") |
| get_output_path | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/run_LLM_simulations.py code served (permissive licence) · get_code("1b525d98f94cb69e") |
| is_in_range | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/postprocess_responses.py code served (permissive licence) · get_code("d79b384b4d592ac8") |
| is_valid_number | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/postprocess_responses.py code served (permissive licence) · get_code("c595d47b7e66dd4c") |
| load_config | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/run_LLM_simulations.py code served (permissive licence) · get_code("28d3823238da92f8") |
| load_label_formatted_csv | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/pricing_analysis.py code served (permissive licence) · get_code("48813b837dd9b3a5") |
| load_randdollar_breakdown | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/pricing_analysis.py code served (permissive licence) · get_code("542761087965a347") |
| prepare_purchase_data | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/pricing_analysis.py code served (permissive licence) · get_code("b3e7794590cd96fb") |
| read_persona_summary | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/convert_persona_to_text.py code served (permissive licence) · get_code("5a782d377e0f03a6") |
| strip_html | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/convert_persona_to_text.py code served (permissive licence) · get_code("4c517edd28330e93") |
| strip_html | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/convert_question_json_to_text.py code served (permissive licence) · get_code("c472e1d7777b89a0") |
| summary_mad | Ran | tianyipeng-lab/digital-twin-simulation/evaluation/mad_accuracy_evaluation.py code served (permissive licence) · get_code("3c07cde0759188ad") |
| validate_matrix_response | Ran | tianyipeng-lab/digital-twin-simulation/text_simulation/postprocess_responses.py code served (permissive licence) · get_code("2ea6c23f2d53961f") |
| format_question_text | Not yet run | tianyipeng-lab/digital-twin-simulation/text_simulation/convert_persona_to_text.py code served (permissive licence) · get_code("9ed4cb51542a8ede") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
LLM-based digital twin simulation, where large language models are used to emulate individual human behavior, holds great promise for research in AI, social science, and digital experimentation. However, progress in this area has been hindered by the scarcity of real, individual-level datasets that are both large and publicly available. This lack of high-quality ground truth limits both the development and validation of digital twin methodologies. To address this gap, we introduce a large-scale, public dataset designed to capture a rich and holistic view of individual human behavior. We survey a representative sample of $N = 2,058$ participants (average 2.42 hours per person) in the US across four waves with 500 questions in total, covering a comprehensive battery of demographic, psychological, economic, personality, and cognitive measures, as well as replications of behavioral economics experiments and a pricing survey. The final wave repeats tasks from earlier waves to establish a test-retest accuracy baseline. Initial analyses suggest the data are of high quality and show promise for constructing digital twins that predict human behavior well at the individual and aggregate levels. By making the full dataset publicly available, we aim to establish a valuable testbed for the development and benchmarking of LLM-based persona simulations. Beyond LLM applications, due to its unique breadth and scale the dataset also enables broad social science research, including studies of cross-construct correlations and heterogeneous treatment effects.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2505.17479")
get_code_for_paper("2505.17479")
have("2505.17479")
Connect an agent — have() is free.