Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The volume of data that is generated each day is rising rapidly. There is a need to analyze this data efficiently and produce results quickly. Data science offers a formal methodology for processing and analyzing data. It involves a work-flow with multiple stages, such as, data collection, data wrangling, statistical analysis and machine learning. In this paper, we look at data analytics systems that support the data science work-flow. The variety of current commercial and open-source data analytics systems differ significantly in terms of available features, functionality, and scalability. A benchmark can be used to evaluate the functionality and performance of a system. However, there is no standard benchmark for evaluating or comparing these data systems for doing data science. In this paper, we introduce a data science benchmark, Sanzu, to evaluate systems with data processing and analytics tasks. Our benchmark includes a micro and macro benchmark. The micro benchmark tests basic operations in isolation. It consists of task suites for reading and writing, data wrangling, statistical analysis, machine learning and time series analysis. Each macro workload evaluates an analytics application where a series of analysis or functions are based on a real world application. The macro benchmark focuses on sports and smart grid analytics. We evaluate these tasks on five different popular data science frameworks and systems: R, Anaconda Python, Dask, PostgreSQL (MADlib) and PySpark. For micro benchmark we generate synthetic datasets with 3 scale factors: 1, 10 and 100 (scale factor 1=1 million). The macro benchmark uses data generated from real-world data sources.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.010 | 0.004 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it