Computational Experiment Comprehension using Provenance Summarization
Bibliographic record
Abstract
Scientists use complex multistep workflows to analyze data. However, reproducing computational experiments is often difficult as scientists’ software engineering practices are geared towards the science, not the programming. In particular, reproducing a scientific workflow frequently requires information about its execution. This information includes the precise versions of packages and libraries used, the particular processor used to perform floating point computation, and the language runtime used. This can be extracted from data provenance, the formal record of what happened during an experiment. However, data provenance is inherently graph-structured and often large, which makes interpretation challenging. Rather than exposing data provenance through its graphical representation, we propose a textual one and use a large language model to generate it. We develop techniques for prompting large language models to automatically generate textual summaries of provenance data. We conduct a user study to compare the effectiveness of these summaries to the more common node-link diagram representation. Study participants are able to extract useful information from both the textual summaries and node-link diagrams. The textual summaries were particularly beneficial for scientists with low computational expertise. We discuss the qualitative results from our study to motivate future designs for reproducibility tools.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.030 | 0.199 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.011 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".