Changing computational research. The challenges ahead
Bibliographic record
Abstract
The past year has been an interesting one for those interested in reproducible research.There have been great examples of replicability [1,2] in research communication, and examples of horrifying failure of reproducibility (as described in [3]) with serious questions being raised on the ability of our current system of research communication to guarantee, or even encourage, that published research be reproducible or replicable.When we launched the call for papers for Open Research Computation in late 2010 we saw a clear need for higher standards.Computational research should stand out as an exemplar of just how reproducible research can be, yet it falls short more often than not.With modern computational tools it is entirely possible to provide packages which allow direct replication of results.It is possible to provide data and code in the form of a functional virtual machine image along with automated tests to ensure everything is working as expected.But alongside this we can support the reader's ability to modify and re-purpose tools, to run them against new data, indeed to support efforts to deliberately break the system to identify its limitations.In short, to do what we are supposed to do as scientistsreplicate, reproduce, and test the limits of our models and understanding.We deliberately set the bar high, because we felt it should be high, and because we felt that current standards were, in general, not high enough.Over the past year commentaries [4][5][6] have supported these principles, recognizing that there are serious problemsbut few have actually backed up those words with actions.As with data, so with code, journal statements requiring that it be available often lack substancehow is it to be made availableand policies generally lack teeth.
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 | 0.088 | 0.208 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.012 | 0.037 |
| Scholarly communication | 0.024 | 0.073 |
| Open science | 0.008 | 0.015 |
| Research integrity | 0.038 | 0.065 |
| Insufficient payload (model declined to judge) | 0.029 | 0.017 |
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".