TREC Deep Learning Track: Reusable Test Collections in the Large Data\n Regime
Bibliographic record
Abstract
The TREC Deep Learning (DL) Track studies ad hoc search in the large data\nregime, meaning that a large set of human-labeled training data is available.\nResults so far indicate that the best models with large data may be deep neural\nnetworks. This paper supports the reuse of the TREC DL test collections in\nthree ways. First we describe the data sets in detail, documenting clearly and\nin one place some details that are otherwise scattered in track guidelines,\noverview papers and in our associated MS MARCO leaderboard pages. We intend\nthis description to make it easy for newcomers to use the TREC DL data. Second,\nbecause there is some risk of iteration and selection bias when reusing a data\nset, we describe the best practices for writing a paper using TREC DL data,\nwithout overfitting. We provide some illustrative analysis. Finally we address\na number of issues around the TREC DL data, including an analysis of\nreusability.\n
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 | 0.032 | 0.095 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.007 | 0.008 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.007 | 0.007 |
| Research integrity | 0.003 | 0.007 |
| Insufficient payload (model declined to judge) | 0.027 | 0.024 |
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".