Validation: A Critical First Step in the Evaluation of Systems for Legal Corpus Determination
Bibliographic record
Abstract
The continued growth of very large data environments, both proprietary and Web-based, increases the importance of effective and ecient legal corpus selection and searching. Current “database selection” research focuses largely on completely autonomous and automatic selection, searching, and results merging in distributed environments. This fully automatic approach has significant deficiencies, including reliance upon thresholds below which data sets with relevant documents are not searched (compromised recall). It also merges result sets, often from disparate data sources, some that users may have discarded before their source selection task completed (diluted precision). We examine the impact that user interaction can have on the process of legal corpus selection. After analyzing thousands of real user queries, we show that precision can be significantly increased when queries are categorized by the users themselves, then interpreted and treated accurately by the system. As a precursor to evaluation, in this workshop, we present three behind-thescenes system validation exercises to assist us in determining whether certain system design decisions are justified in the context of our long-term goals of providing a corpus selection tool to legal practitioners. We ultimately show that by avoiding a one-size-fits-all approach that restricts the role users can play in information discovery, legal corpus selection eectiveness can be appreciably improved.
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 | 0.170 | 0.315 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.007 | 0.015 |
| Open science | 0.005 | 0.006 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.003 | 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".