Effective Keyword Selection Requires a Mastery of Storage Technology and the Law
Bibliographic record
Abstract
Selecting keywords for searching large volumes of electronically stored information (“ESI”) is an unavoidable, but necessary step in the process of electronic discovery. The parties to a case, or the court, may choose the terms for the search. However, an efficient alternative to both options involves a mediator, neutral, or special master with a thorough understanding of the legal elements of the case and the technology systems that will be subject to keyword search. This alternative can benefit both parties, as well as the court, because a “technology-aware” mediator can expedite an agreement that allows both parties to maintain oversight of the keyword selection process. This serves both parties’ interests because, as the Zubulake court noted, “[i]t might be advisable to solicit a list of search terms from the opposing party for [the purpose of preservation], so that [opposing counsel] could not later complain about which terms were used.” A poorly designed search term list guarantees that the parties will have to perform a series of subsidiary searches as gaps and problems in the original search become apparent. This can easily be mitigated with a mediator who knows the relevant law and technology. An effective search that results in responsive items being identified begins with the intangible creativity that forms a bond between knowledge of the law and technology.
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 | 0.027 | 0.089 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.003 | 0.009 |
| Scholarly communication | 0.012 | 0.025 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.015 | 0.011 |
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".