MétaCan
Menu
Back to cohort
Record W4389012049 · doi:10.48550/arxiv.2011.12183

Generating Intelligible Plumitifs Descriptions: Use Case Application\n with Ethical Considerations

2020· preprint· en· W4389012049 on OpenAlexaboutno aff
David Beauchemin, Nicolas Garneau, Eve Gaumond, Pierre-Luc Déziel, Richard Khoury, Luc Lamontagne

Bibliographic record

VenuearXiv (Cornell University) · 2020
Typepreprint
Languageen
FieldSocial Sciences
TopicArtificial Intelligence in Law
Canadian institutionsnot available
Fundersnot available
KeywordsComputer scienceCode (set theory)JurisdictionIdentity (music)Simple (philosophy)Computer securityLawSource codeCriminal codeArchitectureInternet privacyWorld Wide WebCriminal lawPolitical scienceProgramming languageEpistemology

Abstract

fetched live from OpenAlex

Plumitifs (dockets) were initially a tool for law clerks. Nowadays, they are\nused as summaries presenting all the steps of a judicial case. Information\nconcerning parties' identity, jurisdiction in charge of administering the case,\nand some information relating to the nature and the course of the preceding are\navailable through plumitifs. They are publicly accessible but barely\nunderstandable; they are written using abbreviations and referring to\nprovisions from the Criminal Code of Canada, which makes them hard to reason\nabout. In this paper, we propose a simple yet efficient multi-source language\ngeneration architecture that leverages both the plumitif and the Criminal\nCode's content to generate intelligible plumitifs descriptions. It goes without\nsaying that ethical considerations rise with these sensitive documents made\nreadable and available at scale, legitimate concerns that we address in this\npaper.\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 imitation

Not 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.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.024
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.017
Threshold uncertainty score0.057

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.024
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0030.004
Open science0.0020.004
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0170.005

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.

Opus teacher head0.312
GPT teacher head0.289
Teacher spread0.023 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2020
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicArtificial Intelligence in LawFrench-language works237,207