MétaCan
Menu
Back to cohort
Record W4200126321 · doi:10.5121/csit.2021.112302

Representation Learning and Similarity of Legal Judgements using Citation Networks

2021· article· en· W4200126321 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueNatural Language Processing · 2021
Typearticle
Languageen
FieldSocial Sciences
TopicArtificial Intelligence in Law
Canadian institutionsnot available
Fundersnot available
KeywordsSimilarity (geometry)Representation (politics)Computer scienceEmbeddingCitationNeglectInformation retrievalArtificial intelligenceNatural language processingPsychologyPolitical scienceLawImage (mathematics)World Wide Web

Abstract

fetched live from OpenAlex

India and many other countries like UK, Australia, Canada follow the ‘common law system’ which gives substantial importance to prior related cases in determining the outcome of the current case. Better similarity methods can help in finding earlier similar cases, which can help lawyers searching for precedents. Prior approaches in computing similarity of legal judgements use a basic representation which is either abag-of-words or dense embedding which is learned by only using the words present in the document. They, however, either neglect or do not emphasize the vital ‘legal’ information in the judgements, e.g. citations to prior cases, act and article numbers or names etc. In this paper, we propose a novel approach to learn the embeddings of legal documents using the citationnetwork of documents. Experimental results demonstrate that the learned embedding is at par with the state-of-the-art methods for document similarity on a standard legal dataset.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.907
Threshold uncertainty score0.356

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.043
GPT teacher head0.411
Teacher spread0.368 · 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