MétaCan
Menu
Back to cohort

Code Authorship Attribution using content-based and non-content-based features

2021· article· en· W3198774825 on OpenAlex
Parinaz Bayrami, Jacqueline E. Rice

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAuthorship Attribution and Profiling
Canadian institutionsUniversity of Lethbridge
Fundersnot available
KeywordsComputer scienceIdentification (biology)Field (mathematics)Identity (music)Source codeNatural language processingArtificial intelligenceNatural languageCode (set theory)Writing styleFocus (optics)Computational linguisticsMachine learningLinguisticsProgramming language

Abstract

fetched live from OpenAlex

To attribute authorship (author identification) means to identify the true author of a sample of work among many candidates. Author identification is an important research field in natural language. Machine learning approaches are widely used in natural language analysis, and previous research has shown that similar techniques can be applied in the analysis of computer programming (artificial) languages. This paper focuses on the use of machine learning techniques in the identification of authors of computer programs. We focus on identifying which features capture the writing style of authors in the classification of a computer program according to the author's identity. We then propose a novel approach for computer program author identification. In this method, features from source code of the programs are combined with authors' sociological features (gender and region) to develop the classification model. Several experiments were conducted on two datasets composed of computer programs written in C++. Our models are able to predict an author's identity with a 75% accuracy rate.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.713
Threshold uncertainty score0.901

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.163
GPT teacher head0.312
Teacher spread0.148 · 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

Quick stats

Citations6
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicAuthorship Attribution and ProfilingFrench-language works237,207