MétaCan
Menu
Back to cohort
Record W4389988471 · doi:10.1109/scam59687.2023.00010

Keynotes

2023· article· en· W4389988471 on OpenAlex
Ali Mesbah, Sandeep Kaur Kuttal

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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Software Engineering Methodologies
Canadian institutionsCanadian Natural ResourcesUniversity of British ColumbiaNatural Sciences and Engineering Research Council
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceGenerative grammarGRASPContext (archaeology)Task (project management)Artificial intelligenceCode (set theory)SoftwareSet (abstract data type)Program comprehensionHallucinatingSoftware engineeringHuman–computer interactionProgramming languageSoftware systemEngineering

Abstract

fetched live from OpenAlex

The evolution of generative AI holds tremendous promise for automating and enhancing various facets of software engineering. However, as with any nascent technology, it comes with its own set of challenges. A notable one is that generative AI can occasionally 'hallucinate', producing code that, while syntactically correct, may be contextually off-mark or even erroneous. These instances underscore the urgent need for refined methodologies and deeper insights. In this keynote, Prof. Mesbah delves into the confluence of program analysis and generative AI, charting a course toward more precise and context-aware code generation. He posits that instead of arbitrarily choosing context for a developer task, the context should encapsulate meaningful and pertinent details relevant to the task. By showcasing key findings from his recent research, he will highlight how a software's contextual grasp can be pivotal in enhancing the accuracy of AI-driven code generation.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.310
Threshold uncertainty score0.582

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
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 head0.053
GPT teacher head0.305
Teacher spread0.252 · 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