MétaCan
Menu
Back to cohort
Record W4417174389 · doi:10.36939/ir.202512091609

Data-Driven Methodologies for Intelligent Systems

2025· dissertation· en· W4417174389 on OpenAlexaffabout
Armin Felahatpisheh

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicSpeech and dialogue systems
Canadian institutionsUniversity of WinnipegCanadian Society for Immunology
Fundersnot available
KeywordsInterpretabilityIntelligent decision support systemFeature (linguistics)Modular designVerifiable secret sharingChatbotModel-based reasoningSchema (genetic algorithms)

Abstract

fetched live from OpenAlex

This thesis presents a unified investigation into data-driven intelligent systems through three major contributions: (i) a research study introducing a hierarchical two-level genetic algorithm for automated feature engineering, (ii) Query Weave, a conversational structured-data analysis system, and (iii) ImmiAI, a retrieval-augmented immigration assistance chatbot grounded in authoritative Canadian sources. The first contribution develops a novel genetic algorithm that balances predictive performance and interpretability through multi-objective optimization, ensemble evaluation, and non-linear feature transformations. The second contribution addresses the limitations of large language models in tabular reasoning by proposing a layered architecture for schema profiling, statistical discovery, and service routing. The third contribution integrates web scraping, data-lake pipelines, vector retrieval, and grounded LLM reasoning to support accurate and auditable immigration guidance. Together, these components demonstrate how automation, metadata-driven analytics, and grounded natural-language interfaces can reduce technical barriers and expand access to AI systems. The thesis highlights the importance of verifiable computation, modular reasoning pipelines, and tool-augmented conversational design in the development of trustworthy intelligent systems.

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 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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.476
Threshold uncertainty score0.810

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0030.000
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 head0.223
GPT teacher head0.401
Teacher spread0.178 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
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
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicSpeech and dialogue systemsFrench-language works237,207