MétaCan
Menu
Back to cohort
Record W4410573952 · doi:10.4018/jdm.377526

FADE

2025· article· en· W4410573952 on OpenAlexaff
Omar Al-Shamali, James A. Miller, Shaikh Quader

Bibliographic record

VenueJournal of Database Management · 2025
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsIBM (Canada)University of Alberta
Fundersnot available
KeywordsComputer science

Abstract

fetched live from OpenAlex

Error detection is an important part of preparing data for data analysis. Erroneous data can result in inaccurate analysis, resulting in garbage-in, garbage-out. Currently, many models utilize either or both Qualitative and Quantitative methods to detect errors in the data. However, these methods are still limited in the errors they can detect. Hence FADE, Focused and Attention-based Detector of Errors, was proposed. FADE can detect errors within structured data with rows and columns. FADE utilizes the information found in surrounding cells within the same row to help determine if a cell is erroneous. It also learns the expected structure of the attributes in the dataset and the values expected in each attribute. This results in FADE having a much wider range of error type detection and having a higher classification of errors than other methods. FADE was evaluated and was found to detect these errors with relatively high performance.

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)0.006
metaresearch head score (Gemma)0.038
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.984
Threshold uncertainty score0.000

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.038
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.002
Science and technology studies0.0010.001
Scholarly communication0.0030.006
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0160.009

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 head0.009
GPT teacher head0.286
Teacher spread0.277 · 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.

Study designNot applicable
Domainnot available
GenreOther

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 routes1
Has abstractyes

Explore more

Same venueJournal of Database ManagementSame topicNatural Language Processing TechniquesFrench-language works237,207