MétaCan
Menu
Back to cohort

How Many and Which Training Points Would Need to be Removed to Flip this Prediction?

2023· article· en· W4386566644 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.

fundA Canadian funder is recorded on the work.
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

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning and Data Classification
Canadian institutionsnot available
FundersArmy Research OfficeAtomic Energy of Canada Limited
KeywordsRobustness (evolution)Computer scienceText categorizationCardinality (data modeling)CategorizationTraining setSimple (philosophy)Machine learningArtificial intelligenceSet (abstract data type)Regular polygonAlgorithmData miningMathematics

Abstract

fetched live from OpenAlex

We consider the problem of identifying a minimal subset of training data 𝒮t such that if the instances comprising 𝒮t had been removed prior to training, the categorization of a given test point xt would have been different.Identifying such a set may be of interest for a few reasons.First, the cardinality of 𝒮t provides a measure of robustness (if |𝒮t| is small for xt, we might be less confident in the corresponding prediction), which we show is correlated with but complementary to predicted probabilities.Second, interrogation of 𝒮t may provide a novel mechanism for contesting a particular model prediction: If one can make the case that the points in 𝒮t are wrongly labeled or irrelevant, this may argue for overturning the associated prediction. Identifying 𝒮t via brute-force is intractable.We propose comparatively fast approximation methods to find 𝒮t based on influence functions, and find that—for simple convex text classification models—these approaches can often successfully identify relatively small sets of training examples which, if removed, would flip the prediction.

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: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.809
Threshold uncertainty score0.413

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 head0.050
GPT teacher head0.277
Teacher spread0.227 · 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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicMachine Learning and Data ClassificationFrench-language works237,207