MétaCan
Menu
Back to cohort
Record W6996016301

Quantifying the difference between black boxes and their automata approximations

2021· dissertation· en· W6996016301 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.

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

Bibliographic record

VenueeScholarship@McGill (McGill) · 2021
Typedissertation
Languageen
FieldComputer Science
TopicMachine Learning and Algorithms
Canadian institutionsMcGill University
Fundersnot available
KeywordsBlack boxMetric (unit)AutomatonArtificial neural networkUpper and lower boundsObstacleLine (geometry)Approximations of π
DOInot available

Abstract

fetched live from OpenAlex

In machine learning, the black box nature of neural networks is a significant obstacle to their adoption.For recurrent neural networks, a recent line of work focuses on extracting automata from trained models in order to use them as lightweight interpretable substitute models.We address the problem of providing theoretical guarantees that these extracted approximations are indeed "similar enough" to the originals.We introduce a metric between deterministic automata.We provide a naive method to upper bound it when one of the models is a known automaton and the other is a black box.Finally, we apply this metric to estimate the performance deterioration when the black box is substituted with the automaton.i

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.838
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.002
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 head0.031
GPT teacher head0.267
Teacher spread0.237 · 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