MétaCan
Menu
Back to cohort
Record W4408511407 · doi:10.3386/w33566

A Quest for AI Knowledge

2025· report· en· W4408511407 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

VenueNational Bureau of Economic Research · 2025
Typereport
Languageen
FieldComputer Science
TopicMachine Learning and Data Classification
Canadian institutionsnot available
FundersSocial Sciences and Humanities Research Council of Canada
KeywordsComputer science

Abstract

fetched live from OpenAlex

This paper examines how AI tools that excel at interpolating existing knowledge affect scientific research directions.Using a model where AI assists both scientists (S-AI) and decision-makers (DM-AI), it is shown that AI's impact on research novelty is non-monotonic and depends critically on capability thresholds.While S-AI predictably encourages knowledge consolidation by reducing costs within established domains-potentially creating distinct pockets of deepening-DM-AI generates surprising effects.With limited capabilities, scientists ignore DM-AI.In a moderate regime, scientists "work to the AI," constraining novelty to match AI's operational range.Only with sufficiently advanced DM-AI do scientists unambiguously pursue more novel research.The strong complementarity between AI capabilities and knowledge gaps means that moderate AI may reduce research ambition.These findings challenge the conventional wisdom that interpolative AI uniformly pushes science toward consolidation, revealing a nuanced relationship between AI capabilities and scientific progress instead.

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)0.007
metaresearch head score (Gemma)0.003
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: Other · Consensus signal: Other
Teacher disagreement score0.445
Threshold uncertainty score0.995

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0070.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.000
Research integrity0.0000.001
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 head0.405
GPT teacher head0.587
Teacher spread0.182 · 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