MétaCan
Menu
Back to cohort
Record W7106837064 · doi:10.5281/zenodo.17718180

Collapse Index (CI): A Diagnostic Framework for Bounded, Lightweight, and Reproducible Evaluation of System Instability

2025· preprint· en· W7106837064 on OpenAlexaff

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2025
Typepreprint
Languageen
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsGlycemic Index Laboratories
Fundersnot available
KeywordsInterpretabilityInstabilityBounded functionIndex (typography)Metric (unit)Perturbation (astronomy)Upload

Abstract

fetched live from OpenAlex

This upload contains the preprint “Collapse Index (CI): A Diagnostic Framework for Bounded, Lightweight, and Reproducible Evaluation of System Instability.”The Collapse Index introduces a normalized instability metric designed to reveal hidden brittleness in machine learning systems under benign, non-adversarial perturbations. CI highlights reliability failures that appear stable under standard evaluation methods such as accuracy or confidence-based metrics.The framework emphasizes: • a bounded instability score 0,1 for interpretability • lightweight evaluation requiring only model predictions • dataset-driven perturbation analysis • sealed, reproducible output bundles using cryptographic hashesEach evaluation run produces standardized diagnostics including instability scores, summary tables, and full provenance metadata to support auditability and reproducibility.This deposit includes the full preprint.Associated evaluation artifacts are generated separately and delivered as sealed bundles.Project page: https://collapseindex.orgLicensed under CC BY-NC-ND 4.0.

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)0.022
metaresearch head score (Gemma)0.103
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.022
Threshold uncertainty score0.115

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0220.103
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0070.002
Science and technology studies0.0020.003
Scholarly communication0.0060.005
Open science0.0030.007
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0090.004

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 head0.181
GPT teacher head0.382
Teacher spread0.201 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
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 routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicScientific Computing and Data ManagementFrench-language works237,207