Sign in
← Back to search
github Not archived

Agnuxo1/AIMO-Interp-SmallModels

White-box robustness probes for AIMO Interpretability: Small Track bundle, training-only validation transforms and reproducible controls.

0 awesome lists

Quick read

Stars
1
Forks
0
Open issues
0
Commits
2

Activity and growth

Latest capture 2026-10-29 04:00

Stars · last 7 days
0 0.0%
Commits · last 7 days
0 0.0%
Stars since tracking
0
Stored snapshots
1

Compare the starting count and capture dates, not just the percentage. How to read GitHub star growth. Missing history is not zero growth.

Metadata

Language
Python
License
Apache-2.0
Default branch
main
Created
2026-10-28
First commit
2026-10-28
Last pushed
2026-10-28
GitHub updated
2026-10-28
Last synced
2026-10-29 04:00
Stack scanned
2026-10-29 04:00
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

Sign in to like Agnuxo1/AIMO-Interp-SmallModels
Compare this repository README View on GitHub

AI development signals

0 paths

Agent instructions and tool configuration found in this repository.

No config files detected.

Growth history

Tracked growth

1 observed capture since 2026-10-29. Observed captures are shown by default.

Stars from first capture 0

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

Agnuxo1/aimo-interp-residual-robustness-probes

Residual-stream probes predict whether small math LLMs stay correct under meaning-preserving perturbations — from one forward pass, before generation. AIMO Interpretability Challenge 2026, Small Models Track.

1 stars
Python 0 awesome lists

Agnuxo1/AIMS-PAIEC-2026

Entry to the Predictive AI Evaluation Competition at NeurIPS 2026 (Stanford AIMS): Beta-Binomial shrinkage predictor, independent audit, reproducible protocol and public-data findings.

1 stars
Python 0 awesome lists

Agnuxo1/overture-coverage-gap-equity

Rule-compliant Overture Maps coverage-gap estimator for 9,379 US tracts + a provenance bias discovery (Zindi x Humane Intelligence Bias Bounty)

1 stars
Python 0 awesome lists

Agnuxo1/LightMyCells2-ModalityAware-UNet

Light My Cells 2: modality-aware five-fold U-Net predicting nucleus, mitochondria, tubulin and actin fluorescence from transmitted-light microscopy (Best Focus + MIP), with leakage-safe validation and a Grand Challenge container.

2 stars
Python 0 awesome lists

Agnuxo1/s6e9-honest-ceiling

Fold-safe ensembling to the honest ceiling of Kaggle Playground S6E9, and a Darwin-Cage residual search with a power analysis. Nested OOF 0.946420; 47,679 evolved programs, 0 discoveries.

1 stars
Python 0 awesome lists

Agnuxo1/enveda-casmi-2026-metfrag-ranking

MetFrag-assisted, leader-safe ranking of natural-product structures from MS/MS spectra — Enveda CASMI 2026 (Kaggle) entry with pre-registered experiments and animated figures

1 stars
Python 0 awesome lists