Corpus and context dependence of the Jacobian lens β€” artifact mirror

Fitted operators, experimental records and the corpus pool for the accompanying paper.

Licence. Everything here is CC BY 4.0, without qualification β€” see LICENSE. That is true by construction, not by assertion: this repository contains only artifacts this work produced. No third-party corpus text is distributed here. The corpus pool is rebuilt from its public sources by repro/06_build_corpora.sh and verified against the manifests that ship here; 8 of 11 corpora rebuilt bit-identically when measured. ATTRIBUTION.md has the detail.

Layout

results/lenses/e28/       166 operators + sidecars   corpus x N ladder
results/lenses/plad/       53 operators + sidecars   per-layer activation dumps
results/lenses/ladder/     15 operators + sidecars   canonical model ladder (70m ... 2.8b)
results/lenses/misc/        8 operators              smokes and one-offs
results/<17 experiment dirs>                         per-experiment operators and records
results/*.json            190 experimental records
corpora/                    3 provenance manifests (NO corpus text β€” rebuild it, see ATTRIBUTION.md)

Every .pt is a corpus-averaged Jacobian J_l = E_x[dh_final/dh_l] fitted with the reference implementation at pin 581d398, fp32, TF32 off, uncentered.

Reproducing

Every statistic in the paper recomputes from results/**.json alone β€” no operators, no GPU:

git clone <code repository>
uv sync && bash repro/01_setup_local.sh
bash repro/04_fetch_results.sh          # pulls results/**.json from here, ~7 MB
bash repro/RUN_ALL.sh --tier T0         # 12 modules

--tier T1 re-scores the stored operators on CPU and needs the .pt from this repo (bash repro/03_fetch_artifacts.sh --all). --tier T2 refits on GPU.

Provenance

Each results file carries a provenance block: the producing script and its SHA-256, the commit, the argv, and the SHA-256 of every declared input. payload_sha256 covers the record excluding the provenance block, so it is stable across reruns that change only environment metadata β€” rerun and compare it, and a match means no number moved.

No hostname is recorded. Input hashes are the values at write time; where a record was later redacted, payload_sha256_before_redaction retains the original so both remain verifiable.

No corpus plaintext is distributed β€” see ATTRIBUTION.md for the rebuild.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support