Almost Realism · Research

Data and reproduction

Complete raw data releases

The result store is published on GitHub as self-contained record bundles: protobuf files that carry the conversations, judge scores, outcome events, and any activation tensors. Each experiment’s report-cited dataset digest is stamped in the bundle metadata.

data-20260911

12 September 2026 · 10 files · 8.4 GB

The Study 3 calibration: four store experiments added to the combined records bundle beside the thirteen released in August with their digests unchanged, plus a Study 3 capture bundle of pooled activation records from every steered, envelope, dose-sweep and replay cell. Study 4 collections are deliberately left out and ship with that study.

Cited by Study 3

data-20260830

30 August 2026 · 9 files · 8.1 GB

The Study 2 store consolidated into self-contained bundles: one combined records file carrying every experiment’s report-cited digest, the three Study 2 capture bundles (fixed-input, own-trajectory and fresh-generation replays), the calibration captures, and the token-retention pass in volumes.

Cited by Study 2

data-20260829

29 August 2026 · 122 files · 14 GB

The Study 2 collection in the earlier layout: one bundle per experiment plus loose activation-capture files with manifests. Superseded by the consolidated release the next day; kept because the results post cites it.

Cited by Study 2

data-20260818

18 August 2026 · 23 files · 623 MB

Adds the distress-v3 battery pilots and the first activation captures at reference precision (bail and distress replays, fixture directions), the calibration that the Study 2 registration was built on.

Cited by Study 1

data-20260816

16 August 2026 · 11 files · 101 MB

Study 1 complete: the registered confirmatory run and the method arm, the trial run, instrument and ladder calibration, the judge bake-off, the bail-tool arms, the Gemma distress control and the SmolLM3 probe. One bundle per experiment.

Cited by Study 1