# What the evidence can answer

Questions

Each question has its own page: a short answer, the evidence with its cohort and interval, and its limits. Below them, a map of which kinds of transfer have been measured, which are held, and which have not been tried.

Aggregate measurements, organized by the decision they can inform. They are repeated conditions within protocols, not independent experiments, and not an overall ranking.

## Transfer

Does a decoder still work when the sensor, the display, the electrode layout or the body’s movement changes?

- [Dry vs. wet electrodes](https://bci.report/topics/dry-vs-wet/): Sensor transfer · What changes when a decoder crosses between two native eight-channel recordings from the same 102 people? · 2 s SSVEP · 12 targets · balanced accuracy
- [Screen to VR](https://bci.report/topics/screen-to-vr/): Context transfer · The same 21 people calibrated on a PC screen and tested in a VR headset, and the reverse — and why the result is not the cost of the change. Plus: a P300 decoder trained at one image rate and tested at another. · P300 · 21 people in VR · 9 people across image rates
- [Fewer electrodes](https://bci.report/topics/fewer-electrodes/): Montage · In-ear against scalp for sleep, and four posterior electrodes against sixteen for eyes open or closed — and what neither says about any headset. · Two paired comparisons · 10 and 19 people
- [On the move](https://bci.report/topics/on-the-move/): Motion robustness · Standing, walking and running results, with scalp and ear recordings and incompatible time windows kept apart. · SSVEP balanced accuracy · ERP ROC AUC

## Adapting models

How much calibration a decoder needs, which part of a pretrained model to update, and whether pretraining helps at all.

- [How much calibration?](https://bci.report/topics/calibration-budget/): Calibration budget · Twelve, 24 or 48 labeled trials on a wearable SSVEP task, and up to 40 from a person’s next motor-imagery session, help some methods more than others and not every person—and trial count is not elapsed time. · SSVEP · 102 people · motor imagery, next session · 51 people
- [Which part to update?](https://bci.report/topics/model-adaptation/): Model adaptation · LaBraM on new people, same task, zero labels from the test person: head only, last block or LoRA, printed beside the core matrix’s frozen readout. Plus: the next-day experiment, run and held. · EEGMAT, 36 people · three update rules · next day: held
- [Does pretraining help?](https://bci.report/topics/does-pretraining-help/): Representation controls · Matched pretrained and constructor-random encoders under fixed and train-selected readout settings. · Two tasks · two encoders · three random initializations

## Reliability & clinical

When a decoder should not act, what accuracy hides in sleep staging, and what resting-state EEG can and cannot say about a clinical group.

- [When not to act](https://bci.report/topics/when-not-to-act/): Abstention · Jev-style · A decoder that never acts never fires by mistake. Command detection and false activation, read together — and a Jev-style research plan for when to act, wait or recalibrate. · Idle, 4-person pilot · non-control, 20 people · research plan
- [Sleep-stage balance](https://bci.report/topics/sleep-staging/): Sleep staging · simple baselines · Two simple baselines in 25 healthy sleepers and 55 people with sleep apnoea, as two separate experiments: accuracy beside balanced accuracy, and the stage the stager never predicts. · Dreem DOD-H and DOD-O · 25 and 55 nights · balanced accuracy
- [Clinical groups](https://bci.report/topics/clinical-groups/): Clinical research · A 149-person Parkinson's and control comparison, with an age-and-sex-only comparator printed beside it — and why neither is a diagnosis. · 149 people · one site · balanced accuracy

Transfer coverage

## Which kinds of transfer have been measured

Rows are what changes between training and test; columns are the state of the evidence. Each entry links the page that holds it.

What changes between training and test, and whether this site has evidence on it. Cohort sizes and links only, never scores.

| What changes | Measured | Status only | Held | Not measured |
| --- | --- | --- | --- | --- |
| Person — New people: trained on others, tested on someone the model never saw | [Core matrix · new-person protocols](https://bci.report/#overview) — Every protocol whose split is “transfer to a new person”: participant-disjoint folds.; [Dry vs. wet electrodes](https://bci.report/topics/dry-vs-wet/) n=102 also changes: sensor — Source models trained on other people, so the new person and the new sensor arrive together.; [LaBraM adaptation · EEGMAT](https://bci.report/topics/model-adaptation/#adaptation) n=36 — New people, same task, zero labels from the test person.; [Standing to walking and running, SSVEP](https://bci.report/topics/on-the-move/) n=23 also changes: movement — Trained on other people standing, tested on a new person on the move.; [Pretraining controls](https://bci.report/topics/does-pretraining-help/) n=36 / 10 — Frozen encoders with a readout fitted on other people, on a motor-imagery and a mental-workload task.; [Parkinson’s disease vs. controls](https://bci.report/topics/clinical-groups/) n=149 — Every person held out once; one site, and not a diagnosis.; [Sleep staging · Dreem, two cohorts](https://bci.report/topics/sleep-staging/) n=55 / 25 — Each night held out once and scored by a model fitted on other people’s nights of the same cohort; the two cohorts are separate experiments. |  | [Neural and foundation models on the Dreem cohorts](https://bci.report/releases/#hold-dreem-amplitude-sensitive-models) — Not run: the source’s physical units disagree.; [Foundation models on the clinical cohort](https://bci.report/releases/#hold-clinical-foundation-models) — Not run: the source states no physical amplitude unit. |  |
| Session / day — The same person, another session or another day | [Mobile ERP · first session to the others](https://bci.report/topics/on-the-move/#erp-heading) n=24 / 17 also changes: movement — Fitted on the person’s first session, standing; the session and the movement change together.; [OpenBMI motor imagery · first session to the second](https://bci.report/topics/calibration-budget/#next-session) n=51 — The same person and task: trained on the first session, tested on the second, with and without a few of its labelled trials. | [Cross-session pilot](https://bci.report/topics/model-adaptation/#cross-session) n=1 — One person: every score would be that person’s, so none is published. | [Next-day adaptation](https://bci.report/releases/#hold-bnci2015-001-crossday) — Run and independently replayed; held for a licence and ethics review. |  |
| Sensor / montage — Another sensor type or another set of electrodes | [Dry ⇄ wet electrodes](https://bci.report/topics/dry-vs-wet/) n=102 also changes: person — Trained on one sensor type, tested on the other, in both directions.; [In-ear vs. scalp, sleep](https://bci.report/topics/fewer-electrodes/#montage-finding) n=10 comparison — Both electrode sets scored on the same epochs: a paired comparison, not training on one and testing on the other.; [Posterior subset vs. all electrodes](https://bci.report/topics/fewer-electrodes/#posterior-subset) n=19 comparison — A software subset of one headset, not two devices. |  |  | From one headset or amplifier to another — Every sensor change here is within one study’s own equipment. |
| Context — Another display, movement, or image rate | [Screen ⇄ VR, P300](https://bci.report/topics/screen-to-vr/) n=21 — The same people, calibrated on one display and tested on the other.; [Standing to walking and running, SSVEP](https://bci.report/topics/on-the-move/) n=23 also changes: person — Trained on other people standing, tested on a new person on the move.; [Standing to walking and running, ERP](https://bci.report/topics/on-the-move/#erp-heading) n=24 / 17 also changes: session — The same person; movement and session change together.; [Image rate, P300](https://bci.report/topics/screen-to-vr/#image-rate) n=9 also changes: recording — Trained on one recording at one rate, tested on a different recording: rate and recording change together. |  |  |  |
| Dataset — Trained on one dataset, tested on another |  |  |  | Training on one dataset, testing on another — Not run here. Whether a dataset was in a model’s pretraining data is a different question. |

A state says whether evidence exists, not whether transfer works. n is the number of people behind an entry; two sizes (n=24 / 17) are two analyses or cohorts behind the same entry, largest first. “comparison” marks two electrode sets scored on the same data rather than a transfer from one to the other; “also changes” names what else changed in the same contrast. A held entry is described in the holds register, not here.

Cohort sizes are read from the reviewed downloads: [deployment-topics.json](https://bci.report/data/deployment-topics.json) · [adaptation-update.json](https://bci.report/data/adaptation-update.json) · [clinical-update.json](https://bci.report/data/clinical-update.json) · [large-source-update.json](https://bci.report/data/large-source-update.json) · [context-update.json](https://bci.report/data/context-update.json) · [evidence-update.json](https://bci.report/data/evidence-update.json) · [extension-update.json](https://bci.report/data/extension-update.json) · [Full holds register →](https://bci.report/releases/#holds)

---
Markdown copy of https://bci.report/topics/, generated from the published page. Figures are aggregate results; terms of use: https://bci.report/data-use/