Core-matrix protocol · Transfer to a new person

SSVEP · 4 channels on BETA

The released protocol, with the score of every method run under it.

The protocol at a glance

Task
40 visual targets · 4 posterior electrodes
Evaluation
Transfer to a new person
Dataset
BETA
People
70
Data
11,200 trials · 7 participant-disjoint folds
Input
4 channels selected from a 64-channel recording · 2-second windows
Chance level
2.5%
Metrics
Balanced accuracy (primary) · Macro F1 (secondary)

Results

Compare within this protocol only: other protocols differ in cohort, electrodes, window or chance level.

Standard CCA
57.6% (51.8%–63.5%)
Spectral ridge
48.2% (43.1%–53.3%)
LaBraM
12.9% (11.2%–14.6%)
CBraMod
27.6% (24.1%–31.3%)
EEGNet
44.1% (38.6%–49.6%)
FBCCA
72.3% (67.5%–76.9%)
ShallowFBCSPNet
16.2% (14.1%–18.6%)
Deep4Net
38.7% (33.7%–43.8%)
Balanced accuracy, every method under this protocol. Dot: the estimate; line: descriptive 95% interval; dashed line: chance level.
MethodTraining modeBalanced accuracyMacro F1ChannelsPeopleScoring time
Standard CCAClassical methodKnown-frequency reference · no fitting57.6%51.8%–63.5%0.567Mean across held-out participants4701.1 s
Spectral ridgeClassical methodSupervised fit48.2%43.1%–53.3%0.467Mean across held-out participants4700.7 s
LaBraMFoundation modelFrozen encoder + ridge head12.9%11.2%–14.6%0.110Mean across held-out participants4702.5 s
CBraModFoundation modelFrozen encoder + ridge head27.6%24.1%–31.3%0.257Mean across held-out participants4703.0 s
EEGNetCompact modelScratch · 20 epochs44.1%38.6%–49.6%0.421Mean across held-out participants470146.7 s
FBCCAClassical method · FBCCA-M3-N7-H5 · Local Ubuntu / CPU, training-freeKnown-frequency reference · no fitting72.3%67.5%–76.9%0.720Mean across held-out participants470—
ShallowFBCSPNetCompact model · matrix recipe · AdamW · Apple M5 / MPSScratch · 20 epochs16.2%14.1%–18.6%0.134Mean across held-out participants470—
Deep4NetCompact model · matrix recipe · AdamW · Apple M5 / MPSScratch · 20 epochs38.7%33.7%–43.8%0.373Mean across held-out participants470—

Scoring time covers fitting and prediction in this configuration, may include accelerator waiting, and excludes data preparation. Scoring time is not recorded for the rows of core-matrix-update-20261106.

Not applicable under this protocol: CSP+LDA. The published CSP+LDA recipe is binary and computes one broadband log-variance per spatial filter over the whole window; the 40 BETA targets lie in one 8–15.8 Hz band, 0.2 Hz apart.

Not run under this protocol: Temporal ridge, TS+LR, MDM, XDAWNCov+TS+LR, xDAWN+LDA.

Pick-two protocol comparison

Compare any two methods on SSVEP · 4 channels

Inspect point estimates and 95% intervals side by side on a shared axis. Paired differences appear only where a paired interval is published. Dropdowns are grouped by family alphabetically — never ordered by score.

0%25%50%75%100%Chance 2.5%FBCCA72.3% [67.5–76.9]Standard CCA57.6% [51.8–63.5]
Published paired contrastFBCCA − Standard CCA: +14.7 pp[+10.7, +19.1 pp]

98.75% interval, Bonferroni-adjusted for four contrasts · n = 70 participants · Paired interval excludes zero

Default view (SSVEP · 4 channels): FBCCA balanced accuracy 72.3% (95% interval 67.5–76.9%); Standard CCA 57.6% (95% interval 51.8–63.5%); chance 2.5%.

Published paired contrasts table (9 pairs)
Pair (left minus right)Mean differenceGoverning intervalParticipantsAdjustment & notes
FBCCA − Standard CCA+14.7 pp[+10.7, +19.1 pp]7098.75% interval, Bonferroni-adjusted for four contrasts
FBCCA − EEGNet+28.2 pp[+22.8, +33.9 pp]7098.75% interval, Bonferroni-adjusted for four contrastsagainst the matrix's one-seed EEGNet cell; training variance not included
Deep4Net − EEGNet−5.5 pp[−6.8, −4.1 pp]7095% interval, unadjustedagainst the matrix's one-seed EEGNet cell; training variance not included
ShallowFBCSPNet − EEGNet−27.9 pp[−31.9, −23.9 pp]7095% interval, unadjustedagainst the matrix's one-seed EEGNet cell; training variance not included
ShallowFBCSPNet − Deep4Net−22.4 pp[−26.1, −18.9 pp]7095% interval
Log band-power ridge − Spectral ridge−42.9 pp[−47.7, −38.1 pp]7095% paired participant bootstrap interval, unadjusted
LaBraM at Scale Quark-L − LaBraM at Scale Quark-B+0.1 pp[−0.9, +1.2 pp]7095% paired participant bootstrap interval, unadjusted (21 ladder contrasts)
LaBraM at Scale Quark-H − LaBraM at Scale Quark-L−1.7 pp[−2.7, −0.8 pp]7095% paired participant bootstrap interval, unadjusted (21 ladder contrasts)
LaBraM at Scale Quark-H − LaBraM at Scale Quark-B−1.6 pp[−2.5, −0.7 pp]7095% paired participant bootstrap interval, unadjusted (21 ladder contrasts)

How these rows were run

FBCCA on beta-8ch and beta-4ch

Recipe
FBCCA: FBCCA-M3-N7-H5
Hardware
FBCCA: Local Ubuntu / CPU, training-free

Filter-bank CCA, recipe FBCCA-M3-N7-H5: seven Chebyshev sub-bands (6–90 Hz), five harmonics, weights n^−1.25 + 0.25 (Chen et al. 2015, M3); our SciPy realisation. It reads the authors' 3–100 Hz window, and its own filter bank takes the place of the 6–80 Hz step. Window, electrodes, targets and people are those of the matrix. No training; folds unused.

FBCCA and CCA are given the 40 stimulus frequencies and use no training data.

The same recipe appears on card 11 (other endpoints) and in the electrode-shift study (the 8-electrode figure); these rows give its 40-target value under the core protocol, and the 8-electrode figure was known before this run. New SSVEP frequencies → Fewer electrodes →

ShallowFBCSPNet and Deep4Net under the matrix recipe

Recipe
ShallowFBCSPNet, Deep4Net: matrix recipe · AdamW
Hardware
ShallowFBCSPNet, Deep4Net: Apple M5 / MPS

Paired differences

Each difference is the mean over people of each person’s difference in balanced accuracy, in percentage points (pp), on the same windows and people.

FBCCA on beta-8ch and beta-4ch

DifferenceMean (pp)98.75% interval, Bonferroni-adjusted for four contrasts95% interval, unadjustedReading
FBCCA − Standard CCAFBCCA-M3-N7-H5+14.7 pp10.7 to 19.111.5 to 18.1higher

The difference belongs to the whole recipe (filter bank, band edges, five against three harmonics).

against the matrix's one-seed EEGNet cell; training variance not included
DifferenceMean (pp)98.75% interval, Bonferroni-adjusted for four contrasts95% interval, unadjustedReading
FBCCA − EEGNetFBCCA-M3-N7-H5+28.2 pp22.8 to 33.924.0 to 32.6higher

98.75 % intervals are Bonferroni-adjusted for four contrasts; the 95 % intervals beside them are unadjusted. Row intervals are the matrix's descriptive 95 % participant bootstrap.

ShallowFBCSPNet and Deep4Net under the matrix recipe

against the matrix's one-seed EEGNet cell; training variance not included
DifferenceMean (pp)95% interval, unadjustedBonferroni interval over 18 contrastsReading
Deep4Net − EEGNet−5.5 pp−6.8 to −4.1−7.5 to −3.5lower
ShallowFBCSPNet − EEGNet−27.9 pp−31.9 to −23.9−34.4 to −21.9lower

The paired 95 % interval governs the wording; the Bonferroni interval beside it covers all 18 contrasts. Read at 95 % without correction, about one in 20 contrasts with no true difference may show one by chance.

Beside the core matrix

Log band-power ridge (5 bands, visible channels)

Five log band powers (1–4, 4–8, 8–13, 13–30 and 30–45 Hz) per channel on all recorded channels of the protocol, from one Hann periodogram of each published window after removing each channel's window mean and a per-window robust amplitude scaling, read by the core ridge head (alpha 100) on the published windows and participant-held-out folds. It uses the same windows, people, folds and ridge head as the Spectral ridge row, repeated from the table above.

MethodTraining modeBalanced accuracyMacro F1ChannelsPeople
Spectral ridgeClassical method · core matrix row aboveSupervised fit48.21%43.06%–53.29%0.467470
Log band-power ridge (5 bands, visible channels)Classical methodSupervised fit5.30%4.78%–5.84%0.034470

Differences from two published rows

Each difference is this row minus the named row on the same people, with a paired participant bootstrap (10,000 draws): an interval wholly above zero reads above, wholly below reads below, and one that includes zero reads not separated, which does not show the two are equivalent. The intervals are descriptive, conditional on these folds, with no multiplicity correction.

Minus the Spectral ridge row: −42.91 pp (−47.74 to −38.10): below. The two rows differ in bands, normalisation, estimator, frequency range and sampling rate at once, so the difference measures the whole recipe.

Minus REVE Large, a frozen-encoder row chosen on these same test folds: −41.05 pp (−45.48 to −36.69): below.

Notes on this comparator

Run as a broad-band control stated before scoring: 5 broad bands cannot resolve 40 targets 0.2 Hz apart. Chance is 2.5%.

Beside the core matrix

Further foundation encoders, frozen

Each encoder replaces LaBraM or CBraMod in the frozen recipe above; the windows, people, folds, ridge head and scoring stay the same. Rows are grouped by model family; a row is above or below another only where their 95% intervals do not overlap. Each interval is a descriptive participant bootstrap with no multiplicity correction, and with 126 frozen cells an occasional non-overlap is expected by chance. Every encoder sees this protocol’s published windows, usually shorter than its pretraining context.

Standard CCA
57.6% (51.8%–63.5%)
Spectral ridge
48.2% (43.1%–53.3%)
LaBraM
12.9% (11.2%–14.6%)
CBraMod
27.6% (24.1%–31.3%)
EEGNet
44.1% (38.6%–49.6%)
REVE Base
25.5% (22.4%–28.8%)
REVE Large
46.4% (41.7%–51.2%)
LUNA Base
9.0% (8.1%–10.1%)
LUNA Large
11.2% (9.8%–12.6%)
BrainOmni Base
13.0% (10.6%–15.6%)
CodeBrain
11.2% (9.8%–12.7%)
EEGMamba
32.7% (28.9%–36.7%)
ST-EEGFormer Base
17.5% (15.8%–19.3%)
ST-EEGFormer Large
22.4% (19.9%–25.0%)
eeg-fm-masking MAE (r=9 cm, L=2)
47.1% (42.1%–52.1%)
ERP-FM Base
20.9% (18.4%–23.5%)
SingLEM
20.5% (17.8%–23.3%)
ZUNA 1.1
8.4% (7.5%–9.4%)
Balanced accuracy under this protocol. Grey: the released rows above; rust: the further encoders, in family order. Dot: the estimate; line: 95% interval; dashed line: chance level.
EncoderTraining modeBalanced accuracyMacro F1ChannelsPeoplePretraining exposure
REVE Base1Foundation modelFrozen encoder + ridge head25.5%22.4%–28.8%0.232470not in the authors' published pretraining list (checked 2026-10-04)source ↗
REVE Large2Foundation modelFrozen encoder + ridge head46.4%41.7%–51.2%0.445470not in the authors' published pretraining list (checked 2026-10-04)source ↗
LUNA Base3Foundation modelFrozen encoder + ridge head9.0%8.1%–10.1%0.069470not in the authors' published pretraining list (checked 2026-10-04)source ↗
LUNA Large4Foundation modelFrozen encoder + ridge head11.2%9.8%–12.6%0.090470not in the authors' published pretraining list (checked 2026-10-04)source ↗
BrainOmni Base5Foundation modelFrozen encoder + ridge head13.0%10.6%–15.6%0.119470not in the authors' published pretraining list (checked 2026-10-04)source ↗
CodeBrain6Foundation modelFrozen encoder + ridge head11.2%9.8%–12.7%0.091470not in the authors' published pretraining list (checked 2026-10-04)source ↗
EEGMamba7Foundation modelFrozen encoder + ridge head32.7%28.9%–36.7%0.305470not in the authors' published pretraining list (checked 2026-10-04)source ↗
ST-EEGFormer Base8Foundation modelFrozen encoder + ridge head17.5%15.8%–19.3%0.148470in the authors' published pretraining listsource ↗
ST-EEGFormer Large9Foundation modelFrozen encoder + ridge head22.4%19.9%–25.0%0.193470in the authors' published pretraining listsource ↗
eeg-fm-masking MAE (r=9 cm, L=2)10Foundation modelFrozen encoder + ridge head47.1%42.1%–52.1%0.454470not in the authors' published pretraining list (checked 2026-10-04)source ↗
ERP-FM Base11Foundation modelFrozen encoder + ridge head20.9%18.4%–23.5%0.175470not in the authors' published pretraining list (checked 2026-10-04)source ↗
SingLEM12Foundation modelFrozen encoder + ridge head20.5%17.8%–23.3%0.153470not in the authors' published pretraining list (checked 2026-10-04)source ↗
ZUNA 1.113Foundation modelModel card: research use only, not for diagnosis or clinical use.Frozen encoder + ridge head8.4%7.5%–9.4%0.053470Exposure unknownunknown: the authors do not list their pretraining data closely enough to decidesource ↗

Pretraining exposure is what each model’s authors publish as their pretraining list, checked on 2026-10-04: a dataset absent from it is “not in the authors’ published pretraining list”, which is not proof that its recordings were never seen. ST-EEGFormer lists BETA and SingLEM lists TMNRED; ZUNA 1.1 publishes no list, so every one of its cells is unknown; EEGMamba’s list is read from its official code (its paper was not read), with medium confidence.

Row footnotes

  1. Input removes the per-segment per-channel mean before the published /100 scaling (declared before scoring); a no-mean-removal sensitivity run scores P300 0.71 percentage points higher and sleep 1.40 lower.
  2. Input removes the per-segment per-channel mean (declared before scoring); the no-mean-removal sensitivity run scores P300 2.06 percentage points lower and sleep 0.93 lower.
  3. Resampled to 256 Hz and truncated to whole 40-sample patches; 1-2 s windows and 4-8 channel montages are outside the authors' tested regime.
  4. As LUNA Base. Frozen probes only.
  5. p300-target and semantic-target not run: the 2 s tokenizer window cannot be met by 1 s segments without zero padding. Upstream common average reference kept on 4-8 channel montages.
  6. Published CBraMod pooling (patch mean, channels kept); LoRA effectively adapts only the V projection (1-token attention window upstream).
  7. Published CBraMod pooling; LoRA on Mamba2 in_proj and out_proj (24 targets).
  8. BETA cells are pretraining-exposed (BETA is in the ST-EEGFormer corpus).
  9. BETA cells are pretraining-exposed. The authors' downstream class (1-based temporal index) was used; Large may have been pretrained with a 0-based index. Frozen probes only.
  10. Paper-recommended masking geometry; channel-retained pooling (C x 512). Three sibling checkpoints appear in the masking ablation panel.
  11. In design: p300-target and semantic-target. The other six protocols are negative controls outside the model's design. ERP windows have no pre-stimulus baseline.
  12. semantic-target is pretraining-exposed (TMNRED is in the SingLEM corpus). Each channel is encoded independently; the last 0.25 s of each 2 s segment is not seen by the tokenizer.
  13. Pretraining exposure unknown for every core dataset (no published source list). Encoder only; no channel upsampling or reconstruction.
  14. A sibling of the paper-recommended checkpoint in the masking ablation: the same architecture, corpus and recipe, another masking framework or geometry.
Masking ablation: three sibling checkpoints of eeg-fm-masking

Intervals are marginal: the same people under two checkpoints are not tested as a pair.

EncoderTraining modeBalanced accuracyMacro F1ChannelsPeoplePretraining exposure
eeg-fm-masking MAE (r=9 cm, L=2)10Foundation model · matrix row aboveFrozen encoder + ridge head47.1%42.1%–52.1%0.454470not in the authors' published pretraining list (checked 2026-10-04)source ↗
eeg-fm-masking JEPA (r=9 cm, L=2)14Foundation modelFrozen encoder + ridge head43.4%38.7%–48.3%0.417470not in the authors' published pretraining list (checked 2026-10-04)source ↗
eeg-fm-masking MAE (r=one channel, L=1)14Foundation modelFrozen encoder + ridge head46.7%41.9%–51.5%0.450470not in the authors' published pretraining list (checked 2026-10-04)source ↗
eeg-fm-masking JEPA (r=one channel, L=1)14Foundation modelFrozen encoder + ridge head45.4%40.6%–50.2%0.438470not in the authors' published pretraining list (checked 2026-10-04)source ↗

Weights licences and terms

No model’s authors endorse these results, and no adapted weights or LoRA deltas were kept or shared.

Notes on these rows

Beside the core matrix

EEGPT, frozen

EEGPT ran in the same runs as the published LaBraM and CBraMod rows above, with only the encoder swapped: the same windows, people, folds, ridge head and scoring.

Standard CCA
57.6% (51.8%–63.5%)
Spectral ridge
48.2% (43.1%–53.3%)
LaBraM
12.9% (11.2%–14.6%)
CBraMod
27.6% (24.1%–31.3%)
EEGNet
44.1% (38.6%–49.6%)
EEGPT
17.3% (15.5%–19.2%)
Balanced accuracy under this protocol. Grey: the released rows above; rust: EEGPT. Dot: the estimate; line: 95% interval; dashed line: chance level.
EncoderTraining modeBalanced accuracyMacro F1ChannelsPeoplePretraining exposure
EEGPTFoundation modelFrozen encoder + ridge head17.3%15.5%–19.2%0.144470not in the authors' published pretraining list (checked 2026-10-12)source ↗

Footnotes to this row

  1. For context: BETA is not in EEGPT’s published pretraining list, but the Tsinghua 40-target SSVEP benchmark (Wang et al., 2017) is, as TSU. BETA’s authors describe BETA as an extension of that benchmark, from the same group with the same 40-target layout and its own recordings; whether anyone took part in both is not stated.
  2. Every core window is shorter than EEGPT’s 4-second pretraining window: 1 or 2 seconds, and sleep as fifteen 2-second segments. The encoder computes each 0.25-second patch the same way at any length; a shorter window gives fewer patches to average.
  3. The readout is the site’s fixed probe on the frozen summary tokens, as for the published LaBraM and CBraMod rows: ridge (alpha 100) on 2,048 pooled values, and on idle a per-person logistic head. It is not the authors’ downstream probe, a learnable spatial filter with a linear head, and the windows are fed without the average reference EEGPT was pretrained with.

Against the published rows

Each row of the table above that experiments.json holds, by whether its 95% interval and EEGPT’s overlap (no multiplicity correction):

EEGPT’s exposure is read from its authors’ published pretraining list, checked on 2026-10-12, as for the further encoders. Its pretraining corpus: Five public datasets, as the paper’s Table 1 lists them: PhysioMI (PhysioNet motor imagery and execution), HGD, TSU (the Tsinghua 40-target SSVEP benchmark), SEED and M3CV; 58 electrodes, 256 Hz, millivolts, average reference, 4-second windows.

Licence and terms

Frozen-probe comparison

LaBraM at Scale and REVE Small, frozen

Six LaBraM at Scale encoders and REVE Small’s encoder in the same frozen recipe as the rows above: the same windows, people, folds, head and scoring, with no random-initialization control.

Balanced accuracy with its 95% interval, and macro F1, frozen encoders.
EncoderBalanced accuracy (95% interval)Macro F1Exposure
LaBraM at Scale · Quark ladder
Quark-BLocal Ubuntu / CPU27.8%24.0%–31.9%0.261—
Quark-LLocal Ubuntu / CPU28.0%24.0%–32.2%0.259—
Quark-HLocal Ubuntu / CPU26.2%22.3%–30.3%0.244—
Quark-G†Local Ubuntu / CUDA26.8%22.8%–31.1%0.255—
LaBraM at Scale · Atom-L and Molecule-L
Atom-LLocal Ubuntu / CPU28.0%24.3%–31.8%0.251—
Molecule-LLocal Ubuntu / CPU28.9%25.1%–33.0%0.265—
REVE Small · early checkpoint (epoch 15 of 200)
REVE SmallLocal Ubuntu / CPU35.9%32.0%–40.0%0.334—

† Quark-G: Run on Local Ubuntu / CUDA; its step is read against a GPU re-run of Quark-H and includes the probe's input width doubling from 800 to 1600 under one fixed penalty (see the topic page).

Unless a cell is flagged, its dataset is not in that collection’s published pretraining list (the LaBraM at Scale pretraining manifest at faa387d9, checked 2026-11-05); REVE Small’s is read from the REVE corpus list (checked 2026-10-04).

The Quark ladder’s paired differences across protocols, the Quark-G step among them, are on “Does pretraining help EEG foundation models like LaBraM and CBraMod?”.

Terms: LaBraM at Scale’s code and weights under MIT (Pan-Junyu/LaBraM-at-Scale @ a0b0ce27); REVE Small under the REVE Responsible Use License v1.0 (reve-small @ 3565bdcb), aggregate scientific results only. No weights are distributed.

Limits

Near-floor scores are not ordered reliably between the 8- and 4-electrode subsets. Electrode subsets from laboratory recordings do not validate a physical low-channel cap. Prompted SSVEP does not measure idle false activations. Single-seed results; pretraining overlap unknown.

On “pretraining overlap unknown”: LaBraM’s and CBraMod’s exposure was checked on 2026-10-04 against their authors’ published pretraining lists. Pretraining exposure ↓

The protocol, step by step

  1. Seven participant-disjoint folds: train on 60 people, test on ten. All four blocks stay with their participant.
  2. Two seconds from stimulus onset; no visual-latency shift. Source data were already zero-phase filtered. Additional 6–80 Hz filtering applies to each selected window separately.
  3. Microvolt units are inferred from an independently documented loader, not explicitly stated in the author MAT description. Inconsistent phase metadata are unused by all methods.
  4. Standard CCA uses known frequencies and three harmonics without training labels. Frozen encoders use training-only standardized ridge heads (alpha 100). EEGNet trains from scratch for 20 epochs with one seed (20260912).
  5. Electrodes: POZ, O1, OZ, O2.
  6. Uniform-guessing reference: 2.5%. Descriptive 95% intervals resample participants; training sets overlap across folds.
  7. No cross-task overall ranking, model fine-tuning optimum or hardware benchmark is claimed.

Stability

One fixed seed and training budget; multi-seed sensitivity pending.

Pretraining exposure

Unknown unless explicitly documented; no unseen-pretraining claim.

Checked 2026-10-04. LaBraM: not in the authors' published pretraining list (checked 2026-10-04) source ↗; CBraMod: not in the authors' published pretraining list (checked 2026-10-04) source ↗. The released sentence above predates this check. Further encoders: the exposure column of their table above → · EEGPT: its own section above →

Notes on the methods

Model terms

Source and licence

BETA

Credit Bingchuan Liu et al. · BETA: A Large Benchmark Database Toward SSVEP-BCI Application (2020), doi:10.3389/fnins.2020.00627. Figshare 12264401 v3; mirror Bingchuan/BETA.

Licence CC BY 4.0 ↗

Dataset record ↗ · Every result on this dataset →

The figures here are aggregate measurements computed by BCI Report under the licence above; the data remain their creators’.

Permitted scope Personal noncommercial research; aggregate results only

Privacy Only cohort aggregates are published here: no recording, no participant identifier, no per-person score. The full review note is in the protocol JSON ↓

Public-data register note Eligible only under the stated personal, research-led, noncommercial operation. Any ads, sponsorship, fees, or use directed toward commercial advantage requires fresh review or permission.

Rights reviewed · against figshare.com ↗ · doi.org ↗

Reproducibility record

Protocol id
beta-ssvep-2s-posterior4and8-subject7fold-v1/posterior4
Dataset release
Hugging Face mirror of BETA database, Figshare record 12264401 v3 · mirror d4290c0200db8a104e0f557349dc49f90ba79506 · upstream Figshare version 3, 2022-06-15
Hardware
Apple M5 / MPS and CPU
Scoring stage sum
153.9 s · may include accelerator waiting
Audit record SHA-256
ccddf911864b8471f488e46cae45a3651369dae1134afcdeaede68bdfcc31950
Summary SHA-256
547a35763f7bca10a65c7b44c2f8c46af290159c692d237e92cd682fc21127a6
Protocol SHA-256
dcd1d2bf4dbb46b7db8c4562623448633cde4641fa372c90f25ba9d84012c2f0

Rows of core-matrix-update-20261106

FBCCA on beta-8ch and beta-4ch

Protocol SHA-256
e4aa044b2cae88f9fe7815c4ab4e83d79ff740b1c6525e046ca86f45cbe7a698
Audit record SHA-256
66b5815b8c42bc9383af7db706a67a12fddb21c99448b36668ca74203090458e
Hardware
Local Ubuntu / CPU, training-free
Row intervals
participant bootstrap, 10,000 draws
Paired-difference intervals
paired participant bootstrap, 10,000 draws

ShallowFBCSPNet and Deep4Net under the matrix recipe

Protocol SHA-256
a216bfac4ce6dd11c63d499b58bc93aebb89025168911b5d7d7fe265a866da4c
Audit record SHA-256
f5a1c3dab4a7e265fa3413ada48edc89b9fd4ac98ab7dc0d0f9279761e7e0a9e
Hardware
Apple M5 / MPS
Row intervals
participant bootstrap, 10,000 draws
Paired-difference intervals
paired participant bootstrap, 10,000 draws

One training run per cell with the matrix seed and the matrix recipe: AdamW, 20 epochs (sleep 10), no schedule, no early stopping. This is the recipe of the EEGNet cells; it is not tuned for any network and it is not the original papers' training. Intervals describe variation across people, not across training runs.

Downloads

This protocol's rows in core-matrix-update-20261106 · CSV ↓ · Core matrix: rows run under its exact protocols · JSON ↓

Other protocols

All protocols → · The core matrix on the home page → · All datasets → · All methods →

Cite this page

BCI Report (2026). SSVEP · 4 channels on BETA. https://bci.report/protocols/beta-4ch/

Figures from releases core-matrix-update-20261106 (2026-11-06), logpower-ridge-update-20261106 (2026-11-06), foundation-checkpoints-update-20261106 (2026-11-06), eegpt-core-update-20261013 (2026-10-13), foundation-models-update-20261004 (2026-10-04), research-preview-20260920 (2026-09-20). Cite the upstream dataset as well: its credit is on this page.

Every release is archived on Zenodo: doi:10.5281/zenodo.23123296. BibTeX for the site and its releases → · CITATION.cff ↗