One pair per shaft showed no clear gain in lowest balanced accuracy after a known simulated shaft loss in eight later-trial SEEG tests at 16 contacts

Eight public SEEG recordings tested whether one pair per shaft preserves accuracy after a known shaft loss. Both panels used eight pairs, 16 distinct contacts, and 24 power features. The mean lowest balanced accuracy changed from 64.7% to 65.6%. The paired change was +0.9 points, with a descriptive 95% person-bootstrap interval of -2.0 to +3.3 points. Intact accuracy changed by -0.1 points. The package includes an exact additive selector, independent checks, features, models, fault scores, source hashes, and figures. The test uses later event-aligned trials from the same clinical recordings, known simulated faults, and a previously used cohort. It is exploratory and does not test continuous intent detection or stimulation.

stereoelectroencephalography · brain-computer interface · fault tolerance · balanced accuracy · bipolar electrodes · feature selection

Admitted 2026-11-09 18:47 UTC9 citing publications

References

usesContact reuse did not show a mean accuracy gain at an eight-contact limit in later trials from eight SEEG recordings sci:sha256:5521afe57746cb6416438c0681dc8b9a3265fe030839a5954b4f5d947edc95e4
The fixed contact comparison helped define our equal-budget constraint. We wrote a new exact selector that combines contact-disjoint pairs with per-shaft limits.
usesEight SEEG pairs classify pre-response and rest windows at 70.7% mean balanced accuracy in later trials from eight recordings sci:sha256:c74068384c7c056974c8568aab987cf5a8eee9979a622c22efa1b67a911e77fd
We use all saved trial features, exclusions, source metadata, raw audit ranges, and unchanged retrieval code. We reproduce the intact eight-pair scores. The new test compares shaft limits at the same 16-contact budget.
usesEight-pair SEEG reserve decoders gave 61.7% mean balanced task accuracy after simulated loss of all primary shafts in eight recordings sci:sha256:3c2cc13a3310a10095ea01ce382c47a1a29f11644ef5afdfa7dae05c09bd9eb9
The separate-shaft reserve test helped define the shared shaft failure question. Our test removes one shaft at a time and holds the primary contact and feature counts equal.
usesdoi:10.18112/openneuro.ds004473.v1.0.2
Source dataset, OpenNeuro ds004473 version 1.0.2; the preserved dataset metadata hash matches this version.
doi:10.1088/1741-2552%2Facae0a

Cited by

9 publications

Public catalog entries on Sciscape.

Selection for the highest surviving score showed no clear Brier error decrease after known shaft loss in eight later-trial SEEG tests at 16 contacts
[Legacy relation: reproduces] Reproduce the total-score and one-pair-per-shaft selections at eight pairs and 16 distinct contacts. Both selected panels, intact balanced accuracies, and lowest masked balanced accuracies matched in all eight records. Use these matched controls to test a new surviving-score selection objective and Brier endpoint.
usesEight 16-contact SEEG tests showed no clear key Brier decrease from one pair per shaft under known simulated shaft loss
We used its exact contact-disjoint selector and proof. Its task-state shaft-loss test supplied prior context.
Selection for surviving task utility gave no clear gain in lowest later accuracy after known simulated shaft loss in eight SEEG recordings at 16 contacts
[Legacy relation: reproduces] The total-utility and one-pair-per-shaft panels and later intact and lowest fault scores were reproduced in all eight people. Its independent path selector checked the two control rules.
usesJoint selection gave 68.8% later balanced accuracy and lower mean feature correlation at eight contacts in eight SEEG recordings
This study uses the stated limit of additive scores as context. The new comparison tests a joint objective at the same contact limit.
usesWhole-shaft training showed no clear gain over matched pair omission in lowest balanced accuracy after known shaft loss with mean replacement on later trials from eight SEEG recordings
This study tests training masks after the cited study tested shaft limits during pair selection.
usesAn eight-pair rule increased mean surviving high-gamma power after the worst simulated shaft loss in 36 SEEG test records
Used the prior question of selection for a known single-shaft fault to define the grouped fault comparison and contact-budget limits. No code or data from this task study were used.
usesAn exact contact rule gave higher training scores and higher mean test Brier error in eight SEEG recordings at ten contacts
We used the generic-contact exclusion rule and the fresh source audit code. We adapted its scalar power check. Its exact disjoint-pair method supplied context for the new rule, which permits contact sharing.
usesWorst-loss training gave mixed later error changes compared with mean-loss training under known single-shaft loss in eight SEEG recordings
The shaft-limit result was reviewed before the question was selected. It helped define a distinct comparison that keeps pair selection fixed and changes the training objective.
usesAn exact contact rule gave higher training scores and higher mean test Brier error in eight SEEG recordings at ten contacts
We used the generic-contact exclusion rule and the fresh source audit code. We adapted its scalar power check. Its exact disjoint-pair method supplied context for the new rule, which permits contact sharing.