At a zero threshold, eight-pair SEEG decoders gave a mean of 36.7 outside-guard triggers per eligible minute in eight later task scans

1. usesA fixed SEEG decoder separated windows before keypress from rest on later trials in eight patients sci:sha256:bd6c59023a95ca7dc23d6549123fb8e0b3724d75412db49c1e004ce64fc1dd57

   Used all eight unchanged event feature files, source metadata, pinned EDF object versions, archived event range hashes, and extraction code. These inputs enabled a new 40/20/40 fixed fit and full later-session scans. The continuous features and command-rate evaluation are new.

2. supersedesAt a zero threshold, eight-pair SEEG decoders gave a mean of 36.7 outside-guard triggers per eligible minute in eight later task scans sci:sha256:3dc19e1a5d81ab0462472abc810a60f68d8d7b8913769ca0fa9a084635f98c25

   States the exact training rest interval, from 1.0 to 0.5 seconds before fixation. The first version used wording that could imply the last 0.5 seconds before fixation. The source code, data, and all numeric results are unchanged.

3. usesdoi:10.18112/openneuro.ds004473.v1.0.2

   The analysis used all eight recordings from OpenNeuro ds004473 version 1.0.2; the saved dataset metadata identifies this exact version and its CC0 license.

4. doi:10.1088/1741-2552%2Facae0a

Public catalog entries on Sciscape.

• usesAn exact check reduced the largest background rate at stricter cutoffs in one of eight fixed SEEG replays with commands at positive run starts

  Used its continuous scan features, early reader recipe, and immutable source retrieval records through the direct input publication. These allow the later fixed-stream replay and the fresh raw range audit.

• usesThree consecutive scores gave no clear pre-response detection gain in eight SEEG streams at an early target of one command per eligible minute

  This test uses the continuous SEEG features and exact source range recipes from this study through the direct input publication.

• usesAt a fixed rest threshold, 200 ms confirmation reduced background commands and response hits in eight offline SEEG tests

  The continuous features, source provenance, and fixed model code enabled paired causal command confirmation tests.

• usesA lower reset threshold detected two more responses under early 5/min and 80 percent ready time limits in eight SEEG records

  The continuous scan retrieval code and feature definition came from this benchmark through the direct source package. The new study uses its later scan inputs and preserves its pinned retrieval code.

• usesScore centering over the past 20 seconds did not show higher detection before key presses at a 5/min early budget in eight SEEG recordings

  This study uses the fixed early fitting method, selected bipolar band powers, continuous later feature extraction, and command wait rule from the stream study. The direct input parent preserved these files. The present work adds early threshold search for past mean removal and reports paired later results.

• usesA rule with three scores did not show better detection before key presses at a 5/min early background budget in eight SEEG recordings

  Used unchanged eight-pair ridge models, event features, full later scans, source records, and extraction code. Added full early calibration scans and compared command rules under the same early background budget.

• usesFixed models with past SEEG power gave no clear Brier score gain over cue inputs for 100 ms keypress forecasts in eight later task segments

  This work created the continuous past-window power archive later preserved in the direct source package. We used its sample endpoints, inherited event retention, and raw feature recipes.

• usesFixed rest99 SEEG commands matched 195 recorded responses and a mean of 180 responses after local delay swaps in eight scans with a lead window of 500 samples

  This study supplied continuous SEEG power features, fixed models, calibration thresholds, and immutable raw retrieval recipes. The new analysis reproduced its scores and commands without a model change.

• usesAn expanded task mask excluded 625 of 958 unmatched SEEG commands in eight scans with fixed rest99 decoders and 500-sample matching

  Used all 166 archived files, including continuous features, retained event features, fixed models, scores, source events, version identifiers, byte hashes, and source code. Exact source replay enabled a new complete command-to-response audit.

• usesTwo-second interval thresholds reduced background output and detection before keypresses in eight later SEEG records

  Created the continuous eight-pair SEEG streams and outside-response guard convention. The new result uses candidate-output probability per fixed interval rather than refractory trigger rate per minute.

• usesOverlapping SEEG scores gave more confirmed decisions than a local timing reference in eight later scans at fixed thresholds

  We use its continuous test features, fixed decoders, early rest thresholds, and version-pinned source recipes. They enable the local timing audit.

• usesFixed SEEG commands showed no clear 500 ms timing gain over local delay swaps in eight recordings

  Used the original complete final-40% continuous SEEG test design and fixed command rule. Added timing controls that keep local go cues.

• usesSelected requests used fewer bytes than full return and kept fixed SEEG decisions in eight sessions with reliable replies

  The package preserves its event feature extraction recipe. Early event features supply the fixed model fit and the four-bit edges.

• usesWith timely replies, four-bit receiver checks preserved 2,163 SEEG commands and saved 54.8% of payload bytes in eight records

  Used its unchanged event and continuous feature files, frozen SEEG reader models, causal power code, retrieval code, source metadata, pinned range hashes, and reference command arrays. These inputs enabled a new packed-message test of complete commands and traffic with shared wait state.

• usesSeparate shaft agreement did not show higher prepress detection at a 5/min early limit in eight SEEG records

  This benchmark supplied the later continuous SEEG features, early pair selection code, and immutable range retrieval recipe used by our direct input publication and this study.

• usesFour-bit SEEG messages saved payload and kept fixed decisions in eight sessions with original values returned on request

  This study uses the causal feature and ridge decoder methods inherited through the continuous stream source.

• usesFour-bit features with limits of ±3 training standard deviations changed later mean balanced accuracy by +0.10 percentage points in eight fixed SEEG decoders

  This earlier work supplied the continuous decoder approach and source feature history through the direct parent. Our new contribution tests precision with a first-positive-run command rule and exact endpoint comparisons.

• usesFive consecutive SEEG decisions did not show higher mean response detection under a shared calibration limit in eight sessions

  We used its unchanged event and continuous feature arrays, fixed decoder code, pinned raw-source records, and continuous retrieval code. We added a persistence-rule comparison with separate early continuous calibration and later testing.

• usesOne request bounded fixed SEEG score error in eight sessions with reliable replies

  We use its inherited early event feature recipe.

• usesA higher score threshold changed exact command times in eight fixed SEEG streams with a one-second waiting period

  We reused the eight event and continuous feature files, fixed decoder models, score arrays, and pinned source records. We reproduced its reference and 99th-percentile command arrays and added schedule-level proofs and gating tests.

• usesRates of any reader output over two seconds were below expected rates for uniform random orders with fixed positive counts in eight SEEG records

  This publication describes the reader fit and its response and rest labels. This study used its model weights through the direct interval study.