Methodology

Reviewed by TypeFuel Lab. Last updated June 2, 2026. Research Preview methodology, not validation results.

Can cognitive fatigue be measured from computer work rhythm?

Can cognitive fatigue show up in how your work rhythm changes at the computer? TypeFuel is testing that question with private timing patterns and quick self-reports during real work.

TypeFuel is testing whether cognitive fatigue at the computer can be modeled from private desktop timing patterns and short self-reported check-ins. In v0.1, the visible learning gauge uses keyboard timing, correction patterns, and rhythm variability compared with each person's own baseline. The model does not compare users against one another, does not read typed content, and does not treat the gauge as a validated fatigue score. Check-ins using the 1-7 Samn-Perelli scale provide the self-reported reference point. The validation question is whether TypeFuel's signal predicts those check-ins better than simple baselines like time of day, previous check-ins, and keyboard rhythm alone. Published work on keystroke dynamics, typewriting performance, and keyboard/mouse fatigue detection makes the direction plausible, but TypeFuel will only claim cognitive fatigue measurement after the Research Preview meets its thresholds with real users.

The v0.1 gauge is conservative. It starts with keyboard timing, corrections, and rhythm variability compared with your own baseline. Cursor rhythm is research-only unless validation shows it adds value.

What the research says

These studies make the premise plausible. They do not validate TypeFuel. Research Preview exists to test whether these signals work in our product, with our privacy constraints, and with real users.

These papers are research context, not TypeFuel validation results. The Research Preview tests whether this direction holds in TypeFuel, with TypeFuel's privacy constraints and real desktop work data.

Core evidence we rely on

• de Jong et al. (2020). Real-life office typing and mental fatigue work supports the idea that typing behavior can change over the workday. TypeFuel uses it to justify testing correction patterns and inter-key timing against personal baseline, not as TypeFuel validation. Read the PLOS ONE paper →
• Pimenta, Carneiro, Novais, and Neves. Prior work on mental fatigue from keyboard and mouse interaction patterns is direct precedent for testing whether private computer interaction patterns can carry fatigue-relevant signal. Read the Springer paper →
• Acien et al. (2022). Keystroke dynamics as a mental-fatigue marker candidate supports the choice to start with typing rhythm and correction patterns. We do not claim TypeFuel achieves their reported performance. Read the JMIR paper →
• Samn-Perelli Fatigue Scale. The 1-7 Samn-Perelli scale is the sole self-reported ground truth during Research Preview. It is subjective fatigue, not an objective medical measure.

What does TypeFuel measure?

TypeFuel computes per-minute aggregates. Raw typed content and raw work content are not stored.

Scored signal: keyboard timing and correction patterns

Only these passive features affect the v0.1 learning gauge:

1. Backspace rate: backspaces divided by total keydowns. Higher personal z-score means more correction friction.
2. Median inter-key interval inside typing bursts: median time between consecutive keydowns inside bursts with no gap greater than 2 seconds. Higher personal z-score means slower rhythm.
3. Coefficient of variation of inter-key interval: std(IKI) divided by mean(IKI) inside bursts. Higher personal z-score means more irregular typing rhythm.

Ground truth: Samn-Perelli check-ins

Check-ins are not passive features. They are the calibration and validation target: the self-reported reference point TypeFuel compares the learning gauge against.

Research-only metrics: captured for learning, not v0.1 score

• mouse_path_inefficiency: actual cursor path length divided by straight-line distance from movement start to click. This does not know what the user clicked on and is not target accuracy.
• direction_changes_per_trajectory: meaningful direction changes before a click, research-only.
• idle_ratio / pause rhythm: confidence and context, not direct fatigue.
• active_minute and interaction_mode: data sufficiency and context, not fatigue by themselves.

What we do not capture

TypeFuel does not capture typed content, app names, window titles, browser URLs, screen text, file names, contacts, work content, or UI targets. For mouse path inefficiency, we only use cursor movement coordinates and click position; we do not know what the click was on. Read The Deal for the plain-language data trade before preview installation.

How the learning gauge works

The visible Research Preview gauge from day 14 is keyboard-only. It uses personal z-scores from backspace rate, median inter-key interval, and IKI variability, then maps that signal to the 1-7 Samn-Perelli scale.

Your gauge is learning. It is not a validated fatigue score.

• Personal baseline first; no cross-user component.
• Mouse metrics do not move the v0.1 visible gauge.
• Check-ins adjust calibration and show divergence.
• No 0-100 public score in Research Preview.
• No diagnosis, treatment, prevention, or burnout detection.

The key validation question is whether any feature improves prediction of Samn-Perelli check-ins beyond time of day, previous check-ins, and the keyboard-only model. Only features that improve beyond the keyboard-only model should be candidates for v1.0.

Validation criteria

We will ship v1.0 only when all of the following criteria are met on the Research Preview cohort:

If any of these fail, v1.0 does not ship. We continue iterating in Research Preview and update this page with what we found. See the Roadmap for what happens before and after validation.

What we still need to prove

• A measured effect size on TypeFuel data.
• An AUC for a high-fatigue classifier.
• A reliability diagram for score calibration.
• Subgroup analyses across typing speed, age range, keyboard type, or operating system.
• A test-retest correlation on real users.
• Any individual-level accuracy claim.
• Evidence that research-only cursor metrics improve prediction beyond the keyboard-only model.

What changes at v1.0

1. The Research Preview learning gauge is replaced by a validated local score, only if the evidence earns it.
2. The feature set can expand beyond keyboard-only only when research-only cursor metrics prove incremental lift beyond the keyboard model.
3. TypeFuel runs 100% local: features extracted on-device, score computed on-device. No behavioral data leaves the user's machine.

Request the Desktop Preview

TypeFuel is coming this summer for Mac and Windows. Preview cohorts start with desktop installation, onboarding, baseline building, and short check-ins.