pith. sign in

arxiv: 1907.07232 · v1 · pith:2ZKX6MVFnew · submitted 2019-07-16 · 💻 cs.HC · eess.SP

A Novel Slip-Kalman Filter to Track the Progression of Reading Through Eye-Gaze Measurements

Stephen Bottos , Balakumar Balasingam This is my paper

Pith reviewed 2026-05-24 20:31 UTC · model grok-4.3

classification 💻 cs.HC eess.SP
keywords eye trackingKalman filterreading progressiongaze datahuman-computer interactiontext readingslip filter
0
0 comments X

The pith

A Slip-Kalman filter tracks reading progression from noisy eye-gaze data of inexpensive devices.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a method for tracking how eyes progress through text on a computer screen using measurements from affordable eye-tracking equipment. It relies on a newly designed Slip-Kalman filter that accounts for the way gaze slips from one line to the next. This setup aims to determine which lines were read or skipped and to calculate the time spent on each line. A sympathetic reader cares because it offers a practical way to study reading patterns without costly specialized hardware. The claim is supported by testing the filter on eye-tracking recordings from 25 pages.

Core claim

The authors establish that their novel Slip-Kalman filter can track the progression of reading by processing eye-gaze data, allowing the identification of read and skipped lines as well as time spent per line, and they demonstrate this capability using data collected from a commercial desk-mounted eye-tracking device across 25 pages.

What carries the argument

The Slip-Kalman filter, a state estimator custom-designed to model the forward slip of gaze position along lines of text while rejecting measurement noise.

If this is right

  • The approach identifies lines of text that were read or skipped during a reading session.
  • It estimates the duration spent on each line based on gaze data.
  • The filter operates effectively with output from low-cost commercial eye-trackers.
  • Its performance is shown on a dataset of 25 pages of eye-tracking recordings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This technique could enable large-scale studies of digital reading habits using widely available hardware.
  • Extensions to other sequential visual tasks, such as following diagrams or code, appear possible.
  • Combining the filter with measures of comprehension could reveal links between gaze patterns and understanding.

Load-bearing premise

The custom Slip-Kalman filter accurately converts the noisy signals from commercial eye-trackers into correct line-by-line reading records without needing extra checks against actual reading behavior.

What would settle it

Running the filter on eye-gaze data where the reader is instructed to follow a specific sequence of lines and then checking if the output matches the instructed sequence would reveal if the tracking is accurate.

Figures

Figures reproduced from arXiv: 1907.07232 by Balakumar Balasingam, Stephen Bottos.

Figure 1
Figure 1. Figure 1: Tracking eye-gaze while reading using normal Kalman filter. The standard Kalman filter is unsuitable for use with eye-gaze data collected during a reading activity, due to the presence of very pronounced over-estimation at each line-change. noted that at the end of each line, the drastic change in state results in over-estimation of the true position. After a short amount of time, somewhere around mid-line… view at source ↗
Figure 2
Figure 2. Figure 2: Possible indicators of a new line.] Both NIS and the estimated velocity were candidates for new line indicators. However, the velocity indicator simply outperforms NIS as indicator of a new line while reading. A summary of the proposed Slip-KF is given in Algorithm 2. The Slip-KF monitors the estimated velocity at each instant, checking it against a pre-defined threshold. If this threshold is exceeded, rat… view at source ↗
Figure 3
Figure 3. Figure 3: shows the result of the proposed Slip-KF while reading a sample page of the above mentioned experimental data. This figure must be viewed in comparison to [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Line detection accuracy. The line detection accuracy of the proposed method is between 97% and 98% [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Comparison between measured and estimated x-coordinates. Three full sample pages of real data are shown, plotting each measured and estimated x-coordinate according to their index for comparison. Through examination, one can observe that the Slip-KF estimation procedure is highly effective in terms of noise elimination. that the Slip-KF estimation procedure is highly effective in terms of noise elimination… view at source ↗
read the original abstract

In this paper, we propose an approach to track the progression of eye-gaze while reading a block of text on computer screen. The proposed approach will help to accurately quantify reading, e.g., identifying the lines of text that were read/skipped and estimating the time spent on each line, based on commercially available inexpensive eye-tracking devices. The proposed approach is based on a novel Slip Kalman filter that is custom designed to track the progression of reading. The performance of the proposed method is demonstrated using 25 pages eye-tracking data collected using a commercial desk-mounted eye-tracking device.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript proposes a novel Slip-Kalman filter custom-designed to track eye-gaze progression while reading blocks of text on a screen. The approach aims to identify read or skipped lines and estimate per-line dwell times using data from inexpensive commercial eye-trackers. Performance is demonstrated solely on 25 pages of eye-tracking data collected with a desk-mounted commercial device.

Significance. If the filter could be shown to produce accurate line-level reading metrics from noisy commercial eye-tracker output, the work would provide a practical, low-cost method for quantifying reading behavior in HCI applications. The custom filter design targets a specific use case not directly addressed by standard Kalman variants.

major comments (1)
  1. [Abstract] Abstract: the central claim that the method 'accurately quantify[s] reading' (identifying read/skipped lines and estimating time per line) is unsupported; the demonstration on 25 pages supplies no quantitative metrics, error bars, baselines, ground-truth annotations, or exclusion criteria against which accuracy can be evaluated.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and the opportunity to clarify our manuscript. We address the single major comment below and are willing to revise the abstract to ensure claims are properly supported by the presented evidence.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that the method 'accurately quantify[s] reading' (identifying read/skipped lines and estimating time per line) is unsupported; the demonstration on 25 pages supplies no quantitative metrics, error bars, baselines, ground-truth annotations, or exclusion criteria against which accuracy can be evaluated.

    Authors: We agree that the abstract's phrasing overstates what the current demonstration supports. The manuscript shows the Slip-Kalman filter output on 25 pages of eye-gaze data from a commercial tracker but does not include quantitative accuracy metrics, error bars, baseline comparisons, or ground-truth line annotations. We will revise the abstract to remove the word 'accurately' and rephrase the central claim to 'track the progression of reading' and 'provide a means to identify read or skipped lines and estimate per-line dwell times,' aligning the language with the qualitative demonstration actually provided. If space permits in a revision, we can also add a brief limitations paragraph noting the absence of quantitative validation. revision: yes

Circularity Check

0 steps flagged

No circularity: custom filter design independent of fitted inputs or self-citations

full rationale

The abstract and available description present the Slip-Kalman filter as a novel, custom-designed component for mapping eye-gaze to reading progression. No equations, parameter-fitting steps, or self-citations are shown that would make any claimed output equivalent to its inputs by construction. The demonstration uses raw commercial eye-tracker data, but this is an external validation issue rather than a reduction of the derivation itself. The central claim remains a proposed method whose performance is asserted separately from any definitional loop.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

Review is based solely on the abstract; no equations, parameter tables, or model derivations are visible, so the ledger is necessarily incomplete.

axioms (1)
  • domain assumption Commercial desk-mounted eye trackers produce data suitable for line-level reading progression tracking when processed by an appropriate filter.
    Implicit in the claim that the proposed filter will accurately quantify reading from such devices.
invented entities (1)
  • Slip-Kalman filter no independent evidence
    purpose: To model eye-gaze progression and slips between text lines during reading.
    Introduced in the paper as the core technical contribution.

pith-pipeline@v0.9.0 · 5622 in / 1208 out tokens · 23185 ms · 2026-05-24T20:31:25.282780+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

16 extracted references · 16 canonical work pages · 1 internal anchor

  1. [1]

    gazept gazepoint eye tracker website,

    “gazept gazepoint eye tracker website,” https://www.gazept.com/, ac- cessed: 2018-20-11

    work page 2018

  2. [2]

    Eye tracking of attention in the affective disorders: A meta-analytic review and synthesis,

    T. Armstrong and B. O. Olatunji, “Eye tracking of attention in the affective disorders: A meta-analytic review and synthesis,” Clinical psychology review, vol. 32, no. 8, pp. 704–723, 2012

    work page 2012

  3. [3]

    Bar-Shalom, X

    Y . Bar-Shalom, X. R. Li, and T. Kirubarajan, Estimation with applica- tions to tracking and navigation: theory algorithms and software . John Wiley & Sons, 2004

    work page 2004

  4. [4]

    An Approach to Track Reading Progression Using Eye-Gaze Fixation Points

    S. Bottos and B. Balasingam, “An approach to track reading progression using eye-gaze fixation points,” arXiv preprint arXiv:1902.03322, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1902

  5. [5]

    Tracking the progression of reading through eye-gaze measure- ments,

    ——, “Tracking the progression of reading through eye-gaze measure- ments,” in 22nd International Conference on Information Fusion. IEEE, 2019, pp. 1–8

    work page 2019

  6. [6]

    Eye movements and word skipping during reading revisited

    D. Drieghe, K. Rayner, and A. Pollatsek, “Eye movements and word skipping during reading revisited.” Journal of Experimental Psychology: Human Perception and Performance, vol. 31, no. 5, p. 954, 2005

    work page 2005

  7. [7]

    Long short-term memory,

    S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997

    work page 1997

  8. [8]

    E. B. Huey, The psychology and pedagogy of reading . The Macmillan Company, 1908

    work page 1908

  9. [9]

    Slip-gear

    J. W. Hughes, “Slip-gear.” Feb. 22 1910, uS Patent 950,290

    work page 1910

  10. [10]

    Visual fixation patterns during viewing of naturalistic social situations as predictors of social competence in individuals with autism,

    A. Klin, W. Jones, R. Schultz, F. V olkmar, and D. Cohen, “Visual fixation patterns during viewing of naturalistic social situations as predictors of social competence in individuals with autism,” Archives of general psychiatry, vol. 59, no. 9, pp. 809–816, 2002

    work page 2002

  11. [11]

    Reading type classification based on generative models and bidirectional long short-term memory,

    S. S. Mozaffari, F. Raue, S. D. Hassanzadeh, S. Agne, S. S. Bukhari, and A. Dengel, “Reading type classification based on generative models and bidirectional long short-term memory,” 2018. 6

    work page 2018

  12. [12]

    Looking you in the mouth: abnormal gaze in autism resulting from impaired top- down modulation of visual attention,

    D. Neumann, M. L. Spezio, J. Piven, and R. Adolphs, “Looking you in the mouth: abnormal gaze in autism resulting from impaired top- down modulation of visual attention,” Social cognitive and affective neuroscience, vol. 1, no. 3, pp. 194–202, 2006

    work page 2006

  13. [13]

    Maximizing read- ing: pattern analysis to describe points of gaze,

    R. Paeglis, K. Bagucka, N. Sjakste, and I. Lacis, “Maximizing read- ing: pattern analysis to describe points of gaze,” in Mathematics of Data/Image Pattern Recognition, Compression, and Encryption with Applications IX , vol. 6315. International Society for Optics and Photonics, 2006, p. 63150R

    work page 2006

  14. [14]

    Understanding eye movements in reading,

    K. Rayner, “Understanding eye movements in reading,” Scientific Studies of Reading, vol. 1, no. 4, pp. 317–339, 1997

    work page 1997

  15. [15]

    Louis ´emile javal (1839–1907): The father of orthop- tics,

    G. Roper-Hall, “Louis ´emile javal (1839–1907): The father of orthop- tics,” American Orthoptic Journal , vol. 57, no. 1, pp. 131–136, 2007

    work page 1907

  16. [16]

    Attentional disengagement predicts stress recovery in depression: An eye-tracking study

    A. Sanchez, C. Vazquez, C. Marker, J. LeMoult, and J. Joormann, “Attentional disengagement predicts stress recovery in depression: An eye-tracking study.” Journal of Abnormal Psychology , vol. 122, no. 2, p. 303, 2013

    work page 2013