{"id":"e9385585-64e7-4674-bff6-dc8a540394ed","arxiv_id":"2606.12214","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":4.0,"correctness_risk":"high","formal_verification":"none","parameter_count":0,"one_line_summary":"Symbolic ML on VR game user data ranks rotation, acceleration, and low prior experience as top cybersickness causes, varying by game type and exposure duration.","lead":"This paper uses symbolic machine learning on data from 37 participants across two VR games and six protocols to rank factors like rotation and acceleration as cybersickness triggers. A smart generalist might read it to learn practical design adjustments that could reduce discomfort in VR applications.","discovery_kind":"new_application","skeptic_critique":{"model":"grok-4.3","headline":"With n=37, symbolic ML rankings of 'causes' (rotation, acceleration, experience) are likely unstable associations rather than reliable causal factors.","rationale":"The reader's weakest assumption already isolates the exact load-bearing point: small N plus causal interpretation of symbolic output. No stronger internal inconsistency appears from the abstract; the concern is statistical reliability and causal warrant, not a logical contradiction within the reported workflow.","tokens_in":1755,"tokens_out":326,"duration_ms":12524,"concrete_test":"Re-run the symbolic learner (whatever algorithm was used) on 100 bootstrap resamples of the 37 cases; report the fraction of resamples in which rotation and acceleration remain the top two factors for the flight game. If this fraction is below 70%, the reported rankings are not robust.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim asserts that symbolic ML on 37 valid samples ranks rotation/acceleration as more frequent triggers in the flight game vs. race game, with experience level and exposure duration as additional causal factors. Symbolic methods (decision lists, rule induction, etc.) applied to small observational data from two specific games and six protocols can at best surface correlations; without reported cross-validation, permutation tests, or stability analysis, top-ranked factors may be artifacts of the particular 37-participant split or game mechanics rather than generalizable causes. The leap from 'ranked by impact' to 'triggered cybersickness' therefore rests on an untested assumption that the learned rules reflect causation and generalize beyond the tested titles and sample.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The manuscript reports an experimental study applying symbolic machine learning (decision lists and rule induction) to data from 37 valid participants (out of 88 volunteers) who played a flight game and a race game under six protocols. It claims to rank causes of cybersickness, concluding that rotation and acceleration trigger symptoms more frequently in the flight game than the race game, that lower VR experience increases susceptibility (especially in the race game), and that distinct causes emerge for short- versus long-term exposures, with suggested mitigation strategies.","tokens_in":1891,"tokens_out":528,"duration_ms":13350,"significance":"If the symbolic rankings prove stable and the causal interpretation holds, the work could inform VR game design guidelines for reducing cybersickness. The use of symbolic methods offers potential interpretability advantages over black-box models, and the comparison across game types and exposure durations addresses a practical question in HCI. However, the small effective sample and absence of validation details limit immediate impact.","major_comments":[{"comment":"Abstract and Results section: the central ranking of rotation/acceleration as more frequent triggers in the flight game (versus race game) is derived from symbolic ML on only 37 valid samples with no reported cross-validation, permutation testing, or stability analysis across participant splits; without these, the rankings may reflect sampling artifacts rather than reliable associations.","section":"Abstract and Results"},{"comment":"Methods and Results: the leap from learned rules to 'causes that trigger cybersickness' and 'more prone to feel discomfort' is unsupported by any causal identification strategy, confounding controls, or comparison against classical ML feature importances with statistical tests; the paper provides no evidence that the symbolic output distinguishes causation from correlation.","section":"Methods and Results"},{"comment":"Participant recruitment: the reduction from 88 volunteers to 37 valid samples is not accompanied by analysis of selection bias, exclusion criteria effects, or power calculations, which directly affects the generalizability claim for experience level and exposure duration effects.","section":"Methods"}],"minor_comments":[{"comment":"Clarify the exact symbolic algorithms employed (e.g., specific decision-list learner or rule-induction method) and any hyperparameter choices.","section":"Methods"},{"comment":"Add a table or figure showing the top-ranked rules with their coverage and accuracy metrics on the 37 samples.","section":"Results"}],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the thoughtful and constructive comments, which have helped us clarify the scope and limitations of our work. We address each major comment below and indicate where revisions have been made to the manuscript.","responses":[{"response":"We acknowledge that the absence of explicit stability checks leaves the rankings vulnerable to sampling variability. Symbolic rule induction was chosen precisely because it can surface interpretable patterns from modest sample sizes, yet we agree that additional safeguards are warranted. In the revised manuscript we have added (i) 5-fold cross-validation of the induced rule sets and (ii) a bootstrap stability analysis across 100 random participant splits, reporting the frequency with which each top-ranked condition (rotation, acceleration, prior experience) reappears. These results are now summarized in a new subsection of Results and the corresponding tables have been updated.","revision_made":"yes","referee_comment":"[Abstract and Results] Abstract and Results section: the central ranking of rotation/acceleration as more frequent triggers in the flight game (versus race game) is derived from symbolic ML on only 37 valid samples with no reported cross-validation, permutation testing, or stability analysis across participant splits; without these, the rankings may reflect sampling artifacts rather than reliable associations."},{"response":"The referee correctly identifies that our observational design cannot support causal claims. The original wording occasionally used “causes” and “trigger” in a colloquial sense; this was imprecise. We have revised the manuscript throughout to replace such language with “associated factors,” “predictive indicators,” and “frequently co-occurring conditions.” A new paragraph in the Discussion explicitly states the correlational nature of the findings, notes the lack of randomized controls or instrumental-variable strategies, and contrasts the symbolic rules with permutation-based feature importances obtained from a random-forest baseline (now reported in an appendix). No causal identification is claimed or performed.","revision_made":"yes","referee_comment":"[Methods and Results] Methods and Results: the leap from learned rules to 'causes that trigger cybersickness' and 'more prone to feel discomfort' is unsupported by any causal identification strategy, confounding controls, or comparison against classical ML feature importances with statistical tests; the paper provides no evidence that the symbolic output distinguishes causation from correlation."},{"response":"We have expanded the Methods section with a full accounting of the 51 exclusions (motion-sickness history, incomplete sessions, technical failures, and voluntary withdrawal) together with a table comparing demographic and baseline SSQ scores between included and excluded participants. A brief discussion of possible selection effects on the experience-level findings has been added. Because the study is retrospective, formal a-priori power calculations cannot be supplied; we now report post-hoc observed power for the main contrasts and list the modest sample size as an explicit limitation in both the Abstract and Discussion.","revision_made":"partial","referee_comment":"[Methods] Participant recruitment: the reduction from 88 volunteers to 37 valid samples is not accompanied by analysis of selection bias, exclusion criteria effects, or power calculations, which directly affects the generalizability claim for experience level and exposure duration effects."}],"tokens_in":1427,"tokens_out":625,"duration_ms":13881,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The paper runs a user study on two VR games (flight and race) across six protocols, collects discomfort data, and applies symbolic ML to rank factors like rotation, acceleration, prior experience, and exposure duration. It reports that rotation and acceleration trigger more issues in the flight game, less experienced users are more affected overall, experience matters more in the race game due to greater user control, and short versus long sessions surface different triggers. They close with mitigation suggestions for each scenario.\n\nThe concrete comparison between game types and the experience/exposure distinctions are the useful parts. Those observations line up with known VR discomfort patterns and could give game designers some practical pointers on where to focus comfort tweaks.\n\nThe soft spots are the sample and the methods. Thirty-seven valid samples from 88 volunteers is small for feature ranking with symbolic techniques, and nothing in the abstract shows cross-validation, stability checks, or tests that would separate signal from noise in the rankings. The jump from ranked correlations to 'triggered cybersickness' also lacks supporting controls or statistical grounding. Selection effects from the dropped participants are not discussed.\n\nThis is narrow-scope empirical work aimed at VR game developers or HCI researchers who run small targeted studies. It does not introduce new algorithms or frameworks, so broader readers will not get much. A referee could usefully press on the validation and generalizability, but the paper is coherent enough on its own terms to deserve that step rather than a desk reject.","headline":"With n=37 and no reported validation, the symbolic ML rankings of rotation and acceleration as cybersickness triggers are likely unstable associations rather than solid causal factors.","tokens_in":2368,"tokens_out":370,"would_cite":false,"duration_ms":13264,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"Symbolic machine learning ranks rotation and acceleration as top cybersickness triggers in VR flight games compared to racing games.","keywords":["cybersickness","virtual reality","symbolic machine learning","VR games","rotation","acceleration","user experience","exposure duration"],"falsifier":"Re-running the protocols with a larger participant pool or additional game types and obtaining substantially different ranked causes for cybersickness would show the original rankings do not hold.","tokens_in":2660,"feed_emoji":"🎮","tokens_out":639,"duration_ms":23930,"temperature":0.7,"pith_summary":"The paper applies symbolic machine learning to data collected from 37 participants across two VR games and six protocols to rank factors that cause cybersickness. It finds rotation and acceleration trigger symptoms more often in the flight game, while prior VR experience matters more in the race game and causes shift between short and long sessions. This approach matters to a sympathetic reader because it moves beyond general reports of discomfort to identify concrete, game-specific contributors that could be addressed in design. The work treats the rankings as actionable for mitigation strategies tailored to exposure length and user background.","feed_headline":"Rotation and acceleration trigger more cybersickness in VR flight games","feed_subtitle":"Symbolic machine learning on two games shows experience level and exposure time also shape the main discomfort causes.","key_machinery":"Symbolic machine learning algorithms applied to user response data to estimate and rank the relative impact of factors such as rotation, acceleration, and prior VR experience on cybersickness.","core_discovery":"The authors claim that symbolic machine learning applied to participant responses from a flight game and a race game can estimate and rank the impact of potential cybersickness causes, showing rotation and acceleration as more frequent triggers in the flight game, less experienced VR users as more prone overall with the effect stronger in the race game due to its greater user control, and distinct sets of causes arising under short-term versus long-term VR exposures.","pith_inferences":["The same ranking technique could be tested on VR applications outside entertainment, such as training or education, to identify context-specific triggers.","If the game-type differences persist, VR systems might benefit from built-in adjustments that scale movement based on detected user experience and session duration.","The emphasis on controller freedom in the race game suggests that greater user agency in movement options can shift which physical factors dominate discomfort."],"forward_implications":["Rotation and acceleration should be limited in flight-style VR games to reduce the frequency of cybersickness.","Racing-style VR games require designs that accommodate users with varying levels of prior experience to limit discomfort.","Mitigation approaches must be adjusted separately for short-term and long-term VR exposure scenarios.","Symbolic machine learning offers a method to compare and prioritize causes across different VR game mechanics."],"fun_headline_variants":["Symbolic ML ranks rotation as primary VR flight cybersickness cause","Experience level modulates cybersickness in VR race versus flight","Long term VR exposure yields different discomfort causes than short","Acceleration triggers more cybersickness in VR flight than race games"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"The 37 valid samples from two games allow symbolic machine learning to identify true causal factors of cybersickness rather than correlations, and the findings extend beyond these specific titles and protocols.","fun_headline_variants_meta":{"raw":{"variants":["Symbolic ML ranks rotation as primary VR flight cybersickness cause","Experience level modulates cybersickness in VR race versus flight","Long term VR exposure yields different discomfort causes than short","Acceleration triggers more cybersickness in VR flight than race games"]},"model":"grok-4.3","cost_usd":0.006243,"raw_usage":{"total_tokens":2863,"prompt_tokens":678,"num_sources_used":0,"completion_tokens":63,"cost_in_usd_ticks":62428000,"prompt_tokens_details":{"text_tokens":678,"audio_tokens":0,"image_tokens":0,"cached_tokens":64},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2122,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":678,"tokens_out":63,"duration_ms":12490,"temperature":1.0,"reasoning_tokens":2122,"cache_read_input_tokens":64,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-06-27T08:17:34.101830+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"Re-running the protocols with a larger participant pool or additional game types and obtaining substantially different ranked causes for cybersickness would show the original rankings do not hold.","supporting_citations":[],"review_version":1}