A right answer is not always a usable exit.

My solo-authored methodological paper asks whether adaptive neural networks respond to computational depth or surface difficulty. Its central distinction is between an early prediction that happens to be correct and a stopping decision supported by the information the controller has.

Available information comes first.

An evaluator with the answer can recognize a lucky early guess. A deployable stopping controller cannot use that future knowledge. The research audits that information boundary.

Controlled reasoning tasks

The manuscript investigates adaptive neural computation through controlled reasoning tasks. The public page explains the question and its information constraints while the full study is under review.

Submission status

Submitted to the AISTATS 2027 main track. The manuscript and detailed numerical results stay private during review; no acceptance is implied.

The concept illustration above explains the research question; it is not a published finding or a reproduction of a private paper figure.

Compute savings need an attainable stopping rule.

The broader motivation is to separate savings that look possible with hindsight from savings a model can choose in operation. This is a methodological question about evidence available at decision time, rather than another applied classification project.

Learning orders. Bounds decide.

ExactPHQ asks a narrow question: can fewer PHQ-9 items determine the same binary threshold class as all nine? A learned policy chooses what to ask next. A deterministic certificate alone decides when to stop.

These are retrospective question counts and exact fixed-response score classification, not clinical equivalence.

The stopping certificate

For answered items, L is the observed sum. With m unanswered items scored 0–3, U = L + 3m. At T = 10, stop positive if L ≥ T; stop negative if U < T. Otherwise another response is necessary. Model confidence cannot narrow these bounds.

Item 9 is captured first. That protocol does not establish suicide-risk assessment or a safety intervention.

Freeze, replay, replicate.

We developed policies on adult NHANES 2017–2018 records, locked them, and replayed complete responses on two different cycles. The newer cycle is the primary external evaluation; the earlier cycle adds replication.

Empirical dynamic programming plans future question cost. Secondary policies use a categorical MADE density or a compact latent-class mixture. Learning changes the order, never the stopping rule. Later searches are exploratory because they reuse already examined cohorts.

A smaller learning gain, honestly shown.

Most savings come from certified stopping and a good fixed order. In the primary cohort, empirical DP saves only 0.010 questions beyond optimal fixed ordering. Exploratory MADE saves 0.090 beyond fixed and 0.041 beyond an independent-item model.

All 4⁹ fixed patterns had zero class errors in independent exhaustive traces. Preserving five severity bands instead required 8.394 questions in the newer cohort.

What the guarantee covers

The guarantee is exact binary score emulation for a fixed response vector. It does not say a person will give the same responses after reordering. A prospective study would need to measure response consistency, time, dropout and distress, with independent human escalation rules.

• No claim of diagnosis, time savings, or prospective clinical equivalence.
• The binary threshold guarantee does not preserve an exact total or complete severity assessment.
• The work was coauthored by Brandon Baek, Tevyn Yong and Seonho Kim.

A change can disappear before the next check.

RECHECK-ED studies when to place one already permitted flexible nursing reassessment. It combines recent waveform support with the probability that a visible change ends within 20 minutes, while keeping required checks fixed.

A retrospective information-capture study, not a trial of outcomes, nurse workload, or safety.

Timing without moving the protected checks

Two patient-separated, five-member gradient-boosted ensembles estimate waveform-rule support q and 20-minute disappearance e from past information only. Their product q × e forms a short-horizon urgency heuristic. Missing waveforms cannot reassure the controller: an active raw-monitor event triggers a check.

Patients separated. Method frozen.

The method was developed on 450 previously opened MC-MED waveform episodes across 412 patients. Model files, thresholds, code and waveform inventory were frozen before a one-time evaluation on 600 new episodes from 567 different patients.

The other 202 waveform-qualified episodes were already chart-represented. Thirty-one of the 600 episodes had no complete waveform overlap. The case-enriched, single-center sample does not estimate general ED event prevalence.

Capture and selectivity are different gains.

The raw-monitor trigger captured the same 70 episodes as the model. Learning’s incremental result was 56 endpoint-negative triggered actions instead of 67—not fewer total attempted checks. Retrained no-waveform and process-only models also captured 70, with 62 and 60 endpoint-negative prompts.

A research prototype, governed by nurses.

The result supports monitor-responsive timing and a smaller set of endpoint-negative prompts under a fixed experimental budget. It does not establish that nurses missed events, that prompts were unnecessary, or that waiting would be safe. Required, urgent, post-medication and post-procedure checks cannot be moved.

• PPG pulse quality cannot confirm arterial oxygen saturation.
• The replay leaves physiology, treatment and historical documentation unchanged.
• Prospective work needs nursing review, local permissions, override rules and measured patient outcomes.