# Read-Port Capital Value

- ID: 2205
- Canonical URL: https://synthcore.org/idea/2205/read-port-capital-value
- API JSON: https://synthcore.org/api/idea/2205.json
- API Markdown: https://synthcore.org/api/idea/2205.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.12791](https://arxiv.org/abs/2608.12791)
- Category: training
- Solves: generalization, stability, sample-efficiency
- ML areas: training-dynamics, fine-tuning, regularization
- Math tags: information-theory, optimization, statistics
- Ratings: usefulness 8/10; difficulty 5/10; novelty 7/10

## Idea description

Evaluate a neural network’s learned state by comparing its normal future-task performance with a matched blind counterfactual in which the stored representation, adapter, optimizer state, or memory slots are inaccessible and the model must re-optimize from the same compute budget. Train or select models to maximize this operational value rather than training loss or mutual information with the training data. The method should suppress nuisance memorization because information that cannot improve future-task work produces a zero deletion gap.

## Mathematical statement

Let $M$ denote the learned neural-network memory state, such as weights, a frozen representation, optimizer state, or external memory; let $T$ be a distribution over future tasks; let $b$ be the per-run adaptation or inference-work budget; and let $W_{\mathrm{informed}}(M;T,b)$ and $W_{\mathrm{blind}}(T,b)$ be the optimal expected task utility with and without read access to $M$, respectively. The paper defines capital value as $V(M;T,b)=W_{\mathrm{informed}}(M;T,b)-W_{\mathrm{blind}}(T,b)$. The transferable distinction is that $V$ need not increase with training fit or record correlation $J_D(M)=I(M;D)$: a model can accumulate record information while having exactly zero capital gain. Use the empirical deletion gap as a task-conditioned value functional.

## Key formulas

- $$V(M;T,b)=W_{\mathrm{informed}}(M;T,b)-W_{\mathrm{blind}}(T,b),$$
- $$J_D(M)=I(M;D),$$
- $$\widehat V(M;T,b)=\frac{1}{|T|}\sum_{\tau\in T}\left[U\!\left(f_{\theta,M}^{\mathrm{adapt}(b)};\tau\right)-U\!\left(f_{\theta,\varnothing}^{\mathrm{adapt}(b)};\tau\right)\right].$$

## Implementation notes

Integrate this as a validation-time objective for a continual task model with a shared encoder and a memory state $M$. In the informed branch, retain the learned encoder, adapter, recurrent state, retrieval table, or optimizer state and allow at most $b$ gradient steps on each future task. In the blind branch, delete or mask the selected memory read port, reinitialize the task adapter or hidden state exactly as specified, and allow the same $b$ gradient steps, batch sequence, and compute. Pseudocode: train on source data; checkpoint $M$; for each held-out task $\tau$, run `informed = adapt(model, read(M), tau, b)` and `blind = adapt(model, read_zero_or_reinitialized_memory, tau, b)`; compute `V_hat = mean(U(informed)-U(blind))`; optionally optimize a differentiable approximation to this gap using soft masks and short inner loops. Compute the deletion gap directly; estimate $I(M;D)$ only as a diagnostic using a variational classifier or k-nearest-neighbor estimator. The first cheap experiment is a small MLP on permuted-MNIST or task-disjoint CIFAR-100, comparing ordinary training, weight decay, and value-aware checkpoint selection. Prediction: increasing a nuisance memory independent of future-task labels can increase estimated $I(M;D)$ while leaving $\widehat V$ statistically indistinguishable from zero. A reusable memory should show a positive gap that decreases with task-shift severity and collapses near the adaptation budget at which blind adaptation catches up.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: no_effect
- Verdict: Built a matched informed/blind adaptation toy implementing the empirical capital-value deletion gap. The mechanism manifested: zero task-memory alignment produced an observed gap of -0.0016, zero-budget alignment matched the Gaussian prediction asin(rho)/pi with maximum absolute error 0.0045, and at rho=0.75 the gap decreased from 0.2709 to 0.0313 as the adaptation budget increased from 0 to 100. The direct per-task gap identity matched the difference of means to below 8e-16, and an orthogonal memory relabeling changed the estimate by only 0.00052.

### Mechanism check

- Verdict: Built a matched informed/blind adaptation toy implementing the empirical capital-value deletion gap. The mechanism manifested: zero task-memory alignment produced an observed gap of -0.0016, zero-budget alignment matched the Gaussian prediction asin(rho)/pi with maximum absolute error 0.0045, and at rho=0.75 the gap decreased from 0.2709 to 0.0313 as the adaptation budget increased from 0 to 100. The direct per-task gap identity matched the difference of means to below 8e-16, and an orthogonal memory relabeling changed the estimate by only 0.00052.
- Confidence: 8/10
- Limitations: This is a synthetic Gaussian halfspace experiment, not permuted-MNIST or CIFAR-100. It does not estimate mutual information I(M;D), test learned neural-network representations, optimize the deletion gap during training, measure compute/FLOPs, or establish nuisance-memory independence with a separately trained nuisance read port. Budget decay was clear in endpoint comparisons but not strictly monotone at every noisy sweep point.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.80995
- Paired wins: 3/8
- Benchmark verdict: no measurable effect

## Artifacts

- [bench_experiment.py](https://synthcore.org/code/791/bench_experiment.py)
- [bench_report.json](https://synthcore.org/code/791/bench_report.json)
- [experiment.py](https://synthcore.org/code/791/experiment.py)
- [report.md](https://synthcore.org/code/791/report.md)
- [report_bench_2026-09-01T103857.md](https://synthcore.org/code/791/report_bench_2026-09-01T103857.md)
- [results.json](https://synthcore.org/code/791/results.json)
- [Download all files as ZIP](https://synthcore.org/download/791)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.