← Research map
Technical noteObserve

Restricted noisy experiments

Can a predictive capability be acquired through the experiments an interface actually permits?

Read Online Or start with the explanation below.

Why this question matters

A representation may exist even when the available probes cannot identify it. The note makes the experiment interface and target explicit, so that an impossibility statement about identification is not silently transferred to prediction.

Setup and results

A transcript-law obstruction bounds prediction risk. In the symmetric binary family the best permitted channel gives the exact majority-error frontier, including randomized ties and the even/odd zero branch. Irreversible scout-and-commit, adaptive allocation and priced stopping examples provide finite comparisons. Asymmetric policy mixtures and prior lower bounds give exact minimax certificates, including the 23/70 example.

Limits and negative results

Likelihoods and permissions are inputs to the model. The result does not solve general constrained stochastic experiment design, infer finite storage from real-dimensional state descriptions, or strengthen deterministic homotopy admissibility assumptions. Historical closure hashes are evidence of particular rounds, not proof that later assemblies received those reviews.

Reading guide

Read the transcript obstruction and exactly solved restricted experiment first, including Theorem 4.2 and its tie convention. Continue to the asymmetric extension and inspect both upper-policy and lower-prior certificates.

Place in the research programme

Read alongside Acquirable Predictive Models and finite-memory tracking. The connection is a declared finite sensing problem, not an empirical account of how a mind learns its interface.

Edition and review status

Brian Theory is the author; this is an AI-assisted research draft. Documented specialist and hostile AI review rounds informed development, but not every round was blind, independently provisioned or cover-to-cover on the final assembly. These checks are not external human peer review or journal acceptance. Targeted human review and historical novelty assessment remain pending.

Sources and reproducibility

Read the complete manuscript, open its page-faithful PDF reader, or download the exact PDF. Exact LaTeX and figure dependencies contain the manuscript inputs and a checksum manifest. This source-only package does not contain the computational verification programs; their public release and independent execution are not certified here. Read the manuscript’s reproducibility sections for the scope of its finite checks.

PDF SHA-256: 2936fc342e4ab9594a60fc3ffe11c0b997c4716a3a4e68b28af1686cea3ed40b. Main LaTeX SHA-256: 2370fc2ac619394458597e388bb54e5ccbfa3ca29476cdf2f5ce81b4d4e3b6ee.

Related manuscript

Acquiring a Predictive Capability through Restricted Noisy Experiments Exact frontiers and certified asymmetric irreversible acquisition

AI-assisted research draft; internal AI checks documented. External human review and novelty assessment remain pending.

Reading scope: Finite known model families and supplied likelihoods/permissions. Prediction is distinct from historical parameter identification; general stochastic design and novelty remain open.

Site reading copy 1 from 13 November 2026 manuscript with localized corrections and approved author credit; exact edition hashes linked below.

Technical material

Exact LaTeX source and figure dependencies

See this manuscript's index entry
Phase: ObserveObserveManuscript: Acquiring a Predictive Capability through Restricted Noisy Experiments Exact frontiers and certified asymmetric irreversible acquisitionAcquiring a Predictive Ca…Project: Acquirable Predictive ModelsAcquirable Predictive Mod…Project: Adaptive bit acquisition and memoryAdaptive bit acquisition…Project: Finite-memory adaptive trackingFinite-memory adaptive tr…Restricted noisy experiments
  • Phases
  • Manuscripts
  • Projects

Conceptual and navigational links, not proof dependencies.