# DIAL-CAN structural-obstruction calibration

- **Registry ID:** `ic-dial-can`
- **Book:** Infinitesimal Creativity
- **Documentation status:** `local-curated`
- **Experimental status:** registered calibration and negative learner studies
- **Canonical documentation URL:** https://categorical-ai.sridharmahadevan.com/experiments/ic-dial-can

## Purpose

Bracket calibration, stochastic GAN dynamics, smooth observer ablation, decision regions, and finite-sample estimation.

## Book location

- Chapter 19: Artistic Theory Extension

## Documented studies

- No study-level titles are registered; consult the family-level record.

## Associated code packages

- `synthetic-creativity-archive` — Infinitesimal Creativity registered experiment archive; **local-curated**; license decision pending. Registered, developmental, negative, and transport experiment directories underlying Chapters 10–19. Public packets require separate provenance, dependency, rights, and privacy review.

## Start here

These concrete files are selected from the complete resolved source surface. They orient the reader; they are not a claim that every family is independently reproducible.

- **implementation · staged-not-public** — `synthetic-creativity-archive:dial_can_0_bracket_calibration.py`. Locate this file in the curated companion packet; no public download is currently offered.
- **implementation · staged-not-public** — `synthetic-creativity-archive:dial_can_1_stochastic_gan.py`. Locate this file in the curated companion packet; no public download is currently offered.
- **implementation · staged-not-public** — `synthetic-creativity-archive:dial_can_1b_smooth_observer.py`. Locate this file in the curated companion packet; no public download is currently offered.
- **implementation · staged-not-public** — `synthetic-creativity-archive:dial_can_2_decision_regions.py`. Locate this file in the curated companion packet; no public download is currently offered.

## Entry points

- `run.py in each packet`

## Result artifacts

- `RESULTS.md`
- `registration.json`

## Resolved code surfaces (5)

- **implementation** — `synthetic-creativity-archive:dial_can_0_bracket_calibration.py`
- **implementation** — `synthetic-creativity-archive:dial_can_1_stochastic_gan.py`
- **implementation** — `synthetic-creativity-archive:dial_can_1b_smooth_observer.py`
- **implementation** — `synthetic-creativity-archive:dial_can_2_decision_regions.py`
- **implementation** — `synthetic-creativity-archive:dial_can_3_finite_estimator.py`

## Frozen run records (5)

- `2026-08-18_dial_can_0_bracket_calibration_registered`
- `2026-08-18_dial_can_1_stochastic_gan_registered`
- `2026-08-18_dial_can_1b_smooth_observer_registered`
- `2026-08-18_dial_can_2_decision_regions_registered`
- `2026-08-18_dial_can_3_finite_estimator_registered`

## Evidence boundary

The finite-sample controller does not meet the full learned-controller target; style-classifier deviation is not theory extension.

A code or artifact link establishes traceability. It does not by itself establish independent reproduction, statistical adequacy, correctness, or support for a claim beyond this boundary.