R14 commitment

Authored design — 2026-09-15. Section 3. This cascade elaborates the existing checklist item. It is not a dispatch, implementation receipt or completion verdict. Work outside WM-01–14 still requires Joe’s explicit greenlight; having a cascade is necessary but not permission.

Section 3/4 index · Exact TODO · Cascade JSON

Situation and design problem

Commitment modulation must act under a law and mode that actually admits it. Channel precision, temporal preference and policy commitment must not exchange meanings.

Governing checklist snapshot

R14 commitment. PARTIAL: applicable posterior/gain law, actual selection influence and R20 composition. Variational-mode insensitivity cannot be counted as successful modulation. Built evidence: Temperature/precision components and pinned witnesses

This is the checklist’s dated evidence account, not a new deployment census. Existing source/test evidence keeps its bounded credit. The acceptance obligation above governs this design.

Pattern applications

R14-1 — Pin the commitment law

Pattern: aif/policy-precision-commitment-temperature

Identify applicable posterior/temperature or precision law, input scale and mode. Produce a declared commitment contract; do not universally impose the seed’s simple softmax on an incompatible variational mode.

R14-2 — Compose monitoring inputs

Pattern: wm-connected-learning/modulation-needs-an-applicable-consumer

Use R20’s actual trips, history and restoration state with the declared composition order. Retain each factor and the effective result, including floors and saturation.

R14-3 — Apply to the real candidate distribution

Pattern: aif/policy-precision-commitment-temperature

Keep full policy identities, prior and applicable F/G inputs unchanged except for the authorized modulation. Retain the consumed commitment value and resulting choice distribution.

R14-4 — Test effect and restoration

Pattern: wm-connected-learning/modulation-needs-an-applicable-consumer

Show an applicable case where composition changes the distribution and a restored case where the admitted baseline returns. Inapplicable modes or saturated factors must be labelled, not counted as successful influence.

Composition and interfaces

Each node’s stated artifact is the input or constraint for the related node below. These are design dependencies, not a claim that a runtime scheduler automatically fires patterns. Existing WM producers are reused through the linked contracts; no second implementation is implied.

Retain the actual subject, source/model revision, task/occurrence, cutoff, producer and consumer for each interface. A missing field is a named gap; a default that changes the meaning is not an adapter. Reuse existing records where they satisfy these obligations. If a new component is indispensable, identify its exact TODO/cascade clause before seeking a separately bounded implementation instruction.

Worked situation

A trip reduces a multiplier, but a gain floor makes the effective value unchanged. Reporting the raw multiplier as successful modulation would hide the floor. The record must show both values and the actual distribution.

This is a distinguishing design example, not a claimed production experiment.

Implementation sequence and closure evidence

1. Bind the first application to the actual source, task and authority. Resolve the decisions below before their dependent change; do not reproduce a known gap merely to claim activity.
2. Implement only the specifically dispatched producer/consumer change from the middle applications. Retain the meaningful pre-change failure and relevant post-change controls; do not start a general infrastructure project.
3. Acquire the final application’s evidence and independent review. Compare it against every clause of the exact TODO, identifying any still-open dependency. Source, tests, serving state, ordinary use and whole-run validation receive different credit.

Distinguishing controls: Exercise active, saturated, inapplicable and restored cases; reject channel-precision substitution and a posterior using the pre-composition value.

Closure rule: every part of the quoted obligation must be supported by the indicated artifacts and actual connections. A useful rejection proves the rejecting boundary only. One accepted subclause does not tick the whole item. A bellback must supply the exact reviewed subject, executed checks, independent verdict and remaining clauses.

Dependencies and authority boundaries

R7 · R20 · WM-11 · R6

No new temperature law, gain coefficient or fuel preference is adopted; unresolved mode authority blocks the dependent claim.

Dependency links describe required interfaces; they do not authorize work on those items. No implementation outside the existing TODO list is approved. Publication does not select a numerical law, settle an unresolved operator ruling or authorize a run.

Pattern and source scope

All seeded patterns are applied above. The JSON pins their source bytes and the governing checklist/rulings. Historical formulas, thresholds and examples in a pattern remain scoped examples unless the governing contract adopts them. This draft adds no pattern-library entries and claims no independent semantic ratification.

Existing pattern source snapshots

Reference text; historical examples and prescriptions retain the scope stated above.

@flexiarg aif/policy-precision-commitment-temperature
@title Policy Precision as Commitment Temperature
@sigils [🍲/由]
@audience fulab agents, aif implementers
@tone technical
@style pattern
@holds-at R14   ;; pegged 2026-08-30 (claude-15): the catalogue paragraph numbered R14 in p4ng/sec-catalog.tex; see PREREG-war-machine §1b

@see-also aif/hierarchical-budget-aware-action-selection
@see-also aif/expected-free-energy-scorecard
@why R14 dossier problem: R14 solves how operational confidence controls commitment without changing the underlying value model: the roster places **“Commitment temperature”** in SELECT (`p4ng/empirics-futon/control-stages.edn:25`; control-stage numbering). (source: futon2 holes labs wm-contract PROBLEMS-r16-r13-r14-batch4.md, R14, The problem it solves; L3 rationale-backfill pilot, zai-1, 2026-09-05)
@how own mechanism: Maintain a commitment temperature that modulates how strongly the policy commits to low-G choices. (source: this pattern's ! conclusion line; L3 rationale-backfill pilot, zai-1, 2026-09-05)
@why problems/commitment-temperature-is-instrumented-as-gain (L14 edge-resolution; basis: holds -- the problem node's own holds-at token covers this pattern; source: receipt runs/L14-edge-resolution.edn; zai-1, 2026-09-05)
@why problems/r14-commitment-temperature (L14 edge-resolution; basis: holds -- the problem node's own holds-at token covers this pattern; source: receipt runs/L14-edge-resolution.edn; zai-1, 2026-09-05)
! conclusion: Maintain a commitment temperature that modulates how strongly the policy commits to low-G choices.

  + context: Even with identical scores, the agent sometimes should explore alternatives and other times should commit.

  + IF:
    You want exploration versus exploitation to depend on operational pressure (deadlines, repeated failures, user impatience, instability), not on randomness alone.

  + HOWEVER:
    Without an explicit (tau), the agent either thrashes or tunnels with no controllable dial.

  + THEN:
    Maintain (tau) as a commitment temperature that modulates softmax over (-G/tau), coupled to diagnostic signals (recent regressions, uncertainty in (mu), contradiction rate, time pressure, repeated test failures).

  + BECAUSE:
    A single commitment dial allows systematic control of stochasticity without changing the scoring model.

  + NEXT-STEPS:
    - Add :aif/tau-adjustment event type to tatami_schema.clj with keys [:prev-tau :next-tau :trigger :diagnostic-signals].
    - Implement tau-coupling rules in aif_bridge.clj: increase tau on :test-failure or :uncertainty > 0.7; decrease on :tests-passing streak.
    - Persist tau history in lab/aif/tau-cache.edn keyed by pattern-id; load on session start.
    - Add (policy-entropy session) metric to aif_coverage.clj; correlate with outcome stability in session summaries.
    - DONE (UKRN v3 HO-05, 2026-05-14): abstain? rule implemented at notebooks/ukrn_v3_efe.clj:75-92. Computes G-spread across top-K candidates, divides by τ, abstains if the resulting discriminability is ≤ floor (default 0.5, configurable). Edge case: < 2 candidates returns true (degenerate). Test abstain-fires-only-under-low-discriminability covers well-separated, weakly-separated, threshold, and just-over-threshold regimes. Closes R6 abstain criterion for UKRN v3-runner. Evidence: handoffs/v3_runner/validation_HO-05.md.
    - Practice (HO-05): abstain semantics are part of R6 in the AIF completeness criteria. An implementation that has softmax without abstain is operationally incomplete — it always picks something, even when statistically indistinguishable candidates would warrant inaction. Make abstain explicit; make the threshold configurable.