- The question
- Does naming the posture a question deserves change what the answering model actually computes — or only how it talks?
- The instrument
- A 3B LoRA compass (v9, Ministral base; a 1.5B v1.0 also ships) reads the geometry, tone, and epistemic weight of a question and issues OPEN / PAUSE / WITNESS — HOLD, in the paper's vocabulary — to condition a larger 9B action model. Ships as a native macOS app, fully local on Apple Silicon.
- The finding
- It changes the computation. Token-level entropy profiling shows ΔH = +0.47 nats (JSD = 0.076): the compass measurably restructures the probability distribution rather than restyling the output. Ablation confirms signal-specificity — wrong-signal WITNESS conditioning collapses responses, full wins 31–2.
- What failed
- The original framing treated the compass as a filter on outputs. That was wrong in a checkable way: a filter cannot move token-level entropy before the tokens exist. The mechanism is field conditioning through attention geometry, which is a different claim than the one first made.
- Standing
- Study + instrumentPublishedSupported within scope
Study + instrument
Phenomenological Compass
A two-stage inference architecture: a small compass reads the epistemic weight of a question and conditions a larger action model.
Study + instrumentPublishedSupported within scope
96% signal accuracy (101/105) · ΔH = +0.47 nats · one architecture family
Metrics with scope
Every number names what was measured, on what sample, and as of when.
Signal accuracy
96% (101/105)
105-question epistemic-posture eval; WITNESS classification 100%
As of 2026-04-02 · source
Entropy restructuring
+0.47 nats
Token-level ΔH, JSD = 0.076, one architecture family
As of 2026-04-02 · source
Ablation
31–2
Full-signal vs. wrong-signal WITNESS conditioning, head-to-head
As of 2026-04-02
From wonder to receipt
Phenomenological Compass
Wonder initiated the search. Rigor changed the answer.
Study + instrumentPublishedSupported within scope
- 01Wonder
Does it matter, to the machine, whether a question is asked with reverence or with haste?
- 02Hypothesis
If posture is real to the model, conditioning on an explicit epistemic signal should change the shape of the probability distribution — not just the wording of the reply.
- 03Instrument
A 3B LoRA compass emitting OPEN / PAUSE / WITNESS, wired ahead of a 9B action model, with token-level entropy profiling on both paths.
- 04Encounter
ΔH = +0.47 nats, JSD = 0.076. The distribution moved. Wrong-signal conditioning collapsed the response, so the effect is signal-specific rather than a generic prompt-length artifact.
- 05Standing
Supported within scope: one architecture family, one eval set, not yet replicated across model scales.
- 06Receipt
DOI 10.5281/zenodo.19377144 · phenomenological-compass