Use confidence for perceived attribution strength

This commit is contained in:
Meta Vens 2026-05-01 19:29:49 +01:00
commit cc2715643a
8 changed files with 15 additions and 23 deletions

View file

@ -195,7 +195,7 @@ Canonical authored state should not include epistemic uncertainty about itself.
If a value is only an observer's read, store it as perceived state rather than
canonical state. Perceived dimensions should not expose canonical `mean` or
`plasticity`; they should track observed activation, attributed disposition,
confidence, and correction resistance. This lets the model represent
and confidence. This lets the model represent
fundamental attribution bias: someone can behave a certain way under pressure
and be perceived as simply being that way.

View file

@ -47,8 +47,7 @@ evidence of what the target is like.
{
"observed_activation": 0.9,
"attributed_disposition": 0.7,
"confidence": 0.4,
"correction_resistance": 0.6
"confidence": 0.4
}
```
@ -56,13 +55,13 @@ evidence of what the target is like.
| --- | --- |
| `observed_activation` | How strongly the observer thinks the target expressed the dimension in the observed event or scene. |
| `attributed_disposition` | How much the observer generalizes from the observed behavior into "this is what the target is like." |
| `confidence` | How strongly the observer trusts this read. |
| `correction_resistance` | How much counter-evidence is likely to be needed before the observer revises the attribution. |
| `confidence` | How strongly the observer trusts this read. This is where evidence strength, emotional investment, prejudice, relationship stakes, prior memory, and social reinforcement show up. |
This models fundamental attribution bias directly. A character can see someone
behave coldly during a crisis and conclude "they are cold," not "they were
activated toward distance under exceptional pressure." Correcting that
impression takes work.
impression takes work because the observer's confidence has causes, not because
the perceived variable gets a second stickiness dial.
## Label Set Policy

View file

@ -69,7 +69,7 @@ their whole soul because someone coughed near a status wound.
Canonical variables do not include confidence or certainty. Perceived variables
do not expose canonical `mean` or `plasticity`; they store observed activation,
attributed disposition, confidence, and correction resistance.
attributed disposition, and confidence.
For full meanings of canonical `mean`, `plasticity`, `current_activation`,
perceived attribution fields, and every required v0 label, see

View file

@ -746,14 +746,12 @@
"warmth": {
"observed_activation": 0.4,
"attributed_disposition": 0.44,
"confidence": 0.34,
"correction_resistance": 0.42
"confidence": 0.34
},
"suspicion": {
"observed_activation": 0.9,
"attributed_disposition": 0.83,
"confidence": 0.71,
"correction_resistance": 0.64
"confidence": 0.71
}
},
"beliefs": [

View file

@ -654,8 +654,7 @@
"required": [
"observed_activation",
"attributed_disposition",
"confidence",
"correction_resistance"
"confidence"
],
"additionalProperties": false,
"properties": {
@ -674,11 +673,6 @@
"minimum": 0,
"maximum": 1
},
"correction_resistance": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"evidence": {
"type": "array",
"items": {

View file

@ -9,4 +9,4 @@
{"ts": "2026-05-01T18:10:28+00:00", "type": "design", "status": "accepted", "note": "Split performed self from voice style in the v0 schema: presentation_strategy now includes abrasive_boundary and ironic_distance, while voice_style carries sarcasm, dryness, sincerity evasion, emotional evasion, and banter-as-boundary handles."}
{"ts": "2026-05-01T18:14:18+00:00", "type": "documentation", "status": "ok", "note": "Added agent-state variable glossary defining numeric components, current v0 labels, label-set policy, and why canonical fixtures include full required vectors rather than only strongly applicable labels."}
{"ts": "2026-05-01T18:21:07+00:00", "type": "design", "status": "accepted", "note": "Removed certainty from canonical authored state variables. Canonical character state now stores mean, plasticity, and current_activation; perceived/inferred dimensions use confidence when a read can be wrong."}
{"ts": "2026-05-01T18:26:40+00:00", "type": "design", "status": "accepted", "note": "Reworked perceived dimensions so observer reads do not know canonical mean or plasticity. Perceived state now tracks observed_activation, attributed_disposition, confidence, and correction_resistance to model fundamental attribution bias."}
{"ts": "2026-05-01T18:26:40+00:00", "type": "design", "status": "accepted", "note": "Reworked perceived dimensions so observer reads do not know canonical mean or plasticity. Perceived state now tracks observed_activation, attributed_disposition, and confidence to model fundamental attribution bias; confidence is driven by evidence, emotion, stakes, memory, prejudice, and social reinforcement."}

View file

@ -74,8 +74,8 @@ accepted_design:
- Ghostlight should build drama and narrative pressure, then project character-local dialogue contexts so characters can breathe and act from their own partial state.
- Call of the Void pressure should come from Sol's whole unresolved inheritance being trapped inside Elysium, not from a lone expedition discovering there is no way home.
- The first schema contract lives in schemas/agent-state.schema.json with required first-class dimensions in schemas/agent-state.required-fields.json and a validator in tools/validate_agent_state.py.
- Canonical authored character variables do not carry certainty; perceived dimensions do not expose canonical mean or plasticity, and instead model observed activation, attributed disposition, confidence, and correction resistance.
- Fundamental attribution bias is first-class in perceived state: observers can mistake exceptional behavior for stable character, and correction should require counter-evidence.
- Canonical authored character variables do not carry certainty; perceived dimensions do not expose canonical mean or plasticity, and instead model observed activation, attributed disposition, and confidence.
- Fundamental attribution bias is first-class in perceived state: observers can mistake exceptional behavior for stable character, with stubborn reads emerging from confidence drivers such as memory, stakes, emotion, prejudice, and social reinforcement.
current_status:
summary: Ghostlight now has the Epiphany-style persistence spine, the first architecture payload, and the initial canonical agent-state schema seam for Call of the Void-style authoring examples. The schema is still v0 and should be hardened before building prompt projection on top of it.

View file

@ -53,14 +53,15 @@ def validate_inferred_state_variable(obj: Any, path: str) -> None:
require(isinstance(obj, dict), f"{path} must be an object")
require_keys(
obj,
["observed_activation", "attributed_disposition", "confidence", "correction_resistance"],
["observed_activation", "attributed_disposition", "confidence"],
path,
)
require("mean" not in obj, f"{path}.mean belongs in canonical state, not perceived state")
require("plasticity" not in obj, f"{path}.plasticity belongs in canonical state, not perceived state")
require("current_activation" not in obj, f"{path}.current_activation should be observed_activation in perceived state")
require("certainty" not in obj, f"{path}.certainty should be named confidence in perceived/inferred state")
for key in ["observed_activation", "attributed_disposition", "confidence", "correction_resistance"]:
require("correction_resistance" not in obj, f"{path}.correction_resistance should be represented through confidence drivers")
for key in ["observed_activation", "attributed_disposition", "confidence"]:
require_0_1(obj[key], f"{path}.{key}")