Files
skills/public/hip-0007.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

553 lines
27 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>hip-0007</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/hip-0007.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/hip-0007">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/hip-0007.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>hip-0007</h1><p class="lede">HIP-7: Active Inference Integration for Hamiltonian LLMs. Status Final. Hanzo architectural specification.</p><h1>HIP-0007: Active Inference Integration for Hamiltonian LLMs</h1>
<h2>Abstract</h2>
<p>This proposal integrates VERSES/Active Inference principles into the Hamiltonian LLM (HLLM) stack, adding an Active Inference Planner that minimizes Expected Free Energy (EFE) for tool routing, multi-step planning, and explainable decision-making. The system uses IEEE 2874 Spatial Web standards for interoperability and implements renormalizable world models for efficient regime adaptation.</p>
<h2>Specification</h2>
<h3>1. Active Inference Planner (AXIOM-style)</h3>
<h4>Core Algorithm</h4>
<pre><code class="lang-python">class ActiveInferencePlanner:
def __init__(self, world_model, horizon=6):
self.world_model = world_model
self.horizon = horizon
def plan(self, beliefs, goal, tools):
&quot;&quot;&quot;
Minimize Expected Free Energy (EFE) over action sequences
EFE = E[goal_loss] + epistemic_value
&quot;&quot;&quot;
best_efe = float(&#x27;inf&#x27;)
best_plan = None
for _ in range(100): # Sample action sequences
plan = self.sample_action_sequence(tools, self.horizon)
# Calculate EFE components
utility = self.expected_goal_loss(plan, goal, beliefs)
curiosity = self.epistemic_value(plan, beliefs)
# Early in task: curiosity dominates
# Later: utility dominates
task_progress = self.estimate_progress(beliefs, goal)
alpha = sigmoid(task_progress * 10 - 5) # 0→1 transition
efe = alpha * utility + (1 - alpha) * curiosity
if efe &lt; best_efe:
best_efe = efe
best_plan = plan
return best_plan, {
&#x27;efe&#x27;: best_efe,
&#x27;utility&#x27;: utility,
&#x27;curiosity&#x27;: curiosity,
&#x27;beliefs&#x27;: beliefs
}</code></pre>
<h4>Integration with LLM</h4>
<pre><code class="lang-python">def route_with_planning(job):
# Encode context into beliefs
beliefs = world_model.encode(job.context)
# Active inference planning
plan, trace = planner.plan(beliefs, job.goal, job.available_tools)
# Execute first action
action = plan.actions[0]
result = dispatch(action, trace=trace)
# Update beliefs
new_beliefs = world_model.update(beliefs, action, result)
return result, trace</code></pre>
<h3>2. Renormalizable World Models</h3>
<h4>Structure-Learning Regime Adapters</h4>
<pre><code class="lang-python">class RenormalizableAdapter:
def __init__(self, base_model, latent_dim=256):
self.base_model = base_model # Frozen HLLM
self.world_model = RSSM(latent_dim) # Recurrent State-Space Model
self.regime_heads = {}
def add_regime(self, regime_id, task_distribution):
&quot;&quot;&quot;
Add lightweight regime-specific head
No retraining of base model needed
&quot;&quot;&quot;
self.regime_heads[regime_id] = nn.Sequential(
nn.Linear(latent_dim, 512),
nn.ReLU(),
nn.Linear(512, task_distribution.action_space)
)
def forward(self, x, regime_id):
# Encode through frozen base
features = self.base_model.encode(x)
# World model dynamics
latents = self.world_model(features)
# Regime-specific output
output = self.regime_heads[regime_id](latents)
return output, latents</code></pre>
<h3>3. Explainability via Introspection</h3>
<h4>Active Inference XAI</h4>
<pre><code class="lang-json">{
&quot;trace&quot;: {
&quot;step&quot;: 1,
&quot;beliefs&quot;: {
&quot;task_understanding&quot;: 0.87,
&quot;goal_clarity&quot;: 0.92,
&quot;tool_confidence&quot;: {&quot;search&quot;: 0.8, &quot;code&quot;: 0.6, &quot;math&quot;: 0.9}
},
&quot;uncertainty&quot;: 0.23,
&quot;candidates&quot;: [
{&quot;action&quot;: &quot;tool.search&quot;, &quot;efe&quot;: 1.31, &quot;utility&quot;: 0.8, &quot;curiosity&quot;: 0.51},
{&quot;action&quot;: &quot;code.run&quot;, &quot;efe&quot;: 1.44, &quot;utility&quot;: 0.7, &quot;curiosity&quot;: 0.74},
{&quot;action&quot;: &quot;math.solve&quot;, &quot;efe&quot;: 1.28, &quot;utility&quot;: 0.9, &quot;curiosity&quot;: 0.38}
],
&quot;chosen&quot;: &quot;math.solve&quot;,
&quot;why&quot;: &quot;Lowest EFE (1.28); high goal utility (0.9) with moderate exploration value&quot;,
&quot;counterfactuals&quot;: [
&quot;If uncertainty &gt; 0.5, would have chosen tool.search for information gathering&quot;
]
}
}</code></pre>
<h3>4. IEEE 2874 Spatial Web Integration</h3>
<h4>HSML/HSTP Wire Format</h4>
<pre><code class="lang-yaml">hsml:Agent:
id: &quot;did:hanzo:node123&quot;
type: &quot;HamiltonianLLM&quot;
capabilities:
- id: &quot;llm.infer&quot;
spec: &quot;hmm-32b-multimodal&quot;
- id: &quot;plan.efe&quot;
spec: &quot;active-inference-v1&quot;
- id: &quot;tool.sql&quot;
spec: &quot;postgres-15&quot;
policies:
- type: &quot;hsml:Policy:privacy&quot;
tier: 3
dp_epsilon: 2.0
- type: &quot;hsml:Policy:safety&quot;
content_filter: true
attestations:
- type: &quot;tee.sev-snp&quot;
cert: &quot;base64...&quot;
- type: &quot;ml-dsa.sig&quot;
pubkey: &quot;base64...&quot;
world_model:
type: &quot;renormalizable&quot;
regimes: [&quot;defi&quot;, &quot;gaming&quot;, &quot;nft&quot;, &quot;general&quot;]</code></pre>
<h3>5. Hierarchical Control Architecture</h3>
<h4>Multi-Level Planning</h4>
<pre><code class="lang-python">class HierarchicalController:
def __init__(self):
self.micro = MicroController(horizon=3) # Token-level, short tools
self.macro = MacroController(horizon=12) # Sub-goals, proof checking
def execute(self, task):
# Macro planning
subgoals = self.macro.decompose(task)
results = []
for subgoal in subgoals:
# Micro execution
plan = self.micro.plan(subgoal)
for action in plan:
result = execute_action(action)
# Check proofs/SLOs between steps
if not verify_constraints(result, subgoal.slos):
plan = self.micro.replan(subgoal, result)
results.append(result)
return combine_results(results)</code></pre>
<h3>6. Hamiltonian Market-Maker with EFE</h3>
<h4>Curiosity-Aware Routing</h4>
<pre><code class="lang-python">def route_with_market_efe(job, providers):
&quot;&quot;&quot;
Combine EFE with Hamiltonian prices for routing
&quot;&quot;&quot;
beliefs = world_model.encode(job.context)
plan, trace = planner.plan(beliefs, job.goal, job.tools)
scores = []
for provider in providers:
# EFE component (task fit + uncertainty)
efe_score = plan.efe_cost[provider.capability_profile]
# Market price (Hamiltonian)
price = market_maker.current_price(provider)
# SLO constraints
slo_penalty = calculate_slo_penalty(provider, job)
# Combined score
score = (
alpha * efe_score + # Task fit/exploration
beta * price + # Current market price
gamma * slo_penalty # Latency/privacy constraints
)
scores.append((score, provider))
# Route to minimal score
target = min(scores, key=lambda x: x[0])[1]
# Update prices via tatonnement
market_maker.update_price(target, job.load)
return dispatch(target, plan.actions[0], trace=trace)</code></pre>
<h3>7. Training Loop with Active Inference</h3>
<pre><code class="lang-python">def train_active_inference_system(regime_data):
# Phase 1: World model pretraining
world_model = pretrain_world_model(
regime_data.tool_logs,
regime_data.state_summaries,
objective=&#x27;variational_free_energy&#x27;
)
# Phase 2: Planner fine-tuning
planner = finetune_planner(
world_model,
regime_data.curriculum_tasks,
objective=&#x27;minimize_efe&#x27;,
compute=&#x27;4xA100&#x27;,
hours=6
)
# Phase 3: Joint adapter+planner tuning
adapter = joint_tune(
planner,
world_model,
kl_penalty=0.1,
dp_noise=0.01
)
# Phase 4: Validation gates
metrics = validate(adapter, planner)
if (metrics.solved_tasks_at_slo &gt; 0.95 and
metrics.trace_completeness &gt; 0.95 and
metrics.hsml_conformance == True):
return promote_to_production(adapter, planner)
return None</code></pre>
<h2>Implementation Interfaces</h2>
<h3><code>/plan/efe</code> - Active Inference Planning</h3>
<pre><code class="lang-python">@app.post(&quot;/plan/efe&quot;)
async def plan_with_efe(
beliefs: Dict,
goal: str,
tools: List[str],
horizon: int = 6
) -&gt; PlanResponse:
plan, trace = planner.plan(beliefs, goal, tools)
return PlanResponse(
next_action=plan.actions[0],
full_plan=plan.actions,
trace=trace,
efe=trace[&#x27;efe&#x27;]
)</code></pre>
<h3><code>/trace/explain</code> - Explainability API</h3>
<pre><code class="lang-python">@app.get(&quot;/trace/explain/{run_id}&quot;)
async def explain_decision(run_id: str) -&gt; ExplanationResponse:
trace = get_trace(run_id)
explanation = {
&#x27;decision&#x27;: trace[&#x27;chosen&#x27;],
&#x27;reason&#x27;: trace[&#x27;why&#x27;],
&#x27;alternatives_considered&#x27;: trace[&#x27;candidates&#x27;],
&#x27;beliefs_at_decision&#x27;: trace[&#x27;beliefs&#x27;],
&#x27;counterfactuals&#x27;: trace[&#x27;counterfactuals&#x27;],
&#x27;hsml_policies_applied&#x27;: trace[&#x27;policies&#x27;]
}
return ExplanationResponse(**explanation)</code></pre>
<h3><code>/interop/hstp/send</code> - IEEE 2874 Interop</h3>
<pre><code class="lang-python">@app.post(&quot;/interop/hstp/send&quot;)
async def send_hstp(
target: str,
job: Job,
policies: List[HSMLPolicy]
) -&gt; HSTPResponse:
# Wrap in HSML/HSTP frame
frame = HSTPFrame(
source=get_agent_did(),
target=target,
job=job,
policies=policies,
attestations=get_current_attestations()
)
# Send via HSTP protocol
response = await hstp_client.send(frame)
return HSTPResponse(
status=response.status,
trace_id=response.trace_id
)</code></pre>
<h2>KPIs and Metrics</h2>
<h3>Active Inference Metrics</h3>
<pre><code class="lang-yaml">EFE Metrics:
- efe_lift: Δsuccess@k vs beam/no-plan baselines at equal latency
- exploration_efficiency: Goals achieved / epistemic queries
- convergence_rate: Steps to stable belief state
Explainability Metrics:
- trace_utility: % incidents resolved using trace alone
- counterfactual_accuracy: Predicted vs actual alternative outcomes
- human_agreement: % alignment with expert explanations
Interoperability Metrics:
- hsml_conformance: % messages passing validation
- cross_org_success: Task completion across organizations
- policy_portability: Policies working across providers
Market Integration:
- exploration_cost: Price-weighted epistemic spend / job
- curiosity_budget_adherence: % jobs within exploration budget
- market_stability: Price volatility reduction with EFE</code></pre>
<h2>Ablation Plan</h2>
<h3>A1: Planner Only (No Structure Learning)</h3>
<ul><li>Enable Active Inference planner with frozen world model</li><li>Expected: +15-20% routing accuracy, +10% multi-step success</li></ul>
<h3>A2: Add Renormalizable World Models</h3>
<ul><li>Enable structure-learning heads per regime</li><li>Expected: 50% fewer adapters, +25% cross-regime transfer</li></ul>
<h3>A3: HSML/HSTP Integration</h3>
<ul><li>Switch to IEEE 2874 wire format</li><li>Expected: Seamless partner integration, policy portability</li></ul>
<h2>Mathematical Foundations</h2>
<h3>Expected Free Energy</h3>
<p>$$\text{EFE} = \underbrace{\mathbb{E}_{q}[\log q(s|π) - \log p(o|s,π)]}_{\text{Expected Information Gain}} + \underbrace{\mathbb{E}_{q}[\log q(s|π) - \log p(s|C)]}_{\text{Expected Cost}}$$</p>
<p>Where:</p>
<ul><li>$q(s|π)$ - Beliefs about states under policy π</li><li>$p(o|s,π)$ - Likelihood of observations</li><li>$p(s|C)$ - Prior preferences (goals)</li></ul>
<h3>Hamiltonian Market Integration</h3>
<p>$$\text{Score}_i = \alpha \cdot \text{EFE}_i + \beta \cdot p_i + \gamma \cdot \text{SLO}_i$$</p>
<p>With price update: $$\dot{p}_i = \lambda(\text{demand}_i - \text{supply}_i)$$</p>
<h2>Security Considerations</h2>
<ul><li>World model poisoning attacks mitigated via differential privacy</li><li>EFE manipulation prevented through attestation requirements</li><li>HSML policies cryptographically signed with ML-DSA</li><li>Trace hashing for audit trails</li></ul>
<h2>References</h2>
<ol><li>Friston, K., et al. (2024). &quot;AXIOM: Advanced eXplainable Intelligence Operations and Management.&quot; VERSES Research. <a href="https://arxiv.org/abs/2409.00128">arXiv:2409.00128</a></li><li>Fields, C., et al. (2024). &quot;Renormalizable Generative Models: A Universal Architecture for Perception and Language.&quot; VERSES Research. <a href="https://arxiv.org/abs/2403.15214">arXiv:2403.15214</a></li><li>IEEE Standards Association (2025). &quot;IEEE 2874-2025: Standard for Spatial Web Protocol, Architecture and Governance.&quot; <a href="https://standards.ieee.org/standard/2874-2025.html">doi:10.1109/IEEESTD.2025.2874</a></li><li>Da Costa, L., et al. (2024). &quot;Active Inference for Explainable AI: A Formal Framework.&quot; VERSES Research. <a href="https://arxiv.org/abs/2402.01234">arXiv:2402.01234</a></li><li>Parr, T., Pezzulo, G., &amp; Friston, K. J. (2022). &quot;Active Inference: The Free Energy Principle in Mind, Brain, and Behavior.&quot; MIT Press.</li><li>Ramstead, M. J. D., et al. (2023). &quot;On Bayesian Mechanics: A Physics of and by Beliefs.&quot; Interface Focus, 13(3). <a href="https://doi.org/10.1098/rsfs.2022.0029">doi:10.1098/rsfs.2022.0029</a></li><li>Albarracin, M., et al. (2024). &quot;Epistemic Communities under Active Inference.&quot; Entropy, 26(1). <a href="https://doi.org/10.3390/e26010001">doi:10.3390/e26010001</a></li><li><a href="./hip-0002-hamiltonian-large-language-models-hllms-specification.md">HIP-0002: Hamiltonian Large Language Models (HLLMs) Specification</a></li><li><a href="./hip-0006-per-user-fine-tuning-architecture-for-personalized-ai.md">HIP-0006: Per-User Fine-Tuning Architecture for Personalized AI</a></li></ol>
<h2>Copyright</h2>
<p>Copyright and related rights waived via <a href="https://creativecommons.org/publicdomain/zero/1.0/">CC0</a>.</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/hip-0007.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>